Semiconductor scheduling algorithm model configuration system, method, device and medium

Abstract

The invention relates to the technical field of semiconductor manufacturing, in particular to a semiconductor scheduling algorithm model configuration system, method and equipment and a medium. The system comprises a data configuration module, an algorithm configuration module, a parameter analysis module, a task scheduling module, a data acquisition module, a model execution module and a result processing module. The data configuration module receives data model configuration parameters input by a user; the algorithm configuration module receives algorithm model configuration parameters. The parameter analysis module analyzes parameters and generates a data preprocessing rule and an algorithm model instance, the task scheduling module creates a scheduling task and triggers a process, the data acquisition module acquires original data from a source data table and preprocesses the original data, the model execution module executes a scheduling algorithm based on the algorithm instance, and the result processing module outputs standard data. According to the invention, decoupling of the data and the algorithm is realized, and the adaptability and expandability of the system are improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of semiconductor manufacturing, and particularly relates to a semiconductor scheduling algorithm model configuration system, method, device and medium. BACKGROUND

[0002] In the field of semiconductor manufacturing, scheduling algorithms are key tools for optimizing production processes, improving equipment utilization, and shortening delivery cycles. In the prior art, semiconductor scheduling usually relies on commercial software or customized solutions. These systems support dynamic scheduling and equipment load balancing, but there are significant deficiencies in algorithm model configuration. Common configuration strategies are limited to allowing users to check certain business objectives (such as processing completion as soon as possible or high priority first) or simple restrictions on material resources (such as specifying upper limits for machine processing), resulting in a high coupling between data parameters and algorithm models, which cannot be independently configured. This coupling results in repeated definition of data parameters, poor scalability, and the need to rebuild models when new business scenarios are added, increasing development costs and operational complexity. At the same time, existing systems lack global constraint configuration, focusing more on resource constraints and ignoring overall optimization goals, and the operation interface is complex, requiring high technical requirements for business personnel and a significant use threshold. These deficiencies collectively result in a lack of flexibility and low efficiency in semiconductor scheduling systems when adapting to changing business scenarios. SUMMARY

[0003] The technical problem to be solved by the present application is to provide a semiconductor scheduling algorithm model configuration system, method, device and medium to address the deficiencies in the prior art, to solve the high coupling between data parameters and algorithm models, to achieve independent parameter configuration and modular reuse, and to improve system adaptability, reduce operational difficulty and enhance scalability.

[0004] The first aspect of the present application discloses a semiconductor scheduling algorithm model configuration system, comprising: a data configuration module for receiving user input data model configuration parameters, the data model configuration parameters including a data item set, a data item type and a data item action range, wherein the data item set is used to specify the data type to be processed, including wafer batch data, machine data or processing relationship data, the data item type includes a filtering type, a priority type or a supplement type, and the data item action range is used to mark the machine processing mode; an algorithm configuration module for receiving user input algorithm model configuration parameters, the algorithm model configuration parameters including target class parameters and constraint class parameters, wherein the target class parameters are used to define optimization goals and their priority weights, and the constraint class parameters are used to define business constraints and their variable parameters; A parameter analysis module, connected with the data configuration module and the algorithm configuration module, is configured to analyze the data model configuration parameters and the algorithm model configuration parameters, and generate data preprocessing rules and algorithm model instances; A task scheduling module, connected with the parameter analysis module, is configured to create scheduling tasks based on the analyzed parameters, and trigger data acquisition operations of the data acquisition module and scheduling algorithm execution operations of the model execution module, wherein the model execution module is configured to execute based on the algorithm model instances generated by the parameter analysis module; A data acquisition module, connected with the task scheduling module, is configured to acquire raw data from a source data table, and filter and convert the raw data according to the data preprocessing rules, to generate preprocessed data; A model execution module, connected with the data acquisition module and the parameter analysis module, is configured to execute scheduling algorithms according to the algorithm model instances and the preprocessed data, to generate scheduling results; A result processing module, connected with the model execution module, is configured to post-process the scheduling results, and convert them into standard output data; The data configuration module, the algorithm configuration module, the parameter analysis module, the task scheduling module, the data acquisition module, the model execution module, and the result processing module are connected through parameter transmission and event triggering, so that the data model configuration parameters are independent of the algorithm model configuration parameters, but can be dynamically associated through shared variables.

[0005] The data configuration module is further configured to receive machine group configuration parameters, the machine group configuration parameters including machine group names, machine types, and running modes, wherein the machine group is configured to define a combination of machine groups with the same processing technology, and the parameter analysis module is configured to dynamically adjust the data filtering range in the data preprocessing rules according to the machine group configuration parameters.

[0006] In the algorithm configuration module, the target class parameters include multiple optimization targets, each of which is configured with a priority order and a weight value, and the model execution module is configured to solve the optimization targets using a multi-objective optimization algorithm according to the priority order and the weight value, wherein the optimization targets with higher priority are satisfied first, and the weight values are used to adjust the optimization intensity when the priorities are the same.

[0007] In the algorithm configuration module, the constraint class parameters include common constraints and specific constraints, the common constraints are reusable constraints for multiple algorithm models, and the specific constraints are constraints specific to a single algorithm model, wherein each constraint is configured with a variable parameter, the variable parameter includes a time limit parameter or a resource quantity parameter, and the parameter analysis module is configured to dynamically inject the constraint rules into the algorithm model instances according to the variable parameters.

[0008] The common constraint in the constraint class parameter includes a latest start time constraint, and a variable parameter is a station time constraint duration, which represents a time constraint that must be observed between stations, and the model execution module ensures that the processing start time is not later than the sum of the specified time and the station time constraint duration; the specific constraint includes a lithography area wafer loading and unloading port quantity constraint, and a variable parameter is a wafer loading and unloading port quantity, and the model execution module limits the number of wafer batches processed at the same time according to the wafer loading and unloading port quantity.

[0009] The data configuration module further allows a user to configure a variable name for a data item, the algorithm configuration module requires the variable name to be assigned when a data item is selected, and the parameter analysis module associates the data model configuration parameter and the algorithm model configuration parameter through the variable name, so as to decouple the data parameter and the algorithm model.

[0010] The task scheduling module is further configured with a running frequency parameter, which is used to trigger a scheduling task periodically, and the task scheduling module dynamically manages the scheduling task according to the creation and deletion of the algorithm model instance, wherein a corresponding scheduling task is automatically created when a new algorithm model instance is added, and a corresponding scheduling task is automatically deleted when an algorithm model instance is deleted; the data acquisition module updates the pre-processing data according to the latest configuration parameter each time the task is executed.

[0011] The model execution module adopts a scheduling algorithm based on operational research constraint programming, the algorithm model instance is composed of multiple algorithm basic classes, each algorithm basic class represents an abstract business rule, and includes a target basic class or a constraint basic class.

[0012] The target basic class includes a priority violation target, a minimum overall scheduling duration target or a resource utilization rate target, the constraint basic class includes an earliest start time constraint or a machine processing quantity constraint, and the parameter analysis module dynamically instantiates the target basic class or the constraint basic class according to user configuration selection and parameters.

[0013] The result processing module further converts the scheduling result into a data format that can be docked by a platform, for visual display or further analysis, and completes the entire closed loop from configuration to execution.

[0014] The second aspect of the present application discloses a semiconductor scheduling algorithm model configuration method, including the following steps: S1: Receive data model configuration parameters input by the user. The data model configuration parameters include a set of data items, a type of data item, and a scope of data item. The set of data items is used to specify the data type to be processed, including wafer batch data, machine data, or processing relationship data. The type of data item includes a filtering type, a priority type, or a supplementary type. The scope of data item is used to calibrate the machine processing mode. S2: Receive algorithm model configuration parameters input by the user. The algorithm model configuration parameters include target class parameters and constraint class parameters. The target class parameters are used to define the optimization target and its priority weight, and the constraint class parameters are used to define business constraints and their variable parameters. S3: Parse the data model configuration parameters and algorithm model configuration parameters to generate data preprocessing rules and algorithm model instances; S4: Create a scheduling task based on the parsed parameters, and trigger the data acquisition operation of the data acquisition module and the scheduling algorithm execution operation of the model execution module, wherein the model execution module executes based on the algorithm model instance generated by the parameter parsing module; S5: Obtain raw data from the source data table, and filter and transform the raw data according to the data preprocessing rules to generate preprocessed data; S6: Execute the scheduling algorithm based on the algorithm model instance and preprocessed data to generate scheduling results; S7: Post-process the scheduling results and convert them into standardized output data.

[0015] A third aspect of the present invention discloses an electronic device, comprising: a memory and a processor, wherein the processor and the memory are connected; The memory is used to store programs; The processor invokes a program stored in the memory to execute the method provided in the second aspect embodiment described above.

[0016] The fourth aspect of the present invention discloses a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a computer to perform the method provided in the second aspect embodiment.

[0017] Compared with existing technologies, this invention has the following advantages: The data configuration module of this invention allows users to independently configure data model parameters, including data item sets, types, and scope, thereby completely decoupling data parameters from the algorithm model. For example, users can flexibly set data items (such as filtering wafer batch data or machine data) through a graphical interface, avoiding the problems of redundant definition and model binding of data parameters in existing technologies, and improving the system's flexibility to adapt to changes in business scenarios. This decoupling design allows data parameters to be reused in multiple algorithm models, reducing configuration costs and supporting rapid expansion into new business scenarios without secondary development.

[0018] Meanwhile, the algorithm configuration module realizes comprehensive productization and configurability of the algorithm model by receiving the target class parameters and the constraint class parameters input by the user; the user can dynamically define the optimization target (such as minimizing the scheduling time length) and the priority weight thereof, and the business constraint (such as the machine processing limit), thereby solving the limitation of the prior art that only supports partial target checking or resource constraint. The parameter analysis module further converts the configuration parameters into data preprocessing rules and algorithm model instances, and the automated process reduces manual intervention and lowers the operation threshold, so that the business personnel can easily use the system without deep technical background.

[0019] In addition, the task scheduling module, the data acquisition module, the model execution module and the result processing module work cooperatively to form a closed-loop automated scheduling process; the system can automatically create a scheduling task, acquire and preprocess data, execute an algorithm and process the result based on the configuration parameters, which not only improves the scheduling efficiency but also ensures the standardization of the output data. Overall, the present application significantly improves the adaptability, scalability and ease of use of the semiconductor scheduling system through modular decoupling and automated integration, and overcomes the defects of high coupling degree, difficult operation and insufficient expandability in the background technology.

[0020] The technical solutions of the present application will be further described in detail below with reference to the accompanying drawings and embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 The system module diagram of Embodiment 1 of the present application.

[0022] Figure 2 The method flowchart of Embodiment 2 of the present application. DETAILED DESCRIPTION

[0023] Embodiment 1 As shown in Figure 1 , a semiconductor scheduling algorithm model configuration system comprises: a data configuration module configured to receive data model configuration parameters input by a user, wherein the data model configuration parameters comprise a data item set, a data item type and a data item action range, the data item set is used to specify a data type to be processed and comprises wafer batch data, machine data or processing relationship data, the data item type comprises a screening type, a priority type or a supplementary type, and the data item action range is used to demarcate a machine processing mode; an algorithm configuration module configured to receive algorithm model configuration parameters input by the user, wherein the algorithm model configuration parameters comprise target class parameters and constraint class parameters, the target class parameters are used to define an optimization target and a priority weight thereof, and the constraint class parameters are used to define a business constraint and a variable parameter thereof; A parameter analysis module, connected with the data configuration module and the algorithm configuration module, is configured to analyze the data model configuration parameters and the algorithm model configuration parameters, and to generate data pre-processing rules and algorithm model instances. A task scheduling module, connected with the parameter analysis module, is configured to create scheduling tasks based on the analyzed parameters, and to trigger data acquisition operations of the data acquisition module and scheduling algorithm execution operations of the model execution module, wherein the model execution module is configured to execute based on the algorithm model instances generated by the parameter analysis module; A data acquisition module, connected with the task scheduling module, is configured to acquire raw data from a source data table, and to filter and convert the raw data according to the data pre-processing rules to generate pre-processed data. A model execution module, connected with the data acquisition module and the parameter analysis module, is configured to execute scheduling algorithms according to the algorithm model instances and the pre-processed data to generate scheduling results. A result processing module, connected with the model execution module, is configured to post-process the scheduling results to convert them into standard output data. The data configuration module, the algorithm configuration module, the parameter analysis module, the task scheduling module, the data acquisition module, the model execution module, and the result processing module are connected through parameter passing and event triggering to realize linkage, so that the data model configuration parameters are independent of the algorithm model configuration parameters, but can be dynamically associated through shared variables.

[0024] In implementation, a user inputs data model configuration parameters through a graphical user interface, specifically including a data item set, a data item type, and a data item scope. For example, in a lithography area scheduling scenario, the user adds a data item, the data item set is specified as a Lot type, indicating processing of wafer batch data, the data item type is selected as a filtering type, used to filter high-priority wafer batches, and the data item scope is set as a single-wafer processing mode to match the characteristics of a lithography machine. The user names the data item as “high-priority Lot filtering”, and configures a variable name such as “priority_level” through a variable name field for subsequent dynamic assignment. In implementation, the system background stores the parameters as structured data, and when the user saves the configuration, the data configuration module generates reusable data rules. Through this parameterized design, the data model configuration parameters are stored independently, avoiding direct binding with the algorithm model, and realizing flexible adjustment of data input; when the business scenario of a semiconductor factory changes, such as adding a lithography process station, the user only needs to modify the data item parameters without rebuilding the entire model, improving the adaptability and configuration efficiency of the system.

[0025] Next, the algorithm configuration module receives user inputted algorithm model configuration parameters, including target class parameters and constraint class parameters. The target class parameters are used to define optimization targets and their priority weight, for example, in the lithography area scheduling, the user selects the priority violation target as the first optimization target, sets the priority order as 1, and the weight value as 0.7, and selects the minimum overall scheduling time length target as the second optimization target, the priority order is 2, and the weight value is 0.3. The constraint class parameters are used to define business constraints and their variable parameters, the user selects a public constraint such as the latest start time constraint, and sets the variable parameter station time constraint length as 1 hour, indicating that the processing start time cannot be later than the planned time plus 1 hour; at the same time, a specific constraint such as a lithography area wafer loading and unloading port number constraint is selected, and the variable parameter wafer loading and unloading port number is set to 4, indicating that the number of wafer batches processed by the machine at the same time is limited by the number of ports. When implemented, the algorithm configuration module provides a drop-down list and a numerical input box for user interaction, and the parameters are parsed and stored as an algorithm instance template. By decomposing the algorithm model into configurable units of targets and constraints, the business personnel can customize the optimization strategy without programming, reducing the operation complexity, supporting the accurate execution of multi-objective optimization algorithms, and improving the rationality of the scheduling results.

[0026] The parameter parsing module is connected with the data configuration module and the algorithm configuration module, and is used to parse user inputted parameters and generate data preprocessing rules and algorithm model instances. In the lithography area example, the parameter parsing module reads the variable name "priority_level" of the data item "high priority Lot filtering", and the priority setting in the algorithm target, generates the data preprocessing rule: in the data acquisition stage, the Lot data with high variable value is preferentially filtered; at the same time, according to the constraint parameters such as the station time constraint length, the constraint rule is dynamically injected into the algorithm model instance to form an executable constraint planning model. When implemented, the parameter parsing module uses a parsing engine to map the configuration parameters to internal rule objects, ensuring that the data parameters and algorithm parameters are associated through shared variables. Through this parsing mechanism, the dynamic linkage of data model configuration parameters and algorithm model configuration parameters is realized, avoiding parameter duplication definition, ensuring configuration consistency, and improving the system's ability to handle complex scenarios.

[0027] The task scheduling module creates scheduling tasks based on the output of the parameter parsing module and configures the running frequency parameters such as triggering every 5 minutes. When the user logs in the lithography area scheduling model, the task scheduling module periodically starts the task and triggers the data acquisition module to execute. The data acquisition module obtains raw data from the source data table (such as the Lot information table, machine information table and product line information table) and filters and converts according to the data preprocessing rules. For example, in the lithography area scenario, the rule requires filtering the Lot data that will arrive at the lithography site and applying priority filtering to generate preprocessed data such as high-priority Lot list and available machine list. In implementation, the data acquisition module uses SQL query or API call to obtain data and performs data cleaning and conversion. Through task scheduling and real-time data updating, the scheduling process is automated, manual intervention is reduced, and system response speed and production efficiency are improved.

[0028] The model execution module executes the scheduling algorithm according to the algorithm model instance and the preprocessed data, and uses the constraint programming method based on operations research to solve it. In the lithography area example, the algorithm model instance combines the priority violation target, the minimum scheduling time target and the lithography area specific constraint, and the model execution module uses a multi-objective optimization algorithm (such as linear programming or heuristic algorithm) to calculate the optimal scheduling scheme, ensuring that high-priority Lots are processed first and machine port quantity limits are observed. After solving, the scheduling results such as processing order, start time and resource allocation table are generated. In implementation, the model execution module calls the algorithm library to perform calculation and handle constraint conflicts. Through the combination of modular algorithm base classes, flexible application of business rules is realized, scheduling accuracy and resource utilization are improved, and rapid iteration optimization is supported.

[0029] The result processing module post-processes the scheduling results generated by the model execution module and converts them into a platform-compatible data format such as JSON or XML format. In the lithography area scenario, the result processing module maps the scheduling results into a standardized data structure for visual display or further analysis, such as generating a Gantt chart or production report. In implementation, the result processing module uses a data converter to standardize the original results and outputs them to the user interface or external system. Through the standardization of result format, closed-loop management from configuration to execution is realized, data-driven decision optimization is supported, and system integrability is enhanced.

[0030] The whole system is linked through parameter transmission and event triggering between modules, for example, the variable name of the data configuration module and the parameter value of the algorithm configuration module are dynamically associated through shared variables. In the lithography area scheduling embodiment, the user configures the data item variable name "priority_level" and selects the variable assignment "high" in the algorithm model, and the parameter analysis module ensures that the data filtering and algorithm target are synchronized. Through this decoupling design, the data model configuration parameters are independent of the algorithm model configuration parameters, but can dynamically adapt to business changes, achieving high modularity and scalability of the system, significantly reducing the coupling degree, enabling the semiconductor factory to quickly adapt to new requirements and improving overall operational efficiency.

[0031] In one embodiment, the data configuration module is also used to receive a machine group configuration parameter, the machine group configuration parameter including a machine group name, a machine type, and a running mode, wherein the machine group is used to define a combination of machine groups with the same processing technology, and the parameter analysis module dynamically adjusts the data filtering range in the data preprocessing rule according to the machine group configuration parameter.

[0032] In implementation, in the lithography area scheduling scenario, the user inputs the machine group configuration parameter through the data configuration module, for example, the machine group name is set to "IMM lithography machine group", the machine type is specified as a lithography machine, and the running mode is selected as a single boat mode, to define a combination of machine groups with the same processing technology. In implementation, the data configuration module provides a form interface for the user to input these parameters, and the system background stores the parameters as a machine group object; the parameter analysis module is connected with the data configuration module, and after analyzing the machine group configuration parameter, dynamically generates a data preprocessing rule, for example, in the data acquisition stage, the rule requires only filtering the machine data belonging to the IMM lithography machine group, and excluding other types of machines. Through the fine configuration of the machine group parameter, the accuracy of the data filtering range is realized, ensuring the optimization of the scheduling model for specific production areas, avoiding data redundancy, and improving processing efficiency; in the lithography area example, when the user adds similar machine groups, only the parameters need to be adjusted without modifying the core rules, improving the reusability and adaptability of the system.

[0033] In one embodiment, in the algorithm configuration module, the target type parameter includes multiple optimization targets, each optimization target is configured with a priority order and a weight value, and the model execution module uses a multi-objective optimization algorithm for solving according to the priority order and the weight value, wherein the target with high priority is satisfied first, and the weight value is used to adjust the optimization intensity when the priority is the same.

[0034] In implementation, in the lithography area scheduling, the user defines multiple optimization targets through the algorithm configuration module, for example, selects the priority violation target as the first optimization target, sets the priority order as 1, and the weight value as 0.7, and selects the minimum overall scheduling time length target as the second optimization target, the priority order is 2, and the weight value is 0.3. In implementation, the algorithm configuration module uses a graphical interface to allow the user to drag the target order and input the weight value, and the parameters are parsed into a target list; the model execution module executes a multi-objective optimization algorithm according to these parameters, such as using the weighted sum method or the priority method, and in solving, the high-priority target is given priority (such as ensuring that high-priority Lots are processed first), and when the priority is the same, the optimization intensity is adjusted through the weight value (such as the target with a high weight value is allocated more resources). Through the fine configuration of multi-objective parameters, flexible optimization of the scheduling algorithm is realized, which enables the user to dynamically adjust the optimization direction according to business needs, and improves the accuracy and practicality of the scheduling result; in the lithography area scenario, this configuration method avoids the limitations of a single target, and supports comprehensive optimization of complex production environments.

[0035] In one embodiment, in the algorithm configuration module, the constraint class parameters include common constraints and specific constraints, the common constraints are constraints that can be reused by multiple algorithm models, and the specific constraints are constraints that are exclusive to a single algorithm model, wherein each constraint is configured with a variable parameter, and the variable parameter includes a time limit parameter or a resource quantity parameter, and the parameter parsing module dynamically injects constraint rules into the algorithm model instance according to the variable parameter.

[0036] In implementation, in the lithography area scheduling, the user selects constraint class parameters through the algorithm configuration module, for example, a common constraint such as a latest start time constraint, and a variable parameter station time constraint duration of the common constraint is set to 1 hour, and a specific constraint such as a lithography area wafer loading and unloading port quantity constraint, and a variable parameter wafer loading and unloading port quantity of the specific constraint is set to 4. In implementation, the algorithm configuration module divides the constraints into a common library and a specific library, the user checks the required constraints and inputs the variable parameter values; after the parameter parsing module parses these parameters, it dynamically injects constraint rules into the algorithm model instance, for example, maps the station time constraint duration to a time limit rule, and maps the port quantity to a resource limit rule. Through the classification and parameterization design of the constraints, modular management of the constraint rules is realized, the common constraints can be reused among multiple models (such as the latest start time constraint is also applicable to the diffusion area), and the specific constraints focus on local needs, reducing the configuration complexity; in the lithography area example, this design ensures comprehensive coverage of business constraints, improving the scalability and maintainability of the system.

[0037] In one embodiment, the common constraint in the constraint class parameter includes a latest start time constraint, and the variable parameter of the latest start time constraint is a site time constraint duration, which represents a time constraint that must be observed between sites, and the model execution module ensures that the processing start time is not later than the sum of the specified time and the site time constraint duration; the specific constraint includes a lithography area wafer loading and unloading port quantity constraint, and the variable parameter of the lithography area wafer loading and unloading port quantity constraint is a wafer loading and unloading port number, and the model execution module limits the number of wafer lots processed simultaneously according to the wafer loading and unloading port number.

[0038] In implementation, in a lithography area scheduling scenario, when a user configures a latest start time constraint, the variable parameter of the site time constraint duration is set to 1 hour, which means that the processing start time cannot be later than the planned time plus 1 hour; at the same time, the user configures a lithography area wafer loading and unloading port quantity constraint, and the variable parameter of the wafer loading and unloading port number is set to 4, which means that the number of wafer lots processed simultaneously by the machine is limited by the port number. In implementation, the parameter analysis module converts these variable parameters into specific rules in the algorithm model instance, and the model execution module ensures that the processing time meets the site constraint and limits the number of port uses when solving. Through parameterization of specific constraint instances, accurate modeling of specific scenarios of semiconductor production is achieved, so that the scheduling algorithm can comply with the actual business rules; in the lithography area example, this implementation avoids time conflicts and resource overloading, and improves the reliability and efficiency of production planning.

[0039] In one embodiment, the data configuration module further allows a user to configure a variable name for a data item, the algorithm configuration module requires the variable name to be assigned when selecting the data item, and the parameter analysis module associates the data model configuration parameter and the algorithm model configuration parameter through the variable name to achieve decoupling of the data parameter and the algorithm model.

[0040] In implementation, in a lithography area scheduling scenario, a user configures a variable name for a data item through the data configuration module, for example, sets the variable name "priority_level" for the data item "high priority Lot filtering"; the algorithm configuration module requires the variable name to be assigned when selecting the data item, for example, assigns "priority_level" as "high". In implementation, the data configuration module provides a variable name field for the user to input, and the parameter analysis module reads the variable name and the assignment to dynamically associate the data model and the algorithm model, for example, filters high priority Lot data according to the assignment in the data preprocessing stage. Through the variable name mechanism, decoupling of the data parameter and the algorithm model is achieved, so that the user can independently configure data input without binding algorithm logic; in the lithography area scenario, this design supports dynamic adjustment of parameters, reduces repeated configuration work, and improves the flexibility and user experience of the system.

[0041] In one embodiment, the task scheduling module is further configured with a running frequency parameter for triggering the scheduled task periodically, and the task scheduling module dynamically manages the scheduled task according to the creation and deletion of the algorithm model instance, wherein a corresponding scheduled task is automatically created when a new algorithm model instance is added, and a corresponding scheduled task is automatically deleted when an algorithm model instance is deleted; the data acquisition module updates the pre-processing data according to the latest configuration parameter at each task execution.

[0042] In implementation, in the lithography area scheduling, the user sets the running frequency parameter through the task scheduling module, such as triggering the scheduled task once every 5 minutes; the task scheduling module creates a periodic task based on this parameter, and triggers the data acquisition module to obtain the latest data from the source data table. In implementation, the task scheduling module starts the task using the timer mechanism, and the data acquisition module updates the pre-processing data according to the latest configuration parameter at each execution, for example, refreshing the Lot state and machine availability. Through the configuration of the running frequency, the automatic periodic execution of the scheduled task is realized, and the data real-time performance is ensured; in the lithography area example, this periodic scheduling avoids manual frequent triggering, and improves the system response speed and production efficiency.

[0043] In one embodiment, the scheduling algorithm used by the model execution module is based on the operational research constraint programming, and the algorithm model instance is composed of multiple algorithm base classes, each of which represents an abstract business rule, including a target base class or a constraint base class.

[0044] In implementation, in the lithography area scheduling, the model execution module uses the constraint programming algorithm, and the algorithm model instance is composed of multiple algorithm base classes, such as a target base class like a priority violation target and a constraint base class like an earliest start time constraint. In implementation, the parameter parsing module instantiates these base classes according to user configuration, and the model execution module combines them for solving. Through the modular combination of the algorithm base class, the high configurability of the scheduling algorithm is realized, and the flexible application of complex business rules is supported; in the lithography area scenario, this design improves the expansibility and solving accuracy of the algorithm.

[0045] In one embodiment, the target base class includes a priority violation target, a minimum overall scheduling time length target, or a resource utilization rate target, the constraint base class includes an earliest start time constraint or a machine processing quantity constraint, and the parameter parsing module dynamically instantiates the target base class or the constraint base class according to the selection and parameters configured by the user.

[0046] In implementation, in the lithography area scheduling, the user selects target base classes such as priority violation targets and constraint base classes such as earliest start time constraints through the algorithm configuration module; the parameter analysis module dynamically instantiates these classes according to the user configuration, for example, sets parameters for the priority violation target. In implementation, the base class represents an abstract business rule, and after instantiation, it is integrated into the algorithm model. Through dynamic instantiation, accurate mapping of business rules is achieved, enabling the system to quickly adapt to changing requirements; in the lithography area example, this implementation enhances the practicality and adaptability of the model.

[0047] In one embodiment, the result processing module also converts the scheduling result into a data format that can be interfaced by the platform for visual display or further analysis, completing the entire configuration-to-execution closed loop.

[0048] In implementation, in the lithography area scheduling, after the model execution module generates the scheduling result, the result processing module converts it into JSON or XML format for visual display or analysis. In implementation, the result processing module uses a data converter to standardize the result and output it to the platform interface. Through standardization of the result format, a closed loop from configuration to execution is achieved, supporting data-driven decision optimization; in the lithography area scenario, this processing improves the availability of the result and the system integration.

[0049] Embodiment 2 As shown in Figure 2 A semiconductor scheduling algorithm model configuration method, comprising the following steps: S1: receiving user input data model configuration parameters, the data model configuration parameters including a data item set, a data item type, and a data item action range, wherein the data item set is used to specify the data type to be processed, including wafer batch data, machine data, or processing relationship data, the data item type includes a filtering type, a priority type, or a supplement type, and the data item action range is used to mark the machine processing mode; S2: receiving user input algorithm model configuration parameters, the algorithm model configuration parameters including target class parameters and constraint class parameters, wherein the target class parameters are used to define optimization targets and their priority weights, and the constraint class parameters are used to define business constraints and their variable parameters; S3: analyzing the data model configuration parameters and the algorithm model configuration parameters to generate data preprocessing rules and algorithm model instances; S4: creating a scheduling task based on the analyzed parameters and triggering data acquisition operations of the data acquisition module and scheduling algorithm execution operations of the model execution module, wherein the model execution module is executed based on the algorithm model instances generated by the parameter analysis module; S5: obtaining raw data from a source data table and filtering and converting the raw data according to the data preprocessing rules to generate preprocessed data; S6: performing a scheduling algorithm according to the algorithm model instance and the preprocessed data, to generate a scheduling result; S7: post-processing the scheduling result, to convert into standard output data.

[0050] The semiconductor scheduling algorithm model configuration method provided by the embodiment has the same implementation principle and technical effects as the system embodiment in Embodiment 1. For brevity, the part not mentioned in the method embodiment can refer to the corresponding content in Embodiment 1.

[0051] Embodiment 3 A computer readable storage medium, having a computer program stored thereon, the computer program being run by a computer to execute the semiconductor scheduling algorithm model configuration method described in Embodiment 2.

[0052] Embodiment 4 An electronic device, comprising: a memory and a processor, the processor and the memory being connected; The memory is configured to store a program. The processor is configured to invoke the program stored in the memory to execute the semiconductor scheduling algorithm model configuration method described in Embodiment 2.

[0053] It should be noted that the electronic device can be, but is not limited to, a personal computer (PC), a tablet computer, a mobile internet device (MID), and the like.

[0054] It should be noted that the processor, the memory and other components that can appear in the electronic device are directly or indirectly electrically connected to each other to realize the transmission or interaction of data. For example, the processor, the memory and other components that can appear can be electrically connected to each other through one or more communication buses or signal lines.

[0055] It should be noted that each embodiment in the specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same and similar parts between the embodiments can be referred to each other.

[0056] In several embodiments provided in the present application, it should be understood that the disclosed system and method can also be implemented by other manners. The system embodiments described above are only illustrative, for example, the flowcharts and block diagrams in the drawings show the possible implementation architecture, function and operation of the system, method and computer program product according to the embodiments of the present application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logic function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different order from that noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0057] In addition, the functional modules in the embodiments of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0058] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a notebook computer, a server, a mobile phone, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0059] The above is only the preferred embodiment of the present application, and does not limit the present application in any way. Any simple modification, change and equivalent structural change made according to the technical essence of the present application to the above embodiments are still within the protection scope of the technical solutions of the present application.

Claims

1. A semiconductor scheduling algorithm model configuration system, characterized by, The application relates to a data processing system, comprising: a data configuration module for receiving user-inputted data model configuration parameters, the data model configuration parameters comprising a data item set, a data item type and a data item action range, wherein the data item set is used for specifying a data type to be processed, the data item type comprises a screening type, a priority type or a supplementary type, and the data item action range is used for marking a machine processing mode; an algorithm configuration module for receiving user-inputted algorithm model configuration parameters, the algorithm model configuration parameters comprising target class parameters and constraint class parameters, wherein the target class parameters are used for defining an optimization target and a priority weight thereof, and the constraint class parameters are used for defining a business constraint and a variable parameter thereof; a parameter analysis module connected with the data configuration module and the algorithm configuration module, and used for analyzing the data model configuration parameters and the algorithm model configuration parameters, and generating a data preprocessing rule and an algorithm model instance; a task scheduling module connected with the parameter analysis module, and used for creating a scheduling task based on the analyzed parameters, and triggering a data acquisition operation of a data acquisition module and a scheduling algorithm execution operation of a model execution module, wherein the model execution module is executed based on the algorithm model instance generated by the parameter analysis module; the data acquisition module connected with the task scheduling module, and used for acquiring original data from a source data table, and screening and converting the original data according to the data preprocessing rule to generate preprocessed data; the model execution module connected with the data acquisition module and the parameter analysis module, and used for executing a scheduling algorithm according to the algorithm model instance and the preprocessed data to generate a scheduling result; a result processing module connected with the model execution module, and used for post-processing the scheduling result to convert the scheduling result into standard output data.

2. The semiconductor scheduling algorithm model configuration system of claim 1, wherein, The data configuration module is further used for receiving machine group configuration parameters, the machine group configuration parameters comprising a machine group name, a machine type and a running mode, wherein the machine group is used for defining a combination of a plurality of machines with the same processing technology, and the parameter analysis module dynamically adjusts a data screening range in the data preprocessing rule according to the machine group configuration parameters.

3. The semiconductor scheduling algorithm model configuration system of claim 1, wherein, In the algorithm configuration module, the target class parameters comprise a plurality of optimization targets, each optimization target is configured with a priority order and a weight value, the model execution module adopts a multi-target optimization algorithm for solving according to the priority order and the weight value, wherein a target with a high priority is preferentially met, and the weight value is used for adjusting an optimization intensity when the priorities are the same.

4. The semiconductor scheduling algorithm model configuration system of claim 1, wherein, In the algorithm configuration module, the constraint class parameters comprise common constraints and specific constraints, the common constraints are reusable constraints for a plurality of algorithm models, and the specific constraints are constraints exclusively belonging to a single algorithm model, wherein each constraint is configured with a variable parameter, the variable parameter comprises a time limit parameter or a resource quantity parameter, and the parameter analysis module dynamically injects a constraint rule into the algorithm model instance according to the variable parameter.

5. The semiconductor scheduling algorithm model configuration system of claim 4, wherein, The common constraint in the constraint class parameter includes a latest start time constraint, and a variable parameter of the latest start time constraint is a site time constraint duration, the site time constraint duration represents a time constraint that must be observed between sites, and the model execution module ensures that the processing start time is not later than the sum of the specified time and the site time constraint duration; the specific constraint includes a lithography area wafer loading and unloading port quantity constraint, and a variable parameter of the lithography area wafer loading and unloading port quantity constraint is a wafer loading and unloading port number, and the model execution module limits the number of wafer batches processed simultaneously according to the wafer loading and unloading port number.

6. The semiconductor scheduling algorithm model configuration system of claim 1, wherein, The data configuration module also allows a user to configure a variable name for a data item, the algorithm configuration module requires the variable name to be assigned when selecting the data item, and the parameter analysis module associates the data model configuration parameter and the algorithm model configuration parameter through the variable name.

7. The semiconductor scheduling algorithmic model configuration system of claim 1, wherein, The task scheduling module is also configured with a running frequency parameter for triggering the scheduling task periodically, and the task scheduling module dynamically manages the scheduling task according to the creation and deletion of the algorithm model instance, wherein a corresponding scheduling task is automatically created when a new algorithm model instance is added, and a corresponding scheduling task is automatically deleted when an algorithm model instance is deleted; the data acquisition module updates the pre-processing data according to the latest configuration parameter each time the task is executed.

8. A method of configuring a model of a semiconductor scheduling algorithm, the method comprising: receiving a plurality of parameters of the model; and determining a configuration of the model based on the plurality of parameters. The method comprises the following steps: S1: receiving a data model configuration parameter input by a user, the data model configuration parameter comprising a data item set, a data item type and a data item action range, wherein the data item set is used to specify a data type to be processed, including wafer batch data, machine data or processing relationship data, the data item type comprises a screening type, a priority type or a supplement type, and the data item action range is used to mark a machine processing mode; S2: receiving an algorithm model configuration parameter input by a user, the algorithm model configuration parameter comprising a target class parameter and a constraint class parameter, wherein the target class parameter is used to define an optimization target and a priority weight thereof, and the constraint class parameter is used to define a business constraint and a variable parameter thereof; S3: analyzing the data model configuration parameter and the algorithm model configuration parameter to generate a data pre-processing rule and an algorithm model instance; S4: creating a scheduling task based on the analyzed parameter, and triggering a data acquisition operation of a data acquisition module and a scheduling algorithm execution operation of a model execution module, wherein the model execution module is executed based on the algorithm model instance generated by a parameter analysis module; S5: acquiring original data from a source data table, and screening and converting the original data according to the data pre-processing rule to generate pre-processing data; S6: executing a scheduling algorithm according to the algorithm model instance and the pre-processing data to generate a scheduling result; S7: post-processing the scheduling result to convert it into standard output data.

9. An electronic device, comprising: The method comprises: a memory and a processor, the processor and the memory are connected; the memory is used to store a program; the processor calls the program stored in the memory to execute the method in claim 8.

10. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and the computer program is run by a computer to execute the method in claim 8.

Images