A method and system for automatic testing of information technology equipment

Abstract

The present invention discloses an automatic testing method and system for ICT equipment, which relates to the technical field of ICT equipment testing. The method comprises the following steps: parsing test requirements input by a user through a natural language interface, extracting key parameters and retrieving historical cases, and generating a structured test requirement table; constructing a multi-objective optimization model based on the structured test requirement table, and outputting a test strategy matrix after iterative updating by using an improved NSGA-III algorithm using chaotic mapping; performing feature extraction and anomaly detection on test logs, and identifying abnormal features through a dynamic threshold model; constructing a fault propagation graph model based on the abnormal features, locating root cause nodes by applying an improved causal reasoning algorithm, and generating a strategy iteration scheme; the present invention improves the Pareto front coverage by using an improved NSGA-III algorithm through a chaotic mapping initialization population and a dynamic target space adaptation mechanism, and at the same time combines the resource weight allocation formula of the aging-time decay factor to achieve coordinated optimization of test cost and extreme scenario coverage.

Description

Technical Field

[0001] The present invention relates to the field of information and communication technology equipment testing technology, and in particular to an automatic testing method and system for information and communication equipment. Background Art

[0002] In recent years, multimodal intelligent test systems have gradually become a research hotspot in the field of industrial inspection and equipment verification. The core challenge lies in how to integrate multi-source heterogeneous data (text, voice, image) to achieve accurate parameter extraction and generate robust test strategies through dynamic optimization algorithms. Existing technologies usually adopt rule-based multimodal semantic alignment methods combined with static knowledge bases for parameter disambiguation, but have limitations in processing domain-specific terminology and dynamic semantic associations. In addition, test resource configuration is mostly based on linear programming or traditional genetic algorithms, which makes it difficult to balance the conflicting relationships between parameter approximation, test cost and scenario coverage in non-uniform target space. In terms of environmental calibration, existing methods generally adopt a fixed step size adjustment strategy, which leads to inefficient overshoot compensation and a lack of dynamic verification mechanism for impedance matching and signal reflection coefficient.

[0003] Current technologies suffer from two major shortcomings: First, existing semantic disambiguation models fail to incorporate the topological relevance of domain knowledge graphs, making core parameter screening susceptible to interference from synonyms, and candidate term probability calculations fail to consider the dynamic weight distribution of multimodal query vectors. Second, traditional multi-objective optimization algorithms (such as NSGA-II) are prone to falling into local optimality when dealing with non-uniform Pareto fronts. This is particularly true in scenarios where test resource allocation is coupled with the dynamic attenuation of aging factors, making it difficult to maintain a balance between solution distribution and convergence speed. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an automatic testing method for ICT equipment to solve the problems of inaccurate parameter semantic ambiguity elimination and insufficient distribution of multi-objective optimization solution sets in multi-modal testing scenarios.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for automatically testing an information-based device, which comprises:

[0008] Parse user-entered test requirements through a natural language interface, extract key parameters, retrieve historical cases, and generate a structured test requirement table;

[0009] Construct a multi-objective optimization model, use the NSGA-III algorithm improved by chaotic mapping, and output the test strategy matrix after iterative update;

[0010] Build a physical test environment through programmable power supply and temperature control equipment to generate real-time environmental state vectors;

[0011] Combining the real-time environment state vector and the test strategy matrix, the test parameters are dynamically adjusted through an online learning algorithm to form a test log with environmental compensation.

[0012] Perform feature extraction and anomaly detection on test logs, and identify abnormal features through dynamic threshold models;

[0013] Construct a fault propagation graph model, apply an improved causal reasoning algorithm to locate the root cause node, and generate a policy iteration plan.

[0014] As a preferred solution of the automatic testing method for ICT equipment described in the present invention, the extraction of key parameters includes semantic disambiguation of the test requirements input by the user, generating candidate terms, and screening the candidate terms.

[0015] As a preferred solution of the automatic testing method for information-based innovative equipment described in the present invention, the construction of a multi-objective optimization model is to define the minimization of the weighted deviation between the test setting value and the target value, the minimization of the total test cost and the maximization of the coverage of potential failure scenarios through a structured requirement test table.

[0016] As a preferred solution of the automatic testing method for the ICT equipment of the present invention, the NSGA-III algorithm improved by chaotic mapping and the output test strategy matrix after iterative update include the following steps:

[0017] Perform chaotic mapping on the target optimization model to generate the initial population and dynamically adjust it;

[0018] Simulated binary crossover and polynomial mutation are used to perform multi-objective iterative optimization on the dynamically adjusted initialized population to generate a Pareto optimal solution set.

[0019] Select the scenario with the highest scenario coverage in the Pareto optimal solution set as the test sequence;

[0020] Dynamically adjust resource allocation weights based on the Pareto optimal solution set;

[0021] Combining the test sequence, the parameter combination in the Pareto optimal solution set, and the resource allocation weight, a test strategy matrix is ​​obtained.

[0022] As a preferred solution of the automatic testing method for information technology equipment described in the present invention, the dynamic adjustment of test parameters through an online learning algorithm includes injecting bit error rate data into the test signal, adjusting the frequency offset of the test signal through an online learning algorithm, and dynamically changing the frequency adjustment depth of the test signal.

[0023] As a preferred solution of the automatic testing method of the information-based equipment of the present invention, the method of identifying abnormal features through a dynamic threshold model includes the following steps:

[0024] Use LSTM autoencoder to learn the potential distribution of normal data through the encoding-decoding process, and calculate the reconstruction error as the deviation;

[0025] Calculate the mean and standard deviation of all deviations;

[0026] Dynamically adjust the deviation threshold based on the mean and standard deviation of all deviations;

[0027] The calculated deviation is compared with the adjusted deviation threshold to identify abnormal features.

[0028] As a preferred solution of the automatic testing method of the information-based equipment described in the present invention, the generation strategy iteration solution includes the following steps:

[0029] Construct a fault propagation diagram and calculate the root cause probability of each component;

[0030] Sort the root cause probabilities of each component in descending order, select the key root causes, and generate optimization suggestions;

[0031] According to the temperature sensitivity of the key root causes, the environmental parameters are adjusted to obtain the updated environmental configuration;

[0032] Merge the optimization suggestions and updated environment configuration into the test strategy matrix, define priority rules, update the test strategy matrix, and generate a strategy iteration plan.

[0033] In a second aspect, the present invention provides an automatic testing system for ICT equipment, comprising:

[0034] The requirement parsing module parses the test requirements input by the user through a natural language interface, extracts key parameters, retrieves historical cases, and generates a structured test requirement table;

[0035] The strategy generation module builds a multi-objective optimization model based on the structured test requirement table, uses the NSGA-III algorithm improved by chaos mapping, and outputs the test strategy matrix after iterative updates;

[0036] The environmental control module builds a physical test environment through programmable power supplies and temperature control devices according to the test strategy matrix and generates a real-time environmental state vector;

[0037] The adaptive test module combines the real-time environment state vector and the test strategy matrix to start the multi-dimensional test case execution engine, dynamically adjusts the test parameters through the online learning algorithm, and generates a structured test log;

[0038] The anomaly diagnosis module extracts features and detects anomalies in test logs, identifying abnormal features through a dynamic threshold model;

[0039] The policy iteration module builds a fault propagation graph model based on abnormal features, applies an improved causal reasoning algorithm to locate the root cause node, and generates a policy iteration plan.

[0040] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the automatic testing method for information technology equipment as described in the first aspect of the present invention.

[0041] In a fourth aspect, the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program is executed by a processor, it implements any step of the automatic testing method of the information and communication equipment described in the first aspect of the present invention.

[0042] The beneficial effects of the present invention are as follows: the cosine similarity between the pre-trained vector and the query vector is used to calculate the probability of candidate terms, and the semantic topological relationship of the knowledge graph is combined to screen out accurate terms above the threshold. Compared with the traditional disambiguation method based on word frequency, the term misjudgment rate is reduced; the improved NSGA-III algorithm improves the Pareto front coverage through the chaotic mapping initialization population and the dynamic target space adaptation mechanism, and at the same time combines the resource weight allocation formula of the aging-time decay factor to achieve the coordinated optimization of test cost and extreme scenario coverage; the progressive approximation algorithm improves the convergence speed of environmental parameters through the coarse-fine adjustment dual-stage control and discretized first-order inertia correction; the reflection coefficient of link calibration is reduced through the closed-loop control of the impedance matching verification model and the voltage standing wave ratio; the accuracy of abnormal type judgment is improved through the dynamic deviation threshold, and the fault propagation path identification accuracy is improved by combining the root cause location model of the improved PageRank algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 This is a flow chart of the automatic testing method for the ICT equipment in Example 1.

[0045] Figure 2 This is a module diagram of the automatic testing system for the ICT equipment in Example 1.

[0046] Figure 3This is the logic diagram of the improved NSGA-III algorithm in Example 1.

[0047] Figure 4 This is a flowchart of abnormality diagnosis and root cause location in Example 1. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0051] Example 1, reference Figures 1 to 4 , which is the first embodiment of the present invention, provides a method for automatically testing a trusted device, comprising the following steps:

[0052] S1. Receive user input text, language, and images, map different modal data to a unified semantic space through a pre-trained multimodal encoder, and generate a query vector. Construct a disambiguation matrix based on the domain knowledge graph, perform semantic disambiguation on the query vector, and calculate the probability of candidate terms, which is expressed as:

[0053]

[0054] Among them, E(t u |Q) indicates that in the original query Q input by the user, the candidate term h u The probability of h u represents the u-th candidate term, u represents the candidate term index, Q represents the original query entered by the user, Represents the candidate term h u The pre-trained vector of , v represents the query vector, n represents the total number of terms in the knowledge graph, Represents the semantic vector of the term in the knowledge graph, h b represents the bth term in the knowledge graph, and b represents the query term index in the knowledge graph.

[0055] A term threshold is set to filter out candidate terms with a probability greater than the term threshold (e.g., "85°C" is filtered out instead of the ambiguous "high temperature"), and a core parameter set is generated. Semantic disambiguation is used to avoid confusion between synonyms such as "temperature" and "humidity."

[0056] Retrieve the top-K similar cases from the knowledge graph, construct a historical case vector set, weight them through the attention mechanism, obtain the comprehensive parameter weight, and automatically match the test standard template according to the parameter type to generate dynamic constraints. Dynamically calculate the allowable deviation through Monte Carlo simulation, perform structured mapping of requirements, and generate a structured test requirement table.

[0057] S2. The structured test requirement table includes environmental parameter categories, target values, and allowable deviations. Based on the structured test requirement table, a multi-objective optimization model is defined to minimize the weighted deviation between the test set value and the target value, minimize the total test cost, and maximize the coverage of potential failure scenarios. The details are as follows:

[0058] The parameter approximation objective function that minimizes the weighted deviation of the test set value from the target value is:

[0059]

[0060] Among them, f1(x) represents the parameter approximation objective function, i represents the parameter index, n represents the total number of parameters, and x i represents the test setting value of the i-th parameter, w i Represents the weight of the i-th parameter, y i represents the target value of the i-th parameter, and x represents the test setting value.

[0061] Minimize testing costs:

[0062]

[0063] Where f2(x) represents the test cost objective function, j represents the test resource index, m represents the total number of test resources, c j Denotes the cost of the j-th test resource.

[0064] Maximize coverage of potential failure scenarios:

[0065]

[0066] Among them, f3(x) represents the scenario coverage objective function, k represents the extreme scenario index, P(k|x) represents the probability of the kth extreme scenario under the test setting value x, and p represents the total number of extreme scenarios.

[0067] An improved NSGA-III algorithm is used to generate an initialization population by performing chaotic mapping on the target optimization model to enhance population diversity and avoid premature convergence. The initialization population is dynamically adjusted according to the target space distribution to adapt to the non-uniform target space and improve the Pareto front coverage. Multi-objective iterative optimization is performed on the dynamically adjusted initialization population using simulated binary crossover and polynomial mutation. The iteratively optimized solution set is divided into multiple frontier levels through non-dominated sorting, and high-level solutions are retained first. During this period, the niche retention method is used to calculate the crowding distance to maintain the distribution of the solution set in the target space, and finally a Pareto optimal solution set is generated. The scenario coverage is sorted according to each Pareto solution in the Pareto optimal solution set, and the scenario with the highest probability is selected as its test sequence. The aging-time dynamic attenuation factor in the test value is adjusted according to the generated Pareto optimal solution set, and the expression is:

[0068] Ψ i =1-exp(-λl i );

[0069] Among them, i represents the aging-time dynamic attenuation factor of the i-th parameter, λ represents the equipment aging factor, l i It represents the estimated execution time of the i-th test resource during the test process.

[0070] Adjust resource allocation weights based on the aging-time dynamic attenuation factor, expressed as:

[0071]

[0072] Among them, R j represents the weight of the j-th test resource, I ij Indicates the indicator function, that is, if the test parameter is i and the test resource is j, it is 1, otherwise it is 0. ik Indicates that the test resource is i and the extreme scenario is k, which is 1, otherwise it is 0.

[0073] Combining the test sequence, the parameter combination in the Pareto optimal solution set, and the resource allocation weight, a test strategy matrix is ​​obtained.

[0074] S3. Based on the test strategy matrix, parse the initial environmental parameters defined therein, including core voltage, initial temperature, initial humidity, and clock frequency reference, and send instructions to the programmable power supply via the GPIB / USB bus to set the voltage output and control the temperature control box to calibrate the initial environmental parameters.

[0075] Extract target environmental parameters from the test strategy matrix, such as high temperature test scenario and high humidity test scenario; Based on the target environment, the initial environmental parameters are adjusted in stages using a progressive environmental approximation algorithm, including a coarse adjustment stage and a fine adjustment stage; the coarse adjustment stage is when ||T target -T current ||>10%·T target When the step length is large, the high rate factor is set according to the equipment safety margin to accelerate the adjustment. When a problem is found, the discretized first-order inertia link is used to correct it, and the maximum single-step change in the large step length is limited. The iteration is continued until the fine-tuning stage is reached, that is, when ||T target -T current ||≤10%·T target When the fine adjustment is started, a small step size and a low rate factor are set to suppress overshoot, and the overshoot amount is defined. When the fine adjustment result is greater than the overshoot amount, the overshoot compensation mechanism is triggered to continue iterating until the environment is stable and the calibrated environmental parameters are obtained. Among them, T target represents the target environment parameters, T current Represents the initial environment parameters.

[0076] Based on the calibrated environmental parameters, the test sequence requirements are extracted from the test strategy matrix. If the test item includes "PCIe endpoint to root complex latency test," direct port connection is required. If the test item includes "multi-device concurrent bandwidth test," expansion through a PCIe switch is required. For the physical ports of the device under test, a connection matrix is ​​generated, expressed as:

[0077]

[0078] Among them, C ad Indicates the connection strength coefficient between ports a and d. When C ad =1.0 means direct connection, which requires strict impedance matching (such as direct connection between CPU and GPU), C ad =0.5 means connecting through a switch group, allowing a certain signal attenuation (such as extending peripherals), P direct Represents the set of all port pairs that need to be directly connected, P switch Indicates the set of all port pairs that need to be connected through a switch group.

[0079] Traverse all C ad , filter out C ad = 1.0, for each directly connected link, calculate the matching resistance value, the expression is:

[0080]

[0081] in, Indicates the terminal resistance value, which is used to eliminate signal reflection. The calculation formula is as follows:

[0082] Measuring Signal Reflection Coefficient Using a Vector Network Analyzer When Z L =R term When |Γ|<0.1 is required, the simultaneous equations are solved to obtain R term , verify the voltage standing wave ratio Z0 = 85Ω, which is the characteristic impedance of the transmission line defined by the PCIe 4.0 standard and is determined by the transmission line geometry and dielectric material. Γ represents the reflection coefficient, and Z L Represents the equivalent load of the terminal resistance and transmission line impedance; based on the impedance matching verification results, complete the construction of the dynamic test environment and generate a real-time environment state vector.

[0083] S4. Read the initial value of the fundamental frequency amplitude from the signal parameters of the test strategy matrix, and calculate the actual fundamental frequency signal amplitude by combining the terminal resistance value in the real-time environment state vector. The expression is:

[0084]

[0085] Among them, A represents the actual fundamental frequency signal amplitude, A base Indicates the initial value of the fundamental frequency signal amplitude.

[0086] The compensated fundamental signal amplitude is configured to the amplitude register of the arbitrary waveform generator via the GPIB bus to complete the fundamental amplitude initialization. The initial pulse amplitude is read from the stress test of the test strategy matrix and incremented according to the preset gradient rule. For example, after every 10 pulse cycles, the initial pulse amplitude is increased by 10% (upper limit 0.5×A). The gradient parameter is monitored in real time by the FPGA counter and dynamically updated to the pulse amplitude register of the waveform generator. The initial pulse interval is set by the test strategy and then dynamically modified based on the bit error rate feedback. The adjusted pulse interval is written to the time series controller of the waveform generator via a high-precision timer. In the arbitrary waveform generator, the fundamental sine wave is generated by the DDS (direct digital synthesis) module, and the pulse sequence is generated by the high-speed arbitrary sequence generator (ASG). The test signal is injected into the arbitrary waveform generator to generate bit error rate data and generate a composite reference signal. The expression is:

[0087]

[0088] Where s(t) represents the composite reference signal at time t, f0 represents the fundamental frequency, which is related to the test protocol, and B qrepresents the amplitude of the qth pulse, which is used to simulate burst load pressure. q represents the pulse index, N represents the total number of pulses, t represents time, Δ represents the pulse time interval, which is used to control the density of the stress test, and δ represents the Dirac function, which is used to simulate burst load pressure.

[0089] Through the physical layer injection interface of the protocol analyzer, the composite reference signal is superimposed on the differential signal line of the device under test, and the reflection coefficient Γ is monitored to ensure impedance matching. Real-time monitoring of the bit error rate data generated by the injected test signal BER (As PCIe 4.0 requires ∈ BER <10 -12 ) and adjust the frequency offset Δf of the test signal through the online learning algorithm. BER <0.1×10 -12 When Δf is increased to strengthen the stress test, when ∈ BER ≥0.1×10 -12 When the frequency modulation depth is 1000MHz, Δf is reduced to avoid equipment overload; the adjusted Δf is input to the clock generator to dynamically change the frequency modulation depth of the test signal.

[0090] Drift detection is performed based on the temperature measurement value in the real-time environmental state vector, and a temperature threshold is set. When the absolute value of the difference between the temperature measurement value and the target temperature value is greater than the temperature threshold, voltage compensation is triggered. The voltage is adjusted by programming the power supply to offset the voltage change caused by temperature drift and maintain the stability of the device operating point. The performance indicators, abnormal events and compensated environmental parameters during the dynamic adjustment process are packaged into a structured test log according to the timestamp.

[0091] S5. Extract time series data from structured test logs and construct a single time point feature vector. Construct a time series matrix with the time window as the span. Use the LSTM autoencoder to learn the potential distribution of normal data through the encoding-decoding process. Calculate the Frobenius norm of the reconstruction error as a deviation calculation method to measure the reconstruction error between the current data and the learned normal distribution, reflecting the degree of abnormality. The expression is:

[0092]

[0093] Where D represents the deviation, represents the reconstructed output matrix of the LSTM autoencoder for the time series matrix X, X represents the time series matrix, ||·|| F Represents the matrix Frobenius norm, which computes the square root of the sum of the squares of all elements.

[0094] Calculate the mean and standard deviation of all deviations within the time window [tW, t], and the expression is:

[0095]

[0096] Among them, μ D represents the mean of all deviations in the sliding window, W represents the size of the sliding window, r represents the index variable in the sliding window, D r represents the deviation value calculated at time point r, σ D It represents the standard deviation of all deviations within the sliding window, reflecting the discreteness of the data.

[0097] Based on the mean and standard deviation of all deviations, the deviation threshold is dynamically adjusted. The expression is:

[0098] θ=μ D +3σ D ·(1-e -Ω / γ );

[0099] Where θ represents the adjusted deviation threshold, Ω represents the total time from the start of the test to the current run, and γ represents the attenuation coefficient, which controls the relaxation rate of the deviation threshold over the running time. When D > θ, the anomaly type determination and time correlation analysis are performed based on the deviation contribution of each dimension in the time series matrix to locate the anomaly start time. The anomaly feature vector is generated by combining the anomaly type determination result, anomaly start time, and anomaly severity.

[0100] S6. Based on historical fault data and domain knowledge, we define the vertex set as hardware components (such as CPU, PCIe controller, power module, etc.) and the edge set as fault propagation paths (such as "unstable power supply voltage → CPU clock jitter → increased PCIe bit error rate"). The edge weight matrix represents the conditional probability, that is, the probability of one fault causing another, which can be calculated using existing Bayesian networks or causal discovery algorithms. Based on the anomaly type determination result and the anomaly start time in the anomaly feature vector, we activate the relevant subgraph and complete the construction of the fault propagation graph. We apply the improved PageRank algorithm to iteratively calculate the root cause probability of each component, expressed as:

[0101]

[0102] Among them, G(g α ) represents the αth hardware component node g α The root cause probability, g α represents the αth hardware component node, represents the damping coefficient (usually set to 0.85), which controls the balance between random jumps and propagation, g β represents the βth hardware component node, M(g α ) indicates all points to g α The set of neighbor nodes, L(g β ) represents node g β The total number of outgoing edges (i.e., the number of fault propagation path branches), G(gβ ) represents the βth hardware component node g β The root cause probability.

[0103] The calculated root cause probabilities of each component are sorted in descending order, and a root cause threshold is set based on historical fault data. The vertex with a root cause probability greater than the root cause threshold is selected as the key root cause. For the key root cause component, the best parameter adjustment strategy is matched from the historical optimization solution library to generate optimization suggestions. Based on the temperature sensitivity of the root cause component, the environmental parameters are adjusted to obtain an updated environmental configuration. The optimization suggestions and the updated environmental configuration are merged into the test strategy matrix, and priority rules are defined to update the test strategy matrix.

[0104] This embodiment also provides an automatic testing system for ICT equipment, including: a requirement parsing module, which parses the test requirements input by the user through a natural language interface, extracts key parameters and retrieves historical cases, and generates a structured test requirement table; a strategy generation module, which constructs a multi-objective optimization model based on the structured test requirement table, and uses the NSGA-III algorithm improved by chaos mapping to output a test strategy matrix after iterative updating; an environment control module, which builds a physical test environment through programmable power supplies and temperature control devices according to the test strategy matrix, and generates a real-time environment state vector; an adaptive test module, which combines the real-time environment state vector and the test strategy matrix to start a multi-dimensional test case execution engine, dynamically adjusts test parameters through an online learning algorithm, and forms a structured test log; an anomaly diagnosis module, which performs feature extraction and anomaly detection on the test log, and identifies anomaly features through a dynamic threshold model; a strategy iteration module, which constructs a fault propagation graph model based on the anomaly features, applies an improved causal reasoning algorithm to locate the root cause node, and generates a strategy iteration plan.

[0105] This embodiment also provides a computer device suitable for the automatic testing method of an information-based innovation device, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the automatic testing method of an information-based innovation device proposed in the above embodiment.

[0106] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0107] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by the processor, the method for automatically testing the information and innovation equipment proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, abbreviated as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, abbreviated as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, abbreviated as EPROM), programmable read-only memory (Programmable Red-Only Memory, abbreviated as PROM), read-only memory (Read-Only Memory, abbreviated as ROM), magnetic memory, flash memory, disk or optical disk.

[0108] In summary, the present invention achieves this by: calculating the probability of candidate terms using the cosine similarity between the pre-trained vector and the query vector, and screening out precise terms above the threshold in combination with the semantic topological relationship of the knowledge graph. Compared with the traditional disambiguation method based on word frequency, the term misjudgment rate is reduced; the improved NSGA-III algorithm improves the Pareto front coverage by initializing the population through chaotic mapping and the dynamic target space adaptation mechanism, and at the same time, combines the resource weight allocation formula of the aging-time decay factor to achieve the coordinated optimization of test cost and extreme scenario coverage; the progressive approximation algorithm improves the convergence speed of environmental parameters through coarse-tuning and fine-tuning dual-stage control and discretized first-order inertia correction; reduces the reflection coefficient of link calibration through the closed-loop control of the impedance matching verification model and the voltage standing wave ratio; improves the accuracy of abnormal type judgment through the dynamic deviation threshold, and improves the accuracy of fault propagation path identification by combining the root cause location model of the improved PageRank algorithm.

[0109] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for automatically testing an information-based device, characterized in that: include, Parse user-entered test requirements through a natural language interface, extract key parameters, retrieve historical cases, and generate a structured test requirement table; Construct a multi-objective optimization model, use the NSGA-III algorithm improved by chaotic mapping, and output the test strategy matrix after iterative update; Build a physical test environment through programmable power supply and temperature control equipment to generate real-time environmental state vectors; Combining the real-time environment state vector and the test strategy matrix, the test parameters are dynamically adjusted through an online learning algorithm to form a test log with environmental compensation. Perform feature extraction and anomaly detection on test logs, and identify abnormal features through dynamic threshold models; Construct a fault propagation graph model, apply an improved causal reasoning algorithm to locate the root cause node, and generate a policy iteration plan.

2. The automatic testing method for ICT equipment according to claim 1, characterized in that: The extracting of key parameters includes performing semantic disambiguation on the test requirements input by the user, generating candidate terms, and screening the candidate terms.

3. The automatic testing method for ICT equipment according to claim 1, characterized in that: The multi-objective optimization model is constructed by defining, through a structured requirement test table, minimizing the weighted deviation between the test set value and the target value, minimizing the total test cost, and maximizing the coverage of potential failure scenarios.

4. The automatic testing method for ICT equipment according to claim 1, characterized in that: The NSGA-III algorithm improved by chaotic mapping and outputting the test strategy matrix after iterative update includes the following steps: Perform chaotic mapping on the target optimization model to generate the initial population and dynamically adjust it; Simulated binary crossover and polynomial mutation are used to perform multi-objective iterative optimization on the dynamically adjusted initialized population to generate a Pareto optimal solution set. Select the scenario with the highest scenario coverage in the Pareto optimal solution set as the test sequence; Dynamically adjust resource allocation weights based on the Pareto optimal solution set; Combining the test sequence, the parameter combination in the Pareto optimal solution set, and the resource allocation weight, a test strategy matrix is ​​obtained.

5. The automatic testing method for ICT equipment according to claim 1, characterized in that: The dynamic adjustment of the test parameters by the online learning algorithm includes injecting bit error rate data into the test signal, adjusting the frequency offset of the test signal by the online learning algorithm, and dynamically changing the frequency adjustment depth of the test signal.

6. The automatic testing method for ICT equipment according to claim 1, characterized in that: The method of identifying abnormal features by using a dynamic threshold model includes the following steps: Use LSTM autoencoder to learn the potential distribution of normal data through the encoding-decoding process, and calculate the reconstruction error as the deviation; Calculate the mean and standard deviation of all deviations; Dynamically adjust the deviation threshold based on the mean and standard deviation of all deviations; The calculated deviation is compared with the adjusted deviation threshold to identify abnormal features.

7. The automatic testing method for ICT equipment according to claim 1, characterized in that: The generation strategy iteration scheme includes the following steps: Construct a fault propagation diagram and calculate the root cause probability of each component; Sort the root cause probabilities of each component in descending order, select the key root causes, and generate optimization suggestions; According to the temperature sensitivity of the key root causes, the environmental parameters are adjusted to obtain the updated environmental configuration; Merge the optimization suggestions and updated environment configuration into the test strategy matrix, define priority rules, update the test strategy matrix, and generate a strategy iteration plan.

8. An automatic testing system for an ICT device, based on the automatic testing method for an ICT device according to any one of claims 1 to 7, characterized in that: include, The requirement parsing module parses the test requirements input by the user through a natural language interface, extracts key parameters, retrieves historical cases, and generates a structured test requirement table; The strategy generation module builds a multi-objective optimization model based on the structured test requirement table, uses the NSGA-III algorithm improved by chaos mapping, and outputs the test strategy matrix after iterative updates; The environmental control module builds a physical test environment through programmable power supplies and temperature control devices according to the test strategy matrix and generates a real-time environmental state vector; The adaptive test module combines the real-time environment state vector and the test strategy matrix to start the multi-dimensional test case execution engine, dynamically adjusts the test parameters through the online learning algorithm, and generates a structured test log; The anomaly diagnosis module extracts features and detects anomalies in test logs, identifying abnormal features through a dynamic threshold model; The policy iteration module builds a fault propagation graph model based on abnormal features, applies an improved causal reasoning algorithm to locate the root cause node, and generates a policy iteration plan.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, it implements the steps of the automatic testing method for ICT equipment described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the automatic testing method of the information and communication equipment described in any one of claims 1 to 7 are implemented.

Images