System evolution capability verification method and system based on breakpoint regression and entropy analysis

Abstract

The embodiment of the invention discloses a system evolution capability verification method and system based on breakpoint regression and entropy analysis, and the method comprises the steps: constructing a system evolution evaluation system comprising a plurality of evaluation dimensions; a stable closed environment is provided through an environment control module, and operation data of a target system in the closed environment is collected through a multi-mode sensor network; adopting a preset breakpoint detection algorithm, setting a significance level index, analyzing the operation data, identifying a state sudden change point of the target system, and calculating a breakpoint regression design score; based on an information entropy principle, calculating a structure entropy, a function entropy and an energy entropy; calculating an evolutionary ability index according to the structural entropy, the functional entropy, the energy entropy and the breakpoint regression design score; and judging whether the target system has the autonomous evolution ability or not according to the evolution ability index. According to the invention, precise control and high-precision multi-dimensional data acquisition of the system environment are realized, and quantitative verification of the system evolution capability is realized.

Description

Technical Field

[0001] This application relates to the field of scientific verification technology for complex systems, specifically to a method and system for verifying the evolutionary capability of a system based on breakpoint regression and entropy analysis. Background Technology

[0002] Non-living systems are systems that do not possess the characteristics of life. They do not engage in life activities such as metabolism, growth, reproduction, sensing, or adaptation; their changes are primarily governed by physical and chemical laws. Verification of whether non-living systems possess autonomous evolutionary capabilities typically revolves around factors such as variation, heredity, and selection, observing whether these factors lead to continuous functional adaptation and increased complexity. Verifying the evolutionary capabilities of non-living systems can provide new design ideas and optimization methods for fields such as materials science, artificial intelligence, and systems engineering.

[0003] In existing technologies, the verification methods for whether non-living systems have the ability to evolve autonomously mainly have the following shortcomings: 1) One-sided indicators: focusing only on a single dimension, such as complexity, leads to a high false positive rate; 2) Coarse data: low data sampling rate and poor environmental control result in a signal-to-noise ratio that is usually less than 20dB; 3) Method limitations: mainly relying on subjective threshold setting, resulting in poor repeatability; 4) Long verification cycle: using traditional methods for verification, the verification cycle is generally more than 6 months, which is time-consuming. Summary of the Invention

[0004] In view of the above problems, this application is made in order to provide a system and method for verifying the evolutionary capability of a system based on regression discontinuity and entropy analysis to overcome or at least partially solve the above problems.

[0005] According to one aspect of the embodiments of this application, a method for verifying the evolutionary capability of a system based on regression discontinuity and entropy analysis is provided, including: Construct a system evolution evaluation framework that includes multiple evaluation dimensions; these dimensions include: structural complexity, functional diversity, environmental adaptability, energy utilization efficiency, and information processing capability. The environmental control module provides a stable closed environment for the target system, and the multimodal sensor network collects the operating data of the target system in the closed environment. A pre-defined breakpoint detection algorithm is used, a significance level index is set, the running data is analyzed, the state change points of the target system are identified, and the breakpoint regression design score is calculated. Based on the principle of information entropy, we calculate the structural entropy of the target system in the dimension of structural complexity, the functional entropy in the dimension of functional diversity, and the energy entropy in the dimension of energy utilization efficiency. The evolutionary capability index is calculated based on structural entropy, functional entropy, energy entropy, and regression discontinuity design score. Based on the evolutionary capability index, determine whether the target system has the ability to evolve autonomously.

[0006] Optionally, providing a stable, enclosed environment for the target system through an environmental control module, and further collecting operational data of the target system in the enclosed environment through a multimodal sensor network, includes: The environmental control module provides the target system with a closed environment where the control accuracy of environmental parameters is within a preset range; the environmental parameters include temperature, humidity, and vibration. The system uses mechanical, optical, thermal, and electromagnetic sensors in a multimodal sensor network to collect operational data of the target system in a closed environment at a sampling frequency that meets the sampling requirements.

[0007] Optionally, a preset breakpoint detection algorithm is used, a significance level index is set, the operating data is analyzed, the state change points of the target system are identified, and the breakpoint regression design score is calculated, which further includes: The system's evolutionary capability index is determined based on operational data, and the algorithm information density is used as the driving variable for regression at breakpoints. Using a breakpoint regression model corresponding to a pre-defined breakpoint detection algorithm, the state change points of the target system are identified, and the jump effect at the state change points is calculated. The jump effect at the state change point is standardized and normalized to obtain the discontinuity regression design score.

[0008] Optionally, the preset breakpoint detection algorithm is an improved Bai-Perron multi-structure breakpoint detection algorithm; The improved Bai-Perron multi-structure breakpoint detection algorithm includes: using the Bayesian information criterion to determine the optimal number of breakpoints, using the bootstrap method for sample processing, and setting the minimum segment length.

[0009] Optionally, determining whether a target system possesses autonomous evolutionary capability based on the evolutionary capability index further includes: If the evolutionary capability index is greater than the index threshold and the probability corresponding to the assumption that the target system does not have autonomous evolution capability is less than the probability threshold, then the target system is determined to have autonomous evolution capability.

[0010] Optionally, the metrics for structural complexity include: number of components, connection density, hierarchy depth, and modularity index.

[0011] According to another aspect of the embodiments of this application, a system evolution capability verification system based on regression discontinuity and entropy analysis is provided, comprising: The building module is used to construct a system evolution evaluation framework that includes multiple evaluation dimensions, including: structural complexity, functional diversity, environmental adaptability, energy utilization efficiency, and information processing capability. The environmental control module is used to provide a stable, closed environment for the target system; Multimodal sensor networks are used to collect operational data of a target system in a closed environment; The breakpoint analysis module is used to analyze the running data using a preset breakpoint detection algorithm and a significance level index, to identify the state change points of the target system and calculate the breakpoint regression design score. The entropy calculation module is used to calculate the structural entropy of the target system in the dimension of structural complexity, the functional entropy in the dimension of functional diversity, and the energy entropy in the dimension of energy utilization efficiency, based on the principle of information entropy. The evolutionary capability verification module is used to calculate the evolutionary capability index based on structural entropy, functional entropy, energy entropy, and breakpoint regression design score; and to determine whether the target system has the ability to evolve autonomously based on the evolutionary capability index.

[0012] According to another aspect of the embodiments of this application, a computing device is provided, including: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-mentioned system evolution capability verification method based on breakpoint regression and entropy analysis.

[0013] According to another aspect of the embodiments of this application, a computer storage medium is provided, wherein at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to perform the operation corresponding to the above-described system evolution capability verification method based on breakpoint regression and entropy analysis.

[0014] According to another aspect of the embodiments of this application, a computer program product is provided, including at least one executable instruction, which causes a processor to perform operations corresponding to the above-described system evolution capability verification method based on breakpoint regression and entropy analysis.

[0015] According to the technical solution provided in this application, a system evolution evaluation system with multiple evaluation dimensions is constructed. An environmental control module provides a stable closed environment for the target system, and a multimodal sensor network collects the operating data of the target system in this closed environment. This achieves precise control of the system environment and high-precision multi-dimensional data acquisition, effectively improving data accuracy and comprehensiveness. Innovatively, regression breakdown and entropy analysis are introduced into the verification of the system's autonomous evolution capability. Regression breakdown analysis is performed on the operating data of the target system to identify state mutation points and calculate the regression breakdown design score. Based on the principle of information entropy, the structural entropy corresponding to the structural complexity dimension, the functional entropy corresponding to the functional diversity dimension, and the energy entropy corresponding to the energy utilization efficiency dimension are calculated. These are then used to calculate the evolution capability index. Based on the evolution capability index, it is possible to accurately determine whether the target system possesses autonomous evolution capability, achieving quantitative verification of the system's autonomous evolution capability. This also effectively improves repeatability, reduces energy consumption, shortens the verification cycle, and significantly saves time costs. Furthermore, this solution can provide a quantitative standard for the essential distinction between living and non-living systems, and has significant application value in fields such as artificial intelligence, robot autonomy assessment, and reliability verification of complex mechanical systems.

[0016] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of the embodiments of this application and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of this application more obvious and understandable, specific implementation methods of the embodiments of this application are described below. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart illustrating a system evolution capability verification method based on regression discontinuity and entropy analysis according to an embodiment of this application is shown. Figure 2 A schematic diagram of the technical framework of a system evolution capability verification method based on regression discontinuity and entropy analysis is shown. Figure 3 A schematic diagram illustrating the principle of a system evolution capability verification method based on regression discontinuity and entropy analysis is shown. Figure 4 The graph showing the entropy change trend of a certain industrial robot system is presented. Figure 5A diagram showing the comparison of system complexity indices between living and non-living systems is presented. Figure 6 A structural block diagram of a system evolution capability verification system based on regression discontinuity and entropy analysis according to an embodiment of this application is shown; Figure 7 A schematic diagram of the structure of a computing device according to an embodiment of this application is shown. Detailed Implementation

[0018] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0019] Figure 1 A flowchart illustrating a system evolution capability verification method based on regression discontinuity and entropy analysis according to an embodiment of this application is shown, as follows: Figure 1 As shown, the method includes the following steps: Step S101: Construct a system evolution evaluation framework that includes multiple evaluation dimensions.

[0020] This application constructs a system evolution assessment framework encompassing multiple evaluation dimensions, which can quantitatively assess whether a target system possesses autonomous evolutionary capabilities. The target system refers to a non-living system whose autonomous evolutionary capabilities need to be verified, such as mechanical systems, natural non-living systems, electronic systems, and physical systems. The multiple evaluation dimensions include: structural complexity, functional diversity, environmental adaptability, energy utilization efficiency, and information processing capability.

[0021] Those skilled in the art can set corresponding indicators for each evaluation dimension according to actual needs. Taking the structural complexity dimension as an example, the indicators for the structural complexity dimension may include: number of components, connection density, hierarchy depth, and modularity index. Specifically, connection density can be represented by ρ, ρ=2L / [N(N-1)]; where L represents the actual number of connections; and N represents the number of components. The modularity index can be represented by Q, Q∈[0,1].

[0022] Step S102: Provide a stable closed environment for the target system through the environmental control module, and collect the operating data of the target system in the closed environment through the multimodal sensor network.

[0023] The environmental control module provides a closed environment for the target system, ensuring that the environmental parameters are controlled within a preset precision range. These environmental parameters include temperature, humidity, vibration, and electromagnetic fields. For example, the environmental control module can maintain a stable closed environment with temperature variations within ±0.1℃, humidity variations within ±1%RH, and vibration variations less than 0.01g, allowing the target system to conduct closed-environment experiments. Those skilled in the art can also set other environment-related parameters, which are not specifically limited here.

[0024] By utilizing mechanical, optical, thermal, and electromagnetic sensors within a multimodal sensor network, operational data of the target system in a closed environment is acquired at sampling frequencies that meet sampling requirements. Specifically, the sampling frequency can be greater than or equal to 1 kHz, achieving high-precision data acquisition and effectively improving data accuracy.

[0025] Step S103: Using a preset breakpoint detection algorithm, setting a significance level index, analyzing the running data, identifying the state change points of the target system, and calculating the breakpoint regression design score.

[0026] Regression Discontinuity Design (RDD) is a quasi-experimental research method and one of the core methods of causal inference, primarily used to identify changes in the effect of a treatment at a critical point. In existing technologies, RDD is mainly applied in fields such as economics to estimate threshold effects. Recent studies have applied RDD to ecology and complex systems, for example, to analyze threshold effects of species diversity in ecology and critical behavior of phase transitions in complex systems. However, no relevant schemes have been found to apply RDD to verifying the autonomous evolutionary capacity of systems. This application innovatively introduces both RDD and entropy analysis into the verification of the autonomous evolutionary capacity of systems to determine whether the target system possesses autonomous evolutionary capacity. The RDD design can effectively control confounding variables and identify causal effects.

[0027] The process involves determining the system's evolutionary capability index based on operational data, using algorithm information density as the driving variable for regression discontinuity. A regression discontinuity model corresponding to a pre-defined discontinuity detection algorithm is employed to identify state abrupt changes (i.e., discontinuities) in the target system and calculate the jump effect at these points. The jump effect at each discontinuity is then standardized and normalized to obtain the regression discontinuity design score. This score is a quantitative indicator measuring whether a significant structural change exists in the target system at the algorithm information density discontinuity.

[0028] The formula for calculating the regression discontinuity model is:

[0029] Where Y represents the system evolution capability index, which is determined based on the operating data of the target system. For example, the system evolution capability index may be the rate at which new functions appear. AID represents the algorithm information density, which is the driving variable for regression discontinuity. This application introduces the algorithm information density as the driving variable for regression discontinuity, which can realize cross-system consistency measurement. This represents the breakpoint threshold, which can be set. The theoretical value is 0.3 bits / kg; D represents the processing variable, when AID ≥ At that time, D=1; The jump effect at the state mutation point is used to measure the degree of activation of autonomous evolutionary ability. The jump effect can be calculated based on relevant data on both sides of the state mutation point (such as the system evolutionary ability index); f(·) represents the local polynomial control function. and ε represents the model parameters; ε represents the error term.

[0030] Specifically, the preset breakpoint detection algorithm can be an improved Bai-Perron multiple structural breakpoint detection algorithm. The standard Bai-Perron algorithm is a metrological method for detecting multiple structural breaks in time series data. It can systematically identify structural changes in time series models even when the number, location, and form of breakpoints are unknown.

[0031] The improved Bai-Perron multi-structural breakpoint detection algorithm may include: determining the optimal number of breakpoints using the Bayesian Information Criterion (BIC), processing samples using a bootstrap method, and setting a minimum segment length. The introduction of the bootstrap method effectively improves the reliability for small samples; the minimum segment length can be set using l. min It means, l min =max(15, 0.1T), where T represents the total number of samples. The BIC value can be calculated using the following formula: BIC = ln(σ) 2 ) + (m+1)ln(T) / T Where, σ 2 represents the residual variance; m represents the number of breakpoints; T represents the total number of samples.

[0032] The hypothesis testing framework established in this application is as follows: H0: The target system does not have the ability to evolve autonomously, that is, the apparent "evolution" of the target system is a random fluctuation caused by environmental noise; H1: The target system has the ability to evolve autonomously, that is, the target system can generate autonomous evolution with directionality and continuity.

[0033] The significance level index refers to the upper probability limit of committing a Type I error (false positive) in hypothesis testing; that is, the maximum allowable probability of incorrectly rejecting H0 when the null hypothesis H0 is true. The significance level index can be represented by α, and in specific application scenarios, α can be set to 0.01.

[0034] Step S104: Based on the principle of information entropy, calculate the structural entropy of the target system in the dimension of structural complexity, the functional entropy in the dimension of functional diversity, and the energy entropy in the dimension of energy utilization efficiency.

[0035] Based on the principle of information entropy, calculate the structural entropy H of the target system in the dimension of structural complexity. s Functional entropy H corresponding to the functional diversity dimension f And the energy entropy H corresponding to the energy utilization efficiency dimension. e .

[0036] Specifically, structural entropy H s The calculation formula is: H s =-Σp i log2p i ; where p i This represents the probability of the i-th structural event occurring.

[0037] Functional entropy H f The calculation formula is: H f =-Σ(f j / F)log2(f j / F); where f j Let F = Σf represent the probability of the j-th function occurring. j .

[0038] Energy entropy H e The calculation formula is: H e =-Σe k log2e k ; where e k This represents the probability of the k-th energy event occurring.

[0039] Step S105: Calculate the evolutionary capability index based on structural entropy, functional entropy, energy entropy, and the breakpoint regression design score.

[0040] This application fully integrates structural entropy, functional entropy, energy entropy, and regression discontinuity design score to construct a formula for calculating the evolutionary capability index. The formula for calculating the evolutionary capability index is as follows: ECI = 0.35×ΔH s + 0.28×ΔH f + 0.22×ΔH e+ 0.15×RDD score Where ECI represents the evolutionary capacity index; ΔH s H represents the structural entropy s The change value, ΔH s According to the structural entropy H s Calculation yielded ΔH f The change in functional entropy, ΔH f According to the functional entropy H f Calculation yielded ΔH e Represents energy entropy H e The change value, ΔH e Based on energy entropy H e Calculated; RDD score represents the score of the regression discontinuity design; 0.35, 0.28, 0.22 and 0.15 are weights, which are determined by principal component analysis. Specifically, the weights can be obtained through multiple (e.g., 1000) Monte Carlo simulations.

[0041] Optionally, for the environmental adaptability dimension and the information processing capability dimension, the corresponding entropy can also be calculated and integrated into the calculation of the evolutionary capability index. The weights in the evolutionary capability index calculation formula can be adjusted so that the obtained evolutionary capability index can more comprehensively reflect whether the target system has the ability to evolve autonomously.

[0042] Step S106: Determine whether the target system has the ability to evolve autonomously based on the evolutionary capability index.

[0043] To more accurately determine whether a target system possesses autonomous evolution capabilities, the determination process can also incorporate the probability p corresponding to the hypothesis that the target system does not possess autonomous evolution capabilities (the probability corresponding to the null hypothesis H0). Specifically, the probability p can be the probability of observing the current sample result under the premise that the null hypothesis H0 is true. The smaller the p value, the more sufficient the evidence to reject the null hypothesis H0.

[0044] Specifically, if the evolutionary capability index (ECI) is greater than the exponent threshold and the probability corresponding to the assumption that the target system does not possess autonomous evolutionary capability is less than the probability threshold, then the target system is determined to possess autonomous evolutionary capability. Multiple experiments have demonstrated that when the exponent threshold is set to 0.7 and the probability threshold is set to 0.01, it can accurately determine whether the target system possesses autonomous evolutionary capability. That is, when ECI > 0.7 and p < 0.01, the target system is determined to possess autonomous evolutionary capability.

[0045] Figure 2 This diagram illustrates the technical framework of a system evolution capability verification method based on regression discontinuity and entropy analysis. Figure 2As shown, the entire processing of this method can be divided into three stages: stage 1 is the data acquisition stage, stage 2 is the breakpoint and entropy value analysis stage, and stage 3 is the capability verification stage.

[0046] The data acquisition phase corresponds to the data acquisition layer. In this layer, an environmental control module provides a stable, enclosed environment for the target system (e.g., temperature control, vibration control, electromagnetic shielding, etc.). A multimodal sensor network is used to collect the target system's operational data in this enclosed environment. This network can include mechanical, optical, thermal, and electromagnetic sensors, enabling systematic, diverse, and comprehensive collection of the target system's operational data, thus offering resilience against risks. To facilitate the processing of the collected operational data, such as breakpoint regression analysis, a series of data preprocessing steps, such as filtering, standardization, and alignment, can also be performed.

[0047] The breakpoint and entropy analysis stage corresponds to the breakpoint regression and entropy analysis layer. In the breakpoint regression and entropy analysis layer, time series segmentation modeling, Bayesian breakpoint detection, and mutation feature quantification analysis are performed to identify the state mutation points of the target system and calculate the breakpoint regression design score. It also calculates the entropy corresponding to each evaluation dimension, such as structural entropy, functional entropy, and energy entropy.

[0048] The capability verification stage corresponds to the evolutionary capability verification layer. The evolutionary capability index is calculated, and based on the evolutionary capability index, it is determined whether the target system has the ability to evolve autonomously.

[0049] Figure 3 A schematic diagram illustrating the principle of a system evolution capability verification method based on regression discontinuity and entropy analysis is shown, as follows: Figure 3 As shown, a multimodal sensor network monitors and collects operational data of the target system in a closed environment. Environmental interference filtering and data standardization are performed in the real-time data acquisition layer, and the processed data flows into the real-time stream processing layer. In the real-time stream processing layer, the time series is cached using a sliding window, breakpoint regression analysis is performed using an online breakpoint detection engine, and structural entropy, functional entropy, and energy entropy are calculated in real time using an entropy calculation engine, thereby calculating the evolutionary capability index in real time. The online breakpoint detection engine can employ a real-time Bai-Perron algorithm processor implemented on an FPGA, and the entropy calculation engine can employ a 128-bit floating-point unit conforming to the IEEE 754-2008 standard. This application designs an FPGA-based real-time processing architecture, realizing high-speed data acquisition, breakpoint analysis, and entropy calculation, significantly improving processing efficiency.

[0050] Data processed by the real-time stream processing layer can be stored in the system status time-series database for unified management and effective storage. The real-time decision-making layer verifies autonomous evolution capabilities, provides anomaly warnings, and generates verification reports compliant with ISO / IEC 17025 standards. The real-time decision-making layer can also connect to external systems via external system interfaces. Furthermore, the data processed by the real-time stream processing layer and the results obtained from the real-time decision-making layer can be visualized, specifically through dashboards, trend charts, etc. Warnings can also be issued via display units and buzzers when anomalies occur.

[0051] Under the same testing environment, the system evolution capability verification method based on regression discontinuity and entropy analysis provided in this application was used to verify 1000 sets of data samples from non-living systems. Experiments show that the system evolution capability verification method based on regression discontinuity and entropy analysis provided in this application has a verification accuracy of over 98.7%, which is far higher than the verification accuracy of qualitative observation and traditional statistical methods. In terms of processing speed, compared with the verification cycle of 6 months required by traditional statistical methods, this application can complete the verification in only 72 hours, which greatly improves the processing speed and saves time costs significantly. In addition, compared with traditional statistical methods, the method provided in this application effectively improves repeatability and reduces energy consumption.

[0052] The present application will now be described with reference to specific embodiments.

[0053] In one embodiment, taking an industrial robot system as the target system as an example, the experimental setup is as follows: the robot model in the industrial robot system is KUKA KR 1000 Titan, and the multimodal sensor network includes a laser displacement meter (0.1μm), a 6-axis force sensor (0.01N), a thermal imager (0.1℃), etc., wherein the sampling frequency for force data is 5kHz, and the sampling frequency for other data is 1kHz; the experiment lasts for 30 days.

[0054] Figure 4 The graph showing the entropy change trend of an industrial robot system is shown below. Figure 4 As shown, the industrial robotic arm in the industrial robot system operates continuously, and the entropy change of the industrial robot system is monitored. Figure 4 It can be seen that the entropy value shows an overall upward trend, with a change in entropy value Δ of +0.45 bits. All detected breakpoints show negative changes, consistent with the theoretical expectation that non-living systems cannot autonomously reduce their entropy value (n=50), where n represents the number of experiments. Through breakpoint regression analysis and entropy calculation, the breakpoint location is found to be at 300 hours, with a BIC value of -12.45, p=0.008, and ΔH... s =+0.18, ΔHf =+0.22, ΔH e +0.15, RDD score The value is 0.31, and the calculated ECI (Evolutionary Capability Index) is 0.204. Since its ECI is less than 0.7, the industrial robot system is determined to lack autonomous evolution capability.

[0055] In another embodiment, Table 1 shows a data comparison between living systems and non-living systems. By comparing the ECI values ​​of living systems (such as bacteria, plants and animals) and non-living systems (mechanical systems, natural non-living systems), it can be demonstrated that the ECI values ​​of non-living systems are significantly lower than those of living systems. Furthermore, there exists an ECI threshold (approximately 0.7), and only systems exceeding this threshold can possess true autonomous evolutionary capabilities. Living systems cannot autonomously evolve from non-living systems because the ECI values ​​of non-living systems cannot reach the threshold required by living systems.

[0056] Table 1. Data Comparison between Living and Non-living Systems

[0057] Figure 5 A diagram illustrating the comparison of system complexity indices between living and non-living systems is shown, such as... Figure 5 As shown, the slope of the curve for living systems is 0.15 ± 0.03 (p < 0.001), while the slope of the curve for non-living systems is 0.01 ± 0.05 (p = 0.82).

[0058] According to the system evolution capability verification method based on regression discontinuity and entropy analysis provided in the embodiments of this application, a system evolution evaluation system with multiple evaluation dimensions is constructed. An environmental control module provides a stable closed environment for the target system, and a multimodal sensor network collects the operating data of the target system in the closed environment. This achieves precise control of the system environment and high-precision multi-dimensional data acquisition, effectively improving data accuracy and comprehensiveness. The method innovatively introduces regression discontinuity and entropy analysis into the verification of the system's autonomous evolution capability. Regression discontinuity analysis is performed on the operating data of the target system to identify state change points, calculate the regression discontinuity design score, and based on information... The entropy principle calculates the structural entropy of a target system in terms of structural complexity, functional entropy in terms of functional diversity, and energy entropy in terms of energy utilization efficiency. This entropy is then used to calculate an evolutionary capability index. Based on this index, it is possible to accurately determine whether a target system possesses autonomous evolutionary capability, thus achieving quantitative verification of the system's autonomous evolutionary capability. Furthermore, this approach effectively improves repeatability, reduces energy consumption, shortens the verification cycle, and significantly saves time and costs. This method also provides a quantitative standard for the essential distinction between living and non-living systems, and has significant application value in fields such as artificial intelligence, robot autonomy assessment, and reliability verification of complex mechanical systems.

[0059] Figure 6 A structural block diagram of a system evolution capability verification system based on regression discontinuity and entropy analysis according to an embodiment of this application is shown, as follows: Figure 6 As shown, the system includes: a construction module 610, an environmental control module 620, a multimodal sensor network 630, a breakpoint analysis module 640, an entropy calculation module 650, and an evolutionary capability verification module 660.

[0060] Module 610 is used to construct a system evolution evaluation framework that includes multiple evaluation dimensions. These dimensions include: structural complexity, functional diversity, environmental adaptability, energy utilization efficiency, and information processing capability.

[0061] The environmental control module 620 is used to provide a stable, closed environment for the target system.

[0062] The multimodal sensor network 630 is used to collect operational data of a target system in a closed environment.

[0063] The breakpoint analysis module 640 is used to: use a preset breakpoint detection algorithm, set a significance level index, analyze the running data, identify the state change points of the target system, and calculate the breakpoint regression design score.

[0064] The entropy calculation module 650 is used to calculate the structural entropy of the target system in the dimension of structural complexity, the functional entropy in the dimension of functional diversity, and the energy entropy in the dimension of energy utilization efficiency, based on the principle of information entropy.

[0065] The evolutionary capability verification module 660 is used to: calculate the evolutionary capability index based on structural entropy, functional entropy, energy entropy and breakpoint regression design score; and determine whether the target system has autonomous evolutionary capability based on the evolutionary capability index.

[0066] Optionally, the environmental control module 620 is further configured to: provide the target system with a closed environment where the control accuracy of environmental parameters is within a preset control accuracy range; wherein the environmental parameters include: temperature, humidity, and vibration. The multimodal sensor network 630 is further configured to: acquire the target system's operating data in the closed environment through mechanical sensors, optical sensors, thermal sensors, and electromagnetic sensors at a sampling frequency that meets the sampling requirements.

[0067] Optionally, the breakpoint analysis module 640 is further configured to: determine the system evolution capability index based on the running data, and use the algorithm information density as the driving variable for breakpoint regression; use the breakpoint regression model corresponding to the preset breakpoint detection algorithm to identify the state change points of the target system and calculate the jump effect at the state change points; and standardize and normalize the jump effect at the state change points to obtain the breakpoint regression design score.

[0068] Optionally, the preset breakpoint detection algorithm is an improved Bai-Perron multi-structure breakpoint detection algorithm; the improved Bai-Perron multi-structure breakpoint detection algorithm includes: using Bayesian information criterion to determine the optimal number of breakpoints, using bootstrapping method for sample processing, and setting minimum segment length.

[0069] Optionally, the evolutionary capability verification module 660 is further configured to: determine that the target system has autonomous evolutionary capability if the evolutionary capability index is greater than the index threshold and the probability corresponding to the hypothesis that the target system does not have autonomous evolutionary capability is less than the probability threshold.

[0070] Optionally, the metrics for structural complexity include: number of components, connection density, hierarchy depth, and modularity index.

[0071] The descriptions of the above modules refer to the corresponding descriptions in the method embodiments, and will not be repeated here.

[0072] The system evolution capability verification system based on regression discontinuity and entropy analysis provided in this application includes a construction module that builds a system evolution evaluation system with multiple evaluation dimensions, an environmental control module that provides a stable closed environment for the target system, and a multimodal sensor network that collects the operating data of the target system in the closed environment. This achieves precise control of the system environment and high-precision multi-dimensional data acquisition, effectively improving data accuracy and comprehensiveness. The system innovatively introduces regression discontinuity and entropy analysis into the verification of the system's autonomous evolution capability. It performs regression discontinuity analysis on the operating data of the target system to identify state change points, calculates the regression discontinuity design score, and, based on information... The entropy principle calculates the structural entropy of a target system in terms of structural complexity, functional entropy in terms of functional diversity, and energy entropy in terms of energy utilization efficiency. This entropy is then used to calculate an evolutionary capability index. Based on this index, it is possible to accurately determine whether a target system possesses autonomous evolutionary capability, thus achieving quantitative verification of the system's autonomous evolutionary capability. Furthermore, this approach effectively improves repeatability, reduces energy consumption, shortens the verification cycle, and significantly saves time and costs. This method also provides a quantitative standard for the essential distinction between living and non-living systems, and has significant application value in fields such as artificial intelligence, robot autonomy assessment, and reliability verification of complex mechanical systems.

[0073] This application provides a non-volatile computer storage medium storing at least one executable instruction or computer program that enables a processor to perform the operation corresponding to the system evolution capability verification method based on breakpoint regression and entropy analysis in any of the above method embodiments.

[0074] This application provides a computer program product, which includes at least one executable instruction or computer program that enables a processor to perform the operation corresponding to the system evolution capability verification method based on breakpoint regression and entropy analysis in any of the above method embodiments.

[0075] Figure 7 The diagram shows a structural schematic of a computing device according to one embodiment of the present application. The specific embodiments of the present application do not limit the specific implementation of the computing device.

[0076] like Figure 7 As shown, the computing device may include: a processor 702, a communications interface 704, a memory 706, and a communications bus 708.

[0077] The processor 702, communication interface 704, and memory 706 communicate with each other via communication bus 708. Communication interface 704 is used to communicate with other network elements such as clients or other servers. Processor 702 executes program 710, specifically performing the relevant steps in the embodiment of the system evolution capability verification method based on breakpoint regression and entropy analysis for computing devices described above.

[0078] Specifically, program 710 may include program code that includes computer operation instructions.

[0079] The processor 702 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The computing device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0080] Memory 706 is used to store program 710. Memory 706 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0081] Specifically, program 710 can be used to cause processor 702 to execute the system evolution capability verification method based on breakpoint regression and entropy analysis in any of the above method embodiments. The specific implementation of each step in program 710 can be found in the corresponding descriptions of the steps and units in the above embodiments of system evolution capability verification based on breakpoint regression and entropy analysis, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments, and will not be repeated here.

[0082] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of this application are not directed to any particular programming language. It should be understood that the contents of the embodiments of this application described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best implementation of the embodiments of this application.

[0083] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0084] Similarly, it should be understood that, in order to simplify this disclosure and aid in understanding one or more of the various inventive aspects, in the foregoing description of exemplary embodiments of the present application, various features of the present application embodiments are sometimes grouped together into a single embodiment, figure, or description thereof. However, this approach to disclosure should not be construed as reflecting an intention that the claimed embodiments of the present application require more features than expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the present application.

[0085] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0086] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are meant to be within the scope of the embodiments of this application and form different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

[0087] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of this application. The embodiments of this application can also be implemented as device or apparatus programs (e.g., computer programs and computer program products) for performing part or all of the methods described herein. Such programs implementing the embodiments of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0088] It should be noted that the above embodiments are illustrative of the embodiments of this application and not limiting of the embodiments of this application, and those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of this application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

Claims

1. A method for verifying the evolutionary capability of a system based on regression discontinuity and entropy analysis, characterized in that, include: Construct a system evolution evaluation framework that includes multiple evaluation dimensions; these dimensions include: structural complexity, functional diversity, environmental adaptability, energy utilization efficiency, and information processing capability. The environmental control module provides a stable closed environment for the target system, and the multimodal sensor network collects the operating data of the target system in the closed environment. A preset breakpoint detection algorithm is used, a significance level index is set, the running data is analyzed, the state change points of the target system are identified, and the breakpoint regression design score is calculated. Based on the principle of information entropy, the structural entropy corresponding to the structural complexity dimension, the functional entropy corresponding to the functional diversity dimension, and the energy entropy corresponding to the energy utilization efficiency dimension of the target system are calculated. The evolutionary capability index is calculated based on the structural entropy, the functional entropy, the energy entropy, and the breakpoint regression design score. Based on the evolutionary capability index, it is determined whether the target system possesses autonomous evolutionary capability.

2. The method according to claim 1, characterized in that, The provision of a stable, enclosed environment for the target system via an environmental control module, and the acquisition of operational data of the target system in the enclosed environment via a multimodal sensor network, further include: The environmental control module provides the target system with a closed environment where the control precision of environmental parameters is within a preset control precision range; wherein, the environmental parameters include: temperature, humidity and vibration; The target system's operational data in a closed environment is acquired through mechanical, optical, thermal, and electromagnetic sensors in a multimodal sensor network, at a sampling frequency that meets the sampling requirements.

3. The method according to claim 1, characterized in that, The step of employing a preset breakpoint detection algorithm, setting a significance level index, analyzing the operational data, identifying the state change points of the target system, and calculating the breakpoint regression design score further includes: The system's evolutionary capability index is determined based on the operational data, and the algorithm information density is used as the driving variable for regression at breakpoints. Using a breakpoint regression model corresponding to a preset breakpoint detection algorithm, the state change points of the target system are identified, and the jump effect at the state change points is calculated. The jump effect at the state abrupt change point is standardized and normalized to obtain the breakpoint regression design score.

4. The method according to claim 1, characterized in that, The preset breakpoint detection algorithm is an improved Bai-Perron multi-structure breakpoint detection algorithm; The improved Bai-Perron multi-structure breakpoint detection algorithm includes: using the Bayesian information criterion to determine the optimal number of breakpoints, using the bootstrap method for sample processing, and setting the minimum segment length.

5. The method according to claim 1, characterized in that, The step of determining whether the target system possesses autonomous evolutionary capability based on the evolutionary capability index further includes: If the evolutionary capability index is greater than the index threshold and the probability corresponding to the assumption that the target system does not have autonomous evolution capability is less than the probability threshold, then the target system is determined to have autonomous evolution capability.

6. The method according to any one of claims 1-5, characterized in that, The metrics for structural complexity include: number of components, connection density, hierarchy depth, and modularity index.

7. A system for verifying the evolutionary capability of a system based on regression discontinuity and entropy analysis, characterized in that, include: The building module is used to construct a system evolution evaluation framework that includes multiple evaluation dimensions, including: structural complexity, functional diversity, environmental adaptability, energy utilization efficiency, and information processing capability. The environmental control module is used to provide a stable, closed environment for the target system; A multimodal sensor network is used to collect operational data of the target system in a closed environment; The breakpoint analysis module is used to analyze the running data using a preset breakpoint detection algorithm and a significance level index, identify the state change points of the target system, and calculate the breakpoint regression design score. The entropy calculation module is used to calculate the structural entropy of the target system in the dimension of structural complexity, the functional entropy in the dimension of functional diversity, and the energy entropy in the dimension of energy utilization efficiency, based on the principle of information entropy. The evolutionary capability verification module is used to calculate the evolutionary capability index based on the structural entropy, the functional entropy, the energy entropy, and the breakpoint regression design score; and to determine whether the target system has autonomous evolutionary capability based on the evolutionary capability index.

8. A computing device, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the system evolution capability verification method based on breakpoint regression and entropy analysis as described in any one of claims 1-6.

9. A computer storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the system evolution capability verification method based on breakpoint regression and entropy analysis as described in any one of claims 1-6.

10. A computer program product comprising at least one executable instruction that causes a processor to perform an operation corresponding to the system evolution capability verification method based on breakpoint regression and entropy analysis as described in any one of claims 1-6.

Images