180results about How to "Efficient recommendation" patented technology

A system for recommending personalized favorite programs or channels to internet protocol television (IPTV) users based on a collaborative filtering algorithm is disclosed. The system includes a broadcast provider as an IPTV broadcast provider that provides users with TV contents through the Internet, a service server to receive a broadcast signal and program information from the broadcast provider, to store corresponding information in respective databases, to calculate the program information based on a recommendation algorithm to quantitatively calculate priority, and to list the program information in recommendation order based on the currently broadcast or reproduced program, a relay device to receive recommended program list information and a broadcast signal from the service server and to transmit the recommended program list information and the broadcast signal through a network, and a TV to output the recommended program list information and the broadcast signal from the relay device.

The invention relates to a personalized recommendation method based on commodity property entropy. The method comprises the following steps of: achieving the browsing history of electronic commerce website users through a script; analyzing the browsing history; and generating a recommendation result and performing personalized recommendation. In the method, the user profile based on the commodity property entropy can help the recommendation calculation method to find the preference of the users in different property classification, and different recommendation is generated by utilizing the information of the users in the browsing process and according to the actual selection of the users, so that diversity of the commodity page recommendation is improved. Based on a recommendation system requiring personalized recommendation, the hit rate of recommendation is maintained and recommendation diversity is improved. By the method, on the premise of not changing greatly, the results generated by other recommendation calculation methods are sequenced again, so that the effect of the original recommendation calculation method is not influenced, diversity of the commodity page personalized recommendation is improved, and recommendation on the commodity pages is more effective.

A system and method for measuring, analyzing, and tracking the past performance of security analysts' earnings estimates and recommendations. A database containing historical information pertaining to analyst earnings estimates and recommendations is downloaded into the system. Pre-calculated data values are also added to the database including adjustment factors a single or set of analysts based upon their historical earnings estimates as compared to actual earnings estimates over time, and other user-defined performance analysis set parameters and metrics. A weighting factor may also be calculated for a set of analysts based upon factors such as the recency of an analyst's earnings estimates. Using these adjustment and weighting factors and each analyst's actual earnings estimate, a custom composite estimate may be derived. A front-end graphical user interface (GUI) is used to view analyst historical data either as raw data or, by using a data visualization technique, as a graph or chart.

The invention discloses a method for recommending an opposite sex friend in an SNS community. The SNS community at least comprises a first user and a second opposite sex user. The method comprises the following steps of: (a) collecting personal characteristic information of the first user and the second opposite sex user in opposite sex friends-making appeals; (b) storing the information; (c) extracting the information and judging whether the first user and the second opposite sex user pass the opposite sex friend threshold standard set by the two parties simultaneously when the first user requests to acquire an opposite sex friend or the first user logs in the SNS community; (d) performing matching operation based on the personal complex characteristic information of the two parties; and (e) when the personal complex characteristic information between the first user and the second opposite sex user is matched, recommending the second opposite sex user to the first user serving as an opposite sex friend. The method and the system for recommending the opposite sex friend specially aiming at the SNS community are expanded, and the friend-making accuracy and pertinence in the SNS community are improved.

Provided are a method and an apparatus for predicting a preference rating for content, and a method and an apparatus for selecting sample content in order to predict a preference rating for the content. In the method of predicting a preference rating for the content, a list of users having similar preferences to a target user is extracted from content usage information collected with respect to the same content, and the target user's preference rating for the content is predicted by applying preference rating information of the users with similar preferences to a machine learning algorithm.

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.

A method of recommending a friend in a first terminal is provided. The method includes generating first interest keyword information by analyzing event information of the first terminal, receiving second interest keyword information of a second terminal, comparing the first interest keyword information and the second interest keyword information, and displaying information recommending a user of the second terminal as a friend based on a result of the comparing.

The invention provides a socialized recommendation method based on a matrix decomposition and network embedding joint model. The method comprises the following steps: constructing a user-article scoring matrix and user-user social network and generating a user social corpus according to user-user social network; utilizing a user-article scoring data and a user social corpus training matrix decomposition and network embedding joint model to obtain a user feature matrix and an article feature matrix; predicting an unobserved score according to the user feature matrix and the article feature matrix; and recommending a plurality of articles with relatively high prediction score values to the corresponding users. According to the method, a matrix decomposition model and a network embedding model are seamlessly integrated by designing a unified target function; based on a unified optimization framework, bidirectional promotion and collaborative optimization between a matrix decomposition model and a network embedding model are realized, so that interested articles can be accurately recommended to a user.

The invention discloses a media data recommendation method and device and a storage medium, and belongs to the technical field of Internet. The method comprises the steps of obtaining user characteristics of a target user; obtaining a plurality of alternative media data matched with the interest label characteristics according to the plurality of media data to be recommended; for each piece of alternative media data in the plurality of pieces of alternative media data, combining the user characteristics with the data characteristics of the alternative media data to obtain combined associationcharacteristics, and obtaining the correlation degree of the association characteristics based on a first recommendation model; and determining target media data recommended to the target user according to the correlation degrees corresponding to the plurality of alternative media data. According to the technical scheme, the multiple pieces of alternative media data matched with the interest labelfeatures are screened out, the calculated amount can be reduced, the recommendation efficiency can be improved, the correlation degree can be determined according to the correlation features and thefirst recommendation model, personalized recommendation can be effectively conducted on the target user, the accuracy of the correlation degree is improved, and therefore the recommendation effect isimproved.

Embodiments of the present application relate to a method for recommending information, a system for recommending information, and a computer program product for recommending information. A method for recommending information is provided. The method includes determining a set of specific first users comprising at least one specific first user who complies with a first preset condition, the determination being based on operating behavior information of a set of one or more first users recorded in a system, looking up, in the set of specific first users, targeted specific first users having a similarity to a current user who complies with a second preset condition, and providing recommendation information to the current user based on the operating behavior information of the targeted specific first users.

The present invention discloses an information conversion ratio prediction method, and an information recommendation method and device. The information conversion ratio prediction method comprises thesteps of: determining information to be recommended and user feature information; predicting conversion probabilities corresponding to at least two factors influencing an information conversion process to be recommended according to the recommendation information and the feature information; and predicting the conversion rate of the information to be recommended according to the conversion probabilities corresponding to the at least two factors.

The invention concerns a method for assisting user searches in a support system and a system for performing the method which comprises the steps of providing a support data structure with nodes comprising support information of a support database, and providing at least one behavioral data structure comprising information about the time the user(s) spend at said nodes, and information about the transition probabilities between each upper node and its lower nodes, and calculating for each lower node that is located below a current node, navigated to by a user of the support data structure, the expectation value of the time gained by navigating directly to that lower node, and selecting at least one of the lower nodes based on said expectation value.

The invention provides a personalized product recommendation method based on combined non-negative matrix decomposition. The method comprises a step of capturing data information which comprises the score of a purchased product by a user, the friend relation between users and a text evaluation of the purchased product by the user in the Internet, a step of converting the data information into a data matrix, wherein the data information of each user is a row vector, a step of using a method of combined non-negative matrix decomposition to separate the original data matrix into a plurality of data matrices under a plurality of low-dimensional spaces, and a step of estimating the scores of all products which are not purchased by each user according to the data matrices under the low-dimensional spaces and carrying out product recommendation according to high and low scores. The method has the advantages that a user structure relation and product evaluation information in a social network are comprehensively considered, a problem that a traditional method can not effectively process a new user is solved, and the effective product recommendation is carried out on a new user who has not purchase any product.

The invention discloses a goods recommending method and system, and relates to the big data field; the method comprises the following steps: obtaining a user behavior log formed by the user buying orbrowsing goods; processing the user behavior log so as to obtain feature information of the user buying or browsing goods; weighting the feature information according to a preset weight coefficient, thus obtaining a goods recommending level; recommending the goods according to the recommending level. The method and system obtain the user behavior log formed by the user buying or browsing goods, extract the feature information of the user buying or browsing goods, obtain the goods recommending level according to the feature information, and recommend the goods according to the level, thus satisfying advertisement input demands of different users, and providing customized advertisement recommendations for various users; the method and system are strong in pertinency and practical values.

A category pair is generated in a round-robin fashion for all of categories by obtaining each category of a document directory, each category of a bookmark, and a URL registered to each category from each of a document directory storing unit and a bookmark storing unit, and the degree of similarity is calculated for each category pair. Next, a pair of categories whose degrees of association are high is selected from among all of category pairs, and a URL candidate to be recommended each other is extracted for each selected category pair.

The invention relates to a swarm intelligence perception system user recommendation method and belongs to the technical field of swarm intelligence perception system optimization. The method comprisesthe steps that (1) user historical data is acquired; (2) users and task feature vectors are quantified, and a user-task data quality matrix is established; (3) a task message pushing group is obtained from an original user group; (4) final participation users are selected from the pushing group; and (5) final participation user data is acquired, and a user-figure data quality matrix is updated. Compared with the prior art, personal interests and preferences of the users and the problem that different tasks completed by the users are different in data quality are fully considered in the method, and therefore user recommendation can be performed more effectively; and for the users interested in participating in the tasks, the final users participating in the tasks are selected according tohistorical participation data quality of the users and the scale of the currently selected users, therefore, a platform can guarantee completion of the tasks and obtain maximum benefit.