Prediction method, device and computer-readable storage medium

Abstract

A prediction method for predicting the yield of a batch of wafers. During a training period, multiple wafer acceptance test (WAT) sample data of multiple wafers are received; a wafer probe test (CP) is performed on the wafers to generate multiple CP sample data; and the WAT sample data and CP sample data are input to a machine learning model. The machine learning model calculates a correlation between the WAT sample data and the CP sample data. During a prediction period, WAT measurement data is input to the machine learning model. The machine learning model predicts the yield of the batch of wafers based on the correlation and the WAT measurement data.

Description

Technical Field

[0001] This invention relates to a prediction method, and more particularly to a prediction method for wafer yield. Prior Technology

[0002] After wafer manufacturing is completed, the wafer manufacturer provides the entire batch of wafers to the testing company. The testing company performs tests on all dies of each wafer to determine the wafer yield. However, the testing process involves many tests. Testing each die individually would be extremely time-consuming and labor-intensive. Summary of the Invention

[0003] This invention provides a prediction apparatus for predicting the yield of a batch of wafers, comprising a storage circuit, an input / output interface, and a processing circuit. The storage circuit stores a machine learning model. The input / output interface receives complex Wafer Acceptance Test (WAT) sample data and complex Wafer Probe (CP) sample data. The processing circuit reads from the storage circuit to load the machine learning model. During a training period, the processing circuit provides WAT sample data and CP sample data to the machine learning model. The machine learning model calculates a correlation between the WAT sample data and the CP sample data. During a prediction period, the input / output interface receives WAT measurement data, and the processing circuit inputs the WAT measurement data to the machine learning model. The machine learning model predicts the yield of the batch of wafers based on the correlation and the WAT measurement data.

[0004] This invention further provides a prediction method for predicting the yield of a batch of wafers. During a training period, multiple wafer acceptance test (WAT) sample data of multiple wafers are received; a wafer probe test (CP) is performed on the wafers to generate multiple CP sample data; and the WAT sample data and CP sample data are input to a machine learning model. The machine learning model calculates the correlation between the WAT sample data and the CP sample data. During a prediction period, WAT measurement data is input to the machine learning model. The machine learning model predicts the yield of the batch of wafers based on the correlation and the WAT measurement data.

[0005] The prediction method of this invention can be implemented by the prediction device of this invention, which is hardware or firmware capable of performing specific functions, or it can be implemented by recording code in a recording medium and combined with specific hardware. When the code is loaded and executed by an electronic device, processor, computer or machine, the electronic device, processor, computer or machine becomes the prediction device for implementing this invention. Simple Explanation of the Diagram

[0006] Figure 1 is a flowchart illustrating the prediction method of the present invention. Figure 2 is a schematic diagram of the prediction device of the present invention. Implementation

[0007] To make the objectives, features, and advantages of this invention more apparent and understandable, embodiments are provided below, along with detailed descriptions in conjunction with the accompanying drawings. This specification provides different embodiments to illustrate the technical features of different implementations of the invention. The configuration of elements in the embodiments is for illustrative purposes only and is not intended to limit the invention. Furthermore, the repetition of some reference numerals in the embodiments is for simplification and does not imply any correlation between different embodiments.

[0008] Figure 1 is a schematic flowchart of the prediction method of the present invention. The prediction method of the present invention is used to predict the yield of a batch of wafers. The batch of wafers has a plurality of wafers. For example, each batch of wafers may have 25 wafers, and each wafer has a plurality of dies. In one possible embodiment, the prediction method of the present invention can predict the die yield of each wafer. The prediction method of the present invention can exist through program code. The program code may be stored in a computer-readable storage medium. When the program code on the computer-readable storage medium is loaded and executed by a machine, the machine becomes a prediction device for implementing the present invention.

[0009] During training 110, multiple wafer acceptance test (WAT) data are received (step 111). In one possible embodiment, the WAT data is provided by the wafer foundry. The wafer foundry tests each batch of wafers to generate WAT data.

[0010] For example, suppose each batch of wafers has 25 wafers, each wafer has 6 test points, and the wafer manufacturer performs 100 tests on each test point. In this example, each WAT record records the test results of 25 wafers, meaning each WAT record has 25 * 6 * 100 test results. In this embodiment, the multiple WAT records in step 111 refer to the test results of multiple batches of wafers. For ease of explanation, the WAT records during training 110 are referred to as WAT sample records.

[0011] In some embodiments, the manufacturing specifications of each batch of wafers may differ. For example, the first batch of wafers may come from a first process route, which may be used to produce 55-nanometer wafers, and the second batch of wafers may come from a second process route, which may be used to produce 65-nanometer wafers. In this example, each WAT record documents the process route information for that batch of wafers.

[0012] During training 110, a chip probing (CP) test is performed on the complex wafers recorded in the WAT sample data to generate complex CP sample data (step 112). In one possible embodiment, if the first WAT sample data is the test result of the first batch of wafers, then step 112 performs a CP test on each wafer of the first batch of wafers. Since the first batch of wafers includes a complex number of wafers, step 112 generates complex CP sample data after completing the CP test.

[0013] In one possible embodiment, the CP testing operation performs multiple electrical tests on each die of each wafer. Assume the CP testing operation includes 100 test items, each wafer has 1000 dies, and each batch of wafers has 25 wafers. After the CP testing operation, a data log is generated. Each data log includes the electrical test results for each wafer in each batch. For example, each data log may include 100*1000*25 electrical test results. In this example, each data log serves as a CP sample data.

[0014] During training 110, WAT sample data and CP sample data are input to a machine learning model (step 113). In one possible embodiment, the machine learning model calculates the WAT sample data and the CP sample data to generate a correction. For example, this correction may include the correlation between a specific parameter (e.g., Rs_P2) in the WAT sample data and a test item (e.g., RC22M) in the CP sample data. The larger the specific parameter (e.g., Rs_P2), the more likely the test item (e.g., RC22M) is to fail, such as if the test result is not within a normal range.

[0015] In some embodiments, the machine learning model generates a correlation based on abnormal electrical test results from WAT and CP sample data. For example, suppose a specific test item (e.g., RC22M) in a portion of the CP sample data shows an abnormal result. In this example, the machine learning model determines which test result in the WAT sample data is correlated with the abnormal result of the specific test item. Suppose a specific parameter (e.g., Rs_P2) in the WAT sample data is correlated with the abnormal test result of a specific test item in the CP sample data. In this example, the machine learning model establishes a correlation between a specific parameter (e.g., Rs_P2) in the WAT sample data and a specific test item (e.g., RC22M) in the CP sample data.

[0016] Next, during a prediction period 120, WAT data is received (step 121). In one possible embodiment, upon receiving a batch of wafers from the wafer manufacturer, the wafer manufacturer also provides the WAT data for that batch of wafers. For ease of explanation, the WAT data during the prediction period is referred to as WAT measurement data. In one possible embodiment, the WAT measurement data and the WAT sample data are provided by the same wafer manufacturer.

[0017] Input WAT measurement data into the trained machine learning model (step 122). In some embodiments, it is assumed that during training period 110, step 113 trains the corresponding machine learning model based on the production line data recorded by the WAT sample data. When the production line data recorded by a first WAT sample data is related to the 55nm process, step 113 inputs the first WAT sample data and the corresponding first CP sample data into a first machine learning model. When the production line data recorded by a second WAT sample data is related to the 65nm process, step 113 inputs the second WAT sample data and the corresponding second CP sample data into a second machine learning model. When the production line data recorded by a third WAT sample data is related to the 55nm process, step 113 inputs the third WAT sample data and the corresponding third CP sample data into the first machine learning model. In this example, step 113 trains both the first and second machine learning models. Therefore, during prediction period 120, step 122 selects the corresponding machine learning model based on the production line data recorded by the WAT measurement data. For example, when the production line data recorded by the WAT measurement data is related to the 55-nanometer process, step 122 selects the first machine learning model and inputs the WAT measurement data into the first machine learning model.

[0018] Next, a machine learning model is used to calculate the correlation and WAT measurement data to predict the yield of the batch of wafers recorded in the WAT measurement data (step 123). Since the correlation represents the relationship and strength between the test items of the WAT sample data and the test items of the CP sample data, the wafer yield can be predicted based on the correlation.

[0019] For example, suppose the correlation indicates that when a specific parameter (e.g., Rs_P2) in the WAT sample data exceeds a critical value, the corresponding wafer fails a specific test item (e.g., RC22M) in the CP testing operation. In this example, when the machine learning model learns that a specific parameter (e.g., Rs_P2) in the WAT measurement data exceeds a critical value, step 123 directly marks the corresponding wafer as having failed the specific test item. Since the wafer does not actually need to undergo CP testing, testing time and manpower can be significantly reduced.

[0020] In other embodiments, step 123 further predicts the location of defective dies. For example, after performing a CP test, in addition to generating CP sample data, a CP map is also generated. This CP map shows the location of defective dies. Therefore, during training 110, if the CP map is also input into the machine learning model, the correlation generated by the machine learning model includes location information. During prediction 120, step 123 predicts not only the yield of each wafer in the batch but also the location of defective dies on each wafer.

[0021] In some embodiments, the CP test operation includes a plurality of test items, one portion of which corresponds to a first product, and one portion of which corresponds to a second product. The present invention does not limit the types of the first and second products. In one possible embodiment, both the first and second products are functional circuits used to provide a preset function. Taking the first product as an example, the first product may be a conversion circuit (such as an ADC or DAC) providing a conversion function. In another possible embodiment, the first product is a control circuit (such as a DMA controller) used to provide a control function. In some embodiments, step 123 further predicts the yield of the first and second products in a batch of wafers.

[0022] Figure 2 is a schematic diagram of the prediction device of the present invention. As shown, the prediction device 200 is used to predict the yield of a batch of wafers and includes a processing circuit 210 and a storage circuit 220. The storage circuit 220 stores a machine learning model (ML). In one possible embodiment, the storage circuit 220 has a non-volatile memory for storing the machine learning model ML.

[0023] Processing circuit 210 reads from storage circuit 220 to load machine learning model ML. In this embodiment, processing circuit 210 trains machine learning model ML using training data DTR. Training data DTR includes complex WAT sample data SD_W1~SD_Wn and complex CP sample data SD_C1~SD_Cn. During a training period, processing circuit 210 loads machine learning model ML and inputs WAT sample data SD_W1~SD_Wn and complex CP sample data SD_C1~SD_Cn to machine learning model ML to train machine learning model ML. Machine learning model ML calculates WAT sample data SD_W1~SD_Wn and CP sample data SD_C1~SD_Cn to generate a correlation coefficient of return (CORR). In a possible embodiment, processing circuit 210 writes the trained machine learning model ML and the CORR to storage circuit 220.

[0024] In other embodiments, the training data DTR further includes production line data PR. The processing circuit 210 selects different machine learning models based on different production line data PRs. In this example, the storage circuit 220 has a complex machine learning model to predict the wafer yield of different production line data PRs. In some embodiments, the production line data PRs are recorded in WAT sample data SD_W1~SD_Wn.

[0025] In one possible embodiment, the training data DTR further includes product data NM, such as product name (IP name). The product data NM may be recorded in CP sample data SD_C1~SD_Cn. In this example, the CP sample data SD_C1~SD_Cn consists of multiple electrical test results from different batches of wafers. A portion of these electrical test results is for a first product (e.g., an ADC circuit), while another portion is for a second product (e.g., a DAC circuit). In this example, each of the CP sample data SD_C1~SD_Cn records both first product data and second product data. The first product data corresponds to the first product (e.g., an ADC circuit). The second product data corresponds to the second product (e.g., a DAC circuit).

[0026] In other embodiments, the prediction device 200 further includes an input / output interface 230. The input / output interface 230 receives training data DTR and provides training data DTR preprocessing circuitry 210. In one possible embodiment, the WAT sample data SD_W1~SD_Wn is provided by the wafer manufacturer. In this example, the wafer manufacturer provides WAT test data for each batch of wafers to the back-end testing vendor. In this embodiment, the WAT sample data SD_W1~SD_Wn are WAT test data for different batches of wafers. The back-end testing vendor performs CP testing operations on different batches of wafers to generate CP sample data SD_C1~SD_Cn.

[0027] During a prediction period, processing circuit 210 provides input data DIN to a trained machine learning model ML. The machine learning model ML predicts the yield YL of a batch of wafers based on the correlation coefficient (CORR) and the input data DIN. In this embodiment, the input data DIN includes WAT measurement data SD_M. The WAT measurement data SD_M is similar to the WAT sample data SD_W1~SD_Wn, all provided by the wafer manufacturer. In this example, the wafer manufacturer tests a specific batch of wafers to generate the WAT measurement data SD_M. The machine learning model ML predicts the yield of that specific batch of wafers based on the correlation coefficient (CORR) and the WAT measurement data SD_M.

[0028] In some embodiments, the input / output interface 230 further receives input data DIN and provides the input data DIN to the processing circuitry 210. In other embodiments, the prediction device 200 further includes an input / output interface 240 for outputting the predicted yield YL. In one possible embodiment, the processing circuitry 210 uses the input / output interface 230 to output the predicted yield YL.

[0029] In some embodiments, during training, the input / output interface 230 further receives a CP map SD_MP. In this example, the processing circuit 210 provides the CP map SD_MP, WAT sample data SD_W1~SD_Wn, and CP sample data SD_C1~SD_Cn to the machine learning model ML for training the machine learning model ML. During prediction, the machine learning model ML predicts not only the wafer yield YL, but also the location LOC of the defective die for each wafer. In one possible embodiment, the processing circuit 210 writes the prediction results (Location LOC of the defective die) generated by the machine learning model ML to the storage circuit 220.

[0030] In some embodiments, the machine learning model (ML) further predicts the yield of a specific product for each wafer in a batch of wafers. This specific product is a functional circuit, such as an ADC, DAC, etc. Each die of each wafer has at least one functional circuit. In this example, the machine learning model (ML) further predicts the yield of at least one functional circuit for each die.

[0031] The prediction method, or a specific form or part thereof, of this invention can exist in the form of code. The code can be stored on physical media, such as floppy disks, optical discs, hard disks, or any other machine-readable (e.g., computer-readable) storage media, or not limited to external computer program products. When the code is loaded and executed by a machine, such as a computer, that machine becomes a prediction device for this invention. The code can also be transmitted via transmission media, such as wires or cables, optical fibers, or any transmission method. When the code is received, loaded, and executed by a machine, such as a computer, that machine becomes a prediction device for this invention. When implemented in a general-purpose processing unit, the code, combined with the processing unit, provides a unique device that operates similarly to an application-specific logic circuit.

[0032] Unless otherwise defined, all terms herein (including technical and scientific terms) are as commonly understood by one of ordinary skill in the art to which this invention pertains. Furthermore, unless expressly stated otherwise, the definitions of terms in a general dictionary should be interpreted as consistent with their meaning in writings of the relevant technical field, and not as idealized or overly formal expressions. While terms such as “first” and “second” can be used to describe various elements, these elements should not be limited by these terms. These terms are merely used to distinguish one element from another. Within the claims, terms such as “first” and “second” are used as designations and are not intended to impose numerical requirements on their objects.

[0033] While the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the invention. Those skilled in the art can make modifications and refinements without departing from the spirit and scope of the invention. For example, the systems, apparatus, or methods described in the embodiments of the present invention can be implemented in physical embodiments using hardware, software, or a combination of hardware and software. Therefore, the scope of protection of the present invention should be determined by the appended claims.

[0034] Steps 111~113, 121~123: 110: During training 120: Forecast period 200: Predictive device 210: Processing circuit 220: Storage circuit 230, 240: Input / output interface ML: Machine Learning Model DTR: Training Data SD_W1~SD_Wn: WAT sample data SD_C1~SD_Cn: CP sample data CORR: Correlation PR: Production line information NM: Product Information DIN: Input data YL: Yield SD_M: WAT Measurement Data

Claims

1. A prediction method for predicting the yield of a batch of wafers, comprising: During a training period: Receive Wafer Acceptance Test (WAT) sample data for multiple wafers; A wafer probe (CP) test is performed on the wafers to generate multiple CP sample data; the wafer assemblies (WAT) sample data and the CP sample data are input to a machine learning model, wherein the machine learning model calculates a correlation between the WAT sample data and the CP sample data; during a prediction period: WAT measurement data is input to the machine learning model, wherein the machine learning model predicts the yield of the batch of wafers based on the correlation and the WAT measurement data, wherein the CP test operation includes multiple test items, one part of which corresponds to a first product, and one part of which corresponds to a second product.

2. The prediction method as described in claim 1, wherein the machine learning model predicts the location of defective dies in each wafer of the batch of wafers based on the correlation and the WAT measurement data.

3. The prediction method as described in claim 2, wherein the CP sample data are electrical test results of the wafers.

4. The prediction method as described in claim 2, wherein the machine learning model calculates the abnormal electrical test results of the WAT sample data and the CP sample data to generate the correlation.

5. The prediction method as described in claim 1, wherein the machine learning model predicts the yield of the first product and the yield of the second product in the batch of wafers based on the correlation and the WAT measurement data.

6. A prediction apparatus for predicting the yield of a batch of wafers, comprising: A storage circuit stores a machine learning model; An input / output interface for receiving complex wafer acceptance test (WAT) sample data and complex wafer probing (CP) sample data; a processing circuit for reading the storage circuit to read the machine learning model, wherein: during a training period: the processing circuit provides the WAT sample data and the CP sample data to the machine learning model, and the machine learning model calculates the WAT sample data and the CP sample data to generate a correlation; during a prediction period: the input / output interface receives WAT measurement data, and the processing circuit inputs the WAT measurement data to the machine learning model, wherein the machine learning model predicts the yield of the batch of wafers based on the correlation and the WAT measurement data.

7. The prediction apparatus as claimed in claim 6, wherein the machine learning model predicts the location of defective dies in each wafer of the batch of wafers based on the correlation and the WAT measurement data, thereby generating a prediction result, and the processing circuit writes the prediction result into the storage circuit.

8. The prediction apparatus as claimed in claim 6, wherein the machine learning model predicts the yield of one of the products in the batch of wafers based on the correlation and the WAT measurement data, each of the CP sample data including multiple test results, at least one of the test results being for the product.

9. A computer-readable storage medium for storing code that, when executed, performs the following steps: During a training period: receiving complex wafer acceptance test (WAT) sample data of a complex number of wafers; performing a wafer probe (CP) test on the wafers to generate complex CP sample data; inputting the WAT sample data and the CP sample data to a machine learning model, wherein the machine learning model calculates the WAT sample data and the CP sample data to generate a correlation; During a prediction period: inputting WAT measurement data to the machine learning model, wherein the machine learning model predicts the yield of the wafers based on the correlation and the WAT measurement data.

Images