Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

195 results about "Expected value of sample information" patented technology

In decision theory, the expected value of sample information (EVSI) is the expected increase in utility that a decision-maker could obtain from gaining access to a sample of additional observations before making a decision. The additional information obtained from the sample may allow them to make a more informed, and thus better, decision, thus resulting in an increase in expected utility. EVSI attempts to estimate what this improvement would be before seeing actual sample data; hence, EVSI is a form of what is known as preposterior analysis.

Method and system for rating patents and other intangible assets

A statistical patent rating method and system is provided for independently assessing the relative breadth ("B"), defensibility ("D") and commercial relevance ("R") of individual patent assets and other intangible intellectual property assets. The invention provides new and valuable information that can be used by patent valuation experts, investment advisors, economists and others to help guide future patent investment decisions, licensing programs, patent appraisals, tax valuations, transfer pricing, economic forecasting and planning, and even mediation and / or settlement of patent litigation lawsuits. In one embodiment the invention provides a statistically-based patent rating method and system whereby relative ratings or rankings are generated using a database of patent information by identifying and comparing various characteristics of each individual patent to a statistically determined distribution of the same characteristics within a given patent population. For example, a first population of patents having a known relatively high intrinsic value or quality (e.g. successfully litigated patents) is compared to a second population of patents having a known relatively low intrinsic value or quality (e.g. unsuccessfully litigated patents). Based on a statistical comparison of the two populations, certain characteristics are identified as being more prevalent or more pronounced in one population group or the other to a statistically significant degree. Multiple such statistical comparisons are used to construct and optimize a computer model or computer algorithm that can then be used to predict and / or provide statistically-accurate probabilities of a desired value or quality being present or a future event occurring, given the identified characteristics of an individual patent or group of patents.
Owner:PATENTRATINGS

System and method for determining value at risk of a financial portfolio

The present invention provides a system and method for accurately estimating value-at-risk (VAR) of a financial portfolio. The present invention analyzes a distribution of sorted financial data samples to determine an accurate range of upper and lower limits of an expected value of VAR so that an analyst or another financial analysis system may select an appropriate VAR value from the range presented.
Owner:AXIOM SOFTWARE LAB

Pricing of options using importance sampling and stratification/ Quasi-Monte Carlo

A computer implemented method prices derivative securities (for example, options) by selecting an importance sampling (IS) distribution and combining the chosen IS distribution with stratified sampling. The process consists of the steps of choosing an importance sampling distribution and combining the chosen importance sampling with stratification or Quasi-Monte Carlo (QMC) simulation. In the first step, an importance sampling distribution is chosen. In the second step, the chosen importance sampling is combined with stratification or Quasi-Monte Carlo sequencing. The pricing of many types of securities reduces to one of estimating an expectation of a real-valued function of some random variables.
Owner:IBM CORP +1

Cost-benefit approach to automatically composing answers to questions by extracting information from large unstructured corpora

The present invention relates to a system and methodology to facilitate extraction of information from a large unstructured corpora such as from the World Wide Web and / or other unstructured sources. Information in the form of answers to questions can be automatically composed from such sources via probabilistic models and cost-benefit analyses to guide resource-intensive information-extraction procedures employed by a knowledge-based question answering system. The analyses can leverage predictions of the ultimate quality of answers generated by the system provided by Bayesian or other statistical models. Such predictions, when coupled with a utility model can provide the system with the ability to make decisions about the number of queries issued to a search engine (or engines), given the cost of queries and the expected value of query results in refining an ultimate answer. Given a preference model, information extraction actions can be taken with the highest expected utility. In this manner, the accuracy of answers to questions can be balanced with the cost of information extraction and analysis to compose the answers.
Owner:MICROSOFT TECH LICENSING LLC

Systems and methods for guiding allocation of computational resources in automated perceptual systems

ActiveUS20050132378A1Facilitate in inferring human-centric notion of contextReducing computational resource burdenDigital computer detailsBiological neural network modelsPattern perceptionInformation Harvesting
The present invention leverages analysis methods, such as expected value of information techniques, rate-based techniques, and random selection technique, to provide a fusion of low-level streams of input data (e.g., raw data) from multiple sources to facilitate in inferring human-centric notions of context while reducing computational resource burdens. In one instance of the present invention, the method utilizes real-time computations of expected value of information in a greedy, one-step look ahead approach to compute a next best set of observations to make at each step, producing “EVI based-perception.” By utilizing dynamically determined input data, the present invention provides utility-directed information gathering to enable a significant reduction in system resources. Thus, of the possible input combinations, the EVI-based system can automatically determine which sources are required for real-time computation relating to a particular context.
Owner:MICROSOFT TECH LICENSING LLC

Method and apparatus for improved reward-based learning using adaptive distance metrics

The present invention is a method and an apparatus for reward-based learning of policies for managing or controlling a system or plant. In one embodiment, a method for reward-based learning includes receiving a set of one or more exemplars, where at least two of the exemplars comprise a (state, action) pair for a system, and at least one of the exemplars includes an immediate reward responsive to a (state, action) pair. A distance metric and a distance-based function approximator estimating long-range expected value are then initialized, where the distance metric computes a distance between two (state, action) pairs, and the distance metric and function approximator are adjusted such that a Bellman error measure of the function approximator on the set of exemplars is minimized. A management policy is then derived based on the trained distance metric and function approximator.
Owner:IBM CORP

Network global expectation model for multi-tier networks

In the Network Global Expectation Model, expectation values evaluated over the entire network are used as a multi-moment description of the required quantities of key network and network element (NE) resources and commensurate network costs. The Network Global Expectation Model naturally and analytically connects the global (network) and local (network element) views of the communication system, and thereby may be used as a tool to gain insight and very quickly provide approximate results for the preliminary evaluation and design of dynamic networks. Further, the Network Global Expectation Model may serve as a valuable guide in the areas of network element feature requirements, costs, sensitivity analyses, scaling performance, comparisons, product definition and application domains, and product and technology roadmapping. The network is arranged as a multiple tier network of nodes in order to apply the analysis methods of the Network Global Expectation Model. The analytical method is developed to include non-uniform demands on the network.
Owner:LUCENT TECH INC

Automatic exposure method based on analogous column diagram

The invention provides an automatic exposure method based on an analogous column diagram, which has favourable exposure effect on various situations, such as dark background light target, target size uncertainty and the like in deep space exploration. An automatic exposure control system is a closed loop control system and mainly comprises three modules: target gray level statistics, comparative judgment with expected values and exposure time calculation; data statistics analysis is carried out by gray scale region division, gray scale value weighting average calculation and the like so as to determine exposure required by shooting. Because of having low requirement on hardware, the invention can be suitable for different hardware platforms by slightly modifying, and can balance calculation speed, logic resource use, system time sequence requirement and the like according to the practical situation so as to choose different control modes.
Owner:XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI

Method and system for rating patents and other intangible assets

A statistical patent rating method and system is provided for independently assessing the relative breadth (“B”), defensibility (“D”) and commercial relevance (“R”) of individual patent assets and other intangible intellectual property assets. The invention provides new and valuable information that can be used by patent valuation experts, investment advisors, economists and others to help guide future patent investment decisions, licensing programs, patent appraisals, tax valuations, transfer pricing, economic forecasting and planning, and even mediation and / or settlement of patent litigation lawsuits. In one embodiment the invention provides a statistically-based patent rating method and system whereby relative ratings or rankings are generated using a database of patent information by identifying and comparing various characteristics of each individual patent to a statistically determined distribution of the same characteristics within a given patent population. For example, a first population of patents having a known relatively high intrinsic value or quality (e.g. successfully litigated patents) is compared to a second population of patents having a known relatively low intrinsic value or quality (e.g. unsuccessfully litigated patents). Based on a statistical comparison of the two populations, certain characteristics are identified as being more prevalent or more pronounced in one population group or the other to a statistically significant degree. Multiple such statistical comparisons are used to construct and optimize a computer model or computer algorithm that can then be used to predict and / or provide statistically-accurate probabilities of a desired value or quality being present or a future event occurring, given the identified characteristics of an individual patent or group of patents.
Owner:PATENTRATINGS

Enterprise portfolio analysis using finite state Markov decision process

This invention introduces a method, system and computer readable media that enables a computer system or computer networked system to perform enterprise portfolio transition optimization. The invention considers several key factors that are traditionally treated informally. The invention provides a sequential decision model for enterprise portfolio transition management of computer and software resources. Using a finite state Markov Decision process, a mathematical formulation is developed to ensure an optimal enterprise portfolio transition plan, with the objective of balancing expected value and risk, that is solved numerically via an approximate dynamic programming algorithm. The output of the model is a set of recommendations in the form of a transition plan for each of the computer and software resources selected within the enterprise portfolio during each phase of a planning horizon.
Owner:IBM CORP

Quality evaluation method of electricity statistical index data

The invention relates to a quality evaluation method of electricity statistical index data. The method comprises the following steps: obtaining to-be-evaluated electricity statistical index data according to the requirement of an actual evaluation purpose; choosing corresponding data quality evaluation indexes; making data quality evaluation rules corresponding to the data quality evaluation indexes; calculating the weight Wi of a quality evaluation index Ii, and setting an expected value Ei; performing detection and analysis on quality evaluation indexes of the statistical index data, and calculating the percentage Si of data that meets the quality evaluation index Ii; according to the weight Wi, the percentage Si and the set expected value Ei, respectively calculating the comprehensive evaluation value SA, the overall expected value SE and the relative difference SR of the statistical index data, and performing evaluation on the overall quality of the statistical index data according to defined evaluation grades; and processing evaluated unqualified statistical index data. The method provided by the invention can be applied to quality evaluation of electricity statistical index data in the power industry.
Owner:STATE GRID CORP OF CHINA +2

Planning method of distribution network based on fuzzy expected value model

The invention particularly relates to a distribution network distribution method considering the uncertainty of a load prediction result, which takes the fuzzy expected value of the annual investment operating expenses of a distribution network, i.e. the fuzzy expected value of the annual investment expenses and the network loss expenses, as an optimized objective to evaluate the optimization benefits of the distribution network by the fuzzy expected value of the annual investment expenses of the distribution network and the fuzzy expected value of the annual compensation expenses. According to the known planning parameters of the distribution network and the initial net rack data of a planning region and various alternative option data, wherein a load prediction value is represented by fuzzy variables, various alternative options are represented by the variables of 0 to 1, a distribution network optimization planning model based on a fuzzy expected value model is established, and a genetic algorithm is adopted to solve. The invention can reduce the ex-post compensation expenses to a great extent and lowers losses and wastes. Meanwhile, the method considers various factors of the planning of the distribution network, wherein various factors comprise whether to establish a new transformer substation, whether to increase the capacity of the traditional transformer substation, whether to replace a circuit or establish a new circuit and the like.
Owner:杨毅 +1

Industrial big data driven total completion time prediction method

The invention discloses an industrial big data driven total completion time prediction method and relates to the field of engineering application. The method includes: establishing an industrial big data analysis platform; applying an association rule mining algorithm to analyze and mine total completion time influence factors; establishing a neural network model BP; dynamically improving a weight and a threshold of the neural network model BP to acquire a dynamical neural network model DBP; applying an AIGA (adaptive immune genetic algorithm) to optimize the dynamical neural network model DBP so as to acquire a prediction model AIGA-DBP, and computing a total completion time prediction value according to the prediction model AIGA-DBP; when an error of the total completion time prediction value and a total completion time expectation value meets preset conditions, outputting the total completion time prediction value. By the method, the total completion time can be predicated accurately, the work flow of enterprises is optimized, the production efficiency of the enterprises can be improved, and the method is adaptable to various changes of the enterprise due to time lapse.
Owner:XIDIAN UNIV +1

Poor information theory fusion-based product life characteristic information extraction method

InactiveCN102081767AAccurate acquisitionRestore original propertiesInstrumentsPattern recognitionSmall sample
The invention relates to a poor information theory fusion-based product life characteristic information extraction method, which comprises the following steps of: acquiring original information of a small sample; transforming the original information into large-sample generating information by using a right self-service method and performing effective maximum likelihood processing, and acquiring maximum likelihood estimated values of large-sample content of two parameters, namely a Weibull distribution shape parameter and a scale parameter; extracting density functions of the two parameters by using a maximum entropy method; giving a confidence level, and calculating estimation intervals and expected values of the two parameters through the density functions of the shape parameter and the scale parameter respectively; and giving a failure probability, and acquiring the product life characteristic information through Weibull distribution life of the two parameters and reliability calculation thereof. The method has no requirement on completeness of the original information of the small sample, does not need priori information of the shape parameter and the scale parameter, can effectively recover total original characteristics of the product life, disclose nature of the product life information, more accurately acquire the product life characteristic information and reduce the experimental quantity of the product.
Owner:HENAN UNIV OF SCI & TECH

Commoditization of products and product market

The claimed subject matter relates to an architecture that can facilitate the commoditization of both products and product markets in resale domains in order to aid in quantifying a value of used product as well as to enhance efficiencies and / or profits in resale markets. In one aspect, the architecture can determine a recommended (e.g., average) price and listing fee for a product. In another aspect, desired (e.g. indicated by the seller) values can be provided and based upon various market factors and differences between the desired values and the recommended values, the architecture can determine a variety of probabilities relating to the conversion of the product, as well as provide suggestions for increases the potential for a conversion. In addition, the architecture can identify and capitalize on arbitrage opportunities within the market.
Owner:MICROSOFT TECH LICENSING LLC

Observation and analysis based code optimization

Observation and analysis based optimization of software code is disclosed. An expected value is chosen for a dynamic attribute that cannot be determined, prior to execution of the associated software code, to be guaranteed to have that expected value at runtime. An optimized version of the software code is generated, including one or more optimizations based on an assumption that the dynamic attribute will have the expected value. Non-exhaustive examples of a dynamic attribute include a variable type; a location in memory; a location in which a global object, property, or variable is stored; the contents of a global function or method; and a value of a global property or variable. A check is performed during execution of the optimized version of the software code, prior to executing the portion that has been optimized based on the assumption, to verify that the dynamic attribute has the expected value. In the event that it is determined at runtime that the dynamic attribute does not have the expected value, execution reverts to backup code that is not based on the assumption that dynamic attribute will have the expected value.
Owner:APPLE INC

Bus dynamic departure scheduling optimization method based on genetic algorithm

The invention discloses a bus dynamic departure scheduling optimization method based on a genetic algorithm. The method specifically comprises the steps that information of vehicles and passengers running on a single line is collected before the starting moment of a planning period; a passenger flow arrival rate function is obtained according to the real-time data and prediction, and parameters needed by model calculation are determined at the starting moment of the planning period; a scene-based dynamic bus departure scheduling robust optimization model is established by taking minimization of an expected value of total waiting time of passengers as an objective function under the condition that scenes on a single line are different; a genetic algorithm is designed for solving, and according to the probability of subjective occurrence of each scene in the preference adjustment model and the magnitude of a regret value in the model constraint, different solutions for selecting an optimal departure scheme are obtained. According to the method, the problem of dynamic bus departure scheduling under the condition that the passenger arrival rate is uncertain is solved, the waiting time of passengers is shortened, the potential risk of bus operation is reduced, and the safety and the stability of a bus system are improved.
Owner:HANGZHOU DIANZI UNIV

Method and apparatus for mapping uncertainty and generating a map or a cube based on conditional simulation of random variables

A new method is presented for generating a probability map, a cutoff map, and a confidence limit map in one single operation. In addition, the new method can also generate a cube representing a cubic volume of earth formation by using the same method for generating the aforementioned maps. This is accomplished by:[0001](a) gridding a cross section, (b) Kriging the gridded cross section thereby producing a plurality of expected values and a corresponding plurality of standard deviations associated, respectively, with the plurality of intersections on the gridded cross section, (c) generating a plurality of probability density functions which correspond, respectively, to the plurality of expected values / standard deviations of the plurality of intersections, (d) integrating each of the probability density functions thereby generating a plurality of cumulative distribution functions which correspond, respectively, to the plurality of probability density functions, (e) choosing a value from each of the cumulative distribution functions associated with each of the intersections of the gridded cross section, and (f) assigning such value to its associated intersection of the gridded cross section and assigning a unique color to each such value, thereby generating a map illustrating the characteristics of the cross section through the earth formation. Since a cube includes a plurality of gridded cross sections, by generating a map for each cross section, the new method will generate the cube.
Owner:SCHLUMBERGER TECH CORP

System and method for determining an optimized process configuration

The disclosed embodiments relate to a system and method for processing data. The system may involve a process-modeling tool adapted to define a process model, to define mapping from a resource to an activity in the process model, and to define a metric on the process model. Additionally, the system may have a designation module adapted to designate a goal and define constraints. Also included may be a process simulation engine adapted to employ the process model to simulate a process execution based on the process data according to different configurations and to produce process execution data that comprises an expected value for the metric. Further, a process improvement engine may be a component adapted to evaluate the process simulation data produced by the process simulation engine and to provide process improvement data indicative of changes in the expected value of the metric. A search tool may further be included that is adapted to search a configuration space that comprises the process improvement data to determine a prospective configuration that causes the expected value of the metric to approach the goal.
Owner:HEWLETT PACKARD DEV CO LP

Equipment residual life prediction method and system

The invention discloses an equipment residual life prediction method and system. The method comprises the following steps: establishing an equipment degradation mathematical model based on a nonlineardiffusion process; obtaining an estimated value of the equipment degradation parameter under the acceleration stress as first data; calculating a degradation parameter value under normal working stress according to the first data to obtain second data; determining the distribution type of the second data through goodness-of-fit test; obtaining a posteriori distribution function and an expected value of the second data according to the distribution type of the second data; obtaining a first residual life probability density function according to the posteriori distribution function, the expected value and the equipment degradation mathematical model; correcting the first residual life probability density function according to a total probability formula to obtain a second residual life probability density function; and predicting the residual life of the equipment according to the second residual life probability density function. The prediction precision of the residual life of the equipment can be improved.
Owner:中国人民解放军火箭军工程大学

Power distribution network fault recovery method based on real-time contingency sets

Disclosed is a power distribution network fault recovery method based on real-time contingency sets. The method includes the steps of determining a contingency severity index firstly, obtaining the expected value of influence of contingencies by combining the contingency severity index with the probability of occurrence of the contingencies, sorting the contingencies according to the severity levels according to the expected value of influence of the contingencies, screening out the contingency sets needing fault recovery analysis, updating the contingency sets within each time period, and outputting corresponding fault recovery schemes in real time. The real-time contingency sets are established, the contingencies with the small expected value of influence are omitted, only the fault recovery schemes of the contingencies with the high expected value of influence are analyzed, the number of the contingencies needing to be analyzed by on-line dynamic safety assessment is largely decreased, the calculation time for analysis of the fault recovery schemes is shortened, and real-time fault recovery plans are achieved before faults occur.
Owner:STATE GRID LIAONING ELECTRIC POWER CO LTD SHENYANG POWER +2

Seam hole reservoir body detection method and detection device

The invention discloses a seam hole reservoir body detection method and detection device. The detection method includes the steps that multiple effective attributes of a target to be detected are selected; a mathematical expectation value of a known reservoir body is output, an overdetermined equation is established for all the effective attributes in combination with linear combination of attribute values of the effective attributes, and the least square solutions of the overdetermined equation are solved to serve as attribute weighing coefficients of the effective attributes; according to the attribute weighing coefficients, multiple preferred attributes are selected from the multiple effective attributes; according to the attribute weighing coefficients and the preferred attributes, fusion of the preferred attributes is achieved with a linear weighing method. The detection method and detection device solve the technical problem that when information parameters in a single seismic attribute are used for detecting complicated seam hole type reservoir stratums, the detection is not accurate, and the detection method and detection device have the advantage that when a complex reservoir body is detected through multi-attribute information, the reservoir body can be predicted more accurately.
Owner:CHINA PETROLEUM & CHEM CORP

Network global expectation model for rapidly quantifying network needs and costs

InactiveUS20050060395A1Increasing and decreasing level of detailIncreasing and decreasing of and sophisticationWavelength-division multiplex systemsDigital computer detailsTechnology roadmapsCommunications system
In the network global expectation model of the present invention, expectation values evaluated over the entire network are used as a multi-moment description of the required quantities of key network and network element (NE) resources and commensurate network costs. The network global expectation model of the present invention naturally and analytically connects the global (network) and local (network element) views of the communication system, and thereby may be used as a tool to gain insight and very quickly provide approximate results for the preliminary evaluation and design of dynamic networks. Further, the network global expectation model of the present invention may serve as a valuable guide in the areas of network element feature requirements, costs, sensitivity analyses, scaling performance, comparisons, product definition and application domains, and product and technology roadmapping.
Owner:LUCENT TECH INC

Test method and test system for testing trusted computing password support platform

The invention relates to a test method and a test system for testing a trusted computing password support platform. The test method comprises the following steps of: obtaining atom behavior and packaging the atom behavior as a test case; analyzing the test case to obtain the test case data; calling a data conversion interface to convert the analyzed test case data into a network byte order, and outputting a test expected value to a journal file; inputting the analyzed test case data in a trusted computing interface for test, and returning back a test actual value to the journal file; verifying the test actual value and the test expected value, and recording the check result in the journal file; and analyzing and counting the test result, and outputting a test statistical result. By the technology provided by the invention, convenient and fast test management and test statistical analysis functions can be realized, and the test efficiency is improved.
Owner:NATIONZ TECH INC

Method and apparatus for determining expected values in the presence of uncertainty

Disclosed are methods and apparatus for predicting an expected value associated with an end event of an event sequence. In one embodiment, the following operations are performed: (a) providing a current set of input attributes and contextual data collected during performance of previous event sequences; (b) predicting a plurality of expected values for going from a first event of a known event sequence to each of a plurality of subsequent events of the known event sequence based at least on the current set of input attributes and the collected contextual data; and (c) predicting an expected value for going from a first event of an unknown event sequence to an end event of such unknown event sequence based on at least two of the expected values predicted for the known event sequence and based at least on the current set of input attributes and the collected contextual data. The expected value for reaching the end goal of the unknown event sequence cannot be determined with a degree of certainty that is higher than a predetermined value and wherein the expected value for reaching the end goal of the known event sequence can be determined with a degree of certainty that is higher than the predetermined value.
Owner:ORACLE INT CORP

Accident black-spot identification optimizing method

InactiveCN101833610AOvercome the drawback of requiring a large number of reference road unitsThe result is accurateSpecial data processing applicationsBlack spotExpected value of sample information
The invention discloses an accident black-spot identification optimizing method. Improvement is made based on an empirical Bayes method, and an accident model is constructed to obtain a mean value and a variance of before-accident distribution, so the shortcoming that a great number of reference road units are needed in the empirical Bayes method is overcome. On the part of an accident regression model, a variable is an expected value of the number of accidents happening on a certain road unit in a certain period and independent variables are values representing the traffic of the road unit and road characteristics, and parameters of the before-accident distribution can be obtained by using the expected value of the number of the accidents and the variance so as to determine the before-accident distribution. Simultaneously, through optimization, expectation obtained from after-accident distribution consists of two parts which are a predicted value and a correction term of the predicted value respectively, so the correction of the predicted value can be obtained. Accident back-spot identification results calculated by using the method are more accurate than those calculated by the conventional method, so casualties, vehicle damages, road property losses and the like caused by the accidents are reduced.
Owner:BEIJING UNIV OF TECH

Employing a combined function for exception exploration in multidimensional data

There is provided a method for providing a function for use in detecting a presence of an exception in multidimensional data. The method comprises the steps of (a) partitioning the multidimensional data into at least a first region and a second region; (b) assigning a first region-specific function to the first region and a second region-specific function to the second region; and (c) determining a combined function from the first region-specific function and the second region-specific function. The combined function is used to calculate an expected value of the multidimensional data for distinguishing the presence of an exception.
Owner:IBM CORP

Method for updating regression coefficients in a causal product demand forecasting system

An improved method for forecasting and modeling product demand for a product. The forecasting methodology employs a causal methodology, based on multiple regression techniques, to model the effects of various factors on product demand, and hence better forecast future patterns and trends, improving the efficiency and reliability of the inventory management systems. A product demand forecast is generated by blending forecast or expected values of the non-redundant causal factors together with corresponding regression coefficients determined through the analysis of historical product demand and factor information. The improved method provides for the saving and updating of previously calculated intermediate regression analysis results and regression coefficients, significantly reducing data transfer time and computational efforts required for additional regression analysis and coefficient determination.
Owner:TERADATA

Fault diagnosis method for unmanned aerial vehicle gyroscope

The invention discloses a fault diagnosis method for an unmanned aerial vehicle gyroscope. The fault diagnosis method comprises the steps that the proximity of a sample and an expected value is calculated on the basis of a fuzzification technique, a sample membership degree factor is designed according to the proximity probability and configured into a mathematical model representing a support vector machine, and the influences generated by the sample distribution unbalance and the noise characteristic are eliminated; support vector machine training is conducted in an off-line mode, decision function parameters of an optimal interval classification face for distinguishing a positive sample and a negative sample are acquired, when an unmanned aerial vehicle flies, attitude signals output by an airborne sensor gyroscope are collected in real time, feature vectors of the signals are extracted by adopting a db4 wavelet basis decomposition method, normalized and then input to a decision function of the optimal interval classification face, a category label of a to-be-decomposed signal is calculated in real time, and the fault condition of the gyroscope is recognized. According to the diagnosis method, the biasing degree of a fault classification hyperplane is significantly decreased, the fault diagnosis precision is improved, the calculation amount is low, and the on-line real-time performance of a fault diagnosis algorithm is achieved.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Control method and device for predicting user behavior based on large data

The invention provides a control method for predicting a user behavior based on large data. The control method is used in classification analysis based on a user behavior large-data set so that a behavior expectation index I is predicted and calculated. The control method comprises the following steps: a, obtaining a user behavior variable y; b, on the basis of a function f(u, y, [phi] ... ...), obtaining characteristic parameters [beta]<1>, [beta]<2> ... [beta] through calculation; c, on the basis of a linear combination formula u=[beta]<1>*1+[beta]<2>*2+...[beta]*p, obtaining an expectation value u through calculation; and d, on the basis of a formula I=g(u), obtaining the behavior expectation index I through calculation. A corresponding control device is further provided. Client indexes aiming at a user risk, a purchase preference, renewal of insurance, insurance adding and other aspects can be designed through the method and device, a specific number of data is preferably selected from thousands of user data, a refined prediction model is constructed, and visual evaluation is performed on a user's future behavior trend on the basis of the prediction model.
Owner:CHINA PACIFIC INSURANCE (GRP) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products