Abstract: Aspects of the present invention include a method, system and computer program product for preventing certain sensitive private or personal information of a user from being recorded or stored and/or uploaded by a third party input method editor while the user is entering information into a computer that is part of a network. The method includes a processor creating a model containing privacy information about a user of a computer; extracting the privacy information from the model; analyzing the information entered into the computer by the user; determining that the user has entered any of the privacy information into the computer; and if the processor has determined that the user has entered any of the privacy information into the computer, preventing any recording, storing or uploading of the privacy information.

Abstract: A method for identifying popular segments of a network video comprising: receiving video player operation information for a plurality of video players operated by users accessing the network video; evaluating a popularity measure for one or more segments of the network-video using the received operation information so as to identify popular segments of the network video.

Abstract: Embodiments of the present disclosure relate to non-sequential document comparison. A first plurality of segments in a first document and a second plurality of segments in a second document are obtained. In response to a first segment from the first plurality of segments being associated with a second segment from the second plurality of segments, a third segment from the first plurality of segments is associated with a fourth segment from the second plurality of segments.

Abstract: The methods, systems, and computer program products described herein provide ways to generate an informative training corpus of samples for use in machine training a high-quality sentiment analysis computer model. In some aspects, a method is disclosed including receiving a plurality of training samples, extracting semantic and sentiment elements of one or more of the training samples, generalizing the semantic and sentiment elements of the one or more of the training samples, generating an informative ranking score for one or more of the training samples based on the generalized semantic and sentiment elements, selecting informative training samples from the plurality of training samples based at least in part on the generated informative ranking scores, and adding the selected informative training samples to an informative training corpus.

Abstract: A method for categorizing a use scenario of a product is disclosed. The method includes extracting, from a text describing the use scenario of the product, at least one feature tuple capable of characterizing the use scenario and performing a latent semantic association analysis on the at least one feature tuple to obtain a latent topic sequence for the use scenario. Further, the method includes determining a product scenario category to which the use scenario belongs according to the latent topic sequence for the use scenario. Additionally, a corresponding apparatus is also disclosed.

Abstract: An interactive shopping advisor receives a natural language query for a product search, generates an initial product recommendation from the natural language query, receives a natural language preference parameter for refining the product search, maps the natural language preference parameter to a product attribute value for the product search, identifies an adjustment orientation of the product attribute value from the natural language preference parameter, and applies the adjustment orientation to the natural language query to provide a refined product recommendation for the product search.

Abstract: A method and apparatus for generating a document structure. The method includes the steps of: aligning various parts in the first version and the second version in at least one pair of historical versions among a plurality of historical versions of a document; dividing the first version and the second version into a plurality of blocks on the basis of a Levenshtein distance between the aligned parts; evaluating a level of the block in the document structure on the basis of text features of the block among the plurality of blocks; and generating the document structure on the basis of a position of the block according to an evaluation result. An apparatus for generating a document structure is also provided. According to the present invention, document structures can be more conveniently and rapidly generated.

Abstract: A method for identifying popular segments of a network video comprising: receiving video player operation information for a plurality of video players operated by users accessing the network video; evaluating a popularity measure for one or more segments of the network-video using the received operation information so as to identify popular segments of the network video.

Abstract: Provided is a method applied to a system including a plurality of sensors, a proxy, and a server. The method includes: measuring objects by the plurality of sensors to obtain first measurement values; computing a correlation among the first measurement values by the server based on the first measurement values; computing an actual measurement value of a second measurement value by the proxy based on the first measurement values and a given function; verifying the plurality of sensors by setting one or more sensors as verification target sensors in turn by the server at predetermined timing; computing a predicted value of the second measurement value by the server based on the correlation and the first measurement values obtained from the other sensors; and outputting the predicted value of the second measurement value instead of the actual measurement value thereof at least during the verification of the verification target sensors.

Abstract: An authentication method can include, a random expression prompt, recording of the user's expression actions, and an authentication result. This is completed using a terminal device configured to display authentication information, record the user's inputted information, and send an authentication result. The terminal device may be further configured to package an authentication result, and send it to an authentication server. Subsequent actions of the user are allowed or denied based on the authentication result.

Abstract: A method, system, and computer program product, include receiving a request for registration from a service provider, the request for registration comprising characteristic information of a service call to be initiated, determining whether the service receiver has authorized the request for registration, and upon the service receiver having authorized the request for registration, registering the characteristic information of the service call for the service receiver to enable the identification of the service call.

Abstract: Provided is a system for searching for a web document. The system includes a receiver configured to receive a user's search request. A search engine is configured to search for a web document related to the search request based on a web document index, and to determine a move path for accessing the web document based on a move path index of the web document. A sender is configured to send the move path for accessing the web document to the user.

Abstract: Embodiments of the present invention relate to a positioning method and a system thereof, an encoded label generating method and a system thereof. The present invention sets forth a solution of using encoded label to determine coordinate, so as to perform positioning. The positioning method, includes: acquiring a normalized map and a first identification code for identifying the map; acquiring, by scanning a first encoded label, a second identification code and a first coordinate indicated by the first encoded label; and determining a first location in the map corresponding to the first coordinate in response to the second identification code matching with the first identification code.

Abstract: Embodiments of the present disclosure include methods and systems of building an IP multimedia session without the use of a central server and switching IP multimedia session among devices. The method of building an IP multimedia session includes receiving a registering request from a plurality of IP multimedia session participant devices, electing a service device from the plurality of participant devices, and building IP multimedia session among the plurality of participant devices by using the elected service device.

Abstract: Methods and systems for handling queries include extracting keywords related to a first query from one or more information sources. The keywords are classified according to a plurality of categories defined by a query schema. A plurality of the keywords are combined into a second query according to the query schema. The second query is executed to generate one or more results.

Abstract: Technical solutions are described for displaying product labels for a product to a user, where the product is associated with a first category. An example method includes analyzing product reviews posted by the user for a set of other products, which includes a second product from a second category, distinct from the first category. The method also includes identifying a set of product labels personalized for the user based on the analysis of the product reviews for other products, including the second product from the second category. The method also includes obtaining a plurality of product labels associated with the product that is being displayed to the user, based on product labels common to the set of product labels for the user and the plurality of product labels of the product. The method also includes displaying the subset of product labels as part of the information of the product.

Abstract: In an approach for determining an available parking space, a computer accesses a streaming video. The computer identifies a vehicle and a corresponding identification characteristic within the accessed streaming video. The computer retrieves historical data associated with the identified identification characteristic, wherein the historical data includes previous parking locations. The computer determines a preferred parking space within the retrieved historical data associated with the identified identification characteristic. The computer determines whether the identified preferred parking space is available based on a parking database.

Abstract: Technical solutions are described for displaying product labels for a product to a user, where the product is associated with a first category. An example method includes analyzing product reviews posted by the user for a set of other products, which includes a second product from a second category, distinct from the first category. The method also includes identifying a set of product labels personalized for the user based on the analysis of the product reviews for other products, including the second product from the second category. The method also includes obtaining a plurality of product labels associated with the product that is being displayed to the user, based on product labels common to the set of product labels for the user and the plurality of product labels of the product. The method also includes displaying the subset of product labels as part of the information of the product.

Abstract: In an approach for visual liveness detection, a video-audio signal related to a speaker speaking a text is obtained. The video-audio signal is split into a video signal which records images of the speaker and an audio signal which records a speech spoken by the speaker. Then a first sequence indicating visual mouth openness is obtained from the video signal, and a second sequence indicating acoustic mouth openness is obtained based on the text and the audio signal. Synchrony between the first and second sequences is measured, and the liveness of the speaker is determined based on the synchrony.

Abstract: Method and system for preserving confidential information in a sensitive document. The method includes: obtaining a first entity and a second entity from a document, building a first context feature from the first entity and a second context feature from the second entity based on a semantic analysis, determining that the extent of similarity between the first and second context features exceeds a predefined threshold, and replacing the first entity with the second entity in response to a similarity determination. The present invention also provides a computing system for preserving confidential information in a sensitive document.