Production equipment data processing method and device, computer equipment and storage medium

Abstract

The invention relates to a production equipment data processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a state matching database of a production system and equipment monitoring data of at least one piece of production equipment; wherein the state matching database comprises historical state data and abnormal positioning information, and the abnormal positioning information is generated according to the historical state data of the multiple pieces of production equipment and the equipment association relationship between the multiple pieces of production equipment; determining an operation state trend of the production equipment according to the equipment monitoring data and the historical state data; under the condition that the running state trend is the running abnormal trend, generating abnormal source information according to the running state trend and the abnormal positioning information, and performing abnormal data processing according to the abnormal source information; wherein the abnormal source information is used for representing an abnormal reason of the production equipment. The method can improve the abnormity sensing accuracy of the production system.

Description

Technical Field

[0001] This application relates to the field of intelligent manufacturing technology, and in particular, to a method, device, computer device, storage medium, and computer program product for processing production equipment data. Background Art

[0002] At present, the development of the semiconductor industry has entered a highly automated and intelligent stage. The automated manufacturing method has greatly reduced the proportion of manual operations in the semiconductor production process, which is particularly evident in the wafer processing process, making the entire production process more coordinated and controllable, and also significantly improving the efficiency and safety.

[0003] Physically, except for operations that must be handled by professionals such as maintenance and inspection, during the wafer processing process, once the processing equipment starts running, it no longer needs to have any contact with people. Reducing manual operations in an industry like semiconductor production with multiple processes and high-precision requirements undoubtedly helps improve the product yield and operational productivity. In the process of production anomaly management, manual decision-making and operations still account for a large proportion. In related solutions, a monitoring and warning device is set for a certain production machine to complete the automated warning task instead of humans. The currently widely used Fault Detection and Classification (FDC) system, by implementing operating system interaction and integrating multiple functions such as data collection, defect detection, rule setting, alarm statistics, and data access, can already provide a certain degree of help for production in detecting equipment bad trends, monitoring project combinations, and supporting production data collection, achieving goals such as reducing product defects and scrap rates, reducing rework, and maximizing equipment utilization. Nevertheless, the main framework of this system is still based on the integration of multiple workflows and rules, and will still expose the problem of insufficient accuracy when facing new problems and new scenarios.

[0004] It can be seen that in the overall production process of the current related technologies, in the case of a production system including multiple production equipment, only setting an early warning mechanism independently for a certain production equipment cannot solve the problem of overall anomaly perception in the production system. The related technologies still lack overall anomaly perception and early warning, which leads to insufficient accuracy of anomaly perception when the current related technologies process a production system with multiple production equipment. Summary of the Invention

[0005] Based on this, it is necessary to provide a method, device, computer device, computer-readable storage medium, and computer program product for processing production equipment data that can improve the accuracy of anomaly perception in a production system for the above technical problems.

[0006] In a first aspect, the present application provides a method for processing production equipment data, which is applied to a production system. The production system includes multiple production equipment. The method includes:

[0007] Obtain the status matching database of the production system and the equipment monitoring data of at least one of the production equipment. Among them, the status matching database includes historical status data and abnormal location information, and the abnormal location information is generated according to the historical status data of multiple production equipment and the equipment association relationship between each production equipment;

[0008] Determine the operation status trend of the production equipment according to the equipment monitoring data and the historical status data;

[0009] In the case where the operation status trend is an abnormal operation trend, generate abnormal source information according to the operation status trend and the abnormal location information, and perform abnormal data processing according to the abnormal source information. Among them, the abnormal source information is used to characterize the abnormal cause of the production equipment.

[0010] In one embodiment, the step of generating abnormal source information according to the operation status trend and the abnormal location information in the case where the operation status trend is an abnormal operation trend includes:

[0011] In the case where the operation status trend is an abnormal operation trend, determine abnormal equipment according to the operation status trend and the equipment association relationship. Among them, the abnormal equipment includes at least one of the production equipment and the associated equipment of the production equipment;

[0012] In the case where the abnormal equipment includes the associated equipment, obtain the associated monitoring data of the associated equipment;

[0013] Generate abnormal source information according to the operation status trend and the associated monitoring data.

[0014] In one embodiment, the step of generating abnormal source information according to the operation status trend and the associated monitoring data includes:

[0015] Determine the associated status trend of the associated equipment according to the associated monitoring data and the historical status data of the associated equipment;

[0016] Combine the operation status trend and the associated status trend to extract status data features;

[0017] Input the status data features into an abnormal matching model to obtain abnormal source information. Among them, the abnormal matching model is trained according to historical abnormal causes and historical status data features.

[0018] In one embodiment, after generating the abnormal source information according to the operation state trend and the associated monitoring data, the method further includes:

[0019] In response to a matching data update instruction, updating the status matching database according to the operation state trend and the associated monitoring data.

[0020] In one embodiment, the abnormal data processing according to the abnormal source information includes:

[0021] Selecting an abnormal processing entity according to the abnormal source information and generating an abnormal warning message;

[0022] Outputting the abnormal warning message to the operation terminal corresponding to the abnormal processing entity.

[0023] In one embodiment, the selecting an abnormal processing entity according to the abnormal source information and generating an abnormal warning message includes:

[0024] Matching an abnormal processing method according to the abnormal source information;

[0025] Selecting an abnormal processing entity according to the abnormal processing method and generating an abnormal warning message.

[0026] In a second aspect, the present application further provides a production equipment data processing device, which is applied to a production system, and the production system includes a plurality of production equipment; the device includes:

[0027] A data acquisition module, configured to acquire the status matching database of the production system and the equipment monitoring data of at least one of the production equipment; wherein, the status matching database includes historical status data and abnormal location information, and the abnormal location information is generated according to the historical status data of the plurality of production equipment and the equipment association relationship between the production equipment;

[0028] A data analysis module, configured to determine the operation state trend of the production equipment according to the equipment monitoring data and the historical status data;

[0029] An abnormal processing module, configured to generate abnormal source information according to the operation state trend and the abnormal location information in the case that the operation state trend is an abnormal operation trend, and perform abnormal data processing according to the abnormal source information; wherein, the abnormal source information is used to characterize the abnormal reason of the production equipment.

[0030] In a third aspect, the present application further provides a computer device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0031] Obtain the status matching database of the production system and the device monitoring data of at least one of the production devices; wherein, the status matching database includes historical status data and abnormal location information, and the abnormal location information is generated according to the historical status data of multiple production devices and the device association relationships between the production devices;

[0032] Determine the operation status trend of the production device according to the device monitoring data and the historical status data;

[0033] In the case where the operation status trend is an abnormal operation trend, generate abnormal source information according to the operation status trend and the abnormal location information, and perform abnormal data processing according to the abnormal source information; wherein, the abnormal source information is used to represent the abnormal cause of the production device.

[0034] Fourthly, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0035] Obtain the status matching database of the production system and the device monitoring data of at least one of the production devices; wherein, the status matching database includes historical status data and abnormal location information, and the abnormal location information is generated according to the historical status data of multiple production devices and the device association relationships between the production devices;

[0036] Determine the operation status trend of the production device according to the device monitoring data and the historical status data;

[0037] In the case where the operation status trend is an abnormal operation trend, generate abnormal source information according to the operation status trend and the abnormal location information, and perform abnormal data processing according to the abnormal source information; wherein, the abnormal source information is used to represent the abnormal cause of the production device.

[0038] Fifthly, the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0039] Obtain the status matching database of the production system and the device monitoring data of at least one of the production devices; wherein, the status matching database includes historical status data and abnormal location information, and the abnormal location information is generated according to the historical status data of multiple production devices and the device association relationships between the production devices;

[0040] Determine the operation status trend of the production device according to the device monitoring data and the historical status data;

[0041] When the operating state trend is an abnormal operating trend, abnormal source information is generated based on the operating state trend and the abnormal location information, and abnormal data processing is performed according to the abnormal source information; wherein, the abnormal source information is used to characterize the cause of the abnormality of the production equipment.

[0042] The above production equipment data processing method, device, computer equipment, storage medium and computer program product are applied to a production system including multiple production equipment. By obtaining the status matching database of the production system and the device monitoring data of at least one production equipment; wherein, the status matching database includes historical status data and abnormal location information generated according to the historical status data of multiple production equipment and the device association relationship between each production equipment. According to the device monitoring data and historical status data, the operating state trend of the production equipment can be initially determined. When the operating state trend is an abnormal operating trend, abnormal source information is generated based on the operating state trend and the abnormal location information, so as to analyze and obtain the cause of the abnormality of the production equipment, and then abnormal data processing is performed according to the abnormal source information. Since the abnormal location information is generated according to the historical status data of multiple production equipment and the device association relationship between each production equipment, when using the abnormal location information to determine the cause of the abnormality, it is not an independent analysis of a single device, but an overall analysis of the abnormal cause for each related device in the production system. Therefore, the processing result of the subsequent abnormal data will be obtained from the perspective of the overall production system, thereby improving the accuracy of abnormal perception of the production system. Brief Description of the Drawings

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0044] Figure 1 It is an application environment diagram of the production equipment data processing method in an embodiment;

[0045] Figure 2 It is a flowchart of the production equipment data processing method in an embodiment;

[0046] Figure 3 It is a flowchart of step S206 of the production equipment data processing method in an embodiment;

[0047] Figure 4 It is a structural block diagram of the production equipment data processing device in an embodiment;

[0048] Figure 5Internal structure diagram of a computer device in an embodiment;

[0049] Figure 6 Internal structure diagram of a computer device in another embodiment. Detailed implementation manners

[0050] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. 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.

[0051] The production equipment data processing method provided by the embodiments of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The terminal 102 can be used to collect the device monitoring data of the production equipment and send the device monitoring data to the server 104 for analysis. The terminal 102 can also be used to obtain the data monitoring instructions from the manager and send the data monitoring instructions to the server 104 to trigger the server 104 to analyze the current device monitoring data. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers. The data storage system can be used to store the status matching database, and can also be used to store the device monitoring data, etc. Among them, the terminal 102 can be but is not limited to various sensors, such as temperature sensors, humidity sensors, and ranging devices, etc., and can also be various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers. The server 104 can implement the method provided by this application by deploying an AI large model. Generally speaking, an AI large model refers to a large neural network model in deep learning. These models are trained with a large amount of data and computing resources and have powerful language understanding and generation capabilities, and can be used for various natural language processing tasks, such as text generation, translation, summarization, question answering, etc. The full combination of the AI large model and industrial production is inseparable from the artificial intelligence agent (AI agent) module that glues the working core of AI with the requirements and logic in the actual production scenario. After receiving multimodal information, the artificial intelligence agent first uses the AI large model to parse the information, and then compares the analysis result with the pre-loaded requirements or records to obtain the processing method closest to the information requirement, and hands it over to the action end to put the latter into practice. This mode enables the AI large model to quickly adapt to the scenarios and requirements of any industry without changing the underlying logic of the model. Compared with the traditional FDC system, the accuracy of the AI agent is more dependent on the construction of the knowledge base and the method library, but it has an incomparable advantage in the aspect of self-learning.

[0052] However, the integration of current large AI models and industrial production has not been deep enough, and the potential of large AI models in this field has not been fully unleashed. Although at the physical level, various production equipment and supporting technologies are dazzling, their digital cores still lack key components of digital intelligence, and there is still a large gap in the support they can provide to information layer engineers. On the other hand, the integration of AI and work mainly stays on general tasks such as code filling, data collection, and text generation, lacking perception and intervention in professional work and being difficult to provide deeper support. Another point worth noting is that the learning and optimization of large AI models require sufficient data as support. The data middle platform or data pool can meet the relevant needs, but in industrial production, the digital twin platform, which serves as both a data terminal and a functional terminal, is undoubtedly more suitable for the data needs of large AI models and the production information environment. Therefore, it is more reasonable to use the digital twin platform to carry and integrate relevant resources and functions. Therefore, the embodiments of this application achieve autonomous warning and disposal through the combination of the digital twin platform and large AI models, aiming to achieve automated disposal through intelligent agents (AI Agents).

[0053] In an exemplary embodiment, as Figure 2 shown, a method for processing production equipment data is provided. Taking the method applied to the Figure 1 server 104 in it as an example for illustration, this method is applied to a production system. The production system includes multiple production devices and comprises the following steps S202 to step S206. Among them:

[0054] Step S202, obtain the status matching database of the production system and the device monitoring data of at least one production device.

[0055] Among them, the status matching database includes historical status data and anomaly location information. The historical status data refers to the operation records of each production device in the production system at different time points; the anomaly location information is generated based on the historical status data of multiple production devices and the device association relationships between production devices. The anomaly location information is not just a fault record of a certain device, but an anomaly location model derived by analyzing the operation relationships and influencing factors between multiple production devices based on their historical status data. For example, if there are process associations on the production line among multiple devices in a certain production system, the status matching database will store the historical operation trends between these devices and obtain the possible propagation paths of anomalies through statistical analysis.

[0056] Exemplarily, the server 104 can store the state matching database of the production system through the digital twin platform. The digital twin platform, as a data center, stores all relevant data to form the state matching database. Specifically, during the production process, the sensor terminals corresponding to each production device can continuously monitor and collect a large amount of operation data, which can cover multiple dimensions, including environmental parameters, device status, process control information, etc. For example, the temperature sensor continuously monitors the temperature change inside the device, and the humidity sensor tracks the air humidity to ensure that the production environment meets strict process requirements. In addition, the vibration sensor and current monitoring module on the device can be used to detect the wear state of the tool. For example, if the etching head of an etching machine wears, its vibration mode and current consumption will be different from the normal state. For the production process, the server 104 also records the time interval of the wafer entering and leaving different devices to ensure a stable process rhythm and avoid abnormal backlogs or idling. The collection of all these data mainly focuses on PCS (Process Control System) data and KPP (Key Process Parameter). Among them, PCS focuses on the control of the entire production process, such as the start and stop state of the device, process recipe adjustment, etc., while KPP focuses on the core variables that directly affect product quality during production, such as etching rate, lithography exposure time, deposition thickness, etc.

[0057] Exemplarily, the server 104 can respond to the data monitoring instruction from the terminal 102, so as to obtain the device monitoring data of the production equipment from the corresponding sensor terminal. The server 104 can also periodically and automatically obtain the device monitoring data of the production equipment from the sensor terminal. Specifically, after receiving the data monitoring instruction from the terminal 102, the server 104 can actively request the real-time monitoring data of the production equipment from the corresponding sensor terminal. For example, in the wafer manufacturing process, each device is equipped with multiple sensors for monitoring key parameters such as temperature, pressure, current, and vibration. When the terminal 102 issues a query request, the server 104 will, according to this instruction, send a data collection instruction to the sensor terminal of the target device, requiring the sensor to report the latest operation data. Suppose the temperature sensor of an etching machine detects an abnormal temperature. The server 104 can immediately receive this data and store it in the status matching database as an important reference for subsequent anomaly analysis. In order to ensure that the anomaly perception ability of the production system does not depend on manual operation, the server 104 can not only respond to specific monitoring instructions, but also periodically and automatically obtain the operation data of the production equipment from the sensor terminal. Even without an external request, the server 104 will actively collect data from the sensor terminals of each production equipment at set time intervals, such as every 10 seconds, 30 seconds, or 1 minute, so as to ensure the real-time and continuity of the device operation status. For example, on a production line including lithography machines, etching machines, and spin coater / developers, the server 104 will regularly collect the key operation parameters of all devices and compare them with the historical status data to determine whether there is an abnormal trend in the devices. In this way, even if the anomalies in the initial stage of device operation have not reached the alarm threshold, the server 104 can detect possible abnormal signs in advance through the slight fluctuations of the data, and then provide data support for subsequent anomaly analysis and processing.

[0058] Furthermore, after receiving the data from these sensors, the server 104 can transmit it to the digital twin platform, which is not only responsible for virtual modeling of the production process, but also serves as the storage and analysis center of the data. In terms of data storage, all the collected device monitoring data will enter the data middle platform, which is similar to the "data warehouse" of the production system. It can classify and store data from different sources, and at the same time support subsequent rapid retrieval and calculation. On this basis, the AI Memory module undertakes a further task. It is not only a storage unit, but also a smart module dedicated to efficient recall and comparison. AI Memory can sort and index the stored data so that it can be quickly matched with the historical data for subsequent anomaly analysis.

[0059] Exemplarily, if there is a slight deviation in the exposure time of a certain lithography machine on a certain day, AI Memory can quickly retrieve the exposure data under the same historical conditions and determine whether this deviation is within the normal fluctuation range or may cause process problems. In this way, while receiving data, server 104 can use the AI Memory module to perform intelligent data management to form and update the above-mentioned status matching database.

[0060] Step S204: Determine the operation status trend of the production equipment according to the equipment monitoring data and historical status data.

[0061] Exemplarily, server 104 can periodically send analysis requests to the AI large model application framework through the digital twin platform, so as to use machine learning and big data analysis technologies to perform feature recognition and trend judgment on the equipment monitoring data and historical status data. Server 104 can initiate requests based on a fixed time interval (such as once an hour), or dynamically adjust the frequency according to the specific data fluctuations indicated by the equipment monitoring data to ensure that the monitoring of the equipment status is both timely and does not cause waste of computing resources. When receiving the analysis request, server 104 can extract relevant data from the status matching database, including the real-time equipment monitoring data, historical status data, etc. of the equipment. Subsequently, server 104 can perform feature extraction on these data, such as analyzing the fluctuation range of key process parameters (KPP), identifying abnormal patterns in the process control system (PCS) data, and judging whether certain abnormalities have systematic effects.

[0062] Furthermore, after the data processing is completed, server 104 can output various analysis results to display the operation status trend, which can be data visualization analysis charts, such as production trend line charts, scatter charts with abnormal point markings, heat maps of correlation analysis, etc. These charts can help engineers intuitively view the change trend of the equipment status; it can also be an analysis report described in natural language. Server 104 can generate a structured text report based on the data analysis results, which contains information such as the current equipment status, abnormal trend, and predicted influence range.

[0063] Step S206: In the case where the operation status trend is an abnormal operation trend, generate abnormal source information according to the operation status trend and abnormal location information, and perform abnormal data processing according to the abnormal source information.

[0064] Among them, the abnormal source information is used to characterize the abnormal cause of the production equipment.

[0065] Exemplarily, when the operation status trend of the server 104 is an abnormal operation trend through the AI large model intelligent agent (AI Agent), the abnormal devices can be determined according to the operation status trend and the device association relationship; wherein, the abnormal devices include at least one of production devices and associated devices of production devices; when the abnormal devices include associated devices, the associated monitoring data of the associated devices is obtained; and the abnormal source information is generated according to the operation status trend and the associated monitoring data.

[0066] Furthermore, the server 104 can determine specific abnormal devices through the AI large model intelligent agent (AI Agent) according to the identified abnormal operation trend, in combination with the historical state data of the devices and the device topology relationship of the production system. Among them, the abnormal devices can be devices that directly show abnormalities. For example, the gas flow control system of a certain etching machine fluctuates. It can also be an indirect abnormality caused by the abnormality of other devices. For example, the alignment error of a lithography machine may be caused by the unevenness of the previous coating process. Therefore, the server 104 not only analyzes the abnormal data of a single device, but also checks the associated devices of the production device in the entire production chain, that is, the production system, to ensure more accurate judgment of the abnormal source.

[0067] After the scope of the abnormal devices is determined, the server 104 can further obtain the associated monitoring data of these production devices. These data may come from multiple sensors or process control system (PCS) logs. Exemplarily, if the pressure in the vacuum chamber of a certain etching machine is abnormal, the server 104 can track the monitoring data of its fore pump and gas flow control module to determine whether the problem comes from the vacuum system itself or from the fluctuation of the gas supply system. In addition, if it is found that the exposure time of a certain lithography machine fluctuates, the server 104 can check the power stability of the light source and whether there is a temperature change affecting the curing effect of the photoresist.

[0068] After obtaining the data of the associated devices, the server 104 can further analyze through the AI large model intelligent agent (AI Agent) in combination with the operation status trend and these data, and generate abnormal source information. These abnormal source information are not just simple device failure descriptions, but are based on the abnormal transmission path of the overall production system. For example, the server 104 can draw the following conclusion: "The main reason for the current fluctuation of the exposure time of the lithography machine is the unstable rotation coating speed of the previous coating machine, resulting in a deviation in the thickness of the photoresist, which in turn affects the optical uniformity during the exposure process." This analysis method avoids isolated judgment only for a single device, but analyzes the abnormal source from the perspective of the entire production system, improving the accuracy of abnormal perception and the scientific nature of fault diagnosis.

[0069] In the above production equipment data processing method, it is applied to a production system including multiple production equipment, and obtains the status matching database of the production system and the equipment monitoring data of at least one production equipment; wherein, the status matching database includes historical status data and abnormal location information generated according to the historical status data of multiple production equipment and the equipment association relationship between each production equipment. According to the equipment monitoring data and historical status data, the operation status trend of the production equipment can be initially determined. In the case where the operation status trend is an abnormal operation trend, abnormal source information is generated according to the operation status trend and the abnormal location information, so as to analyze the abnormal cause of the production equipment, and then abnormal data processing is performed according to the abnormal source information. Since the abnormal location information is generated according to the historical status data of multiple production equipment and the equipment association relationship between each production equipment, when determining the abnormal cause using the abnormal location information, it is not an independent analysis for a single equipment, but an overall analysis of the abnormal cause for each related equipment in the production system. Therefore, the processing result of the subsequent abnormal data will be obtained from the perspective of the overall production system, thereby improving the accuracy of abnormal perception of the production system. The combination of the AI large model and digital twin further improves the self-learning ability and intelligent level of the data processing process.

[0070] In an exemplary embodiment, as Figure 3 shown, the above steps of generating abnormal source information according to the operation status trend and the associated monitoring data may include step S302 to step S306. Among them:

[0071] Step S302, determine the associated status trend of the associated equipment according to the associated monitoring data and the historical status data of the associated equipment.

[0072] Exemplarily, the server 104 can determine the associated status trend of the associated equipment based on the associated monitoring data and the historical status data of the associated equipment through the AI large model intelligent agent (AI Agent). When an abnormality occurs in a production equipment, it is often not just a problem of a single equipment, but may also be closely related to the status changes of other related equipment. Therefore, the server 104 can extract the monitoring data of its associated equipment according to the equipment related to the current abnormality through the AI large model intelligent agent (AI Agent), and combine the historical status data to analyze the operation status trend of these equipment.

[0073] For example, when a problem occurs in the etcher, the server 104 can check the status data of the previous cleaning machine and the subsequent lithography machine. By analyzing the monitoring data of these devices, the server 104 can determine whether their operating status has changed and generate a status trend of related devices based on this data. If fluctuations occur in the operating time, pressure parameters, or other key process conditions of the cleaning machine, which may affect the subsequent etching process, the server 104 can identify the potential connections of these status changes and then form a more comprehensive associated status trend.

[0074] Step S304: Combine the operating status trend and the associated status trend to extract status data features.

[0075] Exemplarily, the server 104 can extract status data features by combining the current operating status trend and the status trend of related devices through an AI large model intelligent agent (AI Agent). The status data features can include the operating parameters of the device, process control data, and other key factors affecting production. For example, the server 104 may extract specific change patterns from environmental factors such as temperature, humidity, and air pressure, or obtain status features from aspects such as the workload, operating duration, and failure rate of the device. By analyzing these features, the server 104 can discover the trend changes in the device status, thereby providing a basis for subsequent abnormal source location.

[0076] Step S306: Input the status data features into the anomaly matching model to obtain anomaly source information.

[0077] Among them, the anomaly matching model is trained based on historical anomaly causes and historical status data features.

[0078] Exemplarily, the server 104 can vectorize these status data features through an AI large model intelligent agent (AI Agent) and then input them into the anomaly matching model. Subsequently, the server 104 can obtain anomaly source information through model analysis. The anomaly matching model is trained based on historical anomaly causes and historical status data features and can identify which status features are highly correlated with past abnormal situations. The model determines whether an anomaly is caused by certain known reasons by comparing the currently input status data features with the patterns in the historical data. If the model identifies that the currently input status data features match a certain historical anomaly pattern, the server 104 can infer the possible source of the anomaly based on the matching result.

[0079] Furthermore, the server 104 discovers that the chamber pressure fluctuation of the current etcher is extremely similar to a certain past alignment error of the lithography machine, and there is an obvious equipment correlation between the two. The above model can give information about the source of the anomaly, indicating that the alignment error of the lithography machine may cause the instability of the etcher's operation. In this way, the server 104 can accurately identify the root cause of the anomaly and provide a basis for subsequent anomaly handling in a timely manner. The server 104 can generate detailed information about the source of the anomaly based on the output of the anomaly matching model, use the trained anomaly matching model to accurately identify the root cause of the anomaly, and improve the anomaly perception ability of the entire production system.

[0080] In an exemplary embodiment, the server 104 can also select an anomaly handling entity according to the information about the source of the anomaly and generate an anomaly warning message; output the anomaly warning message to the operation terminal corresponding to the anomaly handling entity. Exemplarily, the server 104 can match an anomaly handling method according to the information about the source of the anomaly; select an anomaly handling entity according to the anomaly handling method and generate an anomaly warning message.

[0081] Furthermore, after the information about the source of the anomaly is generated, the server 104 can further trigger an anomaly data processing process through the AI large model intelligent agent (AI Agent). This processing process may include the following methods: if the anomaly has a small impact, the server 104 can perform adaptive adjustment through parameter fine-tuning, such as appropriately compensating the exposure time during the lithography exposure process; if the anomaly has a large impact, the server 104 can send a warning to the engineer to prompt equipment inspection and maintenance. For example, when there is a pressure fluctuation in the vacuum system of the etcher, the server 104 can suggest checking the working state of the vacuum pump and even arranging shutdown maintenance. In addition, in some cases, if the anomaly is determined to be caused by equipment aging or component damage, the server 104 can also trigger the spare parts management system to schedule the replacement of relevant components in advance to reduce the impact of unplanned downtime. Through this holistic analysis and processing method, the server 104 can accurately identify the root cause of the problem in the early stage of the anomaly occurrence and take corresponding countermeasures according to the information about the source of the anomaly, thereby improving the stability and production efficiency of the entire production system.

[0082] Exemplarily, after generating the abnormal source information, the server 104 can first determine a suitable abnormal handling entity through the AI large model intelligent agent (AI Agent) and accurately push the abnormal warning information to the corresponding operation terminal. First, the server 104 can analyze the category, impact range, and possible liability attribution of the abnormality based on the abnormal source information. On this basis, the server 104 can screen out the entity most suitable for handling this abnormality. For abnormalities that can be resolved through automatic adjustment, such as the exposure time deviation of a lithography device, the server 104 can preferentially select the process control system (PCS) as the handling entity and directly push the adjustment instruction to enable the device parameters to be adaptively optimized. If the abnormality involves a hardware failure, such as a decrease in the vacuum chamber pressure of an etcher, the server 104 can send the abnormal information to the corresponding maintenance engineer to remind them to check or repair. In addition, if the abnormality may affect the entire production schedule, such as a key device may experience a long-term downtime, the server 104 can push a warning to the production scheduling system to adjust the production plan and reduce production capacity losses.

[0083] After determining the abnormal handling entity, the server 104 can generate detailed abnormal warning information to ensure that the handling entity can accurately understand the abnormal situation and take measures promptly. The warning information can include the identifiers of the abnormal device and its associated devices to enable the handling entity to clarify the affected range. For example, the server 104 can mark the abnormality of the etcher A12 and point out that the abnormality of this device may be related to the drying process of the previous cleaner B07. In addition, the server 104 can also provide key monitoring data and trend analysis, such as the chamber pressure has dropped to 80% of the normal level in the past 30 minutes. Based on historical data and device association relationships, the server 104 can give the possible source of the abnormality, such as speculating that the vacuum pump may have a reduced pumping efficiency due to aging. To help the abnormal handling entity respond faster, the server 104 can also attach an impact range assessment, such as this abnormality may cause a 5% reduction in the etching rate and affect the alignment accuracy of the subsequent lithography process. Further, the server 104 can also provide recommended handling solutions, such as suggesting checking the status of the vacuum pump and replacing relevant components if necessary to restore the normal operation of the device. Further, when the warning information is ready, the server 104 can push it to the operation terminal corresponding to the abnormal handling entity to take measures in a timely manner. For the operation and maintenance engineer, the server 104 can send the abnormal information to the operation and maintenance platform of the factory management system, enabling the engineer to view the detailed information on the system interface and respond.

[0084] In an exemplary embodiment, after the server 104 generates the abnormal source information through the AI large model intelligent agent (AI Agent) based on the operation state trend and the associated monitoring data, in response to the matching data update instruction, the server 104 updates the state matching database according to the operation state trend and the associated monitoring data.

[0085] Exemplarily, in order to improve the accuracy of subsequent anomaly detection and the self-learning ability of the system, the server 104 can update the state matching database after generating the abnormal source information. The server 104 can respond to the matching data update instruction, start the state update process, and analyze the health status and possible abnormal patterns of the current production equipment according to the latest operation state trend. The server 104 can compare the characteristics of the current anomaly, such as the environmental parameters, equipment operation parameters, and time series data when the anomaly occurs, and match them with the existing historical state data to determine whether there are similar historical anomaly records. If the current anomaly has new characteristics, such as a new type of anomaly that first appears under a certain specific process condition, the server 104 can mark it as a new anomaly pattern and add a corresponding state record to the database.

[0086] During the update process, the server 104 not only simply stores new data points, but also combines the associated monitoring data to optimize the abnormal propagation relationship between devices to update the anomaly location information. For example, if the server 104 finds that the abnormal decrease in the chamber pressure of an etcher is always accompanied by the fluctuation of the drying time of the previous cleaning machine, then the server 104 can strengthen the association between the two in the state matching database for more accurate anomaly tracing in the future. This optimization is not limited to a single device, but is applicable to the entire production system. For example, when the server 104 detects an increase in the alignment error of a lithography device, and this error is more likely to occur under certain photoresist formulations or specific humidity conditions, it will establish a new association between these environmental variables and the abnormal state to make the database more comprehensive.

[0087] After completing the update of the association relationship between abnormal features and devices, the server 104 can also perform data cleaning and optimization through the AI large model intelligent agent (AI Agent) to ensure the efficient operation of the database. The server 104 can automatically identify redundant or low-correlation historical data, filter out outdated data that no longer matches the current production environment, and archive or eliminate it. In addition, the server 104 can also use machine learning algorithms to extract patterns and classify historical data, grouping similar anomalies into the same category to improve query and matching efficiency. After all update operations are completed, the server 104 can synchronize the latest state matching database to the digital twin platform, enabling subsequent anomaly detection and trend analysis to be deduced based on the latest production data, so that the anomaly location data can be continuously updated as the production environment changes, thereby optimizing the anomaly recognition ability, improving the overall perception accuracy of the production system, and ultimately enhancing the intelligent level of semiconductor manufacturing.

[0088] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps is not strictly restricted by order, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0089] Based on the same inventive concept, the embodiments of the present application also provide a production equipment data processing device for implementing the production equipment data processing method described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more of the following embodiments of the production equipment data processing device can refer to the limitations on the production equipment data processing method in the above text, and will not be repeated here.

[0090] In an exemplary embodiment, as Figure 4 shown, a production equipment data processing device is provided. This device is applied to a production system, and the production system includes multiple production equipment; the device includes: a data acquisition module 402, a data analysis module 404, and an anomaly processing module 406, where:

[0091] A data acquisition module 402, configured to acquire a status matching database of a production system and device monitoring data of at least one production device; wherein, the status matching database includes historical status data and anomaly location information, and the anomaly location information is generated according to the historical status data of multiple production devices and the device association relationship between each production device;

[0092] A data analysis module 404, configured to determine the operation status trend of a production device according to the device monitoring data and the historical status data;

[0093] An anomaly handling module 406, configured to generate anomaly source information according to the operation status trend and the anomaly location information and perform anomaly data processing according to the anomaly source information when the operation status trend is an operation anomaly trend; wherein, the anomaly source information is used to characterize the anomaly cause of a production device.

[0094] In one embodiment, the anomaly handling module 406 includes:

[0095] A device determination unit, configured to determine an anomalous device according to the operation status trend and the device association relationship when the operation status trend is an operation anomaly trend; wherein, the anomalous device includes at least one of a production device and an associated device of the production device;

[0096] A data detection unit, configured to acquire associated monitoring data of an associated device when the anomalous device includes an associated device;

[0097] An information generation unit, configured to generate anomaly source information according to the operation status trend and the associated monitoring data.

[0098] In one embodiment, the information generation unit is specifically configured to: determine the associated status trend of an associated device according to the associated monitoring data and the historical status data of the associated device; combine the operation status trend and the associated status trend, and extract status data features; input the status data features into an anomaly matching model to obtain anomaly source information; wherein, the anomaly matching model is trained according to historical anomaly causes and historical status data features.

[0099] In one embodiment, the information generation unit is further configured to: in response to a matching data update instruction, update the status matching database according to the operation status trend and the associated monitoring data.

[0100] In one embodiment, the anomaly handling module 406 further includes: an anomaly warning subunit, configured to select an anomaly handling entity according to the anomaly source information and generate an anomaly warning information; and output the anomaly warning information to the operation end corresponding to the anomaly handling entity.

[0101] In one of the embodiments, the abnormal warning subunit is further configured to: match an abnormal handling method according to the abnormal source information; select an abnormal handling entity according to the abnormal handling method and generate an abnormal warning message.

[0102] Each module in the above production equipment data processing device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0103] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store a status matching database, and can also be used to store device monitoring data, etc. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a production equipment data processing method is implemented.

[0104] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 6As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for processing production equipment data. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0105] Those skilled in the art can understand that Figure 6 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0106] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented: obtaining a status matching database of the production system and device monitoring data of at least one production device; wherein, the status matching database includes historical status data and abnormal location information, and the abnormal location information is generated according to the historical status data of multiple production devices and the device association relationship between each production device; determining the operation status trend of the production device according to the device monitoring data and the historical status data; in the case where the operation status trend is an abnormal operation trend, generating abnormal source information according to the operation status trend and the abnormal location information, and performing abnormal data processing according to the abnormal source information; wherein, the abnormal source information is used to characterize the abnormal cause of the production device.

[0107] In one embodiment, when the processor executes the computer program, the following steps are further implemented: in the case where the operation status trend is an abnormal operation trend, determine the abnormal device according to the operation status trend and the device association relationship; wherein, the abnormal device includes at least one of the production device and the associated device of the production device; in the case where the abnormal device includes the associated device, obtain the associated monitoring data of the associated device; generate the abnormal source information according to the operation status trend and the associated monitoring data.

[0108] In one embodiment, when the processor executes the computer program, the following steps are further implemented: determine the associated status trend of the associated device according to the associated monitoring data and the historical status data of the associated device; combine the operation status trend and the associated status trend to extract the status data features; input the status data features into the abnormal matching model to obtain the abnormal source information; wherein, the abnormal matching model is trained according to the historical abnormal reasons and the historical status data features.

[0109] In one embodiment, when the processor executes the computer program, the following steps are further implemented: in response to the matching data update instruction, update the status matching database according to the operation status trend and the associated monitoring data.

[0110] In one embodiment, when the processor executes the computer program, the following steps are further implemented: select the abnormal handling entity according to the abnormal source information and generate the abnormal warning information; output the abnormal warning information to the operation end corresponding to the abnormal handling entity.

[0111] In one embodiment, when the processor executes the computer program, the following steps are further implemented: match the abnormal handling method according to the abnormal source information; select the abnormal handling entity according to the abnormal handling method and generate the abnormal warning information.

[0112] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the following steps are implemented: obtain the status matching database of the production system and the device monitoring data of at least one production device; wherein, the status matching database includes the historical status data and the abnormal location information, and the abnormal location information is generated according to the historical status data of multiple production devices and the device association relationship between each production device; determine the operation status trend of the production device according to the device monitoring data and the historical status data; in the case where the operation status trend is an abnormal operation trend, generate the abnormal source information according to the operation status trend and the abnormal location information, and perform abnormal data processing according to the abnormal source information; wherein, the abnormal source information is used to represent the abnormal reason of the production device.

[0113] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: when the operation state trend is an abnormal operation trend, determine an abnormal device according to the operation state trend and the device association relationship; wherein, the abnormal device includes at least one of a production device and an associated device of the production device; when the abnormal device includes an associated device, obtain the associated monitoring data of the associated device; generate abnormal source information according to the operation state trend and the associated monitoring data.

[0114] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determine the associated state trend of the associated device according to the associated monitoring data and the historical state data of the associated device; combine the operation state trend and the associated state trend to extract state data features; input the state data features into an abnormal matching model to obtain abnormal source information; wherein, the abnormal matching model is trained according to historical abnormal causes and historical state data features.

[0115] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: in response to a matching data update instruction, update the state matching database according to the operation state trend and the associated monitoring data.

[0116] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: select an abnormal handling entity according to the abnormal source information and generate an abnormal warning message; output the abnormal warning message to the operation terminal corresponding to the abnormal handling entity.

[0117] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: match an abnormal handling method according to the abnormal source information; select an abnormal handling entity according to the abnormal handling method and generate an abnormal warning message.

[0118] In one embodiment, a computer program product is provided, including a computer program, which when executed by a processor, implements the following steps: obtain the state matching database of the production system and the device monitoring data of at least one production device; wherein, the state matching database includes historical state data and abnormal location information, and the abnormal location information is generated according to the historical state data of multiple production devices and the device association relationship between each production device; determine the operation state trend of the production device according to the device monitoring data and the historical state data; when the operation state trend is an abnormal operation trend, generate abnormal source information according to the operation state trend and the abnormal location information, and perform abnormal data processing according to the abnormal source information; wherein, the abnormal source information is used to represent the abnormal cause of the production device.

[0119] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: when the running state trend is an abnormal running trend, determine the abnormal device according to the running state trend and the device association relationship; wherein, the abnormal device includes at least one of the production device and the associated device of the production device; when the abnormal device includes an associated device, obtain the associated monitoring data of the associated device; generate abnormal source information according to the running state trend and the associated monitoring data.

[0120] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determine the associated state trend of the associated device according to the associated monitoring data and the historical state data of the associated device; combine the running state trend and the associated state trend to extract state data features; input the state data features into an abnormal matching model to obtain abnormal source information; wherein, the abnormal matching model is trained according to historical abnormal reasons and historical state data features.

[0121] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: in response to a matching data update instruction, update the state matching database according to the running state trend and the associated monitoring data.

[0122] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: select an abnormal handling entity according to the abnormal source information and generate an abnormal warning message; output the abnormal warning message to the operation terminal corresponding to the abnormal handling entity.

[0123] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: match the abnormal handling method according to the abnormal source information; select the abnormal handling entity according to the abnormal handling method and generate an abnormal warning message.

[0124] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0125] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0126] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0127] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for processing production equipment data, characterized in that: The method is applied to a production system, which includes a plurality of production equipments; the method includes: Acquire a state matching database of the production system and equipment monitoring data of at least one of the production equipment; wherein the state matching database includes historical state data and abnormality location information, and the abnormality location information is generated based on the historical state data of multiple production equipment and the equipment association relationship between each of the production equipment; Determining the operating status trend of the production equipment according to the equipment monitoring data and the historical status data; In the case where the operating status trend is an abnormal operating trend, abnormal source information is generated according to the operating status trend and the abnormal location information, and abnormal data processing is performed according to the abnormal source information; wherein the abnormal source information is used to characterize the abnormal cause of the production equipment.

2. The method according to claim 1, characterized in that When the running state trend is an abnormal running trend, generating abnormal source information according to the running state trend and the abnormal location information includes: In the case where the operation status trend is an abnormal operation trend, an abnormal device is determined according to the operation status trend and the device association relationship; wherein the abnormal device includes at least one of the production device and an associated device of the production device; In a case where the abnormal device includes the associated device, acquiring associated monitoring data of the associated device; Abnormal source information is generated based on the operating status trend and the associated monitoring data.

3. The method according to claim 2, characterized in that The generating of abnormal source information according to the operating status trend and the associated monitoring data includes: Determining an association status trend of the associated device according to the association monitoring data and the historical status data of the associated device; extracting state data features by combining the operating state trend and the associated state trend; The state data features are input into an anomaly matching model to obtain anomaly source information; wherein the anomaly matching model is trained based on historical anomaly causes and historical state data features.

4. The method according to claim 2, characterized in that: After generating the abnormal source information according to the operating status trend and the associated monitoring data, the method further includes: In response to a matching data update instruction, the state matching database is updated according to the operating state trend and the associated monitoring data.

5. The method according to any one of claims 1 to 4, characterized in that: The performing abnormal data processing according to the abnormal source information includes: Select an exception handling subject according to the exception source information and generate exception warning information; The abnormal warning information is output to the operation terminal corresponding to the abnormal processing subject.

6. The method according to claim 5, characterized in that The selecting an exception processing subject according to the exception source information and generating exception warning information includes: Matching an exception handling method according to the exception source information; An exception handling subject is selected according to the exception handling method and exception warning information is generated.

7. A production equipment data processing device, characterized in that: The device is applied to a production system, which includes a plurality of production equipments; the device includes: A data acquisition module, used to acquire a state matching database of the production system and equipment monitoring data of at least one of the production equipment; wherein the state matching database includes historical state data and abnormality location information, and the abnormality location information is generated based on the historical state data of multiple production equipment and the equipment association relationship between each of the production equipment; A data analysis module, used to determine the operating status trend of the production equipment based on the equipment monitoring data and the historical status data; An exception processing module is used to generate exception source information according to the operation status trend and the exception location information when the operation status trend is an operation abnormality trend, and perform exception data processing according to the exception source information; wherein the exception source information is used to characterize the abnormal cause of the production equipment.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images