122 results about "Analysis Dataset" patented technology

The invention provides a method and device for characterizing a vehicle's fuel efficiency and amount of fuel consumed. The method features the steps of: 1) generating a data set from the vehicle that includes vehicle speed, odometer calculation, engine speed, load, mass air flow; 2) transferring the data set to a wireless appliance that includes i) a microprocessor, and ii) a wireless transmitter in electrical contact with the microprocessor; 3) transmitting a data packet comprising the data set or a version thereof with the wireless transmitter over an airlink to a host computer system; and 4) analyzing the data set with the host computer system to determine a status of the vehicle's fuel efficiency.

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.

The invention discloses a multi-source data fusion system and method. The multi-source data fusion system comprises a data source subsystem used for acquiring multi-source data, a scene rule base used for storing a scene rule based on different scenes, a data fusion subsystem used for fusion of the multi-source data so as to form an analysis data set, correlating to the analysis data set according to the scene rule, and outputting a fusion database based on the scene rule, and a fusion database subsystem used for storing the fusion database based on the scene rule. By the adoption of the system and method, data fusion requirements in different scenes can be met, data fusion effectiveness is improved, and accurate data information service can be provided for requirements of different scenes.

The invention discloses a method for extracting internet service flow characteristics. A plurality of distributed flow acquirers are arranged and used for acquiring, selecting and purifying an original data sample, uploading the original data sample, and storing the original data sample in a flow data server; on the basis of pure data which is obtained, a flow characteristic extractor extracts or generates network service flow characteristics and establishes a service flow characteristic base so as to manage and maintain the service flow characteristics; and the flow characteristic extractor also selects appropriate service flow characteristics to assist a researcher or a network manager in further analysis, and provides the appropriate service flow characteristics for deep packet inspect (DPI) equipment. The method is innovated and improved in terms of methods for generating and purifying a database to be analyzed and a standard database, and maintaining a characteristic base. The method is simple and easy to operate. The service flow characteristics of a plurality of application programs can be effectively maintained and dynamically optimized and selected; an inclusive relationship between different service flow characteristics can be reflected, and the characteristics of characteristic sequences, in the same service flow, of a plurality of characteristics are represented; and the method has a good popularization application prospect.

The invention relates to the technical field of trend analysis and fault diagnosis of industrial equipment, and aims to provide an equipment state trend analysis and fault diagnosis method which comprises the following steps: acquiring historical operation parameters of equipment to be diagnosed; preprocessing the historical operation parameters to obtain an analysis data set; establishing a trend algorithm model according to the analysis data set; obtaining current operation parameters of the equipment to be diagnosed, inputting the current operation parameters into the current trend algorithm model, and comparing the current operation parameters with preset normal state parameters to obtain the degradation degree of the equipment to be diagnosed; and obtaining a prediction trend curve according to the current trend algorithm model, and obtaining a predictive maintenance time window according to the prediction trend curve, the current operation parameters and a preset standard limit value. The equipment state can be monitored in real time, an equipment user can master the accurate operation condition of the equipment conveniently, and meanwhile, an enough time window is provided for follow-up maintenance of the equipment.

The invention discloses a mixed isolated island detection method. On the basis of mixing of artificial intelligence, voltage and frequency positive feedback of a decision tree (DT), the method based on artificial intelligence of the decision tree measures and stores characteristic quantity indexes of default events of selected target positions, information of a data collection is extracted and analyzed to train a DT classification device, and the operation state of DG (Distributed Generation) is judged to be whether network operation or isolated island operation through comparing the former data collection with a data collection in the case of pre-specified events. According to the method, on the basis of the DT method, the inverter control-based positive feedback method is further combined, complementarity and compatibility are strong; through introducing positive feedback disturbance, the characteristic quantity indexes can be obviously distinguished in the case of isolated island operation of the system and the network operation, judging the isolated island by the DT method is facilitated, and through increasing difference of the characteristic variable parameters in the case of isolated island operation or non-isolated island operation, the error rate of isolated island detection is thus reduced, and reliability of isolated island detection is improved.

The invention discloses a financial service management information platform which comprises a foundation platform and an application platform. The financial service management information platform can realize cross-system and trans-department data information sharing on the basis of finishing basic data merging and integration of each legal person organization. Data application marts having different service themes are established through a unified data view, the data application marts comprising a business report data mart, a business index system and business analysis data marts having different topics. Therefore, service level of a rural credit system is improved, and wisdom cooperation financial service is realized under the premise of guaranteeing the system to have good expansibility, safety and stability and high availability.

Embodiments of the invention relate to a computer-implemented method and system for providing personalized recommendations for a target user based at least on stored data about the target user. The method comprises obtaining a plurality of feedback data from a plurality of users, wherein the feedback data comprises an indication of a media object, a response obtained from target user related to the feedback data, and at least one demographic data element associated with the target user. A set of personalized recommendations for the target user are identified based at least on stored data about the target user and the feedback data related to the user. The personalized recommendations system identifies media objects to potentially provide to the target user, and selects or filters the identified media objects to form a set of personalized media objects associated with the set of personalized recommendations.

Learning machines, such as support vector machines, are used to analyze datasets to recognize patterns within the dataset using kernels that are selected according to the nature of the data to be analyzed. Where the datasets possesses structural characteristics, locational kernels can be utilized to provide measures of similarity among data points within the dataset. The locational kernels are then combined to generate a decision function, or kernel, that can be used to analyze the dataset. Where an invariance transformation or noise is present, tangent vectors are defined to identify relationships between the invariance or noise and the data points. A covariance matrix is formed using the tangent vectors, then used in generation of the kernel.

Methods and systems are provided to determine suitable hyperparameters for a machine learning model and / or feature engineering process. A suitable machine learning model and associated hyperparameters are determined by analyzing a dataset. Suitable hyperparameter values for compatible machine learning models having one or more hyperparameters in common and a compatible dataset schema are identified. Hyperparameters may be ranked according to each of their respective influences on a model performance metrics, and hyperparameter values identified as having greater influence may be more aggressively searched.

The claimed invention relates to a system and method for generating actionable intelligence and information by utilizing a multi-sensor, multi-temporal; multi-spatial, multi-format data (mSTSFA) architecture stored in a NoSQL data architecture to qualify spatial (accuracy) and contextual information integrated into a real time Engineering Grade location based analysis and predictive analytics engine returning users based queries in a 3D visualization including Virtual Reality (VR) / Augmented Reality functionality. The present invention is a systemized platform for handling geospatial, geophysical, financial, temporal and attribute data input directly to analyze the datasets to serve the operational and business needs of the industries such as transportation, water, environmental, engineering, telecommunication, finance, energy, natural resources, defense and security.

The invention provides a semantic analysis data hashing storage method for an input system, which comprises the following steps: 1) presetting a key mapping table so as to establish mapping relationships among code elements and numbers in each key; 2) establishing a data set where the mapping relationships exist between first information and second information and setting a key value for each record; 3) allocating a plurality of storage areas of which each correspondingly stores one key value list; 4) analyzing the code elements of the first recorded information in the data set, converting the first information into a numeric string according to the mapping relationships in the key mapping table and converting the numeric string into pointer identifiers of a corresponding number pointing to the plurality of storage areas according to preset splitting rules; and 5) storing the key values of the records subjected to the pointer identifier conversion into the key value lists of the storage areas pointed by the pointer identifiers. In addition, the invention also provides a corresponding analysis method. The methods have the advantage of laying the foundation for improvement on the intelligence of a human-computer interaction system.

The invention discloses a relation visual attention mechanism-based scene graph generation method and mainly aims to solve the problem that redundant relation prediction and interpretability are poorin the prior art. According to the embodiments of the invention, the method includes the following steps of: 1) obtaining the category and boundary frame of targets in images through target detection,and establishing a full-connection relation graph; 2) carrying out sparsification on the relational graph through analyzing a data set to obtain sparse relational graph representations; (3) learninga relation attention transfer function through alternate iteration, transferring subjects and objects to relation occurrence sites through union set features, and learning accurate relation representations; and 4) classifying the learned relation representations, and combining the relation representations into a final scene graph. According to the method, on the basis of the internal relationshipof the relation occurrence of two targets, a relation attention mechanism is established to accurately pay attention to a region where relations occur; a scene graph is accurately generated; the interpretability of a network is improved; and the method can be used for image description and visual question and answer tasks.

Various systems, methods, and processes to analyze datasets using heuristic-based data analysis and prioritization techniques to identify, derive, and / or select subsets with important and / or high-priority data for preferential backup are disclosed. A request to perform a backup operation that identifies a dataset to be backed up to a storage device is received. A subset of data is identified and selected from the dataset by analyzing the dataset using one or more prioritization techniques. A backup operation is performed by storing the subset of data in the storage device.

The invention relates to an identification method of the zero error of a wind vane of a wind turbine generator. The identification method includes the steps that operation data of the wind turbine generator in a demand period are read as an initial data set; operation data at the time of normal operation of a yaw control system are screen out from the initial data set as the data set to be analyzed; the data set to be analyzed is divided into N subsets at a certain yaw error interval; the quantized power performance index of each subset is calculated separately; the subset corresponding to themaximum value of the quantized power performance index is taken, and the upper bound and the lower bound of the yaw error are selected in the subset and averaged, that is, an identification value ofthe zero error of the wind vane of the wind turbine generator. The identification method is based on data driving, has high universality, scalability and portability, has great economic value and application significance for improving the performance of wind turbine generators, and has high theoretical research and practical application value on improving the power generation performance of wind turbine generators based on data analysis means.

The invention discloses a data authorization method and device based on hierarchical classification. The method comprises the following steps: establishing a level rule base and a category rule base,analyzing according to attribute characteristics of data items in a data source in combination with the level rule base to obtain content sensitivity levels of the data items, and determining a data source level, a field permission range set corresponding to a user and a first permission range data set according to the content sensitivity levels; analyzing according to the data resource identifierof the data source to obtain a category analysis data set and a classification dimension data set, and determining an authority set of the data source according to data item categories and hierarchies in the classification dimension data set; judging to obtain an authority set of the data item according to the hierarchy of the two associated fields in the field authority range set of the data item; comparing the level of the user with the authority set of the data source and the authority set of the data item to obtain a data range set and a second authority range data set of the user; and combining the first permission range data set and the second permission range data set into a permission range set of the user.

The invention discloses an MWHTS clear sky observation brightness temperature selection method based on cloud water content inversion, and the method comprises the steps: building the matching data ofan MWHTS observation brightness temperature and a climate data set in time and space, calculating a corresponding MWHTS simulation brightness temperature, and forming an analysis data set and a verification data set; taking the cloud water content 0 in the analysis data set as a strict clear sky threshold, selecting the MWHTS strict clear sky observation brightness temperature, and adjusting thestrict clear sky threshold by taking the calculation precision of the MWHTS simulation brightness temperature under the strict clear sky as a standard to form a corresponding clear sky threshold; based on the analysis data set and the BP neural network, establishing an optimal inversion model of MWHTS observation brightness temperature inversion cloud water content; using the MWHTS observation brightness temperature in the verification data set to invert the cloud water content, and selecting the MWHTS clear sky observation brightness temperature according to the cloud water content inversionvalue and the clear sky threshold. According to the method, the MWHTS observation brightness temperature can be directly utilized to realize effective selection of the MWHTS clear sky observation brightness temperature, the accuracy is high, and the operation is simple and feasible.

The invention discloses an MWHTS simulation brightness temperature calculation method based on a deep neural network. The MWHTS simulation brightness temperature calculation method comprises the steps: establishing a matching data set of an MWHTS observation brightness temperature and a climate data set in space and time; dividing the matching data set into a clear sky data set, a cloud data set and a rain data set according to the cloud water content, and respectively forming a corresponding analysis data set and a corresponding verification data set; training a deep neural network model by utilizing the three analysis data sets, inputting atmospheric parameters in the corresponding verification data sets into the trained deep neural network model, and calculating MWHTS simulation brightness temperature; inputting the atmospheric parameters in the three verification data sets into a radiation transmission model to calculate the MWHTS simulated brightness temperature, comparing the calculation precision with the MWHTS simulated brightness temperature calculation precision based on the deep neural network, and selecting MWHTS channels with higher precision to form an MWHTS simulatedbrightness temperature calculation result. According to the method, the interaction between microwaves and atmospheric molecules is modeled by using the deep neural network, the calculation precisionhigher than that of a business radiation transmission model RTTOV is obtained, and the operation is simple and easy to implement.

The invention provides a data analysis method and device. The data analysis method comprises the following steps of: classifying data according to a preset event classification strategy; event classification is carried out on to-be-analyzed data in the to-be-analyzed data set; obtaining event datasets, then, according to a preset service type classification strategy, classifying the service types;performing service type classification on to-be-analyzed data in the event data set; obtaining traffic type datasets, mapping a decision library and an influence result library according to the service type data set; extracting decision behaviors and influence results contained in to-be-analyzed data in the service type data set; According to a preset semantic analysis strategy, obtaining an influence result corresponding to the extracted decision behavior, and for each event, constructing a knowledge graph of the event by taking the event, the service type corresponding to the event, the extracted decision behavior and the extracted influence result as nodes. And the data analysis efficiency can be improved.

The invention discloses a user data classification method and device based on Internet of Things data, computer equipment and a storage medium, is applied to the field of smart medical treatment of smart cities, and relates to data processing and block chains. The method comprises the following steps: after receiving current user medical data uploaded by an Internet of Things medical terminal, a the cloud server forms a to-be-analyzed data set according to the medical data of the current user and other key data corresponding to the current user and retrieved in the cloud server; and by takinga convolutional neural network stored in a cloud server as an operation model of input data composed of the current user medical data and the key data, a classification result is obtained and an optimal treatment path is determined. According to the method, rapid acquisition of the user medical data based on the Internet of Things equipment is realized, the optimal treatment scheme data is rapidlyand accurately recommended based on the historical medical data, and the cost of acquiring the optimal treatment scheme data is reduced.

The invention provides a malicious URL detection method and system. The malicious URL detection method comprises the steps of obtaining a URL to-be-analyzed data set, and obtaining a malicious URL training sample set; utilizing the malicious URL training sample set to train an SVM support vector machine to classify the URL to-be-analyzed data set to obtain a malicious URL data set and a to-be-labeled URL data set; clustering the to-be-labeled URL data set by adopting a clustering algorithm to obtain a to-be-labeled URL sample set; marking the to-be-marked URL sample set according to a malicious judgment result so as to divide the to-be-marked URL sample set into a marked malicious URL sample set and an unmarked URL sample set; combining the marked malicious URL sample set and the maliciousURL training sample set in a set union solving mode to obtain an updated malicious URL training sample set; and subtracting the marked malicious URL sample set from the to-be-marked URL data set to obtain an updated URL test data set. The malicious URL detection method and system are novel in design and high in practicability.

The invention discloses a construction method and prediction method of an industry electric quantity demand prediction model. The construction method of the industry electric quantity demand prediction model comprises the steps that: the first leading factor of industry electric quantity increase is obtained according to a set industry electric quantity correlation analysis program, wherein the industry electric quantity correlation analysis program is a combination of a correlation rule mining program and a principal component analysis program; according to a pre-established historical industry electric quantity correlation analysis data set, the second dominant factor of the industry electric quantity increase is extracted; and according to the first dominant factor and the second dominant factor, an ARIMA model and the multiple regression model are corrected and coupled, so that the industry electric quantity demand prediction model is obtained. Compared with a traditional method, the method has the advantages of greatly improved prediction precision, high applicability and feasibility, can be popularized to other industries.

Embodiments of the invention relate to a computer-implemented method and system for generating personalized recommendations for a target user based at least on stored data about the target user. The method comprises obtaining, at the server computer, data from a plurality of data sources, including entity data associated with a plurality of entities, stored in an entity database, or personal data associated with a plurality of users, stored in a user database. The personalized recommendations system then merges the entity data or personal data and maps the entity or personal data to a corresponding entity or target user, respectively. The entity or personal data is differentiated, a relevance is determined, a weight is assigned to the data and corresponding source to canonicalize the data, the respective databases are updated with the corresponding data, and then a set of personalized recommendations to the target user is generated using the updated databases.

A method employing pattern recognition techniques for identifying the functional status of patients with Pulmonary Hypertension is described. This method describes a process by which sets of cardiopulmonary exercise gas exchange variables are measured during rest, exercise and recovery and stored as unique data sets. The data sets are then analyzed by a series of feature extraction steps, yielding a multi-parametric index (MPIPH) which reflects the current functional status of a patient. The method also employs a description scheme that provides a graphical image that juxtaposes the measured value of MPI to a reference classification system. An additional description scheme provides a trend plot of MPI values measured on a patient over time to provide feedback to the physician on the efficacy of therapy provided to the patient. The method will enable physicians to gather, view, and track complicated data using well-understood visualization techniques to better understand the consequences of their therapeutic actions.

The invention discloses a chart document panel analysis and understanding method, which comprises the following steps of: collecting an initial chart document, and analyzing the initial chart document to obtain a chart analysis data set; constructing a key point segmentation model, and obtaining the position coordinates of the scale points based on the chart analysis data set and the key point segmentation model; constructing a multi-target detection model, carrying out legend position detection based on the multi-target detection model, and obtaining legend positions; and analyzing the position coordinate of the scale point and the legend position based on a matching rule of the scale point and the scale value of the rectangular expansion and a matching rule of the legend and the label of the maximum intersection-to-union ratio to obtain an analysis result of the chart document panel. According to the method provided by the invention, the problem of panel understanding of the chart document is efficiently and accurately solved, and the method plays an important positive role in realizing automatic data extraction and content understanding of the chart document by a machine.

Disclosed are a method and system for propagating data changes in a hierarchy of dataset models in which each dataset model comprises an analytic and one or more parent datasets, including a primordial dataset. The analytic is executed to instantiate a first instance of the data model. After a change in a primordial dataset, each instance of a dataset model that descends from the primordial dataset is invalidated, and the analytic is re-executed to create a second instance of the data model. Analytical results may be displayed. The first dataset model may include a metric in which the definition of the metric comprises metadata of the dataset model. Metric values may be stored in a first cache, re-computed on a new instance of the dataset model, and stored in a second cache.

The invention discloses a big data prediction analysis method, system and device and a storage medium. The method comprises the steps of collecting data to obtain a data set; generating a corresponding rule by using a rule fitting algorithm; performing regularization processing on the original attributes of the data in the data set; generating a prediction model according to the corresponding rules and the original attributes; calculating parameters of the prediction model; obtaining a weight value set of the prediction model according to the parameters; and calculating to obtain a corresponding prediction analysis result according to the weight value set. According to the invention, a unified and effective prediction analysis method is provided for each industry analysis data set according to the characteristics of the industry data set; relationships and rules existing in data are discovered through a big data analysis method, and the future development trend of things is predicted,so that the scientificity of decision making can be improved; meanwhile, enterprises can be helped to analyze future data information, and risks are effectively avoided. The method is widely applied to the technical field of data mining.

The invention provides a medication decision-making method and system based on deep learning. The method comprises the following steps: collecting patient-related information, medication scheme-related information and actual curative effect evaluation information of a medication scheme on an actual curative effect of a patient to obtain an analysis data set; analyzing and processing the analysis data set through a constructed curative effect prediction model so as to predict predicted curative effect evaluation information of each medication scheme for different patient treatment effects; andrecommending the medication scheme suitable for the personalized requirements of the patient to the patient according to the predicted curative effect evaluation information. The medication decision-making method and system have high accuracy and stability during medication scheme recommendation, and are suitable for medical clinical application.

A method, apparatus, and computer program product for digitally presenting statistically-relevant business insights into a set of business metrics for an organization. A computer system identifies a set of organizational characteristics from human resources data of employees of a plurality of organizations, and applies a selected inclusion criteria to the set of organizational characteristics to identify a set of candidate organizations. The computer system identifies a set of benchmark organizations from the set of candidate organizations, and creates a fixed panel of the benchmark organizations. The computer system applies the fixed panel to the human resources data of employees of a plurality of organizations to create an analysis dataset that consists of human resources data of employees of the benchmark organizations. The computer system generates a business insight into the set of business metrics of the organization based on the analysis dataset, and digitally presents the business insight.