654 results about "Factor analysis" patented technology

A mechanism for discerning user preferences for categories of provided content. A computer receives response data including a set of preference values that have been assigned to content items by content users. Output data is computed based on the response data using a latent factor model. The output data includes at least: an association matrix that defines K concepts associated with the content items, wherein K is smaller than the number of the content items, wherein, for each of the K concepts, the association matrix defines the concept by specifying strengths of association between the concept and the content items; and a concept-preference matrix including, for each content user and each of the K concepts, an extent to which the content user prefers the concept. The computer may display a visual representation of the association strengths in the association matrix and/or the extents in the concept-preference matrix.

A mechanism for facilitating personalized learning. A computer receives graded response data including grades that have been assigned to answers provided by learners in response to a set of questions. Output data is computed based on the graded response data using a latent factor model. The output data includes at least: an association matrix that defines a set of K concepts implicit in the set of questions, wherein K is smaller than the number of questions, wherein, for each of the K concepts, the association matrix defines the concept by specifying strengths of association between the concept and the questions; and a learner knowledge matrix including, for each learner and each of the K concepts, an extent of the learner's knowledge of the concept. The computer may display a visual representation of the association strengths in the association matrix and/or the extents in the learner knowledge matrix.

In certain example embodiments of this invention, there is provided systems and/or methods for processing BAM-related data to predict when events of interest are about to happen and/or to identify the root causes of, or at least data correlated with, such events of interest. In certain example embodiments, key performance indicators (KPIs) are gathered and gardened. The gardening process may identify KPI values of interest (e.g., based on a Z-factor analysis thereof across one or more collection intervals). The gardened KPIs may be processed using a time-series transform (e.g., a Fast Fourier Transform), matched to one of a plurality of predefined waveforms, and fed into a dynamic Naïve Bayesian Network (NBN) for prediction. The gardened data also may be used to determine the relevance of the KPI for root causes of problems (e.g., based on a chi-square analysis).

The embodiment of the invention provides a road traffic safety evaluating method and system. The method comprises: establishing a road traffic safety evaluating model by using a factor analysis mathematic model on the basis of a road traffic safety attribute; acquiring a road traffic safety attribute value corresponding to an appointed road segment in an appointed time segment; and analyzing the road traffic safety attribute value of the appointed road segment by using the road traffic safety evaluating model in order to obtain a road traffic safety evaluated result of the appointed road segment. The method and the system solves a problem that a static road traffic safety evaluated result in the prior art cannot reflect a road traffic safety status in real time. The invention relates to the technical field of computers.

A multi parameter dimension reducing oil gas water layer identifying method, which contains 1, investigating oil reservoir geologic condition, collecting the data of test oil and test production of oil reservoir, 2, determining object reservoir layer of well according to electrical logging comprehensive explanation and logging oil gas display result, 3, selecting reservoir parameter of electrical logging and logging, 4, compiling computer program by statistical mathematics-factor analysis method, combining the liquid producing data of object reservoir, making linear combination and dimension reducing to two main factors, 5, using the established oil, gas and water figure board in step 4 to judge oil, gas and water in oil reservoir and other object reservoir.

A credibility evaluation method of software units of a complex software system includes the following steps: A building a credibility index system; B determining a credibility evaluation comment set; C acquiring an objective weight through factor analysis by aid of SPSS (Statistic Package for Social Science), acquiring a subjective weight with an analytic hierarchy process and determining the final factor weights with a dynamic assignment method; D conducting first-level fuzzy evaluation on credibility of the software units; E correcting the evaluation result through multiple fuzzy composition operators; F iterating the above calculation process to achieve multi-level fuzzy comprehensive evaluation on the credibility of the software units. The credibility evaluation method classifies evaluation indexes, so that an evaluation result is more reliable; acquired index weight values better accord with the practical condition of the software units, so an objective and subjective weight structure can be adjusted dynamically according to different software units; the evaluation result is corrected through the multiple fuzzy composition operators so that the evaluation result is more scientific, accurate and reasonable.

[PROBLEMS] To provide a company evaluation device enabling comprehensive evaluation of a company or industry in an easy way.

[MEANS FOR SOLVING PROBLEMS] The device comprises company index acquiring means (transmission/reception means (365) or the like) for acquiring a company index, comprehensive evaluation index acquiring means (transmission/reception means (365) or the like) for acquiring a comprehensive evaluation index, factor analyzing means (information processing means (380)) for performing factor analysis using the acquired company index and generating a factor, contribution ratio calculating means (information processing means (380)) for performing multiple regression analysis using the factor and comprehensive evaluation index and calculating a contribution ratio concerning the comprehensive evaluation index, and output means (display interface (373) or the like) for outputting the factor, contribution ratio, company index, factor loading, and comprehension evaluation index on display means or the like.

PROBLEM TO BE SOLVED: To provide a production management device capable of reducing man-hour required from discovery of a task to factor analysis in a production system. ŽSOLUTION: A graph display part 16 totals information indicating processing statuses regarding the respective work IDs and performs control for displaying processing status analysis information based on at least one parameter on a display device 2B as an analysis result of processing statuses. When an improvement object specification part 15 accepts input of a parameter value of an event for improvement from a user, a work ID list display part 14 displays a list of applicable work IDs. A work ID/process specification part 13 recognizes a work ID selected by the user from the list of work IDs and a selected process and an image display part 12 displays a pickup image regarding the selected work ID and the process on the display device 2B. Ž

The invention discloses a health prediction method and system for a new energy vehicle battery. The method comprises the following steps that: carrying out data analysis processing on vehicle data obtained in real time to obtain vehicle working condition data; independently executing data cleaning, data conversion and data reduction processing on the vehicle working condition data; on the basis of the vehicle working condition data subjected to data preprocessing, adopting a factor analysis method to extract data which influences a battery health degree, adopting a supervised learning method to mine a potential relationship between the data which influences the battery health degree and the vehicle working condition data, and constructing an initial battery health prediction model; carrying out model evaluation and algorithm optimization on the initial battery health prediction model to obtain an optimal battery monitoring prediction model, and finishing battery health prediction under a practical working condition. By use of the method, the dynamic prediction of the health state of the new energy vehicle battery is realized, the dynamic property and the economy of the vehicle can be improved, and the method has the advantages of being simple in operation and easy in implementation.

The invention relates to a quickly judging method for underground water polluted by organic matter, which comprises the following steps: A) collecting underground water samples in, pollution source areas, the upstream, two sides and the downstream of the pollution source areas; B) filtering collected underground samples, and determining soluble organic carbon concentration; C) converging the three-dimensional fluorescence spectrum matrix data of all underground water samples so as to process parallel factor analysis; and D) judging that the underground water is not polluted if component acquired in the parallel factor analysis does not have fluorescence peaks within a range that an excitation wavelength is larger than or equal to 200nm and is less than or equal to 440nm; and an emission wavelength is larger than or equal to 280nm and is less than 380nm; judging that the underground water is polluted if the component acquired in the parallel factor analysis appears the fluorescence peaks within a range that the excitation wavelength is larger than or equal to 200nm and is less than or equal to 440nm; and the emission wavelength is larger than or equal to 280nm and is less than 380nm, wherein the larger the maximum fluorescence strength of the underground fluorescence component is, the severer the pollution degree of the underground is. According to the invention, the quickly judging method is characterized by little sample quantity, quick analysis and high sensitivity.

A method for synthesizing electrocardiogram leads includes obtaining a sequence of voltage-time measurements for a set of electrocardiogram leads and subjecting the measurements to abstract factor analysis to obtain a set of eigenvalues and associated eigenvectors. A minimal subset of electrocardiogram leads is identified from which the voltage-time measurements can be calculated with acceptable error. Simplex optimization is performed on a subset of the voltage-time measurements measured with the minimal subset of electrocardiogram leads to obtain a universal transformation matrix, and the universal transformation matrix is multiplied by the subset of the voltage-time measurements to calculate the full set of voltage-time measurements. The full set of leads can be used to calculate a body surface map, and the eigenvalues can be tracked in time to predict the onset of pathology such as myocardial infarction.

The present invention discloses a shale gas single well geological comprehensive evaluation method. The method comprises the following steps: stratigraphic division and comparison and sedimentary facies analysis; shale gas reservoir forming condition and main controlling factor analysis; shale fragility analysis; evaluation grading according to a shale gas selection region evaluation parameter table suitable for exploration and development of a research region; and finally, optimization of the layer segments of profitability and the ranges of profitability. Through adoption of the technical scheme, the shale gas single well geological comprehensive evaluation method can objectively and roundly evaluate the shale gas single well geological condition and can provide detailed reference data for well exploitation and geological evaluation of adjacent shale gas single wells and shale gas regions in the later period so as to break the limitation of the current evaluation method, define the shale gas single well geological comprehensive condition and avoid unnecessary waste.

The invention discloses a probabilistic neural network algorithm-based cable state evaluation method. The method includes the following steps that: a multi-source information database is constructed according to many types of information sources such as basic information, operation information, operation inspection information and family defects of cable equipment; and the database under an incomplete information condition is pre-processed by using a factor analysis method, and a probabilistic neural network-based multi-source information algorithm is put forward, and the overall state of a cable under an incomplete information condition can be comprehensively evaluated. With the method of the invention adopted, the fault of a cable can be detected timely and judged accurately, and the operating state of the cable can comprehensively reflected.

The present invention provides a method and a system for inspecting and maintaining equipment. According to the method, an equipment functional part is adopted as an object. After that, an inspection and maintenance strategy, spare part materials, an inspection and maintenance standard, and an inspection and maintenance service process, which are adaptive to the technical characteristics of the equipment functional part, are established. The method specifically comprises the steps of S1, identifying the critical functional part of the equipment; S2, establishing a standing book for the critical functional part; S3, conducting the factor and precautions analysis on the critical functional part of the equipment; S4, according to the factor analysis result, establishing an inspection and maintenance structure; S5, according to the inspection and maintenance structure, establishing the inspection and maintenance operation standard for the equipment; S6, setting the inspection and maintenance service flow; S7, according to the inspection and maintenance service flow, conducting the routine inspection and maintenance on the equipment. According to the technical scheme of the invention, the service management process and the service operation behavior of the equipment are in the controlled state. Therefore, the efficient and stable operation of equipment is guaranteed. The quality requirements of products are met and the safety production is ensured.

The invention discloses a store site selection system and a store site selection method. The method comprises the following steps: determining a trading area range according to the business type of a new store, determining existing stores and residential quarters in the trading area and searching attraction influence factor information of the stores; quantizing the environment in the store by using factor analysis; performing multiple linear regression analysis on the amount of sales of a plurality of stores by using a multiple linear regression formula according to the obtained environment in the store and other collected influence factors, determining the influence degree of each influence factor on attraction in the trading area and taking the influence degree as an adjusting index; calculating the attraction of the new store by using a multi-factor attraction model according to the influence factor and the corresponding adjusting index thereof obtained by regression analysis. According to the system and the method, retail enterprises can very conveniently determine the store customer sources and the distribution characteristics according to the store scales, the environments, the service and the like.

The invention relates to a method for establishment, in particular to a method for establishing a power supplier evaluation model. The method includes the three main steps of designing a supplier comprehensive evaluation index system, determining a comprehensive weight vector based on an analytic hierarchy process and by introducing a factor analysis method, and calculating a supplier comprehensive evaluation value by a fuzzy comprehensive evaluation method. The method proposed by the invention for establishing the power supplier evaluation model not only considers the subjectivity of the comprehensive knowledge of group experts, increases the diversity of the system, but also considers the practicality and objectivity of the index data, and corrects the deficiencies of a traditional fuzzycomprehensive evaluation method, making the whole evaluation system more reasonable. In addition, the method of the invention divides the supplier grade into nine different grades according to the supplier comprehensive score, can provide a certain reference for the bidding and procurement work of power companies, and promotes the intensive management and operation efficiency of the power companies.

The invention provides a method for reducing dimensions of high spectroscopic data based on a factorial analysis model, comprising the following steps: (1) reading in the high spectroscopic data; (2) establishing the factorial analysis model for dimension reduction of the high spectroscopic data; (3) calculating average of data, covariance matrix and correlation matrix; (4) calculating proper value and standard eigen vector of the correlation matrix of the data; (5) carrying out solving on factor loading matrix by a parametric estimation method; (6) calculating covariance of special factors and communality of data variables in the factorial analysis model; (7) calculating the biggest factor loading spin matrix based on variance; (8) calculating factor scores by a least square method based on variance; and (9) obtaining eigen dimensionality characterizing high spectroscopic data, thereby realizing dimension reduction of the high spectroscopic data. The method is an automatic method for dimension reduction of the high spectroscopic data, which can effectively remove relativity of wave bands of the high spectroscopic data and improve separability of different categories of ground objects.

The invention provides a model training method, a cross-age face recognition method and corresponding devices, which are used for improving the accuracy rate of cross-age face recognition, and reducing the complexity of cross-age face recognition. The model training method comprises the steps of: acquiring a universal face database and a cross-age face database, wherein the cross-age face database comprises a plurality of face image groups classified according to identity characteristics and age characteristics of faces; and training a deep convolution neural network model guided by a latent factor analysis model by using the universal face database and the cross-age face database, and outputting the deep convolution neural network model after training is finished.

The invention discloses a test run method for an accelerated life test of a gas turbine engine. The test run method comprises the steps that an accelerated factor analysis model of the gas turbine engine under simulated running conditions is established; according to the accelerated factor analysis model, a support vector machine method is used for establishing a surrogate model of three-dimensional finite element stress analysis; the surrogate model is used for obtaining dangerous point stress of the accelerated factor analysis model, and then life indexes of the accelerated factor analysis model are obtained; a Monte Carlo method is used for conducting stochastic simulation on random variables of the life indexes; an optimal design mathematical model of an accelerated life test scheme of stress under the simulated running conditions of the gas turbine engine is established and analyzed, and the test scheme is optimized according to the optimal design mathematical model; a mixing optimization method is adopted to optimize the mathematical model, and the optimized accelerated life test scheme is obtained according to the optimized mathematical model. By means of the test run method, the test period is shortened, and life test expenditure is reduced.

The invention discloses a precipitation prediction method based on a deep network. The precipitation prediction method comprises specific steps as follows: collecting hydrological environment data, preprocessing the data and normalizing the data in a 01 interval; detecting the sufficiency of environmental factors by using KMO test and Bartlett sphericity test, and screening the environmental factors with a factor analysis method after test; using a divided training sample as an input value of the deep network, subjecting the network to hierarchical unsupervised learning and then performing reverse fine adjustment on the whole network by use of a top BP network to guarantee the precision; using a test sample as the input of a trained model and inversely-normalizing the output obtained from the model to obtain the predicted result of precipitation. The precipitation of an area in the future can be predicted more accurately, the factors with lower correlation are screened out with the factor analysis method, the calculation efficiency is improved, and the scientificity and reasonability of the precipitation prediction process are greatly enhanced.

The invention provides a social network rumor detection method based on content and user multi-factor analysis. The method comprises the steps that firstly, a text information case is obtained, and text information and user information of the text information case are obtained; secondly, text content feature models of the text information case are built according to the text information, wherein the text content feature models comprise a keyword matching model, an emotion tendency model, an emotion fluctuation model, a theme clustering matching model and a content influence evaluation model; thirdly, user feature models of the text information case are established according to the user information, wherein the user feature models comprise a content consistency judgment model and a user influence evaluation model; fourthly, feature vectors are constructed according to the text content feature models and the user feature models, a classifier trained, the feature vectors are input into the classifier, a result is output, and a social network rumor is recognized. The method is used for conducting detection without depending on a single feature, misidentification is avoided, and the detection precision is improved.