89 results about "Continuous variable" patented technology

The invention relates to the technical field of industrial equipment intelligent simulation, and discloses a simulation model construction method and system, and the method comprises the following steps: 1, analyzing the electrical control logic of industrial equipment, and converting the electrical control logic into a mixed integer nonlinear programming problem containing a discrete Boolean variable and a continuous variable; 2, modeling the physical field based on a tensor network decomposition algorithm, and generating a compressed low-rank tensor network model; 3, dynamically adjusting parameters of the tensor network model by adopting a hierarchical optimization strategy, wherein the hierarchical optimization strategy switches a global search algorithm and a local optimization algorithm according to an error convergence state; 4, allocating and executing symbol calculation, tensor network operation and parameter optimization tasks through a heterogeneous calculation system; and 5, collecting production line sensor data in real time. According to the method, different physical field sub-models are dynamically activated through Boolean variables, and the accuracy of joint simulation in a complex industrial scene is remarkably improved.

The invention relates to the technical field of machine learning optimization, in particular to a machine learning optimization method based on a QUBO model and quantum annealing, and the method comprises the following steps: firstly, discretizing continuous parameters of the machine learning model into binary variables, and constructing a QUBO objective function; then optimizing the QUBO model by using a quantum annealing algorithm; and finally, solving a globally optimal solution by adjusting annealing parameters, wherein the annealing parameters comprise the initial temperature, the cooling coefficient and the number of iterations. The QUBO model can discretize continuous variables (including parameters such as weights and offsets) in models such as AR, SVM and CNN in machine learning into binary variables, so that a nonlinear relation is better processed, and the calculation complexity in the training process is reduced. Through the QUBO model, the regularization item can be better controlled, and the problem of overfitting is avoided. Meanwhile, the QUBO model can be solved in parallel through quantum calculation or a simulated annealing algorithm, and the calculation efficiency under large-scale data is remarkably improved.

The invention provides a sampling method suitable for continuous-discrete mixed variable design optimization of an advanced reactor. The sampling method comprises the following steps: (1) screening an effective discrete variable combination; (2) constructing a cumulative probability distribution function of the discrete variable combination; (3) hierarchically designing a space based on a cumulative probability distribution function interval; (4) distributing the number of samples according to the interval width proportion of the cumulative probability distribution function of each layer; (5) Latin hypercube sampling is carried out on the continuous variables in each layer; (6) integrating a global sample set and verifying the quality of the global sample set; and (7) constructing an agent model and evaluating precision. According to the method, the probability characteristic of the discrete variable and the space filling characteristic of the continuous variable are integrated, efficient exploration of the nuclear reactor design space is achieved, and compared with a traditional method, the sample quality and the calculation efficiency are remarkably improved.

The invention discloses a roll angle measuring method for a continuous variable roll test of a transient wind tunnel, and belongs to the technical field of wind tunnel test. Comprising the following steps: step S1, early-stage preparation: selecting two angle measurement sensors to carry out measurement work, and installing the two angle measurement sensors and an installation platform according to a preset angle; s2, carrying out field calibration operation; carrying out field calibration on the coefficient of the angle measurement sensor by adopting a fixed attack angle and variable roll angle mode; and S3, data interception, discretization and application during a step variable attack angle continuous variable roll angle test: in a wind tunnel test process, continuously collecting output voltage values of the two angle measurement sensors, calculating roll angles corresponding to the output voltage values, intercepting roll angle range values corresponding to the two angle measurement sensors according to needs, and calculating the roll angle range values of the two angle measurement sensors according to the intercepted roll angle range values. Splicing into a target measurement range; compared with a traditional step variable rolling and fixed rolling variable attack angle test mode, the scheme has the advantage that the test efficiency is greatly improved.

The embodiment of the invention discloses a data processing method, in the method, first intervention data of an intervention variable in a decision service can be utilized to perform causal effect estimation on the decision service based on an anti-fact thought, and anti-fact intervention data obtained based on the anti-fact thought can be a continuous variable. The variable can be a discrete variable, so that the causal effect estimation can be carried out on various types of intervention variables in various decision service scenes. Besides, in the method, the causal effect model can perform causal effect estimation on the input intervention variable in a group corresponding to the input confusion variable so as to obtain an output result about the result variable. Thus, the anti-fact intervention data and the first confusion data are input into the causal effect model, the first estimation result can be obtained through the causal effect model, and for a group described by the first confusion data, accurate causal effect estimation is obtained according to the anti-fact intervention data.

The invention relates to a self-adaptive information negotiation method applicable to a continuous variable quantum key distribution system, which comprises the following steps of: estimating an optimal code rate that an LDPC (Low Density Parity Check) code should reach under a current quantum channel, converting an initial code rate into the optimal code rate by a receiver, and obtaining a low-reliability bit number l which needs to be disclosed in conversion calculation, the method comprises the following steps of: decoding an LLR (Local Library Ratio) by using Bob, sending the LLR to Alice through a classic channel in combination with an encryption technology, sorting absolute values of the LLR by Alice in a decoding iteration process, selecting l bit positions with low reliability, sending the bit positions to Bob, determining a bit value by Bob according to the bit positions with low reliability sent by Alice, and feeding back and sending the bit value to Alice, and correcting the LLR value by Alice according to bit information sent by Bob. According to the method disclosed by the invention, the code rate of the LDPC code can be flexibly adjusted along with the change of the state of the time-varying channel, and the negotiation efficiency is improved, so that the key rate of the system is improved. The method is excellent in performance in a time-varying channel environment, negotiation efficiency under a low signal-to-noise ratio condition can be remarkably improved, and an efficient and reliable information negotiation scheme is provided for practical application of a quantum secret communication system.

The invention relates to a cable tunnel bridge fire prediction method and device, electronic equipment and a storage medium. The cable tunnel bridge fire hazard prediction method comprises the following steps: establishing a cable tunnel bridge fire hazard numerical simulation model, establishing a cable tunnel bridge fire hazard simulation model based on FDS software, obtaining key parameters such as heat release rate, temperature distribution and flame spread boundary under different working conditions, and constructing a multi-time sequence sample data set; performing state discretization on continuous variables such as temperature and a spreading range, and estimating a node prior probability in combination with a statistical frequency; constructing a dynamic Bayesian network topological structure according to a causal relationship among a heat source, temperature and spread, and setting a cross-time slice node dependence path to realize time sequence modeling; inputting a training sample and performing parameter learning to generate a conditional probability table; in the prediction stage, multi-step reasoning is achieved through forward propagation, flame spreading range probability distribution and interval estimation of multiple time steps in the future are obtained, and the specific position where the flame arrives is predicted.

The invention discloses a one-dimensional structured data hypothesis test evaluation method based on zero-knowledge proof, and aims to verify and evaluate the distribution consistency of synthetic data and real data under the condition of strictly protecting the real data and sensitive statistical information thereof. The method comprises the following steps: firstly, for discrete variables and continuous variables, respectively calculating an expected frequency and an observation frequency by adopting a category frequency statistics mode and an equal-width binning mode, and measuring the distribution deviation of synthetic data and real data by adopting chi-square goodness of fit test; and then reconstructing the calculation process of the test statistics into an equivalent form only containing integer addition and multiplication so as to adapt to finite field calculation. And based on the integer formula, constructing a constraint circuit and generating a zero-knowledge proof. According to the invention, a prover can prove the correctness of the hypothesis test result to a verifier under the condition that real data is not disclosed, so that the privacy of the real data is guaranteed, and the credible evaluation of the effectiveness of the synthetic data is realized.

The invention discloses a causal graph inference method and a causal graph inference system which are oriented to strong nonlinear continuous variable distribution and based on RealNVP and micro NOTEARS constraints. According to the method, a structure parameter matrix is constructed to represent candidate causal connection, parent variable condition input is constructed for each variable based on structure parameters, and accurate likelihood modeling is performed on the condition density of each variable by adopting a condition RealNVP normalization flow model. By constructing an objective function containing a conditional log-likelihood item, a sparse regular item and a NOTEARS style differentiable acyclic constraint item, a sparse causal structure meeting acyclic constraint is obtained by utilizing gradient optimization, and a causal graph is output. Further, based on the learned causal graph and a conditional RealNVP model, anti-fact inference is executed under a given intervention condition, and an anti-fact result is output. The method is suitable for strong nonlinear relation and complex continuous distribution scenes, and has the advantages of being stable in structure inference, high in interpretability and capable of supporting anti-fact analysis.

The invention discloses a token stream guide variable code rate image compression method oriented to unification of perception and understanding. The method comprises the following steps of: 1, acquiring a two-dimensional image, and processing the two-dimensional image to acquire a one-dimensional token sequence; 2, processing the one-dimensional token sequence through a variable token mask to generate a binary compressed bit stream; 3, decoding the compressed bit stream to obtain an unmasked token sequence, and carrying out dynamic prediction on the unmasked token sequence to recover a complete token sequence; and 4, realizing human perception through the receiving end I after the complete token sequence is recovered, realizing machine perception through the receiving end II after the complete token sequence is recovered, and finally realizing image compression. The method has the capability that a single model supports the continuous variable bit rate, supports a large language model to directly perform semantic understanding based on the compressed code stream, and has the characteristics of low calculation complexity and low delay.

The invention belongs to the field of continuous variable quantum key distribution, and particularly relates to a spline coordination method suitable for discrete modulation continuous variable quantum key distribution, which can effectively reduce the data coordination difficulty and improve the operation speed of data coordination by using constellation points to replace a quantization mode of mapping a binary sequence by a single orthogonal component. The method is an effective scheme easy to realize high-speed quantum secret communication. And the high-performance error correction code with a fixed code rate is obtained by using the characteristics of the RL-LDPC code, so that the difficulty in obtaining the error correction code is reduced. The method mainly comprises the steps of continuous variable quantization and multi-level coding and multi-level decoding (MLC-MSD). In the continuous variable quantization process, the continuous variables are mapped into the multi-level binary sequence through the constellation point division interval, the number of coding and decoding levels in spline coordination is reduced, and then the complexity of a data coordination model is reduced. In the MLC-MSD, the characteristic that the code rate is moderately modified while the high error correction performance of the RL-LDPC code is maintained is utilized, and the error correction code with the required code rate is obtained.

A method for optimization of multidimensional continuous functions using a quantum processor (50) is disclosed. The method comprises initializing (S400) quantum circuit parameters ({right arrow over (ω)}) to set an initial guess |ψ) of a function ƒ({right arrow over (x)}), running (S410) a variational quantum circuit U({right arrow over (ω)}) over n qubits of the quantum processor (50), implementing (S420) a quantum state tomography function of the individual qubits to estimate qubit parameters [θ, φ, r] of the function ƒ({right arrow over (x)}) for each qubit. The method further comprises estimating (S430) a vector of a continuous variable ({right arrow over (x)}) from the qubit parameters [θ, φ, r], estimating (S440) a value of the function ƒ({right arrow over (x)}) and a gradient ∀ƒ({right arrow over (x)}) of the function ƒ({right arrow over (x)}) at the point of the vector of the continuous variable ({right arrow over (x)}), updating (S450) the quantum circuit parameters ({right arrow over (ω)}) and iterating (S460) the steps S410-S450 until optimization of the function ƒ({right arrow over (x)}).

Detects errors that occur in a continuous variable state. [Solution] The quantum computing device comprises an initialization unit that prepares a continuous quantity state which is the target of a desired processing and a check qubit and initializes the check qubit, and a calculation unit that performs a coherent parity check on the continuous quantity state using the check qubit to detect errors that have occurred in the continuous quantity state.

The invention provides a fault diagnosis method for open set domain generalization under a continuous variable working condition. The method comprises the following steps: firstly, constructing a training sample with time domain data, a working condition index and a fault category index; converting the time domain data into a time-frequency domain and extracting semantic features; a class-specific semantic reconstruction module is adopted to classify the semantic features; a cross-domain alignment module is adopted to estimate mutual information of the semantic features of the training samples and the working condition indexes, and the smaller the mutual information is, the lower the working condition dependence degree is; constructing joint loss including cross-domain alignment loss; the cross-domain alignment loss constrains the feature distribution consistency between continuous domains based on mutual information minimization; back propagation training is carried out by adopting joint loss, so that the class-specific semantic reconstruction module learns and extracts the working condition invariant feature extraction capability; and performing fault classification by using the trained feature extraction module and the class-specific semantic reconstruction module. According to the method, fault diagnosis can be realized under a cross-continuous change working condition, and meanwhile, the method has the capability of identifying unknown fault types.

The invention discloses a code rate adaptive data coordination method suitable for continuous variable quantum key distribution, and belongs to the technical field of continuous variable quantum key distribution. Aiming at the problem that the existing method cannot realize stable and efficient extraction of a key in a key distribution system, high coordination efficiency under a specific code rate is realized by using a protograph LDPC code, and then code rate compatibility is realized through a specific matrix puncturing technology, so that an error floor is effectively reduced, and the key distribution efficiency is improved. And stable and efficient data coordination is realized in a relatively large signal-to-noise ratio range. Through simulation tests, the self-adaptive range of the signal-to-noise ratio is 0.028-0.252, the coordination efficiency can reach more than 95%, the average frame error rate is about 30%, the robustness of the system is effectively improved, and the application of the continuous variable quantum key distribution technology in actual scenes is promoted.

The invention relates to the technical field of semiconductor manufacturing, and provides a cavity temperature rise monitoring method and semiconductor process equipment. The method comprises the steps that real-time data of related variables influencing the heating process of the process chamber are obtained, the real-time temperature actual value of a heating part in the process chamber is obtained, the related variables comprise continuous variables and digital variables, and the digital variables comprise the water passing state and the temperature control mode of the process chamber; the real-time data of the related variables are input into a temperature prediction model obtained through pre-training, the real-time temperature prediction value of the heating component is output through the temperature prediction model, and the temperature prediction model is obtained through training based on the historical temperature actual value of the heating component and the historical data of the related variables; by comparing the real-time actual temperature value of the heating component with the real-time predicted temperature value of the heating component, the real-time monitoring result of the temperature rising process of the process chamber is obtained, so that the accuracy of the monitoring result of the temperature rising process of the process chamber is improved.

The invention provides a scheduling method and system of an integrated energy system and a storage medium, and the method comprises the steps: constructing a mixed integer nonlinear programming model with the minimum total operation cost as a target, carrying out the iterative solving of the model until the upper and lower bounds converge, solving a main problem to obtain a tentative solution of a unit start-stop scheme and the lower bound of the current iteration, and carrying out the scheduling of the unit start-stop scheme. The main problem comprises a regularization item and is constrained by a cut plane, and a penalty coefficient of the regularization item is adjusted according to a distance between a tentative solution and a historical optimal solution and a lower bound gain rate; fixing a tentative solution of the discrete variable, setting solution precision according to a current upper and lower bound gap and a convergence rate, and solving an energy flow sub-problem to obtain a continuous variable solution and an upper bound; if the sub-problem is feasible, weighted averaging is carried out based on dual solutions in historical iteration to generate an optimal cut plane, and the optimal cut plane is added to the main problem; and if the sub-problem is not feasible, identifying a key constraint cluster causing infeasibility, generating a feasible cut plane and adding the feasible cut plane to the main problem.

The invention provides a switching power supply system-oriented efficient global optimal multi-physics co-simulation method and system, and the method comprises the steps: defining a hybrid design space containing discrete variables and continuous variables, and constructing a composite objective function; generating a small number of parameter combinations of the discrete variables and the continuous variables by adopting a mixed horizontal orthogonal array to form an initial sample set; performing multi-physical field simulation on the initial sample set to obtain a performance observation value; constructing an initial Gaussian process proxy model based on the initial sample set and the performance observation value; a discrete forced continuous random sampling strategy is adopted to generate a large number of global uniform samples, iteration is carried out through a Bayesian optimization framework based on the initial Gaussian process proxy model, and optimal candidate points are obtained; and when the composite objective function converges or reaches the maximum number of simulation times, outputting a global optimal design parameter combination.

The application discloses a kind of based on formalization method's trusted machine learning model explanation method and device, it is related to artificial intelligence technical field, the method includes obtaining target machine learning model and its input characteristic value;Input characteristic value is compiled using formalization method, to obtain continuous variable;Continuous variable is discretized, to obtain the input characteristic value after discretization;The logic variable compilation of characteristic value after discretization is carried out, to obtain the variable after formalization compilation;According to the decision rule of model, the logic expression after formalization compilation is simplified, to obtain the rule reason of the expression of implication, that is, decision;Rule reason is obtained using natural language representation, to obtain the explanation result of model.The application uses formalization method to explain trusted machine learning model, compared with traditional explanation method, can more accurately reveal the internal logic of model decision, to improve the reliability of model explanation.

The invention discloses a continuous variable quantum secret sharing method based on a state distinguishing detector. The method comprises the following steps: a user generates a binary key sequence; a QPSK state signal is generated; sequentially coupling the QPSK state signals through an asymmetric beam splitter; the Dealer uses the SDD to estimate the received signal; repeating the steps, and extracting an original combined key; obtaining an original key of each user based on a key sequence combination principle; and calculating a key rate, and extracting a key to complete encryption message decoding. According to the method, quantum state distinguishing is completed through a state distinguishing detector (SDD), and the SDD is allowed to directly determine bit information directly transmitted by different users by identifying mixed state categories, so that each user does not need to declare and discard respective original key subsets, a mapping rule is directly restored, key loss is reduced, and the user experience is improved. And the key rate performance of the SDD-CVQSS protocol is improved. In addition, compared with the traditional CVQSS, the SDD-CVQSS shows obvious advantages in key performance indexes of the key rate and the maximum transmission distance.

An embodiment for generating interpretability data for a target machine learning model by determining sensitive ranges of continuous variables for post-modeling analysis. The embodiment may receive, for the target machine learning model, historical data including a series of relevant continuous variables. The embodiment may generate bins for each relevant continuous variable in the series of relevant continuous variables. The embodiment may calculate overall sensitivity values for pairs of neighbor bins. The embodiment may, in response to the calculated sensitivity value of respective pairs of neighbor bins being below a predetermined threshold value, merge the respective pairs of neighbor bins. The embodiment may generate interpretability data for the target machine learning model based on the merged respective pairs of neighbor bins.

This optimization device is configured to comprise: a variable transformation part (1) that acquires a first continuous variable, which is represented as either a real number value or an integer value, and transforms the first continuous variable into a candidate solution, which is a binary variable; a variable inverse transformation part (2) that inversely transforms the candidate solution into a second continuous variable; an evaluation value calculation part (3) that calculates an evaluation value of the second continuous variable; and a transformation rule update part (4) that updates, on the basis of the evaluation value, each of the rule of transformation into a candidate solution performed by the variable transformation part 1 and the rule of inverse transformation into a second continuous variable performed by the variable inverse transformation part 2.

The invention discloses an optimal communication defense resource allocation method based on two-stage hybrid optimization. According to the technical scheme, the method is characterized by comprising the steps that in the first stage, global configuration rough search is conducted, global exploration is conducted on the AC-ODRA problem under an alternating current model through a myxobacteria algorithm, the deployment position (discrete variable) of defense resources is rapidly determined, and a high-quality candidate solution is obtained; in the second stage, resource input fine adjustment is conducted, specifically, for the candidate solutions in the first stage, the deployment positions of the candidate solutions are fixed, and high-precision local optimization is conducted on the specific resource input amount (continuous variables) under the augmented Lagrange framework through an adaptive torque estimation optimization method of multi-starting-point random disturbance guided by instrument importance. According to the method, global search and local fine tuning are combined, the solving precision and robustness of the AC-ODRA problem are remarkably improved, a defense resource allocation scheme with lower cost can be obtained on the premise of guaranteeing the safety of a power grid, and the method has important theoretical value and application prospects.

The invention provides a relaxation-regularization-based power network multi-error parameter identification method and device, and the method comprises the steps: building a multi-measurement section considering error parameter number constraint and a mixed integer nonlinear programming model of regularization weighted least square estimation based on a state estimation model of weighted least square of a power system; converting the mixed integer nonlinear programming model on the basis of a residual equation, so that the quantity of variables is reduced and cannot be increased along with the increase of the quantity of measurement sections, solving the converted model by utilizing IPOPT, sorting continuous variables si of all parameters in a descending order after solving, selecting the first k parameters as suspicious parameters, and calculating the number of the suspicious parameters; checking each suspicious parameter one by one, and identifying wrong parameters by using a state augmentation method; according to the invention, a plurality of coupling error parameters can be correctly identified at the same time.

The present invention discloses a phase compensation method for a continuous variable system based on Stokes parameter encoding. The process is as follows: calculate the Jones matrix of the encoded light beam at the entire transmitting end; calculate the theoretical output formulas of Stokes parameters S2 and S3; plot the theoretical S2 and S3 output curves; take the maximum values of the theoretical S2 and S3 output curves; plot the actual detected S2 and S3 output curves; take the maximum values of the actual detected S2 and S3 output curves; calculate the difference between the maximum actual value of S2 and the maximum theoretical value, calculate the difference between the maximum actual value of S3 and the maximum theoretical value, and the average value after the two differences is the compensation phase ψ; superimpose the compensation phase ψ into ψ2, that is, the phase of the entire continuous variable system based on Stokes parameter encoding is compensated. The above method solves the phase difference caused by the fast and slow axes of the optical fiber changing with the environment, and ensures the accuracy of Stokes parameter encoding.

The application discloses a linear guide rail SOMC design method, equipment, medium and program product, including: (1) based on the linear guide rail structure characteristics and static load analysis, the simulation model and SOMC design model are constructed with static stiffness as the target, weight and maximum contact stress as the constraint; (2) the design space is constructed, the initial population is generated and the database is established, the high influence continuous variable set and the high influence discrete variable set are obtained through SRC, CEA sensitivity analysis method; (3) the corresponding candidate set is generated based on the two types of variable sets, and the complete candidate guide rail set is obtained through individual pairing; (4) the random forest prediction model is established, the excellent subset is screened and the best offspring guide rail is selected; (5) the database and the prediction model are updated after simulation evaluation, and the step (3) is returned until the index reaches the standard, and the optimal parameter value is output. The application can effectively balance the SOMC process with stiffness as the optimization target, weight and maximum contact stress as the constraint, and realize higher precision and better comprehensive performance.

The invention discloses an all-working-condition risk quantification method applied to a new energy civil aircraft power system, which comprehensively considers the influence of discrete factors and continuous factors, quantifies the performance risk of the power system under all working conditions into a probability density distribution function, and comprises the following steps: defining a discrete variable and continuous variable distribution set; establishing a power system performance change degree probability density function PDFcon under the influence of continuous variables; establishing a power system performance probability density function PDFsys under the common influence of the continuous variable and the discrete variable; and step 4, quantifying the system risk, namely quantifying the system risk under the common influence of the discrete variable and the continuous variable into a probability density distribution function for evaluating the risk of the system at the moment. According to the method, quantitative analysis of all-working-condition risks can be realized, and reliable support is provided for airworthiness verification, safety evaluation and engineering application of a new energy power system.

The application discloses a multi-dimensional time sequence anomaly detection method based on standard Gini index composition, and belongs to the technical field of time sequence anomaly detection. In view of the problem that the existing time sequence anomaly detection method cannot learn the relationship between discrete values and continuous values, when measuring the similarity of sensors, the continuous variable is discretized, and the similarity value between the sensors is obtained by calculating the standard Gini index between the two sensors. The traditional Gini index has a multi-value bias problem, that is, it is biased to give a score to a value with more values and higher attributes, and the standard Gini index can effectively alleviate this problem. The standard Gini index can effectively depict the similarity between sensors with different value types; and the application gives each sensor an embedding vector, which can represent the unique characteristics of each sensor. When reconstructing the data, the embedding vector and the corresponding transformation feature are connected, so that the original data can be better reconstructed.

The invention relates to the technical field of LED driving chips, and discloses an LED driving chip design management method and system based on deep learning, and the method comprises the steps: collecting chip design parameters, application scene data, user behavior data and environment parameters, and obtaining original data; adopting a KNN interpolation algorithm to fill missing values in the original data, and using an isolated forest algorithm to identify and remove abnormal samples to obtain preprocessed data; mapping category variables in the preprocessed data into low-dimensional vectors by adopting embedded codes, performing Z-score standardization on continuous variables, and extracting dynamic control features in a sliding window for user behavior data to obtain a feature data set; inputting the feature data set into a FlashLED-Net hybrid model, dynamically adjusting chip design parameters and a multi-flash mode control strategy, and outputting optimized chip design parameters and control codes; according to the method, manual intervention and trial and error links are greatly reduced, and the chip design period is shortened.

The application provides a real-time entropy evaluation post-processing quantum random number generation method. The quality of random numbers determines the privacy and security of a communication system. Quantum detection is inevitable in the quantum random number generation process, which will introduce side information. Therefore, the quantum noise entropy content of the system must be strictly evaluated, and the random numbers must be post-processed by using a security information theory extractor. The application proposes to reconstruct the quantum state phase space distribution in real time in a continuous variable quantum random number generation scheme and measure the deviation from the ideal value. If the deviation reaches the rejudgment threshold, the entropy evaluation is updated in real time, so as to adjust the size of the post-processing matrix in real time. The seed used to construct the random extractor is also updated in real time. On this basis, the information theory security generalized hash post-processing of multiple quantum random numbers is realized in parallel. The application provides a cost-intensive and expandable random number real-time entropy evaluation post-processing scheme, which can effectively improve the actual security and practicability of the quantum random number generator.