588 results about "Data normalisation" patented technology

The invention relates to a large-scale distributed network safety data acquisition method and system. The method comprises the steps of multimode data acquisition, data analysis and standardization and data distribution and transmission. The system comprises an acquisition agent module, a data acquisition module, a data analysis module and a data distribution and transmission module. With respect to data acquisition, multiple modes such as an active mode, a passive mode and a data stream mirror image mode are adopted, and comprehensive acquisition of various types of data is realized; with respect to data analysis, a data analysis and standardization mechanism based on strategies is adopted, original data are extracted, mapped, replaced, supplemented and the like by means of writing analysis strategies, and therefore quick analysis of a newly added data format and data standardization oriented to multiple application systems are realized; with respect to transmission, the multi-stage connection technology and the multi-path distribution technology are adopted, elastic combination, cascading deployment and multi-path distribution between acquisition systems are realized, and the requirements for vertical and horizontal expansion of a network environment and acquisition of mass data information are met.

A system, method and program product for normalizing, sanitizing and disambiguating structured data. Structured data includes data stored in a database management system (DBMA), as well labeled files (e.g., XML data). An automated data enhancement processing system is provided, comprising: a system for ingesting data structured in at least one predefined database format; and a set of text analytics processes that treat the ingested data as unstructured, and generate normalized data represented and indexed by consistent, structured metadata.

A battery monitoring system may be configured to interface with a first battery monitoring unit and a second battery monitoring unit. The first battery monitoring unit may be configured to output data in a first format. The second battery monitoring unit may be configured to output data in a second format, the second format being different than the first format. The battery monitoring system may include a first polling agent, the first polling agent may be configured to receive data from the first battery monitoring unit and normalize the data into a predetermined data format and store the data in a database. The battery monitoring system may also include a second polling agent. The second polling agent may be configured to receive data from the second battery monitoring unit and normalize the data into the predetermined data format and store the data in a database. Furthermore, the battery monitoring system may be configured to output data associated with the condition of a respective battery unit coupled to at least the first battery monitoring unit and the second battery monitoring unit.

The invention relates to a fusion platform and a fusion method of heterogeneous multi-source data. The fusion platform includes a data collection unit, a data storage unit, a data standardization unit, a user portrait building unit, a knowledge graph building unit and a visualization unit. The data collection unit is used to collect the heterogeneous multi-source data. The data storage unit is used to cache the heterogeneous multi-source data. The data standardization unit carries out lexical, grammatical and/or semantic analysis on the heterogeneous multi-source data to obtain standardized text data. The user portrait building unit utilizes student tags, which are obtained by quantification, to build user portraits of students. The knowledge graph building unit builds knowledge graphs ofthe students, knowledge graphs of teachers and knowledge graphs of courses, and associates the knowledge graphs of the courses, the knowledge graphs of the students and the knowledge graphs of the teachers to obtain course links, social relationships and teacher-student relationships taking the students as centers. The visualization unit shows the course links, the social relationships and the teacher-student relationships taking the students as the centers.

A data infrastructure for graph-based computing that combines the natural language expressiveness of the Semantic Web and the mathematical rigor of graph theory to discover meaningful associations across multiple sources towards computer-assisted serendipitous insight discovery. The process automatically integrates massive size datasets accessed using Semantic Web standards and technologies and normalizes data in graphs. The process generates a plurality of conditional probability distributions based on type-triple meta-data and triple statistics to model saliency and automatically construct and evaluate a plurality of sub-graphs based on the plurality of conditional probabilities for contextual-saliency. The process then renders a plurality of paths (i.e. sequence of associations) that model meaningful pairwise relations between objects of the normalized integrated data. The pluralities of conditional probabilities reveal and rank previously unknown associations between entities of user-interest in the knowledge graph.

The invention provides an industrial soft gateway based on multiple access and edge computing and an implementation method. The industrial soft gateway comprises a configuration interaction module, adata collection module, a data edge computing module and a data sending control module, wherein the configuration interaction module comprises a connection configuration module and a data standardization module; the data collection module is used for a multiple access collection method; the data edge computing module is used for carrying out real-time computing on the data collected by the data collection module; and the data sending control module is used for carrying out caching and task scheduling and allocation of external forwarding on all data to be sent. According to the industrial softgateway based on multiple access and edge computing and the implementation method, a visual interface is arranged to provide connection configuration and standardized operation for various communication protocols and databases, and meanwhile, a graphical monitoring interface of a data collection state, an edge computing result and a forwarding state is provided. Data standardization can be realized, the data noise can be eliminated and the data features can be extracted through the edge computing module, the network transmission data volume of a data cloud platform is reduced, and the data transmission efficiency is improved.

The invention discloses a heart sound signal classification method based on a convolutional recurrent neural network. The method comprises the following steps: performing noise processing on heart sound data; extracting heart sound characteristics of the heart sound signals; standardizing the data; constructing a convolutional recurrent neural network model; training the constructed neural networkby using the training sample data characteristics, and storing the trained network structure and parameters; and testing the test sample data by using the trained model parameters to obtain a final classification and identification result. According to the invention, the system complexity is reduced; the extracted heart sound characteristics do not need to segment heart sound signals; according to the heart sound signal classification method based on the convolutional neural network, the convolutional neural network and the recurrent neural network are connected in series, a deep learning model with the processing advantages of the convolutional neural network and the recurrent neural network is provided, better expressive force is provided for heart sound signal classification, and an effective and convenient tool is provided for detection of normal and abnormal heart sound signals.

The invention provides a mechanical equipment intelligent fault diagnosis method based on a partial migration convolutional network. The method comprises: collecting operation data of mechanical equipment under different operation working conditions; constituting data sets, taking part of data in the data set X as a source domain training sample set and a target domain test sample set; performingdata standardization on each piece of sample data; training two one-dimensional convolutional neural network models with the same structure and different initialization parameters by using the sourcedomain training sample set, and correcting the two trained convolutional neural network models based on the target domain test sample set to obtain a convolutional neural network mechanical equipmentfault diagnosis model; and performing fault diagnosis on the mechanical equipment based on the real-time operation data by using the fault diagnosis model to output a fault type. The method can be effectively used in more real mechanical fault diagnosis, that is to say, the label-free property of the target domain is considered, so that the trained diagnosis model can better diagnose faults of mechanical equipment.

The invention discloses an application platform system of a tobacco commercial system, which comprises an access layer module, a presentation layer module, a service application layer module, a flow integration layer module, an application integration layer module, a data integration layer module, an application support layer module and a foundation support layer module, wherein the access layer module is used for uniformly providing an access service by utilizing a door component of an application platform; the representation layer module is used for uniformly assembling and representing all functions of each application system of the tobacco commercial system based on the functions of the application door component; the service application layer module is used for splitting application into components to form an application component pond; the flow integration layer module is used for providing an enterprise service bus and a service flow integration engine; the application integration layer module is used for realizing the component-based development of the application system; the data integration layer module is used for realizing the integration of the application on a data layer, uniformly managing basic service data, such as service codes and the like, realizing metadata management and data standardization, improving data quality, normalizing and realizing a data exchange and sharing mechanism, and establishing a database and a data quality management system; the application support layer module comprises a basic application server, a database server and message middleware software; and the foundation support layer module is used for providing server equipment, various infrastructures and matched system monitoring and management system software.

The invention discloses a time-of-use electricity price determining method based on load characteristic classification. The method comprises the following steps that data standardization preprocessing is carried out; data after preprocessing are subjected to clustering analysis through a fuzzy c mean value clustering algorithm, and average power load curves of various power consumers are obtained; the power load curves of all the power consumers are divided according to peak-common-trough periods; the demand response degree is analyzed; the power utilization influence degree is analyzed; and according to the demand response degree and the power utilization influence degree of various power consumers, a time-of-use electricity price adjusting mode is determined, the adjusting principle is that the peak-trough electricity price difference ratio and the demand response degree of various power consumers are in inverse relation, and the peak-trough electricity price difference ratio and the power utilization influence degree is in direct ratio relation. Power load data are subjected to clustering analysis, power consumers are classified according to the load characteristics, time-of-use electricity price based on power consumer load characteristic classification is achieved, and important effect is achieved on traditional time-of-use electricity price adjusting.

The invention discloses a vehicle following safety automatic assessment method based on machine learning. The vehicle following safety automatic assessment method comprises the steps that data are acquired; data cleaning is performed on the acquired data, the data meeting the requirements are reserved, and the data are standardized and normalized in the same data set D; extraction and modeling of the required feature fields are performed on the cleaned data; modeling data M used for machine learning are extracted from the cleaned and normalized data according to accident records and relevant monitoring data; the M set is randomly extracted and divided into two subsets MT and ME according to the given proportion, MT is used for model training, and ME is used for model performance verification testing; supervised classification and machine learning algorithms are adopted, modeling learning is performed by utilizing training data MT, the obtained model performance is verified by ME data and relevant confusion matrix and model classification accuracy is calculated; the results of each time are recorded and compared, and an optimal model is selected; and all the records in the data set D are automatically assessed by using the optimal model, and the results are appended to the data set D and the results are outputted.

The invention discloses a method for multi-sensor adaptation and real-time data acquisition of a wearable device. The method comprises the following steps that S1 Bluetooth device adaptation, namely a Bluetooth device develops a broadcast packet feature recognition module, a control interface module and a data standardization module; S2 device binding, namely a cloud server establishes a binding relationship between a user ID (Identification) and a device ID in a database; and S3 concurrent real-time acquisition of multi-sensor data, namely a user logs in to the cloud server on a mobile intelligent terminal to obtain a list for the bound devices, the mobile intelligent terminal opens Bluetooth scan and compares the device ID of each Bluetooth device discovered through scanning with the ID of the bound device, a new device thread is created if matching and a connection is established. The method has the beneficial effects that real-time acquisition of the cross-manufacturer multi-sensor data is realized, real-time processing requirements for the multi-sensor data are met, and real-time concurrent acquisition of the multi-sensor data is realized.

The invention discloses a micro-service-based real-time calculation system for a traffic environment and a realization method thereof. A presentation layer receives a user request operation and sendsa request to an API gateway layer; the API gateway layer performs service discovery and matching by calling a micro-service management layer and calls a micro-service layer for service; a micro-service activates a data collector to collect traffic social data in real time; a data standardization engine standardizes the collected data and transmits the collected data to a distributed message engine; the distributed message engine transmits the standardized data to a flow processing engine, and the flow processing engine sends an accident object result to the distributed message processing engine; and the distributed message engine feeds back an output result to the micro-service layer, and the presentation layer obtains the result from the micro-service layer by calling a corresponding API.A model is abstracted to form an independent layer; the advantage of a domain-driven design method in coping with complex business expansion can be applied; and the running efficiency of a software system can be improved.

A method of identifying a network of actors within a data set, the method comprising: —importing data from one or more data sources; —normalising the data in one or more fields to create a consolidated data set; —identifying one or more networks based on identical or similar instances of one or more pieces of data in the consolidated data set; and —calculating a measure of influence of one or more of the actors in an identified network.

The invention relates to a large data visualization analysis and processing system for enterprise operation data analysis, which is characterized by comprising a data source judgment module, a data collection module, a data storage module, a data cleaning module, a data standardization processing module, and a background task scheduling module, wherein the data source judgment module is used for judging a data source for adopting a corresponding data collection mode; the data collection module collects data according to the corresponding data collection mode; the data storage module stores the data collected by the data collection module into to-be-cleaned data; the data cleaning module carries out data cleaning on the to-be-cleaned data and generates already-cleaned data; the data standardization processing module carries out standardization processing on the already-cleaned data, and a public navigation field is generated and stored to a data pool; and the background task scheduling module calls a built analysis model to analyze the data in the data pool and generates a visualization analysis result report. Compared with the prior art, the system of the invention has the advantages that the working efficiency is improved, cross-system data analysis is supported, secrecy is high and the like.

The invention discloses an intelligent monitoring and early warning system for converter station equipment. The system comprises a data acquisition module, a data preprocessing module, an equipment fault prediction module and an equipment early warning module. The data acquisition module is used for acquiring the state data of the converter station equipment; the data preprocessing module is usedfor carrying out intelligent trend classification, missing value intelligent filling, abnormal value processing and data standardization processing on the data of an equipment state sensor; the equipment fault prediction module is used for carrying out data feature selection on the standardized data obtained by the data preprocessing module, and training, predicting and evaluating equipment parameter monitoring data through an LSTM network according to data features; and the equipment intelligent early warning module is used for comparing a fault threshold expert knowledge base with an outputequipment state prediction result and carrying out intelligent early warning on the equipment. According to the method, the relation between historical monitoring data and different monitoring data ofthe converter station equipment is effectively utilized, an intelligent monitoring and early warning system of the converter station equipment is established, and timely early warning of equipment state parameters is achieved.

The invention provides a method and device for data standardization processing of medical big data and relates to the technical field of medical entity identification. The method comprises the steps that a first group of candidate entities of a to-be-processed statement is determined according to an entity mark sequence of the to-be-processed statement; word extraction is conducted to the to-be-processed statement according to a preset medical noumenon term word extraction strategy, so a second group of candidate entities can be determined; entities in the to-be-processed statement are determined from the first group of candidate entities and the second group of candidate entities; screening is conducted according to preset syntactic analysis and screening rules, so a candidate standardization term in the to-be-be-processed statement can be determined; if the candidate standardization term in the to-be-processed statement can match a preset medical noumenon term library, the candidate standardization term in the to-be-processed statement can be determined as the standardization term; and if the matching fails, a matching failure problem report will be generated, or fuzzy matching will be conducted to the candidate standardization term which is not matched and belongs to a disease term type, so the standardization term can be determined.

A distributed ecological intelligent internet pension service system comprises a government-level multi-department unified command and supervision layer, a region-level central management and control layer, a community-level service guarantee layer and a user terminal function layer. The user terminal function layer acquires user health basic data and sends the data to the region-level central management and control layer; the region-level central management and control layer receives the data and community comprehensive service guarantee service configuration information, builds a user database according to the information, generates region user group reports and distributes the reports to corresponding organizations; the government-level multi-department unified command and supervision layer sends related decisions and instructions to the region-level central management and control layer. The distributed ecological intelligent internet pension service system is an intelligent service system based on the internet of things, the internet and pension, and has the advantages of data standardization, structure networking, system self-evolution, operation disintermediation, high information security degree and the like.

The invention provides a pseudo-acoustic curve construction method based on nonsubsampled Contourlet transformation. The method comprises the following steps: reading logging data; carrying out pretreatment on read logging data curves, wherein the pretreatment comprises curve correction, data standardization and normalization processing; carrying out multistage nonsubsampled Contourlet transformation on the logging data curves respectively, carrying out weight fusion according to a coupling degree between the logging data curves so as to generate a high frequency fusion curve and a low frequency fusion curve; carrying out nonsubsampled Contourlet inverse transformation on the high frequency fusion curve and the low frequency fusion curve so as to generate a pseudo-acoustic curve.