A parameter analysis system and method for electromagnetic monitoring

Abstract

An embodiment of this specification provides a parameter analysis system and method for electromagnetic monitoring, including: a data transmission module, a data caching module, a processing module, a storage module, and an analysis and feedback module; the data transmission module is configured to receive electromagnetic environment test data, and the data caching module is configured to cache the electromagnetic environment test data; and based on a control instruction from the analysis and feedback module, send the electromagnetic environment test data to the processing module and / or the storage module; the processing module is configured to determine data to be analyzed based on the electromagnetic environment test data, and send the data to be analyzed to the storage module; the storage module is configured to store the electromagnetic environment test data and the data to be analyzed; the analysis and feedback module is configured to determine a control instruction to control the data transmission flow direction of the data caching module; based on the data to be analyzed in the storage module, determine whether there is an error in the test parameters through a test parameter judgment model, where the test parameter judgment model is a machine learning model.

Description

[0001] Division Explanation

[0002] This application is a divisional application filed in response to a Chinese application with an application date of April 2, 2024, an application number of 202410389399.0, and an invention title of "An Electromagnetic Monitoring Real-Time Analysis System, Method, Device, and Medium". Technical Field

[0003] This specification relates to the technical field of electromagnetic monitoring, and particularly to a parameter analysis system and method for electromagnetic monitoring. Background Art

[0004] Electromagnetic monitoring is widely used in fields such as communication, radar, aerospace, and radio spectrum management. Traditional electromagnetic monitoring devices generally perform tests automatically according to device parameters pre-adjusted or preset manually in advance. Before automatic testing, in order to ensure the reliability of test data, it is necessary to perform equipment calibration and reasonable configuration of equipment test parameters.

[0005] After obtaining electromagnetic test data, the device can perform real-time statistical analysis and preprocessing of the electromagnetic monitoring data based on its own supporting system. However, during automatic testing, problems such as equipment calibration errors and incorrect settings of equipment test parameters are often relatively hidden. Coupled with possible oversights in manual verification, the quality of the obtained electromagnetic test data is relatively low, or even unusable, and such problems are often discovered only after the automatic testing is completed.

[0006] Therefore, it is necessary to provide a parameter analysis system and method for electromagnetic monitoring, which can timely detect pre-test equipment calibration problems and / or incorrect settings of equipment test parameters during the stage of data statistical analysis by the device itself, thereby ensuring the quality of subsequent collected electromagnetic test data, improving the monitoring efficiency and accuracy, and avoiding unnecessary acquisition costs. Summary of the Invention

[0007] In order to solve the problem that during the stage of data statistical analysis by the device itself, it is impossible to timely detect pre-test equipment calibration problems and / or incorrect settings of equipment test parameters, so as to ensure the quality of subsequent collected electromagnetic test data, improve the monitoring efficiency and accuracy, and avoid unnecessary acquisition costs. This specification provides a parameter analysis system and method for electromagnetic monitoring.

[0008] One or more embodiments of this specification provide a parameter analysis system for electromagnetic monitoring, characterized by including: a data transmission module, a data caching module, a processing module, a storage module, and an analysis and feedback module; the data transmission module is configured to receive electromagnetic environment test data, the electromagnetic environment test data includes at least one set of test item data, and the test item data includes sampling spectrum data, calibration data, antenna and system gain data; the data caching module is configured to cache the electromagnetic environment test data; and based on a control instruction from the analysis and feedback module, send the electromagnetic environment test data to the processing module and / or the storage module; the processing module is configured to determine data to be analyzed based on the electromagnetic environment test data, and send the data to be analyzed to the storage module; the storage module is configured to store the electromagnetic environment test data and the data to be analyzed; the analysis and feedback module is configured to determine the control instruction to control the data transmission flow direction of the data caching module; based on the data to be analyzed in the storage module, determine whether there is an error in the test parameters through a test parameter judgment model, where the test parameter judgment model is a machine learning model; the test parameter judgment model includes a spectrum processing layer and an analysis layer.

[0009] One or more embodiments of this specification provide a parameter analysis method for electromagnetic monitoring, including: receiving electromagnetic environment test data, the electromagnetic environment test data includes at least one set of test item data, and the test item data includes sampling spectrum data, calibration data, antenna and system gain data; determining data to be analyzed based on the electromagnetic environment test data, and storing the electromagnetic environment test data and the data to be analyzed; based on the data to be analyzed, determine whether there is an error in the test parameters through a test parameter judgment model, where the test parameter judgment model is a machine learning model; the test parameter judgment model includes a spectrum processing layer and an analysis layer. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] This specification will be further described in the form of exemplary embodiments, and these exemplary embodiments will be described in detail through the drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0011] Figure 1 is a schematic structural diagram of a real-time analysis system for electromagnetic monitoring shown in some embodiments of this specification;

[0012] Figure 2 is an exemplary flowchart for determining test parameter errors and calibration shown in some embodiments of this specification;

[0013] [[ID=I9]] Figure 3 is an exemplary structural diagram of a test parameter judgment model shown in some embodiments of this specification;

[0014] Figure 4 It is an exemplary structural diagram of the configuration mode of the analysis feedback module shown in some embodiments of this specification;

[0015] Figure 5 It is an exemplary flowchart for determining the number of test cycles shown in some embodiments of this specification. Detailed implementation manners

[0016] To more clearly illustrate the technical solutions of the embodiments of this specification, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the drawings represent the same structure or operation.

[0017] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0018] Unless the context clearly indicates an exceptional situation, the words "a", "one", "kind" and / or "the" etc. do not specifically refer to the singular number and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0019] Flowcharts are used in this specification to illustrate the operations performed by the systems according to the embodiments of this specification. It should be understood that the operations before or after do not necessarily need to be executed precisely in sequence. On the contrary, the steps can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0020] Figure 1 It is a schematic structural diagram of the electromagnetic monitoring real-time analysis system shown in some embodiments of this specification.

[0021] In some embodiments, the electromagnetic monitoring real-time analysis system 100 may include a data transmission module 110, a data caching module 120, a processing module 130, a storage module 140, and an analysis feedback module 150.

[0022] In some embodiments, the data transmission module 110 may be configured to receive electromagnetic environment test data, and the electromagnetic environment test data includes at least one set of test item data.

[0023] The electromagnetic environment test data is multiple sets of test item data generated after the electromagnetic environment test equipment conducts multiple tests.

[0024] The electromagnetic environment test equipment is used to monitor and evaluate the electromagnetic environment conditions in a specific area. It can collect, analyze, and record electromagnetic signals and interference sources in the environment, providing the acquisition and analysis of information such as electromagnetic radiation levels, spectral distributions, and interference source positioning.

[0025] In some embodiments, the electromagnetic environment test equipment may include an input component. An operator can input calibration data, send a calibration completion instruction, etc. through the input component. For example, the electromagnetic environment test equipment may include a keyboard, a mouse / touch screen, a voice input device, a gesture input device, a control button / switch, a knob / slider, or a programmable interface, etc.

[0026] The test item data refers to the data obtained after a test is completed under a specific frequency band, antenna channel, and polarization mode.

[0027] The specific frequency band refers to the frequency band of the electromagnetic radiation to be tested. For example, the frequency bands where interference often occurs in daily life, the frequency bands where a certain electrical appliance usually operates, etc.

[0028] An antenna is a receiver and transmitter of electromagnetic waves. It captures or emits signals and transmits them to the electromagnetic environment test equipment. An antenna channel is the channel or interface of the antenna used to receive and send wireless signals in the electromagnetic monitoring real-time analysis system. It is the physical interface connecting the antenna and the system, carrying the transmission and reception of wireless signals. The antenna channel can be used to transmit electromagnetic radiation of different frequencies.

[0029] The polarization mode is an important index of the antenna. The S pole (South Pole) and N pole (North Pole) of the antenna determine whether electromagnetic radiation can enter the antenna and whether it can be emitted. The polarization mode includes horizontal polarization, vertical polarization, or circular polarization, etc.

[0030] In some embodiments, each set of test item data may have a corresponding number of test cycles and automatic test time. For the content related to the number of test cycles and automatic test time, reference can be made to the relevant description in Figure 4 the relevant description in

[0031] In some embodiments, the test item data includes at least one of sampling spectrum data, calibration data, antenna and system gain data, etc.

[0032] Sampled spectral data is information of a signal at different frequencies (such as amplitude, power, intensity, or phase, etc.), for example, it can be a set of sine waves.

[0033] Calibration data is data generated by manual calibration of an operator. Calibration is an operation actively performed manually by the operator before testing, aiming to avoid interference from other influencing factors (such as system noise, environmental noise, etc.) so as not to affect the quality of test data.

[0034] Antenna and system gain data refers to the ratio of the radiation power flux density of an antenna in a certain specified direction to the maximum radiation power flux density of a reference antenna at the same input power.

[0035] In some embodiments, based on the noise source generating device built in the electromagnetic environment test equipment, by measuring the electromagnetic test signals when the noise source is turned on and off, the antenna and system gain data can be calculated and determined.

[0036] In some embodiments, the electromagnetic environment test equipment can collect electromagnetic environment test data and transmit the collected electromagnetic environment test data to the data transmission module 110.

[0037] In some embodiments, the data transmission module 110 can transmit the received electromagnetic environment test data to the data cache module 120 and / or the processing module 130, etc. For example, the data transmission module 110 can achieve data transmission through wireless communication technologies, etc., and specifically can adopt the method of Wireless Sensor Network (WSN) to receive and transmit electromagnetic environment test data.

[0038] In some embodiments, the data cache module 120 can be configured to cache electromagnetic environment test data. For example, the data cache module 120 can cache electromagnetic environment test data from the data transmission module 110.

[0039] In some embodiments, the data cache module 120 can be configured to send electromagnetic environment test data to the processing module 130 and / or the storage module 140 based on the control instructions of the analysis feedback module 150.

[0040] The control instructions of the analysis feedback module 150 are instructions used to determine the data flow direction. For the specific content of the relevant control instructions, see Figure 1 The following relevant descriptions.

[0041] In some embodiments, the data cache module 120 sends the electromagnetic environment test data to the processing module 130 and / or the storage module 140, etc. according to the control instructions. For example, as Figure 1As shown, the data cache module 120 can receive control instructions from the analysis feedback module 150, and send the cached electromagnetic environment test data to the processing module 130 and / or the storage module 140 according to the control instructions.

[0042] In some embodiments, the processing module 130 can be configured to determine the data to be analyzed based on the electromagnetic environment test data.

[0043] The data to be analyzed is the data to be analyzed obtained after preprocessing (such as statistics, screening, and / or sampling, etc.) of the electromagnetic environment test data.

[0044] In some embodiments, the processing module 130 can preprocess the electromagnetic environment test data in various ways to determine the data to be analyzed.

[0045] For example, the processing module 130 can sample the electromagnetic environment test data, filter the sample data, and determine the sample data whose data before and after filtering meets the preset conditions as the data to be analyzed.

[0046] The preset conditions refer to the conditions for determining the data to be analyzed preset in advance. For example, the preset condition can be that the change value of the data before and after filtering is less than the change threshold, etc. The change threshold can be preset in advance. For example, for the electromagnetic environment test data generated from 8 am to 20 pm on the same day, the processing module 130 can divide it according to the length of one hour, and obtain the data of 12 time periods. In each of these 12 time periods, data with a fixed time length (such as 5 minutes) is randomly sampled, and the sampled data is used as the sampling sample data for this time period.

[0047] The processing module 130 can process the sampling sample data in each time period through a filter to obtain the sample data before and after filtering. If the data before and after sample filtering meets the preset conditions, the processing module 130 can use the electromagnetic environment test data of the time period corresponding to the sample that meets the preset conditions as the data to be analyzed.

[0048] In some embodiments, the processing module 130 can use the length of the test cycle as a division criterion.

[0049] If the data does not change much after being processed by the filter, it means that there is less noise in the data, and this part of the data is good data for analysis.

[0050] In some embodiments, the processing module 130 can send the data to be analyzed to the storage module 140 for storage.

[0051] The processing module 130 can both receive the electromagnetic environment test data cached by the data cache module 120 and send the processed data to be analyzed to the storage module 140.

[0052] In some embodiments, the storage module 140 may be configured to store electromagnetic environment test data, data to be analyzed, and the like.

[0053] In the real-time electromagnetic monitoring and analysis system 100, the storage module 140 may be a hard disk drive or a cloud storage service. The storage module 140 can be used to store electromagnetic environment test data (such as sampled spectrum data, calibration data, etc.) and data to be analyzed, and the like.

[0054] In some embodiments, data such as (historical) electromagnetic environment test data, whether there are test parameter errors, and data to be analyzed can be stored in the storage module 140 in the form of a database.

[0055] Exemplarily, for the real-time electromagnetic monitoring and analysis system used to monitor the radio spectrum, the storage module 140 can save the sampled spectrum data in the database. Each time the storage module 140 receives the sampled spectrum data, it will be stored as a record, and the record includes information such as a timestamp, a frequency range, and a signal strength. The above records can be organized in chronological order for subsequent data analysis and backtracking.

[0056] In some embodiments, the storage module 140 may also store data to be analyzed. For the content of the data to be analyzed, refer to Figure 1 the relevant description of the data to be analyzed generated by the processing module 130 in

[0057] In some embodiments, the storage module 140 may also store various data related to the real-time electromagnetic monitoring and analysis system 100. For example, historical test results, historical test data, initial electromagnetic environment test data, historical electromagnetic environment test data within a historical preset time period, test time, test frequency band, etc. For more content about the above, refer to the relevant description in Figures 2 to 5 below.

[0058] In some embodiments, the analysis and feedback module 150 may be configured to determine a control instruction to control the data transmission flow direction of the data cache module 120. The data transmission flow direction includes sending electromagnetic environment test data to the processing module 130 or the storage module 140; and determining whether there are test parameter errors based on the data to be analyzed in the storage module 140; and in response to the existence of test parameter errors, issuing a parameter error warning.

[0059] The control instruction is an instruction for determining the data transmission flow direction according to whether the electromagnetic environment test data is sent to the processing module or the storage module for processing.

[0060] In some embodiments, the control instruction is preset in the analysis and feedback module 150 according to the analysis and processing flow of the electromagnetic environment test data.

[0061] A test parameter error refers to a condition that indicates a normal test parameter in the data to be analyzed. A test parameter error can be represented by at least one of a textual character, a numerical value, or a symbol. For example, a test parameter error can be represented by a numerical value of 0 or 1. If an error exists, the value is 1, and otherwise, the value is 0.

[0062] The analysis feedback module 150 may calculate similarity between the data to be analyzed and the standard test result data without test parameter errors. If the similarity is lower than a similarity threshold, it is considered that the data to be analyzed has test parameter errors.

[0063] In some embodiments, the test parameter error may include at least one of a calibration error and an antenna parameter setting error. A calibration error is an error in manual calibration, such as improper calibration parameters, calibration failure, or calibration omission. An antenna parameter setting error indicates that the antenna channel is not compatible with the current situation.

[0064] In some embodiments, in response to a test parameter error, the analysis and feedback module 150 will issue a parameter error warning. Parameter error warning methods include, but are not limited to, at least one of an audible or visual alarm, an abnormality notification or alarm message, a remote alarm message, an indicator light, or a log record and report. For details on how the analysis and feedback module 150 determines a test parameter error, interrupts the test, and issues a calibration request using the test parameter judgment model, see Figure 2 Related description in .

[0065] The electromagnetic monitoring real-time analysis system provided in this manual can promptly detect early equipment calibration problems and / or incorrect equipment test parameter settings during the equipment's own data statistical analysis stage, allowing operators to take appropriate measures to repair or adjust them in a timely manner, thereby ensuring the quality of subsequently collected electromagnetic test data, improving monitoring efficiency and accuracy, and avoiding unnecessary collection costs.

[0066] In some embodiments, the electromagnetic monitoring and real-time analysis system 100 can be configured to assist electromagnetic environment testing equipment in performing tests. The system can be configured to execute based on the processor of the electromagnetic environment testing equipment. The processor includes a data transmission module 110, a data cache module 120, a processing module 130, a storage module 140, and an analysis and feedback module 150.

[0067] It should be understood that Figure 1 The illustrated system and its modules can be implemented in various ways. For example, in some embodiments, the data transmission module 110 can include its own cache medium, including the functions of the data cache module 120. For another example, the processing module 130 and the storage module 140 can be integrated into the same module, each performing its own functions.

[0068] It should be noted that the above description of the electromagnetic monitoring real-time analysis system and its modules is only for convenience of description and does not limit this specification to the scope of the examples given. It can be understood that for those skilled in the art, after understanding the principle of the system, they may, without departing from this principle, make arbitrary combinations of each module, or form a subsystem and connect it with other modules. In some embodiments, Figure 1 the data transmission module, data cache module, processing module, storage module, and analysis feedback module disclosed in may be different modules in a system, or a single module may implement the functions of two or more of the above modules. For example, each module may share a storage module, or each module may have its own storage module respectively. Such variations are all within the scope of protection of this specification.

[0069] Figure 2 is an exemplary flowchart for determining test parameter errors and calibration according to some embodiments of this specification. In some embodiments, process 200 may be executed by analysis feedback module 150.

[0070] Step 210, based on the data to be analyzed in the storage module, determine test parameter errors through a test parameter judgment model.

[0071] For the content related to storage module 140, the data to be analyzed, and test parameter errors, please refer to Figure 1 the relevant description.

[0072] The test parameter judgment model may refer to a model for determining test parameter errors. In some embodiments, the test parameter judgment model may be a machine learning model. For example, the test parameter judgment model may include any one or combination of a Convolutional Neural Networks (CNN) model, a Neural Networks (NN) model, or other custom model structures, etc.

[0073] In some embodiments, the input of the test parameter judgment model may include the data to be analyzed, and the output may include test parameter errors.

[0074] The test parameter judgment model 340 can learn the normal range and abnormal patterns of test parameters through the training process and can make predictions and judgments based on the input data. The training data set includes sample data with known correct and incorrect test parameters. These sample data can be manually labeled by humans or labeled by other means. In some embodiments, the test parameter judgment model can be trained based on a large number of first training samples with a first label. The first training sample can be sample data to be analyzed, and the first label of the first training sample can be that the sample measurement parameter is incorrect. In some embodiments, the first training sample can be generated by the processing module 130 based on historical electromagnetic environment test data, and the first label can be determined based on manual annotation. A loss function is constructed based on the first label and the result of the initial test parameter judgment model, and the parameters of the initial test parameter judgment model are iteratively updated based on the loss function. When the loss function of the initial test parameter judgment model meets the iteration condition, the model training is completed, and a trained test parameter judgment model is obtained. Among them, the iteration condition can be that the loss function converges, the number of iterations reaches a threshold, etc. After the test parameter judgment model is trained, the test parameter error can be determined by inputting the data to be analyzed.

[0075] The test parameter judgment model also includes other inputs. For specific details, see Figure 3 the relevant description.

[0076] Step 220, in response to the existence of a test parameter error, interrupt the current test and issue a calibration request.

[0077] The calibration request is a request sent by the analysis feedback module 150 to the operator, prompting the operator to adjust the parameter settings (such as calibration parameter settings and / or antenna parameter settings, etc.) to eliminate the test parameter error after retesting.

[0078] In some embodiments, if there is a test parameter error, the current test is interrupted and a calibration request is issued. For example, if after inputting a certain set of data to be analyzed into the test parameter judgment model, the output indicates that there is a test parameter error, the analysis feedback module 150 can interrupt the test process and send a calibration request to the operator.

[0079] Step 230, in response to obtaining a calibration completion instruction, restart the test.

[0080] After the operator receives the calibration request sent by the analysis feedback module 150, the test parameters will be calibrated, and after the calibration is completed, a calibration completion instruction will be sent to the analysis feedback module 150.

[0081] In some embodiments, if a calibration completion instruction is obtained, the test is restarted. For example, after completing the test parameter calibration, the operator can enter a calibration completion instruction and send the instruction to the analysis and feedback module 150. After receiving the instruction, the analysis and feedback module 150 will restart the test.

[0082] After the restart test, the electromagnetic environment test equipment will restart or be initialized, and then perform the test operation according to the test process from the beginning.

[0083] Causes of test parameter errors include human accidental factors, changes in test scenarios, and environmental interference. Calibration can reduce or eliminate the causes of test parameter errors, but calibration may have problems such as inappropriate calibration parameters and calibration failure, and human omissions may occur. In some embodiments of the present specification, the test parameter judgment model is used to determine whether there is a test parameter error based on the data to be analyzed in the storage module 140, which can avoid the above-mentioned human omissions. By analyzing the above-mentioned configuration method of the feedback module, the system can automatically detect test parameter errors in the data to be analyzed; further analysis of erroneous data can be avoided to ensure the accuracy of the test results; and the system can continue to provide reliable data and results after calibration.

[0084] Figure 3 This is an exemplary structural diagram of a test parameter judgment model according to some embodiments of this specification.

[0085] In some embodiments, the input of the test parameter judgment model 340 also includes interference characteristics 311, initial electromagnetic environment test data 320, historical electromagnetic environment test data 330 within a historical preset time period, test time 313 and test frequency band 314 corresponding to the historical electromagnetic environment test data within a historical preset time period, etc.

[0086] Interference characteristics refer to characteristics that can characterize relevant information about interference. For example, interference characteristics can characterize various information such as the type of interference and the time period in which the interference occurs. For more information about interference characteristics, please refer to the detailed description later in this specification.

[0087] The initial electromagnetic environment test data refers to original (eg, first) electromagnetic environment test data. The analysis and feedback module 150 can obtain the initial electromagnetic environment test data 320 from the storage module 140 .

[0088] A historical preset time period is a pre-defined time range used to review, retrieve, and analyze electromagnetic environment test data within a specific time period. For example, a historical preset time period could be the past week or the previous test cycle.

[0089] The historical electromagnetic environment test data 330 within the historical preset time period, as well as the corresponding test time 313 and test frequency band 314, are obtained by the analysis feedback module 150 from the storage module 140.

[0090] As Figure 3 shown, the test parameter judgment model 340 may include a spectrum processing layer 341 and an analysis layer 342.

[0091] The spectrum processing layer is part of the test parameter judgment model, which performs spectrum analysis and processing on the input electromagnetic environment test data to output spectrum features. The input of the spectrum processing layer 341 may include the initial electromagnetic environment test data 320, the historical electromagnetic environment test data 330 within the historical preset time period, etc.; the output is the spectrum feature 350.

[0092] The spectrum feature refers to the data or features extracted from the electromagnetic environment test data for describing the spectrum characteristics of the signal, so as to reveal information such as the frequency distribution, frequency band occupancy, and power intensity of the signal.

[0093] The analysis layer is one of the components of the test parameter judgment model, which is used to further analyze and judge the accuracy of the test parameters.

[0094] In some embodiments, the input of the analysis layer 342 may include the interference feature 311, the data to be analyzed 312, the spectrum feature 350, the test time 313, the test frequency band 314, etc.; the output is the test parameter error 360.

[0095] For the content related to the electromagnetic environment test data, the data to be analyzed, and the test parameter error, see Figure 1 the relevant descriptions in

[0096] In some embodiments, the output of the spectrum processing layer may be the input of the analysis layer, and the spectrum processing layer and the analysis layer may be jointly trained.

[0097] In some embodiments, each set of sample data for joint training includes sample interference features, sample data to be analyzed, sample initial electromagnetic environment test data, sample historical electromagnetic environment test data, sample test time, and sample test frequency band. The label of the sample data is whether there is an error in the test parameters for each set of data. The sample data for joint training can be obtained from historical data, and the corresponding labels can be manually annotated. Input the sample initial electromagnetic environment test data and sample historical electromagnetic environment test data into the spectrum processing layer to obtain the spectrum features output by the spectrum processing layer; use the spectrum features as training sample data, and input them together with the sample interference features, sample data to be analyzed, sample test time, and sample test frequency band into the analysis layer to obtain the test parameter error output by the analysis layer. Construct a loss function based on the sample data label and the output of the analysis layer, and synchronously update the parameters of the spectrum processing layer and the analysis layer. Through parameter update, obtain the trained spectrum processing layer and analysis layer.

[0098] The above double-layer structure of the test parameter judgment model and the various input data are helpful for the system to conduct a more accurate and comprehensive evaluation and judgment of the electromagnetic environment, help the model capture potential patterns and anomalies in the spectrum data, enable the model to perform advanced data mining and decision-making, and improve the accuracy and reliability of test parameter judgment.

[0099] In some embodiments, the training process of the test parameter judgment model (spectrum processing layer and analysis layer) can be divided into one or more stages. The number of stages can be set according to actual needs.

[0100] In some embodiments, the training process of the test parameter judgment model (spectrum processing layer and analysis layer) can include the first-stage training and the second-stage training, etc. The first-stage training refers to the initial training, and the second-stage training refers to the training conducted after the first-stage training is completed.

[0101] In some embodiments, the first-stage training can include: performing the first-stage training on the test parameter judgment model based on the first training set. The first training set can include a preset proportion of the first type of data, the second type of data, and the third type of data.

[0102] The preset proportion refers to the proportion setting used to construct different category data sets when training the test parameter judgment model. The preset proportion determines the relative proportion of each category of data in the training set to ensure that the model can learn the characteristics and patterns of different category data. For example, for a data set containing three categories, the preset proportion can be that the data of each category accounts for 1 / 3 of the training set. The preset proportion can be preset according to actual needs.

[0103] The first type of data, the second type of data, and the third type of data refer to three different types of data in the first training set that meet the preset proportion.

[0104] In some embodiments, each set of data in the first type of data is a sample interference feature, sample data to be analyzed, sample initial electromagnetic environment test data, sample historical electromagnetic environment test data, sample test time, and sample test frequency band with a label of test parameter error. For example, the analysis and feedback module 150 can obtain the first type of data from a database storing historical electromagnetic environment test data, and the corresponding label is that there is a test parameter error.

[0105] In some embodiments, the second type of data is a sample interference feature, sample data to be analyzed, sample initial electromagnetic environment test data, sample historical electromagnetic environment test data, sample test time, and sample test frequency band without a test parameter error. For example, the analysis and feedback module 150 can obtain the second type of data from a database storing historical electromagnetic environment test data, and the corresponding label is that there is no test parameter error.

[0106] In some embodiments, each set of data in the third type of data is sample data after applying noise. For example, the analysis and feedback module 150 can obtain at least one set of sample interference features, sample data to be analyzed, sample initial electromagnetic environment test data, sample historical electromagnetic environment test data, sample test time, and sample test frequency band with a test parameter error from a database storing historical electromagnetic environment test data, and apply one or more noises to each set of data (the one or more noises include, but are not limited to, salt-and-pepper noise, Gaussian noise, and / or Poisson noise, etc.). The analysis and feedback module 150 can determine each set of data after applying noise as the third type of data, and the corresponding label is that there is a test parameter error.

[0107] In some embodiments, the analysis and feedback module 150 can perform joint training on the test parameter judgment model (spectrum processing layer and analysis layer) in the first stage of training based on the first type of data, the second type of data, and the third type of data. The training process is similar to Figure 3 the above-mentioned joint training process. For more details, see Figure 3 the above-mentioned related description.

[0108] By training the sample data with and without test parameter errors, the test parameter judgment model can learn the features and patterns for distinguishing and judging whether the test parameters are in error. At the same time, adding noise to the third type of data can also help the model better adapt to the noise environment in actual applications.

[0109] In some embodiments, after the first stage of training of the test parameter judgment model (spectrum processing layer and analysis layer) is completed, the analysis and feedback module 150 can perform the second stage of training.

[0110] In some embodiments, the second-stage training is performed on the test parameter judgment model after the first-stage training based on a second training set, which may include a fourth type of data and a fifth type of data.

[0111] In some embodiments, the fourth type of data is a sample interference feature, sample data to be analyzed, sample initial electromagnetic environment test data, sample historical electromagnetic environment test data, sample test time, and sample test frequency band that are misdetected by the test parameter judgment model after the first-stage training as having test parameter errors but are marked as not having test parameter errors in the database storing historical electromagnetic environment test data.

[0112] In some embodiments, the fifth type of data is a sample interference feature, sample data to be analyzed, sample initial electromagnetic environment test data, sample historical electromagnetic environment test data, sample test time, and sample test frequency band that are misdetected by the test parameter judgment model after the first-stage training as not having test parameter errors but are marked as having test parameter errors in the database storing historical electromagnetic environment test data.

[0113] In some embodiments, the analysis feedback module 150 can perform joint training on the test parameter judgment model (spectrum processing layer and analysis layer) after the first-stage training based on the fourth type of data and the fifth type of data. The training process is Figure 3 similar to the above joint training process. For more details, refer to Figure 3 the above related description.

[0114] By performing two-stage training using the first training set and the second training set, the test parameter judgment model can include multi-class data training, enhance the model generalization ability, consider real scenarios, and improve the model robustness. These features enable the test parameter judgment model to better adapt to test parameter error judgments in different situations and improve the performance and reliability of the model in practical applications.

[0115] Figure 4 It is an exemplary structural diagram of the configuration manner of the analysis feedback module shown in some embodiments of this specification.

[0116] In some embodiments, the analysis feedback module 150 can be further configured to determine the test loop count 410 for each set of test item data in at least one set of test item data. In some embodiments, the analysis feedback module 150 can be further configured to adjust the automatic test time 420 for at least one set of test item data.

[0117] For more details about at least one set of test item data, refer to Figure 1 the related description in

[0118] Test cycles refer to the number of times a test item's data is repeated. Each set of test item data corresponds to one test cycle. By adjusting the test cycle number, you can reduce the impact of random errors during testing and improve the accuracy of test results.

[0119] In some embodiments, the analysis and feedback module 150 may determine the number of test cycles for each set of test item data in various ways. For example, the analysis and feedback module 150 may determine the number of test cycles corresponding to each set of test item data based on the number of test parameter errors in each set of test item data in historical test results using a preset algorithm.

[0120] A preset algorithm is a pre-determined algorithm used to calculate the number of test cycles for each set of test item data. For example, the more test parameter errors a set of test item data contains and the more frequent these errors, the greater the number of test cycles for that set of test item data. Using a preset algorithm to determine the number of test cycles can avoid the risk of manual verification revealing insufficient data, necessitating additional testing.

[0121] Historical test results are the results of tests that have been completed in the past. Historical test results include the number of test parameter errors for each set of test item data. The analysis and feedback module can obtain historical test results from the storage module. For more information about test parameter errors, see Figure 1 The relevant description of it in .

[0122] In some embodiments, the preset algorithm may be:

[0123] Number of test cycles = k*number of test parameter errors+b

[0124] Among them, k and b are preset coefficients.

[0125] In some embodiments, determining the number of test cycles for each set of test item data also includes further methods, for details, see Figure 5 Related description in .

[0126] Automatic test time refers to the time it takes to automatically test each set of test item data. Automatic test time determines the time point and test period for each set of test item data in the system.

[0127] In some embodiments, the length of the automatic test time of at least one set of test item data may be determined according to the number of test cycles of the at least one set of test item data:

[0128] The length of automatic test time = Δt*number of test cycles

[0129] Among them, Δt is the length of time required for a single test and can be preset.

[0130] In some embodiments, the analysis feedback module 150 may determine the automatic test time according to the test process and the length of the automatic test time. For example, if the test process includes Test Item 1, Test Item 2, and Test Item 3, and the time lengths required for each single test are 10 min, 5 min, and 8 min respectively, and the test starts at 9:00 AM, then the automatic test times for Test Item 1, Test Item 2, and Test Item 3 are 9:00 - 9:10, 9:10 - 9:15, and 9:15 - 9:23 respectively.

[0131] In some embodiments, the analysis feedback module 150 may determine the interference characteristics based on historical test data; and determine the automatic test time of at least one set of test item data based on the interference characteristics and the number of test cycles of each set of test item data. For more information about historical test data, please refer to Figure 5 the relevant description.

[0132] In some embodiments, the analysis feedback module 150 may determine the interference characteristics 311 in various ways based on historical test data. In some embodiments, the interference characteristics 311 may include the occurrence times of occasional human interference or industrial interference, etc.

[0133] Based on historical test data, the analysis feedback module 150 may count the data abnormal time periods in the data used for analysis due to various interference occurrences, and use the statistical result as the interference characteristics 311.

[0134] In some embodiments, the analysis feedback module 150 may determine the automatic test time 420 of at least one set of test item data in multiple ways based on the interference feature 311 and the number of test cycles 410 of each set of test item data. For example, assume that the test process includes test item 1, test item 2, and test item 3, and the interference feature is that interference of category 1 occurs from 9:10 to 9:13. The interference of category 1 has a serious impact on test item 1 and test item 3, and has an impact on test item 2 but does not affect the test result. Assume that test item 1, test item 2, and test item 3 are to be tested for 10 minutes, 5 minutes, and 8 minutes respectively, and the test starts at 9:00 AM. Then the automatic test times of test item 1, test item 2, and test item 3 are 9:00 - 9:10, 9:10 - 9:15, and 9:15 - 9:23 respectively. Among them, because the interference of category 1 from 9:10 to 9:13 does not affect the test result of test item 2, there is no need to specifically avoid it. Another example, assume that test item 1, test item 2, and test item 3 are to be tested for 20 minutes, 5 minutes, and 8 minutes respectively, and the test starts at 9:00 AM. Then, if the test is interrupted, the automatic test time of test item 1 is 9:00 - 9:10, 9:13 - 9:23; the automatic test times of test item 2 and test item 3 are 9:23 - 9:28 and 9:28 - 9:36 respectively. If the test cannot be interrupted, the automatic test times of test item 1, test item 2, and test item 3 are 9:13 - 9:33, 9:33 - 9:38, and 9:38 - 9:46 respectively.

[0135] In some embodiments, the automatic test time of at least one set of test item data may also be related to the test requirements and the test duration. For example, when there are changes in the test process and the test process includes test items that can be interrupted and those that cannot be interrupted, the automatic test time will be affected to varying degrees. The test requirements refer to the relevant requirements for testing at least one set of test item data. For example, whether the test can be interrupted, requirements for test time points, etc. The test duration refers to the duration of at least one set of test item data.

[0136] In some embodiments, determining the automatic test time of at least one set of test item data based on the interference feature further includes determining the automatic test time of at least one set of test item data through a time determination model based on the interference feature, test requirements, test duration, and the number of test cycles 410 of each set of test item data. Among them, the time determination model may be a machine learning model.

[0137] The interference feature 311, test requirements, test duration, and the number of test cycles 410 of each set of test item data are the inputs of the time determination model, and the automatic test time 420 of at least one set of test item data is the output of the time determination model.

[0138] The time determination model can be obtained through model training. Each set of sample data in the sample data is the sample interference feature, sample test requirement, sample test duration, and the sample test cycle number of each set of test item data in the historical data. The training label is the test data generated after testing the automatic test time corresponding to each set of sample data in the historical data for test parameter errors. The automatic test time with the fewest test parameter errors is used as the training label corresponding to this set of sample data.

[0139] By analyzing the interference features in the historical test data and considering the test cycle number, the system can determine a more appropriate automatic test time and optimize the test plan to cope with the existence of interference, which helps to conduct more tests during periods with less interference. In some embodiments of this specification, based on the interference features, test requirements, test duration, and the test cycle number of each set of test item data, etc., the automatic test time is determined through the time determination model, which can further improve the accuracy of the determined automatic test time.

[0140] Each set of test item data may need to be cycled multiple times, and the automatic test time corresponding to each set of test item data may be different (for example, the automatic test time is in the morning or early morning, etc.). During the actual test process, there may be some uncontrollable factors (such as unknown interference during fixed periods, interference during building construction periods, etc.). Through further configuration of the analysis feedback module, the system can automatically determine the test cycle number required for each set of test item data according to the specific situation; it can automatically adjust the automatic test time of at least one set of test item data according to the complexity of each test item data, test objectives, and actual situation, etc., thereby improving the efficiency and accuracy of the test.

[0141] Figure 5 It is an exemplary flowchart for determining the test cycle number shown in some embodiments of this specification. In some embodiments, process 500 can be executed by the analysis feedback module 150.

[0142] Step 510, based on the historical test data, determine the test parameter frequent items and the support degree corresponding to the test parameter frequent items.

[0143] The historical test data at least includes the historical test results of each test item and the number of test parameter errors, etc. The analysis feedback module 150 can obtain the historical test data from the storage module 140.

[0144] A test parameter frequent item refers to an item where different test item data corresponds to different test times. For example, for the test parameter frequent item, test item 1 corresponds to 100 test times, test item 1 corresponds to 200 test times, test item 2 corresponds to 100 test times, etc. The support degree corresponding to the test parameter frequent item refers to the frequency that can reflect the occurrence of test parameter errors under a certain number of test times. For the same test item, if the corresponding test times are different, the support degrees corresponding to the test parameter frequent items may be different.

[0145] In some embodiments, the analysis and feedback module 150 can determine the test parameter frequent items and their corresponding support degrees based on historical test data through various methods. For example, the analysis and feedback module 150 can count the number of test parameter error times n for each test item at test time i under the same test conditions in the historical test data, determine the test item and its test time i where i ≥ threshold 1 and n ≤ threshold 2 as the test parameter frequent item, and determine the ratio of n to i as the support degree corresponding to the test parameter frequent item. Here, the magnitudes of threshold 1 and threshold 2 can be preset according to actual requirements.

[0146] In some embodiments, i ≥ threshold 1 indicates that the test times of the test item are sufficient, which can exclude the accidental errors of the test. n ≤ threshold 2 indicates that the number of test parameter error times cannot be too high, which can exclude some errors due to errors within non-variables and abnormal tests (for example, there is a problem with the machine, and theoretically the test is correct, but the result shows a test error), etc.

[0147] Step 520: Based on the test parameter frequent items and the support degrees corresponding to the test parameter frequent items, construct a frequent item database.

[0148] A frequent item database refers to a database that can represent the test parameter frequent items corresponding to multiple groups of test items and the support degrees corresponding to the test parameter frequent items.

[0149] In some embodiments, the analysis and feedback module 150 can construct a frequent item database based on the test parameter frequent items and the support degrees corresponding to the test parameter frequent items through various methods. For example, the feedback module 150 can sort the test parameter frequent items in ascending order of the support degree, and select the preset number of test parameter frequent items with the highest ranking and their corresponding support degrees to construct the frequent item database. The preset number can be set according to needs.

[0150] Step 530: Based on the frequent item database, determine the test loop times for each group of test item data. For the content regarding the test loop times for each group of test item data, see Figure 4 the relevant description of it in

[0151] In some embodiments, the analysis feedback module 150 can determine the number of test cycles for each set of test item data based on the frequent item database. For example, the number of tests corresponding to the test parameter frequent item with the lowest support in each test item can be selected as the number of test cycles for each set of test item data.

[0152] By executing the steps in process 500, the system can select the number of tests corresponding to the test parameter frequent item with low support as the number of test cycles for each set of test item data, making the determined number of test cycles more reasonable and accurate to improve test efficiency and accuracy.

[0153] It should be noted that the above descriptions of the processes (such as process 200 and process 500) are only for illustration and explanation, and do not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 200 and process 500 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0154] Some embodiments of this specification also provide an electromagnetic monitoring real-time analysis method, which can be implemented by the electromagnetic monitoring real-time analysis system 100, and the specific steps are as follows.

[0155] The first step is to obtain electromagnetic environment test data. This step can be implemented by the data transmission module 110.

[0156] In some embodiments, electromagnetic environment test data can be obtained, and the electromagnetic environment test data includes at least one set of test item data. The test item data includes sampling spectrum data, calibration data, antenna and system gain data. For the content related to obtaining electromagnetic environment test data, see Figure 1 the relevant descriptions of the data transmission module 110 in

[0157] The second step is to determine and store the data to be analyzed. This step can be implemented by the data cache module 120, the processing module 130 and the storage module 140.

[0158] In some embodiments, the data to be analyzed can be determined based on the electromagnetic environment test data and the data to be analyzed can be stored. For the specific content related to determining and storing the data to be analyzed, see Figure 1 the relevant descriptions of the data cache module 120, the processing module 130 and the storage module 140 in

[0159] The third step is to determine whether there is a test parameter error and whether to issue an error warning. This step can be implemented by the analysis feedback module 150.

[0160] In some embodiments, it is possible to determine whether there is an error in test parameters based on the data to be analyzed; in response to the existence of an error in test parameters, a parameter error warning is issued. For the specific content regarding determining whether there is an error in test parameters and whether to issue an error warning, refer to Figure 1 the relevant description of the analysis feedback module 150 in

[0161] In some embodiments, determining whether there is an error in test parameters based on the data to be analyzed includes: based on the data to be analyzed, determining the test parameter error through a test parameter judgment model, where the test parameter judgment model is a machine learning model.

[0162] In some embodiments, if there is an error in test parameters, this test will be interrupted and a calibration request will be issued.

[0163] In some embodiments, if a calibration completion instruction is obtained, the test will be restarted.

[0164] The above methods and steps for determining whether there is an error in test parameters are executed by the analysis feedback module 150. For the specific content regarding determining the test parameter error, refer to Figure 2 the relevant description of the functions of the analysis feedback module.

[0165] In some embodiments, the electromagnetic monitoring real-time analysis method further includes determining the number of test cycles for each set of test item data in at least one set of test item data, and adjusting the automatic test time for at least one set of test item data.

[0166] These methods and steps are executed by the analysis feedback module 150. For the specific content regarding determining the number of test cycles and adjusting the automatic test time, refer to Figure 4 the relevant description of the configuration method of the analysis feedback module.

[0167] In some embodiments, adjusting the automatic test time for the at least one set of test item data includes two steps. These two steps are executed by the analysis feedback module 150.

[0168] The first step is to determine the interference characteristics.

[0169] In some embodiments, the interference characteristics can be determined based on historical test data. The interference characteristics include the occurrence time of occasional human interference or industrial interference.

[0170] The second step is to determine the automatic test time.

[0171] In some embodiments, the automatic test time for at least one set of test item data can be determined based on the interference characteristics and the number of test cycles of each set of test item data.

[0172] For the specific content of adjusting the automatic test time of the at least one set of test item data, refer to Figure 4 the relevant description of determining the automatic test time in

[0173] One or more embodiments of this specification provide an electromagnetic monitoring real-time analysis device, including a processor, and the processor is used to execute an electromagnetic monitoring real-time analysis method.

[0174] One or more embodiments of this specification also provide a computer-readable storage medium, and the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes an electromagnetic monitoring real-time analysis method.

[0175] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0176] At the same time, this specification uses specific terms to describe the embodiments of this specification. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0177] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numbers and letters, or the use of other names in this specification are not used to limit the order of the processes and methods in this specification. Although some currently considered useful invention embodiments are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims aim to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through a software solution, such as installing the described system on an existing server or mobile device.

[0178] Similarly, it should be noted that, in order to simplify the presentation disclosed in this specification and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of this specification, multiple features are sometimes grouped into one embodiment, drawing or description thereof. However, this disclosure method does not mean that the features required by the object of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the single embodiments disclosed above.

[0179] In some embodiments, numbers are used to describe components and the quantity of attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the said numbers allow a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, and such approximate values may change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of this specification to confirm the breadth of their scope are approximate values, in specific embodiments, such numerical settings are as precise as possible within the feasible range.

[0180] For each patent, patent application, patent application publication and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into this specification as references. Except for the application history documents that are inconsistent with or conflict with the content of this specification, and also except for the documents (currently or subsequently appended to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if there are inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the attached materials of this specification and the content described in this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0181] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example rather than a limitation, alternative configurations of the embodiments of this specification can be considered to be consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments clearly introduced and described in this specification.

Claims

1. A parameter analysis system for electromagnetic monitoring, characterized in that: include: A data transmission module, a data cache module, a processing module, a storage module and an analysis and feedback module; the data transmission module is configured to receive electromagnetic environment test data, the electromagnetic environment test data including at least one set of test item data, the test item data including sampled spectrum data, calibration data, antenna and system gain data; the data cache module is configured to cache the electromagnetic environment test data; and based on the control instructions of the analysis and feedback module, send the electromagnetic environment test data to the processing module and / or the storage module; the processing module is configured to determine the data to be analyzed based on the electromagnetic environment test data, and send the data to be analyzed to the storage module; the storage module is configured to store the electromagnetic environment test data and the data to be analyzed; the analysis and feedback module is configured to determine the control instructions to control the data transmission direction of the data cache module; Based on the data to be analyzed in the storage module, determining whether there is a test parameter error through a test parameter judgment model, wherein the test parameter judgment model is a machine learning model; the test parameter judgment model includes a spectrum processing layer and an analysis layer; The analysis and feedback module is further configured to: determine, based on historical test data, test parameter frequent items and corresponding support degrees of the test parameter frequent items; construct a frequent item database based on the test parameter frequent items and corresponding support degrees of the test parameter frequent items; determine, based on the frequent item database, the number of test cycles for each set of test item data in the at least one set of test item data; and adjust the automatic test time of the at least one set of test item data; The analysis and feedback module is further configured to: determine interference characteristics based on historical test data, the interference characteristics including the occurrence time of occasional human interference or industrial interference; determine the automatic test time of the at least one set of test item data based on the interference characteristics and the number of test cycles of each set of test item data; The analysis and feedback module is further configured to: determine the automatic test time of at least one set of test item data through a time determination model based on the interference characteristics, test requirements, test duration and the number of test cycles for each set of test item data; wherein the time determination model is a machine learning model.

2. The system according to claim 1, wherein The analysis feedback module is further configured to: in response to the test parameter error, issue a parameter error warning, interrupt the current test, and issue a calibration request; in response to obtaining a calibration completion instruction, restart the test.

3. A parameter analysis method for electromagnetic monitoring, comprising: receiving electromagnetic environment test data, the electromagnetic environment test data including at least one set of test item data, the test item data including sampled spectrum data, calibration data, antenna and system gain data; determining data to be analyzed based on the electromagnetic environment test data, and storing the electromagnetic environment test data and the data to be analyzed; Based on the data to be analyzed, determining whether there is a test parameter error through a test parameter judgment model, wherein the test parameter judgment model is a machine learning model; the test parameter judgment model includes a spectrum processing layer and an analysis layer; The method further includes: determining, based on historical test data, test parameter frequent items and corresponding supports of the test parameter frequent items; constructing a frequent item database based on the test parameter frequent items and corresponding supports of the test parameter frequent items; determining, based on the frequent item database, the number of test cycles for each group of test item data in the at least one group of test item data; and adjusting the automatic test time of the at least one group of test item data; The method further includes: determining interference characteristics based on historical test data, the interference characteristics including the occurrence time of occasional human interference or industrial interference; determining the automatic test time of the at least one set of test item data based on the interference characteristics and the number of test cycles of each set of test item data; Determining the automatic test time of at least one group of test item data based on the interference characteristics and the number of test cycles for each group of test item data includes: determining the automatic test time of at least one group of test item data through a time determination model based on the interference characteristics, test requirements, test duration and the number of test cycles for each group of test item data; wherein the time determination model is a machine learning model.

4. The method according to claim 3, wherein The method further includes: in response to the test parameter error, issuing a parameter error warning, interrupting the current test, and issuing a calibration request; in response to obtaining a calibration completion instruction, restarting the test.

Images