Semiconductor data management method and device, electronic equipment and storage medium

Abstract

The invention provides a semiconductor data management method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the clustering extraction of the original data of semiconductors belonging to the same data type in an evaluation period for each evaluation period, and obtaining at least one group of original data sets; for each original data set, corresponding statistical index calculation is carried out according to multiple pieces of original data in the original data set, and at least one statistical index value of the original data set and an evaluation result of each statistical index value are determined; arranging and displaying the statistical index values of the same index type in the original data sets of the same data type in the plurality of evaluation cycles to obtain at least one statistical data table; and determining an overall quality evaluation result of the semiconductor according to the at least one statistical data table and the evaluation result of each statistical index value. Therefore, through clustering, index calculation, dynamic display and overall evaluation of the original data of the semiconductor, the systematicness and accuracy of data management are improved.

Description

Technical Field

[0001] The present application relates to the field of semiconductor technology, and in particular to a semiconductor data management method, device, electronic device and storage medium. Background Art

[0002] In the semiconductor manufacturing process, the Statistical Process Control (SPC) system is a widely used quality monitoring tool for real-time monitoring and control of key parameters in the production process to ensure product quality and production efficiency. However, most current SPC systems have certain limitations in baseline control. For example, existing SPC systems only have the ability to calculate control limits.

[0003] Therefore, due to the defects of the existing SPC system, relevant personnel are unable to timely and accurately understand the status of semiconductor products, which affects production quality and efficiency. Summary of the invention

[0004] In view of this, the purpose of this application is to provide a semiconductor data management method, device, electronic device and storage medium, which not only improves the systematicness and accuracy of data management, but also significantly enhances the scientificity and practicality of semiconductor product quality assessment through clustering, indicator calculation, dynamic display and overall evaluation of semiconductor raw data.

[0005] The present application provides a semiconductor data management method, the management method comprising:

[0006] For each evaluation period, clustering and extracting the original data of semiconductors belonging to the same data type in the evaluation period to obtain at least one group of original data sets;

[0007] For each original data set, corresponding statistical index calculation is performed according to multiple original data in the original data set to determine at least one statistical index value of the original data set and an evaluation result of each statistical index value; wherein the evaluation result of the statistical index value is determined according to the baseline and the control limit;

[0008] Arrange and display the statistical indicator values ​​of the same indicator type in the original data sets of the same data type in multiple evaluation periods in chronological order to obtain at least one statistical data table;

[0009] An overall quality evaluation result of the semiconductor is determined based on at least one statistical data table and an evaluation result of each statistical indicator value.

[0010] Optionally, the management method further includes:

[0011] For each semiconductor, at any evaluation node, obtaining at least one raw data corresponding to the semiconductor;

[0012] For each piece of raw data, according to the data control limit of the corresponding evaluation node, the raw data is analyzed to obtain at least one node evaluation result of the semiconductor;

[0013] A product evaluation result of the semiconductor is generated based on all node evaluation results of the semiconductor.

[0014] Optionally, after obtaining the at least one node evaluation result of the semiconductor, the management method further includes:

[0015] When the node evaluation result indicates that the raw data of the semiconductor exceeds the corresponding data control limit, a production abnormality is determined;

[0016] Send production anomaly reminders to target personnel.

[0017] Optionally, determine the evaluation result of the statistical indicator value by the following steps:

[0018] Obtain the baseline of the evaluation period corresponding to the statistical indicator value;

[0019] Determine the control limit corresponding to the statistical indicator value according to the baseline and the corresponding data fluctuation range;

[0020] The statistical indicator value is evaluated according to the control limit to determine an evaluation result of the statistical indicator value.

[0021] Optionally, evaluating the statistical indicator value according to the control limit to determine the evaluation result of the statistical indicator value includes:

[0022] If the statistical indicator value is within the control limit, determining that the evaluation result of the statistical indicator value is a normal result;

[0023] If the statistical indicator value is within the control limit, it is determined that the evaluation result of the statistical indicator value is an abnormal result.

[0024] Optionally, after determining that the evaluation result of the statistical indicator value is an abnormal result, the management method further includes:

[0025] Determine whether the original data set corresponding to the statistical indicator value meets the data volume requirement;

[0026] If satisfied, the target person will be notified of the overall abnormality and the abnormal result will be marked;

[0027] If not satisfied, mark the abnormal result.

[0028] Optionally, the statistical indicator includes at least one of the following: mean, standard deviation, and range.

[0029] The present application also provides a semiconductor data management device, the management device comprising:

[0030] An extraction module, for clustering and extracting raw data of semiconductors belonging to the same data type in each evaluation period, to obtain at least one set of raw data sets;

[0031] A calculation module, for calculating corresponding statistical indicators for each original data set according to multiple original data in the original data set, and determining at least one statistical indicator value of the original data set and an evaluation result of each statistical indicator value; wherein the evaluation result of the statistical indicator value is determined according to a baseline and a control limit;

[0032] A display module is used to arrange and display the statistical indicator values ​​of the same indicator type in the original data sets of the same data type in multiple evaluation periods in chronological order to obtain at least one statistical data table;

[0033] The first evaluation module is used to determine the overall quality evaluation result of the semiconductor according to at least one statistical data table and the evaluation result of each statistical indicator value.

[0034] Optionally, the management device further includes a second evaluation module, and the second evaluation module is used to:

[0035] For each semiconductor, at any evaluation node, obtaining at least one raw data corresponding to the semiconductor;

[0036] For each piece of raw data, according to the data control limit of the corresponding evaluation node, the raw data is analyzed to obtain at least one node evaluation result of the semiconductor;

[0037] A product evaluation result of the semiconductor is generated based on all node evaluation results of the semiconductor.

[0038] Optionally, the second evaluation module is further used for:

[0039] After obtaining at least one node evaluation result of the semiconductor, when the node evaluation result indicates that the raw data of the semiconductor exceeds the corresponding data control limit, determining a production abnormality;

[0040] Send production anomaly reminders to target personnel.

[0041] Optionally, the calculation module is further used to determine the evaluation result of the statistical indicator value through the following steps:

[0042] Obtain the baseline of the evaluation period corresponding to the statistical indicator value;

[0043] Determine the control limit corresponding to the statistical indicator value according to the baseline and the corresponding data fluctuation range;

[0044] The statistical indicator value is evaluated according to the control limit to determine an evaluation result of the statistical indicator value.

[0045] Optionally, when the calculation module is used to evaluate the statistical indicator value according to the control limit to determine the evaluation result of the statistical indicator value, the calculation module is used to:

[0046] If the statistical indicator value is within the control limit, determining that the evaluation result of the statistical indicator value is a normal result;

[0047] If the statistical indicator value is within the control limit, it is determined that the evaluation result of the statistical indicator value is an abnormal result.

[0048] Optionally, the calculation module is further used for:

[0049] After determining that the evaluation result of the statistical indicator value is an abnormal result, determining whether the original data set corresponding to the statistical indicator value meets the data volume requirement;

[0050] If satisfied, the target person will be notified of the overall abnormality and the abnormal result will be marked;

[0051] If not satisfied, mark the abnormal result.

[0052] Optionally, the statistical indicator includes at least one of the following: mean, standard deviation, and range.

[0053] An embodiment of the present application also provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the management method described above are performed.

[0054] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the management method described above are executed.

[0055] The embodiments of the present application provide a semiconductor data management method, device, electronic device and storage medium, the management method comprising: for each evaluation cycle, clustering and extracting the original data of semiconductors belonging to the same data type within the evaluation cycle to obtain at least one group of original data sets; for each original data set, performing corresponding statistical index calculations based on multiple original data in the original data set to determine at least one statistical index value of the original data set and an evaluation result of each statistical index value; wherein the evaluation result of the statistical index value is determined based on a baseline and a control limit; arranging and displaying the statistical index values ​​of the same index type in the original data sets of the same data type within multiple evaluation cycles in chronological order to obtain at least one statistical data table; and determining the overall quality evaluation result of the semiconductor based on the at least one statistical data table and the evaluation result of each statistical index value.

[0056] In this way, this application can effectively summarize data features, reduce the interference of redundant data, provide a refined data basis for subsequent analysis, and improve data processing efficiency by clustering and extracting raw data belonging to the same data type within the evaluation cycle. By calculating the statistical index value for each group of original data sets and evaluating it in combination with the baseline and control limit, potential abnormal fluctuations or trends in the data can be effectively identified to ensure the accuracy and reliability of data analysis. Arranging the statistical index values ​​of the same data type into a statistical data table in chronological order helps to intuitively observe the law of indicator changes over time, facilitate the discovery of long-term trends or cyclical fluctuations, and provide a basis for process improvement. According to the statistical data table and the evaluation results, the overall quality evaluation results of the semiconductor are further obtained, which is expanded from a single indicator to a global perspective, providing comprehensive quality evaluation support for decision makers, and facilitating the formulation of more targeted improvement measures. In addition, based on the dynamic management of the evaluation cycle, real-time monitoring of semiconductor quality can be achieved, problems can be discovered and early warnings can be issued in a timely manner, and the response speed and reliability of quality control can be improved.

[0057] Therefore, this solution not only improves the systematicness and accuracy of data management, but also significantly enhances the scientificity and practicality of quality assessment through clustering, indicator calculation, dynamic display and overall evaluation of semiconductor raw data.

[0058] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 A flowchart of a semiconductor data management method provided in an embodiment of the present application;

[0061] Figure 2 One of the structural schematic diagrams of a semiconductor data management device provided in an embodiment of the present application;

[0062] Figure 3 A second structural diagram of a semiconductor data management device provided in an embodiment of the present application;

[0063] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0065] In the semiconductor manufacturing process, the Statistical Process Control (SPC) system is a widely used quality monitoring tool for real-time monitoring and control of key parameters in the production process to ensure product quality and production efficiency. However, most current SPC systems have certain limitations in baseline control. For example, existing SPC systems only have the ability to calculate control limits.

[0066] Therefore, due to the defects of the existing SPC system, relevant personnel are unable to timely and accurately understand the status of semiconductor products, which affects production quality and efficiency.

[0067] Based on this, the embodiments of the present application provide a semiconductor data management method, device, electronic device and storage medium, which not only improves the systematicness and accuracy of data management, but also significantly enhances the scientificity and practicality of semiconductor product quality assessment through clustering, indicator calculation, dynamic display and overall evaluation of semiconductor raw data.

[0068] This management method can be used in conjunction with the SPC system, or the solution can be embedded in the SPC system.

[0069] See also Figure 1 , Figure 1 A flowchart of a semiconductor data management method provided in an embodiment of the present application. Figure 1 As shown in , the management method provided by the embodiment of the present application includes:

[0070] S101 . For each evaluation period, clustering and extracting raw data of semiconductors belonging to the same data type within the evaluation period to obtain at least one set of raw data sets.

[0071] S102: For each original data set, corresponding statistical index calculation is performed according to multiple original data in the original data set to determine at least one statistical index value of the original data set and an evaluation result of each statistical index value.

[0072] S103. Arrange and display the statistical indicator values ​​of the same indicator type in the original data sets of the same data type within multiple evaluation periods in chronological order to obtain at least one statistical data table.

[0073] S104: Determine an overall quality evaluation result of the semiconductor according to at least one statistical data table and an evaluation result of each statistical indicator value.

[0074] With respect to step S101 , in this step, the original data within the evaluation period is first collected, and then the original data is screened and clustered according to preset data types to form at least one original data set.

[0075] The number of the original data sets is determined by the data type, and the data type can be preset.

[0076] For example, the data types may include: manufacturing process parameters, electrical performance parameters, physical characteristic parameters, environmental adaptability data, etc.

[0077] The above types can be further divided, for example: manufacturing process parameters may include: wafer manufacturing related parameters, etching process parameters, thin film deposition parameters, etc.; electrical performance parameters may include: current and voltage related parameters, power and efficiency parameters, frequency and delay parameters, etc.; the physical property parameters may include: thermal property parameters, mechanical strength, surface quality, etc.; environmental adaptability data may include: temperature range, anti-electromagnetic interference, humidity and reliability, etc.

[0078] The data type for dividing the data set can be adaptively selected and is not limited here. The length of the evaluation cycle can also be adaptively set and is not limited here.

[0079] Continuing with step S101 , when clustering the original data of the semiconductor, clustering may be performed according to the type identification of the original data (wherein, when each original data is generated, the type identification is added at the same time).

[0080] In addition, before data clustering, the acquired raw data can be preprocessed, such as cleaning the data and removing outliers and null values.

[0081] For step S102, the evaluation result of the statistical indicator value is determined according to the baseline and the control limit. In this step, for each original data set, the statistical indicator (at least one) to be calculated for the original data set is determined; then, according to the determined statistical indicator, multiple original data in the data set are used to calculate in a corresponding manner to obtain at least one statistical indicator value; finally, for each statistical indicator value, the evaluation result of the statistical indicator value is determined according to its corresponding baseline and control limit.

[0082] Here, the statistical indicators corresponding to different original data sets are not necessarily the same, and the baseline and control limit of the same statistical indicator may be different in different evaluation cycles. The control limit of the same statistical indicator can be determined based on the baseline to which it corresponds. The baseline and control limit corresponding to the same statistical indicator in each evaluation cycle are not necessarily the same.

[0083] For example, the statistical indicators corresponding to the original data may include at least one of the following: mean, standard deviation, range, and may also include skewness coefficient, kurtosis, etc.

[0084] The statistical indicators can be determined independently according to actual conditions.

[0085] Continuing with step S102, in one implementation provided in the present application, the evaluation result of the statistical indicator value is determined by the following steps:

[0086] S1021. Obtain the baseline of the evaluation period corresponding to the statistical indicator value.

[0087] S1022. Determine the control limit corresponding to the statistical indicator value according to the baseline and the corresponding data fluctuation range.

[0088] S1023. Evaluate the statistical indicator value according to the control limit to determine an evaluation result of the statistical indicator value.

[0089] For step S1021, the baseline is a reference standard for evaluating the statistical indicator value. For example, it can be obtained in the following ways, which are limited in this step: historical data mean: setting the baseline based on the mean of the statistical indicator over a period of time; experience value or target value: using industry standards or production targets as the baseline; dynamic adjustment: if the data fluctuates greatly, the baseline can use dynamic adjustment methods such as sliding average.

[0090] Here, the baselines corresponding to the same statistical indicator in different evaluation cycles may not be the same; the baseline can be obtained according to the evaluation cycle.

[0091] Regarding step S1022, here, the upper and lower limits allowed are determined according to the standard deviation or deviation range of the historical data. The fluctuation range may include a fixed range or a statistical range.

[0092] In this step, the baseline value is added to or subtracted from the fluctuation range to obtain the control limit. For example, the upper control limit = baseline + fluctuation range; the lower control limit = baseline - fluctuation range.

[0093] With respect to step S1023, in this step, the statistical indicator value is evaluated according to the control limit and in combination with a preset evaluation logic to determine an evaluation result of the statistical indicator value.

[0094] For step S1023, in an embodiment provided in the present application, the statistical indicator value is evaluated according to the control limit to determine the evaluation result of the statistical indicator value, including: if the statistical indicator value is within the control limit, determining that the evaluation result of the statistical indicator value is a normal result; if the statistical indicator value is within the control limit, determining that the evaluation result of the statistical indicator value is an abnormal result.

[0095] In addition, in another embodiment provided by the present application, the statistical indicator value is evaluated according to the control limit to determine the evaluation result of the statistical indicator value, which also includes: the statistical indicator value is within the control limit and is evaluated as normal; slightly over the limit: the indicator value is outside the control limit but close to the upper and lower limits, and is evaluated as slightly abnormal; the indicator value significantly exceeds the control limit and is evaluated as seriously abnormal.

[0096] In addition, in another embodiment provided in the present application, after determining that the evaluation result of the statistical indicator value is an abnormal result, the management method also includes: determining whether the original data set corresponding to the statistical indicator value meets the data volume requirement; if so, providing an overall abnormal reminder to the target personnel and marking the abnormal result; if not, marking the abnormal result.

[0097] In this embodiment, after the statistical index value is evaluated as abnormal, in order to ensure the reliability of the abnormal result, it is necessary to check whether the original data set used to calculate the statistical index value meets the data volume requirement. If the data volume requirement is met, the abnormal result is regarded as a valid abnormality, and an overall abnormal reminder is issued to the target personnel (such as quality management personnel or engineers), and the abnormal result is marked for tracking, analysis and decision-making. If the data volume requirement is not met, the abnormal result can be marked as insufficient data abnormality (further supplementary data or re-evaluation is required), and no abnormal reminder is issued for the time being to avoid unnecessary alarms.

[0098] In this way, by identifying the amount of data, misjudgment due to insufficient data can be avoided, and the user's time cost can be greatly reduced.

[0099] With respect to step S103, in this step, statistical indicator values ​​of the same indicator type of the same data type (such as power consumption) in multiple evaluation cycles are collected. The statistical indicator values ​​in each cycle are arranged in chronological order to form time series data. A statistical data table is drawn based on the formed time series data.

[0100] Here, each statistical indicator can correspond to a statistical data table, or multiple statistical indicators can be aggregated in one table.

[0101] The type of the statistical data table may be any of the following: a time series table, a classification statistical table, a threshold exceeding limit table, a multi-index comparison table, a trend prediction table, or other types, which are not limited here.

[0102] With respect to step S104, in this step, for a batch of semiconductor products, all or part of the statistical data table of the batch of semiconductor products and the evaluation results of each statistical indicator value are obtained, and then a comprehensive analysis is performed to obtain a detailed description of the quality evaluation (overall quality evaluation results).

[0103] Here, when conducting a comprehensive analysis, the evaluation results of each statistical indicator value may be weighted, the overall quality score may be comprehensively calculated, and the overall quality evaluation result of the semiconductor may be generated with reference to the overall quality score.

[0104] When assigning weights to the evaluation results of each statistical indicator value, the weights can be determined based on the importance of the indicator or industry experience.

[0105] After determining the overall quality score, you can set the score range and determine the corresponding quality level (such as excellent, good, medium, and poor).

[0106] In addition, in another embodiment provided by the present application, the management method further includes: for each semiconductor, at any evaluation node, obtaining at least one raw data corresponding to the semiconductor;

[0107] S201. Analyze each piece of original data according to the data control limit of the corresponding evaluation node to obtain at least one node evaluation result of the semiconductor.

[0108] S202: Generate a product evaluation result of the semiconductor based on all node evaluation results of the semiconductor.

[0109] With respect to step S201, in the semiconductor production process, multiple evaluation nodes can be pre-set, and raw data can be collected at each evaluation node on a regular basis or according to an event trigger mechanism. The collected raw data is compared to see whether it falls within the corresponding control limit range, and then the node evaluation result of the semiconductor is generated.

[0110] At least one node evaluation result can be determined for each semiconductor. Each node has predefined data control limits (upper and lower limits).

[0111] Continuing with step S201, in one embodiment provided in the present application, after obtaining at least one node evaluation result of the semiconductor, the management method also includes: when the node evaluation result indicates that the original data of the semiconductor exceeds the corresponding data control limit, determining a production abnormality; and sending a production abnormality reminder to the target personnel.

[0112] Here, in semiconductor production management, the node evaluation results are a specific analysis of each evaluation node. Based on these results, if some raw data is found to be beyond the data control limit, production abnormalities can be determined and relevant personnel can be notified in time to take necessary measures to avoid larger-scale quality problems or production losses.

[0113] Each evaluation node has an acceptable upper and lower limit range to measure whether the original data is qualified. When the value of the original data is not within the control limit range, the node evaluation result will indicate an abnormality.

[0114] Further, the types of anomalies may include: Minor anomalies: small deviations from the control limits, which may be equipment calibration issues. Major anomalies: large deviations from the control limits, which may indicate systematic errors in the production process.

[0115] With respect to step S202, the results of all evaluation nodes are summarized, a product evaluation result is generated according to the rules, and the evaluation result of the product is recorded and stored to support subsequent tracing or analysis.

[0116] For example, if all nodes are normal, the product evaluation result is "qualified". If there are one or more abnormal nodes, the overall evaluation result (such as "need to be re-tested" or "unqualified") is determined according to the severity of the abnormality.

[0117] In this way, this application can effectively summarize data features, reduce the interference of redundant data, provide a refined data basis for subsequent analysis, and improve data processing efficiency by clustering and extracting raw data belonging to the same data type within the evaluation cycle. By calculating the statistical index value for each group of original data sets and evaluating it in combination with the baseline and control limit, potential abnormal fluctuations or trends in the data can be effectively identified to ensure the accuracy and reliability of data analysis. Arranging the statistical index values ​​of the same data type into a statistical data table in chronological order helps to intuitively observe the law of indicator changes over time, facilitate the discovery of long-term trends or cyclical fluctuations, and provide a basis for process improvement. According to the statistical data table and the evaluation results, the overall quality evaluation results of the semiconductor are further obtained, which is expanded from a single indicator to a global perspective, providing comprehensive quality evaluation support for decision makers, and facilitating the formulation of more targeted improvement measures. In addition, based on the dynamic management of the evaluation cycle, real-time monitoring of semiconductor quality can be achieved, problems can be discovered and early warnings can be issued in a timely manner, and the response speed and reliability of quality control can be improved.

[0118] Therefore, this solution not only improves the systematicness and accuracy of data management, but also significantly enhances the scientificity and practicality of quality assessment through clustering, indicator calculation, dynamic display and overall evaluation of semiconductor raw data.

[0119] Based on the same inventive concept, a management device corresponding to the management method is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned management method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0120] See also Figure 2 , Figure 3 , Figure 2 This is one of the structural schematic diagrams of a semiconductor data management device provided in an embodiment of the present application. Figure 3 This is a second structural diagram of a semiconductor data management device provided in an embodiment of the present application. Figure 2 As shown in , the management device 200 includes:

[0121] An extraction module 210 is used to perform clustering extraction on raw data of semiconductors belonging to the same data type in each evaluation period to obtain at least one set of raw data sets;

[0122] A calculation module 220 is used to calculate corresponding statistical indicators for each original data set according to multiple original data in the original data set, and determine at least one statistical indicator value of the original data set and an evaluation result of each statistical indicator value; wherein the evaluation result of the statistical indicator value is determined according to the baseline and the control limit;

[0123] A display module 230 is used to arrange and display the statistical indicator values ​​of the same indicator type in the original data sets of the same data type in multiple evaluation periods in chronological order to obtain at least one statistical data table;

[0124] The first evaluation module 240 is used to determine an overall quality evaluation result of the semiconductor according to at least one statistical data table and an evaluation result of each statistical indicator value.

[0125] Optional, such as Figure 3 As shown, the management device 200 further includes a second evaluation module 250, and the second evaluation module 250 is used to:

[0126] For each semiconductor, at any evaluation node, obtaining at least one raw data corresponding to the semiconductor;

[0127] For each piece of raw data, according to the data control limit of the corresponding evaluation node, the raw data is analyzed to obtain at least one node evaluation result of the semiconductor;

[0128] A product evaluation result of the semiconductor is generated based on all node evaluation results of the semiconductor.

[0129] Optionally, the second evaluation module 250 is further used for:

[0130] After obtaining at least one node evaluation result of the semiconductor, when the node evaluation result indicates that the raw data of the semiconductor exceeds the corresponding data control limit, determining a production abnormality;

[0131] Send production anomaly reminders to target personnel.

[0132] Optionally, the calculation module 220 is further configured to determine an evaluation result of the statistical indicator value through the following steps:

[0133] Obtain the baseline of the evaluation period corresponding to the statistical indicator value;

[0134] Determine the control limit corresponding to the statistical indicator value according to the baseline and the corresponding data fluctuation range;

[0135] The statistical indicator value is evaluated according to the control limit to determine an evaluation result of the statistical indicator value.

[0136] Optionally, when the calculation module 220 is used to evaluate the statistical indicator value according to the control limit to determine the evaluation result of the statistical indicator value, the calculation module 220 is used to:

[0137] If the statistical indicator value is within the control limit, determining that the evaluation result of the statistical indicator value is a normal result;

[0138] If the statistical indicator value is within the control limit, it is determined that the evaluation result of the statistical indicator value is an abnormal result.

[0139] Optionally, the calculation module 220 is further used for:

[0140] After determining that the evaluation result of the statistical indicator value is an abnormal result, determining whether the original data set corresponding to the statistical indicator value meets the data volume requirement;

[0141] If satisfied, the target person will be notified of the overall abnormality and the abnormal result will be marked;

[0142] If not satisfied, mark the abnormal result.

[0143] Optionally, the statistical indicator includes at least one of the following: mean, standard deviation, and range.

[0144] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As shown in , the electronic device 400 includes a processor 410 , a memory 420 and a bus 430 .

[0145] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 via the bus 430. When the machine-readable instructions are executed by the processor 410, the above-mentioned Figure 1 The specific implementation of the steps in the method embodiment shown can be found in the method embodiment, and will not be repeated here.

[0146] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 The specific implementation of the steps in the method embodiment shown can be found in the method embodiment, and will not be repeated here.

[0147] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0148] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0149] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0151] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0152] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A semiconductor data management method, characterized in that: The management method comprises: For each evaluation period, clustering and extracting the original data of semiconductors belonging to the same data type in the evaluation period to obtain at least one group of original data sets; For each original data set, corresponding statistical index calculation is performed according to multiple original data in the original data set to determine at least one statistical index value of the original data set and an evaluation result of each statistical index value; wherein the evaluation result of the statistical index value is determined according to the baseline and the control limit; Arrange and display the statistical indicator values ​​of the same indicator type in the original data sets of the same data type in multiple evaluation periods in chronological order to obtain at least one statistical data table; An overall quality evaluation result of the semiconductor is determined based on at least one statistical data table and an evaluation result of each statistical indicator value.

2. The management method according to claim 1, characterized in that: The management method also includes: For each semiconductor, at any evaluation node, obtaining at least one raw data corresponding to the semiconductor; For each piece of raw data, according to the data control limit of the corresponding evaluation node, the raw data is analyzed to obtain at least one node evaluation result of the semiconductor; A product evaluation result of the semiconductor is generated based on all node evaluation results of the semiconductor.

3. The management method according to claim 2, characterized in that: After obtaining at least one node evaluation result of the semiconductor, the management method further includes: When the node evaluation result indicates that the raw data of the semiconductor exceeds the corresponding data control limit, a production abnormality is determined; Send production anomaly reminders to target personnel.

4. The management method according to claim 1, characterized in that: The evaluation results of the statistical indicator values ​​are determined by the following steps: Obtain the baseline of the evaluation period corresponding to the statistical indicator value; Determine the control limit corresponding to the statistical indicator value according to the baseline and the corresponding data fluctuation range; The statistical indicator value is evaluated according to the control limit to determine an evaluation result of the statistical indicator value.

5. The management method according to claim 4, characterized in that: The step of evaluating the statistical indicator value according to the control limit to determine the evaluation result of the statistical indicator value includes: If the statistical indicator value is within the control limit, determining that the evaluation result of the statistical indicator value is a normal result; If the statistical indicator value is within the control limit, it is determined that the evaluation result of the statistical indicator value is an abnormal result.

6. The management method according to claim 5, characterized in that: After determining that the evaluation result of the statistical indicator value is an abnormal result, the management method further includes: Determine whether the original data set corresponding to the statistical indicator value meets the data volume requirement; If satisfied, the target person will be notified of the overall abnormality and the abnormal result will be marked; If not satisfied, mark the abnormal result.

7. The management method according to claim 1, characterized in that: The statistical indicators include at least one of the following: mean, standard deviation, and range.

8. A semiconductor data management device, characterized in that: The management device comprises: An extraction module, for clustering and extracting raw data of semiconductors belonging to the same data type in each evaluation period, to obtain at least one set of raw data sets; A calculation module, for calculating corresponding statistical indicators for each original data set according to multiple original data in the original data set, and determining at least one statistical indicator value of the original data set and an evaluation result of each statistical indicator value; wherein the evaluation result of the statistical indicator value is determined according to a baseline and a control limit; A display module is used to arrange and display the statistical indicator values ​​of the same indicator type in the original data sets of the same data type in multiple evaluation periods in chronological order to obtain at least one statistical data table; The first evaluation module is used to determine the overall quality evaluation result of the semiconductor according to at least one statistical data table and the evaluation result of each statistical indicator value.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the management method according to any one of claims 1 to 7 are executed.

Images