85 results about "Item score" patented technology

The invention provides for a voice platform to monitor a conversation between a call centre agent and a caller to identify any predetermined keywords or phrases used in the conversation therebetween. These keywords or phrases can then be used to interface into an existing knowledge management system in order to allow information from the system to be pushed to the agent, thus improving agent efficiency. In a preferred embodiment additional processing is provided which generates an information item score based in the detected keywords or phrases, and those information items with the highest scores are then pushed to the agent, by displaying shortcuts to the information to the agent in the form of a shortcut tree.

A system for measuring an ability of a subject. The system includes a set of tasks that require the subject to provide one or more spoken responses. A speech recognition system, which is coupled to receive the spoken responses, provides an estimate of the spoken responses. The estimate may be an estimate of the linguistic content and / or other characteristics of the response. The speech recognition system has an associated operating characteristic relating to its ability to recognize and estimate the content of responses and elements of responses. A scoring device converts the response estimate into one or more item scores. A computation device provides a subject score using a scoring computation model that depends upon the expected item-dependent operating characteristics of the speech recognition system.

Items—including gourmet products—are evaluated and rated by participants in a controlled event, which can be coordinated by software locally or at a dedicated website. Event data, including item scores and participant scores can be shared with vendors, merchants and other commercial entities associated with the products. Promotional incentives from such entities for the products (and related products) can then be directly targeted and provided to participants and other members of the public. The participant's activities can also be collected and disseminated to affiliates / friends of the participants through social networking sites, personalized web pages, etc.

A system and method for caching and / or synching shared media items in a media sharing system are provided. In one embodiment, a user device of a user joins a media sharing system including the user device and one or more other user devices connected via a network such that the user of the user device has access to one or more shared media collections hosted by the one or more other user devices. Shared media items from the one or more shared media collections are scored. The user device then obtains shared media items scored above a defined threshold from the one or more other user devices hosting the one or more corresponding shared media collections and stores those shared media items in local storage. In one embodiment, the local storage is temporary storage, such as a cache.

The invention discloses a recommendation system optimization method with information of a user and an item and a context attribute integrated. According to the method, the information of the user, the item and the context attribute is integrated in a matrix decomposition model, and recommendation accuracy is improved in a personalized recommendation system. The recommendation system optimization method with the information of the user, the item and the context attribute integrated is characterized in that different influences of the information of the user, the item and the context attribute on overall scores, user interests and item scores are considered, and is applied to calculation of an original matrix decomposition model. The influences of the user, the item and the context attribute on the scores are considered at the same time, and therefore the recommendation accuracy is obviously higher than that of the rectangular decomposition model which only adopts user program two-dimensional score matrix information.

The invention relates to a video recommendation method based on timing sequence data mining. The method comprises the steps that 1) video interest gradient change of a user is analyzed via third party data and a user interest gradient curve is obtained, and the singular points of the user interest gradient curve act as time points of user interest migration; 2) the latest interest migration time points of the user are confirmed, and user-item scores after the latest interest migration time points of the user are acquired so that a user-item score matrix meeting the current interest of the user within a selected time window is established; and 3) user customized video recommendation is performed by using a random walk model on the basis of the user-item score matrix. An interest migration problem in the customized video recommendation is considered, and customized video recommendation is performed though integration of a time window method and on the basis of the Random Walker trust degree model so that video recommendation accuracy and efficiency are enhanced.

The invention relates to the field of a recommendation system and discloses a collaborative filtering recommendation method based on emotions and trust. The collaborative filtering recommendation method comprises a step 1 of obtaining an explicit degree of satisfaction by normalizing an item scored matrix of users; calculating the similarity between scored items and items that are not scored according to a vector cosine method, obtaining an implicit degree of satisfaction by using the explicit degree of satisfaction and the similarity, and constituting an extended satisfaction matrix by the explicit degree of satisfaction and the implicit degree of satisfaction; a step 2 of calculating the score similarity and the preference similarity according to the extended satisfaction matrix, and obtaining an objective degree of trust generated by the users on the opinion similarity of the items by using the score similarity, the preference similarity and weights set by a supervised learning algorithm; and a step 3 of abstracting a user social network according to the user satisfaction interaction frequency, establishing a weighted directed graph based on the six-degree partition theory, and calculating a subjective degree of trust generated by familiarity among the users. The method of the invention realizes the collaborative filtering.

A method and program product for automatically generating reports matching user interests represented in a dynamically adjusted user interest analytic model (UIAM). A Multidimensional Expressions (MDX) query is generated based on a user visit to a business intelligence application. Based on initial user visit(s), a cube-based UIAM is constructed by including a representation of a first set of user interest(s) in a first set of UIAM item(s). The cube-based UIAM is transformed into a data warehouse-based UIAM. Based on subsequent user visit(s), UIAM items are updated to represent a second set of user interest(s) and UIAM item scores are adjusted to specify how frequently and recently user interests are indicated by the user visits. An update of data in the data warehouse is detected. Reports representative of user interest(s) represented by the updated UIAM items having the top k scores are generated.

The invention provides a user similarity-based sparse data collaborative filtering recommendation method and mainly aims to solves the problems in the prior art that the calculation of the values of similarity between users is in accurate for sparse data and further the recommendation quality is influenced. The method comprises the steps of (1) establishing a sparse matrix for item scores from users; (2) calculating the overall situation similarity between any two items; (3) calculating the local similarity between any two user scores; (4) calculating the similarity between any two users; (5) predicting scores; (6) generating a recommendation list; (7) completing collaborative filtering item recommendation for all the users. Experimental simulation results show that for sparse data sets, the method has the advantages of guaranteeing higher accuracy of the similarity between users, improving the recommendation quality and better meeting user requirements compared with conventional collaborative filtering recommendation methods.

The present invention discloses an item-based transfer learning recommendation method and a recommendation apparatus thereof. The transfer learning recommendation method comprises the steps of: establishing a user-item scoring matrix for an auxiliary domain and a target domain separately; standardizing the user-item scoring matrices of the auxiliary domain and the target domain; decomposing the standardized user-item scoring matrix of the auxiliary domain so as to acquire an item feature matrix; expanding the user-item scoring matrix of the target domain by use of the item feature matrix; and generating recommendation according to the expanded user-item scoring matrix of the target domain. The transfer learning recommendation apparatus comprises: an establishing module, a standardizing module, an acquiring module, an expanding module and a recommending module. According to the item-based transfer learning recommendation method and the recommendation apparatus thereof, items demanded by the user are recommended for the user more accurately and more reasonably, thereby improving the individuality and intelligence, improving user use efficiency, effectively saving user time, improving service quality of related industries, and effectively solving the problem of overload of the internet information, and the density and accuracy of user-item scoring matrices are improved.

The embodiment of the invention provides a recommendation method, a recommendation device and a mobile terminal. The recommendation method comprises the steps that the item score data of users are acquired, wherein the item score data include historical score values and corresponding historical score time of the historical score values; the corresponding time weight of the historical score values is calculated according to the historical score time; a user similarity value is calculated by using the historical score values and the time weight; and the corresponding item is recommended to the target users based on the user similarity value. According to the recommendation method and the recommendation device, the item score data including the historical score values and the historical score time are acquired, the corresponding time weight of the historical score values is calculated according to the historical score time, and finally the user similarity value is calculated by using the historical score values and the time weight and the corresponding item is recommended to the target users based on the user similarity value so that the objective of recommending the item having high matching degree with the interest of the current user according to the real-time change of the user interest can be realized.

The invention discloses a matrix decomposition recommending method based on an expanded label, comprising: constructing an item-label matrix based on the item label data and calculating the label similarity; constructing a first item pair-label vector based on the item-label matrix; and according to the label similarity, extending the first item pair label-vector as a second item pair-label vector; establishing an item similarity matrix based on the second item pair-label vector; solving a user implicit characteristics matrix and an item implicit characteristics matrix based on the item similarity matrix and the pre-constructed item scoring matrixes; predicting the score by the user to the unrated items; and building a list of recommended items for the user. At the same time, the invention also discloses a matrix decomposition recommending system based on the expanded label. The invention can provide the user with more accurate personalized recommendations when the label is sparse, and relieves the problem of cold starting of the item to a certain extent.

A search refinement method and system to select items from a plurality of items using a user device connected via the internet to a server apparatus. The server apparatus includes a database of items and item attributes. Images of a first subset of the items are transmitted to the user device where they are presented on a display. A change indication selected by a user of the user device is received by the server apparatus, the change indication including at least one of an attribute selection and a reference item selected from the first subset. Responsive to receiving the change indication, an item score is computed for each of the items based on the item's attributes and the change indication. Images of a second subset of the items are presented on the user device. Each time the user initiates a change indication, another subset is presented on the user device, and the user can iteratively refine the search by finding items similar to the items represented by the change indication.

Embodiments of the present application disclose an item recommendation method, apparatus, computer device, and storage medium. The method includes: determining a target user group from a plurality ofuser groups according to a score vector of the target user, and then calculating a similarity value between the target user and each user in the user group to which the target user belongs; Determining a similar user of the target user according to the similarity value; Obtaining items scored by similar users but not scored by target users as recommendation items and generating a first item recommendation table according to the recommendation items; According to the similarity value between the target user and the similar user, the scoring value of each recommended item by the similar user andthe corresponding time attenuation factor, calculating the scoring value of each recommendation item according to the preset calculation formula; sorting a plurality of recommendation items accordingto a preset sorting rule according to an item score value to generate a second item recommendation table and push to a target user. This method can improve the accuracy of item recommendation and effectively avoid the lag problem of recommended projects.

The invention provides a method and device for selecting servers, relates to the technical field of telecommunication and aims at the problem that the application servers cannot be ensured to have enough residual resources to respond to user requests. The method provided by the invention comprises following steps of obtaining preset server indexes and weights corresponding to different server indexes, wherein the sum of the weights of the preset server indexes is 1; obtaining index parameters of alternative application servers corresponding to different server indexes; eliminating the alternative application servers of which index parameters are inconsistent with preset parameter threshold value demands; with respect to the residual alternative application servers, calculating item scores of the various index parameters according to the weights; summing all item scores, thus obtaining the total performance scores of the corresponding alternative application servers; and selecting the application servers from the alternative application servers according to the rank of the total performance scores. The method and the device are mainly applied to the processing of selecting the servers.

The invention discloses a weighted trust relationship-based probability matrix decomposing and recommending method. The weighted trust relationship-based probability matrix decomposing and recommending method comprises the following steps: acquiring a user item score information matrix and an inter-user trust relationship score matrix and filling a trust information matrix with trust data; for theuser item score information matrix, calculating the similarity of a target user and each user according to a similarity calculation formula; fusing the acquired inter-user similarity into trust scoredata to acquire weighted trust score data; combining the acquired weighted trust score data with a probability matrix decomposing method to acquire a probability matrix decomposing and recommending model based on the weighted trust relationship; successfully predicting an item in which the target user is interested according to the acquired recommending model. The weighted trust relationship-based probability matrix decomposing and recommending method mainly aims at a social network site with score information and trust data and is mainly applied to an electronic commerce system; high-qualityand high-accuracy recommendation for the target user is formed effectively.

The invention discloses a collaborative filtering method based on integration of fuzzy weight similarity measurement and clustering. According to a user-item scoring matrix R<m x n>, three different similarity matrixes FCOS, FCOR and FADJ of users are respectively calculated by using fcos, fcor and fadj, and then according to a k-means algorithm and a cluster number kcluster, all users are clustered. A nearest neighbor set s (Ui) of users is determined and then scores are calculated and predicted by using r<i,c>; according to the above-mentioned strategy, the steps are repeated till scores of all user are predicated. By adopting the fuzzy similarity clustering IBCF\UBCF of the invention, the searching accuracy of the neighbor set s (Ui) is obviously improved; by fuzzifying score values and score deviations, the evaluation is closer to the real evaluation of the users to items; by adding fuzzy weight wc during similarity calculation, the similarity between the users tends to be more accurate and thus the performance of a recommender system is improved.

The embodiment of the invention discloses a security estimation method and device. The realization of the method, for example, comprises the steps that the operation behavior set of an object to be evaluated is acquired, and the operation behavior set is a set including operation items corresponding to the object to be evaluated; all the operation items in the operation behavior set are compared with the preset operation item scoring rule, and the scores of the operation items in the operation behavior set are calculated; and the security level of the object to the evaluated is confirmed according to the scores. The operation behavior set of the evaluation object is acquired, all the operation items in the operation behavior set are compared with the preset operation item scoring rule, and the scores of the operation items in the operation behavior set are calculated so that the security level of the object to be evaluated is confirmed through a scoring mode based on statistics of the operation behaviors, and thus accurate security evaluation can be realized.

A user preference and distance weighted clustering method incorporating time factors is disclosed. The user-user attribute matrix constructed by the basic objective characteristics of users is introduced to alleviate the user cold start problem, and the sparsity problem is mainly improved by introducing project characteristics, because the characteristics of the project can reflect user preferences from the content aspect, so that the dimension of the matrix can be reduced; Item characteristics are introduced into user-item scoring to obtain a small-dimensional user-item attribute total scoring matrix. When constructing user-item attribute preference matrix with TF-IDF algorithm, item characteristics are introduced and the influence of user interest drifting with time is considered. Basedon the above three matrices, the weighted Euclidean distance is obtained, and then the weighted Euclidean distance is clustered by using K-Means algorithm. The experimental results on Movie Lens dataset show that this method has better recommendation quality and performance than other related algorithms.

The invention is suitable for the technical field of information and provides a method and a device for recommending items. The method comprises the following steps: acquiring item information within a preset distance scope on a present position of a to-be-recommended user; acquiring a candidate user group according to the item information; calculating an interactive behavior similarity and an item scoring similarity between the to-be-recommended user and each candidate user in the candidate user group; calculating a compound similarity between the to-be-recommended user and each candidate user according to the interactive behavior similarity and the item scoring similarity; selecting N candidate users with the maximal compound similarity and forming a neighbor set of the to-be-recommended user; acquiring the item concerned by each candidate user in the neighbor set; and forecasting a score of the item scored by the to-be-recommended user and recommending M items in the highest scores to the to-be-recommended user. According to the invention, the problems of sparse data and cold starting of the present individual recommendation technique can be solved and the item recommendation accuracy is promoted.

The present invention discloses a recommendation method and apparatus based on the heterogeneous information network. The method is characterized in that: a schematic diagram of the heterogeneous information network is divided into a plurality of sub-diagrams, each of the sub-diagrams corresponds to a unary diagram; based on each of a plurality of user-item similarity matrices, fusion is carried out on each of the user-item similarity matrices, and a user-item scoring equation is constructed; and by optimizing the objective function, the user-item scoring equation is trained according to the known scoring sample to obtain user-item scoring equation parameters, so that scoring of the user for each item can be predicted, the item whose scoring meets the preset condition is recommended to theuser, the problem that the semantic coverage is incomplete when using the element path to analyze similarity between users and items in the prior art is solved, the relevance between features is fully considered, and useful products are recommended to the users.

The invention relates to the technical field of personalized recommendation, in particular to a personalized recommendation method fusing social information. In accordance with the user-item scoring matrix, calculating scoring similarity between users, and screening the nearest neighbor set of scoring; then, according to the nearest neighbor set, calculating the prediction score of the target user; calculating the social similarity between users according to the social network information of users, and screening the social nearest neighbor set; according to the social nearest neighbor set, calculating the prediction score of the target user; by combining the two, predicting the target user 's rating value of the project, and descending the order, recommending the K items with the highest rating to the target user, and generating the recommendation list. Finally, the experimental results show that the performance of the proposed personalized recommendation method is better than the current recommendation method, which can effectively improve the accuracy of recommendation, so as to alleviate the data sparseness and cold start problems.

The invention provides a livestock product monitoring and tracing method and system and relates to the technical field of product tracing. An ear tag number is generated and then entered in an RFID ear tag attached to an ear part of livestock, and breeding information and environment information of the livestock being bred are gathered into breeding environment information which is then entered into the RFID ear tag; a characteristic item score, a characteristic item grade, a reference score and a reference quality grade are gathered as evaluation information; the breeding environment information and the evaluation information in the RFID ear tag is classified and gathered into corresponding livestock product information, and livestock product files are established. Via a technical solution of the livestock product monitoring and tracing method and system, a technical problem that livestock products are low in informatization and intelligentization level due to conventional technologies; whole course on-line monitoring including quality monitoring, source tracing and information storing can be realized; reliable and convenient product evaluation information is provided for consumers, and an informatization and intelligentization level of livestock breeding can be improved.

The invention provides an item scoring prediction method and an apparatus which relate to the technical field of data processing to address the problem in the prior art of failing to have items recommended to users accurately due to the fact that a traditional recommendation system cannot tell similar users for a user. The method is performed through the following steps: obtaining the scoring information of a user to one item; based on the scoring information of the user to the item, generating a user-item type scoring matrix; determining targeted users and similar users based on the user-item type scoring matrix; based on the user-item type scoring matrix and the scoring information of the user to the item, calculating the predicted scorings of an to-be-scored item by the similar users of the targeted users and of the to-be-scored item of targeted users by similar users without scoring; and finally, based on the scoring to the to-be-scored item of targeted users by the similar users of the target users, scoring the to-be-scored items. The invention is provided to recommend items.

The present invention relates to the field of automation technology, in particular to a fractional prediction system and a prediction method. The system comprises: a student practice terminal, the student practice terminal is used for dividing the score prediction nodes of the test questions in the test question bank according to the rule of the student 's problem making or the rule of the test paper' s problem setting, then forming the test questions between two score prediction nodes into sub-node sets, and counting the number of the corresponding sub-node sets to generate the number of testquestions, and then calculating the proportion between them according to the sub-node sets and the number of the students' test questions, and generating the coverage rate of answering, then dividingthe weight of the test questions from different sources according to the source of the test questions, and calculating the scores of the node items according to the correct rate of the test exercisesfrom different sources, and calculating the predicted scores of the child node sets of the students according to the answer coverage, the node item scores and the smoothing function as the basis of the prediction scores.

The invention discloses a cross-domain collaborative filtering method. After the user item scoring data is converted into a training sample set, the user item scoring matrix of each auxiliary domain is processed with the Funk-SVD decomposition to obtain a user potential vector, a first set of extended training samples is then obtained by expanding the set of training samples by using the user potential vector, adding item feature information to expand the first set of extended training samples to obtain a second set of extended training samples, training an unbalanced classifier using the second set of extended training samples, and finally predicting missing data of the user item scoring data based on the unbalanced classifier and generating a recommendation. The problem of data sparsityin the target domain is solved by using auxiliary domain data, and then the unbalanced classifier is trained to predict the missing items in the target domain, and the recommendation data are obtainedto solve the problem of data sparsity and unbalance in the existing recommendation system.