Numerical model running method and device, storage medium and electronic equipment

Abstract

The application provides a numerical model running method and device, a storage medium and an electronic device, and the method comprises the following steps: obtaining an initial field of an inner simulation area at a first reporting time, and obtaining a boundary field of the inner simulation area within a corresponding prediction time range at each reporting time in a plurality of reporting times including the first reporting time, wherein the reporting times other than the first reporting time in the plurality of reporting times are earlier than the first reporting time; performing boundary data fusion on the boundary field of the inner simulation area within the corresponding prediction time range at each reporting time to obtain a fused boundary field; and performing numerical simulation on the inner simulation area based on the initial field of the inner simulation area at the first reporting time and the fused boundary field to obtain a numerical simulation result of the inner simulation area within a target prediction time range. The embodiments of the application can improve the accuracy of the numerical simulation result while ensuring that the business requirements are met.

Description

Technical Field

[0001] This invention relates to the field of numerical simulation technology, and in particular to a method, apparatus, storage medium, and electronic device for running a numerical model. Background Technology

[0002] Currently, during the operation of numerical models (such as meteorological numerical models and air quality numerical models), due to the long running time of these models, the start time for specific forecast operations is generally chosen to be earlier than the start time required by the operational needs. However, for the same forecast period, the earlier the start time, the greater the uncertainty and the higher the probability of large deviations, which can lead to lower accuracy. Conversely, a start time that is too late relative to the operational needs may not meet the operational requirements. Therefore, there is currently no satisfactory solution for improving the accuracy of numerical simulation results while ensuring that operational needs are met. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a numerical model operation method, apparatus, storage medium, and electronic device to solve the problems of low accuracy due to too early reporting time or failure to meet business requirements due to too late reporting time in related technologies. In other words, embodiments of the present invention can realize numerical simulation of the inner simulation region by using the boundary field of the inner simulation region within the corresponding forecast time range of each of the multiple reporting times and the initial field of the inner simulation region under the latest first reporting time among the multiple reporting times. The earlier reporting time can ensure the satisfaction of business requirements, and the later reporting time can ensure the accuracy of numerical simulation results. That is, embodiments of the present invention can effectively improve the accuracy of numerical simulation results of the inner simulation region within the target forecast time range while ensuring that business requirements are met, so that the obtained numerical simulation results have both high accuracy and timeliness.

[0004] According to one aspect of the present invention, a numerical model operation method is provided, the numerical model operation method being applied in an inner-layer simulation service device, the method comprising:

[0005] The initial field of the inner simulation region at the first reporting time is obtained, and the boundary field of the inner simulation region at each of the multiple reporting times including the first reporting time is obtained within the corresponding forecast time range, with one reporting time corresponding to one forecast time range; wherein, the reporting times other than the first reporting time among the multiple reporting times are earlier than the first reporting time.

[0006] The boundary data of the inner simulated region boundary field within the corresponding forecast time range for each of the aforementioned start times are fused to obtain a fused boundary field, which includes the boundary field of the inner simulated region within the target forecast time range.

[0007] Based on the initial field of the inner simulation region and the fused boundary field at the first reporting time, numerical simulation is performed on the inner simulation region to obtain the numerical simulation results of the inner simulation region within the target prediction time range.

[0008] According to another aspect of the present invention, another numerical model operation method is provided, the numerical model operation method being applied in an outer simulation service device, the method comprising:

[0009] Obtain the outer simulation region forecast results for each of the multiple start times within the corresponding forecast time range, with one start time corresponding to one forecast time range;

[0010] Based on the forecast results of the outer simulated region for each start time within the corresponding forecast time range, the boundary field of the inner simulated region for each start time within the corresponding forecast time range and the initial field of the inner simulated region for each start time are determined.

[0011] The initial field of the inner simulation region at each reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time are sent to the inner simulation service device, so that the inner simulation service device can obtain the initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time, thereby performing numerical simulation on the inner simulation region. The plurality of reporting times include the first reporting time, and the reporting times other than the first reporting time are earlier than the first reporting time.

[0012] According to another aspect of the present invention, a numerical model operation apparatus is provided, the apparatus operating on an inner-layer simulation service device, the apparatus comprising:

[0013] The first acquisition unit is used to acquire the initial field of the inner simulation region at the first reporting time, and to acquire the boundary field of the inner simulation region of each reporting time within the corresponding forecast time range among a plurality of reporting times including the first reporting time, wherein one reporting time corresponds to one forecast time range; wherein, among the plurality of reporting times, the reporting time other than the first reporting time is earlier than the first reporting time.

[0014] The first processing unit is used to perform boundary data fusion on the boundary fields of the inner simulated region within the corresponding forecast time range for each reporting time, to obtain a fused boundary field, wherein the fused boundary field includes the boundary field of the inner simulated region within the target forecast time range.

[0015] The first processing unit is further configured to perform numerical simulation on the inner simulation region based on the initial field of the inner simulation region and the fused boundary field at the first reporting time, and obtain the numerical simulation results of the inner simulation region within the target prediction time range.

[0016] According to another aspect of the present invention, another numerical mode operation apparatus is provided, the apparatus operating on an outer simulation service device, the apparatus comprising:

[0017] The second acquisition unit is used to acquire the outer simulation area forecast results of each of the multiple start times within the corresponding forecast time range, with one start time corresponding to one forecast time range.

[0018] The second processing unit is used to determine the boundary field of the inner simulation region and the initial field of the inner simulation region at each start time based on the outer simulation region forecast results within the corresponding forecast time range for each start time.

[0019] The second processing unit is further configured to send the initial field of the inner simulation region at each reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time to the inner simulation service device, so that the inner simulation service device can obtain the initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time, thereby performing numerical simulation on the inner simulation region. The plurality of reporting times includes the first reporting time, and the reporting times other than the first reporting time among the plurality of reporting times are earlier than the first reporting time.

[0020] According to another aspect of the present invention, an electronic device is provided, the electronic device including a processor and a memory storing a program, wherein the program includes instructions that, when executed by the processor, cause the processor to perform the methods mentioned above.

[0021] According to another aspect of the present invention, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform the methods mentioned above.

[0022] This invention provides an embodiment that can obtain the initial field of the inner simulation region at the first reporting time, and the boundary field of the inner simulation region for each of the multiple reporting times, including the first reporting time, within the corresponding forecast time range. Each reporting time corresponds to a forecast time range; wherein, among the multiple reporting times, the reporting times other than the first reporting time are earlier than the first reporting time. Then, boundary data fusion can be performed on the boundary fields of the inner simulation region within the corresponding forecast time range for each reporting time to obtain a fused boundary field, which includes the boundary field of the inner simulation region within the target forecast time range. Based on this, numerical simulation can be performed on the inner simulation region based on the initial field and the fused boundary field at the first reporting time to obtain the numerical simulation results of the inner simulation region within the target forecast time range. As can be seen, the embodiments of the present invention can realize the numerical simulation of the inner simulation region by using the boundary field of the inner simulation region within the corresponding forecast time range for each of the multiple reporting times and the initial field of the inner simulation region under the latest reporting time among the multiple reporting times. The earlier reporting time can ensure the satisfaction of business requirements, and the later reporting time can ensure the accuracy of the numerical simulation results. That is, the embodiments of the present invention can effectively improve the accuracy of the numerical simulation results of the inner simulation region within the target forecast time range while ensuring that business requirements are met, so that the obtained numerical simulation results have both high accuracy and timeliness. Attached Figure Description

[0023] Further details, features, and advantages of the invention are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 A flowchart illustrating a numerical mode operation method according to an exemplary embodiment of the present invention is shown;

[0025] Figure 2 A flowchart illustrating another numerical mode operation method according to an exemplary embodiment of the present invention is shown;

[0026] Figure 3 A flowchart illustrating yet another numerical mode operation method according to an exemplary embodiment of the present invention is shown;

[0027] Figure 4 A schematic block diagram of a numerical mode operation device according to an exemplary embodiment of the present invention is shown;

[0028] Figure 5 A schematic block diagram of another numerical mode operation device according to an exemplary embodiment of the present invention is shown;

[0029] Figure 6A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present invention is shown. Detailed Implementation

[0030] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the invention.

[0031] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0032] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0033] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0034] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0035] Optionally, embodiments of the present invention may involve a distributed mode operation system, which may include, but is not limited to, an inner simulation service device (which may be a local service device) and an outer simulation service device (which may be a cloud service device), etc., and the embodiments of the present invention do not limit this. Based on this, the execution subject of the numerical model operation method provided by the embodiments of the present invention can be a distributed mode operation system, that is, it can be executed by the inner simulation service device and the outer simulation service device; optionally, the numerical model operation method can also be called a distributed simulation system operation method, and one mode system can be used to run a numerical simulation at a reporting time.

[0036] Accordingly, the execution subject of the numerical mode operation method provided in this embodiment of the invention can be one or more electronic devices, and this invention does not limit this; that is, the numerical mode operation method provided in this embodiment of the invention can be executed by one or more electronic devices constituting a distributed mode operation system, and the inner simulation service device and the outer simulation service device can each be composed of at least one electronic device. The electronic device can be a terminal (i.e., a client) or a server. Optionally, the terminal mentioned herein may include, but is not limited to: smartphones, tablets, laptops, desktop computers, smartwatches, smart voice interaction devices, smart home appliances, vehicle terminals, aircraft, etc. The server mentioned herein can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms, etc.

[0037] Based on the above description, this embodiment of the invention proposes a numerical mode operation method. This method can be applied to an inner-layer simulation service device, meaning it can be executed by the inner-layer simulation service device, or by the electronic devices constituting the inner-layer simulation service device. For ease of explanation, the following description will use the execution of this numerical mode operation method by an inner-layer simulation service device as an example; such as... Figure 1 As shown, the numerical model operation method may include the following steps S101-S103:

[0038] S101, obtain the initial field of the inner simulation region at the first reporting time, and obtain the boundary field of the inner simulation region of each reporting time within the corresponding forecast time range among multiple reporting times including the first reporting time, with one reporting time corresponding to one forecast time range; wherein, among the multiple reporting times, the reporting times other than the first reporting time are earlier than the first reporting time.

[0039] Optionally, the multiple reporting start times can be set based on experience or actual needs, and this embodiment of the invention does not limit this. In this embodiment, the first reporting start time is the latest among the multiple reporting start times, that is, the reporting start time with the smallest lead time relative to the business demand time. For example, assuming that the multiple reporting start times include 08:00 (e.g., 08:00 Beijing time) of the previous day (i.e., the day before the business demand time), 20:00 (e.g., 20:00 Beijing time) of the previous day, in this case, the first reporting start time can be 20:00 of the previous day, and so on. Optionally, the business demand time can be set based on experience or actual needs, and this embodiment of the invention does not limit this; for example, the business demand time can be 8:00 AM of the current day, such as 8:00 AM every morning, and so on.

[0040] In this embodiment, the initial field of an inner simulation region can be an initial field of the inner simulation region (also referred to as initial field data), and the boundary field of an inner simulation region can be a boundary field of the inner simulation region (also referred to as boundary field data). Optionally, the inner simulation region can be set empirically or according to actual needs; this embodiment of the invention does not limit this. Optionally, the resolution of the inner simulation region can be the inner layer resolution, so that the inner simulation region is meshed according to the inner layer resolution; optionally, the inner layer resolution can be set empirically or according to actual needs; this embodiment of the invention does not limit this. It should be understood that the inner layer resolution is higher than the resolution of the outer simulation region (i.e., the outer layer resolution), and the outer simulation region may include the inner simulation region. Optionally, an initial field may include, but is not limited to, at least one of the following: the initial meteorological field of each grid in the corresponding simulation region (such as the inner simulation region) and the initial pollutant concentration of the target pollutant. That is, an initial field may include, but is not limited to, at least one of the following: the initial meteorological field of the corresponding simulation region (which may include the initial meteorological field of each grid) and the initial pollutant concentration data (which may include the initial pollutant concentration of the target pollutant in each grid), etc. The embodiments of the present invention do not limit this. Optionally, a boundary field may include, but is not limited to, at least one of the following: the meteorological boundary field of the corresponding simulation region and the pollutant concentration boundary field data of the target pollutant, etc. The embodiments of the present invention do not limit this. Optionally, the target pollutant may be any pollutant, and the embodiments of the present invention do not limit this.

[0041] Optionally, the later a reporting start time is, the shorter the corresponding forecast time range (i.e., the shorter the forecast duration of the forecast time range). In other words, a later reporting start time results in a shorter forecast duration, ensuring that business needs are met. Specifically, for the third and fourth reporting start times among multiple reporting start times, where the third and fourth reporting start times are any different starting times among the multiple reporting start times, when the fourth reporting start time is later than the third reporting start time, the forecast duration of the forecast time range corresponding to the fourth reporting start time is shorter than the forecast duration of the forecast time range corresponding to the third reporting start time. For example, assuming the target forecast time range is the next 15 days, and the multiple forecast times include a first forecast time and a second forecast time, in this case, the forecast time range corresponding to the first forecast time can include the next 3 days, the forecast time range corresponding to the second forecast time range can include the next 15 days (i.e., include the target forecast time range), and so on. Optionally, the forecast time range corresponding to a start time can be set based on experience or according to actual needs, and this embodiment of the invention does not limit this. Optionally, the forecast time range corresponding to a start time may also include the time range between the corresponding start time and the start time of the next day, etc.; for example, assuming a start time is 20:00 on the previous day, then the forecast time range corresponding to that start time may also include 4 hours from 20:00 on the previous day, etc.

[0042] In this embodiment of the invention, the methods for obtaining the initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region at each reporting time within the corresponding forecast time range may include, but are not limited to, the following:

[0043] The first acquisition method: The inner simulation service device stores the initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region at each reporting time within the corresponding forecast time range in its own storage space; in this case, the inner simulation service device can obtain the initial field of the inner simulation region at the first reporting time from its own storage space, as well as the boundary field of the inner simulation region at each reporting time within the corresponding forecast time range among multiple reporting times including the first reporting time.

[0044] The second acquisition method: The initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region at each reporting time within the corresponding forecast time range can be obtained from the outer simulation service equipment; wherein, the initial field of the inner simulation region at a reporting time and the boundary field of the inner simulation region at a reporting time within the corresponding forecast time range can be determined based on the forecast results of the outer simulation region at the corresponding reporting time within the corresponding forecast time range, and so on. Optionally, the inner-layer simulation service device can receive the initial field of the inner-layer simulation region at the first reporting time and the boundary field of the inner-layer simulation region within the corresponding forecast time range for each reporting time from the outer-layer simulation service device, so as to obtain the initial field of the inner-layer simulation region at the first reporting time and the boundary field of the inner-layer simulation region within the corresponding forecast time range for each reporting time from the outer-layer simulation service device; for example, the inner-layer simulation service device can receive the initial field of the inner-layer simulation region at each reporting time and the boundary field of the inner-layer simulation region within the corresponding forecast time range for each reporting time from the outer-layer simulation service device, thereby obtaining the initial field of the inner-layer simulation region at the first reporting time and the boundary field of the inner-layer simulation region within the corresponding forecast time range for each reporting time, and so on. In this case, when the outer simulation service device is a cloud service device (i.e., the cloud) and the memory simulation service device is a local service device (i.e., the local end), the embodiments of the present invention can transmit the initial field of the inner simulation region at each reporting time generated by the cloud and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time to the local end through the cloud download and local end receiving modules.

[0045] S102, perform boundary data fusion on the boundary fields of the inner simulation region within the corresponding forecast time range for each reporting time to obtain the fused boundary field, which includes the boundary fields of the inner simulation region within the target forecast time range.

[0046] Optionally, the target forecast time range can be set based on experience or according to actual needs; this embodiment of the invention does not limit this. In this embodiment, the forecast time range corresponding to the earliest start time among multiple start times may include the target forecast time range.

[0047] Optionally, the inner-layer simulation service equipment can add the inner-layer simulation region boundary field whose first reporting time falls within the corresponding forecast time range to the fused boundary field. For any reporting time other than the first reporting time among multiple reporting times, the inner-layer simulation region boundary field whose reporting time falls within the corresponding forecast time range can be extracted from the inner-layer simulation region boundary field whose reporting time falls within the corresponding extraction time range. This inner-layer simulation region boundary field whose reporting time falls within the corresponding extraction time range can then be added to the fused boundary field. This achieves boundary data fusion of the inner-layer simulation region boundary fields whose reporting times fall within the corresponding forecast time range for each reporting time, resulting in a fused boundary field. The extraction time range corresponding to any reporting time is the time range between the end time of the forecast time range corresponding to the subsequent reporting time of any reporting time and the end time of the forecast time range corresponding to the subsequent reporting time. The subsequent reporting time of any reporting time refers to the first reporting time that follows any reporting time in the order from earliest to latest among multiple reporting times. Correspondingly, the extraction time range corresponding to the first reporting time can be: the forecast time range corresponding to the first reporting time; that is, the boundary field of the inner simulation region within the corresponding extraction time range of the first reporting time can be added to the fused boundary field.

[0048] Based on this, the inner-layer simulation service equipment can stitch together the boundary fields of the inner-layer simulation region within the corresponding extraction time range for each reporting time, thereby achieving boundary data fusion of the boundary fields of the inner-layer simulation region within the corresponding forecast time range for each reporting time, resulting in a fused boundary field. In other words, the fused boundary field can include the boundary fields of the inner-layer simulation region within the corresponding extraction time range for each reporting time, and the time range formed by the extraction time ranges corresponding to each reporting time can include the target forecast time range, thus enabling the fused boundary field to include the boundary field of the inner-layer simulation region within the target forecast time range (which can also be referred to here as the inner-layer simulation region boundary field). Accordingly, for the same forecast period, when the forecast period falls within the forecast time range corresponding to at least two start times, this embodiment of the invention can retain the boundary field of the inner simulation region within the forecast period when the latest start time among the at least two start times is within that forecast period. When the forecast period falls only within the forecast time range corresponding to one start time (here, the earliest start time among multiple start times), the boundary field of the inner simulation region within the forecast period when the earliest start time is within that forecast period can be retained to obtain a fused boundary field, and so on. That is, for any forecast period, this embodiment of the invention can retain the boundary field of the inner simulation region within any forecast period, including the latest start time of any forecast period, within any forecast period for the corresponding forecast time range among multiple start times. Optionally, a forecast time range may include at least one forecast period, and a forecast period may be one hour or two hours, etc., and this embodiment of the invention does not limit this. Based on this, the boundary field of the inner simulation region within a time range for a start time may include the boundary field of the inner simulation region within each forecast period included in the corresponding time range for the corresponding start time, and so on. As can be seen, the embodiments of the present invention can preferentially retain the boundary fields of the inner simulated regions with later reporting times within the corresponding forecast time range, which can effectively improve the accuracy of the fused boundary fields.

[0049] Optionally, multiple reporting times may include a first reporting time and a second reporting time. That is, the number of reporting times can be two, with the second reporting time being earlier than the first reporting time, and the forecast time range corresponding to the second reporting time including the target forecast time range. In this case, any of the above reporting times can be the second forecast time (i.e., any of the above reporting times can only be the second reporting time). In this case, the extraction time range corresponding to the second forecast time is the time range between the end time of the forecast time range corresponding to the first reporting time and the end time of the target forecast time range. For example, assuming the target forecast time range is the next 15 days, the first reporting time is 20:00 (i.e., 20:00 of the previous day), and the second reporting time is 8:00 (i.e., 08:00 of the previous day), and further assuming that the forecast time range corresponding to the second reporting time includes the time range between the second reporting time and the end time of the target forecast time range (such as the boundary field of the inner simulated region within the corresponding forecast time range where the second reporting time is located, which can be represented as B), and further assuming that the forecast time range corresponding to the second reporting time includes the time range between the second reporting time and the end time of the target forecast time range (such as the boundary field of the inner simulated region within the corresponding forecast time range where the second reporting time is located, which can be represented as B), then the forecast time range is within the target forecast time range. 08-15 The file may contain hourly transmission information of the inner simulated region boundary for the next 15 days, starting from 08:00. The forecast time range corresponding to the first reporting time includes the time range from the first reporting time to the end time of the next 3 days (such as the inner simulated region boundary field (which can be represented as B) within the corresponding forecast time range at the first reporting time). 20-3 (The file) can contain hourly transmission information of the inner simulated region boundary for the next 3 days, starting from 20:00; in this case, boundary field data for different time periods can be spliced ​​from different file sources, such as from boundary field file B. 20-3 Extract the boundary fields of the inner-layer simulation region from the first 3 days of the next 15 days (which can be represented as T1, T2, and T3 respectively), from the boundary field file B. 08-15 Extract the boundary fields of the inner simulated region for days 4-15 of the next 15 days (which can be represented as T4, ..., T15, respectively); correspondingly, T1, ..., T15 can be stored in the fused boundary field (which can be represented as B) according to the model requirements (such as the target numerical model). merge In the document; optionally, B can also be included. 20-3 The boundary field of the inner simulated region within the time range between the start time of the target forecast time range starting at 20:00 in the file is added to B. merge The document describes how boundary data fusion is achieved, and so on. It is evident that the inner-layer simulation service device can... 08-15 and B 20-3 The boundary field B is obtained by fusion. merge .

[0050] S103, based on the initial field and fused boundary field of the inner simulation region at the first reporting time, numerical simulation is performed on the inner simulation region to obtain the numerical simulation results of the inner simulation region within the target prediction time range.

[0051] In this embodiment of the invention, the inner-layer simulation service device can start reporting from the first reporting time, thereby realizing numerical simulation of the inner-layer simulation area within the target forecast time range. Optionally, the inner-layer simulation service device can call the target numerical model and perform numerical simulation of the inner-layer simulation area based on the initial field and fused boundary field of the inner-layer simulation area at the first reporting time, to obtain the numerical simulation results of the inner-layer simulation area within the target forecast time range. Optionally, the target numerical model can be set according to experience or according to actual needs, and this embodiment of the invention does not limit it; for example, the target numerical model can be any meteorological model (such as the WRF (Weather Research Forecast) model (a mesoscale weather forecasting model), etc.), or any air quality model (such as NAQPMS (Nested Air Quality Prediction Modeling System), CMAQ (an air quality forecasting and assessment system), CAMx (an atmospheric pollutant calculation model based on atmospheric chemistry for ozone, particulate matter, etc.), WRFChem (an online coupled atmospheric chemistry model), etc., etc., and this embodiment of the invention does not limit it.

[0052] Optionally, numerical simulation of a region can refer to numerical simulation of target simulation factors within the corresponding region; optionally, the target simulation factors can include any meteorological factor and / or any pollutant, such as any meteorological factor or any pollutant, etc., and the embodiments of the present invention do not limit this.

[0053] Based on this, embodiments of the present invention can use the fused boundary field after boundary data fusion and the optimal initial field of the inner simulation region (i.e., the initial field of the inner simulation region at the first reporting time) to drive the inner simulation service equipment to predict the inner simulation region within the target prediction time range. It should be understood that the later the reporting time, the more accurate the initial field. Therefore, the initial field of the inner simulation region at the first reporting time can be the optimal initial field of the inner simulation region. In other words, the initial field generated by the model system that reports later (i.e., the initial field of the inner simulation region at the first reporting time) has the optimal initial information for the reporting of the inner simulation region.

[0054] For example, assuming the target forecast time range is the next 15 days, the fused boundary field can include boundary transmission information for all times in the forecast period of the next 15 days. Furthermore, assuming multiple reporting times include a first reporting time and a second reporting time, with the first reporting time being 20:00 the previous day and the second reporting time being 08:00 the previous day, then compared to the distributed simulation results reported at 08:00 the previous day, this embodiment of the invention can achieve better forecast results through updating the boundary field and the initial field. Specifically, the boundary field reported at 08:00 the previous day can be updated using the initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at the first reporting time, to obtain the fused boundary field and the optimal initial field, thus improving forecast performance. Moreover, compared to the distributed simulation results reported at 20:00 the previous day, the model running time reported at 20:00 the previous day can include the first 3 days of the next 15 days (i.e., no need to run the next 4 to 15 days), resulting in better timeliness. Based on this, the embodiments of the present invention drive the numerical simulation results (also known as inner simulation results) of the inner simulation region within the target prediction time range through the optimal initial field and fused boundary field of the inner simulation region, which can simultaneously possess the advantages of prediction effect and prediction timeliness.

[0055] This invention provides an embodiment that can obtain the initial field of the inner simulation region at the first reporting time, and the boundary field of the inner simulation region for each of the multiple reporting times, including the first reporting time, within a corresponding forecast time range. Each reporting time corresponds to a forecast time range; wherein, among the multiple reporting times, the reporting times other than the first reporting time are earlier than the first reporting time. Then, boundary data fusion can be performed on the boundary fields of the inner simulation region for each reporting time within the corresponding forecast time range to obtain a fused boundary field, which includes the boundary field of the inner simulation region within the target forecast time range. Based on this, numerical simulation can be performed on the inner simulation region based on the initial field and the fused boundary field at the first reporting time to obtain the numerical simulation results of the inner simulation region within the target time range. As can be seen, the embodiments of the present invention can realize the numerical simulation of the inner simulation region by using the boundary field of the inner simulation region within the corresponding forecast time range of each of the multiple reporting times and the initial field of the inner simulation region under the latest reporting time among the multiple reporting times. The earlier reporting time can ensure the satisfaction of business requirements, and the later reporting time can ensure the accuracy of the numerical simulation results. That is, the embodiments of the present invention can effectively improve the accuracy of the numerical simulation results of the inner simulation region within the target time range while ensuring that business requirements are met, so that the obtained numerical simulation results have both high accuracy and timeliness.

[0056] Based on the above description, this embodiment of the invention also proposes a more specific numerical model operation method. Accordingly, this numerical model operation method can be applied to an outer simulation service device, that is, it can be executed by the outer simulation service device, i.e., by the electronic devices constituting the outer simulation service device. For ease of explanation, the following descriptions will use the execution of this numerical model operation method by an outer simulation service device as an example; please refer to... Figure 2 The numerical model operation method may include the following steps S201-S203:

[0057] S201, obtain the outer simulation area forecast results of each of the multiple start times within the corresponding forecast time range, with one start time corresponding to one forecast time range.

[0058] In this invention, a forecast result for an outer simulation region can be a forecast result for that outer simulation region. Optionally, the outer simulation region can be set based on experience or actual needs, and this embodiment of the invention does not limit this. Optionally, the number of outer simulation regions (also called outer nested regions) can be one or more, and this embodiment of the invention does not limit this. Optionally, an outer simulation region can correspond to a resolution, and the resolution of the outer simulation region is lower than that of the inner simulation region. Optionally, the resolution corresponding to an outer simulation region can be set based on experience or actual needs, and this embodiment of the invention does not limit this. For example, assuming the number of outer simulation regions is 2, and the number of start times among multiple start times is 2, then two sets of coarse-resolution numerical simulations can be run separately, and each can run two outer simulation regions, such as the resolution of each outer simulation region being 27km (kilometers) - 9km, etc.

[0059] Optionally, the methods for obtaining the forecast results of the outer simulation region within the corresponding forecast time range for each start time may include, but are not limited to, the following:

[0060] The first method of acquisition: The outer simulation service equipment can obtain the data download link and download the outer simulation regional forecast results for each reporting time within the corresponding forecast time range based on the data download link.

[0061] The second acquisition method: The outer simulation service device can acquire the initial field of the outer simulation region at each of the multiple reporting times; and based on the initial field of the outer simulation region at each reporting time, perform numerical simulations on the outer simulation region according to the forecast time range corresponding to each reporting time, to obtain the forecast results of the outer simulation region at each reporting time within the corresponding forecast time range, and so on. Here, an initial field of the outer simulation region can be a single initial field for the outer simulation region. Optionally, the outer simulation service device can call the target numerical model and, based on the initial field of the outer simulation region at each reporting time, perform numerical simulations on the outer simulation region according to the forecast time range corresponding to each reporting time, to obtain the forecast results of the outer simulation region at each reporting time within the corresponding forecast time range.

[0062] Optionally, one reporting time can correspond to one model system. That is, one model system can run numerical simulations at one reporting time. For example, assuming multiple reporting times include 08:00 and 20:00 of the previous day, after the first model system starts reporting at 08:00, it can generate outer simulation region forecasts for the next 15 days. After the second model system starts reporting at 20:00, it can generate outer simulation region forecasts for the next 3 days. Based on this, after the first and second model systems are completed, they can also generate the initial field of the inner simulation region at the corresponding reporting time and the boundary field of the inner simulation region within the corresponding forecast time range. The model system starting at 20:00 of the previous day has a shorter forecast time, thus enabling it to complete the simulation process earlier to support meeting the final operational timeliness requirements.

[0063] S202, based on the forecast results of the outer simulation region at each start time within the corresponding forecast time range, determine the boundary field of the inner simulation region at each start time within the corresponding forecast time range and the initial field of the inner simulation region at each start time.

[0064] Optionally, the outer simulation service equipment can call the target numerical model (such as calling the module in the target numerical model used to generate the initial field and boundary field), and determine the boundary field of the inner simulation region and the initial field of the inner simulation region at each start time within the corresponding forecast time range based on the outer simulation region forecast results at each start time within the corresponding forecast time range. In other words, according to the model requirements of the target numerical model, the boundary field of the inner simulation region and the initial field of the inner simulation region at each start time can be determined based on the outer simulation region forecast results at each start time within the corresponding forecast time range, and so on.

[0065] It should be understood that there are two contradictions in the numerical computation process: on the one hand, the larger the simulation area and the more grids there are, the greater the computational load and the slower the computation time; on the other hand, the larger the simulation area, the more accurate the boundary field can be provided for the target area, and the more accurate the simulation results. To balance these two contradictions, numerical models generally support multi-layer nested simulations (i.e., setting several layers of different regions with an inclusion relationship from large to small, with different resolutions for different regions, the outer region (i.e., the outer simulation area) has a lower resolution, and the inner region (i.e., the inner simulation area) has a higher resolution). Through model nesting technology, the outer region can simulate a larger space with a smaller computational load (for the same area size, the lower the grid resolution, the fewer the number of grids), while the inner region, because it obtains more accurate simulation results from the input of the outer region and is relatively small (smaller area, fewer grids), can also obtain more accurate calculation results with a smaller computational load. Based on this, embodiments of the present invention can obtain more accurate forecast results for the outer simulation region through a larger outer simulation region, and simultaneously ensure accuracy and timeliness by using different reporting times, thereby obtaining more accurate initial fields and boundary fields of the inner simulation region under different reporting times, so as to improve the accuracy of numerical simulation of the inner simulation region while ensuring that business needs are met.

[0066] S203, the initial field of the inner simulation region at each reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time are sent to the inner simulation service device, so that the inner simulation service device can obtain the initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time, thereby performing numerical simulation on the inner simulation region. The multiple reporting times include the first reporting time, and the reporting times other than the first reporting time are earlier than the first reporting time.

[0067] Based on this, after receiving the initial field of the inner simulation region at each reporting time and the boundary field of the inner simulation region within the corresponding forecast time range for each reporting time, the inner simulation service equipment can determine the initial field of the inner simulation region at the first reporting time from the initial fields of the inner simulation region at each reporting time. Thus, the latest reporting time among multiple reporting times can be taken as the first reporting time, and the initial field of the inner simulation region at the latest reporting time can be taken as the initial field of the inner simulation region at the first reporting time, and so on.

[0068] For example, such as Figure 3As shown, assuming the outer simulation service device is in the cloud and the inner simulation service device is on the local end, multiple reporting times include 08:00 of the previous day (i.e., reporting can start at 08:00) and 20:00 of the previous day (i.e., reporting can start at 20:00). Furthermore, assuming the forecast time range corresponding to 08:00 of the previous day covers the next 15 days, and the forecast time range corresponding to 20:00 of the previous day covers the next 3 days, then after receiving the data from the cloud, the local end can obtain the initial field of the inner simulation region under the reporting time starting at 08:00, and the boundary field of the inner simulation region for the next 15 days under the reporting time starting at 08:00 (i.e., the inner simulation data for the next 15 days). The data is divided into the regional boundary field, the initial field of the inner simulation region reported from 20:00, and the boundary field of the inner simulation region for the next 3 days reported from 20:00. Boundary data fusion is then performed to obtain the fused boundary field. In this case, the first reporting time can be 20:00 of the previous day. Then the local end can report from 20:00 of the previous day to perform numerical simulation of the inner simulation region (i.e., perform numerical simulation of the inner simulation region), thereby obtaining the 15-day forecast result of the inner simulation region reported from 20:00 (i.e., the numerical simulation result of the inner simulation region within the target forecast time range (which may include the next 15 days).

[0069] In summary, the embodiments of the present invention can be applied in scenarios involving the construction of distributed weather forecasting and air quality forecasting model systems. For example, this scheme can be used when a simulation system is deployed according to a distributed simulation plan, and a simple 20:00 start time report cannot meet the timeliness requirements, thus simultaneously satisfying both timeliness and accuracy. Based on this, the embodiments of the present invention can rapidly perform numerical simulations of the outer simulation area using abundant resources such as cloud computing, thereby further improving the efficiency of numerical simulation operations. Furthermore, since the forecast duration for the forecast time range corresponding to a later start time is shorter, the embodiments of the present invention can complete the process of numerically simulating the outer simulation area according to the forecast time range corresponding to the later start time earlier, thereby enabling the inner simulation service equipment to start numerical simulations of the inner simulation area as early as possible to support the final operational timeliness and effectively ensure the accuracy of the numerical simulation results.

[0070] This invention provides an embodiment that can acquire forecast results for the outer simulation region within a corresponding forecast time range for each of multiple reporting times, with each reporting time corresponding to a forecast time range. Then, based on the outer simulation region forecast results for each reporting time within the corresponding forecast time range, the boundary field of the inner simulation region and the initial field of the inner simulation region at each reporting time within the corresponding forecast time range can be determined. Further, the initial field of the inner simulation region at each reporting time and the boundary field of the inner simulation region within the corresponding forecast time range for each reporting time can be sent to the inner simulation service device. This allows the inner simulation service device to obtain the initial field of the inner simulation region at the first reporting time and the boundary fields of the inner simulation region within the corresponding forecast time range for each reporting time, thereby performing numerical simulation of the inner simulation region. The multiple reporting times include the first reporting time, and the reporting times other than the first reporting time are earlier than the first reporting time. As can be seen, the embodiments of the present invention can effectively improve the overall timeliness of the mode operation by running multiple sets of simulations with different start times and different forecast durations (i.e., different forecast time ranges) in the outer simulation service equipment, with the earlier start time simulation service forecast duration being longer (i.e., the forecast time range corresponding to the earlier start time being longer) and the later start time simulation service forecast duration being shorter (i.e., the forecast time range corresponding to the later start time being shorter). Correspondingly, the inner simulation service equipment can receive multiple sets of initial fields of the inner simulation area with different start times. After the boundary field of the inner simulation region is obtained, the initial field and the boundary field are integrated (that is, the initial field of the inner simulation region at the first reporting time is determined from multiple initial fields of the inner simulation region at different reporting times, and the boundary data of the boundary fields of the inner simulation region at each reporting time within the corresponding forecast time range is fused). Based on the integrated initial field and boundary field, the numerical simulation of the inner simulation region is carried out, which makes the final local simulation results (i.e. the numerical simulation results of the inner simulation region within the target forecast time range) have both high accuracy and timeliness.

[0071] Based on the description of the relevant embodiments of the numerical model running method above, this embodiment of the invention also proposes a numerical model running device. This numerical model running device can be a computer program (including program code) running on an inner-layer simulation service device; that is, the numerical model running device can run on an inner-layer simulation service device. Figure 4 As shown, the numerical model running device may include a first acquisition unit 401 and a first processing unit 402. The numerical model running device can perform... Figure 1 The numerical mode operation method shown indicates that the numerical mode operation device can operate the above-mentioned unit:

[0072] The first acquisition unit 401 is used to acquire the initial field of the inner layer simulation region at the first reporting time, and to acquire the boundary field of the inner layer simulation region of each reporting time within the corresponding forecast time range among a plurality of reporting times including the first reporting time, wherein one reporting time corresponds to one forecast time range; wherein, among the plurality of reporting times, the reporting time other than the first reporting time is earlier than the first reporting time.

[0073] The first processing unit 402 is used to perform boundary data fusion on the boundary fields of the inner simulated region within the corresponding forecast time range for each reporting time, to obtain a fused boundary field, wherein the fused boundary field includes the boundary field of the inner simulated region within the target forecast time range.

[0074] The first processing unit 402 is further configured to perform numerical simulation on the inner simulation region based on the initial field of the inner simulation region and the fused boundary field at the first reporting time, and obtain the numerical simulation results of the inner simulation region within the target prediction time range.

[0075] In one implementation, when the first processing unit 402 performs boundary data fusion on the boundary fields of the inner simulated regions whose respective start times are within the corresponding forecast time range to obtain a fused boundary field, it can specifically be used for:

[0076] Add the boundary field of the inner simulated region within the corresponding forecast time range of the first reporting time to the fused boundary field;

[0077] For any reporting time other than the first reporting time among the multiple reporting times, the inner simulated region boundary field of the reporting time within the corresponding forecast time range of the inner simulated region boundary field of the reporting time is extracted, and the inner simulated region boundary field of the reporting time within the corresponding extraction time range of the reporting time is added to the fused boundary field, so as to realize the boundary data fusion of the inner simulated region boundary fields of each reporting time within the corresponding forecast time range to obtain the fused boundary field;

[0078] The extraction time range corresponding to any one of the initial reporting times is the time range between the end time of the forecast time range corresponding to the next initial reporting time of any one initial reporting time and the end time of the forecast time range corresponding to any one initial reporting time. The next initial reporting time of any one initial reporting time refers to the first initial reporting time that is located after any one initial reporting time in the order from early to late among the multiple initial reporting times.

[0079] In another embodiment, the plurality of reporting times include a first reporting time and a second reporting time, the second reporting time being earlier than the first reporting time, and the forecast time range corresponding to the second reporting time including the target forecast time range, and any one of the reporting times being the second forecast time; the extraction time range corresponding to the second forecast time is the time range between the end time of the forecast time range corresponding to the first reporting time and the end time of the target forecast time range.

[0080] In another implementation, the initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region at each reporting time within the corresponding forecast time range are obtained from the outer simulation service device.

[0081] Among them, the initial field of the inner simulation region at a given start time and the boundary field of the inner simulation region at a given start time within the corresponding forecast time range are determined based on the forecast results of the outer simulation region at the corresponding start time within the corresponding forecast time range.

[0082] Based on the description of the relevant embodiments of the numerical model running method above, this embodiment of the invention also proposes another numerical model running device. This numerical model running device can be a computer program (including program code) running on an outer simulation service device; that is, the numerical model running device can run on the outer simulation service device. Figure 5 As shown, the numerical model running device may include a second acquisition unit 501 and a second processing unit 502. The numerical model running device can perform... Figure 2 The numerical mode operation method shown indicates that the numerical mode operation device can operate the above-mentioned unit:

[0083] The second acquisition unit 501 is used to acquire the outer simulation area forecast results of each of the multiple start times within the corresponding forecast time range, with one start time corresponding to one forecast time range.

[0084] The second processing unit 502 is used to determine the boundary field of the inner simulation region and the initial field of the inner simulation region at each start time based on the outer simulation region forecast results of each start time within the corresponding forecast time range.

[0085] The second processing unit 502 is further configured to send the initial field of the inner simulation region at each reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time to the inner simulation service device, so that the inner simulation service device can obtain the initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time, thereby performing numerical simulation on the inner simulation region. The plurality of reporting times includes the first reporting time, and the reporting times other than the first reporting time among the plurality of reporting times are earlier than the first reporting time.

[0086] In one embodiment, when the second acquisition unit 501 acquires the outer simulation region forecast results for each of the multiple start times within the corresponding forecast time range, it may specifically be used for:

[0087] Obtain the initial field of the outer simulation region at each of the multiple reporting times;

[0088] Based on the initial field of the outer simulation region at each of the aforementioned start times, numerical simulations are performed on the outer simulation region according to the forecast time range corresponding to each of the aforementioned start times, to obtain the forecast results of the outer simulation region at each of the aforementioned start times within the corresponding forecast time range.

[0089] According to one embodiment of the present invention, Figure 4 and Figure 5 Each unit in the numerical mode operation device shown can be individually or entirely merged into one or more other units, or one or more of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effects of the embodiments of the present invention. The above units are based on logical function division. In practical applications, the function of one unit can be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of the present invention, any numerical mode operation device may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented collaboratively by multiple units.

[0090] According to another embodiment of the present invention, it is possible to perform operations such as those described above by running on a general-purpose electronic device, such as a computer, which includes processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). Figure 1 The computer program (including program code) involved in each step of the corresponding method shown, to construct such... Figure 4The numerical mode operation apparatus shown herein, and the numerical mode operation method for implementing embodiments of the present invention; correspondingly, it can be implemented by running on a general-purpose electronic device, such as a computer, which includes processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM), capable of performing such operations. Figure 2 The computer program (including program code) involved in each step of the corresponding method shown, to construct such... Figure 5 The numerical mode operation apparatus shown herein, and the numerical mode operation method for implementing embodiments of the present invention, are described. The computer program may be recorded on, for example, a computer storage medium, loaded onto the aforementioned electronic device via the computer storage medium, and run therein.

[0091] This invention provides an embodiment that can obtain the initial field of the inner simulation region at the first reporting time, and the boundary field of the inner simulation region for each of the multiple reporting times, including the first reporting time, within the corresponding forecast time range. Each reporting time corresponds to a forecast time range; wherein, among the multiple reporting times, the reporting times other than the first reporting time are earlier than the first reporting time. Then, boundary data fusion can be performed on the boundary fields of the inner simulation region within the corresponding forecast time range for each reporting time to obtain a fused boundary field, which includes the boundary field of the inner simulation region within the target forecast time range. Based on this, numerical simulation can be performed on the inner simulation region based on the initial field and the fused boundary field at the first reporting time to obtain the numerical simulation results of the inner simulation region within the target forecast time range. As can be seen, the embodiments of the present invention can realize the numerical simulation of the inner simulation region by using the boundary field of the inner simulation region within the corresponding forecast time range for each of the multiple reporting times and the initial field of the inner simulation region under the latest reporting time among the multiple reporting times. The earlier reporting time can ensure the satisfaction of business requirements, and the later reporting time can ensure the accuracy of the numerical simulation results. That is, the embodiments of the present invention can effectively improve the accuracy of the numerical simulation results of the inner simulation region within the target forecast time range while ensuring that business requirements are met, so that the obtained numerical simulation results have both high accuracy and timeliness.

[0092] Based on the description of the method and apparatus embodiments above, an exemplary embodiment of the present invention also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, which, when executed by the at least one processor, causes the electronic device to perform the method according to an embodiment of the present invention.

[0093] An exemplary embodiment of the present invention also provides a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to an embodiment of the present invention.

[0094] An exemplary embodiment of the present invention also provides a computer program product, including a computer program, wherein, when executed by a computer's processor, the computer program is used to cause the computer to perform a method according to an embodiment of the present invention.

[0095] refer to Figure 6 The present invention will now be described in the form of a structural block diagram of an electronic device 600 that can serve as a server or client of the present invention, which is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0096] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. The RAM 603 may also store various programs and data required for the operation of the electronic device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0097] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, output unit 607, storage unit 608, and communication unit 609. Input unit 606 can be any type of device capable of inputting information to electronic device 600. Input unit 606 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of electronic device. Output unit 607 can be any type of device capable of presenting information and may include, but is not limited to, a display, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 608 may include, but is not limited to, disks and optical discs. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0098] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above. For example, in some embodiments, the numerical mode operation method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 600 via ROM 602 and / or communication unit 609. In some embodiments, the computing unit 601 can be configured to perform the numerical mode operation method by any other suitable means (e.g., by means of firmware).

[0099] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0100] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0101] As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0102] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0103] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0104] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0105] Furthermore, it should be understood that the above-disclosed embodiments are merely preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, any equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for operating a numerical mode, characterized in that, The numerical model operation method is applied to the inner-layer simulation service equipment, and the method includes: The initial field of the inner simulation region at the first reporting time is obtained, and the boundary field of the inner simulation region at each of the multiple reporting times including the first reporting time is obtained within the corresponding forecast time range, with one reporting time corresponding to one forecast time range; wherein, the reporting times other than the first reporting time among the multiple reporting times are earlier than the first reporting time. Add the boundary field of the inner simulated region within the corresponding forecast time range of the first reporting time to the fused boundary field; For any reporting time other than the first reporting time among the multiple reporting times, the boundary field of the inner simulated region of the reporting time within the corresponding forecast time range of the inner simulated region is extracted from the boundary field of the inner simulated region of the reporting time within the corresponding extraction time range of the reporting time. This boundary field is then added to the fused boundary field to achieve boundary data fusion of the boundary fields of the inner simulated regions of each reporting time within the corresponding forecast time range, resulting in a fused boundary field. The fused boundary field includes the boundary field of the inner simulated region within the target forecast time range. The extraction time range corresponding to the reporting time is the time range between the end time of the forecast time range corresponding to the subsequent reporting time of the reporting time and the end time of the forecast time range corresponding to the reporting time of the reporting time. The subsequent reporting time refers to the first reporting time after the reporting time among the multiple reporting times, arranged in ascending order. Based on the initial field of the inner simulation region and the fused boundary field at the first reporting time, numerical simulation is performed on the inner simulation region to obtain the numerical simulation results of the inner simulation region within the target prediction time range.

2. The method according to claim 1, characterized in that, The plurality of reporting times include the first reporting time and the second reporting time, the second reporting time being earlier than the first reporting time, and the forecast time range corresponding to the second reporting time including the target forecast time range, and any one of the reporting times being the second forecast time; the extraction time range corresponding to the second forecast time is the time range between the end time of the forecast time range corresponding to the first reporting time and the end time of the target forecast time range.

3. The method according to claim 1 or 2, characterized in that, The initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region at each reporting time within the corresponding forecast time range are obtained from the outer simulation service equipment. Among them, the initial field of the inner simulation region at a given start time and the boundary field of the inner simulation region at a given start time within the corresponding forecast time range are determined based on the forecast results of the outer simulation region at the corresponding start time within the corresponding forecast time range.

4. A method for operating a numerical mode, characterized in that, The numerical model operation method is applied to an outer simulation service device, and the method includes: Obtain the outer simulation region forecast results for each of the multiple start times within the corresponding forecast time range, with one start time corresponding to one forecast time range; Based on the forecast results of the outer simulated region for each start time within the corresponding forecast time range, the boundary field of the inner simulated region for each start time within the corresponding forecast time range and the initial field of the inner simulated region for each start time are determined. The initial field of the inner simulation region at each reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time are sent to the inner simulation service device, so that the inner simulation service device can obtain the initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time, thereby performing numerical simulation on the inner simulation region. The plurality of reporting times include the first reporting time, and the reporting times other than the first reporting time are earlier than the first reporting time.

5. The method according to claim 4, characterized in that, The process of obtaining the outer simulation region forecast results for each of the multiple reporting times within the corresponding forecast time range includes: Obtain the initial field of the outer simulation region at each of the multiple reporting times; Based on the initial field of the outer simulation region at each of the aforementioned start times, numerical simulations are performed on the outer simulation region according to the forecast time range corresponding to each of the aforementioned start times, to obtain the forecast results of the outer simulation region at each of the aforementioned start times within the corresponding forecast time range.

6. A numerical mode operation device, characterized in that, The device operates on an inner-layer simulation service device, and the device includes: The first acquisition unit is used to acquire the initial field of the inner simulation region at the first reporting time, and to acquire the boundary field of the inner simulation region of each reporting time within the corresponding forecast time range among a plurality of reporting times including the first reporting time, wherein one reporting time corresponds to one forecast time range; wherein, among the plurality of reporting times, the reporting time other than the first reporting time is earlier than the first reporting time. The first processing unit is configured to add the inner simulated region boundary field of the first reporting time within the corresponding forecast time range to the fused boundary field; for any reporting time other than the first reporting time among the plurality of reporting times, extract the inner simulated region boundary field of the any reporting time within the corresponding extraction time range from the inner simulated region boundary field of the any reporting time within the corresponding forecast time range, and add the inner simulated region boundary field of the any reporting time within the corresponding extraction time range to the fused boundary field, thereby realizing the processing of each reporting time. Boundary data fusion is performed on the boundary field of the inner simulated region within the corresponding forecast time range to obtain a fused boundary field; wherein, the fused boundary field includes the boundary field of the inner simulated region within the target forecast time range, and the extraction time range corresponding to any first reporting time is: the time range between the end time of the forecast time range corresponding to the next first reporting time of any first reporting time and the end time of the forecast time range corresponding to any first reporting time, and the next first reporting time of any first reporting time refers to the first reporting time after any first reporting time in the order from earliest to latest among the multiple reporting times; The first processing unit is further configured to perform numerical simulation on the inner simulation region based on the initial field of the inner simulation region and the fused boundary field at the first reporting time, and obtain the numerical simulation results of the inner simulation region within the target prediction time range.

7. A numerical mode operation device, characterized in that, The device operates on an outer-layer simulation service device, and the device includes: The second acquisition unit is used to acquire the outer simulation area forecast results of each of the multiple start times within the corresponding forecast time range, with one start time corresponding to one forecast time range. The second processing unit is used to determine the boundary field of the inner simulation region and the initial field of the inner simulation region at each start time based on the outer simulation region forecast results within the corresponding forecast time range for each start time. The second processing unit is further configured to send the initial field of the inner simulation region at each reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time to the inner simulation service device, so that the inner simulation service device can obtain the initial field of the inner simulation region at the first reporting time and the boundary field of the inner simulation region within the corresponding forecast time range at each reporting time, thereby performing numerical simulation on the inner simulation region. The plurality of reporting times includes the first reporting time, and the reporting times other than the first reporting time among the plurality of reporting times are earlier than the first reporting time.

8. An electronic device, characterized in that, include: processor; as well as Stored program memory, The program includes instructions that, when executed by the processor, cause the processor to perform the method according to any one of claims 1-3; or, when executed by the processor, cause the processor to perform the method according to claim 4 or 5.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-3; or, the computer instructions are used to cause the computer to perform the method according to claim 4 or 5.

Images