Semiconductor device detection method and system based on acquired data

Abstract

The invention discloses a semiconductor device detection method and system based on collected data, and relates to the field of semiconductors, and the method comprises the steps: collecting real-time data; obtaining classified real-time data and a risk variable list; a comprehensive risk index is obtained, and an intelligent algorithm is used for outputting parameter indexes and resource configuration in the semiconductor device detection process; whether the comprehensive risk index exceeds an alarm threshold value or not is judged, if the comprehensive risk index exceeds the alarm threshold value, an alarm signal is sent out, and personalized detection process and environment setting are carried out according to generated parameter indexes and resource configuration in the semiconductor device detection process; the semiconductor device is detected according to the personalized detection process and environment setting; the system comprises a real-time data collection module, a risk variable acquisition module, a recommendation module, a setting module and a detection module. According to the method, the safety of the detection process is ensured through real-time risk assessment, and the adaptability and flexibility of the detection process are improved through personalized detection process recommendation.

Description

Technical Field

[0001] The present invention relates to the field of semiconductors, and in particular to a semiconductor device detection method and system based on collected data. Background Art

[0002] The semiconductor industry provides the electronic components that power electronic devices. With the advancement of technology, demand for semiconductor devices is growing, encompassing a wide range of applications, from smartphones, computers, and automobiles to industrial and medical equipment. Semiconductor devices include various types of transistors, integrated circuits (ICs), diodes, and microprocessors. The manufacturing process for these products involves multiple steps, including material preparation, photolithography, etching, doping, chemical vapor deposition (CVD), physical vapor deposition (PVD), metallization, and packaging. Each step has the potential to introduce defects or affect device performance, necessitating rigorous testing.

[0003] Semiconductor device testing refers to a series of inspections performed on semiconductor devices during or after production to ensure their performance, reliability, and compliance with design standards. These inspections typically include electrical performance testing, physical defect detection, and chemical composition analysis. Semiconductor device testing is crucial to ensuring product quality and reliability because it helps identify and eliminate defective products, reduces rework and returns, and protects brand reputation.

[0004] Existing semiconductor device testing technologies, such as Chinese Patent 201611217408.X, disclose an apparatus and method for detecting semiconductor device faults. This method compares the converted low voltage with preset first and second comparison thresholds, and determines whether the semiconductor device has failed based on the comparison result and preset conditions in a judgment module. However, this method has the following shortcomings: relying solely on voltage data cannot fully reflect the health status and potential risks of the device. If the risk response is not rapid enough, timely measures may not be taken before the fault causes system damage. Furthermore, it does not consider the preferences of test engineers, making it impossible to provide personalized test process recommendations.

[0005] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0006] In response to the problems in the related art, the present invention proposes a semiconductor device detection method and system based on collected data to overcome the above technical problems existing in the existing related art.

[0007] To this end, the specific technical solutions adopted in the present invention are as follows:

[0008] According to one aspect of the present invention, a semiconductor device detection method based on collected data is provided, the semiconductor device detection method based on collected data comprising the following steps:

[0009] S1. Collect physical and electrical characteristic data of the semiconductor device to be tested, historical test data of the same type of semiconductor devices, and test engineer preference information, and combine them to obtain real-time data.

[0010] S2. Classify the real-time data into risk variables within a normal operating range and an abnormal range, and obtain a classified real-time data and risk variable list.

[0011] S3. Calculate the potential failure probability, failure severity score, and emergency response index of the risk variables, and obtain a comprehensive risk index. Use intelligent algorithms to output parameter indicators and resource allocation during the semiconductor device inspection process.

[0012] S4. Determine whether the comprehensive risk index exceeds the alarm threshold. If it exceeds the threshold, an alarm signal is issued, and personalized detection process and environment settings are performed based on the parameter indicators and resource configuration generated during the semiconductor device detection process.

[0013] S5. Test the semiconductor device according to the personalized test process and environment settings, and generate a test report.

[0014] Classify real-time data into risk variables within normal operating range and abnormal range. The classified real-time data and risk variable lists include:

[0015] S21. Determine the normal operating range of various physical and electrical parameters of the semiconductor device;

[0016] S22. Setting abnormal thresholds to identify risk variables that exceed normal operating ranges;

[0017] S23. Conduct trend analysis on data of risk variables that are outside the normal operating range.

[0018] Furthermore, calculating the potential failure probability, failure severity score, and emergency response index of the risk variables and obtaining a comprehensive risk index, and using an intelligent algorithm to output parameter indicators and resource allocation during the semiconductor device inspection process includes the following steps:

[0019] S31. Collect real-time data of each risk variable, obtain the real-time data change trend, and predict the future state of the risk variable by establishing a statistical model to obtain the potential failure probability of each risk variable within a pre-set time period in the future;

[0020] S32. Define different fault levels based on the impact of risk variables on semiconductor device performance, and assign a score value to each fault level to indicate the degree of impact of the fault on overall production and performance;

[0021] S33. Evaluate the severity of the fault based on the current state and predicted future state of the risk variable and assign a corresponding fault severity score;

[0022] S34. Based on the impact of a fault on production line operations, assess the time required to take action to resolve the problem and assign a time-related indicator value to each risk variable based on the urgency of the fault resolution.

[0023] S35. Calculate emergency response indicators based on the potential failure probability, failure severity score, and time-related index values ​​of the failure to guide the priority of response measures;

[0024] S36. Assign weights to potential failure probabilities, failure severity scores, and emergency response indicators to reflect their relative importance in the risk assessment;

[0025] S37. Add the weighted values ​​of the potential failure probability, failure severity score, and emergency response index to obtain a comprehensive risk index for each risk variable, and rank the comprehensive risk indices of all risk variables to identify risk variables of concern.

[0026] S38. Based on the comprehensive risk index of risk variables and the preference information of inspection engineers, an intelligent algorithm is used to generate parameter indicators and resource allocation in the semiconductor device inspection process.

[0027] Furthermore, when the emergency response index is calculated by combining the potential failure probability, failure severity score and time-related index value, the calculation formula is:

[0028]

[0029] Where URI represents the emergency response indicator;

[0030] P represents the potential failure probability, S represents the failure severity score, T represents the time-related index value, P threshold A threshold value representing the probability of potential failure;

[0031] a, β, and γ represent the nonlinear weight exponents of potential failure probability, failure severity score, and time-related index value, respectively.

[0032] Furthermore, based on the comprehensive risk index of the risk variables and the preference information of the inspection engineers, the intelligent algorithm is used to generate parameter indicators and resource allocation in the semiconductor device inspection process, including the following steps:

[0033] S381. Standardize the data in the comprehensive risk index and the preference information of the test engineers, and select features related to parameter indicators and resource allocation in the semiconductor device testing process to obtain a data set to be processed;

[0034] S382, applying vector orthogonalization processing to convert the data set to be processed into several independent principal components;

[0035] S383. Determine the optimal number of nearest neighbors, and randomly divide the dataset to be processed into a training set and a test set, ensuring that both the training set and the test set contain the comprehensive risk index and the preference information of the inspection engineer, as well as the corresponding parameter indicators and resource allocation parameters;

[0036] S384. Using the features after vector orthogonalization and the optimal number of nearest neighbors, apply the K-nearest neighbor algorithm for training, and add new data to the training set during each prediction to obtain a trained recommendation model;

[0037] S385. For the new comprehensive risk index and the preference information of the testing engineer, use the trained recommendation model to make predictions;

[0038] S386. Generate targeted parameter indicators and resource configurations for the semiconductor device testing process based on the prediction results of the recommendation model.

[0039] Furthermore, after generating the parameter indicators and resource configuration for the targeted semiconductor device testing process, the following steps are included:

[0040] Use the test set to evaluate the recommendation effect of the recommendation model;

[0041] Adjust the number of nearest neighbors or reselect features based on the evaluation results to optimize the recommendation model;

[0042] Deploy the optimized recommendation model into the detection engineering environment.

[0043] Furthermore, determining the optimal number of nearest neighbors includes the following steps:

[0044] S3831. Randomly select several data objects from the data set to be processed as initial cluster centers to form m agents, and initialize the speed and position of the agents;

[0045] S3832. Calculate the distances from all data objects in each agent to the cluster center, and classify the data according to the nearest neighbor distance principle;

[0046] S3833. Calculate the fitness value of each agent, compare the fitness values, and update the optimal position of the agent;

[0047] S3834. Compare the fitness values ​​of all agents, update the global extreme value, and update the speed and position of the agent;

[0048] S3835, repeat S3832-S3834 until a good enough position is reached or the maximum number of iterations is reached;

[0049] S3836. Output the optimal cluster center and determine the optimal number of nearest neighbors.

[0050] Furthermore, outputting the optimal cluster center and determining the optimal number of nearest neighbors includes the following steps:

[0051] S38361. The cluster center corresponding to the global optimal solution is used as the optimal cluster center;

[0052] S38362. Determine the optimal number of nearest neighbors by running the cluster several times, using a different number of nearest neighbors each time, comparing the results of each run, and selecting the optimal number of nearest neighbors by evaluating the clustering quality.

[0053] Furthermore, performing personalized testing process and environment settings based on the generated parameter indicators and resource configuration during the semiconductor device testing process includes the following steps:

[0054] S41. Allocate personnel and testing resources according to the generated parameter indicators and resource configuration in the semiconductor device testing process;

[0055] S42, setting up the testing process and environment;

[0056] S43, converting the data of the detection process and environment settings into a data format to obtain visual format data;

[0057] S44. Select visualization tools and technology platforms to bind visualization format data with visual elements, and ensure that users can interact with visualization format data through the interface.

[0058] Furthermore, setting up the detection process and environment includes the following steps:

[0059] S421, setting a detection environment for semiconductor devices;

[0060] S422, setting parameters of the detection equipment;

[0061] S423. Determine the test steps, sequence and time schedule.

[0062] Furthermore, semiconductor devices are tested according to the personalized testing process and environment settings, and a test report is generated including:

[0063] S51. Testing semiconductor devices of the same type according to personalized testing procedures and environmental settings;

[0064] S52, collecting semiconductor device detection data, and identifying faults and anomalies in the semiconductor device detection data;

[0065] S52. Generate a test report based on the fault and abnormality identification results.

[0066] According to another aspect of the present invention, a semiconductor device detection system based on collected data is provided. The semiconductor device detection system based on collected data includes a real-time data collection module, a risk variable acquisition module, a recommendation module, a setting module and a detection module.

[0067] Among them, the real-time data collection module is used to collect the physical and electrical characteristic data of the semiconductor device to be tested, the historical detection data of the same type of semiconductor devices and the preference information of the detection engineers, and combine them to obtain real-time data.

[0068] The risk variable acquisition module is used to classify real-time data into risk variables within the normal operating range and the abnormal range, and obtain the classified real-time data and risk variable list.

[0069] The recommendation module is used to calculate the potential failure probability, failure severity score and emergency response index of risk variables, and obtain a comprehensive risk index. It also uses intelligent algorithms to output parameter indicators and resource allocation in the semiconductor device detection process.

[0070] The setting module is used to determine whether the comprehensive risk index exceeds the alarm threshold. If it exceeds the threshold, an alarm signal is issued, and personalized detection process and environment settings are performed based on the parameter indicators and resource configuration generated during the semiconductor device detection process.

[0071] The detection module is used to detect semiconductor devices according to personalized detection processes and environmental settings and generate detection reports.

[0072] The beneficial effects of the present invention are:

[0073] (1) The present invention provides a semiconductor device detection method and system based on collected data, which ensures the safety of the detection process through real-time risk assessment, while personalized detection process recommendations improve the adaptability and flexibility of the detection process.

[0074] (2) By classifying real-time data into risk variables within normal and abnormal ranges, we identify risk variables that require special attention and further analysis. We calculate the potential failure probability, failure severity, and emergency response indicators of the risk variables to generate a comprehensive risk index, which provides input for intelligent algorithms to optimize detection parameters and resource allocation. Furthermore, we conduct actual semiconductor device testing according to personalized testing processes and environmental settings, and generate test reports to provide a basis for quality control and subsequent decision-making.

[0075] (3) Based on the comprehensive risk index of risk variables and the test engineer's preference information, this invention uses an intelligent algorithm to generate parameter indicators and resource allocation for the semiconductor device testing process. This data is then standardized and principal component analyzed to reduce dimensionality and improve model performance. Through optimization techniques, the optimal K value is determined, the data set is segmented, the recommendation model is trained, and predictions are performed, thereby improving the prediction accuracy and applicability of the recommendation model.

[0076] (4) The present invention enhances the user's interactive experience and the transparency of the process by allocating personnel and resources, setting the detection process and environment, converting the setting data into a visual format, and using visualization tools to present the detection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0078] Figure 1 is a flow chart of a semiconductor device detection method based on collected data according to an embodiment of the present invention;

[0079] Figure 2 The diagram is a principle block diagram of a semiconductor device detection system based on collected data according to an embodiment of the present invention.

[0080] In the picture:

[0081] 1. Real-time data collection module; 2. Risk variable acquisition module; 3. Recommendation module; 4. Setting module; 5. Detection module. DETAILED DESCRIPTION

[0082] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. By referring to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0083] According to an embodiment of the present invention, a semiconductor device detection method and system based on collected data are provided.

[0084] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a semiconductor device detection method based on collected data is provided, and the semiconductor device detection method based on collected data includes the following steps:

[0085] S1. Collect physical and electrical characteristic data of the semiconductor device to be tested, historical test data of the same type of semiconductor devices, and test engineer preference information, and combine them to obtain real-time data.

[0086] Among them, physical parameters of semiconductor devices are measured and recorded, such as size, weight, material composition, etc. Electrical characteristics of semiconductor devices, such as resistance, capacitance, leakage current, threshold voltage, etc., are measured by test equipment.

[0087] Extract historical test data for the same type of device from databases or record archives. Communicate with test engineers to understand their preferences and requirements for test processes, parameter settings, etc.

[0088] For example, a batch of newly produced microprocessors is tested, and their physical and electrical data, such as current and voltage, are collected. This data is then used as a reference for test data from similar microprocessors in the past. At the same time, test engineers provide information about their test preferences, such as whether they are more concerned with current stability.

[0089] S2. Classify the real-time data into risk variables within normal operating range and abnormal range, and obtain a list of classified real-time data and risk variables. This specifically includes the following steps:

[0090] Determine the normal operating ranges for various physical and electrical parameters of semiconductor devices based on design specifications, manufacturer data, historical performance data, or industry standards.

[0091] Set anomaly thresholds to identify risk variables that are outside the normal operating range. Filter real-time data and label each data point as normal or abnormal based on whether it falls within the predefined normal operating range.

[0092] Identify key risk variables from abnormal data that indicate early signs of failure or performance issues. Perform trend analysis on data within the abnormal range to identify whether there are persistent or gradually worsening problems.

[0093] In a further embodiment, the real-time data is classified into risk variables within a normal operating range and an abnormal range, and the classified real-time data and risk variable list includes:

[0094] S21. Determine the normal operating range of various physical and electrical parameters of the semiconductor device;

[0095] S22. Setting abnormal thresholds to identify risk variables that exceed normal operating ranges;

[0096] S23. Conduct trend analysis on data of risk variables that are outside the normal operating range.

[0097] S3. Calculate the potential failure probability, failure severity score, and emergency response index of the risk variables, and obtain a comprehensive risk index. Use intelligent algorithms to output parameter indicators and resource allocation during the semiconductor device inspection process.

[0098] In a further embodiment, calculating the potential failure probability, failure severity score, and emergency response index of the risk variables and obtaining a comprehensive risk index, and using an intelligent algorithm to output parameter indicators and resource allocation during the semiconductor device inspection process includes the following steps:

[0099] S31. Collect real-time data of each risk variable, obtain the real-time data change trend, and predict the future state of the risk variable by establishing a statistical model to obtain the potential failure probability of each risk variable within a pre-set time period in the future.

[0100] Statistical models are mathematical models that use historical data to analyze relationships between variables and use these relationships to predict future events or behaviors. In semiconductor device testing, statistical models are used to predict whether specific risk variables (such as current, voltage, and temperature) are likely to exhibit abnormalities in the future.

[0101] Select an appropriate statistical model to analyze risk variables. Common models include linear regression, logistic regression, time series analysis, and survival analysis. The statistical model is trained and validated to produce a predicted value for each risk variable.

[0102] For example, to predict whether a semiconductor device will fail in the future, a statistical model calculates the probability of failure based on the current value of a risk variable. If this probability exceeds a threshold, the risk of the device failing in the future is high.

[0103] S32. Define different fault levels (e.g., minor, moderate, severe) based on the impact of risk variables on semiconductor device performance, and assign a score to each fault level to indicate the degree of impact of the fault on overall production and performance.

[0104] Among them, when defining different fault levels based on the impact of risk variables on the performance of semiconductor devices, the performance standards and key performance indicators of semiconductor devices are determined, including power loss, switching frequency, maximum current carrying capacity, thermal stability, etc. Assess the degree of impact of risk variables (such as voltage fluctuations, temperature rise, current anomalies, etc.) on the above performance standards. Conduct a failure mode impact analysis to determine the impact of different failure modes on device performance. Establish a level classification standard based on the severity of the impact of risk variables on device performance. For example, a minor fault may only cause a slight degradation in performance, while a serious fault may cause the device to fail completely. Define fault levels, such as minor (device performance is slightly degraded, but does not affect the main functions), medium (performance is significantly degraded, which may affect certain functions), and serious (device failure or safety risks).

[0105] S33. Evaluate the severity of the fault based on the current state and predicted future state of the risk variable and assign a corresponding fault severity score;

[0106] The corresponding fault severity level is determined based on the current and predicted status of the risk variable. For example, if a risk variable shows a trend of continued deterioration, it may be assessed as a moderate or severe fault. Each fault severity level is assigned a score. This score should reflect the potential impact of the fault; for example, a minor fault might be assigned a low score, while a severe fault might be assigned a high score.

[0107] S34. Based on the impact of a fault on production line operations, assess the time required to take action to resolve the problem and assign a time-related indicator value to each risk variable based on the urgency of the fault resolution.

[0108] Based on the nature and severity of the fault, the actual time required to resolve the issue (e.g., repair or replacement of a part) is estimated. This takes into account the time required for diagnosis, obtaining replacement parts, and actual repair and testing. Each risk variable is assigned a time-related indicator value that reflects the time required from problem discovery to complete resolution. For example, labels such as "Urgent," "High Priority," "Medium Priority," and "Low Priority" could be used.

[0109] S35. Calculate emergency response indicators based on the potential failure probability, failure severity score, and time-related index values ​​of the failure to guide the priority of response measures.

[0110] When calculating the emergency response index by combining the potential failure probability, failure severity score and time-related index value, the calculation formula is:

[0111]

[0112] Where URI represents the emergency response indicator;

[0113] P represents the potential failure probability, S represents the failure severity score, T represents the time-related index value, P threshold A threshold value representing the probability of potential failure;

[0114] a, β, and γ represent the nonlinear weight exponents of potential failure probability, failure severity score, and time-related index value, respectively.

[0115] S36. Assign weights to potential failure probabilities, failure severity scores, and emergency response indicators to reflect their relative importance in the risk assessment.

[0116] S37. Add the weighted values ​​of the potential failure probability, failure severity score, and emergency response index to obtain a comprehensive risk index for each risk variable, and rank the comprehensive risk indices of all risk variables to identify risk variables of special concern.

[0117] S38. Based on the comprehensive risk index of risk variables and the preference information of inspection engineers, an intelligent algorithm is used to generate parameter indicators and resource allocation in the semiconductor device inspection process.

[0118] In a further embodiment, based on the comprehensive risk index of the risk variables and the preference information of the inspection engineer, using an intelligent algorithm to generate parameter indicators and resource allocation in the semiconductor device inspection process includes the following steps:

[0119] S381. Standardize the data in the comprehensive risk index and the preference information of the testing engineer, and select features related to the parameter indicators and resource allocation in the semiconductor device testing process to obtain the data set to be processed. For example, equipment failure rate, historical accident frequency, engineer sensitivity to cost, etc. are selected as features.

[0120] S382. Use vector orthogonalization to convert the dataset to be processed into several independent principal components. Principal component analysis identifies the main directions of variation in the data and projects the original data onto these directions, forming a new, linearly uncorrelated set of features. These new features, called principal components, are used in place of the original features for model training and prediction, often improving algorithm efficiency and performance.

[0121] S383. Determine the optimal number of nearest neighbors (K value), and randomly divide the data set to be processed into a training set and a test set, and ensure that both the training set and the test set contain the comprehensive risk index and the preference information of the inspection engineer, as well as the corresponding parameter indicators and resource configuration parameters.

[0122] S384. Using the orthogonalized features and the optimal number of nearest neighbors, apply the K-nearest neighbor algorithm for training. During each prediction, new data is added to the training set to obtain a trained recommendation model. The K-nearest neighbor algorithm is an example-based learning algorithm that predicts the classification or regression value of a new sample based on its similarity to samples in the training set.

[0123] S385. For new comprehensive risk indexes and testing engineer preference information, use the trained recommendation model to make predictions; use the predicted historical cases that are most similar to the new inputs to recommend parameter indicators and resource allocations accordingly.

[0124] S386. Generate targeted parameter indicators and resource allocation for the semiconductor device testing process based on the prediction results of the recommendation model. This takes into account the comprehensive risk index and the test engineer's preferences to optimize the testing process and improve efficiency and effectiveness.

[0125] By calculating the probability of potential failure, problems that may occur in semiconductor devices can be identified in advance, so that preventive measures can be taken before the failure actually occurs, avoiding potential risks from evolving into actual failures and reducing downtime and economic losses.

[0126] Fault severity scores can help quantify the impact of semiconductor device failures on the production process, making the inspection process more targeted. This helps prioritize issues that have the greatest impact on production and ensures that resources are properly allocated to the most critical tasks.

[0127] Emergency response indicators guide the prioritization of response measures based on the urgency of semiconductor device failures. This means faster responses to issues requiring immediate resolution, minimizing the impact on production line operations.

[0128] In a further embodiment, generating parameter indicators and resource configurations for a targeted semiconductor device inspection process includes the following steps:

[0129] Use the test set to evaluate the recommendation effect of the recommendation model; use appropriate evaluation indicators such as accuracy, recall, F1 score, ROC curve, etc.

[0130] Adjust the number of nearest neighbors or reselect features based on the evaluation results to optimize the recommendation model; feature selection is based on the understanding of the problem and the importance of the features, using feature selection algorithms or feature importance scores to assist in selection.

[0131] Deploy the optimized recommendation model into the inspection engineering environment, for example, integrate it into the inspection engineer's work platform.

[0132] In a further embodiment, determining the optimal number of nearest neighbors comprises the following steps:

[0133] S3831. Randomly select several data objects in the data set to be processed as initial cluster centers to form m agents, and initialize the speed and position of the agents; the position of the agent represents a possible solution (the position of the cluster center).

[0134] S3832. Calculate the distances from all data objects in each agent to the cluster center, and classify the data according to the nearest neighbor distance principle, that is, each data point is assigned to the category represented by its nearest cluster center.

[0135] S3833. Calculate the fitness value of each agent, compare the fitness values, and update the optimal position of the agent; the fitness value is based on a pre-evaluation standard (such as minimizing the distance within the cluster), and the optimal position of each agent is updated according to the fitness value.

[0136] S3834. Compare the fitness values ​​of all agents, update the global extreme value, and update the speed and position of the agent to explore new possible solutions in the next round of iteration.

[0137] S3835. Repeat S3832-S3834 until a good enough position is reached or the maximum number of iterations is reached.

[0138] S3836. Output the optimal cluster center and determine the optimal number of nearest neighbors.

[0139] In a further embodiment, outputting the optimal cluster center and determining the optimal number of nearest neighbors includes the following steps:

[0140] S38361. The cluster center corresponding to the global optimal solution is used as the optimal cluster center. S38362. The optimal number of nearest neighbors is determined by running the cluster several times, using a different number of nearest neighbors each time, and comparing the results of each run. The optimal number of nearest neighbors is selected by evaluating the clustering quality, such as using the Silhouette Coefficient or other clustering effectiveness indicators.

[0141] S4. Determine whether the comprehensive risk index exceeds the alarm threshold. If it exceeds the threshold, an alarm signal is issued, and personalized detection process and environment settings are performed based on the parameter indicators and resource configuration generated during the semiconductor device detection process.

[0142] In a further embodiment, performing personalized testing process and environment settings based on generated parameter indicators and resource configurations during semiconductor device testing includes the following steps:

[0143] S41. Allocate personnel and testing resources based on the parameter indicators and resource allocation generated during the semiconductor device testing process; comprehensively consider the complexity of the testing task, the availability of testing resources (such as equipment, instruments and tools), and the skills and experience of the personnel to ensure that each testing task has appropriate personnel and resource support.

[0144] S42. Set up the testing process and environment.

[0145] S43. Convert the data of the detection process and environment settings into a visual format, such as JSON, CSV, or XML, to ensure that the data can be effectively processed by visualization tools and technology platforms.

[0146] S44. Select visualization tools and technology platforms, such as Tableau, Power BI, D3.js, etc., to bind visualization format data with visual elements and ensure that users can interact with visualization format data through the interface.

[0147] In a further embodiment, setting up the detection process and environment includes the following steps:

[0148] S421. Set the inspection environment for semiconductor devices, including temperature, humidity, clean room conditions, etc.

[0149] S422. Set the parameters of the testing equipment, such as voltage, current, test frequency, etc.

[0150] S423. Determine the test steps, sequence and time schedule.

[0151] S5. Test the semiconductor device according to the personalized test process and environment settings, and generate a test report.

[0152] This involves analyzing test results and, if any failures are detected, determining the cause. The test report is reviewed by the responsible person to ensure accuracy and completeness. The test report is submitted to the relevant engineers, project management team, or client to ensure all stakeholders understand the test results.

[0153] In a further embodiment, testing a semiconductor device according to a personalized testing process and environment settings and generating a test report includes:

[0154] S51. Detect semiconductor devices of the same type according to personalized detection procedures and environmental settings.

[0155] S52, collecting semiconductor device detection data, and identifying faults and anomalies in the semiconductor device detection data;

[0156] Specifically, the electrical characteristic data of the semiconductor device is collected after the personalized inspection process and environment setting. The corresponding inspection data of the previous semiconductor device of the same type is retrieved and recorded for comparison with the current data.

[0157] Determine the normal operating range and define the normal operating range for each electrical parameter based on design specifications, manufacturer data, historical performance data, or industry standards.

[0158] The collected real-time data is filtered and each data point is labeled as normal or abnormal, depending on whether it falls within the predefined normal operating range.

[0159] S52. Generate a test report based on the fault and abnormality identification results.

[0160] like Figure 2 As shown, according to another embodiment of the present invention, a semiconductor device detection system based on collected data is provided, the semiconductor device detection system based on collected data includes a real-time data collection module 1, a risk variable acquisition module 2, a recommendation module 3, a setting module 4 and a detection module 5;

[0161] The real-time data collection module 1 is used to collect the physical and electrical characteristic data of the semiconductor device to be tested, the historical test data of the same type of semiconductor devices and the preference information of the test engineers, and combine them to obtain real-time data.

[0162] The risk variable acquisition module 2 is used to classify the real-time data into risk variables within the normal operating range and the abnormal range, and obtain the classified real-time data and the risk variable list.

[0163] Recommended module 3 is used to calculate the potential failure probability, failure severity score and emergency response index of risk variables, and obtain a comprehensive risk index, and use intelligent algorithms to output parameter indicators and resource allocation in the semiconductor device detection process.

[0164] The setting module 4 is used to determine whether the comprehensive risk index exceeds the alarm threshold. If it exceeds the threshold, an alarm signal is issued, and personalized detection process and environment settings are performed according to the parameter indicators and resource configuration generated during the semiconductor device detection process.

[0165] The detection module 5 is used to detect the semiconductor device according to the personalized detection process and environment settings, and generate a detection report.

[0166] In summary, the present invention provides a semiconductor device detection method and system based on collected data, which ensures the safety of the detection process through real-time risk assessment, and personalized detection process recommendation improves the adaptability and flexibility of the detection process. By dividing real-time data into risk variables within normal and abnormal ranges, risk variables that require special attention and further analysis are determined. The potential failure probability, failure severity and emergency response indicators of the risk variables are calculated to generate a comprehensive risk index, which provides input for the intelligent algorithm to optimize the detection parameters and resource allocation. At the same time, actual semiconductor device detection is performed according to the personalized detection process and environmental settings, and a detection report is generated to provide a basis for quality control and subsequent decision-making. Based on the comprehensive risk index of the risk variables and the preference information of the detection engineer, the present invention uses an intelligent algorithm to generate parameter indicators and resource allocation in the semiconductor device detection process, standardizes the data and performs principal component analysis to reduce the dimension and improve the model performance. Through optimization technology, the optimal K value is determined, the data set is segmented, the recommendation model is trained, and prediction is performed, thereby improving the prediction accuracy and applicability of the recommendation model. The present invention enhances the user's interactive experience and process transparency by allocating personnel and resources, setting the detection process and environment, converting the setting data into a visual format, and using visualization tools to present the detection process.

[0167] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A semiconductor device detection method based on collected data, characterized in that: The semiconductor device detection method based on collected data comprises the following steps: S1. Collect physical and electrical characteristic data of the semiconductor device to be tested, historical test data of the same type of semiconductor devices, and preference information of test engineers, and combine them to obtain real-time data; S2. Classify the real-time data into risk variables within a normal operating range and an abnormal range, and obtain a classified real-time data and a risk variable list; S3. Calculate the potential failure probability, failure severity score and emergency response index of the risk variables, and obtain a comprehensive risk index, and use intelligent algorithms to output parameter indicators and resource allocation in the semiconductor device detection process; S4. Determine whether the comprehensive risk index exceeds the alarm threshold. If it exceeds the threshold, an alarm signal is issued, and a personalized detection process and environment setting are performed according to the parameter indicators and resource configuration generated in the semiconductor device detection process; S5. Test the semiconductor device according to the personalized test process and environment settings, and generate a test report; The real-time data is classified into risk variables within a normal operating range and an abnormal range, and the classified real-time data and risk variable list are obtained, including: S21, determining the normal operating range of various physical and electrical parameters of the semiconductor device; S22. Setting abnormal thresholds to identify risk variables that exceed normal operating ranges; S23. Perform trend analysis on data of risk variables that are outside the normal operating range.

2. A semiconductor device detection method based on collected data according to claim 1, characterized in that: The method of calculating the potential failure probability, failure severity score and emergency response index of the risk variables, obtaining a comprehensive risk index, and using an intelligent algorithm to output parameter indicators and resource configuration in the semiconductor device detection process includes the following steps: S31. Collect the real-time data of each risk variable, obtain the change trend of the real-time data, and predict the future state of the risk variable by establishing a statistical model to obtain the potential failure probability of each risk variable in a pre-set time period in the future; S32. Define different fault levels based on the impact of risk variables on semiconductor device performance, and assign a score value to each fault level to indicate the degree of impact of the fault on overall production and performance; S33. Evaluate the severity of the fault based on the current state and predicted future state of the risk variable, and give a corresponding fault severity score; S34. Based on the impact of the fault on the production line operation, evaluate the time required to take measures to solve the problem, and assign time-related indicator values ​​to each risk variable based on the urgency of fault handling; S35. Calculate the emergency response index based on the potential failure probability, failure severity score and time-related index value of the failure to guide the priority of response measures; S36. Assign weights to potential failure probabilities, failure severity scores, and emergency response indicators to reflect their relative importance in the risk assessment; S37, adding the weighted values ​​of the potential failure probability, the failure severity score and the emergency response index to obtain a comprehensive risk index for each risk variable, and sorting the comprehensive risk indexes of all risk variables to identify the risk variables of concern; S38. Based on the comprehensive risk index of risk variables and the preference information of inspection engineers, an intelligent algorithm is used to generate parameter indicators and resource allocation in the semiconductor device inspection process.

3. A semiconductor device detection method based on collected data according to claim 2, characterized in that: When the emergency response index is calculated by combining the potential failure probability, the failure severity score and the time-related index value, the calculation formula is: In the formula, URI represents the emergency response indicator; P represents the potential failure probability, S represents the failure severity score, T represents the time-related indicator value, P threshold A threshold value representing the probability of potential failure; a, β, and γ represent the nonlinear weight index of potential failure probability, failure severity score, and time-related index value, respectively.

4. A semiconductor device detection method based on collected data according to claim 3, characterized in that: The method of using an intelligent algorithm to generate parameter indicators and resource allocation in a semiconductor device testing process based on a comprehensive risk index of risk variables and preference information of testing engineers includes the following steps: S381. Standardize the data in the comprehensive risk index and the preference information of the test engineer, and select features related to parameter indicators and resource allocation in the semiconductor device testing process to obtain a data set to be processed; S382, applying vector orthogonalization processing to convert the data set to be processed into a number of independent principal components; S383. Determine the optimal number of nearest neighbors, and randomly divide the data set to be processed into a training set and a test set, and ensure that both the training set and the test set contain the comprehensive risk index and the preference information of the inspection engineer, as well as the corresponding parameter indicators and resource configuration parameters; S384, using the features after vector orthogonalization and the optimal number of nearest neighbors, applying the K nearest neighbor algorithm for training, and adding new data to the training set at each prediction, and obtaining a recommended model after training; S385. For the new comprehensive risk index and the preference information of the testing engineer, use the trained recommendation model to make predictions; S386. Generate targeted parameter indicators and resource configurations in the semiconductor device testing process based on the prediction results of the recommended model.

5. A semiconductor device detection method based on collected data according to claim 4, characterized in that: The generation of parameter indicators and resource configuration in the targeted semiconductor device detection process includes the following steps: Use the test set to evaluate the recommendation effect of the recommendation model; Adjust the nearest neighbor value or reselect features based on the evaluation results to optimize the recommendation model; Deploy the optimized recommendation model into the detection engineering environment.

6. A semiconductor device detection method based on collected data according to claim 5, characterized in that: Determining the optimal nearest neighbor quantity value comprises the following steps: S3831, randomly selecting a number of data objects in the data set to be processed as initial cluster centers, forming m agents, and initializing the speed and position of the agents; S3832, calculating the distance from all data objects in each agent to the cluster center, and classifying the data according to the nearest neighbor distance principle; S3833, calculating the fitness value of each agent, and comparing the fitness values, and updating the optimal position of the agent; S3834, comparing the fitness values ​​of all agents, updating the global extreme value, and updating the speed and position of the agent; S3835, repeat S3832-S3834 until a good enough position is reached or the maximum number of iterations is reached; S3836. Output the optimal cluster center and determine the optimal number of nearest neighbors.

7. A semiconductor device detection method based on collected data according to claim 6, characterized in that: The outputting of the optimal cluster center and determining the optimal number of nearest neighbors includes the following steps: S38361. Taking the cluster center corresponding to the global optimal solution as the optimal cluster center; S38362. Determine the optimal number of nearest neighbors by running several times, using a different number of nearest neighbors each time, and compare the results of each run, and select the optimal number of nearest neighbors by evaluating the clustering quality.

8. The semiconductor device detection method based on collected data according to claim 7, characterized in that: The personalized testing process and environment setting according to the parameter indicators and resource configuration generated in the semiconductor device testing process includes the following steps: S41, allocating personnel and testing resources according to the generated parameter indicators and resource configuration in the semiconductor device testing process; S42, setting up the testing process and environment; S43, converting the data of the detection process and the environment setting into a data format to obtain visual format data; S44. Select visualization tools and technology platforms to achieve the binding of visualization format data with visual elements and ensure that users can interact with visualization format data through the interface; The setting of the detection process and environment includes the following steps: S421, setting a detection environment for semiconductor devices; S422, setting parameters of the detection equipment; S423. Determine the test steps, sequence and time schedule.

9. A semiconductor device detection method based on collected data according to claim 8, characterized in that: The testing of semiconductor devices according to the personalized testing process and environment settings and generating a testing report include: S51, testing semiconductor devices of the same type according to personalized testing procedures and environment settings; S52, collecting semiconductor device detection data, and identifying faults and abnormalities of the semiconductor device detection data; S52: Generate a test report based on the fault and abnormality identification results.

10. A semiconductor device detection system based on collected data, characterized in that: Used to implement the semiconductor device detection method based on collected data as described in any one of claims 1 to 9, the semiconductor device detection system based on collected data includes a real-time data collection module, a risk variable acquisition module, a recommendation module, a setting module and a detection module; The real-time data collection module is used to collect the physical and electrical characteristic data of the semiconductor device to be tested, the historical test data of the same type of semiconductor devices and the preference information of the test engineers, and combine them to obtain the real-time data; The risk variable acquisition module is used to classify the real-time data into risk variables within a normal operating range and an abnormal range, and obtain the classified real-time data and a risk variable list; The recommendation module is used to calculate the potential failure probability, failure severity score and emergency response index of the risk variable, and obtain a comprehensive risk index, and use an intelligent algorithm to output parameter indicators and resource configuration in the semiconductor device detection process; The setting module is used to determine whether the comprehensive risk index exceeds the alarm threshold. If it exceeds the threshold, an alarm signal is issued, and personalized detection process and environment settings are performed according to the parameter indicators and resource configuration generated in the semiconductor device detection process; The detection module is used to detect semiconductor devices according to personalized detection procedures and environmental settings, and generate a detection report.

Images