144 results about "Density distribution function" patented technology

The invention relates to a trajectory data-based signal intersection periodic flow estimation method. The method comprises the following steps that: 1) the trajectory point data of sampled vehicles are acquired, and the key point information of the vehicles entering and leaving a queue is obtained; 2) a fitting method is adopted to estimate the queuing waves and evanescent waves of vehicle queuing, and the intersection point of the queuing waves and the evanescent waves is taken as the flow estimated value of queuing vehicles; 3) the density distribution function of full-cycle flow is obtainedaccording to the flow estimated value, and the proportion of non-stop vehicles in the full-cycle flow; and 4) a full-cycle flow estimation problem is transformed into a parameter estimation problem based on the Poisson distribution and M3 distribution of the non-queuing vehicles according to the density distribution function of the full-cycle flow, and a maximum likelihood estimation method is used to perform estimation, and the maximum-likelihood expectation-maximization method is adopted to perform solving, and the estimated value of the arrival flow of each cycle can be obtained. Comparedwith the prior art, the method of the present invention has the advantages of the fusion of model analysis and statistical analysis, the full use of trajectory information, wide applicability and thelike.

The invention discloses a determination method for heat source model parameters in multiplewire submerged-arc welding by numerical simulation. The determination method comprises the following steps of: determining a heat-flow density distribution function in the multiplewire submerged-arc welding process; initially determining the heat source model parameters, wherein the heat source model parameters to be determined includes Ui, Ii, v, n, taui, etai, alphai, f<fi>, bi, ci, a<fi>, and a<bi>; and finally determining a heat-source model, wherein the determined parameters are substituted into the heat-flow density distribution function q(x, y, z, t) which is then taken as a thermology boundary condition for repeated iterative computations by a numerical simulation tool, the computation result of iterative computation of each time is compared with the shape of a joint fusion pool obtained by actual welding, the heat-source model parameters bi, ci, a<fi>, a<bi> are gradually adjusted by a range of 5% according to the comparison results until the errors between the parameters of the fusion depth and the fusion width of a simulated fusion pool and the fusion depth and the fusion width of the actual joint fusion pool are smaller than 10%, and then the determination of the heat-source model parameters in the multiplewire submerged-arc welding is finished.

The invention provides a method for updating an electronic product reliability prediction model complying with exponential distribution, which comprises the following steps of: 1, analyzing a use region of products; 2, acquiring calendar year meteorological information of each province and city in the use region, and calculating a year average value of temperature stress and humidity stress in each region; 3, respectively constructing a temperature and humidity probability density distribution function, and solving a year average value of temperature stress and humidity stress in the use region; 4, analyzing each stress borne in a product use process; 5, selecting a reliability prediction manual, and calculating an element work failure rate according to a stress analysis model; 6, drawinga product mission reliability block diagram and compressively calculating a product work failure rate; 7, carrying out an acceleration life test and recording test data; 8, product mean life to failure under a test condition and work failure rate under a normal work condition; and 9, comparing product work failure rates obtained by reliability prediction and the accelerated life test, calculatingerrors generated by the humidity stress, and offering a reliability prediction correction model.

The invention provides a service life prediction method of a vertical machining center milling cutter updated by Bayesian information on the basis of a state space model. According to the structural features of the vertical machining center milling cutter, a degeneration signal of the vertical machining center milling cutter is collected, and the obtained signal is processed to obtain a degeneration information characteristic quantity; and according to the obtained degeneration information characteristic quantity of the vertical machining center milling cutter, the state space model used for predicting the service life of the vertical machining center milling cutter is established. On the basis of a Bayesian theory under probability statistics, an established service life prediction model of the milling cutter is subjected to information alternation by sequential Monte-Carlo simulation, above parameters are estimated in real time, and the service life predication method is established. A residual life probability density distribution function of the vertical machining center milling cutter is output according to a failure threshold of the milling cutter to obtain a residual life prediction value. The service life prediction method has the beneficial effects that the work reliability of the cutter is improved through the on-line prediction of the residual life of the cutter, sudden accidents are reduced, and heavy losses and casualties are avoided.

The invention discloses a geostatistics simulation based full-formation velocity modeling method. The method includes the steps of determining a preset number of velocity control layers; subjecting post-stack time migration seismic data to well-seismic calibration, subjecting top and bottom boundary layers of each velocity control layer to structural interpretation, and performing comparing and tracking to obtain top and bottom boundary layers and faults of the velocity control layers of a whole area; establishing a formation frame model of the area; establishing a velocity probability density distribution function and a velocity longitudinal variation function for each velocity control layer; establishing a velocity transverse variation function for each velocity control layer; under control of the formation frame model of the area, performing geostatistics simulation via the velocity probability density distribution functions, the velocity longitudinal variation functions and the velocity transverse variation functions of the velocity control layers so as to implement multiple velocity models; averaging the velocity models to obtain a full-formation velocity model.

The invention discloses a soil moisture site data upscaling method based on the Bayesian theory. The soil moisture site data upscaling method includes steps of estimating prior probability density distribution function pre_pdf of a target variable on the basis of sparse site observation data in an upscaling area; inversing MODIS ATI into SM by establishing nonlinear regression relation between the SM and the MODIS ATI, estimating an estimated confidence interval of the soil moisture nonlinear regression and probability distribution as soft data in a probability form; integrating the prior distribution of the target variable and auxiliary information of the probability form from the MODIS ATI through the Bayesian theory, and acquiring posterior probability density distribution function post_pdf of the target variable; calculating the value of the target variable in the maximum probability through maximization of the posterior probability distribution function. By the soil moisture site data upscaling method, uncertainties caused by scale difference between soil moisture remote sensing products and ground site authentication data are effectively reduced. The soil moisture site data upscaling method can be applied to upscaling application of other ground surface parameters.

The invention provides a screen dot design method of a side light type light guide plate of an LED light source, comprising the following steps of: establishing a two-dimensional coordinate plane, and determining a rectangular lighting area; establishing a density distribution function model in the rectangular lighting area; designing a screen dot space distribution function according to the density distribution function model inside the rectangular lighting area; generating original light guide plate random number screen dots according to the screen dot space distribution function; providing an intermolecular potential energy function, regulating the original light guide plate random number screen dots with serious stacking by applying the intermolecular potential energy function, and then generating light guide plate screen dots with reasonable spaces; converting the density distribution function model, the screen dot space distribution function and an intermolecular potential energy function model into computer languages by a VBA development tool facing to objectification, and establishing a VB user interface (VB form). The invention enhances the development speed of the light guide plate and overcomes the defect of manual regulation needed in the screen dot design process of the light guide plate.

The invention discloses a tracking measurement set partitioning method for multiple extended targets based on density analysis and spectrum clustering. The method is mainly used for solving the problems that in noisy environments, the number of the multiple extended targets is unknown, a changing measurement set is difficult to partition and the calculating cost is high. The method comprises the steps of constructing a density distribution function for the measurement set by adopting a Gaussian kernel, then, selecting a density threshold according to a density histogram technology, filtering noise wave measurements out of the measurement set, constructing a noise wave measurement data set removed similarity matrix by introducing an affinity propagation technology, finally, carrying out Laplace spectrum transform on the similarity matrix, and clustering by adopting a K-mean algorithm. The method has the advantages that the measurement set of the multiple extended targets can be accurately partitioned, and the calculating cost is reduced, so that the tracking performance for the multiple extended targets is improved, and the design requirements of actual engineering systems are met.

The invention relates to a method and apparatus for determining a classification boundary between an object, such as a vehicle, and a background, using an object classifier. In an embodiment of the invention, a trained classifier is configured to classify and recognize each a plurality of object images and a plurality of background images. Next, a confidence probability density distribution function is calculated for the vehicle and the background using the determined confidence values for the vehicle images and background images. Once the probability density distribution functions for the vehicle and the background are calculated, the classification boundary between the vehicle and the background is determined using the probability density distribution functions for the vehicle or the background, or both, and a predefined model that is appropriate for the application.

The invention relates to a method for calculating core permeability by adopting digital core simulation. The method comprises the following steps: a, a physical model of porous core media is simulated with the Lattice Boltzmann Method; b, physical field initialization and boundary treatment are performed on the physical model of the porous core media, according to the boundary treatment, mirror boundary is taken as a boundary condition for the Lattice Boltzmann Method, and a simulation area and a plurality of mirror areas with the same structure with the simulation area can be obtained; c, mass force is used for driving a fluid to flow in the simulation area; d, a density distribution function of the simulation area is calculated according to the treated physical model of the porous core media; e, the core permeability is simulated and calculated according to the mass force and the density distribution function. With adoption of the method, the core permeability calculating accuracy is improved, and the core permeability calculating time is shortened.

The invention discloses a hydropower station scheduling risk assessment method based on runoff interval prediction. The method mainly comprises: acquiring a cumulative probability density distribution function of predicated flow error according to analysis for the predicated flow error; simulating the flow process on the basis of actual flow predication intervals and predicated flow variable error intervals in a certain confidence probability; obtaining the output power, the final water level and the reservoir discharge flow of a hydroelectric power station, and comparing the output power, final water level and the reservoir discharge flow with the actual output power, actual final water level and actual reservoir discharge flow of the hydroelectric power station obtained according to the actual flow; finally acquiring the risk probability of abandoning water and the risk probability of failing to complete load tasks. The invention also provides a risk assessment system. The hydropower station scheduling risk assessment method and system can not only make up for the defect of the conventional non-linear stochastic simulation runoff predication method, but largely promote the accuracy of runoff predication results, and provide reference for the middle-term and long-term predications for runoff.

The present invention relates to an optical field polarization state measurement method and device, a computer device and a storage medium. The method comprises the steps of: obtaining incident polarization state data of calibration incident light and emergent polarization state data of calibration emergent light; according to the incident polarization state data and the emergent polarization state data, calculating and obtaining a target Mueller matrix of a phase modulator to be measured; inputting the target Mueller matrix into a pre-constructed polarization state probability density distribution model to output and obtain a target polarization state probability density distribution function corresponding to the target Mueller matrix, wherein horizontal coordinates and vertical coordinates of the target polarization state probability density distribution function are respective Stokes parameters and corresponding probability values, and the target polarization state probability density distribution function corresponds to an optical field to be measured; obtaining a target Stokes parameters corresponding to the maximum probability value in the target polarization state probability density distribution function; and expressing the polarization state of the optical field to be measured through the target Stokes parameters. The method can improve the optical field polarization state measurement precision in low light and can improve the optical field polarization state measurement speed in non-low light.

The invention discloses a method for producing the lattice points of a diffusion plate of a light-emitting diode (LED) backlight module, which comprises the following steps of simulating an LED light distribution curve; obtaining the illuminance of the diffusion plate according to the LED light distribution curve; generating the density distribution function of the lattice points according to the illuminance and transmittance of the diffusion plate; and adopting a macroprogram visual basic for application (VBA) development tool to generate the area distribution of the lattice points. The invention further discloses a device for producing the lattice points of the diffusion plate of the LED backlight module. Through the method and the device for producing the lattice points of the diffusion plate of the LED backlight module, the development speed of a light guide plate can be improved, and the development cost of the light guide plate is saved.

The invention discloses a rotary kiln fault diagnosis method based on weighted kernel principal component analysis (WKPCA). The rotary kiln fault diagnosis method comprises the following steps: collecting and pretreating training sample data in a normal condition, and mapping treated data to a higher dimensional space to obtain a kernel matrix; calculating the characteristic value of the kernel matrix and a characteristic matrix, and establishing a kernel principal component model to obtain kernel principal component variables in the normal condition; using a kernel density estimation function to calculate the density distribution function of each kernel principal component variable in the normal condition; calculating SPE control limit and T2 control limit according to the kernel principal component variables; collecting and pretreating detection sample data in a fault condition in real time; taking each kernel principal component variable of a detection sample into corresponding density distribution functions to obtain the weighed value of each kernel principal component variable, and establishing a weighted matrix; calculating SPE statistical magnitude and T2 statistical magnitude according to the weighed kernel principal component variables, comparing the calculated SPE statistical magnitude and T2 statistical magnitude with the obtained control limits, and judging whether the system breaks down. According to the diagnosis method provided by the invention, the steps of the diagnosis method are reasonable, and the accuracy of fault diagnosis is improved.

The invention discloses a similarity calculation method based on commercial medical insurance claim cases. The method comprises the following steps that of 1 discretizing attribute factors, 2 screening main attribute factors of the claim cases, 3 building claim case standard templates and quantifying claim case weight values and 4 inspecting the standard rationality. According to the method, a traditional method which is adopted by commercial insurance companies and achieved through the step that all the claim cases are manually checked one by one to find possibly-existing fraud cases is abandoned, a traditional information technology and a data mining technology are combined, therefore, business personnel are more efficiently assisted in finding the fraud claim cases, the manual cost is reduced, and the service efficiency is improved; meanwhile, the mode of subjectively defining age segmentation points is abandoned in the aspect of sample age discretization processing, and the segmentation point range is determined according to an actual density distribution function of samples; in addition, the weight value of an initial template is determined by calculating the complexity, and differential calculation is conducted on all groups, so that the weight values of all the templates are optimized under all the accident conditions.

This invention relates to a method for yield loss analysis of process steps of semiconductor wafers having a plurality of dies, and more particularly relates to a defect inspection technique to determine a hit ratio, computation of yield impact contributions for the defects, and determination of a kill ratio for a specific type of defect. Yield loss is estimated ultimately upon a choice of a defect density distribution function. A defect calibrated factor and a yield impact calibrated factor are introduced herein.

The present invention belongs to the technical field of light guide plate design, and aims to provide a light guide plate netted point design method through laser processing. Light guide plate netted points designed by the above method are linear. A density computational formula of the linear netted points is that D=L*S / PxPy, two-dimension coordinate planes using a geometric center of a light guide plate as an origin of the coordinates are established successively according to the above formula, a light emitting region is determined and divided into a plurality of regions which are endowed with different netted point density distribution, and a density distribution function of the light emitting region is obtained so as to determine the density distribution of the light emitting region, until the length L of the netted points is output. According to the whole process, a function language is converted through a VBA development tool into a computer language, thus to realize automatic arrangement of the linear netted points, the whole netted point distribution is not only high in automation degree, but also is short in required development time, few in development expense, simple in production technique, and high in yield. Light guide plates obtained according to a netted point distribution tendency obtained by the above method are excellent in uniformity and meet production requirements.

The invention relates to a bidding strategy for electricity purchase. The strategy comprises that a day similar to an electricity-price-to-predict day is selected via a grey correlation analysis method; according to the electricity price of the similar day, the electricity price of the electricity-price-to-predict day is predicted via a multivariate linear regression method; according to historical electricity prices of the similar days, the predicted electricity price of the similar day is obtained via the multivariate linear regression method, and a relative error probability density distribution function of electricity price prediction is established according to the historical and predicted electricity price; and according to the relative error probability density distribution function and the electricity cost of the electricity-price-to-predict day, bidding for electricity purchase is carried out via particle swarm optimization. According to embodiments of the invention, bidding for electricity purchase is carried out by utilizing the electricity cost of the day similar to the electricity-price-to-predict day, and the accuracy is high; and the established relative error probability density distribution function is used, and the electricity price of the electricity-price-to-predict day is adjusted via particle swarm optimization, so that the electricity purchasing price of the electricity-price-to-predict day is obtained, and bidding for electricity purchase of users is more accurate and more scientific.

The invention relates to a method for analyzing the small disturbance voltage stability of a geomagnetic storm to a power system, and the method comprises the steps: S1, building a layered earth conductivity model, and calculating a geomagnetic storm induction earth electric field; S2, calculating reactive power loss of the transformer caused by the geomagnetic induction current by using a K value method; S3, calculating the GIC-Q of the transformer substations of the multiple geomagnetic storm events under the long-time scale, and performing fitting to obtain a probability density distribution function and a cumulative probability density distribution function of the GIC-Q of each transformer substation; S4, establishing a synchronous generator, an excitation system, an asynchronous motor load and network model, and performing linearization; S5, selecting a root strongly correlated with the dynamic load equivalent asynchronization and the transformation ratio of the on-load voltage regulating transformer according to the participation factors; and S6, fitting a probability distribution function of a feature root real part, and establishing a risk evaluation index of system probability instability caused by geomagnetic storm in combination with the oscillation instability risk coefficient.

The invention discloses a real-time flood control risk analytic calculation method for a parallel reservoir group. The method comprises the following steps that: (1) establishing a mathematical expression of an uncertainty factor to obtain the edge distribution function of the uncertainty factor; (2) on the basis of a Copula function, solving the joint probability density distribution function ofthe multidimensional uncertainty factor; (3) establishing the real-time flood control regulation risk model of the reservoir group, and analyzing the flood control dispatching risk of the reservoir group of each moment; and (4) calculating the real-time flood control regulation risk of the reservoir group. By use of the method, the influence of correlation between uncertainty factors for the real-time flood control regulation risk of the reservoir group is considered, the analytic calculation formula of the real-time flood control dispatching risk of the reservoir group of each moment is solved, and the method is high in calculation efficiency, easy in implementation and high in universality.

The invention relates to the field of life prediction of mechanical and electrical equipment, and discloses a method of predicting the remaining life of equipment based on improved unscented particle filtering, in order to solve the problem that there is a loss of particle diversity for unscented particle filtering in the traditional method of predicting the remaining life of equipment, and to improve the accuracy of equipment life prediction. Unscented Kalman filtering is used as a recommended density distribution function of particle filtering to reduce particle degradation, and a linear optimization re-sampling algorithm is used to optimize the re-sampling part of particle filtering. For the selection of the step length coefficient K of linear optimization re-sampling, an adjustment factor Kb is created, the value of the step length coefficient K is determined adaptively using a fuzzy reasoning system, and finally, the remaining useful life of equipment is predicted. The method of the invention is suitable for residual useful life prediction of mechanical and electrical equipment.

The invention discloses a method for establishing a meteorological satellite composite channel simulation model under the cloudy weather condition. The method comprises the steps of 1 analyzing the influences on the shadowing effect and the multipath effect of a meteorological satellite signal from a cloud layer under the cloudy weather condition, conducting theoretical analysis and providing a receiving signal envelope probability density function and an error rate upper limit function, and 2 establishing the meteorological satellite composite channel simulation model according to analysis results in the step 1. Directing at the problem of the composite effect from the cloud layer to meteorological satellite communication under the cloudy weather condition, the characteristics of the meteorological satellite composite channel are studied, and through theoretical analysis, model establishing and simulation, the static statistics characteristics of the satellite composite channel can be provided qualitatively, the correctness and the effectiveness of theoretical analysis are proved, and certain technical foundation is laid for studying the performance of a meteorological satellite communication system and optimization of the meteorological satellite communication system.

The invention discloses an optimized clustering method, and the method specifically comprises the following steps of S1, selecting the pixels in a data set, and building a dense point set Y; S2, selecting the pixel points from the dense point set Y to form a set Q; S3, selecting m pixel points from the data set, and establishing an alternative initial clustering center point set C; S4, dividing the pixel points in the dense point set Y into a class where each initial clustering center in the set Q is located, and obtaining the average maximum similarity of the first clustering; S5, obtaining the minimum cluster average maximum similarity; and S6, taking the clustering center in the set Q corresponding to the minimum clustering average maximum similarity as an initial clustering center of the optimal kmeans clustering, carrying out kmeans clustering, and obtaining a clustering result. In order to reduce the interference of the noise on the data, the density sparse points are eliminatedby using a density distribution function, some noise interference points and abnormal points are eliminated, and the optimal initial clustering center is selected, so that the number k value of the optimal clustering is determined, and the clustering precision is improved.

The invention provides a calculation method of satellite closed-loop test jet thrust control, which comprises the following steps of: step S1, establishing a jet thrust density distribution function and carrying out piecewise linearization description; step S2, converting a jet instruction opening and closing moment into a jet valve opening and closing moment through the jet thrust density distribution function; step S3, determining the distribution of the jet thrust instruction opening and closing moment in a plurality of dynamic calculation cycles; step S4, establishing a relation between the jet valve opening and closing moment and a dynamic calculation moment; and step S5, calculating the engine thrust of each dynamic calculation cycle in one attitude and orbit control cycle. With the adoption of the calculation method, the calculation problem of jet thrust of each dynamic calculation cycle in the attitude and orbit control cycle as well as the problem that a jet thrust valve switch is nonlinearly modeled, and the nonlinear description of the jet thrust valve switch is introduced into a closed loop test system, so that the closed loop simulation test is more accurate are solved.

The invention discloses a Bayesian seismic inversion method based on [tau] distribution, and relates to the geophysical inversion and oil and gas reservoir prediction field. The method comprises the following steps: 1, inputting data to obtain an initial model of parameters to be inverted and determining parameters of [tau] distribution; 2, selecting an initial model of the t-th channel parameteras an iteration initial model, determining a prior probability density distribution function by parameterized [tau] distribution, inputting data to obtain posterior probability density function and performing MCMC inversion to obtain an inversion result; and 3, determining whether t is greater than seismic data in the input data, if yes, ending inversion to obtain a to-be-inverted wave impedance profile based on the inversion result, and if not, accumulating t and jumping to the step 2 for continuous inversion. The method solves the problem that the existing seismic inversion uses the Gaussiandistribution to simulate the seismic reflection coefficient distribution, resulting in the low precision and resolution of inversion physical parameters, and achieves the effect of improving the accuracy and resolution of the inversion physical parameters.

The invention provides a coupling uncertainty acquisition method for a high-altitude electromagnetic pulse field line based on polynomial chaos expansion. The method comprises the following steps that(1) a coupling model of a field line of a transmission line under a high-altitude electromagnetic pulse is established, and related input parameters are determined; (2) according to uncertainty variables set by a user and a submissive statistic characteristic distribution type of the uncertainty variables, unified conversion is conducted according to demands, corresponding polynomial bases are used, and a coupling random response is subjected to polynomial chaos expansion; (3) according to types of different polynomials, coefficients of all the polynomials are obtained through corresponding-form Gaussian integral, and an analytic expression of a coupling response of the high-altitude electromagnetic pulse field line is obtained; (4) according to the coefficients of all the polynomials anddistribution types of the uncertainty variables, statistic characteristic parameters of the coupling response of the high-altitude electromagnetic pulse field line are obtained, a fluctuation range,a probability density distribution function and a cumulative probability distribution function are obtained by using a Monte-Carlo method.

The invention discloses an acquisition method of a threshold line for confirming a quantum bit quantum state, and relates to the field of quantum measurement and control. The acquisition method includes the steps: preparing the quantum bits into a first quantum state and a second quantum state, and repeatedly measuring the first quantum state and the second quantum state respectively to obtain coordinate point data of a plurality of quantum bit reading signals on an orthogonal plane coordinate system; respectively marking as a first set and a second set, respectively carrying out Gaussian fitting on the coordinate points of the first set and the second set to obtain a first statistical center coordinate point and a second statistical center coordinate point of the Gaussian fitting graph respectively corresponding to the first set and the second set, and respectively corresponding to a first standard deviation and a second standard deviation; respectively determining a first probabilitydensity distribution function in the first set and a second probability density distribution function in the second set; and determining a fidelity function, and determining a corresponding thresholdline as an optimal threshold line when the fidelity function takes the maximum value. The threshold line established according to the acquisition method provided by the invention can provide more accurate reference for the judgment of unknown quantum states.

The invention discloses a nonlinear quantization method of a voice linear prediction model. The method comprises the following steps: line spectral frequency parameter transformation step: transforming line spectral frequency parameters of a voice linear coding prediction model into a line spectrum frequency parameter difference value through linear transformation; nonlinearity decorrelation step: decorrelating the line spectrum frequency parameter difference value through nonlinear transformation by adopting a structured method according to a statistical property of the line spectrum frequency parameter difference value; marginal probability distribution calculation step: calculating marginal probability density distribution by utilizing the statistical property of the decorrelated line spectrum frequency parameter difference value; and scale quantizer design step: designing an optimum scale quantizer based on probability density function according to the obtained marginal probability density distribution function. According to the nonlinear quantization method of the voice linear prediction model, the defects that in the prior art, the time complexity is high, the using effect is poor, and the like can be overcome, so that the advantages of low time complexity and good using effect can be realized.

The invention relates to the technical field of light guide plate design and discloses a light guide plate and an elliptical dot designing method and device of the laser-processing light guide plate. The elliptical dot designing method includes: building a two-dimension coordinate plane on the light guide plate; determining a light emitting area in the two-dimension coordinate plane; building a density distribution function of elliptical dots in the light emitting area; determining adjacent horizontal interval and adjacent vertical interval among the elliptical dots and short-long axial ratio of the elliptical dots; determining long axis of the elliptical dots according the the adjacent horizontal interval, the adjacent vertical interval, the short-long axial ratio and the density distribution function; converting the density distribution function and the long axis of the elliptical dots into a computer instruction to realize distribution of the elliptical dots. Length of the long axis of the elliptical dots acquired by calculation is closer to actual distribution of dots compared with conventional linear dots, so that light guide effect of the light guide plate is improved effectively.