Influence judgment method, system and equipment for auxiliary material parameters and storage medium

Abstract

The invention discloses an auxiliary material parameter influence judgment method, system and device and a storage medium, and relates to the technical field of semiconductor analysis. The method comprises the steps that target auxiliary material parameters and cutting results corresponding to the target auxiliary material parameters are obtained, wherein the target auxiliary material parameters are used for representing historical parameter values of target auxiliary materials; dividing the value range of the target auxiliary material parameter into a plurality of first intervals; according to the distribution condition of the cutting result of each first interval, combining the adjacent first intervals to obtain a plurality of second intervals; according to the central value of the target auxiliary material parameter in each second interval and the median value of the cutting result, an influence curve of the target auxiliary material parameter on the cutting result is determined, and the influence curve is used for judging the influence of the target auxiliary material parameter on the cutting result. According to the method, dynamic binning and noise suppression are carried out on the data, the stage influence curve of the auxiliary material parameters on the cutting result can be accurately described, and the judgment accuracy of the stage influence of the auxiliary material parameters on the cutting result is improved.

Description

Technical Field

[0001] This application relates to the field of semiconductor analysis technology, and particularly relates to a method, system, device and storage medium for determining the influence of auxiliary material parameters. Background Art

[0002] In the silicon wafer cutting process, auxiliary material parameters such as cutting fluid have a significant impact on the final cutting result. Usually, this impact shows a convex function or concave function trend and exhibits a "phased" impact characteristic, that is, the change of parameters within the interval has a small impact on the result, but obvious changes may occur when crossing the interval. Therefore, it is necessary to study and extract the phased impact curve of these parameters on the cutting result. However, due to the interference of environmental noise and the large error of existing data collectors, this phased law may be masked, making it difficult to accurately define the phased impact of auxiliary material parameters on the cutting result. Summary of the Invention

[0003] Embodiments of this application provide a method, system, device and storage medium for determining the influence of auxiliary material parameters to improve the accuracy of determining the phased influence of auxiliary material parameters on the cutting result.

[0004] To solve the above technical problems, embodiments of this application disclose the following technical solutions: In a first aspect, a method for determining the influence of auxiliary material parameters is provided, including: obtaining a target auxiliary material parameter and a cutting result corresponding to the target auxiliary material parameter, where the target auxiliary material parameter is used to represent the historical parameter value of the target auxiliary material; Dividing the value range of the target auxiliary material parameter into multiple first intervals; According to the distribution of the cutting results located in each of the first intervals, merging adjacent first intervals to obtain multiple second intervals; According to the central value of the target auxiliary material parameter and the median value of the cutting result located in each of the second intervals, determining an influence curve of the target auxiliary material parameter on the cutting result, where the influence curve is used to determine the influence of the target auxiliary material parameter on the cutting result.

[0005] In some embodiments, the method for obtaining multiple second intervals includes: Determining the similarity between adjacent first intervals according to the distribution of the cutting results located in each of the first intervals; Starting from the first first interval, successively merging adjacent first intervals with a similarity less than a similarity threshold to obtain multiple second intervals.

[0006] In some embodiments, the successively merging adjacent first intervals with a similarity less than a similarity threshold to obtain multiple second intervals includes: If the similarity between the first interval and the adjacent first interval is less than the similarity threshold, merge the first interval and the adjacent first interval into a new first interval, and repeat the operation of comparing the similarity between the new first interval and the adjacent first interval with the similarity threshold until the similarity between the new first interval and the adjacent first interval is greater than or equal to the similarity threshold. Then, determine the new first interval as the second interval, and continue to determine the comparison result between the similarity of the adjacent first interval and the next adjacent first interval and the similarity threshold.

[0007] In some embodiments, the method for determining the distribution of the cutting results in each of the first intervals includes: Determine the normal proportion and the abnormal proportion of the cutting results in each of the first intervals; According to the normal proportion and the abnormal proportion, determine the distribution of the cutting results in the corresponding first interval.

[0008] In some embodiments, the method for determining the normal proportion and the abnormal proportion of the cutting results in each of the first intervals includes: Perform binary classification processing on the cutting results corresponding to the target auxiliary material parameters according to a preset target yield threshold to obtain a binary classification result; According to the binary classification result and the total number of the cutting results in the first interval, determine the normal proportion and the abnormal proportion of the cutting results in the first interval.

[0009] In some embodiments, dividing the value range of the target auxiliary material parameter into multiple first intervals includes: Divide the value range of the target auxiliary material parameter into multiple first intervals according to the equal-width rule.

[0010] In some embodiments, the median value of the cutting results includes the median or the average value of the cutting results.

[0011] In a second aspect, an influence determination system for auxiliary material parameters is provided, including: An acquisition module, configured to acquire a target auxiliary material parameter and the cutting results corresponding to the target auxiliary material parameter, where the target auxiliary material parameter is used to characterize the historical parameter value of the target auxiliary material; An interval division module, configured to divide the value range of the target auxiliary material parameter into multiple first intervals; An interval merging module, configured to merge adjacent first intervals according to the distribution of the cutting results in each of the first intervals to obtain multiple second intervals; An influence curve determination module, configured to determine an influence curve of the target auxiliary material parameter on the cutting result according to the central value of the target auxiliary material parameter located in each of the second intervals and the median value of the cutting result, where the influence curve is used to determine the influence of the target auxiliary material parameter on the cutting result.

[0012] In a third aspect, an electronic device is provided, including a processor and a memory; a computer program is stored in the memory, and the processor is configured to execute the computer program stored in the memory to implement the method for determining the influence of the auxiliary material parameter as described in any one of the first aspects.

[0013] In a fourth aspect, a computer-readable storage medium is provided, storing computer instructions, where the computer instructions are used to cause a processor to implement the method for determining the influence of the auxiliary material parameter as described in any one of the first aspects when executed.

[0014] One of the above technical solutions has the following advantages or beneficial effects: Compared with the prior art, a method for determining the influence of an auxiliary material parameter in this application includes: obtaining a target auxiliary material parameter and a cutting result corresponding to the target auxiliary material parameter, where the target auxiliary material parameter is used to represent the historical parameter value of the target auxiliary material; dividing the value range of the target auxiliary material parameter into multiple first intervals; merging adjacent first intervals according to the distribution of the cutting results located in each first interval to obtain multiple second intervals; determining an influence curve of the target auxiliary material parameter on the cutting result according to the central value of the target auxiliary material parameter located in each second interval and the median value of the cutting result, where the influence curve is used to determine the influence of the target auxiliary material parameter on the cutting result. The method for determining the influence of the auxiliary material parameter provided in this application realizes dynamic binning and noise suppression of data by dividing the value range of the target auxiliary material parameter into intervals and merging the divided intervals according to the distribution of the cutting results in the divided intervals, and accurately depicts the stage influence curve of the auxiliary material parameter on the cutting result according to the central value of the target auxiliary material parameter and the median value of the cutting result in the merged intervals, thereby improving the determination accuracy of the stage influence of the auxiliary material parameter on the cutting result, and further facilitating the precise optimization of the auxiliary material ratio and the optimization control of the cutting yield, reducing the auxiliary material usage cost, and improving the stability of the cutting process.

[0015] An influence determination system for auxiliary material parameters of the present application divides the value range of target auxiliary material parameters into intervals and merges the divided intervals according to the distribution of the cutting results of the divided intervals, so as to dynamically bin the data and suppress noise, and accurately depict the stage influence curve of the auxiliary material parameters on the cutting results according to the central value of the target auxiliary material parameters in the merged interval and the median value of the cutting results, thereby improving the determination accuracy of the stage influence of the auxiliary material parameters on the cutting results, further facilitating the precise optimization of the auxiliary material ratio and the optimization control of the cutting yield, reducing the use cost of the auxiliary materials, and improving the stability of the cutting process. Brief Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 is a flowchart of an influence determination method for auxiliary material parameters provided in an embodiment of the present application; Figure 2 is a schematic diagram of the fitting result of the influence of the cutting fluid turbidity on the jumper and the broken seam provided in an embodiment of the present application; Figure 3 is a schematic diagram of the structure of the influence determination system for auxiliary material parameters of an embodiment of the present application; Figure 4 is a schematic diagram of the structure of an electronic device of an embodiment of the present application; Reference Signs: 100 - Influence determination system for auxiliary material parameters; 101 - Acquisition module; 102 - Interval division module; 103 - Interval merging module; 104 - Influence curve determination module; 501 - Memory; 502 - Processor. Detailed Description of the Embodiments

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present application.

[0019] In the description of the present application, it should be understood that the orientation or positional relationships indicated by the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings. These are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present application. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more features. In the description of the present application, "a plurality of" means two or more, and at least one means one, two or more, unless otherwise specifically defined.

[0020] Figure 1 is a flowchart of a method for determining the influence of auxiliary material parameters provided in an embodiment of the present application. This method is applicable to the situation of improving the determination accuracy of the phased influence of auxiliary material parameters on the cutting result in a semiconductor silicon wafer analysis system. This method can be executed by a system for determining the influence of auxiliary material parameters, which can be implemented in the form of software and / or hardware, and this system can be configured in the processor of a semiconductor analysis system. Please refer to Figure 1 , and the method includes the following steps: Step 110: Obtain the target auxiliary material parameters and the cutting result corresponding to the target auxiliary material parameters, where the target auxiliary material parameters are used to represent the historical parameter values of the target auxiliary material.

[0021] Among them, the target auxiliary material parameters refer to the parameters of various cutting auxiliary materials in the silicon wafer cutting process, such as the conductivity, pH value, concentration, turbidity, temperature, chemical oxygen demand (COD), surface tension, single-knife liquid supply amount, etc. of auxiliary materials such as cutting fluid. Specifically, it can be set according to the actual situation and will not be specifically limited here.

[0022] Since the performance of the cutting auxiliary materials will directly affect the cutting quality, the setting of the auxiliary material parameters directly affects the quality of the cutting result, such as normal cutting or abnormal cutting. Thus, the cutting result corresponding to the target auxiliary material parameters refers to the cutting result obtained by performing cutting according to the cutting process set with the target auxiliary material parameters. The cutting result corresponding to the target auxiliary material parameters can directly reflect the influence of the setting of the target auxiliary material parameters on the cutting quality. For example, assume that the target auxiliary material parameter is the concentration of the cutting fluid, and the concentration of the cutting fluid is set to M, then the corresponding cutting result will be obtained when cutting according to the cutting fluid concentration of M.

[0023] Among them, the target auxiliary material parameters are used to characterize the historical parameter values of the target auxiliary material. Correspondingly, the cutting results corresponding to the target auxiliary material parameters are used to characterize the cutting results corresponding to the respective historical parameter values of the target auxiliary material. The historical parameter values of the target auxiliary material refer to the target auxiliary material parameter values obtained by cutting according to the set target auxiliary material parameters within a historical time period (such as the past month, quarter, etc., which can be specifically set according to the actual situation). For example, taking the turbidity of the cutting fluid as the auxiliary material parameter, the historical parameter value of the turbidity of the cutting fluid refers to the turbidity of the cutting fluid corresponding to each set turbidity of the cutting fluid within a historical time period (such as within the past quarter). For example, within the past quarter, the turbidity of the cutting fluid is set to X1, X2, X3, … Xn, and the cutting processes are carried out respectively. Correspondingly, the cutting results corresponding to the turbidity of the cutting fluid being X1, X2, X3, … Xn will be obtained. Among them, X1, X2, X3, … Xn are the historical parameter values of the turbidity of the cutting fluid within the past quarter.

[0024] Step 120: Divide the value range of the target auxiliary material parameters into multiple first intervals.

[0025] Among them, the value range of the target auxiliary material parameters is generally set according to the actual business requirements. Exemplarily, taking a certain project as an example, the value ranges of each auxiliary material parameter are respectively: stock solution addition ratio: (0, 1); replacement ratio: (0.02, 0.12); ionic liquid addition ratio: (0.0, 0.15); citric acid: (0.0, 0.2); small ingredient GB: (0.0, 0.2); small ingredient HT: (0.0, 0.2); small ingredient AC: (0.0, 0.2); small ingredient small P: (0.0, 0.2); small ingredient small D: (0.0, 0.2); small ingredient P4: (0.0, 0.2); small ingredient small T: (0.0, 0.2); small ingredient triethanolamine: (0.0, 0.2); single - blade liquid supply volume: (1.0, 10.0).

[0026] Specifically, divide the value range of the target auxiliary material parameters to obtain multiple first intervals to achieve adaptive binning of the target auxiliary material parameters, reduce or eliminate noise interference, and facilitate accurately depicting the phased influence of the target auxiliary material parameters on the cutting results. For example, divide the value range X1, X2, X3, … Xn of the turbidity of the cutting fluid within the past quarter to obtain multiple first intervals. Among them, the specific number of intervals for the first interval can be set according to the actual situation and will not be specifically limited here.

[0027] In some embodiments, dividing the value range of the target auxiliary material parameters into multiple first intervals includes: dividing the value range of the target auxiliary material parameters into multiple first intervals according to the equal - width rule.

[0028] Specifically, the value range of the target auxiliary material parameter is divided into multiple first intervals according to the equal-width rule, so as to realize the adaptive binning of the target auxiliary material parameter, reduce or eliminate noise interference, and facilitate the subsequent accurate characterization of the stage influence of the target auxiliary material parameter on the cutting result. Among them, the number of interval divisions and the interval division width for dividing the value range of the target auxiliary material parameter according to the equal-width rule can be set according to the actual situation, and no specific limitation is made here.

[0029] Exemplarily, the specific process of dividing the value range of the target auxiliary material parameter is as follows: Taking the target auxiliary material parameter X as an example, the value range of the target auxiliary material parameter X is divided into N first intervals according to the equal-width rule: ; Among them, and are the interval endpoints of the th interval; N is a positive integer. Exemplarily, N is 100, and the value of N can be set according to the actual situation, and no specific limitation is made here.

[0030] Among them, the interval division width is: ; Among them, is the interval division width; is the maximum value of the value range of the target auxiliary material parameter X; is the minimum value of the value range of the target auxiliary material parameter X.

[0031] Exemplarily, if the value range of the target auxiliary material parameter X is [0, 1] and N is 100, the first first interval is [0, 0.01).

[0032] Step 130: According to the distribution of the cutting results in each first interval, merge adjacent first intervals to obtain multiple second intervals.

[0033] Since the target auxiliary material parameter is used to represent the historical parameter values of the target auxiliary material, correspondingly, the cutting results corresponding to the target auxiliary material parameter are used to represent the cutting results corresponding to the respective historical parameter values of the target auxiliary material. Therefore, each value of the target auxiliary material parameter corresponds to a corresponding cutting result. Similarly, each value within each of the first intervals obtained by dividing the value range of the target auxiliary material parameter also corresponds to a corresponding cutting result. Thus, after obtaining multiple first intervals, according to the distribution of the cutting results within each first interval, merging adjacent first intervals is beneficial to reducing or eliminating the influence of data acquisition errors and noise interference on the determination of the influence of the auxiliary material parameter, thereby being beneficial to improving the determination accuracy of the stage influence of the auxiliary material parameter on the cutting result.

[0034] In some embodiments, the method for obtaining multiple second intervals includes the following steps: Step 1: Determine the similarity between adjacent first intervals according to the distribution of cutting results in each first interval.

[0035] Specifically, after dividing into multiple first intervals, determining the similarity between adjacent first intervals according to the distribution of cutting results within each first interval is conducive to subsequent dynamic merging of adjacent first intervals, thereby facilitating reducing or eliminating the influence of data acquisition errors and noise interference on the determination of auxiliary material parameters, and further facilitating improving the determination accuracy of the phased influence of auxiliary material parameters on cutting results.

[0036] In some embodiments, the method for determining the distribution of cutting results in each first interval includes: determining the normal proportion and abnormal proportion of cutting results in each first interval; and determining the distribution of cutting results in the corresponding first interval according to the normal proportion and abnormal proportion.

[0037] Among them, the cutting results include normal cutting and abnormal cutting. Correspondingly, the distribution of cutting results is related to the normal proportion and abnormal proportion of cutting results. Therefore, determining the normal proportion and abnormal proportion of cutting results in each first interval can further determine the distribution of cutting results in each first interval.

[0038] In some embodiments, the method for determining the normal proportion and abnormal proportion of cutting results in each first interval includes: performing binary classification processing on the cutting results corresponding to the target auxiliary material parameters according to a preset target yield threshold to obtain a binary classification processing result; and determining the normal proportion and abnormal proportion of cutting results in the first interval according to the binary classification processing result and the total number of cutting results in the first interval.

[0039] Specifically, converting the cutting results corresponding to the target auxiliary material parameters into a binary classification problem, that is, performing binary classification processing on the cutting results corresponding to the target auxiliary material parameters according to a preset target yield threshold to obtain a binary classification processing result. For example, converting the cutting result abnormal rate into a binary classification problem: ; Among them, is the preset target yield threshold. Exemplarily, is 0.0034. In addition it can also be other values, which can be specifically set according to the actual situation and are not specifically limited here.

[0040] It should be noted that the cutting yield of this application can be represented by various different indicators. For example, the unqualified rate of Total Thickness Variation (TTV), the unqualified rate of wire marks, etc. Exemplarily, taking the TTV unqualified rate as an example, TTV is used to represent the difference between the maximum thickness and the minimum thickness of a silicon wafer, and is an important indicator for measuring the thickness uniformity of the silicon wafer. In the semiconductor manufacturing process, the thickness of the silicon wafer must be very uniform across the entire surface. Approximately four or five thousand silicon wafers can be cut in one pass. The inspection opportunity detects the silicon wafers with unqualified TTV. The number of qualified TTV wafers / the total number of wafers can be defined as the TTV qualification rate. If the TTV unqualified rate of this pass is greater than 0.34%, it is marked as 1, and if it is less, it is marked as 0.

[0041] Specifically, according to the binary classification processing result and the total number of cutting results within the first interval, the specific implementation methods for determining the normal proportion and abnormal proportion of the cutting results located in the first interval include: for each first interval , calculate the normal proportion (i.e., the proportion of category 0) within each first interval and the abnormal proportion (i.e., the proportion of category 1) , specifically as follows: ; ; Among them, is an exponential function, representing the value of the abnormal rate y of the target variable cutting result.

[0042] Exemplarily, taking the cutting fluid turbidity as an example, assume that the value range of the cutting fluid turbidity is [0, 1]. Suppose 100 passes are cut using the cutting fluid within this turbidity range. Among them, there are 30 passes with a TTV qualification rate higher than 0.34%, and 70 passes with a TTV qualification rate lower than 0.34%. Then the abnormal proportion of the cutting results is 30%, that is, Pi(1) = 30%, and the normal proportion is 70%, that is, Pi(0) = 70%.

[0043] Step 2: Starting from the first first interval, merge adjacent first intervals with a similarity less than the similarity threshold one by one to obtain multiple second intervals.

[0044] Specifically, assume that the value range of the target excipient parameters is divided into n first intervals, calculate the similarity of these n first intervals, and starting from the first first interval, compare the similarity between the first first interval and the second first interval. If the similarity between the first first interval and the second first interval is less than the similarity threshold, then merge the first first interval and the second first interval, and compare it with the next first interval. If they are similar, continue to merge; if not, start a new round of similarity comparison and merging from the dissimilar first interval, thereby realizing the successive merging of adjacent first intervals to obtain multiple second intervals.

[0045] In some embodiments, successively merging adjacent first intervals with a similarity less than the similarity threshold to obtain multiple second intervals includes: if the similarity between a first interval and an adjacent first interval is less than the similarity threshold, then merge the first interval and the adjacent first interval into a new first interval, and repeat the operation of comparing the similarity between the new first interval and the adjacent first interval with the similarity threshold until the similarity between the new first interval and the adjacent first interval is greater than or equal to the similarity threshold, then determine the new first interval as the second interval, and continue to determine the comparison result of the similarity between the adjacent first interval and the next adjacent first interval with the similarity threshold.

[0046] Among them, the rule for successively merging adjacent first intervals is as follows: for adjacent first intervals and , if their 0, 1 distributions are similar, then merge them into a new interval. Among them, the similarity measure is: ; If , then merge the intervals and recalculate the 1 distribution of the merged interval : ; Among them, is the similarity threshold, and the specific value can be set according to the actual situation and will not be specifically limited here.

[0047] Among them, is the number of data points of the first interval .

[0048] Among them, if the similarity of adjacent first intervals is less than the similarity threshold, it indicates that the adjacent first intervals are relatively similar. Among them, if the similarity of adjacent first intervals is greater than or equal to the similarity threshold, it indicates that the adjacent first intervals are not similar. Thus, by merging adjacent first intervals with high similarity, that is, merging first intervals with relatively similar abnormal proportions (the proportion of category 1), it is beneficial to analyze the impact of target auxiliary material parameters on the cutting result in subsequent stages and improve the determination accuracy of the phased impact of auxiliary material parameters on the cutting result.

[0049] Exemplarily, assume that the value range of the target auxiliary material parameter is divided into n first intervals, calculate the similarity of these n first intervals, and starting from the first first interval, compare the similarity between the first first interval and the second first interval. If the similarity between the first first interval and the second first interval is less than the similarity threshold, then merge the first first interval and the second first interval to obtain a new first interval, and compare the similarity between the new first interval and the next first interval (i.e., the third first interval) with the similarity threshold. If they are similar, continue to merge to obtain a new first interval again, and compare the similarity between the newly obtained first interval and the next first interval (i.e., the fourth first interval). If the new first interval obtained by merging the first first interval and the second first interval is not similar to the third first interval, then take the new first interval obtained by merging the first first interval and the second first interval as the second interval, and start a new round of similarity comparison and merging from the third first interval. Thus, perform multiple traversals until the nth first interval is compared and merged to obtain multiple second intervals.

[0050] Step 140: Determine the influence curve of the target auxiliary material parameter on the cutting result according to the central value of the target auxiliary material parameter located in each second interval and the median value of the cutting result. The influence curve is used to determine the influence of the target auxiliary material parameter on the cutting result.

[0051] Since each first interval is obtained by merging adjacent first intervals with relatively similar abnormal proportions, the phased influence of the target auxiliary material parameter on the cutting result can be accurately characterized according to the target auxiliary material parameter of each second interval and the corresponding cutting result of each second interval, so as to improve the determination accuracy of the phased influence of the auxiliary material parameter on the cutting result.

[0052] Among them, the central value of the target auxiliary material parameter of each second interval is the center point of the value range of the target auxiliary material parameter of each second interval. For example, the value range of a certain second interval is: , then the center point of the value range of this second interval is: ; Among them, the median value of the cutting result of each second interval is the median or average value of the cutting result.

[0053] Specifically, a data set is generated based on the central value of the target auxiliary material parameter in each second interval and the median value of the cutting result. And the generated data set is fitted to obtain the influence curve of the target auxiliary material parameter on the cutting result. Among them, the fitting method can be polynomial fitting or spline interpolation fitting, etc.

[0054] Exemplarily, taking the median value of the cutting result of each second interval as the median of the cutting result as an example, the center point of the value range of the target auxiliary material parameter in each second interval and the median of the cutting result The generated data set is: ; And the data set is fitted to obtain the influence curve of the target auxiliary material parameter on the cutting result is: ; Thus, through the above steps, the value range of the target auxiliary material parameter is divided into intervals to achieve adaptive binning, and the similarity is calculated based on the distribution of the cutting results in the first interval for the divided first intervals. Thus, the first intervals with high similarity (i.e., the first intervals with similar abnormal ratios) are dynamically merged to reduce or eliminate the influence of data acquisition errors and noise interference on the determination of the influence of the auxiliary material parameter, which is beneficial to accurately depict the stage influence of the target auxiliary material parameter on the cutting result. And according to the central value of the target auxiliary material parameter in the merged second interval and the median value of the cutting result, the influence curve of the target auxiliary material parameter on the cutting result is fitted. Through the influence curve, the stage influence of the target auxiliary material parameter on the cutting result can be accurately analyzed, which is beneficial to improving the determination accuracy of the stage influence of the auxiliary material parameter on the cutting result, thereby improving the silicon wafer cutting yield and process stability and reducing the auxiliary material usage cost.

[0055] Figure 2 It is a schematic diagram of the fitting result of the influence of the cutting fluid turbidity on the jumper and the broken seam provided in the embodiment of the present application. Exemplarily, refer to Figure 2, L1 is the fitting curve of the influence of the cutting fluid turbidity on the jumper, L2 is the fitting curve of the influence of the cutting fluid turbidity on the broken seam, and L3 is the fitting curve of the influence of the cutting fluid turbidity on the jumper and the broken seam. Exemplarily, taking the influence of the cutting fluid turbidity on the jumper as an example, referring to curve L1, it can be seen that when the cutting fluid turbidity is set in the range of 30 - 40, the cutting anomaly rate is relatively low, while when the cutting fluid turbidity is set in the range of 70 - 80, the cutting anomaly rate is relatively high. Thus, through the above-mentioned influence determination method of the auxiliary material parameters in this application, the influence curve of the target auxiliary material parameters on the cutting result can be obtained, and the stage influence of the target auxiliary material parameters on the cutting result can be analyzed through the influence curve, which is beneficial to improving the determination accuracy of the stage influence of the auxiliary material parameters on the cutting result, and further beneficial to accurately optimizing the auxiliary material ratio and the optimization control of the cutting yield, reducing the auxiliary material usage cost, and improving the stability of the silicon wafer cutting process.

[0056] Correspondingly, please refer to Figure 3 , Figure 3 is the structural schematic diagram of the influence determination system of the auxiliary material parameters in the embodiment of this application. The influence determination system 100 of the auxiliary material parameters provided in the embodiment of this application includes: an acquisition module 101, configured to acquire the target auxiliary material parameters and the cutting results corresponding to the target auxiliary material parameters, where the target auxiliary material parameters are used to characterize the historical parameter values of the target auxiliary material; an interval division module 102, configured to divide the value range of the target auxiliary material parameters into multiple first intervals; an interval merging module 103, configured to merge adjacent first intervals according to the distribution of the cutting results located in each first interval to obtain multiple second intervals; an influence curve determination module 104, configured to determine the influence curve of the target auxiliary material parameters on the cutting results according to the central value of the target auxiliary material parameters and the median value of the cutting results located in each second interval, where the influence curve is used to determine the influence of the target auxiliary material parameters on the cutting results.

[0057] It can be understood that the influence determination system of the auxiliary material parameters in the embodiment of this application realizes dynamic binning and noise suppression of data by dividing the value range of the target auxiliary material parameters into intervals and merging the divided intervals according to the distribution of the cutting results in the divided intervals, and accurately depicts the stage influence curve of the auxiliary material parameters on the cutting results according to the central value of the target auxiliary material parameters and the median value of the cutting results in the merged intervals, thereby improving the determination accuracy of the stage influence of the auxiliary material parameters on the cutting results, and further being beneficial to accurately optimizing the auxiliary material ratio and the optimization control of the cutting yield, reducing the auxiliary material usage cost, and improving the cutting process stability.

[0058] In some embodiments, the interval merging module 103 is further configured to: determine the similarity of adjacent first intervals according to the distribution of the cutting results located in each first interval; Starting from the first of the first intervals, successively merge adjacent first intervals with a similarity less than the similarity threshold to obtain a plurality of the second intervals.

[0059] In some embodiments, the interval merging module 103 is further configured to: if the similarity between the first interval and an adjacent first interval is less than the similarity threshold, merge the first interval and the adjacent first interval into a new first interval, and repeat the operation of comparing the similarity between the new first interval and the adjacent first interval with the similarity threshold until the similarity between the new first interval and the adjacent first interval is greater than or equal to the similarity threshold, then determine the new first interval as the second interval, and continue to determine the comparison result between the similarity between the adjacent first interval and the next adjacent first interval and the similarity threshold.

[0060] In some embodiments, the interval merging module 103 is further configured to: determine the normal proportion and the abnormal proportion of the cutting results located in each of the first intervals; According to the normal proportion and the abnormal proportion, determine the distribution of the cutting results located in the corresponding first interval.

[0061] In some embodiments, the interval merging module 103 is further configured to: perform binary classification processing on the cutting results corresponding to the target auxiliary material parameters according to a preset target yield threshold to obtain a binary classification processing result; According to the binary classification processing result and the total number of the cutting results within the first interval, determine the normal proportion and the abnormal proportion of the cutting results located in the first interval.

[0062] In some embodiments, the interval dividing module 102 is further configured to: divide the value range of the target auxiliary material parameters into a plurality of first intervals according to the equal-width rule.

[0063] In some embodiments, the median value of the cutting results includes the median or the average value of the cutting results.

[0064] Correspondingly, please refer to Figure 4 , Figure 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application. An electronic device provided by an embodiment of the present application includes a memory 501 and a processor 502. The memory 501 is used to store a computer program. The processor 502 is used to execute the computer program stored in the memory 501. When the computer program stored in the memory 501 is executed, the processor 502 executes the influence determination method for the auxiliary material parameters in the foregoing embodiments of the present application.

[0065] Correspondingly, an embodiment of the present application further provides a computer-readable storage medium storing computer instructions for causing a processor to implement the method for determining the influence of auxiliary material parameters as described in the foregoing embodiments of the present application when executed.

[0066] The foregoing has introduced in detail a method, a system, a device, and a storage medium for determining the influence of auxiliary material parameters provided by the embodiments of the present application. Specific examples are used herein to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the technical solution and its core idea of the present application; those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and 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 application.

Claims

1. A method for determining the influence of auxiliary material parameters, characterized in that, Including: Obtain target auxiliary material parameters and the cutting results corresponding to the target auxiliary material parameters, where the target auxiliary material parameters are used to represent the historical parameter values of the target auxiliary material; Divide the value range of the target auxiliary material parameters into multiple first intervals; According to the distribution of the cutting results in each of the first intervals, merge adjacent first intervals to obtain multiple second intervals; According to the central value of the target auxiliary material parameters in each of the second intervals and the median value of the cutting results, determine the influence curve of the target auxiliary material parameters on the cutting results, where the influence curve is used to determine the influence of the target auxiliary material parameters on the cutting results.

2. The method for determining the influence of excipient parameters according to claim 1, wherein The method for obtaining multiple second intervals includes: Determine the similarity of adjacent first intervals according to the distribution of the cutting results in each of the first intervals; Starting from the first first interval, merge adjacent first intervals with a similarity less than the similarity threshold one by one to obtain multiple second intervals.

3. The method for determining the influence of the excipient parameters according to claim 2, wherein The step of merging adjacent first intervals with a similarity less than the similarity threshold one by one to obtain multiple second intervals includes: If the similarity between the first interval and the adjacent first interval is less than the similarity threshold, merge the first interval and the adjacent first interval into a new first interval, and repeat the operation of comparing the similarity between the new first interval and the adjacent first interval with the similarity threshold until the similarity between the new first interval and the adjacent first interval is greater than or equal to the similarity threshold, then determine the new first interval as the second interval, and continue to determine the comparison result between the similarity of the adjacent first interval and the next adjacent first interval and the similarity threshold.

4. The influence determination method of the excipient parameters according to claim 2, characterized in that The method for determining the distribution of the cutting results in each of the first intervals includes: Determine the normal proportion and abnormal proportion of the cutting results in each of the first intervals; According to the normal proportion and the abnormal proportion, determine the distribution of the cutting results in the corresponding first interval.

5. The method for determining the influence of excipient parameters according to claim 4, characterized in that, The method for determining the normal proportion and abnormal proportion of the cutting results in each of the first intervals includes: Perform binary classification processing on the cutting results corresponding to the target auxiliary material parameters according to a preset target yield threshold to obtain a binary classification result; According to the binary classification result and the total number of the cutting results in the first interval, determine the normal proportion and abnormal proportion of the cutting results in the first interval.

6. The method for determining the influence of the excipient parameters according to claim 1, wherein, The step of dividing the value range of the target auxiliary material parameters into multiple first intervals includes: Divide the value range of the target auxiliary material parameters into multiple first intervals according to the equal-width rule.

7. The method for determining the influence of auxiliary material parameters according to claim 1, wherein The median value of the cutting results includes the median or average value of the cutting results.

8. An influence determination system for auxiliary material parameters, characterized in that, Including: An acquisition module, configured to acquire target auxiliary material parameters and the cutting results corresponding to the target auxiliary material parameters, where the target auxiliary material parameters are used to represent the historical parameter values of the target auxiliary material; An interval division module, configured to divide the value range of the target auxiliary material parameters into multiple first intervals; An interval merging module, configured to merge adjacent first intervals according to the distribution of the cutting results located in each of the first intervals, so as to obtain a plurality of second intervals; An influence curve determination module, configured to determine an influence curve of the target auxiliary material parameter on the cutting result according to the central value of the target auxiliary material parameter located in each of the second intervals and the median value of the cutting results, where the influence curve is used to determine the influence of the target auxiliary material parameter on the cutting result.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory; a computer program is stored in the memory, and the processor is configured to execute the computer program stored in the memory to implement the method for determining the influence of the auxiliary material parameter according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the processor to implement the method for determining the influence of the auxiliary material parameter according to any one of claims 1 to 7 when executed.

Images