Flow engine execution-based process establishment and detection method

Abstract

The invention relates to the field of flow engine establishment and defect detection, in particular to a flow establishment and detection method based on Flowable engine execution, which comprises the steps of S1, defect detection task creation based on a Flowable engine, S2, chip detection preparation, S3, defect detection execution, S4, detection result analysis, S5, defect processing and S6, report generation and auditing. Through automatic and intelligent process management, the efficiency and accuracy of defect detection are improved.

Description

Technical Field

[0001] This patent involves the field of process engine construction and defect detection, and specifically involves a process construction and detection method based on the Flowable engine execution. Background Art

[0002] With the rapid development of electronic technology, baseband chips are increasingly used in modern communication devices. However, defect detection has always been a critical and challenging link in the production process of baseband chips. Traditional defect detection methods mainly rely on manual visual inspection, which is not only inefficient but also easily affected by human factors, making it difficult to ensure the accuracy and consistency of the detection results.

[0003] In order to improve the efficiency and accuracy of defect detection, automated detection technology has gradually been introduced into the production process of baseband chips. However, the existing automated detection system still lacks flexibility and intelligence, and it is difficult to adapt to the detection needs of chips of different batches and specifications. In addition, the processing and analysis of detection data also face huge challenges. How to quickly and accurately analyze a large amount of detection data and determine the type and location of defects is a problem that needs to be solved urgently. Summary of the invention

[0004] According to the description of the existing technical defects in the background technology center, this patent provides a process building and detection method based on the Flowable engine execution, which includes the steps of:

[0005] S1. Create defect detection tasks based on the Flowable engine

[0006] After each batch of baseband chips is produced, the system automatically generates inspection tasks based on the production batch information (including batch number, production date, production line number, etc.) and assigns them to the inspection department.

[0007] S2. Chip test preparation

[0008] Preparation of testing equipment: The testing personnel confirm and prepare testing equipment including high-precision optical microscope, scanning electron microscope (SEM), electron probe microanalyzer (EPMA), etc. to ensure that the equipment is in normal status.

[0009] Environmental parameter setting: According to the specifications of the baseband chip and the production process parameters (such as temperature, humidity, dust-free level, etc.), adjust the conditions of the test environment to ensure that they meet the test requirements.

[0010] S3. Defect detection execution

[0011] Automated testing: Use automated testing equipment to perform defect detection on baseband chips. The detection parameters include but are not limited to: electrical performance parameters (current, voltage, power consumption, etc.), thermal performance parameters (operating temperature, thermal resistance, etc.), and mechanical performance parameters (strength, hardness, etc.).

[0012] Data collection and processing: The system collects test data in real time, processes and analyzes the data through set algorithms (such as Fourier transform, principal component analysis, etc.) to preliminarily determine the defect type.

[0013] S4. Analysis of test results

[0014] Data analysis: The system uses machine learning algorithms (such as support vector machines, convolutional neural networks, etc.) to further analyze the data based on the collected inspection data to determine whether there are defects. If there are defects, the specific location and type of the defects are recorded.

[0015] Manual review: The inspection personnel will manually review and confirm the defect results automatically analyzed by the system to ensure the accuracy of the inspection results.

[0016] S5. Defect handling

[0017] Defect Record: The system records detailed information of each defect, including defect location, type, severity, etc.

[0018] Defect handling task allocation: Flowable automatically generates processing tasks based on the defect type and severity, and assigns them to relevant departments for defect repair or feedback.

[0019] S6. Report generation and review

[0020] Report generation: The system automatically generates a detailed test report based on the test and processing results, including information such as the test process, result analysis, and defect processing.

[0021] Report review: The relevant department reviews the test report and archives and publishes it after confirmation.

[0022] Through automated and intelligent process management, the efficiency and accuracy of defect detection are improved, manual intervention is reduced, and the timely allocation and execution of detection tasks are ensured. This enables efficient and accurate baseband chip defect detection and processing, effectively improving production quality and efficiency.

[0023] Furthermore, the detection task creation step further includes:

[0024] Based on historical inspection data and production process parameters (such as silicon wafer thickness, doping concentration, etc.), the system uses an external corresponding model to predict the types of defects that may exist in the current batch of chips and generates a corresponding inspection plan.

[0025] Using historical data and production process parameters for prediction can identify potential defects in advance and improve the pertinence and effectiveness of detection plans.

[0026] Furthermore, the automated detection step further comprises:

[0027] Use the set detection path and detection point coordinates (such as the alignment mark position of the photolithography mask, the key nodes of the circuit wiring, etc.) for detection, set the detection path and detection point coordinates to ensure the detection coverage and accuracy, and reduce the possibility of missed detection and false detection.

[0028] Furthermore, the data collection and processing step further includes:

[0029] Using the Fourier transform formula

[0030]

[0031] Perform frequency domain analysis on the inspection data to extract defect features.

[0032] F(u, v): Fourier transform result in the frequency domain, representing the value of the image at the frequency coordinate (u, v).

[0033] f(x, y): The original image in the spatial domain, the pixel value at the spatial coordinate (x, y).

[0034] M: The width of the image (i.e. the number of horizontal pixels).

[0035] N: The height of the image (i.e. the number of vertical pixels).

[0036] u: horizontal frequency coordinate in the frequency domain.

[0037] v: vertical frequency coordinate in the frequency domain.

[0038] x: spatial coordinate in the horizontal direction in the spatial domain.

[0039] y: The spatial coordinate in the vertical direction in the spatial domain.

[0040] j: imaginary unit, satisfying j 2 =-1

[0041] e: the base of the natural logarithm, approximately equal to 2.71828

[0042] The principal component analysis formula Z=XW is used to reduce the dimensionality of multidimensional detection data, where X is the original data matrix, W is the transformation matrix, and Z is the data matrix after dimensionality reduction.

[0043] The detection data is processed through Fourier transform and principal component analysis to extract defect features and reduce the dimension, thereby improving the efficiency and accuracy of data processing.

[0044] Furthermore, the data analysis step further includes:

[0045] Use the Support Vector Machine (SVM) classification algorithm

[0046] f(z)=sign(w·z+b)

[0047] Classify inspection data to determine defect type and severity.

[0048] f(z) classification function, output classification result (positive or negative)

[0049] Z: Input vector, representing the data characteristics of the sample.

[0050] W: weight vector, representing the weight of each feature.

[0051] b: Bias term (or intercept), used to adjust the position of the decision boundary.

[0052] Sign: Sign function, used to return the sign of the input. If the input is greater than 0, it returns 1, and if it is less than 0, it returns -1.

[0053] Using the support vector machine classification algorithm to classify the inspection data can accurately determine the defect type and severity, and improve the intelligence level of defect analysis.

[0054] Furthermore, the report generation and review step further includes:

[0055] The system generates a three-dimensional graphical report based on the test results, showing the defect distribution and severity, and providing intuitive defect information reference for relevant departments.

[0056] Also disclosed is a process building and detection system, which includes:

[0057] Defect detection task creation module, when each batch of baseband chips is produced, it automatically generates detection tasks according to the production batch information (including batch number, production date, production line number, etc.) and assigns them to the inspection department;

[0058] The chip test preparation module adjusts the test environment conditions according to the baseband chip specifications and production process parameters (such as temperature, humidity, dust-free level, etc.) to ensure that the test requirements are met;

[0059] The defect detection execution module uses automated detection equipment to perform defect detection on the baseband chip. The detection parameters include but are not limited to: electrical performance parameters (current, voltage, power consumption, etc.), thermal performance parameters (operating temperature, thermal resistance, etc.), and mechanical performance parameters (strength, hardness, etc.). The module collects detection data in real time and processes and analyzes the data through a set algorithm (such as Fourier transform, principal component analysis, etc.) to preliminarily determine the defect type.

[0060] The test result analysis module uses machine learning algorithms (such as support vector machines, convolutional neural networks, etc.) to further analyze the data based on the collected test data to determine whether there are defects. If there are defects, the specific location and type of the defects are recorded;

[0061] Defect handling module, which records detailed information of each defect, including defect location, type, severity, etc. Based on the defect type and severity, the system automatically generates a processing task and assigns it to the relevant department for defect repair or feedback;

[0062] The report generation and review module automatically generates a detailed test report based on the test and processing results, including information such as the test process, result analysis, and defect processing. The test report is reviewed by the relevant departments, and after confirmation, it is archived and the report is released.

[0063] Through modular design, the automatic creation, execution, analysis and processing of defect detection tasks are realized, which improves the flexibility and scalability of the system.

[0064] A computer device is disclosed, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the process building and detection method based on the Flowable engine is implemented. The computer device implements the automatic execution of the above method by executing the corresponding computer program, thereby ensuring the efficient operation of the process.

[0065] A computer-readable storage medium is disclosed, on which a computer program is stored. When the computer program is executed by a processor, the process building and detection method based on the Flowable engine is implemented. The computer program stored on the computer-readable storage medium can be run on the processor to realize the automatic execution of the above method, providing a convenient implementation path. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present invention 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 creative work.

[0067] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0068] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0069] Example 1

[0070] like Figure 1 This embodiment provides a process building and detection method based on Flowable engine execution, which includes the following steps:

[0071] S1. Create defect detection tasks based on the Flowable engine

[0072] After each batch of baseband chips is produced, the system automatically generates inspection tasks based on the production batch information (including batch number, production date, production line number, etc.) and assigns them to the inspection department. The Flowable engine intelligently assigns inspection tasks based on preset rules and the workload of the inspection department to ensure balanced and timely task allocation.

[0073] S2. Chip test preparation

[0074] Preparation of testing equipment: The testing personnel confirm and prepare testing equipment including high-precision optical microscope, scanning electron microscope (SEM), electron probe microanalyzer (EPMA), etc. to ensure that the equipment is in normal status.

[0075] Environmental parameter setting: According to the specifications of the baseband chip and the production process parameters (such as temperature, humidity, dust-free level, etc.), adjust the conditions of the test environment to ensure that they meet the test requirements.

[0076] Equipment calibration: Regularly calibrate the testing equipment to ensure the accuracy and consistency of the test results

[0077] S3. Defect detection execution

[0078] Automated testing: Use automated testing equipment to perform defect detection on baseband chips. The detection parameters include but are not limited to: electrical performance parameters (current, voltage, power consumption, etc.), thermal performance parameters (operating temperature, thermal resistance, etc.), and mechanical performance parameters (strength, hardness, etc.).

[0079] Data collection and processing: The system collects test data in real time, processes and analyzes the data through set algorithms (such as Fourier transform, principal component analysis, etc.) to preliminarily determine the defect type.

[0080] Real-time monitoring: The Flowable engine monitors the detection process in real time to ensure that the detection task is carried out as planned, and promptly issues an alarm when an anomaly is found during the detection process.

[0081] S4. Analysis of test results

[0082] Data analysis: The system uses machine learning algorithms (such as support vector machines, convolutional neural networks, etc.) to further analyze the data based on the collected detection data to determine whether there are defects (use Flowable's service tasks to call external machine learning algorithms. Communicate with external machines through REST APIs or message queues. Use HTTP tasks to send requests to external machine learning services. After the external machine learning algorithm completes the analysis, it returns the results to Flowable. Flowable obtains the analysis results by receiving HTTP responses or reading results from message queues). If there are defects, Flowable records the specific location and type of the defect and triggers the corresponding processing flow. This step is fully automatic.

[0083] Manual review: The inspection personnel will manually review and confirm the defect results automatically analyzed by the system to ensure the accuracy of the inspection results.

[0084] Data visualization: Through data visualization tools, the test results are displayed in the form of charts, which makes it easier for testers to understand and analyze quickly.

[0085] S5. Defect handling

[0086] Defect Record: The system records detailed information of each defect, including defect location, type, severity, etc.

[0087] Defect handling task allocation: Flowable automatically generates handling tasks based on defect type and severity, and assigns them to relevant departments for defect repair or feedback: Define a variable named severity in the Flowable process to store the severity of the defect, set different conditions based on the characteristics of the defect, and use Flowable's conditional expressions to judge the severity of the defect. These characteristics include defect size, location, impact range, etc., automatically generate handling tasks based on severity, and assign them to relevant departments for defect repair or feedback. Doing so can automate process management. Flowable can automatically determine the severity of defects and generate processing tasks, which can reduce human intervention, improve the degree of automation and efficiency of the process, achieve accurate task allocation, and automatically assign tasks to the most appropriate department or personnel to ensure that problems are handled in a timely and effective manner. It can also improve response speed. Automated task generation and allocation can significantly shorten response time, quickly handle defects, reduce losses caused by production stagnation or quality problems, and maintain consistency and standardization. It uses predefined conditions and rules to ensure consistency and standardization of defect handling processes, reduce errors caused by human judgment, and have traceability and monitoring. The historical data query and monitoring functions provided by Flowable can help track the execution of each defect handling task, discover potential problems and optimize them. Of course, it also has a certain degree of flexibility and scalability. Flowable's process definition and conditions

[0088] Expressions can be adjusted and expanded according to actual needs to adapt to different business scenarios and changes.

[0089] Processing progress tracking: The Flowable engine tracks the progress of defect handling tasks in real time to ensure that the processing tasks are completed on time and promptly remind relevant personnel when the tasks are delayed.

[0090] S6. Report generation and review

[0091] Report generation: The system automatically generates a detailed test report based on the test and processing results, including information such as the test process, result analysis, and defect processing.

[0092] Report review: The relevant department reviews the test report and archives and publishes it after confirmation.

[0093] Through automated and intelligent process management, the efficiency and accuracy of defect detection are improved, manual intervention is reduced, and the timely allocation and execution of detection tasks are ensured. This enables efficient and accurate baseband chip defect detection and processing, effectively improving production quality and efficiency.

[0094] Furthermore, the detection task creation step further includes:

[0095] Based on historical inspection data and production process parameters (such as silicon wafer thickness, doping concentration, etc.), the system uses an external corresponding model to predict the types of defects that may exist in the current batch of chips and generates a corresponding inspection plan.

[0096] Using historical data and production process parameters for prediction can identify potential defects in advance and improve the pertinence and effectiveness of detection plans.

[0097] Furthermore, the automated detection step further comprises:

[0098] Use the set detection path and detection point coordinates (such as the alignment mark position of the photolithography mask, the key nodes of the circuit wiring, etc.) for detection, set the detection path and detection point coordinates to ensure the detection coverage and accuracy, and reduce the possibility of missed detection and false detection.

[0099] Furthermore, the data collection and processing step further includes:

[0100] Using the Fourier transform formula

[0101]

[0102] Perform frequency domain analysis on the inspection data to extract defect features.

[0103] F(u, v): Fourier transform result in the frequency domain, representing the value of the image at the frequency coordinate (u, v).

[0104] f(x, y): The original image in the spatial domain, the pixel value at the spatial coordinate (x, y).

[0105] M: The width of the image (i.e. the number of horizontal pixels).

[0106] N: The height of the image (i.e. the number of vertical pixels).

[0107] u: horizontal frequency coordinate in the frequency domain.

[0108] v: vertical frequency coordinate in the frequency domain.

[0109] x: spatial coordinate in the horizontal direction in the spatial domain.

[0110] y: The spatial coordinate in the vertical direction in the spatial domain.

[0111] j: imaginary unit, satisfying j 2 =-1

[0112] e: the base of the natural logarithm, approximately equal to 2.71828

[0113] The principal component analysis formula Z=XW is used to reduce the dimensionality of multidimensional detection data, where X is the original data matrix, W is the transformation matrix, and Z is the data matrix after dimensionality reduction.

[0114] The detection data is processed through Fourier transform and principal component analysis to extract defect features and reduce the dimension, thereby improving the efficiency and accuracy of data processing.

[0115] Furthermore, the data analysis step further includes:

[0116] Use the Support Vector Machine (SVM) classification algorithm

[0117] f(z)=sign(w·z+b)

[0118] Classify inspection data to determine defect type and severity.

[0119] f(z): classification function, output classification result (positive or negative)

[0120] Z: Input vector, representing the data characteristics of the sample.

[0121] W: weight vector, representing the weight of each feature.

[0122] b: Bias term (or intercept), used to adjust the position of the decision boundary.

[0123] Sign: Sign function, used to return the sign of the input. If the input is greater than 0, it returns 1, and if it is less than 0, it returns -1.

[0124] Using the support vector machine classification algorithm to classify the inspection data can accurately determine the defect type and severity, and improve the intelligence level of defect analysis.

[0125] Furthermore, the report generation and review step further includes:

[0126] The system generates a three-dimensional graphical report based on the test results, showing the defect distribution and severity, and providing intuitive defect information reference for relevant departments.

[0127] Also disclosed is a process building and detection system, which includes:

[0128] Defect detection task creation module, when each batch of baseband chips is produced, it automatically generates detection tasks according to the production batch information (including batch number, production date, production line number, etc.) and assigns them to the inspection department;

[0129] The chip test preparation module adjusts the test environment conditions according to the baseband chip specifications and production process parameters (such as temperature, humidity, dust-free level, etc.) to ensure that the test requirements are met;

[0130] The defect detection execution module uses automated detection equipment to perform defect detection on the baseband chip. The detection parameters include but are not limited to: electrical performance parameters (current, voltage, power consumption, etc.), thermal performance parameters (operating temperature, thermal resistance, etc.), and mechanical performance parameters (strength, hardness, etc.). The module collects detection data in real time and processes and analyzes the data through a set algorithm (such as Fourier transform, principal component analysis, etc.) to preliminarily determine the defect type.

[0131] The test result analysis module uses machine learning algorithms (such as support vector machines, convolutional neural networks, etc.) to further analyze the data based on the collected test data to determine whether there are defects. If there are defects, the specific location and type of the defects are recorded;

[0132] Defect handling module, which records detailed information of each defect, including defect location, type, severity, etc. Based on the defect type and severity, the system automatically generates a processing task and assigns it to the relevant department for defect repair or feedback;

[0133] The report generation and review module automatically generates a detailed test report based on the test and processing results, including information such as the test process, result analysis, and defect processing. The test report is reviewed by the relevant departments, and after confirmation, it is archived and the report is released.

[0134] Through modular design, the automatic creation, execution, analysis and processing of defect detection tasks are realized, which improves the flexibility and scalability of the system.

[0135] A computer device is disclosed, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the process building and detection method based on the Flowable engine is implemented. The computer device implements the automatic execution of the above method by executing the corresponding computer program, thereby ensuring the efficient operation of the process.

[0136] A computer-readable storage medium is disclosed, on which a computer program is stored. When the computer program is executed by a processor, the process building and detection method based on the Flowable engine is implemented. The computer program stored on the computer-readable storage medium can be run on the processor to realize the automatic execution of the above method, providing a convenient implementation path.

[0137] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0138] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0139] As an example, executable instructions may, but do not necessarily, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, for example, in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0140] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0141] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0142] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0143] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0144] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A process building and detection method based on Flowable engine execution, which is applied in the production process of chip baseband, characterized in that: Includes steps: S1. Create defect detection tasks based on the Flowable engine. After each batch of baseband chips is produced, the detection tasks are automatically generated according to the production batch information and assigned to the detection department. S2. Chip test preparation, S2.1 Preparation of testing equipment: prepare high-precision optical microscope, scanning electron microscope, electron probe microanalyzer and other testing equipment; S2.2 Environmental parameter setting: adjust the test environment conditions according to the baseband chip specifications and production process parameters; S3. Defect detection execution, S3.1 Automated testing: Use automated testing equipment to perform defect detection on baseband chips. Testing parameters include but are not limited to electrical performance parameters, thermal performance parameters, and mechanical performance parameters; S3.2 Data collection and processing: collect test data in real time, process and analyze the data through the set algorithm, and preliminarily determine the defect type; S4. Analysis of test results, S4.1 Data analysis: Based on the collected test data, use machine learning algorithms to further analyze the data to determine whether there are defects. If there are defects, record the specific location and type of the defects; S4.2 Review: Review and confirm the defect results automatically analyzed by the system; S5. Defect handling, S5.1 Defect record, record the detailed information of each defect, including defect location, type, severity, etc.; S5.2 Defect handling task allocation: Flowable automatically generates handling tasks based on defect type and severity, and assigns them to relevant departments for defect repair or feedback; S6. Report generation and review, Report generation: Based on the test and processing results, a detailed test report is automatically generated, including information such as the test process, result analysis, defect processing, etc., and the review is completed.

2. According to the process building and detection method based on Flowable engine execution according to claim 1, it is characterized in that: The detection task creation step further includes: Based on historical inspection data and production process parameters, Flowable uses an external corresponding model to predict the types of defects that may exist in the current batch of chips and generates corresponding inspection plans.

3. The process building and detection method based on Flowable engine execution according to claim 1 is characterized in that: The automated detection step further comprises: Use the set detection path and detection point coordinates for detection to ensure detection coverage and accuracy.

4. The process building and detection method based on Flowable engine execution according to claim 1 is characterized in that: The data collection and processing steps further include: Using the Fourier transform formula Perform frequency domain analysis on the inspection data to extract defect features; F(u,υ): Fourier transform result in the frequency domain, indicating the value of the image at the frequency coordinate (u,υ); f(x, y): the original image in the spatial domain, the pixel value at the spatial coordinate (x, y); M: width of the image (i.e. number of horizontal pixels); N: the height of the image (i.e. the number of vertical pixels); u: frequency coordinate in the horizontal direction in the frequency domain; υ: frequency coordinate in the vertical direction in the frequency domain; x: spatial coordinate in the horizontal direction in the spatial domain; y: spatial coordinate in the vertical direction in the spatial domain; y: imaginary unit, satisfying j 2 =-1 e: the base of natural logarithm, approximately equal to 2.71828; The principal component analysis formula Z=XW is used to reduce the dimensionality of multidimensional detection data, where X is the original data matrix, W is the transformation matrix, and Z is the data matrix after dimensionality reduction.

5. The process building and detection method based on Flowable engine execution according to claim 1 is characterized in that: The data analysis step further comprises: Use the Support Vector Machine (SVM) classification algorithm f(z)=sign(w·z+b) Classify the inspection data to determine the defect type and severity; f(z) classification function, output classification result (positive or negative) Z: input vector, representing the data characteristics of the sample; W: weight vector, representing the weight of each feature; b: Bias term (or intercept), used to adjust the position of the decision boundary; Sign: Sign function, used to return the sign of the input. If the input is greater than 0, it returns 1, and if it is less than 0, it returns -1.

6. The process building and detection method based on Flowable engine execution according to claim 1 is characterized in that: The report generation and review steps further include: The system generates a three-dimensional graphical report based on the test results, showing the defect distribution and severity, and providing intuitive defect information reference for relevant departments.

7. A process building and detection system, characterized in that: include: Defect detection task creation module, when each batch of baseband chips is produced, it automatically generates detection tasks according to the production batch information and assigns them to the detection department; A chip test preparation module, which adjusts the conditions of the test environment according to the specifications and production process parameters of the baseband chip; Defect detection execution module, which uses automated detection equipment to perform defect detection on baseband chips. The detection parameters include but are not limited to: electrical performance parameters, thermal performance parameters, and mechanical performance parameters. The module collects detection data in real time, processes and analyzes the data through a set algorithm, and preliminarily determines the defect type; The test result analysis module uses machine learning algorithms to further analyze the collected test data to determine whether there are defects. If there are defects, the specific location and type of the defects are recorded; Defect handling module, which records detailed information of each defect, including defect location, type, severity, etc. Based on the defect type and severity, the system automatically generates a processing task and assigns it to the relevant department for defect repair or feedback; The report generation and review module automatically generates a detailed test report based on the test and processing results, including information such as the test process, result analysis, and defect processing. The test report is reviewed by the relevant departments, and after confirmation, it is archived and the report is released.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the process building and detection method based on the Flowable engine execution described in any one of claims 1-7 is implemented.

9. 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 the processor, the process building and detection method based on Flowable engine execution according to any one of claims 1 to 7 is implemented.

Images