Measurement value determination method and device of measurement point, equipment and storage medium

Abstract

The invention discloses a method and a device for determining a measurement value of a measurement point location, electronic equipment and a storage medium. The method comprises the steps of obtaining a first point location set, a second point location set and a third point location set of a target product, and obtaining a mapping relation between the second point location set and the third point location set; the second point location set is a subset of the first point location set; the third point location set is a complementary set of the second point location set relative to the first point location set; the mapping relationship comprises a mapping relationship between each measurement point location in the third point location set and at least one measurement point location in the second point location set; and determining the measurement value of each measurement point location in the third point location set according to the measurement value of each measurement point location in the second point location set and the mapping relationship between the second point location set and the third point location set. According to the scheme, the problem of low detection efficiency caused by excessive product measurement point positions is solved, the number of the measurement point positions is simplified based on the incidence relation between the measurement point positions, and the point position measurement efficiency is improved on the basis of ensuring normal completion of the measurement task.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a measurement value determination method and device for measurement points, an electronic device and a storage medium. BACKGROUND

[0002] At present, in the product processing process controlled by digitalization, product point measurement is needed to ensure the consistency of product quality. In order to ensure the reliability of detection, the existing point measurement method usually measures all the points marked in the drawing, but the number of points marked in the drawing is too large, the measurement period is long, and some points are repeatedly tested, resulting in low detection efficiency. SUMMARY

[0003] The present application provides a measurement value determination method and device for measurement points, an electronic device and a storage medium, to solve the problem of low detection efficiency caused by too many product measurement points, and to simplify the number of measurement points based on the correlation between the measurement points, thereby improving the point measurement efficiency while ensuring the normal completion of the measurement task.

[0004] According to an aspect of the present application, a measurement value determination method for measurement points is provided, which comprises:

[0005] Obtaining a first point set, a second point set and a third point set of a target product, and obtaining a mapping relationship between the second point set and the third point set determined in advance; the first point set comprises measurement points associated with the quality detection result of the target product; the second point set is a subset of the first point set determined based on product design drawings, product processing tools and process flow; the third point set is the complement of the second point set relative to the first point set; the mapping relationship between the second point set and the third point set comprises the mapping relationship between each measurement point in the third point set and at least one measurement point in the second point set;

[0006] According to the measurement values of the measurement points in the second point set and the mapping relationship between the second point set and the third point set, the measurement values of the measurement points in the third point set are determined.

[0007] According to another aspect of the present application, a measurement value determination device for measurement points is provided, which comprises:

[0008] The mapping relationship acquisition module is used to acquire a first set of points, a second set of points, and a third set of points for the target product, and to acquire a pre-determined mapping relationship between the second set of points and the third set of points. The first set of points includes measurement points associated with the quality inspection results of the target product. The second set of points is a subset of the first set of points determined based on product design drawings, product processing tools, and process flow. The third set of points is the complement of the second set of points relative to the first set of points. The mapping relationship between the second set of points and the third set of points includes the mapping relationship between each measurement point in the third set of points and at least one measurement point in the second set of points.

[0009] The measurement value determination module is used to determine the measurement values ​​of each measurement point in the third point set based on the measurement values ​​of each measurement point in the second point set and the mapping relationship between the second point set and the third point set.

[0010] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0011] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the measurement value determination method for measurement points according to any embodiment of the present invention.

[0012] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the measurement value determination method for measurement points as described in any embodiment of the present invention.

[0013] The technical solution of this invention involves obtaining a first set of measurement points, a second set of measurement points, and a third set of measurement points for a target product, and obtaining a predetermined mapping relationship between the second set of measurement points and the third set of measurement points. The first set of measurement points includes measurement points associated with the quality inspection results of the target product. The second set of measurement points is a subset of the first set of measurement points determined based on product design drawings, product processing tools, and process flow. The third set of measurement points is the complement of the second set of measurement points relative to the first set of measurement points. The mapping relationship between the second set of measurement points and the third set of measurement points includes the mapping relationship between each measurement point in the third set of measurement points and at least one measurement point in the second set of measurement points. Based on the measurement values ​​of each measurement point in the second set of measurement points and the mapping relationship between the second set of measurement points and the third set of measurement points, the measurement values ​​of each measurement point in the third set of measurement points are determined. This technical solution solves the problem of low detection efficiency caused by too many measurement points for a product. Based on the correlation between measurement points, the number of measurement points is reduced, improving the measurement efficiency of measurement points while ensuring the normal completion of the measurement task.

[0014] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of a method for determining the measurement value of a measurement point according to Embodiment 1 of the present invention;

[0017] Figure 2 This is a flowchart of a method for determining the measurement value of a measurement point according to Embodiment 2 of the present invention;

[0018] Figure 3 This is a schematic diagram of the structure of a measurement point determination device according to Embodiment 3 of the present invention;

[0019] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the measurement value determination method for measurement points according to embodiments of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.

[0022] Example 1

[0023] Figure 1 This document provides a flowchart of a method for determining the measurement values ​​of measurement points according to Embodiment 1 of the present invention. This embodiment is applicable to CNC machining scenarios, particularly for the measurement of product points. The method can be executed by a device for determining the measurement values ​​of measurement points. This device can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0024] S110. Obtain a first set of measurement points, a second set of measurement points, and a third set of measurement points for the target product, and obtain a predetermined mapping relationship between the second set of measurement points and the third set of measurement points; the first set of measurement points includes measurement points associated with the quality inspection results of the target product; the second set of measurement points is a subset of the first set of measurement points determined based on product design drawings, product processing tools, and process flow; the third set of measurement points is the complement of the second set of measurement points relative to the first set of measurement points; the mapping relationship between the second set of measurement points and the third set of measurement points includes the mapping relationship between each measurement point in the third set of measurement points and at least one measurement point in the second set of measurement points.

[0025] This solution can be executed by electronic devices such as computers and servers. The electronic devices can acquire all measurement points required for the quality inspection of the target product and generate a first set of measurement points. The target product can be any product manufactured using CNC machining that requires quality inspection, such as a mobile phone casing or an LCD panel. Measurement points are the locations on the target product where quality inspection is required.

[0026] Electronic devices can generate measurement point selection criteria based on product design drawings, processing tools, and the product's technological process. Based on these criteria, a second set of measurement points is obtained by selecting the points that must be measured from a first set. In a specific example, the processing tool can be a cutting tool, the technological process can be the tool path sequence, and the measurement point selection criteria can include selecting only the first measurement point from the measurement points in the product design drawings that require the same cutting tool to pass through, according to the tool path sequence. By selecting measurement points based on these criteria, the number of points requiring actual measurement can be reduced.

[0027] The electronic device can obtain a second set of measurement points by removing the measurement points contained in the second set of measurement points from the first set of measurement points. Understandably, the union of the second set of measurement points and the third set of measurement points is the first set of measurement points. To reduce the number of measurement points that need to be measured, the measurement points in the third set of measurement points can be represented using one or more measurement points from the second set of measurement points. Therefore, the electronic device can determine the correlation between the measurement points in the second set of measurement points and the measurement points in the third set based on the characteristics of the measurement points. Then, after actually collecting the measurement values ​​of the measurement points in the second set of measurement points, it can estimate the measurement values ​​of the measurement points in the third set based on the correlation between the measurement points in the second set of measurement points and the measurement points in the third set of measurement points.

[0028] Specifically, each measurement point in the third set can be mapped to one or more measurement points in the second set. That is, the measurement value of each measurement point in the third set can be represented by the measurement values ​​of one or more measurement points in the second set. The mapping relationship between the measurement points in the third set and the measurement points in the second set can be linear or non-linear.

[0029] S120. Based on the measured values ​​of each measurement point in the second set of points and the mapping relationship between the second set of points and the third set of points, determine the measured values ​​of each measurement point in the third set of points.

[0030] The electronic device can pre-calculate the actual measurement operations on the target product based on the measurement methods of each measurement point in the second set of points, thereby obtaining the measurement values ​​of each measurement point in the second set of points. For example, the measurement operations could include measuring the external dimensions of the target product, detecting surface defects, and measuring the light reflectance coefficient of the target product. After obtaining the measurement values ​​of each measurement point in the second set of points, the electronic device can determine the measurement values ​​of each measurement point in the third set of points based on the mapping relationship between the measurement points in the third set and the measurement points in the second set, thus obtaining the measurement values ​​of all measurement points in the first set of points.

[0031] The technical solution of this invention involves obtaining a first set of measurement points, a second set of measurement points, and a third set of measurement points for a target product, and obtaining a predetermined mapping relationship between the second set of measurement points and the third set of measurement points. The first set of measurement points includes measurement points associated with the quality inspection results of the target product. The second set of measurement points is a subset of the first set of measurement points determined based on product design drawings, product processing tools, and process flow. The third set of measurement points is the complement of the second set of measurement points relative to the first set of measurement points. The mapping relationship between the second set of measurement points and the third set of measurement points includes the mapping relationship between each measurement point in the third set of measurement points and at least one measurement point in the second set of measurement points. Based on the measurement values ​​of each measurement point in the second set of measurement points and the mapping relationship between the second set of measurement points and the third set of measurement points, the measurement values ​​of each measurement point in the third set of measurement points are determined. This technical solution solves the problem of low detection efficiency caused by too many measurement points for a product. Based on the correlation between measurement points, the number of measurement points is reduced, improving the measurement efficiency of measurement points while ensuring the normal completion of the measurement task.

[0032] Example 2

[0033] Figure 2 This is a flowchart of a method for determining the measurement value of a measurement point according to Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Figure 2 As shown, the method includes:

[0034] S210. Obtain the first set of locations, the second set of locations, and the third set of locations for the target product.

[0035] S220. According to the preset grouping principle, the measurement points in the first set of points are grouped, and the correlation of the measurement points in each group is determined; the grouping principle is that there is at least one measurement point in each group that belongs to the second set of points, and there is at least one measurement point in each group that belongs to the third set of points.

[0036] In this scheme, the electronic device can group the measurement points in the first set of points according to a preset grouping principle, ensuring that each group contains at least one measurement point belonging to the second set of points and at least one measurement point belonging to the third set of points. After obtaining the groups, the electronic device can determine the correlation between the measurement points in each combination. Specifically, the electronic device can acquire the control parameters and product quality parameters of each measurement point at historical time points as characteristic parameters of each measurement point, and determine the correlation of the measurement points in that combination based on the characteristic parameters of the measurement points in each combination. The control parameters can be the CNC (Computerized Numerical Control) machine parameters corresponding to the measurement point, and the product quality parameters can be the IPQC (In-Process Quality Control) data corresponding to the measurement point.

[0037] Optionally, determining the correlation of measurement points in each group includes:

[0038] Obtain the control parameters and product quality parameters associated with each measurement point at historical time points, and use them as characteristic parameters of each measurement point.

[0039] Based on the characteristic parameters of the measurement points in each group, and using a pre-defined correlation evaluation model, the correlation of the measurement points in each group is determined.

[0040] Electronic equipment can acquire control parameters and product quality parameters for each measurement point at multiple historical time points, using these parameters as a set of characteristic parameters for each measurement point. Based on a pre-defined correlation assessment model, the electronic equipment can determine the correlation between the measurement points in each group. The correlation assessment model can include models such as Pearson correlation coefficient, regression analysis, and principal component analysis.

[0041] For combinations of only two measurement points, electronic devices can determine the correlation between them based on correlation coefficient calculation formulas such as Pearson and Spearman. For combinations of more than two measurement points, electronic devices can determine the correlation between the measurement points in the combination based on methods such as multiple linear regression and principal component analysis.

[0042] This scheme can pre-determine the correlation between the measurement points in the third set and the measurement points in the second set, and propose uncorrelated measurement point combinations. This is beneficial for screening out measurement point combinations with strong correlation, thereby ensuring the reliability of the measurement point prediction in the third set.

[0043] S230. Based on the correlation of measurement points in each group, determine the target group set and determine the measurement point mapping relationship of each target group in the target group set; the target group is a group in which there is a correlation between measurement points; the measurement point mapping relationship is the mapping relationship between the first point and the second point, where the first point is a measurement point belonging to the second point set and the second point is a measurement point belonging to the third point set.

[0044] Electronic devices can filter out groups of measurement points that are correlated with each other based on the correlation among the measurement points in each group, forming a target group set. Each target group includes at least one first point and at least one second point. The first point is a measurement point belonging to the second point set, and the second point is a measurement point belonging to the third point set. Electronic devices can determine the mapping relationship between the first and second points in each target group based on the measurement values ​​of each measurement point at historical time points.

[0045] In a feasible solution, determining the mapping relationship of measurement points for each target group in the target group set includes:

[0046] Obtain the measurement values ​​of each measurement point at historical time points;

[0047] The measurement value of the first point in the target group at a historical time point is used as input data, and the measurement value of the second point in the target group at a historical time point is used as label. Based on the target group matching prediction algorithm, a target group matching measurement value prediction model is trained. The target group matching measurement value prediction model is used to characterize the mapping relationship between the first point and the second point in the target group.

[0048] Electronic devices can acquire measurement values ​​of various measurement points at multiple historical time points. For each target group, a measurement value prediction model is trained using the measurement values ​​of each measurement point in that target group at historical time points. This model represents the mapping relationship between the first and second measurement points in the target group. Understandably, the measurement values ​​of the first measurement point in the target group at historical time points can be used as input data, and the measurement values ​​of the second measurement point at historical time points can be used as labels to train a measurement value prediction model matching the target group. Specifically, the electronic device can pre-select a prediction algorithm suitable for the target group based on the number of measurement points in the target group and the ratio of the first to the second measurement points. The prediction algorithm can be a regression algorithm such as a decision tree or random forest, or a deep learning algorithm such as a neural network.

[0049] For example, if the target group matching prediction algorithm is a random forest, the electronic device can pre-acquire measurement values ​​of each measurement point in the target group at multiple historical time points. The first and second measurement values ​​at the same historical time point are used as a training sample, resulting in multiple training samples. The electronic device can then divide each training sample into a predetermined number of data subsets, the predetermined number being divisible by the total number of training samples. The electronic device can then sequentially use each data subset as a validation subset, and other datasets outside the validation subset as training data subsets, resulting in a predetermined number of datasets. The electronic device can pre-set model parameters such as the parameters of individual decision trees, the configuration parameters of the entire random forest, training parameters, and tuning parameters. Based on the pre-set model parameters and each dataset, the pre-built random forest model is trained to obtain the target group matching measurement value prediction model. The electronic device can use the training data subsets from each dataset to train the random forest model, and use the validation data subsets from each dataset to validate the training results for this dataset, outputting the corresponding evaluation metric for this dataset. The evaluation metrics may include Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R²). The electronic device can average the evaluation metrics across the validation subsets of each dataset to obtain the model evaluation result for the random forest model. If the model evaluation result meets preset requirements, the electronic device can use the trained random forest model as a measurement prediction model for target group matching, specifically for predicting the measurement value of the second point in the target group.

[0050] For example, if the prediction algorithm for target group matching is a neural network, the electronic device can pre-acquire measurement values ​​of each measurement point in the target group at multiple historical time points. The measurement values ​​of the first and second points at the same historical time point are used as a set of training samples, resulting in multiple sets of training samples. The measurement values ​​of the first point in each set of training samples are input into the neural network. The training loss rate is calculated based on the comparison between the output of the neural network and the measurement value of the second point. The weights in the neural network are updated at least once based on the training loss rate until the evaluation metric of the neural network meets preset conditions. The neural network of the last iteration is used as the measurement value prediction model for target group matching, for predicting the measurement value of the second point in the target group. The evaluation metrics of the neural network can include test loss rate, test accuracy, etc.

[0051] In another feasible solution, determining the mapping relationship of measurement points for each target group in the target group set includes:

[0052] Obtain the measurement values ​​of each measurement point at historical time points and a pre-set set of prediction algorithms; the set of prediction algorithms includes at least two prediction algorithms;

[0053] The measurement value of the first point in the target group at a historical time point is used as input data, and the measurement value of the second point in the target group at a historical time point is used as label. Based on each prediction algorithm in the prediction algorithm set, prediction models for each candidate measurement value are trained in turn. Each candidate measurement value prediction model is matched with a prediction algorithm.

[0054] The evaluation index of each candidate measurement prediction model is determined. Based on the evaluation index of each candidate measurement prediction model, the target measurement prediction model is selected from the candidate measurement prediction models as the target group matching measurement prediction model. The target group matching measurement prediction model is used to characterize the mapping relationship between the first point and the second point in the target group.

[0055] To better characterize the mapping relationship between the first and second points in the target group, the electronic device can pre-set a set of prediction algorithms. Each prediction algorithm in the set can be trained to obtain a measurement prediction model, which is used to predict the measurement value of the second point in the target group. The electronic device can use the measurement value of the first point in the target group at a historical time point as input data, and the measurement value of the second point in the target group at a historical time point as a label. Based on each prediction algorithm in the set, the electronic device trains the corresponding candidate measurement prediction model for each prediction algorithm. The electronic device can unify the evaluation index of each candidate measurement prediction model, and select the target measurement prediction model with the smallest measurement prediction error from among the candidate measurement prediction models as the measurement prediction model for target group matching.

[0056] This approach selects the most suitable prediction algorithm from the set of prediction algorithms for the target group and trains it to obtain a measurement prediction model that best matches the target group, thereby achieving accurate prediction of the second point in the target group.

[0057] Based on the above scheme, the evaluation indicators include positive evaluation indicators and negative evaluation indicators;

[0058] The step of determining the target measurement prediction model as the measurement prediction model for target group matching from among the candidate measurement prediction models based on the evaluation indicators of each candidate measurement prediction model includes:

[0059] The evaluation indicators of each candidate measurement prediction model are standardized and unified into evaluation indicators of the same direction.

[0060] The evaluation results of each candidate measurement prediction model are calculated based on the evaluation indicators and weight coefficients of each evaluation indicator.

[0061] Based on the evaluation results of each candidate measurement prediction model, the target measurement prediction model is selected from among the candidate measurement prediction models as the measurement prediction model for target group matching.

[0062] Understandably, evaluation metrics can include positive metrics, where a higher value is better, such as the coefficient of determination. Evaluation metrics can also include negative metrics, where a lower value is better, such as mean absolute error, mean square error, and root mean square error. If multiple evaluation metrics exist, including both positive and negative metrics, electronic design can standardize the evaluation metrics of each candidate quantity prediction model, unifying them into metrics of the same direction. For example, the standardized formula for a negative evaluation metric can be expressed as: The standardized formula for positive evaluation indicators can be expressed as: ;in, This indicates the standardized values ​​of the evaluation indicators. This indicates the values ​​of the evaluation indicators before standardization. This represents the minimum value of the evaluation index in each candidate measurement prediction model. This represents the maximum value of the evaluation index in each candidate measurement prediction model.

[0063] For each candidate measurement prediction model, the electronic device can calculate the weighted sum of the evaluation indicators and their weighting coefficients as the evaluation result of the candidate measurement prediction model. For example, the evaluation result of the candidate measurement prediction model can be expressed as follows: ,in, Each represents an evaluation indicator. These represent the weight coefficients of each evaluation indicator. The electronic device can compare the evaluation results of each candidate measurement prediction model and determine the target measurement prediction model with the best evaluation result from among the candidate measurement prediction models as the measurement prediction model for target group matching.

[0064] This scheme can standardize evaluation indicators of different directions when there are multiple evaluation indicators, so as to ensure the consistency of evaluation standards of each candidate measurement prediction model and the reliability of the evaluation results of each candidate measurement prediction model.

[0065] S240. Input the measurement values ​​of the first point in each target group into the measurement value prediction model matched by each target group to obtain the measurement values ​​of the second point in each target group.

[0066] After obtaining the measurement prediction model matching each target group, for each target group, the electronic device can input the measurement value of the first point in the target group into the measurement prediction model matching the target group to obtain the measurement value of the second point in the target group.

[0067] In the quality inspection process of the target product, this solution only requires measuring the measurement points in the second set of points, eliminating the need to measure the measurement points in the third set of points. This greatly reduces the number of points that need to be actually measured and improves the efficiency of point measurement.

[0068] Example 3

[0069] Figure 3 This is a schematic diagram of a device for determining the measurement value of a measurement point according to Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0070] The mapping relationship acquisition module 310 is used to acquire a first set of points, a second set of points, and a third set of points for the target product, and to acquire a predetermined mapping relationship between the second set of points and the third set of points; the first set of points includes measurement points associated with the quality inspection results of the target product; the second set of points is a subset of the first set of points determined based on product design drawings, product processing tools, and process flow; the third set of points is the complement of the second set of points relative to the first set of points; the mapping relationship between the second set of points and the third set of points includes the mapping relationship between each measurement point in the third set of points and at least one measurement point in the second set of points.

[0071] The measurement value determination module 320 is used to determine the measurement values ​​of each measurement point in the third point set based on the measurement values ​​of each measurement point in the second point set and the mapping relationship between the second point set and the third point set.

[0072] Optionally, the mapping relationship between the second set of points and the third set of points includes at least one set of measurement point mapping relationships;

[0073] The device further includes a mapping relationship determination module, comprising:

[0074] The correlation determination unit is used to group the measurement points in the first set of points according to a preset grouping principle, and determine the correlation of the measurement points in each group; the grouping principle is that there is at least one measurement point in each group that belongs to the second set of points, and at least one measurement point in each group that belongs to the third set of points.

[0075] The mapping relationship determination unit is used to determine the target group set based on the correlation of measurement points in each group, and to determine the mapping relationship of measurement points in each target group in the target group set; the target group is a group in which measurement points are correlated; the measurement point mapping relationship is the mapping relationship between a first point and a second point, where the first point is a measurement point belonging to the second point set, and the second point is a measurement point belonging to the third point set.

[0076] Based on the above scheme, the correlation determination unit is specifically used for:

[0077] Obtain the control parameters and product quality parameters associated with each measurement point at historical time points, and use them as characteristic parameters of each measurement point.

[0078] Based on the characteristic parameters of the measurement points in each group, and using a pre-defined correlation evaluation model, the correlation of the measurement points in each group is determined.

[0079] In one feasible solution, the mapping relationship determination unit is used for:

[0080] Obtain the measurement values ​​of each measurement point at historical time points;

[0081] The measurement value of the first point in the target group at a historical time point is used as input data, and the measurement value of the second point in the target group at a historical time point is used as label. Based on the target group matching prediction algorithm, a target group matching measurement value prediction model is trained. The target group matching measurement value prediction model is used to characterize the mapping relationship between the first point and the second point in the target group.

[0082] In another feasible embodiment, the mapping relationship determination unit is further configured to:

[0083] Obtain the measurement values ​​of each measurement point at historical time points and a pre-set set of prediction algorithms; the set of prediction algorithms includes at least two prediction algorithms;

[0084] The measurement value of the first point in the target group at a historical time point is used as input data, and the measurement value of the second point in the target group at a historical time point is used as label. Based on each prediction algorithm in the prediction algorithm set, prediction models for each candidate measurement value are trained in turn. Each candidate measurement value prediction model is matched with a prediction algorithm.

[0085] The evaluation index of each candidate measurement prediction model is determined. Based on the evaluation index of each candidate measurement prediction model, the target measurement prediction model is selected from the candidate measurement prediction models as the target group matching measurement prediction model. The target group matching measurement prediction model is used to characterize the mapping relationship between the first point and the second point in the target group.

[0086] Based on the aforementioned scheme, the evaluation indicators include positive evaluation indicators and negative evaluation indicators;

[0087] The mapping relationship determination unit is specifically used for:

[0088] The evaluation indicators of each candidate measurement prediction model are standardized and unified into evaluation indicators of the same direction.

[0089] The evaluation results of each candidate measurement prediction model are calculated based on the evaluation indicators and weight coefficients of each evaluation indicator.

[0090] Based on the evaluation results of each candidate measurement prediction model, the target measurement prediction model is selected from among the candidate measurement prediction models as the measurement prediction model for target group matching.

[0091] In this embodiment, the measurement value determination module 320 is specifically used for:

[0092] The measurement values ​​of the first point in each target group are input into the measurement value prediction model matched for each target group to obtain the measurement values ​​of the second point in each target group.

[0093] The measurement point determination device provided in the embodiments of the present invention can execute the measurement point determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0094] Example 4

[0095] Figure 4 A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0096] like Figure 4As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0097] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0098] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as the method for determining the measurement value of a measurement point.

[0099] In some embodiments, the method for determining the measurement value of a measurement point can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the method for determining the measurement value of a measurement point described above can be performed. Alternatively, in other embodiments, processor 411 can be configured to perform the method for determining the measurement value of a measurement point by any other suitable means (e.g., by means of firmware).

[0100] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0101] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable measurement point determination device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0102] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0103] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0104] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0105] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0106] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0107] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining the measured value of a measurement point, characterized in that, The method includes: Obtain a first set of measurement points, a second set of measurement points, and a third set of measurement points for the target product, and obtain a pre-determined mapping relationship between the second set of measurement points and the third set of measurement points; the first set of measurement points includes measurement points associated with the quality inspection results of the target product; the second set of measurement points is a subset of the first set of measurement points determined based on product design drawings, product processing tools, and process flow; the third set of measurement points is the complement of the second set of measurement points relative to the first set of measurement points; the mapping relationship between the second set of measurement points and the third set of measurement points includes the mapping relationship between each measurement point in the third set of measurement points and at least one measurement point in the second set of measurement points. Based on the measured values ​​of each measurement point in the second set of points and the mapping relationship between the second set of points and the third set of points, determine the measured values ​​of each measurement point in the third set of points.

2. The method according to claim 1, characterized in that, The mapping relationship between the second set of points and the third set of points includes at least one set of measurement point mapping relationships; The process of determining the mapping relationship between the second set of points and the third set of points is as follows: According to the preset grouping principle, the measurement points in the first set of points are grouped, and the correlation between the measurement points in each group is determined. The grouping principle is that each group has at least one measurement point belonging to the second set of points and at least one measurement point belonging to the third set of points; Based on the correlation of measurement points in each group, a target group set is determined, and the mapping relationship of measurement points in each target group in the target group set is determined; the target group is a group in which there is a correlation between measurement points; the mapping relationship of measurement points is the mapping relationship between a first point and a second point, where the first point is a measurement point belonging to the second point set, and the second point is a measurement point belonging to the third point set.

3. The method according to claim 2, characterized in that, Determining the correlation of measurement points in each group includes: Obtain the control parameters and product quality parameters associated with each measurement point at historical time points, and use them as characteristic parameters of each measurement point. Based on the characteristic parameters of the measurement points in each group, and using a pre-defined correlation evaluation model, the correlation of the measurement points in each group is determined.

4. The method according to claim 2, characterized in that, The determination of the measurement point mapping relationship of each target group in the target group set includes: Obtain the measurement values ​​of each measurement point at historical time points; The measurement value of the first point in the target group at a historical time point is used as input data, and the measurement value of the second point in the target group at a historical time point is used as label. Based on the target group matching prediction algorithm, a target group matching measurement value prediction model is trained. The target group matching measurement value prediction model is used to characterize the mapping relationship between the first point and the second point in the target group.

5. The method according to claim 2, characterized in that, The determination of the measurement point mapping relationship of each target group in the target group set includes: Obtain the measurement values ​​of each measurement point at historical time points and a pre-set set of prediction algorithms; the set of prediction algorithms includes at least two prediction algorithms; The measurement value of the first point in the target group at a historical time point is used as input data, and the measurement value of the second point in the target group at a historical time point is used as label. Based on each prediction algorithm in the prediction algorithm set, prediction models for each candidate measurement value are trained in turn. Each candidate measurement value prediction model is matched with a prediction algorithm. The evaluation index of each candidate measurement prediction model is determined. Based on the evaluation index of each candidate measurement prediction model, the target measurement prediction model is selected from the candidate measurement prediction models as the target group matching measurement prediction model. The target group matching measurement prediction model is used to characterize the mapping relationship between the first point and the second point in the target group.

6. The method according to claim 5, characterized in that, The evaluation indicators include positive evaluation indicators and negative evaluation indicators; The step of determining the target measurement prediction model as the measurement prediction model for target group matching from among the candidate measurement prediction models based on the evaluation indicators of each candidate measurement prediction model includes: The evaluation indicators of each candidate measurement prediction model are standardized and unified into evaluation indicators of the same direction. The evaluation results of each candidate measurement prediction model are calculated based on the evaluation indicators and weight coefficients of each evaluation indicator. Based on the evaluation results of each candidate measurement prediction model, the target measurement prediction model is selected from among the candidate measurement prediction models as the measurement prediction model for target group matching.

7. The method according to claim 4 or 5, characterized in that, The step of determining the measurement values ​​of each measurement point in the third point set based on the measurement values ​​of each measurement point in the second point set and the mapping relationship between the second point set and the third point set includes: The measurement values ​​of the first point in each target group are input into the measurement value prediction model matched for each target group to obtain the measurement values ​​of the second point in each target group.

8. A device for determining the measurement value of a measurement point, characterized in that, The device includes: The mapping relationship acquisition module is used to acquire a first set of points, a second set of points, and a third set of points for the target product, and to acquire a pre-determined mapping relationship between the second set of points and the third set of points. The first set of points includes measurement points associated with the quality inspection results of the target product. The second set of points is a subset of the first set of points determined based on product design drawings, product processing tools, and process flow. The third set of points is the complement of the second set of points relative to the first set of points. The mapping relationship between the second set of points and the third set of points includes the mapping relationship between each measurement point in the third set of points and at least one measurement point in the second set of points. The measurement value determination module is used to determine the measurement values ​​of each measurement point in the third point set based on the measurement values ​​of each measurement point in the second point set and the mapping relationship between the second point set and the third point set.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the measurement value determination method for measurement points according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining the measurement value of the measurement point as described in any one of claims 1-7.

Images