Large language model auxiliary test measurement method and system

Abstract

The invention provides a large language model auxiliary test measurement method and system, and relates to the technical field of test measurement, and the method comprises the steps: collecting the measurement original data, drawing images and measurement parameters of a tested circuit through a measurement test device, determining the data content of an input large language model according to the question type selected by a user, when the problem type is a waveform quality related problem, inputting a drawing image and a measurement and calculation parameter to the large language model, and when the problem type is a data calculation and analysis related problem, inputting measurement original data and the measurement and calculation parameter to the large language model; through a dynamic time warping algorithm, based on waveform similarities of the same channel at different moments recorded in the whole period, waveform change information of the tested circuit in the whole test measurement process is obtained; and generating a test measurement analysis report, wherein the analysis report comprises waveform quality analysis, circuit noise source analysis, existing problems and solutions, parameter information and a data operation synthesis result.

Description

Technical Field

[0001] The present invention relates to test measurement technology, and in particular to a large language model-assisted test measurement method and system. Background Art

[0002] Electronic measurement and testing technology has become an indispensable part of modern scientific research, industrial production and education. As an innovative tool in the field of electronic measurement, desktop test and measurement software has been favored by a large number of users for its convenience, efficiency and accuracy.

[0003] Desktop test and measurement software displays complex electronic signals in an intuitive and easy-to-understand waveform form, helping users quickly analyze and identify common signal characteristics in circuits. It can not only display key parameters such as signal amplitude, frequency, phase, etc. in real time, but also supports a variety of signal processing and filtering functions.

[0004] In the process of measurement and testing, the understanding of some uncommon waveforms and the reasons for the generation of such waveforms often confuse some novices or non-professional users. Limited analysis methods are not targeted enough in different scenarios. Summary of the invention

[0005] The embodiments of the present invention provide a large language model-assisted test measurement method and system, which can solve the problems in the prior art.

[0006] According to a first aspect of the embodiments of the present invention,

[0007] Provides large language model-assisted testing and measurement methods, including:

[0008] Collecting raw measurement data, drawing images and calculated parameters of the circuit under test through the measurement test equipment, wherein the raw measurement data is multi-dimensional numerical data, the drawing images are generated by drawing according to the raw measurement data, and the calculated parameters include voltage parameters and time parameters calculated based on the raw measurement data, and inputting at least two of the raw measurement data, the drawing images and the calculated parameters into the large language model;

[0009] Determine the data content to be input into the large language model according to the type of question selected by the user; when the question type is a question related to waveform quality, input the drawing image and the measurement parameters into the large language model; when the question type is a question related to data calculation and analysis, input the measured raw data and the measurement parameters into the large language model;

[0010] Through a dynamic time warping algorithm, based on the waveform similarity of the same channel at different times recorded in a full cycle, the waveform change information of the tested circuit in the entire test and measurement process is obtained; through the multi-modal image recognition ability of the large language model, the input drawing image is understood and analyzed to obtain waveform quality analysis results and circuit noise source analysis results; and / or, through the generalized reasoning ability of the large language model, based on the input measurement raw data and measurement parameters, more dimensional parameter information is obtained, and mathematical operations are performed on the measurement raw data of multiple channels to synthesize new waveforms; a test measurement analysis report is generated, and the analysis report includes waveform quality analysis, circuit noise source analysis, existing problems and solutions, parameter information, and data operation synthesis results.

[0011] In an optional embodiment,

[0012] Through the dynamic time warping algorithm, based on the waveform similarity of the same channel at different times recorded in the full cycle, the waveform change information of the circuit under test during the entire test and measurement process is obtained, including:

[0013] Acquire multiple timing waveform data collected by the same measurement channel of the circuit under test at different times;

[0014] Based on a dynamic time warping algorithm, an optimal matching path between every two time series waveform data in the plurality of time series waveform data is found through dynamic programming, wherein the optimal matching path maximizes the similarity between the two time series waveform data;

[0015] According to the optimal matching path, the similarity between each two time series waveform data is calculated to obtain similarity measurement values ​​of the time series waveform data of the same measurement channel at different times;

[0016] Based on the similarity metric value, obtaining a change trend of the waveform sequence of the same measurement channel during the entire test measurement process;

[0017] Generate test measurement full cycle record data, the record data contains the characteristic information and similarity change information of the same measurement channel waveform at different times, so as to record the state change of the test measurement object in the whole test process.

[0018] In an optional embodiment,

[0019] According to the optimal matching path, calculating the similarity between each two time series waveform data, and obtaining the similarity measurement values ​​of the time series waveform data of the same measurement channel at different times includes:

[0020] Initialize the distance matrix and create a matrix of size (N+1)x(M+1), where N and M are the lengths of the two timing waveforms respectively. Set the initial value of the matrix to infinity and the origin of the matrix to 0.

[0021] Iteratively calculate the distance between the corresponding elements of two time series waveforms and update the distance matrix;

[0022] The distance matrix is ​​traced back to find a path with the shortest cumulative distance, which is used as the optimal matching path of the two timing waveforms. The shortest distance value is the similarity measurement value of the two timing waveform data.

[0023] In an optional embodiment,

[0024] Through the generalized reasoning ability of the large language model, based on the input measurement raw data and measurement parameters, more dimensional parameter information is obtained, and mathematical operations are performed on the measurement raw data of multiple channels to synthesize new waveforms, including:

[0025] Acquire measurement raw data collected by multiple measurement channels of the measured object and measurement parameters calculated based on the measurement raw data, wherein the measurement raw data is waveform data in the time domain or frequency domain, and the measurement parameters include voltage parameters and time parameters;

[0026] Inputting the measured raw data and the corresponding measurement parameters into a pre-trained large language model, wherein the large language model is trained based on a large amount of test measurement data and corresponding analysis results, and has the ability to understand, generalize and reason about the test measurement data;

[0027] Utilizing the generalized reasoning capability of the large language model, extracting the high-dimensional feature information contained in the raw measurement data, and combining the measurement parameters to obtain the deep feature parameters of multiple measurement channels of the measured object under different working conditions;

[0028] According to the preset mathematical operation rules, the raw data of multiple measurement channels are fused and processed to generate a new synthetic waveform corresponding to the actual working state of the measured object;

[0029] The novel synthetic waveform sets different mathematical operation rules according to actual application requirements, including linear combination, nonlinear transformation, and time-frequency domain conversion of waveform data of different measurement channels.

[0030] In an optional embodiment,

[0031] Determining the data content input into the large language model according to the type of question selected by the user, when the type of question is a waveform quality related question, inputting a drawing image and a measurement parameter into the large language model, and when the type of question is a data calculation and analysis related question, inputting measurement raw data and a measurement parameter into the large language model includes:

[0032] Obtaining the type of question selected by the user, wherein the type of question includes questions related to waveform quality and questions related to data calculation and analysis;

[0033] Adaptively determining the test measurement data type and content input into the large language model according to the question type selected by the user;

[0034] When the problem type is a waveform quality-related problem, the waveform drawing image of the measured object and related measurement parameters are input into the large language model, and the measurement parameters include numerical values ​​representing waveform characteristics calculated based on the measurement data;

[0035] When the problem type is a problem related to data calculation and analysis, the original data obtained by measurement and collection and the relevant measurement parameters are input into the large language model, and the original data is a time series numerical vector.

[0036] In an optional embodiment,

[0037] The method further comprises:

[0038] The large language model adaptively calls the corresponding data processing flow and algorithm model according to the input test measurement data type and content;

[0039] When the input data type is a waveform drawing image, the image recognition algorithm is called to extract features and understand the semantics of the input image, and combined with the measurement parameters, the analysis results related to the waveform quality are output;

[0040] When the input data type is raw measurement data, the numerical calculation and statistical analysis algorithms are called to process the raw data, and the calculation and analysis results related to the performance indicators of the measured object are output in combination with the measurement parameters;

[0041] Among them, the large language model adopts a learning paradigm that combines pre-training and fine-tuning. Through pre-training on massive test measurement-related corpus, it has basic knowledge and common sense in the field of test measurement. For different types of test measurement problems, it uses customized data for problem-based fine-tuning to enable it to quickly adapt to specific problems.

[0042] According to a second aspect of the embodiments of the present invention,

[0043] Provides a large language model-assisted test and measurement system, including:

[0044] The first unit is used to collect measurement raw data, drawing images and measurement parameters of the measured circuit through the measurement test equipment, wherein the measurement raw data is multi-dimensional numerical data, the drawing image is generated by drawing according to the measurement raw data, and the measurement parameters include voltage parameters and time parameters calculated based on the measurement raw data, and at least two of the measurement raw data, drawing images and measurement parameters are input into the large language model;

[0045] The second unit is used to determine the data content to be input into the large language model according to the type of question selected by the user, and when the type of question is a waveform quality-related question, input the drawing image and the measurement parameters into the large language model; when the type of question is a data calculation and analysis-related question, input the measurement raw data and the measurement parameters into the large language model;

[0046] The third unit is used to obtain the waveform change information of the tested circuit in the whole test and measurement process through the dynamic time warping algorithm based on the waveform similarity of the same channel at different times recorded in the whole cycle; understand and analyze the input drawing image through the multimodal image recognition ability of the large language model to obtain the waveform quality analysis result and the circuit noise source analysis result; and / or, through the generalized reasoning ability of the large language model, based on the input measurement raw data and measurement parameters, obtain parameter information of more dimensions, perform mathematical operations on the measurement raw data of multiple channels to synthesize new waveforms; generate a test measurement analysis report, the analysis report includes waveform quality analysis, circuit noise source analysis, existing problems and solutions, parameter information, and data operation synthesis results.

[0047] According to a third aspect of the embodiments of the present invention,

[0048] An electronic device is provided, comprising:

[0049] processor;

[0050] a memory for storing processor-executable instructions;

[0051] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0052] A fourth aspect of the embodiments of the present invention is:

[0053] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0054] This application can improve the user's ability to interpret data during the measurement of signal processes; improve the efficiency of non-professional users in solving problems caused by unusual waveforms; and record debugging test measurement behaviors throughout the entire cycle to quickly focus on problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flowchart of a large language model-assisted test measurement method according to an embodiment of the present invention;

[0056] Figure 2 It is a schematic diagram of the structure of a large language model assisted test and measurement system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0059] Figure 1 FIG. 1 is a flow chart of a large language model-assisted test measurement method according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0060] S101. Collecting raw measurement data, drawing images and calculated parameters of the circuit under test through the measurement test equipment, wherein the raw measurement data is multi-dimensional numerical data, the drawing images are generated by drawing according to the raw measurement data, and the calculated parameters include voltage parameters and time parameters calculated based on the raw measurement data, and inputting at least two of the raw measurement data, drawing images and calculated parameters into the large language model;

[0061] S102. According to the type of question selected by the user, determine the data content to be input into the large language model. When the question type is a waveform quality-related question, input the drawing image and the measurement parameters into the large language model. When the question type is a data calculation and analysis-related question, input the measured raw data and the measurement parameters into the large language model.

[0062] S103. Through the dynamic time warping algorithm, based on the waveform similarity of the same channel at different times recorded in the whole cycle, the waveform change information of the tested circuit in the whole test and measurement process is obtained; through the multi-modal image recognition ability of the large language model, the input drawing image is understood and analyzed to obtain the waveform quality analysis results and the circuit noise source analysis results; and / or, through the generalized reasoning ability of the large language model, based on the input measurement raw data and measurement parameters, more dimensional parameter information is obtained, and the measurement raw data of multiple channels are mathematically operated to synthesize new waveforms; a test measurement analysis report is generated, and the analysis report includes waveform quality analysis, circuit noise source analysis, existing problems and solutions, parameter information, and data operation synthesis results.

[0063] In an optional embodiment,

[0064] Through the dynamic time warping algorithm, based on the waveform similarity of the same channel at different times recorded in the full cycle, the waveform change information of the circuit under test during the entire test and measurement process is obtained, including:

[0065] Acquire multiple timing waveform data collected by the same measurement channel of the circuit under test at different times;

[0066] Based on a dynamic time warping algorithm, an optimal matching path between every two time series waveform data in the plurality of time series waveform data is found through dynamic programming, wherein the optimal matching path maximizes the similarity between the two time series waveform data;

[0067] According to the optimal matching path, the similarity between each two time series waveform data is calculated to obtain similarity measurement values ​​of the time series waveform data of the same measurement channel at different times;

[0068] Based on the similarity metric value, obtaining a change trend of the waveform sequence of the same measurement channel during the entire test measurement process;

[0069] Generate test measurement full cycle record data, the record data contains the characteristic information and similarity change information of the same measurement channel waveform at different times, so as to record the state change of the test measurement object in the whole test process.

[0070] Exemplarily, this application proposes a full-cycle waveform similarity analysis method based on a dynamic time warping algorithm, which is used to obtain waveform change information of the circuit under test during the entire test and measurement process. This method achieves comprehensive monitoring of the state changes of the object under test by analyzing the waveform similarity of the same channel at different times. The specific steps and technical content of this method are described in detail below:

[0071] First, it is necessary to obtain multiple timing waveform data collected by the same measurement channel of the circuit under test at different times. These data represent the different states of the object under test during the test and measurement process.

[0072] The specific steps are as follows:

[0073] 1) Set the sampling time interval: Set the appropriate sampling time interval according to the characteristics of the object being tested and the test requirements. For example, for a circuit that changes faster, it can be set to 1ms; for a circuit that changes slower, it can be set to 100ms.

[0074] 2) Determine the number of sampling points: Determine the number of sampling points for each waveform based on the test period and sampling frequency. For example, if the test period is 1s and the sampling frequency is 1kHz, the number of sampling points for each waveform is 1000 points.

[0075] 3) Perform multiple sampling: During the entire test cycle, waveform data is collected multiple times at set time intervals. For example, if the test cycle is 1 hour and the sampling interval is 1 minute, a total of 60 waveform data need to be collected.

[0076] 4) Data preprocessing: Preprocess the collected raw data, including denoising, normalization and other operations, for subsequent analysis.

[0077] Example: Assume that the test cycle of a circuit is 10 minutes, waveform data is collected every 30 seconds, and each waveform contains 1000 sampling points. Then, 20 time-series waveform data will be obtained in the end, and each waveform data is a one-dimensional array containing 1000 values.

[0078] Next, the dynamic time warping (DTW) algorithm is used to find the optimal matching path between each two time series waveform data. The DTW algorithm can process time series of different lengths and is insensitive to local nonlinear scaling of the time axis, so it is particularly suitable for waveform similarity analysis.

[0079] The implementation steps are as follows:

[0080] 1) Construct a distance matrix: For the two waveforms A and B to be compared, construct a distance matrix D of size m×n, where m and n are the lengths of the two waveforms. Each element D[i][j] in the matrix represents the distance between the i-th point of waveform A and the j-th point of waveform B.

[0081] 2) Initialize the cumulative distance matrix: Create a cumulative distance matrix C of the same size as the distance matrix D, and initialize the first element C[0][0] = D[0][0].

[0082] 3) Fill the cumulative distance matrix: Starting from the upper left corner, fill the cumulative distance matrix C by row or column. For each element C[i][j], its value is equal to D[i][j] plus the minimum value of the three adjacent elements to its left, above, and above the left.

[0083] 4) Backtrack to find the optimal path: Starting from the lower right corner of matrix C, backtrack to the upper left by comparing the values ​​of adjacent elements until reaching the upper left corner, and the optimal matching path can be obtained.

[0084] 5) Output the optimal matching path: record the path obtained by backtracking as the optimal matching result between the two waveforms.

[0085] Example: Assume there are two simplified waveforms A = [1, 2, 3, 4, 5] and B = [2, 3, 4, 5, 6] of length 5. Through the above steps, we can get an optimal matching path [(0, 0), (1, 1), (2, 2), (3, 3), (4, 4)]. This means that the first point of A matches the first point of B, the second point of A matches the second point of B, and so on.

[0086] Based on the obtained optimal matching path, the similarity between every two timing waveform data is calculated to obtain the similarity measurement values ​​of the timing waveform data of the same measurement channel at different times.

[0087] The calculation steps are as follows:

[0088] 1) Path distance calculation: Along the optimal matching path, accumulate the distance between each pair of matching points to obtain the total path distance.

[0089] 2) Normalization: Considering the influence of waveforms of different lengths, the total path distance is divided by the length of the matching path to obtain the normalized distance.

[0090] 3) Similarity conversion: convert the normalized distance to a similarity value. You can use methods such as exponential functions to map the distance to a similarity value between 0 and 1, where a larger value indicates more similarity.

[0091] 4) Construct a similarity matrix: Calculate the similarity of all collected waveforms pairwise and construct a similarity matrix.

[0092] Example: Assuming that a total of 5 waveforms are collected, the calculated similarity matrix is ​​as follows:

[0093] [1.00,0.95,0.88,0.82,0.75];

[0094] [0.95,1.00,0.93,0.87,0.80];

[0095] [0.88,0.93,1.00,0.94,0.86];

[0096] [0.82,0.87,0.94,1.00,0.91];

[0097] [0.75,0.80,0.86,0.91,1.00];

[0098] The value on the diagonal is 1, indicating that the similarity between the waveform and itself is 1. The matrix is ​​symmetrical. For example, 0.95 in the first row and second column indicates that the similarity between the first waveform and the second waveform is 0.95.

[0099] Based on the calculated similarity metric value, the changing trend of the waveform sequence of the same measurement channel during the entire test measurement process is analyzed.

[0100] The analysis steps are as follows:

[0101] 1) Time series construction: The similarity values ​​of each waveform and all other waveforms form a time series. For example, for the first waveform, its time series is [1.00, 0.95, 0.88, 0.82, 0.75].

[0102] 2) Trend identification: Analyze the changing trend of each time series, which can be done using simple slope calculations or more complex time series analysis methods.

[0103] 3) Threshold setting: Set the threshold of similarity change to determine whether the waveform change is significant. For example, a similarity drop of more than 0.1 can be considered a significant change.

[0104] 4) Change point detection: Detect significant change points in the waveform sequence based on the set threshold.

[0105] 5) Trend visualization: Use line graphs and other methods to visualize waveform change trends for intuitive understanding.

[0106] Example: By analyzing the first row [1.00, 0.95, 0.88, 0.82, 0.75] of the above similarity matrix, it can be found that the waveform similarity shows a downward trend, and the similarity of the 4th and 5th waveforms relative to the 1st waveform decreases by more than 0.1, which can be determined as significant change points.

[0107] Finally, the full-cycle record data of the test measurement is generated, which contains the characteristic information and similarity change information of the waveform of the same measurement channel at different times, so as to record the state changes of the test measurement object during the entire test process.

[0108] The generation steps are as follows:

[0109] 1) Waveform feature extraction: Extract key features from each acquired waveform, such as statistics such as maximum value, minimum value, mean value, standard deviation, and time domain features such as peak value, valley value, rise time, and fall time.

[0110] 2) Summary of similarity changes: Summarize the similarity changes between each waveform and other waveforms, including average similarity, maximum similarity drop, number of significant changes, etc.

[0111] 3) Status marking: According to the similarity change and the preset threshold, the status at each moment is marked, such as "stable", "slight change", "significant change", etc.

[0112] 4) Data organization: Organize waveform features, similarity information and status marks in chronological order to form structured recorded data.

[0113] 5) Data storage: Save the generated full-cycle record data in an appropriate format (such as CSV, JSON, etc.) to facilitate subsequent analysis and processing.

[0114] Example: Assuming that 10 waveforms are collected during a test, the generated full-cycle record data may be as follows:

[0115] Time, maximum value, minimum value, mean value, standard deviation, average similarity, maximum similarity drop, number of significant changes, status;

[0116] 1,5.2,-3.1,1.5,2.3,1.00,0.00,0,stable;

[0117] 2,5.3,-3.0,1.6,2.2,0.95,0.05,0,stable;

[0118] 3,5.5,-2.8,1.8,2.1,0.91,0.09,0,slight change;

[0119] 4,5.8,-2.5,2.1,2.0,0.86,0.14,1,significant change;

[0120] 5,6.2,-2.1,2.5,1.9,0.81,0.19,2,significant change;

[0121] In this way, the state changes of the object under test during the entire test process can be fully recorded, providing an important basis for subsequent analysis and diagnosis.

[0122] In summary, the full-cycle waveform similarity analysis method based on dynamic time warping proposed in this application realizes the comprehensive analysis and recording of the waveform changes of the circuit under test during the entire test and measurement process through the steps of multi-time waveform data acquisition, dynamic time warping algorithm implementation, similarity measurement value calculation, waveform change trend analysis and full-cycle record data generation. This method can effectively capture the dynamic characteristics of the object under test and provide new ideas and means for circuit performance evaluation and fault diagnosis.

[0123] In an optional embodiment,

[0124] According to the optimal matching path, calculating the similarity between each two time series waveform data, and obtaining the similarity measurement values ​​of the time series waveform data of the same measurement channel at different times includes:

[0125] Initialize the distance matrix and create a matrix of size (N+1)x(M+1), where N and M are the lengths of the two timing waveforms respectively. Set the initial value of the matrix to infinity and the origin of the matrix to 0.

[0126] Iteratively calculate the distance between the corresponding elements of two time series waveforms and update the distance matrix;

[0127] The distance matrix is ​​traced back to find a path with the shortest cumulative distance, which is used as the optimal matching path of the two timing waveforms. The shortest distance value is the similarity measurement value of the two timing waveform data.

[0128] By way of example, this application describes in detail a method for calculating the similarity of time series waveforms based on dynamic programming. This method achieves accurate quantification of the similarity between any two time series waveform data by constructing a distance matrix, iteratively calculating element distances, and backtracking to find the optimal matching path. The specific implementation process and technical details of this method will be gradually introduced below.

[0129] First, a distance matrix needs to be initialized to store the cumulative distances of each element between two time series waveforms.

[0130] The specific steps are as follows:

[0131] 1) Determine the matrix size: Assume that the two timing waveforms to be compared are A and B, with lengths of N and M respectively. Then create a matrix D of size (N+1)×(M+1). The matrix size is 1 more than the waveform length to handle boundary conditions.

[0132] 2) Initialize the matrix elements: Initialize all elements of the matrix D to a very large value, usually the largest floating point number in the programming language. This is to ensure that these initial values ​​will not interfere with the actual distance calculation in subsequent calculations.

[0133] 3) Set the starting point: Set the upper left corner element D[0][0] of matrix D to 0. This point represents the starting position of the two waveforms, and the cumulative distance is naturally 0.

[0134] 4) Processing boundary conditions: The first row and the first column can be selectively processed to reflect the matching of the starting part of the waveform.

[0135] Example:

[0136] Assume that there are two simplified time series waveforms A = [1, 2, 3] and B = [2, 3, 4, 5]. The initialized distance matrix D (using inf to represent a very large number) is as follows:

[0137]

[0138] Next, the distance matrix is ​​gradually filled and updated by iteratively calculating the distance between the corresponding elements of the two time series waveforms.

[0139] The calculation steps are as follows:

[0140] 1) Define the distance metric: Select an appropriate distance metric to calculate the distance between two waveform elements. Commonly used methods include Euclidean distance, Manhattan distance, etc. In this example, we use a simple absolute difference as the distance metric.

[0141] 2) Iteratively fill the matrix: Starting from the upper left corner, traverse the matrix D by row or column. For each element D[i][j], its value is equal to the distance between A[i-1] and B[j-1], plus the minimum value of the three adjacent elements on its left D[i][j-1], above D[i-1][j], and above left D[i-1][j-1].

[0142] 3) Boundary processing: For the elements in the first row and the first column, since there are no elements on the left or above, special processing is required. Usually, the cumulative distance can be set to infinity, or appropriately set according to the specific application.

[0143] 4) Complete filling: Repeat step 2 until the lower right corner element of matrix D is filled, at which point the entire matrix calculation is completed.

[0144] Example:

[0145] Continuing to use the previous waveforms A = [1, 2, 3] and B = [2, 3, 4, 5], the filled distance matrix D is as follows:

[0146]

[0147] Finally, by backtracking the distance matrix, a path with the shortest cumulative distance is found as the optimal matching path of the two timing waveforms.

[0148] The steps of backtracking are as follows:

[0149] 1) Determine the starting point: Start backtracking from the lower right corner element D[N][M] of the distance matrix D. The value of this element is the cumulative distance between the two complete waveforms.

[0150] 2) Select direction: For the current position (i, j), compare the values ​​of the three adjacent elements D[i-1][j] (above), D[i][j-1] (left), and D[i-1][j-1] (top left), and select the element with the smallest value as the next backtracking point.

[0151] 3) Record the path: Record the coordinates (i, j) of each step, which constitute the optimal matching path.

[0152] 4) Termination condition: When backtracking reaches the upper left corner of the matrix D[0][0], the backtracking process ends.

[0153] 5) Path reversal: Since backtracking is performed from the end point to the starting point, the recorded path needs to be reversed to obtain the optimal matching path from the starting point to the end point.

[0154] Example:

[0155] For the previously filled distance matrix, the optimal matching path obtained by backtracking is:

[0156] [(0,0),(1,1),(2,2),(3,3),(3,4)];

[0157] This means that the first point of waveform A matches the first point of B, the second point of A matches the second point of B, and the third point of A matches the third and fourth points of B.

[0158] Finally, the similarity measure between the two time series waveform data is determined based on the optimal matching path obtained by backtracking.

[0159] The steps to determine are as follows:

[0160] 1) Extract the shortest distance: The element D[N][M] in the lower right corner of the distance matrix D is the shortest cumulative distance.

[0161] 2) Normalization: Considering the influence of waveforms of different lengths, the accumulated distance can be normalized by dividing it by the path length.

[0162] 3) Similarity conversion: convert the normalized distance value into similarity. A common method is to use an exponential function to map the distance to a similarity value between 0 and 1, where a larger value indicates a greater similarity.

[0163] 4) Result output: Output the calculated similarity measurement value as a quantitative indicator of the similarity between the two time series waveform data.

[0164] Example:

[0165] For the previous example, the shortest cumulative distance is 2 (the value in the bottom right corner of the matrix).

[0166] Suppose we use simple linear normalization and divide the distance by the path length of 5, resulting in a normalized distance of 0.4.

[0167] It is then converted into a similarity value using the exponential function e^(-0.4)≈0.67.

[0168] Therefore, the similarity measure value of waveforms A and B is 0.67, indicating that they have a moderate degree of similarity.

[0169] By repeating the above steps, the similarity between multiple time series waveform data collected by the same measurement channel at different times can be calculated, so as to obtain the similarity change of the time series waveform data of the measurement channel in the whole test measurement process.

[0170] The specific analysis steps are as follows:

[0171] 1) Time window division: According to the test requirements, the entire test process is divided into multiple time windows.

[0172] 2) Waveform pairing: pair the waveforms within each time window and the waveforms between adjacent time windows.

[0173] 3) Batch calculation: Use the above method to batch calculate the similarity measure between each pair of waveforms.

[0174] 4) Similarity matrix construction: All calculated similarity measurement values ​​are organized into a matrix, and each element of the matrix represents the similarity between the waveforms at two specific moments.

[0175] 5) Trend analysis: Based on the similarity matrix, analyze the changing trend of waveform similarity over time and identify possible abnormal points or change patterns.

[0176] Example:

[0177] Assume that in a test process lasting 10 minutes, waveform data is collected once a minute, and a total of 10 waveforms are obtained. The calculated similarity matrix may be as follows:

[0178]

[0179] From this matrix, we can observe that the waveforms at adjacent moments have high similarity, while the similarity gradually decreases as the time interval increases. In particular, we can notice that the similarity pattern of the waveforms changes significantly from the 6th minute, which may indicate that some state transition has occurred in the circuit under test at this time.

[0180] Through this method, we can not only quantify the similarity between waveforms at any two moments, but also comprehensively analyze the dynamic characteristic changes of the circuit under test during the entire test and measurement process. This provides strong data support for circuit performance evaluation, fault diagnosis and anomaly detection.

[0181] In summary, the timing waveform similarity calculation method based on dynamic programming proposed in this application realizes the accurate quantification of timing waveform similarity through steps such as distance matrix initialization, iterative calculation, and optimal path backtracking. Combined with multi-time waveform analysis, this method can effectively capture the state changes of the object under test during the test process, laying the foundation for further circuit analysis and diagnosis.

[0182] In an optional embodiment,

[0183] Through the generalized reasoning ability of the large language model, based on the input measurement raw data and measurement parameters, more dimensional parameter information is obtained, and mathematical operations are performed on the measurement raw data of multiple channels to synthesize new waveforms, including:

[0184] Acquire measurement raw data collected by multiple measurement channels of the measured object and measurement parameters calculated based on the measurement raw data, wherein the measurement raw data is waveform data in the time domain or frequency domain, and the measurement parameters include voltage parameters and time parameters;

[0185] Inputting the measured raw data and the corresponding measurement parameters into a pre-trained large language model, wherein the large language model is trained based on a large amount of test measurement data and corresponding analysis results, and has the ability to understand, generalize and reason about the test measurement data;

[0186] Utilizing the generalized reasoning capability of the large language model, extracting the high-dimensional feature information contained in the raw measurement data, and combining the measurement parameters to obtain the deep feature parameters of multiple measurement channels of the measured object under different working conditions;

[0187] According to the preset mathematical operation rules, the raw data of multiple measurement channels are fused and processed to generate a new synthetic waveform corresponding to the actual working state of the measured object;

[0188] The novel synthetic waveform sets different mathematical operation rules according to actual application requirements, including linear combination, nonlinear transformation, and time-frequency domain conversion of waveform data of different measurement channels.

[0189] In an optional embodiment,

[0190] Determining the data content input into the large language model according to the type of question selected by the user, when the type of question is a waveform quality related question, inputting a drawing image and a measurement parameter into the large language model, and when the type of question is a data calculation and analysis related question, inputting measurement raw data and a measurement parameter into the large language model includes:

[0191] Obtaining the type of question selected by the user, wherein the type of question includes questions related to waveform quality and questions related to data calculation and analysis;

[0192] Adaptively determining the test measurement data type and content input into the large language model according to the question type selected by the user;

[0193] When the problem type is a waveform quality-related problem, the waveform drawing image of the measured object and related measurement parameters are input into the large language model, and the measurement parameters include numerical values ​​representing waveform characteristics calculated based on the measurement data;

[0194] When the problem type is a problem related to data calculation and analysis, the original data obtained by measurement and collection and the relevant measurement parameters are input into the large language model, and the original data is a time series numerical vector.

[0195] Exemplarily, this application describes in detail an adaptive data input method based on question type, which intelligently determines the data content input to the large language model according to the question type selected by the user. This method can effectively improve the efficiency and accuracy of the large language model when processing different types of test measurement questions. The specific implementation process and technical details of this method will be gradually introduced below.

[0196] First, a question type identification mechanism needs to be established to determine which category the question the user is concerned about belongs to.

[0197] The specific steps are as follows:

[0198] 1) Question type definition: Two major types of questions are defined in advance:

[0199] - Waveform quality related issues: mainly focus on the visually discernible attributes of the signal, such as shape and characteristics.

[0200] -Problems related to data calculation and analysis: mainly focus on the numerical characteristics, statistical properties and other indicators that need to be calculated.

[0201] 2) User interface design: Design an intuitive user interface that allows users to clearly select the question type.

[0202] 3) Keyword analysis: Perform keyword analysis on the question description entered by the user to assist in determining the question type.

[0203] 4) Historical data learning: Based on the user’s historical query records, a question type prediction model is established.

[0204] 5) Type confirmation: Comprehensively consider user selection, keyword analysis and historical data prediction results to finally determine the question type.

[0205] Example:

[0206] Assume that the user selects "Waveform quality related issues" through the interface and enters the following problem description:

[0207] "Is there an overshoot on the rising edge of this signal? If so, how much?"

[0208] The system performs the following steps:

[0209] 1. Record the user's direct selection: waveform quality related issues;

[0210] 2. Analyze the key words in the problem description: rising edge, overshoot;

[0211] 3. Query history: 70% of the user’s previous queries were related to waveform quality issues;

[0212] 4. Comprehensive judgment: confirm that this is a waveform quality-related issue;

[0213] Based on the determined question type, the system needs to adaptively select the appropriate data type to input into the large language model.

[0214] The selection steps are as follows:

[0215] 1) Data type mapping: Establish a mapping relationship between problem type and data type.

[0216] - Waveform quality related issues → Waveform drawing image + measurement parameters

[0217] -Data calculation and analysis related issues → original measurement data + measurement parameters

[0218] 2) Data availability check: Check whether the required data type is available. If not, consider alternatives or prompt the user.

[0219] 3) Data format conversion: Convert the selected data into an input format acceptable to the large language model.

[0220] 4) Data combination: Combine multiple types of data as needed, such as image data and text data.

[0221] 5) Input optimization: Perform necessary optimization on input data, such as compression and standardization, to improve model processing efficiency.

[0222] After the large language model processes the input data, the output results need to be processed and applied.

[0223] The processing steps are as follows:

[0224] 1) Result analysis: Analyze the output of the model and extract key information.

[0225] 2) Result verification: Compare and verify the analysis results of the model with those of traditional methods.

[0226] 3) Visual processing: convert the analysis results into intuitive charts or reports.

[0227] 4) Result storage: The analysis results are stored in the database for subsequent trend analysis and model optimization.

[0228] 5) Feedback mechanism: allows users to evaluate and provide feedback on analysis results to continuously improve system performance.

[0229] 1. Overshoot phenomenon: The rising edge of the signal does have an overshoot phenomenon. The measured parameters show that the overshoot amplitude is 4%, which is considered to be within the acceptable range in most applications (usually less than 5% is considered acceptable).

[0230] 2. Cause of overshoot: The overshoot phenomenon is likely caused by the resonance formed by parasitic inductance and load capacitance in the signal path. The high slew rate (0.5V / ns) may exacerbate this phenomenon.

[0231] 3. Impact Assessment: Although 4% overshoot is acceptable in many cases, it may cause problems in some high-precision applications, such as front-end signal processing of analog-to-digital converters.

[0232] 4. Suggestions for improvement:

[0233] -Optimize PCB layout and reduce parasitic inductance of signal paths.

[0234] -Consider adding appropriate damping networks in the signal path.

[0235] - If possible, try reducing the drive strength slightly to reduce the slew rate.

[0236] -Use a driver with pre-emphasis to provide extra drive strength at the beginning of the rising edge and then reduce the drive strength as it approaches the target voltage.

[0237] 5. Further analysis: It is recommended to perform frequency domain analysis to observe the high-frequency components caused by overshoot to more fully evaluate its impact.

[0238] In general, although overshoot exists, it is relatively mild and will not cause serious problems in most applications, but there is still room for optimization.

[0239] The analysis results include direct answers to questions, as well as in-depth technical insights and improvement suggestions. The system can further process the results, such as generating a PDF report containing the original waveform, key parameter tables and analysis conclusions.

[0240] In summary, the adaptive data input method based on question type proposed in this application significantly improves the efficiency and accuracy of the large language model in dealing with test and measurement problems by intelligently identifying the problem type and selecting and processing the input data accordingly. This method can not only handle traditional numerical analysis problems, but also effectively analyze problems that require visual insight, such as waveform quality. By optimizing the quality and structure of the input data, this method fully taps the potential of the large language model and provides a powerful intelligent analysis tool for the test and measurement field. This method is expected to play an important role in many fields such as electronic testing, signal processing, and fault diagnosis, and promote the development of test and measurement technology in a smarter and more efficient direction.

[0241] In an optional embodiment,

[0242] The method further comprises:

[0243] The large language model adaptively calls the corresponding data processing flow and algorithm model according to the input test measurement data type and content;

[0244] When the input data type is a waveform drawing image, the image recognition algorithm is called to extract features and understand the semantics of the input image, and combined with the measurement parameters, the analysis results related to the waveform quality are output;

[0245] When the input data type is raw measurement data, the numerical calculation and statistical analysis algorithms are called to process the raw data, and the calculation and analysis results related to the performance indicators of the measured object are output in combination with the measurement parameters;

[0246] Among them, the large language model adopts a learning paradigm that combines pre-training and fine-tuning. Through pre-training on massive test measurement-related corpus, it has basic knowledge and common sense in the field of test measurement. For different types of test measurement problems, it uses customized data for problem-based fine-tuning to enable it to quickly adapt to specific problems.

[0247] Figure 2 FIG. 1 is a schematic diagram of the structure of a large language model-assisted test and measurement system according to an embodiment of the present invention. Figure 2 As shown, the system comprises:

[0248] The first unit is used to collect measurement raw data, drawing images and measurement parameters of the measured circuit through the measurement test equipment, wherein the measurement raw data is multi-dimensional numerical data, the drawing image is generated by drawing according to the measurement raw data, and the measurement parameters include voltage parameters and time parameters calculated based on the measurement raw data, and at least two of the measurement raw data, drawing images and measurement parameters are input into the large language model;

[0249] The second unit is used to determine the data content to be input into the large language model according to the type of question selected by the user, and when the type of question is a waveform quality-related question, input the drawing image and the measurement parameters into the large language model; when the type of question is a data calculation and analysis-related question, input the measurement raw data and the measurement parameters into the large language model;

[0250] The third unit is used to obtain the waveform change information of the tested circuit in the whole test and measurement process through the dynamic time warping algorithm based on the waveform similarity of the same channel at different times recorded in the whole cycle; understand and analyze the input drawing image through the multimodal image recognition ability of the large language model to obtain the waveform quality analysis result and the circuit noise source analysis result; and / or, through the generalized reasoning ability of the large language model, based on the input measurement raw data and measurement parameters, obtain parameter information of more dimensions, perform mathematical operations on the measurement raw data of multiple channels to synthesize new waveforms; generate a test measurement analysis report, the analysis report includes waveform quality analysis, circuit noise source analysis, existing problems and solutions, parameter information, and data operation synthesis results.

[0251] According to a third aspect of the embodiments of the present invention,

[0252] An electronic device is provided, comprising:

[0253] processor;

[0254] a memory for storing processor-executable instructions;

[0255] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0256] A fourth aspect of the embodiments of the present invention is:

[0257] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0258] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0259] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A large language model-assisted test measurement method, characterized in that: include: Collecting raw measurement data, drawing images and calculated parameters of the circuit under test through the measurement test equipment, wherein the raw measurement data is multi-dimensional numerical data, the drawing images are generated by drawing according to the raw measurement data, and the calculated parameters include voltage parameters and time parameters calculated based on the raw measurement data, and inputting at least two of the raw measurement data, the drawing images and the calculated parameters into the large language model; Determine the data content to be input into the large language model according to the type of question selected by the user; when the question type is a question related to waveform quality, input the drawing image and the measurement parameters into the large language model; when the question type is a question related to data calculation and analysis, input the measured raw data and the measurement parameters into the large language model; By using a dynamic time warping algorithm, based on the waveform similarity of the same channel at different times recorded in the entire cycle, the waveform change information of the circuit under test during the entire test and measurement process is obtained; by using the multimodal image recognition capability of the large language model, the input drawing image is understood and analyzed to obtain waveform quality analysis results and circuit noise source analysis results; and / or, by using the generalized reasoning capability of the large language model, based on the input measurement raw data and measurement parameters, more dimensional parameter information is obtained, and mathematical operations are performed on the measurement raw data of multiple channels to synthesize new waveforms; Generate a test measurement analysis report, which includes waveform quality analysis, circuit noise source analysis, existing problems and solutions, parameter information, and data calculation synthesis results.

2. The method according to claim 1, characterized in that Through the dynamic time warping algorithm, based on the waveform similarity of the same channel at different times recorded in the full cycle, the waveform change information of the circuit under test during the entire test and measurement process is obtained, including: Acquire multiple timing waveform data collected by the same measurement channel of the circuit under test at different times; Based on a dynamic time warping algorithm, an optimal matching path between every two time series waveform data in the plurality of time series waveform data is found through dynamic programming, wherein the optimal matching path maximizes the similarity between the two time series waveform data; According to the optimal matching path, the similarity between each two time series waveform data is calculated to obtain similarity measurement values ​​of the time series waveform data of the same measurement channel at different times; Based on the similarity metric value, obtaining a change trend of the waveform sequence of the same measurement channel during the entire test measurement process; Generate test measurement full cycle record data, the record data contains the characteristic information and similarity change information of the same measurement channel waveform at different times, so as to record the state change of the test measurement object in the whole test process.

3. The method according to claim 2, characterized in that According to the optimal matching path, calculating the similarity between each two time series waveform data, and obtaining the similarity measurement values ​​of the time series waveform data of the same measurement channel at different times includes: Initialize the distance matrix and create a matrix of size (N+1)x(M+1), where N and M are the lengths of the two timing waveforms respectively. Set the initial value of the matrix to infinity and the origin of the matrix to 0. Iteratively calculate the distance between the corresponding elements of two time series waveforms and update the distance matrix; The distance matrix is ​​traced back to find a path with the shortest cumulative distance, which is used as the optimal matching path of the two timing waveforms. The shortest distance value is the similarity measurement value of the two timing waveform data.

4. The method according to claim 1, characterized in that: Through the generalized reasoning ability of the large language model, based on the input measurement raw data and measurement parameters, more dimensional parameter information is obtained, and mathematical operations are performed on the measurement raw data of multiple channels to synthesize new waveforms, including: Acquire measurement raw data collected by multiple measurement channels of the measured object and measurement parameters calculated based on the measurement raw data, wherein the measurement raw data is waveform data in the time domain or frequency domain, and the measurement parameters include voltage parameters and time parameters; Inputting the measured raw data and the corresponding measurement parameters into a pre-trained large language model, wherein the large language model is trained based on a large amount of test measurement data and corresponding analysis results, and has the ability to understand, generalize and reason about the test measurement data; Utilizing the generalized reasoning capability of the large language model, extracting the high-dimensional feature information contained in the raw measurement data, and combining the measurement parameters to obtain the deep feature parameters of multiple measurement channels of the measured object under different working conditions; According to the preset mathematical operation rules, the raw data of multiple measurement channels are fused and processed to generate a new synthetic waveform corresponding to the actual working state of the measured object; The novel synthetic waveform sets different mathematical operation rules according to actual application requirements, including linear combination, nonlinear transformation, and time-frequency domain conversion of waveform data of different measurement channels.

5. The method according to claim 1, characterized in that Determining the data content input into the large language model according to the type of question selected by the user, when the type of question is a waveform quality related question, inputting a drawing image and a measurement parameter into the large language model, and when the type of question is a data calculation and analysis related question, inputting measurement raw data and a measurement parameter into the large language model includes: Obtaining the type of question selected by the user, wherein the type of question includes questions related to waveform quality and questions related to data calculation and analysis; Adaptively determining the test measurement data type and content input into the large language model according to the question type selected by the user; When the problem type is a waveform quality-related problem, the waveform drawing image of the measured object and related measurement parameters are input into the large language model, and the measurement parameters include numerical values ​​representing waveform characteristics calculated based on the measurement data; When the problem type is a problem related to data calculation and analysis, the original data obtained by measurement and collection and the relevant measurement parameters are input into the large language model, and the original data is a time series numerical vector.

6. The method according to claim 5, characterized in that The method further comprises: The large language model adaptively calls the corresponding data processing flow and algorithm model according to the input test measurement data type and content; When the input data type is a waveform drawing image, the image recognition algorithm is called to extract features and understand the semantics of the input image, and combined with the measurement parameters, the analysis results related to the waveform quality are output; When the input data type is raw measurement data, the numerical calculation and statistical analysis algorithms are called to process the raw data, and the calculation and analysis results related to the performance indicators of the measured object are output in combination with the measurement parameters; Among them, the large language model adopts a learning paradigm that combines pre-training and fine-tuning. Through pre-training on massive test measurement-related corpus, it has basic knowledge and common sense in the field of test measurement. For different types of test measurement problems, it uses customized data for problem-based fine-tuning to enable it to quickly adapt to specific problems.

7. A large language model-assisted test measurement system, used to implement the method according to any one of claims 1 to 6, characterized in that: include: The first unit is used to collect measurement raw data, drawing images and measurement parameters of the measured circuit through the measurement test equipment, wherein the measurement raw data is multi-dimensional numerical data, the drawing image is generated by drawing according to the measurement raw data, and the measurement parameters include voltage parameters and time parameters calculated based on the measurement raw data, and at least two of the measurement raw data, drawing images and measurement parameters are input into the large language model; The second unit is used to determine the data content to be input into the large language model according to the type of question selected by the user, and when the type of question is a waveform quality-related question, input the drawing image and the measurement parameters into the large language model; when the type of question is a data calculation and analysis-related question, input the measurement raw data and the measurement parameters into the large language model; The third unit is used to obtain waveform change information of the circuit under test during the entire test and measurement process based on the waveform similarity of the same channel at different times recorded in the full cycle through a dynamic time warping algorithm; understand and analyze the input drawing image through the multimodal image recognition capability of the large language model to obtain waveform quality analysis results and circuit noise source analysis results; and / or, through the generalized reasoning capability of the large language model, based on the input measurement raw data and measurement parameters, obtain parameter information of more dimensions, and perform mathematical operations on the measurement raw data of multiple channels to synthesize new waveforms; Generate a test measurement analysis report, which includes waveform quality analysis, circuit noise source analysis, existing problems and solutions, parameter information, and data calculation synthesis results.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images