437 results about "Prediction score" patented technology

Methods of quantifying a reputation for a data source are presented. Historical documents having opinions and that are attributed to a data source are identified. The opinions preferably are quantifiable and can be converted into a predication. As the predications are verified, the data source is assigned one or more predication scores indicating the accuracy of the predications. A reputation score for a new document having a new predication can be assigned to the data source as a function of the predictions scores from the historical documents, data source affiliations, document topics, or other parameters. The reputation score relating to the new document can be presented to a user via a computer interface as a single-value, or multiple values corresponding to different topics.

The invention relates to a space-time attention based video classification method, which comprises the steps of extracting frames and optical flows for training video and video to be predicted, and stacking a plurality of optical flows into a multi-channel image; building a space-time attention model, wherein the space-time attention model comprises a space-domain attention network, a time-domain attention network and a connection network; training the three components of the space-time attention model in a joint manner so as to enable the effects of the space-domain attention and the time-domain attention to be simultaneously improved and obtain a space-time attention model capable of accurately modeling the space-domain saliency and the time-domain saliency and being applicable to video classification; extracting the space-domain saliency and the time-domain saliency for the frames and optical flows of the video to be predicted by using the space-time attention model obtained by learning, performing prediction, and integrating prediction scores of the frames and the optical flows to obtain a final semantic category of the video to be predicted. According to the space-time attention based video classification method, modeling can be performing on the space-domain attention and the time-domain attention simultaneously, and the cooperative performance can be sufficiently utilized through joint training, thereby learning more accurate space-domain saliency and time-domain saliency, and thus improving the accuracy of video classification.

A computer implemented sales prediction system collects data relating to events of visitors showing an interest in a client company from plural data sources, an organization module which organizes collected data into different event types and separates the collected event counts in each event type between non-recent events and recent events occurring within a predetermined time period, a first processing module which periodically calculates weighting for each event type based on recent events and non-recent events for the event type compared to totals for other selected event types, a second processing module which periodically calculates sales prediction scores for each visitor and companies with which visitors are associated based on the accumulated event data and weighting, and a reporting and data extract module which is configured to detect variation in sales prediction scores over time to identify spikes which can predict upcoming sales and to provide predicted sales information and leads to the client company.

The invention discloses a personalized tourist attraction recommending method based on a knowledge domains map. The personalized tourist attraction recommending method based on the knowledge domains map comprises the following steps: constructing a tourist area knowledge domains map through a massive amount of data on the internet; coding information in the knowledge domains map through an improved TransE model; training attractions and user nodes into a n-dimensional vector (which is assumed to have n attributes) according to the number of link attributes; also showing the relation between users and attractions as an n-dimensional vector; after vector representation of the users and the attractions, calculating similarity of the users and similarity of the attractions; substituting the similarity into a prediction scoring formula to obtain two prediction scores; then normalizing difference between vectors calculated by f (h, r, t) to the range between scoring threshold values to obtain a third prediction score; and finally, carrying out weighted averaging on the three prediction scores to obtain a final scoring list which is used for recommending tourist attractions for the users.By the personalized tourist attraction recommending method based on the knowledge domains map, the problems of poor semanteme, low recommending accuracy and cold start in the prior art are solved, and the practicality is good.

The invention discloses a TV shopping commodity recommendation method based on a classification algorithm. The TV shopping commodity recommendation method comprises the steps of: converting a prediction problem into a classification problem by utilizing logistic regression and a random forest, namely, predicting that purchasing behaviors of a user about a commodity can be divided into two categories: purchasing and not purchasing; extracting features from commodity information, user information and a user behavior record as input, and taking a prediction score of the user as output, thereby forming a function; and training a model by adopting a linear regression method, and converting the problem into a training classifier problem. The TV shopping commodity recommendation method does not carry out prediction and calculation on the basis of a heuristic rule, but carries out prediction on the basis of data analysis and statistics as well as machine learning for training model; and new users and new commodities can be calculated and predicted quickly as long as the model is trained.

The invention discloses a sample prediction method based on federation training, comprises the following steps: federating two aligned training samples by using an XGboost algorithm to construct a gradient lifting tree model, wherein the gradient lifting tree model comprises a plurality of regression trees, and a split node of the regression tree corresponds to a feature of the training sample; based on the gradient lifting tree model, jointly predicting the sample to be predicted to determine a sample class of the sample to be predicted or to obtain a prediction score of the sample to be predicted. The invention also discloses a sample prediction device based on federation training and a computer-readable storage medium. The invention realizes federated training modeling by using trainingsamples of different data parties, and further realizes sample prediction based on the established model.

The present invention provides a method for preparing a reference model for cancer relapse prediction that provides higher resolution grading than Gleason score alone. The method encompasses obtaining from different individuals a plurality of prostate carcinoma tissue samples of known clinical outcome representing different Gleason scores; selecting a set of signature genes having an expression pattern that correlates positively or negatively in a statistically significant manner with the Gleason scores; independently deriving a prediction score that correlates gene expression of each individual signature gene with Gleason score for each signature gene in said plurality of prostate carcinoma tissue samples; deriving a prostate cancer gene expression (GEX) score that correlates gene expression of said set of signature genes with the Gleason score based on the combination of independently derived prediction scores in the plurality of prostate cancer tissue samples; and correlating said GEX score with the clinical outcome for each prostate carcinoma tissue sample. A set of signature genes is provided that encompasses all or a sub-combination of GI_2094528, KIP2, NRG1, NBL1, Prostein, CCNE2, CDC6, FBP1, HOXC6, MKI67, MYBL2, PTTG1, RAMP, UBE2C, Wnt5A, MEMD, AZGP1, CCK, MLCK, PPAP2B, and PROK1. Also provided a methods for predicting the probability of relapse of cancer in an individual and methods for deriving a prostate cancer gene expression (GEX) score for a prostate carcinoma tissue sample obtained from an individual.

The invention discloses a social-label-based method for optimizing a personalized recommendation system. In the method, social label similarity and score similarity are adopted and applied to calculation of a user-and-project oriented K-nearest neighbor model, and then a user and a project of a K-nearest neighbor are used for calculating a prediction score of the project by the user at the same time. Because the label similarity and the score similarity are adopted in the method at the same time, so that the K-nearest neighbor calculation of the user and the project is more accurate, the recommendation accuracy is obviously higher than that obtained by singly adopting the score similarity, and a cold-start problem based on a label similarity model can be solved. Therefore, a data sparsityproblem can be solved by using a user-and-project oriented recommendation model, and the recommendation accuracy is also obviously higher than that of a conventional user-oriented recommendation model and a project-oriented recommendation model.

The invention relates to a collaborative filtering method for personalized recommendation fusion content and behavior. The method comprises the following steps of, (1) characteristic input, includinga project-attribute matrix representing a project content and a user behavior matrix representing user behaviors; (2) content-based project clustering for calculating the similarity of projects and clustering the projects; (3) score prediction and feature filling including carrying out score prediction on the non-scoring projects, and filling a user-project scoring matrix; (4) behavior-based userclustering including clustering users according to a project clustering result and a user-project scoring matrix; (5) score predication and project recommendation including determining the clusteringcluster where the target users are located, finding a nearest neighbor user set, performing score prediction on the non-scoring projects of the target users, and finally recommending the first N projects with the highest prediction scores to the target users. Compared with the prior art, the collaborative filtering method effectively solves the problems of data sparsity and cold start, and ensureshigh recommendation efficiency.

The embodiment of the invention provides a resource recommendation method and device and electronic equipment. The method comprises the following steps: receiving a resource recommendation request ofa target user; according to the resource recommendation request, obtaining feature information of the target user and feature information of to-be-recommended resources associated with the target userfrom an online database, wherein the feature information of the to-be-recommended resources comprises information of multiple historical operation behavior data of the to-be-recommended resources; inputting the feature information of the target user and the feature information of the to-be-recommended resource into an online machine learning model to obtain a prediction score of the to-be-recommended resource; and selecting one or more to-be-recommended resources from the to-be-recommended resources according to the prediction score, and recommending the one or more to-be-recommended resources to the target user to complete resource recommendation for the target user.

The invention relates to a dynamic recommendation method capable of adapting to user interest changes based on time information. The method comprises the steps that a user-object explicit rating matrix is built; a user-object implicit rating matrix is built; a user-object comprehensive rating matrix is built; similarity between two users is calculated; K users close to the target user similarity are obtained as the neighbour set of target users; a monotone decreasing exponential time function is selected as a rating weighting function, and the weighting factor of each user in the rating weighting function is calculated according to different interest change trends embodied by the scores of the users; a TOP-N recommendation method is adopted, and N objects with very top predication scores are recommended to the users. According to the method, the changes of the user interest along with time are considered, and the more precise personalized object recommendation service is provided for the users.

The invention discloses a video classification method and device based on deep learning. The method comprises the following steps of acquiring a data set and a category label of the video; and equallydividing the obtained video into N segments, at the training stage, randomly selecting M frames for each video, stacking the video frames into a multi-channel image; and passing through a convolutional neural network, extracting video space weighted characteristics of the video divided into N segments, and passing through a convolutional neural network, extracting video time weighted characteristics of the video divided into N segments, and obtaining video multi-scale features of the video divided into the N segments, fusing the N segments of video features to calculate a prediction score, obtaining a final video classification, storing the trained video classification model, and classifying the test video by applying the trained video classification model. Through the mode, the effect and accuracy of video feature extraction can be improved.

The embodiment of the invention provides a recommendation method and apparatus based on heterogeneous information network representation. The method includes: extracting target network node representation from a preset heterogeneous information network; acquiring target matrix decomposition according to the target network node representation and a preset matrix decomposition model; and a prediction score of a commodity by a user is obtained by using the obtained target matrix decomposition; and according to the prediction score of a commodity by the user, the user or the commodity is used as ato-be-recommended object for recommendation. Therefore, the recommendation rate is increased.

The invention discloses a shop recommendation method based on a position of a mobile user. The method comprises sending position information of the user to a server by a mobile phone used by the user, finding all shops related to the position by the server according to the position information sent by the user, finding all users related to the shops, and finally generating a user-shop scoring matrix; and the method further comprises initially filling the obtained user-shop scoring matrix, performing similarity calculation on a target user vector and other user vectors in the obtained matrix, generating neighbor users, performing scoring prediction on an unscored shop of the target use according to the neighbor users, and performing recommendation for the user according to a prediction result. After prediction scores of the unscored shops of the target user are obtained, the recommendation is performed for the user; and all the prediction scores are ranked, and then the shops, which have the high prediction scores and are the former N items, are recommended to the user.

The invention discloses a language identification method of a scene text image in combination with global and local information. Basic features of a character image are extracted, and then global andlocal feature representations are extracted respectively; the global extraction branch uses global maximum pooling to express the whole graph as a vector, and category score prediction is carried out;probability prediction is performed on the local blocks of the image by the local aggregation branches respectively, and then the series of probability distributions are combined to obtain a categoryprediction score of a local level; and finally, global and local prediction scores are dynamically fused according to the branch prediction conditions to obtain a final identification result. According to the method, overall features and local differentiated features of the character images are noticed at the same time, and end-to-end training can be achieved in one step. Compared with an existing technology utilizing local features, the method has the advantages that the local differentiated features can be accurately extracted, excellent effects are achieved in the aspects of accuracy, operation efficiency and universality, and high practical application value is achieved.

Disclosed are methods and systems for creating, evaluating, and tuning a predictive engine for machine learning, and for replaying performance of the predictive engine, including steps to deploy a variant of the predictive engine; receive a plurality of queries to the predictive engine variant from an end-user device; apply a query segment filter to the plurality of queries to generate a replay group of queries, wherein for each query in the replay group, the engine variant generates a corresponding predicted result, receives a corresponding actual result, and computes a corresponding prediction score; group queries in the replay group into one or more segments; and generate, as a replay of the performance of the engine variant, an accumulated prediction score over each of the one or more query segments of the replay group by applying an accumulation function. The present invention substantially improves on systems that utilize predictive engines.

The invention discloses an item-based explicit and implicit feedback mixing collaborative filtering recommendation algorithm. The method comprises the following steps of obtaining the information of interest of users on every item and establishing the score matrix of every user on all the items; calculating the average score of every user, the quantity of the scoring users of every item and the average score of every item; calculating a common comment user quantity matrix; calculating the Pearson similarity and the modified cosine similarity of between any two items; calculating the similarity based on explicit feedback; calculating the cosine similarity based on implicit feedback; calculating a final similarity; obtaining the nearest neighbor set I of a current item; when providing a recommendation list to a target user u, according to the score matrix, obtaining the scored items and the unscored items of the target user u; calculating the prediction scores of the unscored items of the target user u and selecting N items with the highest scores inside the unscored items of the target user u to the user. The item-based explicit and implicit feedback mixing collaborative filtering recommendation algorithm can effectively improve the accuracy of prediction recommendation.

A cyber-security system and method for proactively predicting cyber-security threats are provided. The method comprises receiving a plurality of security events classified to different groups of events; correlating the plurality of received security events to classify potential cyber-security threats to a set of correlation types; determining a correlation score for each classified potential cyber-security threat; and determining a prediction score for each classified potential cyber-security threat, wherein the prediction score is determined based in part on the correlation score.

The invention discloses a recommendation method based on singular value decomposition and classifier combination. The recommendation method comprises the steps of computing average score and probability distribution of an item through data preprocessing; training a singular value decomposition model through a stochastic gradient descent method, computing an entropy set of a scored item set of the user in item classification through a computing method of entropy, and determining an uncertainty critical value of the item; and comparing and predicting uncertainty and critical value of the item to determine whether to use a classifier, and recommending N items with highest scores in all non-scored items of the user through a Top-N method. According to the method, individual recommendation is produced on the basis of analysis of historical score data of the user; predicting score of a designated item i is acquired through a singular value decomposition algorithm, information entropy of the item for each user is calculated so as to determine whether to classify, and final prediction score of the item is acquired through the classifier, so that the accuracy of the recommendation method is improved.

The invention relates to the technical field of computers, and discloses a recommendation method and device, and the method comprises the steps: generating a feature sequence according to to-be-predicted data of a user for a target object and a preset coding rule, obtaining the probability distribution information corresponding to each feature in the feature sequence, and carrying out the calculation to obtain a feature vector corresponding to each feature; According to the values of the N features and the feature vectors corresponding to the N features respectively, obtaining a prediction score of the user for the target object; And when the prediction score is greater than or equal to a preset threshold, recommending the target object to the user. In the embodiment of the invention, Dueto the fact that the feature vectors corresponding to the features are obtained according to the probability distribution information corresponding to the features, the feature vectors corresponding to the features are accurate, the prediction result is accurate, and compared with the mode that point estimation is directly used for determining the feature vectors, the prediction result in the embodiment of the invention better conforms to the actual situation.

The invention discloses a drug target interaction prediction method based on multilayer network representation learning, and mainly solves the problem of low prediction accuracy in the prior art. Themethod comprises the following steps: downloading data from a drug and protein database, and respectively constructing multilayer similarity networks of drugs and proteins; calculating diffusion states of the two similarity networks respectively, and integrating the diffusion states respectively to obtain feature vectors of drugs and proteins; taking known drug target interaction data as supervision information, putting the drug and protein feature vectors into the same drug target space, and respectively obtaining projection matrixes of the drug and the protein by using a bilinear function; obtaining a prediction score matrix of drug target interaction according to the two projection matrixes and ranking the prediction score matrix; regarding eight top-ranked unknown drug target pairs aspotential drug target interactions. According to the method, the prediction accuracy of drug target interaction is improved, and the method can be used for predicting candidates of drug target pairs.

The invention discloses a project-level and feature-level deep collaborative filtering recommendation algorithm based on an attention mechanism. The algorithm comprises the following steps of S1, counting historical project scores of a user; S2, calculating the feature level content representation of the user on the target project according to the historical project score of the user; and S3, calculating a project-level prediction score of the user for the target project according to the historical project score of the user and the technical result of the S2. According to the algorithm, the recommendation precision is improved to a certain extent by combining attention mechanisms on a project level and a feature level, and compared with the prior art, the algorithm has higher interpretability in analysis of historical preferences of users. The extended DACFs, such as recently proposed neural collaborative filtering and discrete collaborative filtering, will also be considered in othercollaborative filtering models, a higher-order characteristic level attention mechanism is explored for future research, and the theoretical basis of research of the recommendation system is further tamped.

The invention provides an ordering strategy-based information filtering system, which relates to the technical field of information filtering, and solves the problems of inconsistency between an optimization objective and a filtering problem evaluating indicator, the deviation of a model optimization result and restricted performance in the conventional information filtering model. The information filtering system of the invention consists of a training model, a filter and a feature weight library, wherein a method for identifying a new information unit by the filter comprises the following steps: converting an information filtering problem into an ordering problem; performing optimization aiming at a core evaluating indicator 1-ROCA; establishing an ordering strategy-based information filtering model, wherein the ordering strategy-based information filtering model adopts an ordering logistic regression learning algorithm and comprehensively uses a TONE strategy-based parameter weight updating algorithm and resampling technology to obtain a weight parameter and obtain a prediction score value of the new information unit; and judging the attribute of a new mail according to the result of comparison of the prediction score with a predetermined threshold. The method of the invention can be applied to various information filtering and information push systems.

The invention discloses a collaborative filtering algorithm based on user and project mixing, and the algorithm comprises the steps: 1, carrying out the arrangement of a user-project scoring data set, and building a user-project scoring matrix U; 2, calculating the similarities of articles, and ordering the similarities from the big to the small; 3, generating a 'nearest neighbor N' of articles according to the similarity ordering of the articles; 4, calculating the similarities between a target user T and other users, and ordering the similarities from the big to the small; 5, generating a 'nearest neighbor N' of users according to the similarity ordering of the users. The algorithm gives consideration to the similarities of the users and the similarities of the projects, obtains a project prediction score (giving consideration to the similarities of the users and the similarities of the projects at the same time) through employing a weighting method, carries out recommendation according to the ordering of scores, can reduce the value of an MAE (mean average error), and improves the accuracy of a recommended algorithm.

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.

Systems and methods for domain adaptation are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

The invention discloses a user multi-interest and interest shift-based collaborative filtering recommendation algorithm. The user multi-interest and interest shift-based collaborative filtering recommendation algorithm comprises the steps of 1) structuring a user-project attribute category correlation matrix; 2) according to the user-project attribute category correlation matrix, computing user similarity to predict the degree of preference of a user to unknown project attribute categories and further to recommend preference categories to the user; 3) classifying scoring matrixes according tothe recommended categories, and computing the project similarity under every category; 4) considering the interest shift of the user, computing the time weight and the degree of novelty of the projects to acquire a preliminary prediction score; 5) combining user-project attribute category preference to acquire a final prediction score. The user multi-interest and interest shift-based collaborativefiltering recommendation algorithm takes projects as the bridge between users and project attribute categories, acquires preference to the project attribute categories, well solves the problem of singleness of user interest models, takes interest shift of the users and the degree of novelty of the projects simultaneously into consideration and accordingly ensures more accurate final recommendation results.

A computer-implemented method for generating a predictive output based on a predictive input includes generating a plurality of rule-based prediction scores by executing one or more prediction rules on the prediction input, wherein each prediction rule of the one or more prediction rules is associated with a rule condition and one or more predictive weights, each predictive weight of the one or more predictive weights is associated with a related prediction category of a plurality of prediction categories, and each prediction category of the plurality of prediction categories is associated with a rule-based prediction score; determining a rule-based prediction output based at least in part on the plurality of rule-based prediction scores; and providing the plurality of rule-based prediction scores and the rule-based prediction output to a machine learning engine, wherein the machine learning engine is configured to generate a machine-learning based prediction output based at least in part on the plurality of rule-based prediction scores and the rule-based prediction output.

A system and method for retrieving and intelligently grouping definitions with common semantic meaning is disclosed. In response to a user's textual query for the definition of a term or phrase, a set of documents is retrieved from a repository of structured documents. The retrieved documents are labeled with a prediction score based upon predetermined glossary characteristics of the documents. In order to determine whether the retrieved documents are likely to be definitions, features commonly found in definitions are identified. The identified features are classified with numeric values and weighed using a support vector regression algorithm. Definitions that fail to meet a predetermined threshold score are discarded, and those that exceed a predetermined threshold score are labeled and stored in the local database.

The invention discloses an abdominal multi-organ nuclear magnetic resonance image segmentation method and system based on FCN, and a medium. The abdominal multi-organ nuclear magnetic resonance imagesegmentation method comprises the following implementation steps: acquiring an input image and carrying out data preprocessing and image normalization operation; inputting the normalized abdominal multi-organ nuclear magnetic resonance image into a trained high-resolution full convolutional neural network model to obtain a final prediction image, wherein the high-resolution full convolutional neural network model is pre-trained to establish a mapping relationship between the normalized abdominal multi-organ nuclear magnetic resonance image and the corresponding final prediction image; and activating the final prediction graph by using an activation function to obtain a prediction score graph, and taking a category with the highest prediction score at each pixel position as a prediction label category of the pixel position to obtain a final segmentation prediction graph. According to the abdominal multi-organ nuclear magnetic resonance image segmentation method, automatic segmentation of the abdominal multi-organ nuclear magnetic resonance image can be realized, for example, the abdominal multi-organ MR image is segmented according to five different region types of an organ-free region, a liver region, a right kidney region, a left kidney region and a spleen region.