92 results about "Information overload" patented technology

In cognitive radar information networks (CRINs) human-like cognitive abilities of attention and intelligence are built into radar systems and radar information networks (RINS) to assist operators with information overload. A CRIN comprises a plurality of radar sensing nodes monitoring an environment, a repository or memory, and a cognitive radar controller. Each radar sensing node includes a radio frequency transmitter, a transmitting antenna, and a receiver and receiving antenna. The receiver includes a digital radar processor for generating receiver information from the received echoes about the environment. The repository is configured for receiving and storing the receiver information generated by the digital radar processor. The cognitive controller is configured to automatically focus the system's attention on a region of interest within the surveillance volume in response to an attention request, by selecting the transmitter's waveform, selecting the receiver's processing mode, and controlling the transmitter's antenna. The cognitive controller learns from the environment by exploiting the repository's historical receiver information and further learns from the consequences of its past decision.

The invention relates to a customized screening system and a customized screening method for microblog. The customized screening system for the microblog comprises a background module and an interactive module, wherein the background module is used for acquiring data, analyzing the data, performing local storage, establishing an index and providing a search function; and the interactive module performs information interaction with the background module and provides a WEB interface interacted with the background module. The system is a solution for solving the problem of information overloading, namely, a type of information which a user concerns is targetedly screened out of huge microblog data, a great deal of non-concerned information is filtered for the user, and the data can be locally stored so that the user can use the data for a long time conveniently; the safety of the system is enhanced by a verification mechanism; the working logic of the whole system is clear and smooth; the coupling degree among modules of the system is reduced; and each module consists of a plurality of modules so as to facilitate the functional expansion of each module.

The invention discloses a personalized recommendation method and system based on a probability model and user behavior analysis. The method includes the steps that article information and article attribute information are extracted, and operation behaviors of users on articles are extracted; interest points are obtained according to the article attribute information and the operation behaviors of the users on the articles; user interest similarity is obtained according to the operation behaviors of the users on the articles, and similar users are obtained; a decay factor is obtained according to the operation behaviors of the users on the articles based on the time dimension, and a user model is set up; interest characteristic information, at all dimensions, of the users is obtained according to the user model; after filtering, a recommendation algorithm is adopted to generate results to be recommended, and algorithm fusion is conducted to obtain personalized recommendation results of the users. After original data is preprocessed, the user model is set up, the interest points of the users and essential information acquisition requirements are depicted accurately to provide accurate personalized recommendation, and therefore the problems of information overload and long-tail articles in the network are solved.

A method and system for generating answers to questions based on electronic data summary which is itself derived on context and semantics of a corpus of authoritative documents and its subsequent usage is disclosed. The method and system provides for generating a taxonomy of concepts, assigning unique-identifiers and weights to the taxonomy concepts using a given corpus of electronic data, using the taxonomy to identify the semantics of the document to be summarized, generating an ontology from a summarized authoritative text, having the ontology generation and the summary generation in a feedback loop, selecting text from a given document based on the weights of unique-identifiers in the taxonomy/ontology, sentences as a summary and pruning of the list based upon an entropy threshold, and the presence of a probability distribution, publishing of the summary in a known format on server or any other software/hardware platform with or without monetization for consumption, usage of the summary to generate answers which can be configured using an ontology and thus prevent denial of information/information overload.

A driving support apparatus includes an output unit installed in a steering wheel that outputs steer information about a rotation operation of the steering wheel to the driver through the output unit. By providing the driver with steer information from the output unit in the steering wheel, the driver may recognize the contents of the output of the steer information. Further, since the steer information has a high priority for the driver due to its direct relevance to movement and a travel direction of the vehicle, providing such high priority steer information in an easily-recognizable manner improves driver awareness or readiness to recognize lower-priority information. Thus, information overload by the driver caused by information from various driving support techniques is prevented.

A visualization of a set of related data items is accomplished by ranking a plurality of secondary data items with respect to their relationship to a principal data item. The set of related data items may be stored in any form, including, for example, as a relational database, an object database, or an XML document. The related items display names can be formatted and ranked according to the properties of the item, so as to avoid duplication and information overload for the user. The ranked data can be displayed along curved segments in a graphical chart, so as to allow convenient visualization of the data and the data's relationship to the principal item that may be prominently displayed at the center of the chart.

The invention relates to a grouping processing method and device of contact persons. The grouping processing method comprises the following steps: receiving media information sent by the contact persons; extracting key characteristics in the media information; according to corresponding relation between the pre-stored key characteristics and the attributes of the contact persons, searching whether the key characteristics in the media information correspond to the attributes of the contact persons or not; if so, dividing the contact persons into groups corresponding to the attributes according to the searched attributes of the contact persons. According to the grouping processing method and device, the contact persons in address books of various communication tools or communication applications can be automatically and accurately grouped, and when a user utilizes the communication tools or applications to group sending or sharing of information, contact persons in a target group can be accurately selected according to the divided groups, so that the problems of mistaken storage of information, information overload and flow waste of non-target contact persons are avoided.

The present invention provides significantly improved accessibility of website content on mobile and tablet devices with an emphasis on preserving the original intent of the content author/designer by inferring the characteristics of navigability, content organization and chunking and then adapting the original content for multiple end user device profiles using a rule based techniques. Aspects of the present invention address issues with information searching, navigation constraints of the devices, the content organization, information clutter and information overload on web pages and adapting the content to leverage device specific features by generating extensible user interface widget code.

The invention discloses a text topic analysis technology based short text recommendation method. Information forwarded or published by a user is subjected to topic analysis by utilizing a text topic model to obtain topic preferences of the user, and information meeting the user preferences is recommended from large amounts of unread information, so that the information overloading problem of a system is better solved. Based on a biterm topic model (BTM) and a short text based aggregation method, a new short text topic analysis-oriented topic model, namely, a user-based biterm topic model (UBTM), is proposed; and an experiment in a real data set from microblog shows that the UBTM can obtain a topic with higher quality in comparison with a conventional short text topic analysis method. A UBTM based short text recommendation experiment also shows that the short text recommendation method proposed by the invention has a better recommendation effect.

The invention relates to a text message recommendation method, a server, a browser and a system. The method includes that when a user visits a webpage of the browser, a background server obtains corresponding keywords from a text index pool according to an access request sent by the browser; a recommendation text message list is obtained from a keyword index pool according to the corresponding keywords; the recommendation text message list is embedded into a current webpage to return to the browser to be displayed to the user, the user can click the keywords as required to obtain the recommendation text message list, thereby, by means of using the keywords as a bridge for connecting the user and a webpage message text, information overload can be effectively lowered and recommendation efficiency and effectiveness of text messages can be improved under the condition that an original page is not greatly modified, and requirements of the user for rapidly browsing the webpage can be met.

The invention discloses a fiend trend acquisition method and a fiend trend acquisition device capable of solving information overload. The method is characterized by comprising the following steps of: sending a request for viewing friend trends; acquiring friendships and friend privacy conditions of a user; acquiring dynamic data from a database according to the privacy conditions; merging the dynamic data and generating dynamic items; and outputting the dynamic items to the user. The method can acquire dynamic information of friends in a time inverted order, can display more substantial contents in dynamic blocks, and solves the problem of the information overload in the dynamic blocks.

The present invention discloses a generic similarity calculation method based on a heterogeneous information network, comprising steps of: step 1, preprocessing an input data set, to ensure validity of input data; step 2, performing metadata extraction: extracting description information of the input data, and storing the description information in a metadata library; step 3, establishing a heterogeneous information network mode via user interaction, and storing the network mode; step 4, performing similarity calculation by using a metapath-based similarity calculation method of the heterogeneous information network; step 5, performing post similarity processing, to form overall similarity as final output. The generic similarity calculation method and system based on a heterogeneous information network have the beneficial effects: modeling is performed by using the heterogeneous information network, and a generic similarity calculation method is proposed; different types of data sets can be processed; various demands of similarity calculation can be met; a user can designate various calculation methods and post-result processing manners; the degree of freedom of selection is high; the calculation accuracy and efficiency are improved; and the problem of information overload is better solved.

The invention discloses a user interest-based information aggregation method and system. The user interest-based information aggregation system includes a content classification module, a classification content storage module, an information flow generation module, an information aggregation module and a conventional content storage module. The method specifically includes the following steps that: new content generated by users in a social network is acquired, the new content is scored and classified sequentially according to different sources of the new content; the new content and original unread content of the users are sequenced together according to scoring results, and the sequenced content is stored; when new content reading requests of the users are received, new content which are unread and generated before the requests or all the new content is extracted and returned; and the new content and historical content which have been read by the users are merged, and the merged content is pushed. According to the method and system of the invention, content is re-sequenced and displayed according to the correlation degrees of the content and the interests of the users; the interests of the users are analyzed, so that content which the users are interested in can be filtered out for the users; and therefore, the problem of information overloading caused by too large information flow in the social network existing in a traditional information aggregation system can be solved.

In described embodiments, fluid user models are employed for personalized mobile applications, referred to herein as recommender systems. The described embodiments augment media with additional information highly personalized to a user based on a variety of factors with different time sensitivity and include, but are not limited to, a user's general preferences, history, immediate context and attention, and emotional states when the user experiences and/or interacts with the media. Embodiments solve various problems of information overload stemming from both i) the complexity in characterizing the information and ii) its potential relevancy and in understanding and coding the user's needs.

The invention discloses a human face identification and gesture interaction-based television entertainment system. The television entertainment system specifically comprises an image acquisition module, a gesture interaction module, an instruction control module, a human face identification module, a personalized recommendation module, and an interface system. According to the television entertainment system, a gesture interaction function is innovatively added based on a conventional family television entertainment system from a family entertainment product concept, and a one-to-one personalized recommendation service is provided for a current user by utilizing real-time human face identification, so that the problems of poor interactivity and content information overload in a family entertainment product are well solved. Compared with other gesture interaction systems, an interaction system provided by the invention has the advantages of low cost, few changes and the like, the user demands are further met and the user experience effect is improved. In addition, a recommendation system effectively fuses a plurality of recommendation algorithms and accurately provides personalized entertainment information recommendation for the user, and the family entertainment product effect is improved.

A transactional messaging system displaying financial transactions in a user interface structured to resemble an email messaging user interface and/or an instant messaging user interface. The financial transactional messaging system presents and interacts with the financial transactions as email or instant messages, reducing the complexity of tracking, managing and processing transactions while preserving the full capabilities of a transaction processing system. Different transactions scenarios, such as requesting money, sending money, refunding a payment, sending payouts, cash on delivery (COD) and other financial transactions are presented utilizing different transactional process types that are organized under different mailbox folders such as inbox, sent items and deleted items. Inside each folder, the different transactions appears as emails that can be read, processed (pay, accept, release funds, decline, etc.) and/or with graphical elements like icons reflecting the current transaction attributes such as state or the actual activity performed by the transaction on the user's account. Relationships between a user selected transaction and the parties involved in the transaction in the role of payee or payor, are illustrated using email based schemes such as sender/recipient that focus on the selected transaction to avoid confusion due to information overload.

The invention relates to an active information providing method in a wireless application protocol (WAP) environment. The active information providing method takes active service as guidance, takes user information requirements as a driving basis and comprises the steps of calculating and changing user interests and performing multiple-terminal self-adaptive processing and active information pushing of user data. Accurate information can be provided actively and timely according to different users, and the problems of information overload and low information using efficiency existing in the information intensive field are solved. In addition, relevant parameters are timely adjusted according to user feedback, support is provided for personalized information providing, and the accuracy and the efficiency of information service are improved.