Chip detection report generation method, computer device and computer readable storage medium
By automating the processing of raw data from chip testing equipment, identifying and filtering microscopic characterization images, and generating accurate chip testing reports, the problem of invalid images being mixed in is solved, and the efficiency of report generation is improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-31
- Publication Date
- 2026-04-17
AI Technical Summary
In existing chip testing report generation methods, the data output by the device cannot be directly processed, resulting in invalid images being mixed into the report, leading to inaccurate reports. Furthermore, manual operation is inefficient and prone to data insertion errors.
By connecting to chip testing equipment, raw data is acquired, image data is analyzed to identify microscopic characterization images and mark them as processed images, and after preprocessing, the data is filled into the report template. Combined with parameter data processing and template management, chip testing reports are automatically generated.
Ensure accurate image data in chip testing reports, reduce invalid images, improve report generation efficiency, achieve full-process automation, and reduce time consumption.
Smart Images
Figure CN121882009A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the technical field of chip testing result processing, specifically to a method for generating a chip testing report, a computer device, and a computer-readable storage medium. Background Technology
[0002] In the chip manufacturing and testing industry, FIB (Focused Ion Beam) and TEM (Transmission Electron Microscopy) are commonly used testing methods. FIB can perform precise micro- and nano-fabrication of chips and prepare ultra-thin samples for TEM analysis, while TEM can provide high-resolution images of the chip's microstructure. Combining the two can obtain key information such as chip manufacturing process, internal structure, and defect distribution.
[0003] After chip testing is completed, generating and analyzing the report typically relies on manual operation. Technicians need to manually collect the test data from the equipment, insert the data into the report template according to a preset order, and then add text descriptions and formatting adjustments. However, manual operation leads to low efficiency and is prone to problems such as data insertion errors.
[0004] One method for creating an analysis report involves: creating an analysis report template file based on requirements; adding tags to the analysis report template file; formatting the raw data into analysis report content data according to a specified format; obtaining template structure data based on the correspondence between the data corresponding to various tag names in the report content data and the various tag names in the analysis report template file; editing the grouped template pages based on the analysis report content data and the template structure data; and finally, clearing all grouped tags from the analysis report to obtain the analysis report.
[0005] However, existing methods cannot directly process the data output by the device when generating chip inspection reports. This results in the direct insertion of device output data into the chip inspection report, leading to the inclusion of other devices or unprocessed images. Consequently, the chip inspection report contains multiple invalid data points. Chip inspection reports need to accurately present core FIB and TEM information, such as FIB cross-sectional structure and TEM microscopic defect images. If the images output by the device are not microscopic representations and cannot reflect micro- and nano-scale details, inserting invalid images into critical pages can mislead personnel and lead to inaccurate chip inspection reports. Summary of the Invention
[0006] The primary objective of this invention is to provide a method for generating chip testing reports that can eliminate invalid data and ensure accurate presentation of chip testing reports.
[0007] A second objective of the present invention is to provide a computer device for implementing the above-described method for generating chip test reports.
[0008] A third objective of this invention is to provide a computer-readable storage medium that applies the above-described method for generating chip test reports.
[0009] To achieve the first objective of this invention, the method for generating a chip testing report provided by this invention includes: connecting to a chip testing device and acquiring multiple raw data from the chip testing device, the multiple raw data including image data and parameter data; analyzing the image data to determine whether the image data contains microscopic characterization images; if the image data contains microscopic characterization images, marking the image data as a processed image and storing the processed image; inputting the processed image into a report generation module; processing the parameter data; obtaining a report template according to template information, filling the processed image into the image display area of the report template according to mapping rules, and filling the parameter data into the table area of the report template; and arranging the image display area and table area according to preset rules to generate a chip testing report.
[0010] As can be seen from the above solution, by analyzing and filtering the raw images output by the chip testing equipment before filling them into the report template, the chip testing report contains no invalid images, ensuring that the images in the report support the testing theory. Furthermore, this invention automates the entire process of data acquisition and analysis, template management, automatic filling and layout, and report generation, reducing report generation time and improving efficiency.
[0011] In a further proposed solution, the steps for analyzing image data include: extracting device identification information or chip microstructure information from the image data, and identifying the image data based on the device identification information or chip microstructure information.
[0012] Therefore, it can be seen that the identification information and detection parameters of the detection device that extracts microscopic representation images from image data can be used to identify whether the chip is a microscopic representation image.
[0013] In a further proposed solution, the steps for processing the parameter data include: validating the range values of the element data of the parameter data and marking the element data.
[0014] This demonstrates that processing parameter data makes chip testing reports more accurate.
[0015] In a further proposed solution, the processed image is filled in front of the image display area of the report template according to the mapping rules, and the processed image is scaled according to the preset size of the template.
[0016] Therefore, scaling the processed image makes it more consistent with the layout specifications of the chip inspection report.
[0017] In a further proposed solution, before obtaining the report template based on the template information, the following steps are performed: obtaining the chip data information input by the user; after filling the parameter data into the table area, the following steps are performed: filling the chip data information into the text area of the report template.
[0018] Therefore, chip data includes information such as project number and testing personnel, which makes the chip testing report more complete.
[0019] In a further embodiment, after the processed image is formed, the following steps are performed: preprocessing the processed image; the preprocessing steps include: applying Gaussian filtering to denoise the processed image, applying a contrast enhancement algorithm to process the denoised processed image, and applying an image centering cropping algorithm to process the processed image after applying the contrast enhancement algorithm.
[0020] Therefore, preprocessing the image makes it more consistent with the layout specifications of the chip inspection report.
[0021] To achieve the second objective, the computer device provided by the present invention includes a processor and a memory, the memory storing a computer program, which, when executed by the processor, implements the above-described method for generating a chip detection report.
[0022] To achieve the third objective, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed, it implements the chip test report generation method of the above claims. Attached Figure Description
[0023] Figure 1 This is a flowchart of an embodiment of the chip testing report generation method of the present invention.
[0024] The present invention will be further described below with reference to the accompanying drawings and embodiments. Detailed Implementation
[0025] The chip testing report generation method provided by this invention identifies and analyzes image data, filters microscopic characterization images, and then automatically generates a chip testing report, ensuring that the images in the chip testing report do not contain invalid images and that the images in the chip testing report can support the testing theory.
[0026] Example of a method for generating chip test reports: When generating a chip inspection report, the processor first executes step S1, connecting to the chip inspection equipment and acquiring multiple raw data sets from the equipment. Chip inspection equipment includes FIB (Film Injection Block) and TEM (Transformation and Electron Microscopy) devices, and the system may also connect to other inspection equipment such as optical microscopes and SEM (Search Engine Microscopy) devices. Due to issues such as system data channel multiplexing, image data from other devices may be sent to the processor for processing.
[0027] Multiple raw data sets include image data and parametric data. Image data includes cross-sectional images of the chip generated by FIB and microstructure images captured by TEM. Parametric data includes processing parameters, EDS elemental composition data, and electron diffraction data.
[0028] After acquiring multiple raw data sets from the chip inspection equipment, step S2 is executed to analyze the image data. Since the raw data may contain data from other inspection equipment, analysis and filtering are necessary. Specifically, device identification information and chip microstructure information are extracted from the image data, and the image data is identified based on either the device identification information or the chip microstructure information. Device identification information for the FIB and TEM equipment is extracted using a device metadata parsing algorithm. If the image data lacks device identification information, chip microstructure information is identified using a feature extraction algorithm.
[0029] The device metadata parsing algorithm identifies whether image data contains device identification information and extracts the device serial number and affiliated organization code from the file metadata in the image data. In the feature extraction algorithm, the algorithm is pre-trained by setting up a set of microscopic representation images and a set of control images from other detection devices. Technicians label the chip microstructure in the microscopic representation image set as microscopic representation images and the control image set as non-microscopic representation images. The labeled microscopic representation images and the labeled control image set are then input into the feature extraction algorithm for training, resulting in a trained feature extraction algorithm. The trained feature extraction algorithm is then used to extract chip microstructure features and determine whether the extracted chip microstructure features are the same as those in the microscopic representation images. The microscopic representation images include chip cross-sectional images generated by FIB and microstructure images captured by TEM.
[0030] After analyzing the image data, step S3 is executed to determine whether the image data has a microscopic characterization image. Specifically, it is determined whether the device identification information of the image data is the identification information of a FIB device or a TEM device. If the device identification information of the image data is the identification information of a FIB device or a TEM device, then step S4 is executed to mark the image data as a processed image and store the processed image in the memory. If the device identification information of the image data is not the identification information of a FIB device or a TEM device, then step S8 is executed to not save the image data.
[0031] If the image data does not contain device identification information, it is determined whether the output of the feature extraction algorithm is a chip microstructure feature of the micro-representation image. If so, step S4 is executed to mark the image data as a processed image and store the processed image in the memory. If the output of the feature extraction algorithm is not a chip microstructure feature of the micro-representation image, step S8 is executed to not save the image data.
[0032] Before storing the processed image in the memory, i.e. after the processed image is formed, the processed image is preprocessed. The preprocessing steps include: applying Gaussian filtering to denoise the processed image, applying a contrast enhancement algorithm to process the denoised processed image, and applying an image centering cropping algorithm to process the processed image after applying the contrast enhancement algorithm.
[0033] After storing the processed image in the memory, step S5 is executed to process the parameter data. The parameter data processing steps include range verification of the element data and marking the element data. The element data is the EDS element content. The EDS element content is generated by analyzing the characteristic X-ray energy produced by the sample when the EDS device (Energy Dispersive X-ray Spectrometer) is combined with a FIB device or TEM device to detect the chip sample, and the range verification is performed on the element data. Range verification of the element data includes determining whether the element data value is within a preset range. If it is, the element data is marked as normal; if the element data value is outside the preset range, the element data is marked as abnormal.
[0034] After processing the parameter data, step S6 is executed: obtain the report template based on the template information, fill the processed image into the image display area of the report template according to the mapping rules, and fill the parameter data into the table area of the report template.
[0035] Before retrieving the report template from the template information, the system obtains the chip data information input by the user. The memory pre-stores various report templates, categorized according to the chip application area or testing focus. The chip data information includes the project number, testing personnel, chip application area, and testing focus. The report template is then retrieved from the memory based on the chip application area and testing focus.
[0036] According to the mapping rules, the processed image is filled before the image area of the report template. The processed image is then scaled according to the template's preset size. After scaling, the processed image is filled into the image display area of the report template according to the mapping rules. Parameter data is filled into the table area of the report template, and chip information is filled into the text area of the report template. The mapping rules include the relationship between image data or parameter data and the various display areas of the template, which include the image display area, table area, and text area.
[0037] After filling the image display area of the report template with the processed image according to the mapping rules and filling the table area of the report template with the parameter data, step S7 is executed to arrange the image display area and table area according to the preset rules to generate a chip detection report.
[0038] The layout of the image display area and table area according to preset rules includes: arranging the images according to the preset rules, where the first image of multiple processed images is placed on the first page, and subsequently, every two processed images occupy one page of the chip detection report. Training is performed using grouped cases of historical report images, and a clustering algorithm is used to group the multiple processed images, which are then arranged according to the aforementioned layout rules.
[0039] Then, a multi-image layout algorithm is used to arrange the image display area. If the current page of the chip detection report displays only one processed image, a centered position is used, determined by the size difference between the page and the processed image. If the current page displays two processed images, they are arranged side-by-side, with a 1cm gap between them and the main body of each image horizontally centered. If the current page displays more than two processed images, a matrix arrangement is used, calculating the row and column spacing. The multi-image layout algorithm can be trained based on multi-image layout examples from historical high-quality reports, learning the mapping relationship between input features such as the number, size, and content type of images in historical high-quality reports and layout parameters (such as spacing, number of rows and columns, and coordinates).
[0040] After using a multi-image layout algorithm to arrange the image display area, the table area is then arranged using preset table rules, such as centering the table.
[0041] After completing the report template layout, output the chip testing report.
[0042] By analyzing and filtering the raw images output by the chip testing equipment before filling them into the report template, this invention ensures that the chip testing report contains no invalid images and that the images in the report support the testing theory. Furthermore, this invention automates the entire process of data acquisition and analysis, template management, automatic filling and layout, and report generation, reducing report generation time and improving efficiency.
[0043] Computer device embodiment: The computer device in this embodiment includes a processor and a memory. The memory stores a computer program, and when the processor executes the computer program, it implements the above-described method for generating a chip test report.
[0044] A computer device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that a computer device may include more or fewer components, or a combination of certain components, or different components; for example, a computer device may also include input / output devices, network access devices, buses, etc.
[0045] Examples of computer-readable storage media: The method for generating a chip test report in a computer device described in the above embodiments can be stored in a computer-readable storage medium in the form of a computer program. When the computer program is executed by a processor, it can complete the steps of the above embodiments of the method for generating a chip test report in a computer device. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.
[0046] The above are merely preferred embodiments of the present invention, but the design concept of the invention is not limited thereto. Without departing from the concept of the present invention, many other equivalent embodiments may be included. Those skilled in the art can make various obvious changes, readjustments and substitutions without departing from the protection scope of the present invention.
Claims
1. A method for generating a chip testing report, the method comprising: Connect to a chip testing device and acquire multiple raw data from the chip testing device, including image data and parameter data; Its features are: The image data is analyzed to determine whether it contains microscopic representations. If the image data is a microscopic representation image, mark the image data as a processed image and store the processed image; The parameter data is processed; Obtain the report template based on the template information, fill the processed image into the image display area of the report template according to the mapping rules, and fill the parameter data into the table area of the report template; The image display area and the table area are arranged according to preset rules to generate a chip testing report.
2. The method for generating a chip testing report according to claim 1, characterized in that: The steps for analyzing the image data include: Extract device identification information or chip microstructure information from the image data, and identify the image data based on the device identification information and the chip microstructure information.
3. The method for generating a chip testing report according to claim 1, characterized in that: The steps for processing the parameter data include: The element data of the parameter data is validated for range values, and the element data is marked.
4. The method for generating a chip testing report according to any one of claims 1 to 3, characterized in that: According to the mapping rules, the processed image is filled in before the image display area of the report template, and the following is also performed: The processed image is scaled according to the preset size of the template.
5. The method for generating a chip testing report according to any one of claims 1 to 3, characterized in that: Before retrieving the report template based on the template information, the following steps are also performed: Obtain chip data information input by the user; After filling the table area with parameter data, the following steps are also performed: Fill the text area of the report template with the chip data information.
6. The method for generating a chip testing report according to any one of claims 1 to 3, characterized in that: After the processed image is generated, the following steps are also performed: The image to be processed is preprocessed; The steps for preprocessing the image include: The image is denoised using Gaussian filtering, then processed using a contrast enhancement algorithm, and finally processed using an image centering and cropping algorithm.
7. A computer device, comprising a processor and a memory, the memory storing a computer program that, when executed by the processor, implements the method for generating a chip test report according to any one of claims 1 to 6.
8. A computer readable storage medium having stored thereon a computer program, characterized in that When the computer program is executed, it implements the method for generating a chip test report as described in any one of claims 1 to 6.