Handler automatic alarm processing system based on image recognition and processing method thereof

Abstract

The invention discloses a handler automatic alarm processing system based on image recognition and a processing method thereof, and relates to the field of semiconductor test systems. The system comprises an image acquisition module, a server and a simulated manual click plug-in, the image acquisition module is used for shooting alarm information, the server is internally provided with an image receiving module, an autonomous judgment module and an information recording module, and the image receiving module is used for receiving the alarm information collected by the image acquisition module; and the autonomous judgment module autonomously obtains a judgment result of the alarm information according to the learning model. Image recognition and machine learning technologies are utilized to recognize Handler alarm, test position material conditions, material position information in shuttle / boat and the like, judgment is carried out through logic set in a learning model, and finally corresponding instructions are executed according to one of judgment results Retry, Skip and manual assistance.

Description

Technical Field

[0001] The present invention relates to the technical field of semiconductor testing systems, and in particular to a handler automatic alarm processing system based on image recognition and a processing method thereof. Background Art

[0002] Currently, semiconductor testing equipment is equipment used to test and detect semiconductor devices. They are generally used to verify the performance, reliability and consistency of semiconductor devices. Semiconductor testing equipment uses various testing methods and techniques, such as electrical performance testing, functional testing, reliability testing and packaging testing, to ensure that semiconductor devices meet specifications and quality requirements.

[0003] Most semiconductor testing equipment is a multi-process combination structure, so that different performance of semiconductor equipment can be tested in sequence. In order to ensure the normal operation of the entire testing process, corresponding alarm components are often installed in each part to promptly remind the operator when an error occurs in the equipment. When the operator discovers it, the alarm can be manually turned off.

[0004] With respect to the above-mentioned related technologies, it is found that the current manual clearing of alarms by operators is inefficient and has the risk of processing errors, and once an erroneous operation occurs during manual clearing, it is difficult to trace back. Summary of the invention

[0005] In order to achieve the effect of efficient, accurate and clear alarm, the present application provides a handler automatic alarm processing system based on image recognition and a processing method thereof.

[0006] The present invention is achieved in that:

[0007] A handler automatic alarm processing system based on image recognition comprises: an image acquisition module, a server and a simulated manual click plug-in, wherein the image acquisition module is used to shoot alarm information, the server is provided with an image receiving module, an autonomous judgment module and an information recording module, the image receiving module is used to receive the alarm information collected by the image acquisition module; the autonomous judgment module autonomously obtains a judgment result on the alarm information according to a learning model; the information recording module is used to record the alarm information and pictures; the simulated manual click plug-in selects whether to clear the alarm according to the judgment result of the autonomous judgment module.

[0008] By adopting the above technical solution, after receiving the handler alarm information, the server can use the acquisition module to collect images of the alarm information and material location information. The collected image information can be sent to the server through the image receiving module in the server. After receiving the image information, the server can process the information through the autonomous judgment module to ensure that the autonomous judgment module can independently draw a judgment result on the alarm information according to the learning model. At the same time, the alarm information and pictures are recorded through the equipment information recording module as a backup to facilitate the traceability of the alarm information later. By simulating the setting of manual click plug-in, it is convenient to choose whether to start according to the judgment result of the autonomous judgment module. When it needs to be started, the manual click on the alarm information can be simulated to clear the alarm, thereby achieving the purpose of automatic alarm processing of the machine.

[0009] Furthermore, the image acquisition module is composed of a plurality of cameras, and the plurality of cameras are respectively installed at a plurality of material contact positions.

[0010] By adopting the above technical solution, the image acquisition module of the system is composed of several cameras. When it is easy to use, the camera installed at the position can be synchronously started according to the alarm position. In this way, targeted image acquisition of alarm information and material position information at a specific position can be achieved, ensuring that the collected data is more accurate.

[0011] Furthermore, the material contact parts include a machine screen, a test position, a shuttle assembly and a crystal boat.

[0012] By adopting the above technical solution, a camera is set at the machine screen. When the alarm is activated, the camera can directly shoot the alarm information on the machine screen to achieve the purpose of fast and accurate data collection. A camera is set at the test position to ensure that the material on the test position can be directly photographed when the equipment alarms. By installing a camera at the position of the shuttle component, it is convenient for the tool to shoot the material when moving the material during the manufacturing process. The BOAT is a commonly used tool, mainly used for carrying, conveying, cleaning and processing chips. In this way, a camera is installed on the BOAT to shoot the material on the tool. Through the distribution of several cameras, it is ensured that when an alarm occurs in each processing section, the material position of the processing section can be quickly photographed, thereby ensuring the accuracy and timeliness of information collection.

[0013] Furthermore, the judgment result of the autonomous judgment module is one of Retry, Skip and manual assistance.

[0014] By adopting the above technical solution, the judgment results of the autonomous judgment module are set to three types: Retry, Skip and manual assistance. Retry and Skip in the first two cases are rollback operations, which can reduce manual intervention, provide a fault-tolerant mechanism, and enhance the robustness of the system. When it is judged as a result of manual assistance, human intervention is required to perform manual operations.

[0015] Furthermore, the simulated manual click plug-in simulates manual click on the alarm information to clear the alarm when receiving the judgment result of Retry or Skip.

[0016] By adopting the above technical solution, when the autonomous judgment module determines that the result is Retry or Skip, the server can start the rollback operation. The server starts the simulated manual click plug-in to simulate manual clicks on the alarm information to clear the alarm, thereby achieving the effect of automatic machine response processing.

[0017] Furthermore, the server is provided with a data terminal connected to the information recording module, and the data terminal is used to summarize various alarm data of the production line handler, and classify the alarm data according to the judgment result of the autonomous judgment module, so as to achieve the correspondence between the alarm data and the judgment result.

[0018] By adopting the above technical solution, a data terminal is set up in the server to organize the data involved in the equipment operation process. When aggregating the data, all the collected data, judgment data and execution data need to be collected, and then classified and organized according to the judgment results of the autonomous judgment module.

[0019] Furthermore, the data terminal is provided with a data access module, and the data access module is used to access various alarm data classified and summarized by the data terminal.

[0020] By adopting the above technical solution and setting a data access module in the data terminal, it is convenient to store the sorted data through the data access module when in use, and the stored data can be directly accessed, which effectively increases the traceability of the alarm information.

[0021] Furthermore, the data access module is configured with a storage module, and the storage module includes a cloud storage unit and a local storage unit.

[0022] By adopting the above technical solution, the data access module can be used to store and organize information through the storage module, and the storage module can be set as a cloud storage unit and a local storage unit. This not only ensures that data storage is more secure, but also makes it easy to retrieve information by using cloud reading and downloading and local reading and downloading, thereby achieving the purpose of improving storage security and increasing flexibility of use.

[0023] A processing method of a handler automatic alarm processing system based on image recognition comprises the following steps:

[0024] S1: Image acquisition. When the server receives the alarm information from the handler, each camera collects images at each location for logical judgment.

[0025] S2: Logical judgment, analyzing and processing the alarm through alarm information and processing logic;

[0026] S3: Return the processing result. The server terminal returns the judgment result to the handler plug-in;

[0027] S4: Resume production, the plug-in executes the instructions sent by the server and clears the alarm.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention utilizes image recognition and machine learning technology to identify Handler alarms, material conditions at the test position, material location information in the shuttle / boat, etc., and makes judgments through the logic set in the learning model, and finally executes the corresponding instructions according to one of the judgment results Retry, Skip and manual assistance. When the judgment result is Retry or Skip, the processing result can be returned to the simulated manual click plug-in on the handler. The plug-in will simulate manual clicks on the alarm information to clear the alarm, and the equipment can automatically resume production, thereby improving equipment efficiency. At the same time, by setting a data terminal to aggregate various alarm data of the production line handler, the learning iteration efficiency is accelerated and the accuracy is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] 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.

[0030] Figure 1 is a schematic diagram of the structure of a processing system in an embodiment of the present invention;

[0031] Figure 2It is a flow chart of a processing method of a handler automatic alarm processing system based on image recognition of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0034] Unless otherwise specifically stated, the relative arrangement of the parts and steps described in these embodiments, the numerical expressions and numerical values ​​do not limit the scope of the present invention. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship. The technology, methods and equipment known to ordinary technicians in the relevant field may not be discussed in detail, but in appropriate cases, the technology, methods and equipment should be regarded as a part of the authorization specification. In all examples shown and discussed here, any specific value should be interpreted as merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0035] In the description of the present invention, it is necessary to understand that the directions or positional relationships indicated by directional words such as "front, back, up, down, left, right", "lateral, vertical, perpendicular, horizontal" and "top, bottom" are usually based on the directions or positional relationships shown in the drawings. They are only for the convenience of describing the present invention and simplifying the description. Unless otherwise specified, these directional words do not indicate or imply that the devices or elements referred to must have a specific direction or be constructed and operated in a specific direction. Therefore, they cannot be understood as limiting the scope of protection of the present invention. The directional words "inside and outside" refer to the inside and outside relative to the contours of each component itself.

[0036] For ease of description, spatially relative terms such as "above", "above", "on the upper surface of", "above", etc. may be used here to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" may include both "above" and "below". The device may also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatially relative descriptions used here are interpreted accordingly.

[0037] In addition, it should be noted that the use of terms such as "first" and "second" to limit components is only for the convenience of distinguishing the corresponding components. If not otherwise stated, the above terms have no special meaning and therefore cannot be understood as limiting the scope of protection of the present invention.

[0038] The following is combined with Figure 1 and attached Figure 2 This application is described in further detail.

[0039] Reference Figure 1 and Figure 2 As shown, a handler automatic alarm processing system based on image recognition includes: an image acquisition module, a server and a simulated manual click plug-in. The image receiving module is used to receive the alarm information collected by the image acquisition module. The autonomous judgment module autonomously obtains the judgment result of the alarm information according to the learning model. The information recording module is used to record the alarm information and pictures. The simulated manual click plug-in chooses whether to clear the alarm according to the judgment result of the autonomous judgment module. The image acquisition module is composed of a plurality of cameras. The image acquisition module of the system composed of a plurality of cameras can be easily used to synchronously start the camera installed at the position according to the alarm position, so that the alarm information and material position information at a specific position can be targeted for image acquisition, ensuring that the collected data is more accurate.

[0040] Several cameras are installed at locations that contact materials such as the machine screen, test position, shuttle assembly and crystal boat, so that stable shooting of alarm information and material position can be achieved, thereby providing various image information for the server. By setting a camera on the machine screen, when the alarm is activated, the camera can directly shoot the alarm information on the machine screen to achieve the purpose of fast and accurate collection. By setting a camera on the test position, it is ensured that the material on the test position can be directly photographed when the equipment alarms. By installing a camera at the position of the shuttle assembly, it is convenient for the tool to shoot the material when moving the material during the manufacturing process. The crystal boat (BOAT) is a commonly used tool, mainly used for carrying, conveying, cleaning and processing chips. In this way, installing a camera on the crystal boat can shoot the material on the tool. Through the distribution of several cameras, it is ensured that when an alarm occurs in each processing section, the material position of the processing section can be quickly photographed to ensure the accuracy and timeliness of information collection.

[0041] BOAT is a tool used to carry and transport chips in the semiconductor manufacturing process. Its name "Crystal Boat" vividly describes its role in semiconductor manufacturing, just like a small boat (single wooden boat), responsible for carrying chips between different process steps. The manufacturing process of semiconductor chips usually requires a series of physical and chemical processes, such as high-temperature heating, cleaning, etching, drying, chemical treatment, etc. In order to transport chips from one process link to another, BOAT plays an important role.

[0042] After receiving the alarm information from the handler, the server can use the acquisition module to collect images of the alarm information and material location information. The collected image information can be sent to the server through the image receiving module in the server. After receiving the image information, the server can process the information through the autonomous judgment module to ensure that the autonomous judgment module can independently draw a judgment result on the alarm information based on the learning model. At the same time, the alarm information and pictures are recorded through the equipment information recording module as a backup to facilitate the traceability of the alarm information later. By simulating the setting of manual clicks on the plug-in, it is convenient to choose whether to start according to the judgment result of the autonomous judgment module. When it needs to be started, the alarm information can be cleared by simulating manual clicks on the alarm information, thereby achieving the purpose of automatic alarm processing of the machine.

[0043] The server is the main body of the system. By setting up an image receiving module, an autonomous judgment module and an information recording module in the server, the image receiving module in the server cooperates with the image acquisition module to receive the captured information to the server. At the same time, the photos and graphics received from each camera can be used as the basis for judging the alarm processing. The server processes the received information through the autonomous judgment module. The autonomous judgment module autonomously judges whether to Retry, Skip or manual assistance based on the learning model. At the same time, the alarm information and pictures are recorded through the information recording module for subsequent learning iterations, thereby increasing the accuracy of the model. By setting the judgment results of the autonomous judgment module to Retry, Skip and manual assistance, the Retry and Skip in the first two cases are rollback operations, which can reduce manual intervention, provide a fault-tolerant mechanism, and enhance the robustness of the system. When it is judged as a result of manual assistance, manual intervention is required.

[0044] The simulated manual click plug-in simulates manual clicks on the alarm information to clear the alarm. After clearing the alarm, the equipment will automatically resume production, eliminating the problems of manual operation errors and poor timeliness. The simulated manual click plug-in simulates manual clicks on the alarm information to clear the alarm when receiving the judgment result of Retry or Skip. When the autonomous judgment module judges the result as Retry or Skip, the server can start the rollback operation. The server starts the simulated manual click plug-in to simulate manual clicks on the alarm information to clear the alarm, so as to achieve the effect of automatic machine response processing. When manual assistance is needed, manual reset operation is required, thereby ensuring that this equipment can automatically judge and clear alarms based on image recognition technology and machine learning, thereby improving the OEE and equipment efficiency of the production line.

[0045] Overall equipment effectiveness (OEE) is essentially the ratio of actual qualified output to theoretical output within load time. The calculation of overall equipment effectiveness is the ratio of net production time of qualified products to total available production time. That is, overall equipment effectiveness not only examines the time utilization of equipment, but also examines the performance degradation and qualified product rate caused by operation and process. The automatic judgment and clearing of alarms by the machine can improve both process and time, which is beneficial to improving overall equipment effectiveness.

[0046] The server is provided with a data terminal connected to the information recording module. The data terminal is used to summarize various alarm data of the production line handler, and at the same time, the alarm data is classified according to the judgment result of the autonomous judgment module, so that the alarm data corresponds to the judgment result. By adopting the above technical solution, the data involved in the equipment operation process is sorted by setting a data terminal in the server, which is convenient for better tracing of each information in the later stage and increasing the reliability of the equipment. When summarizing the data, it is necessary to collect all the collected data, judgment data and execution data, and then classify and organize them according to the judgment result of the autonomous judgment module. The data terminal is provided with a data access module, which is used to access various alarm data classified and summarized by the data terminal. By setting the data access module in the data terminal, it is convenient to store the sorted data through the data access module when in use, and the stored data can be directly accessed, which effectively increases the traceability of the alarm information. The data access module is configured with a storage module, and the storage module includes a cloud storage unit and a local storage unit. The data access module can be used to store and organize information through the storage module, and the storage module can be set as a cloud storage unit and a local storage unit. This not only ensures that data storage is more secure, but also makes it easy to retrieve information by using cloud reading and downloading and local reading and downloading methods, thereby achieving the purpose of improving storage security and increasing flexibility of use. At the same time, a cloud communication module can also be set up, and the data communication of the cloud storage unit is performed through the communication module when used. The data communication between the cloud communication module and the cloud storage unit can be carried out in a wired or wireless manner. The data stored in the local storage unit can be directly displayed on the display device and then read, and can also be directly copied through hardware devices such as hard disks.

[0047] A processing method of a handler automatic alarm processing system based on image recognition comprises the following steps:

[0048] When an alarm occurs, the server receives the Handler alarm signal.

[0049] S1: Image acquisition. The camera collects images at various positions for logical judgment. At the same time, the information collected from different positions can be classified and transmitted. According to different classification and transmission methods, different contents of the images can be extracted. For example, the image of the machine screen only needs to extract the text alarm information on the image, while the images taken at the test position, shuttle assembly and crystal boat only need to extract the location information of the material. Classification can not only improve the accuracy of the information, but also increase the response speed.

[0050] S2: Logical judgment, analyzing and processing the alarm through alarm information and processing logic.

[0051] S3: Return the processing result. The server terminal returns the judgment result to the handler plug-in.

[0052] S4: Resume production, and the plug-in executes the command sent by the server to clear the alarm.

[0053] Working principle: The present invention is based on image recognition technology and uses machine learning to automatically determine and clear alarms, thereby improving the OEE and equipment efficiency of the production line. In actual use, cameras (as image acquisition modules) are installed on material contact points such as the machine screen, test position, shuttle, and boat. In this way, several cameras can be used to capture alarm information and material positions in real time, and the image signal is sent to the server for logical judgment. When the server determines that it is Retry or Skip, the processing result will be returned to the simulated manual click plug-in on the handler. The plug-in will simulate manual clicks on the alarm information to clear the alarm, and the equipment will automatically resume production, thereby improving equipment efficiency.

[0054] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A handler automatic alarm processing system based on image recognition, characterized in that: include: An image acquisition module, a server and a simulated manual click plug-in, wherein the image acquisition module is used to shoot alarm information, and the server is provided with an image receiving module, an autonomous judgment module and an information recording module, wherein the image receiving module is used to receive the alarm information collected by the image acquisition module; the autonomous judgment module autonomously obtains a judgment result on the alarm information according to a learning model; the information recording module is used to record the alarm information and pictures; and the simulated manual click plug-in selects whether to clear the alarm according to the judgment result of the autonomous judgment module.

2. According to the image recognition-based automatic alarm processing system of claim 1, it is characterized in that: The image acquisition module is composed of a plurality of cameras, and the plurality of cameras are respectively installed at a plurality of material contact positions.

3. According to the image recognition-based automatic alarm processing system of claim 2, it is characterized in that: The material contact parts include a machine screen, a test position, a shuttle assembly and a wafer boat.

4. The automatic alarm processing system for handlers based on image recognition according to claim 3 is characterized in that: The judgment result of the autonomous judgment module is one of Retry, Skip and manual assistance.

5. The automatic alarm processing system for handlers based on image recognition according to claim 4 is characterized in that: The simulated manual click plug-in simulates manual click on the alarm information to clear the alarm when receiving the judgment result of Retry or Skip.

6. The automatic alarm processing system for handlers based on image recognition according to claim 5 is characterized in that: The server is provided with a data terminal connected to the information recording module, and the data terminal is used to summarize various alarm data of the production line handler, and at the same time classify the alarm data according to the judgment result of the autonomous judgment module, so as to achieve the correspondence between the alarm data and the judgment result.

7. The automatic alarm processing system for handlers based on image recognition according to claim 6 is characterized in that: The data terminal is provided with a data access module, and the data access module is used to access various alarm data classified and summarized by the data terminal.

8. The automatic alarm processing system for handlers based on image recognition according to claim 7 is characterized in that: The data access module is configured with a storage module, and the storage module includes a cloud storage unit and a local storage unit.

9. A processing method of a handler automatic alarm processing system based on image recognition according to any one of claims 1 to 8, comprising the following steps: S1: Image acquisition. When the server receives the alarm information from the handler, each camera collects images at each location for logical judgment. S2: Logical judgment, analyzing and processing the alarm through alarm information and processing logic; S3: Return the processing result. The server terminal returns the judgment result to the handler plug-in; S4: Resume production, the plug-in executes the instructions sent by the server and clears the alarm.

Images