118 results about "Relevance feedback" patented technology

A system and method (and signal medium) for interactively displaying information, include a ticker display for displaying items having different views, a tracker for tracking a user's eye movements while observing a first view of information on the ticker display, and a mechanism, based on an output form the tracker, for determining whether a current view has relevance to the user.

A methodology of highly interactive intra-object relevance feedback is used to retrieve multimedia data from a database. The query object could consist of one or more images, images derived from video, a video sequence, or an audio clip. The query is adjusted using the information fed-back by the user about the relevance of previously extracted part(s) from the object itself, such that the adjusted query is a better approximation to the user's perception. The information fed-back by the user during intra-query modification is used for intra-object learning of the user's perception. The refined query is subsequently used for inter-object relevance feedback where data is retrieved from the database based on parameters learnt by intra-query object feedback mechanism, and the user provides feedback by ranking the retrieved objects in order of their relevance to him or her. In the system according to the invention, inter-object learning of user's perception is expedited by utilizing the learnt parameters in the intra-object relevance feedback. Furthermore, the methodology of the invention allows for building refined queries based on part(s) or sub-sequence(s) of the query object rather than the entire object itself, thereby reducing the number of irrelevant objects, retrieved from the database. The methodology allows synthesis and modification of the input query object itself in the event a query object is not directly available, and, also to learn the user's perception.

An image retrieval system performs both keyword-based and content-based image retrieval. A user interface allows a user to specify queries using a combination of keywords and examples images. Depending on the input query, the image retrieval system finds images with keywords that match the keywords in the query and / or images with similar low-level features, such as color, texture, and shape. The system ranks the images and returns them to the user. The user interface allows the user to identify images that are more relevant to the query, as well as images that are less or not relevant to the query. The user may alternatively elect to refine the search by selecting one example image from the result set and submitting its low-level features in a new query. The image retrieval system monitors the user feedback and uses it to refine any search efforts and to train itself for future search queries. In the described implementation, the image retrieval system seamlessly integrates feature-based relevance feedback and semantic-based relevance feedback.

A system and method are provided that use explicitly and implicitly derived models of user information needs and content and presentation preferences together with relevancy feedback to expand a user's original query to the most related terms in a corpus and / or to allow the user to provide interactive feedback to enhance the relevance of selected news stories and display profile of the selected news stories. By personalizing both the selection of stories and the form in which they are delivered, users are provided with tailored broadcast news.

A multimedia object retrieval and annotation system integrates an annotation process with object retrieval and relevance feedback processes. The annotation process annotates multimedia objects, such as digital images, with semantically relevant keywords. The annotation process is performed in background, hidden from the user, as the user conducts normal searches. The annotation process is “semi-automatic” in that it utilizes both keyword-based information retrieval and content-based image retrieval techniques to automatically search for multimedia objects, and then encourages users to provide feedback on the retrieved objects. The user identifies objects as either relevant or irrelevant to the query keywords and based on this feedback, the system automatically annotates the objects with semantically relevant keywords and / or updates associations between the keywords and objects. As the retrieval-feedback-annotation cycle is repeated, the annotation coverage and accuracy of future searches continues to improve.

A method and apparatus for dynamically adjusting the user interface of a search engine in order to effectively communicate the improved relevancy achieved through real-time implicit re-ranking of search results is described. Real-time implicit re-ranking occurs without delay after every user action as the search is being conducted, so finding methods of immediately altering the search page without disrupting the user experience is important. Graphical icons next to search results are employed to enable generating and removing re-ranked results, referred to as “recommended” search results. Clusters based on the real-time user model are also displayed to facilitate query reformulations. Sponsored links are selected using the real-time user model along with a combination of RPC and CTR information and are displayed in a manner similar to the organic results, or used to replace the initial sponsored links altogether.

An adaptive temperature dependent clock feedback control system and method for adaptively varying a frequency of a clock signal to a circuit such that the circuit may operate at a maximum safe operating clock frequency based on a circuit junction temperature. The clock control system includes a thermal sensor and a temperature dependent dynamic overclock generator circuit. The thermal sensor detects a junction temperature corresponding to at least a portion of the circuit on a semiconductor die. The temperature dependent dynamic overclock generator circuit varies the clock signal based on the semiconductor die junction temperature, such that the clock signal operates at the highest possible operating frequency associated with the detected junction temperature. The frequency of the clock signal is increased from a first frequency to at least a second frequency and a third frequency if the junction temperature is below a lower junction temperature threshold.

This invention discloses a method for media-crossing searches based on content relativity, which applies the typical relativity analysis to analyze the content characters of different mode media data, maps a visual sense character vector of image data and an auditory character vector of audio data in a low dimension isomorphic sub-space simultaneously by a sub-space mapping algorithm, measures the relativities among different mode data based on a general distance function and modifies the topological structure of a multi-mode data set in the sub-space to increase the cross media search efficiency effectively.

A multimedia information retrieval system includes a storage and an electronic processing device. The latter is configured to perform a process including: computing values of a pairwise similarity measure quantifying pairwise similarity of documents of a multimedia reference repository; storing the computed values in the storage; performing an initial information retrieval process respective to the multimedia reference repository to return a set of initial repository documents; and identifying a set of top ranked documents of the multimedia reference repository based at least on the stored computed values pertaining to the set of initial repository documents.

There is provided a computer-executable method for ordering documents for review in response to an electronic discovery request. The method involves determining, by a processor, one or more metrics of the documents, the one or more metrics indicating at least one of privilege and responsiveness of the documents. The method also involves estimating a relevancy of the documents according to the metrics. The method also involves ordering the documents from most relevant to least relevant according to the relevancy, receiving relevance feedback from a first document reviewer, updating the order according to the relevance feedback, and sending a first subset of the updated ordered documents to a second document reviewer for review.

A method for retrieving information from a computer system including a user terminal and a storage area, includes retrieving first information from the storage area using a first search query, the first search query having a first element and a first weight that is associated with the first element. The first search query has been formulated to retrieve target information. The first information includes at least a first data block. Second information is retrieved from the storage area using a second search query. The second search query has the first element, and a second weight that is associated with the first element. The second search query is derived from a relevance feedback provided on the first data block of the first information. An end-search criterion is provided to the user terminal. The end-search criterion provides information as to whether or not to end a first retrieval procedure for the target information. The first retrieval procedure being associated with a search query set, the search query set including a plurality of search queries, each having the first element.

The invention relates to a three-dimensional model retrieval method based on multi-feature relevance feedback, comprising the following steps: a server processes each three-dimensional model in a three-dimensional model database to obtain color view arrays; three-dimensional model features are acquired and synthesized to generate a feature database; features of a two-dimensional sketch offered by a computer client are calculated and matched with feathers in the feature database, the distance between the two-dimensional sketch and each three-dimensional model is calculated, the three-dimensional models as a retrieval result are sorted and outputted according to the distance values; the client labels each retrieval result with 'relevance' or 'irrelevance', returns labeled three-dimensional model information to the server, the server learns the information, classifies the three-dimensional database by SVM fusion method, sorts and outputs the three-dimensional models as a retrieval result; the above steps are repeated until a satisfactory three-dimensional model retrieval result is outputted to a user.

The invention discloses a method for generating suggested keywords of sponsored search advertisement based on user feedback, which develops semantic relatedness between words and establishes a learning machine to evaluate the relatedness of word pairs by utilizing the feedback information of users on the relatedness of a small quantity of word pairs so as to select words which has high relatednesswith seed keywords describing advertiser products or service concepts as the suggested keywords to be recommended to advertiser users, wherein an active learning method is used for selecting a word pair sample with maximal information quantity to evaluate user relatedness so as to enhance the efficiency and the precision of generating related suggested keywords. The invention can effectively generate hundreds of to thousands of related words to be used as the suggested keywords to be recommended to the advertiser users corresponding to each seed keyword; in addition, the advertiser users carry out sponsored search bidding for the suggested keywords, thus the related click rate of the sponsored advertisement can be effectively enhanced, and the advertisement benefit is increased.

A real time streaming video capture, delivery, and alert system may capture a streaming video of a live event and deliver it into a computer network as the live event is being captured. The system may include a camera, a network interface, a source operator interface configured to receive alerts, and a processing system. The system may issue an alert when the live event is currently of interest.A streaming video search engine may allow prospective viewers to locate at least one streaming video that is currently of interest from among several streaming videos. The engine may include a network interface configured to receive source alerts from real time streaming video capture, delivery, and alert systems, a memory system, a processing system, a searching system, and a viewer interface.

In document retrieval having the relevance feedback function to modify a searching profile for retrieval on the basis of a user's evaluation to evaluate a search result as pertinent or impertinent, recommencement of the relevance feedback returned to a desired time is permitted. An evaluation inputted by a user, a searching profile modified by the evaluation and a search result based on the searching profile are all saved while making the correspondence between them. When a request for restoration of searching profile is made, a searching profile corresponding to an evaluation designated by the user is restored.

The invention relates to a search engine technology based on relevance feedback and clustering. By simultaneously utilizing user relevance feedback information and relavancy sequencing to direct the clustering of retrieval results, the invention ensures that the final partitioning of the retrieval results meet user query requirements; and in a clustering process, a large amount of documents and repeated webpage which are irrelevant to a user are removed, the clustering speed is improved and the retrieval results are optimized at the same time. In the clustering process, a clustering center is not modified by a clustering cluster irrelevant to the user, thereby result documents relevant to the user are ensured not to be lost when noise is introduced in irrelevant document clustering.

A method is provided, including: detecting interactions by a plurality of users with a plurality of content items, each content item having an associated content item vector; for a given user, identifying interactions occurring during a current time period, including identifying positive interactions with a first set of the content items, and negative interactions with a second set of the content items; processing a first set of the content item vectors that are associated with the first set of the content items to determine a positive interaction vector; processing a second set of the content item vectors that are associated to the second set of the content items to determine a negative interaction vector; for the given user, generating a current user profile vector for the current time period, using the positive interaction vector, the negative interaction vector, and a prior user profile vector for a prior time period.

The invention discloses an image retrieval method based on hierarchical features and genetic programming relevance feedback. The method includes the steps: (1), performing adaptive segmentation for a retrieval image submitted by a user to obtain segmented regions; (2) extracting global features of the retrieval image, and extracting local low-level features of the segmented regions; (3) computing an optimal region, corresponding to each segmented region, of each image in a standard image library; (4) constructing a global-optimal region similarity matched pattern; (5) by attaching average weight to various similarities in the similarity matched pattern, computing similarity of the retrieval image to each image in the standard image library, sorting according to the similarity to obtain an initial retrieval result, and returning a plurality of previous images most similar to the retrieval image of the user to a user side; and (6) enabling the user to participate in feedback until satisfactory images are retrieved. The method can be closer to retrieval intention of the user, and is capable of extracting content features of the image effectively and completing retrieval quickly and effectively.

The invention belongs to the technical field of image processing and particularly provides a semantic propagation and mixed multi-instance learning-based Web image retrieval method. Web image retrieval is performed by combining visual characteristics of images with text information. The method comprises the steps of representing the images as BoW models first, then clustering the images according to visual similarity and text similarity, and propagating semantic characteristics of the images into visual eigenvectors of the images through universal visual vocabularies in a text class; and in a related feedback stage, introducing a mixed multi-instance learning algorithm, thereby solving the small sample problem in an actual retrieval process. Compared with a conventional CBIR (Content Based Image Retrieval) frame, the retrieval method has the advantages that the semantic characteristics of the images are propagated to the visual characteristics by utilizing the text information of the internet images in a cross-modal mode, and semi-supervised learning is introduced in related feedback based on multi-instance learning to cope with the small sample problem, so that a semantic gap can be effectively reduced and the Web image retrieval performance can be improved.

Provided are methods of performing a database search using relevance feedback, in which a ranking scheme is applied to a database system for efficient database search, and a recording medium having a program recorded thereon for executing the same. The method includes receiving relevance feedback for a first search result, deriving a relevance function based on the received relevance feedback, and applying the first search result to the relevance function and providing a second search result ordered according to a relevance level. Accordingly, an accurate relevance function can be derived from a small amount of feedback by using relevance feedback and a ranking scheme, such that an efficient database search can be achieved without a user reviewing all search results to obtain a desired result.

Methods, computer products, and systems for selecting advertisements in response to an internet query are provided. The method provides for receiving an internet query that includes query terms, retrieving and then ranking a first set of advertisements in response to the internet query using a query likelihood model. The method then selects sampling words using pseudo-relevance feedback and translation models, the internet query, and the first set of ad materials obtained using the query likelihood model. The sampling words are chosen from a distribution of words from the words in the first set of ad materials, and the pseudo-relevance feedback model is used to select a word (w) in the distribution of words based on a probability that word w generates query term q(p(q|w)). The translation model is used to calculate the probability p(q|w) based on a translation probability that w translates into q(t(q|w)). The method also includes retrieving and ranking a second set of ad materials using an expanded query formed by adding the selected sampling words to the original internet query. The second set of ad materials is then presented to the user. The use of translation models enhances the topicality of the results because the distribution words selected are related to the terms in the original query as indicated by their translation probabilities.

Speculative query expansion is a way to increase the effectiveness of relevance feedback. Instead of picking the best expansion query beforehand, multiple queries are executed and the best expansion query is selected afterward, but with no additional effort (or information) required from the user. From the best expansion query, search results and expanded queries more pertinent to the user can therefore be provided.

The invention relates to a remote sensing image retrieval method based on improved support vector machine relevance feedback. The method comprises the following steps of: establishing a remote sensing image database, and selecting an image meeting a retrieval object from the remote sensing image database as a query image; performing remote sensing image feature extraction on the remote sensing image database to obtain feature vectors; calculating Euclidean distances between the feature vectors of images and the query image in the remote sensing image database based on the feature vectors, andreturning a given number of remote sensing images sequentially from short distances to long distances as initial retrieval results; and performing relevance feedback, namely evaluating the initial retrieval results, and finishing retrieval if the initial retrieval results are satisfactory. By the method, the problems of the conventional support-vector-machine-based relevance feedback algorithm about retrieval result sequencing, particularly the problems about classification and identification in a high-dimensional feature space are well solved, and remote sensing image retrieval accuracy and retrieval result sequencing rationality can be effectively improved; and the method can be used for a plurality of application fields related to remote sensing image retrieval.

The invention provides a pseudo-correlation feedback model information retrieval method and system based on semantic similarity. The method comprises the following steps: carrying out a first query from a target document set according to a query keyword to extract a pseudo-related document set, carrying out query expansion by adopting a Rochio algorithm, carrying out query expansion according to the semantic similarity of sentences, fusing the results of the two query expansion methods, and carrying out a second query to realize final information retrieval. According to the invention, when theextended lexical item is selected; the importance degree relationship between the query lexical item and the extension word in the traditional method can be highlighted; the semantic correlation of the sentences where the lexical items are located is combined; the condition that lexical items are associated when sentence semantics are similar in reality is met; According to the method and the device, the conditions that the semantics are related even if the lexical items are different are represented, so that the query words have better regional indexing in a multi-semantic environment, a large amount of useless and irrelevant information can be removed from mass information, more accurate candidate words can be obtained, and the precision of expanded query and final retrieval can be improved.

The invention discloses a search method for relevance feedback images based on an ant colony algorithm and a probability hypergraph, which comprises a training stage and a search stage. The training stage comprises the following steps of extracting low-level features of images, studying a dictionary and performing the high level representation of the images in a library image. The search stage comprises the following steps of extracting low-level features of sample images; performing the high level representation of the sample images; constructing an affinity matrix; initializing or updating a pheromone matrix; labeling positive correlation images and negative collation images for search results of all sample images in the image library; calculating a semantic pheromone matrix; calculating an affinity enhancing probability; enhancing the affinity matrix by using the ant colony algorithm; constructing a hypergraph; and returning the search result and finishing search, or updating the pheromone matrix for the next search. According to the method, an efficient and accurate image search technology is provided for image search and a higher use value is realized.

An interactive system provides for increasing retrieval performance of images depicting text by allowing users to provide relevance feedback on words contained in the images. The system includes a user interface through which the user queries the system with query terms for images contained in the system. Word image suggestions are displayed to the user through the user interface, where each word image suggestion contains the same or slightly variant text as recognized from the word image by the system than the particular query terms. Word image suggestions can be included in the system by the user to increase system recall of images for the one or more query terms and can be excluded from the system by the user to increase precision of image retrieval results for particular query terms.

The invention, which belongs to the technical field of car networking communinication, relates to an adaptive rate control method based on mobility and DSRC / WAVE network relevance feedback. The method comprises establishment of a traffic flow density prediction module, a t+1 time communication interference calculation module, an SINR calculation module, a t+1 time available link bandwidth calculation module, a channel congestion cost calculating module and an adaptive message generation rate calculation module. A traffic flow density value at a next time is predicted; according to the density value of the next time, a transmitting power, and a rate, an interference module of a communication process is established, a signal to noise ratio is calculated, and an available link bandwidth of a node at the next time is predicted; on the basis of mismatching of a transmission rate and mismatching of a transmission queue length, a channel congestion cost module is established, so that a message generation rate at the next time is adjusted adaptively. According to the method, adaptive rate adjustment is carried out in advance by using the prediction technology, so that the channel congestion is avoided; and the low communication delay and the high data packet transmission rate are guaranteed with the low calculation time and cost.

In a retrieval application, a document relevance scoring function comprises a weighted combination of scoring components including at least one of a pseudo-relevance scoring component and a cross-media relevance scoring component. Weights of the document relevance scoring function are optimized to generate a trained document relevance scoring function. The optimizing is respective to a set of training documents including at least some multimedia training documents and a set of training queries and corresponding training document relevance annotations. A retrieval operation is performed for an input query respective to a database using the trained document relevance scoring function to retrieve one or more documents from the database.

A method and a system for the creation of agents to be used for recommending media content to a user (207). The agent comprises a profile of media content and can further comprise an algorithm for recommending media (201) on a media system (208). The media system (208) can be a VCR, a TV, a set-top box, a DVD player, a radio or a personal computer. The method includes the steps of validating an agent in an off-line system (210), transferring agents forth and back between the off-line system (210) and an on-line system (203). The step of validating includes the steps of composing a test set of historical content, estimating scores of an agent in the test set, determine average difference between agent scores and historical relevance feedback, determining performance of an agent using average difference of all agents over the test set and reliability of historical relevance feedback. The method further includes the steps of nominating agents in the on-line system (203), selecting agents and copying agents forth and back between the on-line system (203) and the off-line system (210); importing, generating, training, ranking, nominating and deleting agents in the off-line system (210).