Model Calculation Scheduling Method, Device, Equipment, Medium and Product

Abstract

The present application discloses a model calculation scheduling method, apparatus, device, medium and product. The method includes: for each of a plurality of computing units, determining the position information of the basic section of the computing unit; and based on the position information of the computing unit in the upstream and downstream topological relationships, determining the type of the model processing unit of the basic section, the input task of the model processing unit, the output task of the model processing unit, and the computing process information corresponding to the model processing unit; in response to the calculation instruction information for the basin, generating a calculation task scheduling instruction based on the types of the respective model processing units; in response to the calculation task scheduling instruction, obtaining the identification information of the scheduling scheme of the basin; based on the identification information of the scheduling scheme, starting the target computing processes corresponding to the respective target model processing units on each target computing node; and controlling the operation of the respective target model processing units to generate a calculation result.

Description

Technical Field

[0001] The present application relates to the technical field of water conservancy projects, and particularly to a model calculation scheduling method, device, equipment, medium and product. Background Art

[0002] With the development of big data and artificial intelligence technologies, large-scale distributed computing has become an important means for processing massive data and complex models. Especially in the water conservancy industry, where informatization started relatively late, the traditional single-host single-scheme model calculation can no longer meet the requirements of current large-area and real-time calculations.

[0003] Existing parallel computing scheduling is mostly carried out in a fixed area, single model, and multi-threaded manner, making it inconvenient to independently debug and parameterize the model, and not supporting the quick addition of different models. As a result, the following disadvantages will occur: (1) Poor compatibility with multiple models, mostly for single models; (2) Existing ones are mostly multi-threaded scheduling of models at the code level, which is likely to cause inconvenience in debugging the model itself; (3) The existing framework lacks compatibility with the dynamic expansion of large areas, the dynamic expansion of models, and different precisions of the same model. Summary of the Invention

[0004] In view of this, embodiments of the present application provide a model calculation scheduling method, device, equipment, medium and product, aiming to achieve the calculation scheduling of multiple models, multiple processes, and multiple host computing nodes in a large river basin.

[0005] The technical solution of the embodiments of the present application is implemented as follows:

[0006] In a first aspect, embodiments of the present application provide a model calculation scheduling method, including:

[0007] Based on the upstream-downstream topological relationship between sub-basin partitions of a river basin and the area data of each sub-basin partition, determine multiple calculation units of the river basin; the upstream-downstream topological relationship is generated based on the encoding of each sub-basin partition of the river basin;

[0008] For each calculation unit among the multiple calculation units, determine the position information of the basic section of the calculation unit; and based on the position information of the calculation unit in the upstream-downstream topological relationship, determine the type of the model processing unit of the basic section, the input task of the model processing unit, the output task of the model processing unit, and the calculation process information corresponding to the model processing unit; the number of model processing units includes multiple;

[0009] In response to the calculation instruction information for the river basin, generate a calculation task scheduling instruction based on the types of the model processing units;

[0010] In response to the computing task scheduling instruction, obtain the identification information of the scheduling plan for the basin; the scheduling plan includes a plurality of target model processing units, the computing process information corresponding to each of the target model processing units, and the target computing nodes corresponding to each of the target model processing units, and the target model processing unit is one of the plurality of model processing units;

[0011] Based on the identification information of the scheduling plan, on each of the target computing nodes, start the target computing processes corresponding to each of the target model processing units; and control each of the target model processing units to run to generate the computing result of the basin;

[0012] Wherein, the model processing unit is a model processing unit after standard encapsulation.

[0013] In one embodiment, the method further includes:

[0014] For each of the plurality of computing units, obtain the location information of the outlet node corresponding to the computing unit;

[0015] Based on the location information of the outlet node, determine the location information of the basic section of the computing unit.

[0016] In some embodiments, the controlling each of the target model processing units to run to generate the computing result of the basin includes:

[0017] For each of the target model processing units in the scheduling plan, based on the type information of the target model processing unit, generate a start instruction corresponding to the type information;

[0018] In response to the start instruction, start the operation of the computing program package of the target model processing unit to generate a model computing result; wherein, the computing program package includes input file information, output file information, output directory information, log directory, and configuration file; wherein, the configuration file is used to store the input path information and output path information of the target model processing unit based on a set text format; the set text format includes JSON format;

[0019] Based on each of the model computing results, generate the computing result of the basin.

[0020] In some embodiments, the method further includes:

[0021] Based on the spatial geometric information of the plurality of computing units, classify the computing result to generate classification result data; and in response to a result display request, display the classification result data.

[0022] In some embodiments, the method further includes:

[0023] Obtain a monitoring request;

[0024] In response to the monitoring request, display at least one of the following:

[0025] The identification information of the scheduling scheme, the computing process information of each model processing unit, the computing status information of each model processing unit, and the computing progress information of each model processing unit, where the computing process information includes the number of processes and the process status.

[0026] In some embodiments, the method further includes:

[0027] Obtain a parameter change request for the model processing unit;

[0028] In response to the parameter change request, update the initial parameters of the model processing unit to target parameters.

[0029] In some embodiments, the method further includes:

[0030] Obtain indication information for adding a model processing unit; the indication information includes the type of the model processing unit to be added;

[0031] In response to the indication information, based on the type of the model processing unit to be added, determine the target computing unit corresponding to the model processing unit to be added, and add the model to be added to the target computing unit;

[0032] Based on the position information of the base section of the target computing unit, determine the input task corresponding to the model processing unit to be added, the output task corresponding to the model processing unit to be added, and the process information of the model processing unit to be added.

[0033] In a second aspect, an embodiment of the present application provides a model calculation scheduling device, and the device includes:

[0034] A first determination module, configured to determine a plurality of computing units of the basin based on the upstream and downstream topological relationships between the sub-basin partitions of the basin and the area data of each sub-basin partition; the upstream and downstream topological relationships are generated by encoding each sub-basin partition of the basin;

[0035] A second determination module, configured to, for each computing unit among the plurality of computing units, determine the position information of the base section of the computing unit; and based on the position information of the computing unit in the upstream and downstream topological relationships, determine the type of the model processing unit of the base section, the input task of the model processing unit, the output task of the model processing unit, and the computing process information corresponding to the model processing unit; the number of model processing units includes a plurality;

[0036] A generation module, configured to generate a computing task scheduling instruction based on the types of the model processing units in response to computing indication information for the basin.

[0037] An acquisition module, configured to acquire identification information of a scheduling scheme for the basin in response to the computing task scheduling instruction; the scheduling scheme includes a plurality of target model processing units, computing process information corresponding to each of the target model processing units, and target computing nodes corresponding to each of the target model processing units, and the target model processing unit is one of the plurality of model processing units.

[0038] A scheduling module, configured to start target computing processes corresponding to the target model processing units on the target computing nodes based on the identification information of the scheduling scheme; and control the operation of the target model processing units to generate a computing result.

[0039] Wherein, the model processing unit is a model processing unit after being standardized and encapsulated.

[0040] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory for storing a computer program that can run on the processor, wherein the processor is configured to execute the steps of the method in the first aspect of the embodiment of the present application when running the computer program.

[0041] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method in the first aspect are implemented.

[0042] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method in the first aspect are implemented.

[0043] The technical solution provided by the embodiments of the present application, a model calculation scheduling method includes: determining a plurality of calculation units of the basin based on the upstream and downstream topological relationships between the sub-basin partitions of the basin and the area data of each sub-basin; the upstream and downstream topological relationships are generated based on the coding of the sub-basin partitions of the basin; for each calculation unit among the calculation units, determining the position information of the basic section of the calculation unit; and based on the position information of the calculation unit in the upstream and downstream topological relationships, determining the type of the model processing unit of the basic section, the input task of the model processing unit, the output task of the model processing unit, and the calculation process information corresponding to the model processing unit; the number of model processing units includes a plurality; in response to the calculation instruction information for the basin, generating a calculation task scheduling instruction based on the types of the model processing units; in response to the calculation task scheduling instruction, obtaining the identification information of the scheduling plan of the basin; the scheduling plan includes a plurality of target model processing units, the calculation process information corresponding to each target model processing unit, and the target calculation nodes corresponding to each target model processing unit, and the target model processing unit is one of the plurality of model processing units; based on the identification information of the scheduling plan, starting the target calculation processes corresponding to the target model processing units on each target calculation node; and controlling the operation of each target model processing unit to generate a calculation result; wherein, the model processing unit is a model processing unit after standardized encapsulation.

[0044] In this way, the embodiments of the present application start from a global perspective, and significantly improve the efficiency, resource utilization rate, and system stability of large basin calculation tasks by accurately dividing the calculation units of the basin, constructing upstream and downstream topological relationships, realizing multi-process parallel calculation, and standardizing and encapsulating model processing units. Specifically, (1) Through the topological coding and calculation unit division of the sub-basins of the basin, it is ensured that the tasks of each calculation unit can be executed collaboratively, thereby avoiding resource waste and improving calculation efficiency. (2) Multi-process parallel calculation can make full use of the resources of multiple calculation nodes and shorten the overall calculation time. (3) The standardized and encapsulated model processing units ensure that different models can run on independent nodes without interfering with each other, making the system more stable and facilitating expansion and maintenance. This standardized processing also ensures that multiple models can run in parallel on different calculation nodes and will not affect the stability of the overall system due to the update or debugging of a single model; thus realizing efficient calculation scheduling of multiple models, multiple processes, and multiple host calculation nodes within a large basin. Brief Description of the Drawings

[0045] Figure 1 It is a schematic flowchart of the model calculation scheduling method provided by the embodiments of the present application;

[0046] Figure 2 It is a schematic structural diagram of model assembly on the basic section provided by the embodiments of the present application;

[0047] Figure 3Schematic diagram of the structured computing program package provided by the embodiments of the present application;

[0048] Figure 4 Schematic diagram of the interface of the computing progress provided by the embodiments of the present application;

[0049] Figure 5 Schematic diagram of the system structure and process of the large-scale distributed model hybrid computing scheduling scheme based on the basic section provided by an application example of the present application;

[0050] Figure 6 Schematic diagram of the structure of the model computing scheduling device provided by the embodiments of the present application;

[0051] Figure 7 Schematic diagram of the structure of the electronic device provided by the embodiments of the present application. Detailed implementation manners

[0052] The present application will be further described in detail below with reference to the accompanying drawings and embodiments.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used in the specification of this application herein are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0054] The embodiments of the present application provide a model computing scheduling method, which includes the following steps:

[0055] Step 110: Determine multiple computing units of the basin based on the upstream-downstream topological relationship between the sub-basin partitions of the basin and the area data of each sub-basin; the upstream-downstream topological relationship is generated based on the encoding of the sub-basin partitions of the basin.

[0056] It can be understood that a basin refers to a water flow gathering area of a region, which can be divided into multiple sub-basin partitions (such as rivers, tributaries, etc.). Each sub-basin can be regarded as a hydrological unit, and its characteristics such as size, shape, and location are different. The area data of each sub-basin reflects its geographical characteristics.

[0057] Here, the upstream-downstream topological relationship refers to the water flow transfer relationship between different sub-basins. For example, the water flow of one sub-basin will affect the downstream basin. This relationship is determined based on the flow direction and gathering mode of the water flow within the basin.

[0058] It can be understood that by encoding the sub-basin partitions, these sub-basins and their upstream-downstream relationships can be identified in a structured manner, so that the topological relationship of each sub-basin (i.e., its relative position in the basin) can be clearly identified and used for the division of computing tasks.

[0059] Here, according to the above upstream and downstream topological relationships and area data, the basin can be divided into multiple calculation units. Each calculation unit represents a calculation area of the basin, and their division basis may involve factors such as terrain, climate, and hydrological characteristics. The calculation units can be assigned to different computing resources for processing in subsequent steps.

[0060] Exemplarily, in order to support multiple models in the same area, from large to small, first for the entire target area, according to the collected small watershed data of the area and the upstream and downstream topology, for different basins and different partitions, from upstream to downstream, every 200 - 500 square kilometers of area is taken as a calculation unit.

[0061] Taking the national area as an example, collect the basic data of small watersheds and select and determine seven major basin partitions; within each basin partition, divide it into 200 calculation units according to the area and number of small watersheds.

[0062] Step 120: For each of the multiple calculation units, determine the location information of the basic section of the calculation unit; and based on the location information of the calculation unit in the upstream and downstream topological relationships, determine the type of the model processing unit of the basic section, the input task of the model processing unit, the output task of the model processing unit, and the calculation process information corresponding to the model processing unit; the number of model processing units includes multiple.

[0063] Here, the basic section refers to a specific geographical section (such as a river section or a hydrological section) used to describe the calculation unit, and these sections are usually used to describe hydrological data such as the distribution, flow velocity, and water level of the water flow in the basin. Through the basic section, the water flow dynamics within the calculation unit can be further understood. The basic section is the starting and ending position for basin calculation and analysis.

[0064] For each of the calculation units in each calculation unit, there is a corresponding basic section, so that the location information of the basic section of the calculation unit can be determined. Here, the basic section refers to the key position in the model calculation, usually located at the outlet of the calculation unit or key nodes (such as water collection points).

[0065] Here, the location information of each calculation unit is its position relationship in the upstream and downstream chain of the basin, usually referring to its position in the upstream and downstream chain of the basin. For example, for a calculation unit located upstream, its output may be used as the input of the downstream calculation unit. The downstream calculation unit then needs to receive necessary data from the upstream to ensure the continuity of the calculation logic of the entire basin.

[0066] Here, the position data of the computing unit refers to the specific position of each computing unit in the watershed, such as whether it is located upstream, in the middle reaches, or downstream. The position data is usually the result of geographic information data (GIS data), which can help the system accurately locate each computing unit.

[0067] Here, for each computing unit among the computing units, the type, input task, and output task of the corresponding model processing unit are selected according to the position information of the computing unit in the upstream-downstream topological relationship.

[0068] It can be understood that the type of the model processing unit can be selected according to the characteristics of the basic section and the calculation requirements. The types of model processing units include: API model and SKBY model. For example, hydrological models, climate models, or geological models, etc.

[0069] Here, the input task of each model processing unit refers to the data it needs, and these data are usually from the upstream computing unit or an external input source; while the output task is the result generated after the model runs, and these results may be used as the input for the downstream computing unit or as the final calculation output.

[0070] Here, each model processing unit has independent computing process information (such as process ID, execution status, etc.) so as to (1) run independently and avoid mutual interference between tasks. (2) Support parallel processing and improve computing efficiency.

[0071] Here, according to the upstream-downstream topological relationship of the computing unit, the system matches the input task, output task, and computing process information with a specific model processing unit. Through this matching, it can be ensured that each model processing unit can smoothly obtain the required data. The output results can be seamlessly connected to downstream tasks or output as independent results.

[0072] Exemplarily, as Figure 2 shown, Figure 2 is a structural schematic diagram of model assembly on the basic section. For the calculation area, a basic section with upstream-downstream topology is established. Basic section 1 flows to basic section 2, and basic section 2 flows to basic section 3. The same or different calculation models can be selected on different basic sections. API model is used for basic section 1, SKBY model is used for basic section 2, SKBY model is used for basic section 3, and API model is used for basic section 4, which conveniently realizes the hybrid assembly of different models.

[0073] Here, the traditional method is to use the same calculation model for the entire selected area. For example, the API model can be used for the entire area for calculation, or the SKBY model can be used for the entire area for calculation. Since mixing is not possible, the advantages of each model cannot be exploited. The soil types, soil textures, terrains, etc. in different regions are different, and the optimal models applicable may be different. Using a single model uniformly will not yield the optimal results.

[0074] However, the present application, based on the model assembly of the sectional basis for partitioning, well solves this problem. The optimal models matching the terrain, geology and other characteristics can be selected for different regions to achieve the optimal solution.

[0075] Step 130: In response to the calculation instruction information for the basin, generate a calculation task scheduling instruction based on the types of each model processing unit.

[0076] Here, the calculation instruction information refers to the specific requirements or instructions for the calculation task, coming from users, the scheduling system or other control centers. The instruction information includes the objectives of the basin calculation, task priorities, requirements for calculation resources, and other contents.

[0077] Here, in response to the calculation instruction information, the embodiments of the present application need to generate the corresponding calculation task scheduling instruction. This process arranges the calculation order, allocates calculation resources according to the type of each model processing unit (such as hydrological simulation, climate model, etc.), and ensures that the calculation tasks are executed in the order of the topological relationship.

[0078] Here, by reasonably scheduling the calculation tasks, it is ensured that each model processing unit runs on a suitable calculation node, and can timely obtain the input data and generate the output data. The calculation task scheduling instruction is the core control logic of the system, used to manage the order of task execution and resource allocation.

[0079] Step 140: In response to the calculation task scheduling instruction, obtain the scheduling plan for the basin; the scheduling plan includes multiple target model processing units, the calculation process information corresponding to each target model processing unit, and the target calculation nodes corresponding to each target model processing unit, and the target model processing unit is one of the multiple model processing units.

[0080] Here, the scheduling plan is a set of detailed calculation task arrangement plans generated by the system after receiving the calculation task scheduling instruction. This plan will list the specific execution plans for each target model processing unit, including on which calculation node to execute, when to execute, and how to execute. After determining the scheduling plan, the identification information of the scheduling plan can be obtained.

[0081] Here, the target model processing unit refers to the model processing unit to perform the model processing task, and the target model processing unit is one of multiple model processing units. The scheduling scheme needs to list all target model processing units, as well as their corresponding target computing nodes and computing process information.

[0082] Here, each target model processing unit will be assigned to a specific target computing node. These target computing nodes are hardware resources with computing capabilities, and the process information indicates the running mode of the target model processing unit on the computing node, including tasks such as startup, monitoring, and control.

[0083] Step 150: Based on the identification information of the scheduling scheme, on each target computing node, start the target computing process corresponding to each target model processing unit; and control the operation of each target model processing unit to generate a computing result;

[0084] Among them, the model processing unit is a model processing unit after standardized encapsulation.

[0085] It can be understood that once the scheduling scheme is determined, based on the identification information of the scheduling scheme, corresponding processes can be started on each target computing node. Each process corresponds to a model processing unit, and it will start to execute according to the predetermined computing task.

[0086] It can be understood that after starting the process on the target computing node, the system will monitor the running status of each model processing unit to ensure that it executes tasks according to the scheduling scheme. If there is a problem during the computing process of a certain model processing unit, the system will take corresponding error correction or adjustment measures.

[0087] It can be understood that the model processing unit after standardized encapsulation indicates that each model is encapsulated into an independent unit with a unified interface and data format. This enables different model processing units to run on different computing nodes and are not affected by the update or debugging of other models during the scheduling process. Standardized encapsulation can improve the compatibility, scalability, and maintainability of the system.

[0088] By developing a web service interface, each computing node can be monitored. This interface mainly realizes the startup, shutdown, status monitoring, etc. of the program (model processing module) under the specified model package directory. The model processing module is a secondary encapsulation package developed in C# language for each model, aiming to continuously expand the model and provide support for the scheduling module in a consistent way. Through this model processing module intermediate layer, the scheduling management only needs to manage this single model processing module program.

[0089] In addition, this standardized encapsulation supports multiple platforms (such as Windows and Linux systems), and realizes the scheduling management of model processing programs on servers with different architectures with a unified interface.

[0090] Thus, from a global perspective, the embodiments of the present application significantly improve the efficiency, resource utilization rate, and system stability of large watershed computing tasks by precisely dividing the computing units of the watershed, constructing the upstream and downstream topological relationships, implementing multi-process parallel computing, and standardizing and encapsulating the model processing units. Specifically, (1) Through the topological coding and calculation unit division of the sub-watersheds of the watershed, it is ensured that the tasks of each calculation unit can be executed collaboratively, thereby avoiding resource waste and improving the calculation efficiency. (2) Multi-process parallel computing can make full use of the resources of multiple computing nodes and shorten the overall calculation time. (3) The standardized and encapsulated model processing units ensure that different models can run on independent nodes without interference, making the system more stable and facilitating expansion and maintenance. This standardized processing also ensures that multiple models can run in parallel on different computing nodes and will not affect the stability of the overall system due to the update or debugging of a single model; thus, efficient computing scheduling of multiple models, multiple processes, and multiple host computing nodes within a large watershed is achieved.

[0091] In some embodiments, the method further includes:

[0092] For each of the multiple calculation units, obtaining the location information of the outlet node corresponding to the calculation unit;

[0093] Based on the location information of the outlet node, determining the location information of the basic section of the calculation unit.

[0094] It can be understood that the outlet node refers to the boundary position of each calculation unit, usually located at the outlet of the calculation unit, where data flows out of the unit. In hydrological or watershed calculations, the outlet node may involve catchment points, discharge outlets, or other key hydrological positions.

[0095] Here, based on the location information of the outlet node, the specific location of the basic section can be deduced. The outlet node is usually the boundary of the calculation unit. Based on the geographical coordinates of this node and the water flow characteristics of the watershed, the location of the basic section required by the hydrological model within the calculation unit can be determined.

[0096] Here, there are various types of basic sections, such as cross-sections and longitudinal sections. Different types of basic sections are applicable to different hydrological calculation tasks. According to the type information of the basic section, the system can further select the corresponding model processing unit (such as a water flow model or a water quality model) to ensure the accuracy of the calculation task.

[0097] In some embodiments, controlling the operation of each target model processing unit to generate the calculation results of the watershed includes:

[0098] For each target model processing unit in the scheduling scheme, based on the type information of the target model processing unit, generate a startup instruction corresponding to the type information;

[0099] In response to the startup instruction, start the operation of the calculation program package of the target model processing unit to generate a model calculation result; wherein, the calculation program package includes input file information, output file information, output directory information, log directory, and configuration file; wherein, the configuration file is used to store the input path information and output path information of the target model processing unit based on a set text format; the set text format includes the JSON format;

[0100] Based on each model calculation result, generate the calculation result of the basin.

[0101] Here, each target model processing unit has different types and calculation requirements, so the system generates corresponding startup instructions based on its type information. The startup instructions specifically specify how to start the calculation task of the model processing unit, such as the input files and model configurations that need to be loaded.

[0102] Here, the calculation task of each model processing unit is managed by a calculation program package. The calculation program package includes: Input file information: that is, the input data required by the model (such as hydrological data, meteorological data, etc.). Output file information: that is, the result files generated during the calculation process. Output directory information: the directory where the calculation results are stored. Log directory: used to store the log files generated during the execution of the model, which is convenient for subsequent debugging and viewing the execution status. The configuration file contains the configuration parameters required for the model to run, such as input path, output path, and other information. These configuration files are usually stored in text format to ensure that the model can correctly read and write data.

[0103] Here, the set text format includes the JSON format. It has strong compatibility, readability, and is easy to interact with other systems.

[0104] Here, after the model runs, relevant calculation results will be generated, and these results will be used for subsequent data analysis and decision support.

[0105] Exemplarily, to achieve the hybrid assembly of different calculation models based on the basic section, it is first necessary to ensure that the calculation program packages of each model follow unified specifications and interfaces, so that the calculation engine can process different calculation program packages with consistent operations. The structure of the calculation program package is designed with 4 core directories: the input directory (stores input data), the output directory (stores output results), the log directory (stores log files), and the sim configuration file directory (stores configuration files in JSON format). Each JSON file includes parameters such as the input and output paths required for model calculation, the computing resources used (such as GPU index), and the calculation time. In this way, when executing, whether using the API model or the SKBY model, the corresponding input file can be loaded and calculated through a consistent command (such as API.exe appsetting.json), ensuring the smooth operation of the model.

[0106] Specifically, as Figure 3 shown, Figure 3 is a schematic diagram of the structured calculation program package. In Figure 3 , the sim directory contains the appsetting.json file. The input directory contains input files. The output directory contains output files. The log directory contains log files. API.exe and SKBY.exe are executable files. API.jar is the executable file for the Java version.

[0107] All the program packages are designed to be text-interactive, including 4 directories: the input directory for input, the output directory for output, the log directory for logs, and the sim configuration file directory. The sim configuration file directory contains configuration files in JSON format, which store information such as the input and output file paths involved in model calculation, the used gpu index number, and the calculation time. Taking the API and SKBY calculation programs as examples, using the command API.exe appsetting.json can read the input files in the input directory from the json file and output them to the output directory. Using the command SKBY.exe appsetting.json can read the input files in the input directory from the json file and output them to the output directory. If it is a calculation program package for the Java version, the input files in the input directory can also be parsed in the way of java - jar API.jar appsetting.json, and output files are generated in the output directory. Through this standardized structure requirement based on files, calculation programs in different languages can be supported, and it is also convenient to view and debug the input and troubleshoot the output through text files.

[0108] Thus, this computing management method based on standardized encapsulation and configuration files enables seamless docking of different models and greatly improves the compatibility, scalability, and maintainability of the models. Whether adding new models or updating existing models, it can be quickly implemented while maintaining the stability of the system.

[0109] In some embodiments, the method further includes:

[0110] Classifying the calculation results based on the spatial geometric information of the multiple computing units to generate classified result data; and displaying the classified result data in response to a result display request.

[0111] Here, the spatial geometric information generally includes three basic geometric elements: points, lines, and surfaces. Each spatial element represents a different type of geographical entity. A point represents a specific location on the Earth's surface, without width or depth, and is usually used to represent a single geographical location (such as a measurement point, a river confluence). A line represents a geometric object with length but no width, and is used to represent roads, rivers, watershed boundaries, etc. A surface represents a geometric object with area, and is usually used to describe a region, such as the geographical area of a computing unit or a watershed, a soil type area, etc.

[0112] Exemplarily, points may include stations, hydrological stations, reservoir stations, sluice dams, etc. Lines may include river channels, levees, pipe networks. Surfaces may include rainfall surfaces, watershed surfaces, and inundation surfaces.

[0113] Here, according to the spatial geometric information (points, lines, surfaces), the calculation results will be classified by different regions. This enables the results to more accurately match the geographical features within the watershed. For example, the calculations in the upstream region may focus on the analysis of precipitation, while the downstream region pays attention to the changes in water levels. Such classification enhances the comprehensibility and practicality of the data.

[0114] The classified calculation results can be displayed in different ways to help users view the required calculation data according to geographical location and task requirements. For example: point data can display the calculation results of weather stations and monitoring points; line data shows the water flow changes along paths such as rivers and dams; surface data displays relevant hydrological information, such as water levels and precipitation, in different regions of the watershed.

[0115] In some embodiments, the method further includes:

[0116] Obtaining a monitoring request;

[0117] In response to the monitoring request, displaying at least one of the following:

[0118] Identification information of the scheduling scheme, computing process information of each model processing unit, computing status information of each model processing unit, and computing progress information of each model processing unit. The computing process information includes the number of processes and the process status.

[0119] Here, the monitoring request is usually initiated by a user or a system administrator to view the running status of the model processing unit and ensure the stability of the system and the smooth progress of the computing task.

[0120] Here, after the system responds to the monitoring request, it displays at least one of the following:

[0121] The process information provides information about the computing processes, including the current number of processes (the number of processes running simultaneously) and the status of each process (e.g., whether it is running, waiting, completed, crashed and exited, etc.). The computing status reflects the running progress of each model processing unit, whether there are errors or exceptions, or whether the computing task is successfully completed. The computing progress information (e.g., overall progress percentage, specific progress of partitions or tasks).

[0122] Exemplarily, the computing status and process data displayed by the system help users to understand the execution of the computing task in real time. The specific display content includes: information about the currently used scheduling scheme (such as the scheduling scheme ID). Computing status information, clearly indicating the current status of the task (e.g., computing, normal exit, waiting for computing, crashed and exited, etc.). Computing progress information (e.g., overall progress percentage, specific progress of partitions or tasks). Computing log records, providing detailed logs of the current computing task to help users understand possible problems during the execution process.

[0123] In practical applications, when responding to the monitoring request, the process data and computing status can help users or system administrators quickly evaluate the health status of the system and the progress of the computing task. The computing progress and logs can provide further details to help track problems, optimize the computing process, or adjust strategies.

[0124] As Figure 4 shown, Figure 4 For the computing progress monitoring interface, the specific content is as follows:

[0125] Scheduling scheme (sk_001): The currently used scheduling scheme, which can help users understand the current task configuration and execution plan.

[0126] Current computing status: Lists different computing statuses (such as computing, normal exit, waiting for computing, etc.), providing users with clear task status information.

[0127] Calculation Progress: Through the progress percentage and process details, users can understand the specific progress of each area and process. The calculation progress of multiple areas (such as Zhangweixin River and Sinvsi) is shown here, and the completion status of each process is marked (for example, Process 1 has been completed, and Processes 2 to 6 have not started yet).

[0128] Calculation Log: Real-time records of various states during the calculation process, facilitating the tracking of task execution and the resolution of potential problems.

[0129] In some embodiments, the method further includes:

[0130] Obtain a parameter change request for the model processing unit;

[0131] In response to the parameter change request, update the initial parameters of the model processing unit to the target parameters.

[0132] It can be understood that users or administrators may need to adjust the parameters of the model (such as initial water level, precipitation, temperature, etc.). The system automatically updates the initial parameters of the model processing unit according to the parameter change request. This process ensures that the model can perform calculations based on the latest data and requirements, maintaining high precision and adaptability.

[0133] In some embodiments, the method further includes:

[0134] Obtain indication information for adding a model processing unit; the indication information includes the type of the model processing unit to be added;

[0135] In response to the indication information, based on the type of the model processing unit to be added, determine the target calculation unit corresponding to the model processing unit to be added, and add the model to be added to the target calculation unit;

[0136] Based on the location information of the basic section of the target calculation unit, determine the input task corresponding to the model processing unit to be added, the output task corresponding to the model processing unit to be added, and the process information of the model processing unit to be added.

[0137] Next, a detailed description of the embodiments of the present application will be given in combination with an application example.

[0138] With the development of big data and artificial intelligence technologies, large-scale distributed computing has become an important means for processing massive data and complex models. Especially in the water conservancy industry, where informatization started relatively late, the traditional single-host single-scheme model calculation can no longer meet the current requirements for large-area and real-time calculations. Existing parallel computing scheduling is mostly carried out in a fixed area, single-model, multi-threaded manner, making it inconvenient to independently debug and parameterize the model, and not supporting the rapid addition of different models.

[0139] This application example is based on the water conservancy industry, adopts a unified regional topology coding, and performs secondary encapsulation on multiple models, extracts inputs, outputs, and upstream and downstream relationships, and debugs the models in independent processes. Finally, it is assembled into a multi-process topology-based parallel computing. It realizes the computing scheduling of multiple models, large regions, multiple processes, and multiple host computing nodes.

[0140] It can be seen from this that the disadvantages of the related technologies include:

[0141] (1) Poor compatibility with multiple models, mostly for single models

[0142] (2) Existing ones mostly perform multi-threaded scheduling of models at the code level, which is likely to cause inconvenience in debugging the models themselves

[0143] (3) Existing frameworks lack compatibility with the dynamic expansion of large regions, the dynamic expansion of models, different precisions of the same model, etc.

[0144] Based on this, this application example provides a large-scale distributed model hybrid computing scheduling method based on basic cross-sections. Based on starting from local areas to river basins and then to the national region, considering the overall situation, adopting a unified upstream and downstream topological relationship of the river basin, forming computing partitions, each partition can bind multiple models, different precisions of the same model, etc. By encapsulating the three elements of input, output, and upstream and downstream topology processing of the models within the computing partitions, an independent multi-process scheduling management program is written. It realizes the synchronous computing of multiple models in different computing partitions within the region in the form of multiple processes on multiple computing nodes, facilitating the independent debugging and testing of the models, greatly improving the computing time, and can continuously append new models, update the model precision scale, and continuously expand the computing region. Finally, it realizes the hybrid computing of multiple models within the national region and the output of model results.

[0145] Specifically, taking the national region as an example, collect the basic data of small river basins and select and determine the seven major river basin partitions; within each river basin partition, divide it into 200 computing units according to the area and number of small river basins; extract the outlet nodes of the 200 computing units as basic cross-sections to determine 200 basic cross-sections for controlling the computing; the scheduling engine controls a certain river basin on multiple specified computer nodes to simultaneously start 200 processes to calculate the computing units controlled by the 200 control cross-sections at the same time; the computing engine dynamically updates the model inputs, updates the model parameters, searches for and waits for the upstream and downstream topology of the model, and parses and stores the results in the database after the computing is completed; at the same time, the scheduling engine monitors the start, shutdown, and status of the 200 processes; the results of the model store time series data according to the element types of points, lines, and surfaces for application display.

[0146] Next, combined with Figure 5 , the specific introduction of this solution will be carried out. Figure 5The architecture and workflow of the solution are presented in a modular form. From watershed division to model calculation and then to result display, each step has a clear division of labor and management, ensuring the efficient operation of the system and the accurate processing of data.

[0147] 1. Based on the watershed units within the region, divide the calculation units to form the basic cross-sections.

[0148] As Figure 5 shown, to support multiple models in the same region, the method of dividing the large into small is adopted. First, for the entire target region, according to the collected small watershed data of the region and the upstream and downstream topologies, for different watersheds and different partitions, from upstream to downstream, every 200 - 500 square kilometers of the region is taken as a calculation unit, and the key position (such as the outlet) of this calculation unit is selected as a basic cross-section. The purpose is to provide a basis for binding n models to each basic cross-section in the next step and subsequent calculation scheduling based on this unified basic cross-section.

[0149] Specifically, it includes: 1. Determine the number of watersheds: First, determine the number of watersheds within the study area. 2. Form watershed partitions: Divide the entire watershed into multiple partitions, and each partition corresponds to a basic cross-section. 3. Divide the calculation units: In each watershed partition, further divide the calculation units, which are the basic units for model calculation. 4. Form the basic cross-sections: Determine the basic cross-sections of each calculation unit, which are the starting and ending points of model calculation.

[0150] 2. Bind n model processing units to each basic cross-section.

[0151] After determining the basic cross-sections, map and bind 0 - n model processing modules (processes) to each basic cross-section. Simply put, each basic cross-section corresponds to a calculation unit, a calculation unit contains multiple small watersheds, each basic cross-section maps n model calculation modules, and each model calculation module corresponds to a calculation process. As long as the basic cross-sections are well managed, the basic objects of the entire calculation scheduling are well managed.

[0152] Based on the model configuration of the basic cross-sections (workstations), realize the hybrid assembly of multiple models: such as Figure 2As shown in the figure, for the calculation area, a basic section with upstream and downstream topologies is established. The rapid section 1 flows to the basic section 2, the basic section 2 flows to the basic section 3. The same or different calculation models can be selected for different basic sections. The API model is used for the basic section 1, the SKBY model is used for the basic section 2, the SKBY model is used for the basic section 3, and the API model is used for the basic section 4, which can conveniently achieve the hybrid assembly of different models. The traditional method is to select the same calculation model for the entire area. For example, the API model can be used for the entire area for calculation, or the SKBY model can be used for the entire area for calculation. Since mixing cannot be carried out, the advantages of each model cannot be exerted. The soil types, soil textures, terrains, etc. in different areas are different, and the most suitable models may be different. Using the same model uniformly cannot obtain the optimal results. However, the model assembly based on the partitioned basic section well solves this problem. The optimal models matching the terrain, geology and other characteristics can be selected for different areas to achieve the optimal solution.

[0153] Specifically, it includes the following steps: 1 Update the model package input: Configure model processing units for each basic section, and these units are responsible for specific calculation tasks. 2 Update the model package parameters: Update the parameters of the model package according to the characteristics of the basic section to adapt to different calculation requirements. 3 Update the upstream and downstream topology data: Update the upstream and downstream topology data related to the basic section, including information such as water sources, working conditions, and flood diversion. 4 Parse the model results and store them in the database.

[0154] 3. Process scheduling management module.

[0155] As Figure 5 shown in the figure, based on this process scheduling management module, the following can be achieved: 1 Start the calculation process to start the calculation task of the model. 2 Process shutdown: After the calculation task is completed, close the corresponding process. 3 Process status monitoring: Real-time monitor the status of each calculation process to ensure the smooth progress of the calculation task.

[0156] The process scheduling management module develops a web service interface to monitor each calculation node. It mainly realizes the start, shutdown, status monitoring, etc. of the program (model processing module) under the specified model package directory. The model processing module is a secondary encapsulation package developed in C# language for each model. The purpose is to continuously expand the model and provide support for the scheduling module in a consistent way. Through this model processing module middle layer, the scheduling management only needs to manage this unique model processing module program. It supports both Windows and Linux systems and realizes the scheduling management of model processing programs on different architecture servers with a consistent interface.

[0157] The most crucial part in the process scheduling and management module is: a unified and standardized model calculation program package. To achieve the mixed assembly of different calculation models based on the basic cross-section, it is necessary to have unified and standardized requirements for the algorithm packages of the calculation models, so that the calculation engine can process different calculation program packages with consistent operations. For example Figure 3 As shown, all program packages are designed to be text-based interactions, including 4 directories: input directory, output directory, log directory, and sim configuration file directory. Among them, the sim configuration file directory contains configuration files in JSON format, which store information such as the input and output file paths involved in model calculation, the GPU index number used, and the calculation time. Taking the API and SKBY calculation programs as examples, using the API.exe appsetting.json command can read the input files in the input directory from the JSON file and output them to the output directory. Using the SKBY.exe appsetting.json command can read the input files in the input directory from the JSON file and output them to the output file. If it is a Java version of the calculation program package, the input files in the input directory can also be parsed in the way of java-jar API.jar appsetting.json, and output files are generated in the output directory. Through this file-based standardized structure requirement, calculation programs in different languages can be supported, and it is also convenient to view and debug the input and troubleshoot the output through text files

[0158] 4. Result query and display module

[0159] Here, the result display module can display calculation results such as points, lines, and surfaces

[0160] Specifically, it includes: Points (stations, hydrological stations, reservoir stations, sluice dams, etc.): Display calculation results related to stations. Lines (rivers, levees, pipe networks): Display calculation results related to rivers, levees, and pipe networks. Surfaces (rainfall surfaces, basin surfaces, inundation surfaces): Display calculation results related to rainfall surfaces, basin surfaces, and inundation surfaces

[0161] Here, the objects and calculation results concerned by different calculation models are not the same. Classified by the attributes of spatial shapes into three major types of results: points, lines, and surfaces. In the model processing module, the data in the result directory of each model is parsed and stored in the database according to the type, and a result viewing interface is provided for users through the service interface, as Figure 4 shown

[0162] In addition, it also includes a database module, specifically including: a real-time database: storing real-time data for real-time calculation and monitoring. A business database: storing business-related data, including model parameters, calculation results, etc. A role permission database: managing user roles and permissions to ensure secure access to data.

[0163] To implement the method of the embodiment of the present application, the embodiment of the present application also provides a model calculation scheduling device. This model calculation scheduling device corresponds to the above-mentioned model calculation scheduling method, and each step in the embodiment of the above-mentioned model calculation scheduling method is also fully applicable to the embodiment of this model calculation scheduling device.

[0164] As Figure 6 shown, the model calculation scheduling device 600 includes: a first determination module 601, a second determination module 602, a generation module 603, an acquisition module 604, and a scheduling module 605. The first determination module 601 is used to determine multiple calculation units of the basin based on the upstream and downstream topological relationships between the sub-basin partitions of the basin and the area data of each sub-basin; the upstream and downstream topological relationships are generated based on the encoding of the sub-basin partitions of the basin; the second determination module 602 is used to, for each calculation unit among the multiple calculation units, determine the position information of the basic section of the calculation unit; and based on the position information of the calculation unit in the upstream and downstream topological relationships, determine the type of the model processing unit of the basic section, the input task of the model processing unit, the output task of the model processing unit, and the calculation process information corresponding to the model processing unit; the number of model processing units includes multiple; the generation module 603 is used to generate a calculation task scheduling instruction based on the types of the respective model processing units in response to the calculation instruction information for the basin; the acquisition module 604 is used to obtain the identification information of the scheduling plan of the basin in response to the calculation task scheduling instruction; the scheduling plan includes multiple target model processing units, the calculation process information corresponding to each target model processing unit, and the target calculation nodes corresponding to each target model processing unit, and the target model processing unit is one of the multiple model processing units; the scheduling module 605 is used to start the target calculation processes corresponding to the respective target model processing units on the respective target calculation nodes based on the identification information of the scheduling plan; and control the operation of the respective target model processing units to generate calculation results; wherein, the model processing unit is a standardized encapsulated model processing unit.

[0165] In some embodiments, the acquisition module 604 is further used to, for each calculation unit among the multiple calculation units, obtain the position information of the outlet node corresponding to the calculation unit; the second determination module 602 is further used to determine the position information of the basic section of the calculation unit based on the position information of the outlet node.

[0166] In some embodiments, the scheduling module 605 is further configured to generate a start instruction corresponding to the type information for each target model processing unit in the scheduling scheme based on the type information of the target model processing unit.

[0167] In response to the start instruction, start the operation of the calculation program package of the target model processing unit to generate a model calculation result; wherein, the calculation program package includes input file information, output file information, output directory information, log directory, and configuration file; wherein, the configuration file is used to store the input path information and output path information of the target model processing unit based on a set text format; the set text format includes JSON format; based on each model calculation result, generate the calculation result of the basin.

[0168] In some embodiments, the generation module 603 is further configured to classify the calculation results based on the spatial geometric information of multiple calculation units to generate classification result data; and in response to the result display request, display the classification result data.

[0169] In some embodiments, the model calculation scheduling device further includes a display module 606, configured to obtain a monitoring request; in response to the monitoring request, display at least one of the following: the identification information of the scheduling scheme, the calculation process information of each model processing unit, the calculation status information of each model processing unit, and the calculation progress information of each model processing unit, and the calculation process information includes the number of processes and the process status.

[0170] In some embodiments, the model calculation scheduling device further includes an update module 607, configured to obtain a parameter change request for the model processing unit; in response to the parameter change request, update the initial parameters of the model processing unit to target parameters.

[0171] In some embodiments, the acquisition module 603 is further configured to acquire indication information for adding a model processing unit; the indication information includes the type of the model processing unit to be added; the second determination module 602 is further configured to, in response to the indication information, determine a target calculation unit corresponding to the model processing unit to be added based on the type of the model processing unit to be added, and add the model to be added to the target calculation unit; based on the position information of the basic section of the target calculation unit, determine the input task corresponding to the model processing unit to be added, the output task of the model processing unit to be added, and the process information of the model processing unit to be added.

[0172] In practical applications, the first determination module 601, the second determination module 602, the generation module 603, the acquisition module 604, the scheduling module 605, the display module 606, and the update module 607 can be implemented by a processor in the model calculation scheduling device. Of course, the processor needs to run a computer program in the memory to implement its functions.

[0173] It should be noted that: the model calculation scheduling device provided in the above embodiment only uses the division of the above program modules as an example when performing model calculation scheduling. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the model calculation scheduling device provided in the above embodiment and the model calculation scheduling method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0174] Based on the hardware implementation of the above program modules and in order to implement the method of the embodiment of the present application, the embodiment of the present application also provides an electronic device. Figure 7 Only an exemplary structure of the electronic device is shown, not all structures, and it can be implemented as needed. Figure 7 Partial or complete structure shown. Figure 7 As shown, the electronic device 700 provided in the embodiment of the present application includes: at least one processor 701, a memory 702, a user interface 703 and at least one network interface 704. The various components in the electronic device 700 are coupled together through a bus system 705. It can be understood that the bus system 705 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 705 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, in Figure 7 Various buses are labeled as bus system 705.

[0175] The user interface 703 may include a display, a keyboard, a mouse, a trackball, a click wheel, keys, buttons, a touch pad or a touch screen.

[0176] The memory 702 in the embodiment of the present application is used to store various types of data to support the operation of the electronic device. Examples of such data include: any computer program used to operate on the electronic device.

[0177] The three-dimensional modeling method of the ore body of the electronic device disclosed in the embodiments of the present application can be applied to the processor 701 or implemented by the processor 701. The processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the three-dimensional modeling method of the ore body of the electronic device can be completed by the integrated logic circuit of the hardware in the processor 701 or the instructions in the form of software. The above-mentioned processor 701 may be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 701 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. Combining the steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in the storage medium, and this storage medium is located in the memory 702. The processor 701 reads the information in the memory 702 and combines its hardware to complete the steps of the model calculation and scheduling method of the electronic device provided in the embodiments of the present application.

[0178] In an exemplary embodiment, the electronic device may be implemented by one or more application-specific integrated circuits (ASICs, Application Specific Integrated Circuit), DSPs, programmable logic devices (PLDs, Programmable Logic Device), complex programmable logic devices (CPLDs, Complex Programmable Logic Device), field programmable gate arrays (FPGAs, Field Programmable Gate Array), general-purpose processors, controllers, microcontroller units (MCUs, Micro Controller Unit), microprocessors (Microprocessor), or other electronic components, and is used to execute the foregoing method.

[0179] It can be understood that the memory 702 may be a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), an erasable programmable read-only memory (EPROM, Erasable Programmable Read-Only Memory), an electrically erasable programmable read-only memory (EEPROM, Electrically

[0180] Erasable Programmable Read-Only Memory), ferromagnetic random access memory (FRAM), Flash Memory, magnetic surface memory, optical disc, or Compact Disc Read-Only Memory (CD-ROM); the magnetic surface memory may be a disk memory or... The volatile memory may be a Random Access Memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), Direct Rambus Random Access Memory (DRRAM). The memories described in the embodiments of the present application are intended to include but not be limited to these and any other suitable types of memories.

[0181] In an exemplary embodiment, the embodiments of the present application further provide a computer storage medium, specifically a computer-readable storage medium, on which a computer program is stored, and the above computer program can be executed by a processor to complete the steps of the method of the embodiments of the present application. The computer-readable storage medium may be a memory such as ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.

[0182] In an exemplary embodiment, the embodiment of the present application further provides a computer program product, including a computer program, which can be executed by a processor 701 of an electronic device to complete the steps of the method of the embodiment of the present application.

[0183] It should be noted that: "first", "second", etc. are used to distinguish similar objects and do not necessarily have to be used to describe a specific order or sequence.

[0184] In addition, the technical solutions described in the embodiments of the present application can be arbitrarily combined without conflict.

[0185] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A model calculation scheduling method, characterized in that, Including: Determining a plurality of computing units of the basin based on the upstream-downstream topological relationship between sub-basin partitions of the basin and the area data of each of the sub-basin partitions; The upstream-downstream topological relationship is generated based on the encoding of each sub-basin partition of the basin; For each computing unit of the plurality of computing units, determining the location information of the basic section of the computing unit; And based on the location information of the computing unit in the upstream-downstream topological relationship, determining the type of the model processing unit of the basic section, the input task of the model processing unit, the output task of the model processing unit, and the computing process information corresponding to the model processing unit; the number of the model processing units includes a plurality; In response to the computing instruction information for the basin, generating a computing task scheduling instruction based on the types of the respective model processing units; In response to the computing task scheduling instruction, obtaining the identification information of the scheduling scheme of the basin; the scheduling scheme includes a plurality of target model processing units, the computing process information corresponding to each of the target model processing units, and the target computing nodes corresponding to each of the target model processing units, and the target model processing unit is one of the plurality of model processing units; Based on the identification information of the scheduling scheme, starting the target computing processes corresponding to the respective target model processing units on each of the target computing nodes; and controlling the operation of each of the target model processing units to generate the computing result of the basin; Wherein, the model processing unit is a model processing unit after standardized encapsulation.

2. The method according to claim 1, characterized in that, The method further includes: For each computing unit of the plurality of computing units, obtaining the location information of the outlet node corresponding to the computing unit; Based on the location information of the outlet node, determining the location information of the basic section of the computing unit.

3. The method according to claim 1, characterized in that, The controlling the operation of each of the target model processing units to generate the computing result of the basin includes: For each target model processing unit among the target model processing units in the scheduling scheme, generating a start instruction corresponding to the type information based on the type information of the target model processing unit; In response to the start instruction, starting the operation of the computing program package of the target model processing unit to generate a model computing result; wherein, the computing program package includes input file information, output file information, output directory information, log directory, and configuration file; wherein, the configuration file is used to store the input path information and output path information of the target model processing unit based on a set text format; the set text format includes JSON format; Based on each of the model computing results, generating the computing result of the basin.

4. The method according to claim 1, characterized in that, The method further includes: Classifying the computing result based on the spatial geometric information of the plurality of computing units to generate classified result data; and in response to a result display request, displaying the classified result data.

5. The method according to claim 1, characterized in that, The method further includes: Obtaining a monitoring request; In response to the monitoring request, displaying at least one of the following: The identification information of the scheduling scheme, the computing process information of each of the model processing units, the computing status information of each of the model processing units, and the computing progress information of each of the model processing units, where the computing process information includes the number of processes and the process status.

6. The method according to claim 1, characterized in that, The method further includes: Obtaining a parameter change request for the model processing unit; In response to the parameter change request, updating the initial parameters of the model processing unit to target parameters.

7. The method according to claim 1, characterized in that, The method further includes: Obtaining indication information for adding a model processing unit; the indication information includes the type of the model processing unit to be added; In response to the indication information, based on the type of the model processing unit to be added, determining the target computing unit corresponding to the model processing unit to be added, and adding the model to be added to the target computing unit; Based on the position information of the base section of the target computing unit, determining the input task corresponding to the model processing unit to be added, the output task corresponding to the model processing unit to be added, and the process information of the model processing unit to be added.

8. A model calculation scheduling device, characterized in that, The apparatus includes: A first determination module, configured to determine a plurality of computing units of the basin based on the upstream and downstream topological relationships between the sub-basin partitions of the basin and the area data of each of the sub-basin partitions; the upstream and downstream topological relationships are generated by encoding the sub-basin partitions of the basin; A second determination module, configured to, for each computing unit of the plurality of computing units, determine the position information of the base section of the computing unit; and based on the position information of the computing unit in the upstream and downstream topological relationships, determine the type of the model processing unit of the base section, the input task of the model processing unit, the output task of the model processing unit, and the computing process information corresponding to the model processing unit; the number of the model processing units includes a plurality; A generation module, configured to, in response to the computing indication information for the basin, generate a computing task scheduling instruction based on the types of the model processing units; An acquisition module, configured to, in response to the computing task scheduling instruction, acquire the identification information of the scheduling scheme of the basin; the scheduling scheme includes a plurality of target model processing units, the computing process information corresponding to each of the target model processing units, and the target computing nodes corresponding to each of the target model processing units, and the target model processing unit is one of the plurality of model processing units; A scheduling module, configured to, based on the identification information of the scheduling scheme, start the target computing processes corresponding to the target model processing units on each of the target computing nodes; and control the operation of each of the target model processing units to generate a computing result; Wherein, the model processing unit is a standardized encapsulated model processing unit.

9. An electronic device, characterized in that, Including: A processor and a memory for storing a computer program that can run on the processor, where The processor, when running the computer program, executes the steps of the method according to any one of claims 1 to 7.

10. A storage medium, on which a computer program is stored, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images