46 results about "Interactive visual analysis" patented technology

Fraud detection is facilitated by developing account cluster membership rules and converting them to database queries via an examination of clusters of linked accounts abstracted from the customer database. The cluster membership rules are based upon certain observed data patterns associated with potentially fraudulent activity. In one embodiment, account clusters are grouped around behavior patterns exhibited by imposters. The system then identifies those clusters exhibiting a high probability of fraud and builds cluster membership rules for identifying subsequent accounts that match those rules. The rules are designed to define the parameters of the identified clusters. When the rules are deployed in a transaction blocking system, when a rule pertaining to an identified fraudulent cluster is triggered, the transaction blocking system blocks the transaction with respect to new users who enter the website.

A Customer Relationship Management (CRM) system that dynamically builds predictive models. The system is used by business users who are unfamiliar with the art of data mining. A model-building mechanism in a data mining subsystem is presented with a training segment consisting of records with appropriate input attributes and an output attribute to be predicted; the model-building mechanism builds a model in the form of a business measure that can subsequently be applied to make predictions against other like segments.

A Customer Relationship Management (CRM) system that incorporates predictive models. The system is used by business users who are unfamiliar with the art of data mining. The predictive model, which is constructed by a model-building mechanism in a data mining subsystem, accepts the appropriate input attributes, performs calculations against a segment comprised of records, and generates an output attribute.

A method (and system) of providing an interactive visual analysis of business expenditure, includes using an interactive graphical view to gain insight into purchase information for assisting in understanding purchase activities and making decisions on purchasing.

Generally the background of the present invention is the field of artificial vision systems, i.e. systems having a visual sensing means (e.g. a video camera) and a following processing stage implemented using a computing unit. The processing stage outputs a representation of the visually analysed scene, which output can then be fed to control different actors, such as e.g. parts of a vehicle (automobile, plane, . . . ) or a robot, preferably an autonomous robot such as e.g. a humanoid robot.

The invention belongs to the technical field of industrial big data application, and particularly relates to an industrial big data multidimensional analysis and visualization method based on a JSON document structure. The method comprises the following steps: by taking JSON as a basic carrier of data, constructing an industrial data mart in parallel by utilizing Spark and ElasticSearch through configuring a relational database and a file system data source and defining data conversion and data cleaning operations; configuring an overall process of data analysis in a graphical mode to construct an analysis data set of a multi-dimensional structure, and repeated association operation on massive data being avoided; and for a specific data analysis scene, customizing each dimension calculation index of the data analysis report in a visual dragging mode based on a pre-constructed multi-dimensional analysis data set, and generating an interactive graphic analysis report. According to the method, the JSON document format is used as a carrier of basic data, and the advantages of the JSON document format in storage and analysis are utilized, so that multi-dimensional analysis structure modeling and user-defined interactive analysis are more convenient and efficient.

Multi-dimensional temporal data can provide insight into patterns, trends and correlations. Traditional 2D-charts are widely used to support domain analysts' work, but are limited to present large-scale complicated data intuitively and do not allow further exploration to gain insight. A visual analytics system and method which supports interactive analysis of multi-dimensional temporal data, incorporating the idea of a novel visualization method is provided. The system extends the ability of mapping techniques by visualizing domain data based on a 3D geometry enhanced by color, motion and sound. It allows a compact universal overview of large-scale data and drilling down for further exploration. By customizable visualization, it can be adapted to different data models and applied to multiple domains. It helps analysts interact directly with large-scale data, gain insight into the data, and make better decisions.

The invention discloses a learning behavior dynamic prediction method and device, equipment and a storage medium. The prediction method comprises the following steps: based on the learning behavior data of a user in a historical period, adopting a long-short-time memory cycle neural network as a prediction model for training to obtain an optimal model; and acquiring learning behavior data of the user in the first time period, and outputting a prediction result based on the optimal model. The invention adopts LSTM-RNN as a prediction model to predict the output results, can improve the accuracyof the prediction, and uses an interactive visual analysis mode to display user information data, facilitates viewing and analysis of user data information at the background of the system, so as to help teachers to timely and intuitively know the results of data analysis, and then achieve the ''closed loop'' of the teaching process. The invention can be widely applied to various learning behaviorprediction systems.

The invention provides a sports video event analysis method. The method comprises the following steps that: mark lines in a field are extracted, and a field region where an event happens is identified through a scene classification method, so as to classify the line mode of a competition event; through an interactive analysis of multi-object tracks, interactive tracks of a ball and team members are generated according to the competition event, and a hierarchical detailed-to-rough analysis is carried out according to an interactive mode of the competition event; and finally, a tactical mode summary with an abstract property is formed and presented to users. The method automatically analyzes strategic methods adopted when the team members (teams) in the video event complete a tactical movement from professional view, and presents in a concise clear mode, so as to provide help for the learning and training of coaches and the team members.

This invention relates to graphical user-interactive displays for use in MS-based analysis of protein impurities, as well as methods and software for generating and using such. One aspect provides a user-interactive display comprising an extracted mass chromatogram (XIC), an MS1 spectrum and an MS2 spectrum, all simultaneously representing a user-selected peptide. Another aspect provides a user interactive display simultaneously presenting paired spectra (XIC, MS1 and/or MS2) for a variant peptide and its corresponding wildtype counterpart.

Along with the booming development of academic research, quantity of academic document is larger and larger, and demands on document data analysis is prominent day by day. The invention belongs to an interactive visualized analysis system structure facing massive document information, the interactive visualized analysis system structure suitable for the massive document data is established, and the original massive data are calculated by using classifying and clustering thoughts, so the problem that the analysis result of a scientific document network is lack of graphic display is solved. The structure is divided into four layers: a user interface layer, an analysis result layer, an analysis statistical layer and a data model layer. The user interface layer is a system-user interaction interface; the analysis result layer realizes visualized display of an analysis result; the analysis statistical layer realizes analysis of massive documents and the data model layer maintains connection of a database and realizes access of the database. The structure analyzes the massive documents, realizes visualized display and realizes interaction function with a user.

Multi-dimensional temporal data can provide insight into patterns, trends and correlations. Traditional 2D-charts are widely used to support domain analysts' work, but are limited to present large-scale complicated data intuitively and do not allow further exploration to gain insight. A visual analytics system and method which supports interactive analysis of multi- dimensional temporal data, incorporating the idea of a novel visualization method is provided. The system extends the ability of mapping techniques by visualizing domain data based on a 3D geometry enhanced by color, motion and sound. It allows a compact universal overview of large-scale data and drilling down for further exploration. By customizable visualization, it can be adapted to different data models and applied to multiple domains. It helps analysts interact directly with large-scale data, gain insight into the data, and make better decisions.

The invention provides an indoor face recognition and positioning method based on a panoramic camera. The technical method comprises the following steps: building internal space visual analysis, panoramic camera erection, face recognition, positioning calculation and positioning output. 3-D digital model of that panoramic camera and the building, The invention is characterized in that the indoor space analysis is carried out through the three-dimensional digital model of the building, the fixed point position of the panoramic camera is selected, the panoramic camera is installed and debugged,the face is monitored and detected, the face position is recognized through the geometric relationship between the camera and the monitored person, and the accurate positioning of the indoor face is realized. The invention does not rely on a wearable device, The signal base station can effectively solve the problems that the existing indoor positioning method needs to cooperate with mobile equipment, is susceptible to electromagnetic interference, has poor precision, is difficult to accurately dock with a specific person, has small application range, wastes resources seriously, and can be widely used in indoor navigation, loss prevention, security management, suspect tracing, 120 ambulance, and other aspects.

A request for data is processed by identifying data within a data store satisfying the request, where an amount of the identified data exceeds a threshold, analyzing the identified data to produce an initial result set with a reduced amount of data including information summarizing the identified data, and generating one or more succeeding result sets each from a corresponding prior result set until a succeeding result set includes an amount of data satisfying the threshold. Each succeeding result set includes a reduced amount of data relative to the corresponding prior result set, and generating each succeeding result set includes filtering the corresponding prior result set and generating the succeeding result set including information summarizing the filtered result set.

Preferably, test-patterns print on separate, multiple print-medium cards, each including a ramp with colors graded along a certain direction—and, superimposed on the ramp, a candidate add-on colorant. Ramps preferably are printed in so-called “customer colors”, common in snapshots and particularly snapshot regions that include sky. Positions or amounts of the candidate add-on colorant canvass a likely range of values that optimize camouflaging or suppression of a banding artifact (due to seams in the pagewide array) that is extended along the same certain direction. For each seam and each “customer color” used, an operator holds up several cards for comparison, selecting the best one to three. Operators thus can evaluate candidate colorant patterns in context of many different tones of the sky and other customer colors. Preferably banding suppression is integrated with linearization: at each seam a series of linearization tables is smoothly interpolated between measurement-based tables for adjacent inkjet dice.

The invention relates to a high-dimensional data visual analysis method. The method comprises the steps that local subspace difference-geodesic distance projection is built on original high-dimensional data; mapping of clustering point clusters is built; visual analysis views of a series of subspaces are built. The invention further discloses an analysis system achieving the high-dimensional data visual analysis method. Accordingly, by building mapping of the local subspace difference-geodesic distance projection and clustering point clusters and the visual analysis views of the series of subspaces, a series of interactive visual analysis operations are put forward, a reliable technological base is provided for visual subspace clustering and analysis, a user can be effectively guided and assisted to conduct effective analysis and exploration on high-dimensional data, the frequencies of tests and errors of the user are significantly reduced in the high-dimensional data processing process, the data redundancy is reduced, the interactivity of the data analysis process is enhanced, and the reliability of the result is improved.

The invention discloses a visual understanding and diagnosis method for an interactive video abstract model, and the method comprises the following steps: carrying out the feature extraction of an original video set, obtaining five descriptive feature scores, taking the extracted features as a verification set, and obtaining a significance score through machine learning training; through the abovesteps, performing interactive visual analysis of multi-feature inspection and multi-level exploration through the video view, the projection view, the detail view and the continuous frame view. A user is helped to explore and analyze video content and internal relations existing in a video abstraction model. According to the invention, data are obtained through a model analysis method, and a visual understanding and diagnosis method of an interactive video abstract model is designed to help understand the internal relation existing in the video abstract model. And a set of visual analysis system is provided to help a user to explore and analyze video contents, and the model is deeply explored from three aspects of videos, events and frames through a video view, a projection view, a sequence frame view and a detail view.

The invention discloses a microscopic visual analysis method for high-density group trajectory data. The method comprises the steps of original trajectory data processing, data statistics and data feature analysis; displaying the feature distribution of the trajectory data in time and space dimensions through a feature statistical view based on the small-multipules, wherein the multi-resolution river view is used for supporting the change of track data displayed from a multi-level aggregation angle; projecting views of the trajectories to reveal correlations between high-density group trajectories; and the multi-level space map being used for displaying the specific distribution condition of the track data. The invention designs a set of interactive visual analysis method, and the method consists of a feature statistics view, a multi-resolution river view, a trajectory projection view and a multi-level space map, so as to help understand the microscopic evolution relation of high-density group trajectory data. And a solution is provided for subsequent microscopic visual analysis of high-density group trajectory data.

The invention discloses a network penetration identification method based on interactive behavior analysis, and the method comprises the steps: employing a Seek client to collect the interactive behavior data of a honeypot machine as an analysis object, carrying out feature extraction and cleaning, feature classification and feature coding on collected data to form a feature sequence; according tothe characteristic that an interactive behavior characteristic sequence has uncertain length and time sequence, adopting an LSTM model as an attack recognition classifier, analyzing an activation function, a loss function and a gradient descent algorithm respectively, selecting an appropriate model to be used as the model, and then optimizing a training model through multiple times of hyper-parameter parameter adjustment. Modeling is carried out according to the time sequence of capturing behavior data features, the features are screened to reduce the feature dimension, and the training speedand precision of the model are improved through feature coding. Through repeated parameter tuning training, the penetration attack identification accuracy and the false alarm rate of the model are obviously superior to those of other models.

The invention relates to a electromagnet data interactive visual analysis method based on VTK. . An electromagnet data interactive visual analysis system is built by using a VTK visual toolkit. Firstly, volume data gray level distribution characteristics are obtained by means of an electromagnet data gray level statistical histogram. The threshold value, opacity and color of the contour surface isset according to the data. The interactive design of multiple equivalence surfaces is realized. A user can explore field intensity distribution of an interested plane through a multi-angle slicing function. An interactive marking function is provided for the user to enable the user to add an analysis result as a three-dimensional mark into a rendering scene. A shadow effect is improved by utilizing an illumination design module to realize multi-view, high-quality and interactive visual analysis of the electromagnet data.

The invention discloses an interactive interface analysis and optimization method related to a visual field position, which can improve the visual search efficiency of an interactive interface and reduce user errors. The visual field position rule, the eye movement index and the interactive interface are combined, a central nest visual area and an auxiliary central visual area are put forward to serve as key areas of a visual search target under task driving, and the visual field position of a target information block corresponding to the task is a key factor of visual search. Therefore, the invention provides an interactive interface analysis and optimization method based on the visual field position. The method includes: Obtaining the size of a display and the sight distance of an operator; Calculating the sizes of the central pit visual area and the auxiliary central pit visual area by using a trigonometric function; Marking a visual area range on the interface; And evaluating the position of the information block based on the visual area range, and performing adjustment. According to the method, the search efficiency can be improved, human errors are reduced, and the security of the interactive interface is improved.