A data processing method and device based on multi-resolution simulation object

Abstract

The present invention discloses a data processing method and device based on multi-resolution simulation objects, the method comprising: obtaining to-be-processed simulation task information and multi-resolution simulation object information; the multi-resolution simulation object information comprises a plurality of simulation object sets; the simulation object sets comprise a plurality of basic simulation object representations; analyzing and processing the to-be-processed simulation task information to obtain target simulation requirement information; the target simulation requirement information comprises M target simulation requirement representations; the target simulation requirement representations comprise a first requirement vector and a second requirement vector; selecting and processing the target simulation requirement information using the multi-resolution simulation object information to obtain target simulation object information; the target simulation object information comprises M target simulation object representations.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a data processing method and device based on multi-resolution simulation objects. Background Art

[0002] In the simulation of complex systems, different simulation tasks have varying requirements for data accuracy and processing speed. High-resolution data can provide more accurate simulation results, but at the cost of high computational cost and slow processing speed. Low-resolution data has a fast computational speed but lower accuracy. Therefore, a data processing method and device based on multi-resolution simulation objects are provided. This method dynamically selects and calls simulation objects of different resolutions based on the requirements of the simulation task. While ensuring simulation accuracy, this method improves data processing efficiency, reduces computational cost, and thus enhances adaptability to a variety of simulation tasks and scenarios. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a data processing method and device based on multi-resolution simulation objects, which is conducive to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0004] In order to solve the above technical problems, a first aspect of an embodiment of the present invention discloses a data processing method based on a multi-resolution simulation object, the method comprising:

[0005] Acquire information of simulation tasks to be processed and multi-resolution simulation object information; the multi-resolution simulation object information includes a plurality of simulation object sets; the simulation object sets include a plurality of basic simulation object representations;

[0006] Analyze and process the simulation task information to be processed to obtain target simulation requirement information; the target simulation requirement information includes M target simulation requirement representations; the target simulation requirement representations include a first requirement vector and a second requirement vector;

[0007] The target simulation requirement information is selectively processed using the multi-resolution simulation object information to obtain target simulation object information; the target simulation object information includes M target simulation object representations.

[0008] A second aspect of an embodiment of the present invention discloses a data processing device based on a multi-resolution simulation object, the device comprising:

[0009] An acquisition module, configured to acquire information of simulation tasks to be processed and multi-resolution simulation object information; the multi-resolution simulation object information includes a plurality of simulation object sets; the simulation object sets include a plurality of basic simulation object representations;

[0010] A first processing module is configured to analyze and process the simulation task information to be processed to obtain target simulation requirement information; the target simulation requirement information includes M target simulation requirement representations; the target simulation requirement representations include a first requirement vector and a second requirement vector;

[0011] The second processing module is used to select and process the target simulation requirement information using the multi-resolution simulation object information to obtain target simulation object information; the target simulation object information includes M target simulation object representations.

[0012] A third aspect of the present invention discloses another data processing device based on a multi-resolution simulation object, the device comprising:

[0013] a memory storing executable program code;

[0014] a processor coupled to a memory;

[0015] The processor calls the executable program code stored in the memory to execute part or all of the steps in the data processing method based on the multi-resolution simulation object disclosed in the first aspect of the embodiment of the present invention.

[0016] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the data processing method based on multi-resolution simulation objects disclosed in the first aspect of an embodiment of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 1 is a schematic diagram of a scenario of a data processing system based on a multi-resolution simulation object provided by an embodiment of the present invention;

[0019] Figure 2 This is a flow chart of a data processing method based on a multi-resolution simulation object disclosed in an embodiment of the present invention;

[0020] Figure 3 It is a structural diagram of a data processing device based on a multi-resolution simulation object disclosed in an embodiment of the present invention;

[0021] Figure 4It is a structural diagram of another data processing device based on multi-resolution simulation objects disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or device.

[0024] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0025] In this application, the word "exemplary" is used to mean "serving as an example, illustration, or illustration." Any embodiment described in this application as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is given to enable any person skilled in the art to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that one of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in this application.

[0026] It should be noted that since the method of the embodiment of the present application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, time is actually time information. It can be understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, the corresponding data exist for the computer device to process. The details will not be repeated here.

[0027] It should be noted that the artificial intelligence related technologies that may be involved in this application are briefly described. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that machines have the functions of perception, reasoning and decision-making.

[0028] Artificial intelligence (AI) technology is a comprehensive discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0029] Computer vision (CV) is the science of making machines "see." Specifically, it refers to machine vision, where cameras and computers replace the human eye in identifying and measuring objects, performing further image processing to create images more suitable for human observation or transmission to instruments. As a scientific discipline, computer vision studies related theories and technologies, attempting to build artificial intelligence systems capable of extracting information from images or multidimensional data. Computer vision technologies typically include image processing, image recognition, image semantic understanding, image retrieval, optical character recognition (OCR), video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, and common biometric recognition technologies such as facial recognition and fingerprint recognition.

[0030] Unimodal information is data consisting of only one type, such as text, images, audio, video, or electromagnetic signals. Multimodal information is data that includes at least two types of unimodal information. Furthermore, multimodal information is suitable for complex tasks that require integrating multiple information sources, such as sentiment analysis, robot interaction, and autonomous driving. By integrating information from multiple modalities, higher performance and accuracy can often be achieved on the task.

[0031] A large model refers to an artificial neural network model with a very large number of parameters. In the field of artificial intelligence, a large model generally refers to a model with hundreds of millions to trillions of parameters. Models usually need to be trained on large-scale data sets and require a large amount of computing resources to be optimized and adjusted. Large models are generally used to solve complex tasks such as natural language processing, computer vision, and speech recognition. Generative AI is an AI that can create new content and ideas, including conversations, stories, images, videos, and music. In the embodiment of the present application, the large model can be ChatGPT, BERT, XLNet, Zhipu model, Claude, Moonshot AI model, ChatGLM model, Tongwen Qianyi model, MiniMax model, Spark model, Llama model, 360GPT model, Qwen model, Baichuan model, Skylark model, vivoLM model, Wenxin Yiyan and other large-scale language models, which are not limited in the embodiment of the present application.

[0032] The embodiments of the present application provide a data processing method, apparatus, computer device, and computer-readable storage medium based on a multi-resolution simulation object, which are described in detail below.

[0033] See also Figure 1 , Figure 1 This is a schematic diagram of a scenario of a data processing system based on a multi-resolution simulation object provided by an embodiment of the present application. The data processing system based on a multi-resolution simulation object may include a computer device 100, in which a data processing device based on a multi-resolution simulation object is integrated, such as Figure 1 Computer equipment in.

[0034] In the embodiment of the present application, the computer device 100 is mainly used to obtain information of simulation tasks to be processed and multi-resolution simulation object information; the multi-resolution simulation object information includes a plurality of simulation object sets; the simulation object sets include a plurality of basic simulation object representations;

[0035] Analyze and process the simulation task information to be processed to obtain target simulation requirement information; the target simulation requirement information includes M target simulation requirement representations; the target simulation requirement representations include a first requirement vector and a second requirement vector;

[0036] The target simulation requirement information is selectively processed using the multi-resolution simulation object information to obtain target simulation object information; the target simulation object information includes M target simulation object representations.

[0037] It can dynamically select and call simulation objects of different resolutions according to the needs of the simulation task, improve data processing efficiency and reduce computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0038] In the embodiments of the present application, the computer device 100 may be an independent server, or a server network or server cluster composed of servers. For example, the computer device 100 described in the embodiments of the present application includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. A cloud server is composed of a large number of computers or network servers based on cloud computing.

[0039] It is understood that the computer device 100 used in the embodiments of the present application can be a device that includes both receiving and transmitting hardware, that is, a device that has receiving and transmitting hardware capable of performing two-way communication over a two-way communication link. Such a device may include: a cellular or other communication device that has a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. The specific computer device 100 can be a desktop terminal or a mobile terminal. The computer device 100 can also be a mobile phone, a tablet computer, a laptop computer, etc.

[0040] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is only one application scenario of the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or fewer computer devices as shown in Figure 1 Only one computer device is shown in the figure. It can be understood that the data processing system based on multi-resolution simulation objects can also include one or more other services, which are not specifically limited here.

[0041] In addition, if Figure 1 As shown, the data processing system based on multi-resolution simulation objects may further include a memory 200 for storing data, such as image data, position information, and the like.

[0042] It should be noted that Figure 1The scenario diagram of the data processing system based on multi-resolution simulation objects shown is merely an example. The data processing system based on multi-resolution simulation objects and the scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art will appreciate that, with the evolution of the data processing system based on multi-resolution simulation objects and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.

[0043] The present invention discloses a data processing method and device based on multi-resolution simulation objects. These methods facilitate the dynamic selection and invocation of simulation objects of different resolutions according to the requirements of the simulation task. While ensuring simulation accuracy, they improve data processing efficiency, reduce computational costs, and thus enhance adaptability to various simulation tasks and scenarios. These are described in detail below.

[0044] Example 1

[0045] See also Figure 2 , Figure 2 This is a flow chart of a data processing method based on a multi-resolution simulation object disclosed in an embodiment of the present invention. Figure 2 The data processing method based on multi-resolution simulation objects described above is applied to a management system, such as a local server or cloud server for management, etc., which is not limited in the embodiment of the present invention. Figure 2 As shown, the data processing method based on the multi-resolution simulation object may include the following operations:

[0046] 101. Obtain information about pending simulation tasks and multi-resolution simulation objects.

[0047] In an embodiment of the present invention, the multi-resolution simulation object information includes a plurality of simulation object sets; and the simulation object sets include a plurality of basic simulation object representations.

[0048] 102. Analyze and process the simulation task information to be processed to obtain target simulation requirement information.

[0049] In an embodiment of the present invention, the target simulation requirement information includes M target simulation requirement representations; the target simulation requirement representations include a first requirement vector and a second requirement vector.

[0050] 103. Utilize the multi-resolution simulation object information to select and process the target simulation requirement information to obtain the target simulation object information.

[0051] In the embodiment of the present invention, the target simulation object information includes M target simulation object representations.

[0052] It should be noted that the above-mentioned basic simulation objects represent simulation models corresponding to the simulation objects, such as simulation models of vehicles, simulation models of spacecraft, etc., which are not limited in the embodiments of the present invention.

[0053] It should be noted that the above-mentioned simulation object set represents a collection of simulation models at the same resolution level, which is not limited in the embodiment of the present invention.

[0054] It should be noted that the above M is a positive integer greater than or equal to 1, and is not limited in the embodiment of the present invention.

[0055] It should be noted that the above-mentioned target simulation object is used to schedule the corresponding simulation model for simulation at different times to achieve effective scheduling of simulation models with different resolutions and improve the efficiency of model simulation, which is not limited in the embodiment of the present invention.

[0056] It can be seen that implementing the data processing method based on multi-resolution simulation objects described in the embodiment of the present invention is beneficial to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0057] In an optional embodiment, the above analysis and processing of the pending simulation task information to obtain target simulation requirement information includes:

[0058] Decomposing the simulation task information to be processed to obtain timing simulation task information; the timing simulation task information includes M simulation tasks arranged in simulation execution timing;

[0059] Based on the timing simulation task information, the target simulation requirement information is determined.

[0060] It should be noted that the above-mentioned determination of the target simulation requirement information based on the timing simulation task information is to determine the simulation object model of the corresponding resolution according to the timing sequence of the simulation, so as to achieve efficient and accurate scheduling of the simulation object model in an orderly manner according to the actual requirements of the simulation. The embodiments of the present invention do not limit this.

[0061] In this optional embodiment, as an optional implementation manner, the above-mentioned decomposition processing of the simulation task information to be processed to obtain the timing simulation task information includes:

[0062] Normalizing the simulation task information to be processed to obtain normalized simulation task information;

[0063] Perform multimodal decomposition on the normalized simulation task information to obtain modal decomposition task information;

[0064] Perform noise reduction and feature extraction on the modal decomposition task information to obtain the task modal feature information;

[0065] The task modal feature information is processed into a time sequence task reconstruction to obtain the time sequence simulation task information.

[0066] It should be noted that the above-mentioned time series task reconstruction processing of the task modal feature information is to reconstruct the modal components after noise reduction and feature extraction into a time series simulation task to be simulated, so as to match the subsequent simulation object representation model, which is not limited in the embodiment of the present invention.

[0067] It should be noted that the above-mentioned noise reduction and feature extraction processing of the modal decomposition task information utilizes singular spectrum analysis to analyze and process each modal component to further remove noise and extract task feature information, which is not limited in the embodiment of the present invention.

[0068] It should be noted that the above-mentioned multimodal decomposition of the normalized simulation task information utilizes variational modal decomposition to decompose the normalized normalized simulation task information into multiple modal components so as to match simulation models of different resolutions according to the simulation modal requirements, which is not limited in the embodiments of the present invention.

[0069] It should be noted that the above normalization of the simulation task information to be processed is normalization of the simulation task data, scaling the data to the range of [0, 1] to eliminate the dimensional differences between different variables, which is not limited in the embodiment of the present invention.

[0070] It can be seen that implementing the data processing method based on multi-resolution simulation objects described in the embodiment of the present invention is beneficial to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0071] In another optional embodiment, determining target simulation requirement information based on the timing simulation task information includes:

[0072] Based on the timing simulation task information, initial simulation requirement information is determined; the initial simulation requirement information includes M initial simulation requirement values;

[0073] Based on the initial simulation requirement information, target simulation requirement information is determined.

[0074] It should be noted that the above-mentioned M initial simulation demand values ​​are quantitative calculation processing of the simulation demand to improve the accuracy and efficiency of scheduling simulation object models with different resolutions, and the embodiment of the present invention does not limit this.

[0075] It can be seen that implementing the data processing method based on multi-resolution simulation objects described in the embodiment of the present invention is beneficial to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0076] In yet another optional embodiment, determining initial simulation requirement information based on the timing simulation task information includes:

[0077] For any simulation task in the timing simulation task information, evaluating and analyzing the simulation accuracy corresponding to the simulation task to obtain a first demand evaluation value corresponding to the simulation task;

[0078] Evaluate and analyze the simulation time corresponding to the simulation task to obtain a second demand evaluation value corresponding to the simulation task;

[0079] Evaluate and analyze the simulation complexity corresponding to the simulation task to obtain a third requirement evaluation value corresponding to the simulation task;

[0080] Calculating the first demand evaluation value, the second demand evaluation value, and the third demand evaluation value using the demand calculation model to obtain an initial simulation demand value corresponding to the simulation task;

[0081] The demand calculation model is:

[0082] Initial simulation demand value=first coefficient·first demand evaluation value+second coefficient·second demand evaluation value+third coefficient·third demand evaluation value.

[0083] It should be noted that the above-mentioned evaluation and analysis of the simulation accuracy corresponding to the simulation task and the evaluation and analysis of the simulation time corresponding to the simulation task are obtained by querying the simulation accuracy comparison table and the simulation time comparison table, respectively, and the embodiment of the present invention does not limit this. Further, the above-mentioned simulation accuracy comparison table and simulation time comparison table can be respectively:

[0084]

[0085]

[0086] Simulation time Second Need Assessment Value Within 1 minute 1 (1 minute, 5 minutes] 0.8 (5 minutes, 10 minutes] 0.5 More than 10 minutes 0.3

[0087] It should be noted that the sum of the first coefficient, the second coefficient, and the third coefficient is 1, and its value is a value between 0 and 1. Furthermore, the third coefficient is greater than or equal to the first coefficient, and the first coefficient is greater than or equal to the second coefficient, which is not limited in the embodiment of the present invention. Furthermore, the above-mentioned ordering of the third coefficient, the first coefficient, and the second coefficient is mainly based on the consideration that simulation complexity is the main influencing factor of the multi-resolution simulation model, and secondly, considering that simulation accuracy is displayed on the front-end display screen, which is an important reference basis for users to implement human-in-the-loop simulation (i.e., by establishing a resolution controller to achieve change control of the simulation model structure), so its weight coefficient is ranked second, and the simulation time is relatively weakened, which is not limited in the embodiment of the present invention.

[0088] It can be seen that implementing the data processing method based on multi-resolution simulation objects described in the embodiment of the present invention is beneficial to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0089] In yet another optional embodiment, evaluating and analyzing the simulation complexity corresponding to the simulation task to obtain a third requirement evaluation value corresponding to the simulation task includes:

[0090] Calculate the ratio of the memory required for the simulation task to the basic memory to obtain the memory ratio corresponding to the simulation task;

[0091] Calculate the ratio of GPU required for the simulation task to the basic GPU, and obtain the GPU ratio corresponding to the simulation task;

[0092] Determine whether the memory ratio and the GPU ratio are both less than or equal to a first ratio threshold, and obtain a ratio determination result;

[0093] When the proportion judgment result is yes, the first preset evaluation value is determined as the third demand evaluation value corresponding to the simulation task;

[0094] When the proportion judgment result is no, the second preset evaluation value is determined as the third demand evaluation value corresponding to the simulation task.

[0095] It should be noted that the above-mentioned basic memory and basic GPU are the currently available hardware resources of the server. Furthermore, the memory and GPU required for the calculated simulation task are estimated based on the number of parameters of the simulation model and the size of the input data, so as to adaptively change the system resolution and the corresponding system structure according to the simulation environment. For example, a high-resolution model can provide detailed detailed information, but requires more computing resources, while a low-resolution model is faster. This is not limited in the embodiments of the present invention.

[0096] It should be noted that the first resource usage threshold is 0.8, which is not limited in the present embodiment. Furthermore, the first resource usage threshold is set to account for the fact that if a single model exceeds 0.8 hardware resource usage, the simulation speed may be significantly reduced, hindering the high-speed advancement of the overall simulation task. Therefore, a certain resource margin is required, which is not limited in the present embodiment.

[0097] It should be noted that the first preset evaluation value and the second preset evaluation value are 0.8 and 0.4 respectively, which are not limited in this embodiment of the present invention.

[0098] It can be seen that implementing the data processing method based on multi-resolution simulation objects described in the embodiment of the present invention is beneficial to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0099] In an optional embodiment, the above-mentioned determination of target simulation requirement information based on the initial simulation requirement information includes:

[0100] For any initial simulation requirement value in the initial simulation requirement information, convert the initial simulation requirement value to obtain an initial resolution level corresponding to the initial simulation requirement value;

[0101] Determine whether the distribution order of the initial simulation demand value is the first order, and obtain a order determination result;

[0102] When the sorting judgment result is yes, the initial resolution level is determined to be the target resolution level corresponding to the initial simulation requirement value;

[0103] When the sorting judgment result is no, it is determined that the level difference between the initial resolution level corresponding to the initial simulation requirement value and the target resolution level corresponding to an initial simulation requirement value that is ranked before the initial simulation requirement value is within 1 level difference unit, and a level judgment result is obtained;

[0104] When the level judgment result is yes, the initial resolution level is determined to be the target resolution level corresponding to the initial simulation requirement value;

[0105] When the level judgment result is no, the initial resolution level corresponding to the initial simulation requirement value is adjusted to a level difference unit different from the target resolution level corresponding to the initial simulation requirement value before the initial simulation requirement value, to obtain the updated initial resolution level corresponding to the initial simulation requirement value;

[0106] Determining the updated initial resolution level corresponding to the initial simulation requirement value as the target resolution level corresponding to the initial simulation requirement value;

[0107] Perform vector conversion on the target resolution level to obtain the target simulation requirement representation corresponding to the initial simulation requirement value.

[0108] It should be noted that the above-mentioned conversion processing of the initial simulation demand value to obtain the initial resolution level corresponding to the initial simulation demand value is to first perform a unified interval conversion on the initial simulation demand value to weaken the excessive calculation amount caused by the small-scale change of the initial simulation demand value, and then adjust the demand level for the first time according to the transformation relationship between the two adjacent demand values, and finally perform standard form quantization processing of the demand level according to the standardized vector conversion relationship to improve the scheduling efficiency and accuracy of subsequent simulation object models with different resolutions. The embodiments of the present invention are not limited to this.

[0109] It should be noted that the above conversion process of the initial simulation demand value to obtain the initial resolution level corresponding to the initial simulation demand value is performed according to the demand value and resolution level conversion table:

[0110] Initial simulation demand value Resolution level (0.8，1] First level (0.6，0.8] Second level (0.3，0.6] Third level Less than or equal to 0.3 Fourth Level

[0111] It should be noted that whether the distribution order of the initial simulation demand value is the first order represents whether the simulation timing corresponding to the initial simulation demand value is the first, which is not limited in the embodiment of the present invention.

[0112] It should be noted that the above judgment that the initial resolution level corresponding to the initial simulation requirement value and the target resolution level corresponding to an initial simulation requirement value whose distribution ranking is before the initial simulation requirement value are within 1 level difference unit is based on the consideration that the parameters of the two adjacent simulation object models need to be migrated to the next simulation object model after the simulation of the previous simulation object model is completed. If the difference between the two resolution levels is too large, the simulation data may not be able to be migrated to the simulation object of the next time series, resulting in a problem of simulation data discontinuity. Therefore, by adjusting and optimizing the resolution of the simulation object of the next time series through the resolution level difference between adjacent simulation objects, the efficiency of the entire simulation process can be improved, and the embodiments of the present invention do not limit this.

[0113] It should be noted that the above-mentioned initial resolution level corresponding to the initial simulation requirement value is adjusted to a target resolution level corresponding to an initial simulation requirement value before the initial simulation requirement value, which is 1 level difference unit different from the target resolution level corresponding to the initial simulation requirement value before the initial simulation requirement value. The updated initial resolution level corresponding to the initial simulation requirement value is to bring the resolution level of the simulation object corresponding to the latter time series closer to the previous resolution level. For example, if the previous resolution level is the fourth level and the current one is the first level, the difference between the two is 3 levels, and the current one needs to be adjusted to the third level. This is not limited in the embodiments of the present invention.

[0114] It should be noted that the above-mentioned vector conversion of the target resolution level is to convert each resolution level into a corresponding vector (i.e., a first requirement vector, which can be set by the user or directly converted from a large model, and is not limited in the embodiment of the present invention), such as converting the first level to (0,0,1,1,1), and then splicing the converted resolution level with the basic vector corresponding to the simulation object (i.e., a second requirement vector, which can be set by the user or directly converted from a large model, and is not limited in the embodiment of the present invention), thereby forming a corresponding target simulation requirement representation, and is not limited in the embodiment of the present invention.

[0115] It can be seen that implementing the data processing method based on multi-resolution simulation objects described in the embodiment of the present invention is beneficial to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0116] In another optional embodiment, the target simulation requirement information is selectively processed using the multi-resolution simulation object information to obtain the target simulation object information, including:

[0117] For any target simulation requirement representation in the target simulation requirement information, a first requirement vector in the target simulation requirement representation is calculated and processed with a simulation object set in the multi-resolution simulation object information using a requirement matching model to obtain a plurality of object set matching values;

[0118] Among them, the demand matching model is:

[0119]

[0120] Where PPZ represents the object set matching value; X represents the first requirement vector in the target simulation requirement representation; Y represents the simulation object set;

[0121] Determine the simulation object set corresponding to the maximum object set matching value as the target simulation object set;

[0122] Using the demand matching model, a basic simulation object representation in the target simulation object set and a second demand vector in the target simulation demand representation are calculated and processed to obtain a plurality of object representation matching values;

[0123] The basic simulation object representation corresponding to the maximum object representation matching value is determined as the target simulation object representation corresponding to the target simulation requirement representation.

[0124] It should be noted that the above-mentioned basic simulation object representations are stored in different simulation object sets according to the resolution level. Therefore, it is necessary to first use the first demand vector and the vector corresponding to the simulation object set (which can be set by the user or directly converted from the large model, and the embodiment of the present invention is not limited thereto) to perform the first matching positioning, so as to first accurately locate the simulation object set where the simulation object representation model to be matched is located, so as to reduce the amount of data for matching calculation and improve the efficiency and accuracy of the simulation object representation model matching search. Furthermore, after determining the simulation object set where the simulation object representation model is located, the vector representation corresponding to the simulation object itself (which can be set by the user or directly converted from the large model, and the embodiment of the present invention is not limited thereto), that is, the second demand vector, is used for further model matching, so as to efficiently and accurately match the simulation object representation model required for the actual simulation process, that is, the target simulation object representation, and the embodiment of the present invention is not limited thereto.

[0125] It can be seen that implementing the data processing method based on multi-resolution simulation objects described in the embodiment of the present invention is beneficial to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0126] Example 2

[0127] See also Figure 3 , Figure 3 This is a structural diagram of a data processing device based on a multi-resolution simulation object disclosed in an embodiment of the present invention. Figure 3 The described device can be applied to a management system, such as a local server or a cloud server for management, etc., and the embodiment of the present invention does not limit this. Figure 3 As shown, the device may include:

[0128] An acquisition module 201 is configured to acquire information of a simulation task to be processed and information of a multi-resolution simulation object; the multi-resolution simulation object information includes a plurality of simulation object sets; and the simulation object sets include a plurality of basic simulation object representations.

[0129] The first processing module 202 is configured to analyze and process the simulation task information to be processed to obtain target simulation requirement information; the target simulation requirement information includes M target simulation requirement representations; the target simulation requirement representations include a first requirement vector and a second requirement vector;

[0130] The second processing module 203 is configured to select and process the target simulation requirement information using the multi-resolution simulation object information to obtain target simulation object information; the target simulation object information includes M target simulation object representations.

[0131] It can be seen that implementation Figure 3 The described data processing device based on multi-resolution simulation objects is conducive to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0132] In another optional embodiment, Figure 3 As shown, the simulation task information to be processed is analyzed and processed to obtain the target simulation requirement information, including:

[0133] Decomposing the simulation task information to be processed to obtain timing simulation task information; the timing simulation task information includes M simulation tasks arranged in simulation execution timing;

[0134] Based on the timing simulation task information, the target simulation requirement information is determined.

[0135] It can be seen that implementation Figure 3 The described data processing device based on multi-resolution simulation objects is conducive to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0136] In another optional embodiment, Figure 3 As shown, based on the timing simulation task information, the target simulation requirement information is determined, including:

[0137] Based on the timing simulation task information, initial simulation requirement information is determined; the initial simulation requirement information includes M initial simulation requirement values;

[0138] Based on the initial simulation requirement information, target simulation requirement information is determined.

[0139] It can be seen that implementation Figure 3 The described data processing device based on multi-resolution simulation objects is conducive to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0140] In another optional embodiment, Figure 3 As shown, based on the timing simulation task information, the initial simulation requirement information is determined, including:

[0141] For any simulation task in the timing simulation task information, evaluating and analyzing the simulation accuracy corresponding to the simulation task to obtain a first demand evaluation value corresponding to the simulation task;

[0142] Evaluate and analyze the simulation time corresponding to the simulation task to obtain a second demand evaluation value corresponding to the simulation task;

[0143] Evaluate and analyze the simulation complexity corresponding to the simulation task to obtain a third requirement evaluation value corresponding to the simulation task;

[0144] Calculating the first demand evaluation value, the second demand evaluation value, and the third demand evaluation value using the demand calculation model to obtain an initial simulation demand value corresponding to the simulation task;

[0145] The demand calculation model is:

[0146] Initial simulation demand value=first coefficient·first demand evaluation value+second coefficient·second demand evaluation value+third coefficient·third demand evaluation value.

[0147] It can be seen that implementation Figure 3 The described data processing device based on multi-resolution simulation objects is conducive to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0148] In another optional embodiment, Figure 3 As shown, the simulation complexity corresponding to the simulation task is evaluated and analyzed to obtain the third requirement evaluation value corresponding to the simulation task, including:

[0149] Calculate the ratio of the memory required for the simulation task to the basic memory to obtain the memory ratio corresponding to the simulation task;

[0150] Calculate the ratio of GPU required for the simulation task to the basic GPU, and obtain the GPU ratio corresponding to the simulation task;

[0151] Determine whether the memory ratio and the GPU ratio are both less than or equal to a first ratio threshold, and obtain a ratio determination result;

[0152] When the proportion judgment result is yes, the first preset evaluation value is determined as the third demand evaluation value corresponding to the simulation task;

[0153] When the proportion judgment result is no, the second preset evaluation value is determined as the third demand evaluation value corresponding to the simulation task.

[0154] It can be seen that implementation Figure 3The described data processing device based on multi-resolution simulation objects is conducive to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0155] In another optional embodiment, Figure 3 As shown, based on the initial simulation requirement information, target simulation requirement information is determined, including:

[0156] For any initial simulation requirement value in the initial simulation requirement information, convert the initial simulation requirement value to obtain an initial resolution level corresponding to the initial simulation requirement value;

[0157] Determine whether the distribution order of the initial simulation demand value is the first order, and obtain a order determination result;

[0158] When the sorting judgment result is yes, the initial resolution level is determined to be the target resolution level corresponding to the initial simulation requirement value;

[0159] When the sorting judgment result is no, it is determined that the level difference between the initial resolution level corresponding to the initial simulation requirement value and the target resolution level corresponding to an initial simulation requirement value that is ranked before the initial simulation requirement value is within 1 level difference unit, and a level judgment result is obtained;

[0160] When the level judgment result is yes, the initial resolution level is determined to be the target resolution level corresponding to the initial simulation requirement value;

[0161] When the level judgment result is no, the initial resolution level corresponding to the initial simulation requirement value is adjusted to a level difference unit different from the target resolution level corresponding to the initial simulation requirement value before the initial simulation requirement value, to obtain the updated initial resolution level corresponding to the initial simulation requirement value;

[0162] Determining the updated initial resolution level corresponding to the initial simulation requirement value as the target resolution level corresponding to the initial simulation requirement value;

[0163] Perform vector conversion on the target resolution level to obtain the target simulation requirement representation corresponding to the initial simulation requirement value.

[0164] It can be seen that implementation Figure 3 The described data processing device based on multi-resolution simulation objects is conducive to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0165] In another optional embodiment, Figure 3 As shown, the target simulation requirement information is selected and processed using the multi-resolution simulation object information to obtain the target simulation object information, including:

[0166] For any target simulation requirement representation in the target simulation requirement information, a first requirement vector in the target simulation requirement representation is calculated and processed with a simulation object set in the multi-resolution simulation object information using a requirement matching model to obtain a plurality of object set matching values;

[0167] Among them, the demand matching model is:

[0168]

[0169] Where PPZ represents the object set matching value; X represents the first requirement vector in the target simulation requirement representation; Y represents the simulation object set;

[0170] Determine the simulation object set corresponding to the maximum object set matching value as the target simulation object set;

[0171] Using the demand matching model, a basic simulation object representation in the target simulation object set and a second demand vector in the target simulation demand representation are calculated and processed to obtain a plurality of object representation matching values;

[0172] The basic simulation object representation corresponding to the maximum object representation matching value is determined as the target simulation object representation corresponding to the target simulation requirement representation.

[0173] It can be seen that implementation Figure 3 The described data processing device based on multi-resolution simulation objects is conducive to dynamically selecting and calling simulation objects of different resolutions according to the requirements of the simulation task, improving data processing efficiency and reducing computing costs while ensuring simulation accuracy, thereby improving the adaptability to various simulation tasks and scenarios.

[0174] Example 3

[0175] See also Figure 4 , Figure 4 This is a structural diagram of another data processing device based on a multi-resolution simulation object disclosed in an embodiment of the present invention. Figure 4 The described device can be applied to a management system, such as a local server or a cloud server for management, etc., and the embodiment of the present invention does not limit this. Figure 4 As shown, the device may include:

[0176] A memory 301 storing executable program code;

[0177] a processor 302 coupled to the memory 301;

[0178] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the data processing method based on the multi-resolution simulation object described in the first embodiment.

[0179] Example 4

[0180] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the data processing method based on multi-resolution simulation objects described in the first embodiment.

[0181] Example 5

[0182] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the data processing method based on multi-resolution simulation objects described in embodiment 1.

[0183] The device embodiments described above are merely illustrative. Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0184] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the portion that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0185] Finally, it should be noted that the data processing method and device based on multi-resolution simulation objects disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A data processing method based on a multi-resolution simulation object, characterized in that: The method comprises: Acquire information of a simulation task to be processed and information of a multi-resolution simulation object; the multi-resolution simulation object information includes a plurality of simulation object sets; the simulation object sets include a plurality of basic simulation object representations; the simulation object sets represent a collection of simulation models at the same resolution level; the basic simulation object representations represent simulation models corresponding to the simulation objects; Analyze and process the simulation task information to be processed to obtain target simulation requirement information; the target simulation requirement information includes M target simulation requirement representations; the target simulation requirement representations include a first requirement vector and a second requirement vector; The target simulation requirement information is selected and processed using the multi-resolution simulation object information to obtain target simulation object information; the target simulation object information includes M target simulation object representations; the target simulation object representations are used to schedule corresponding simulation models for simulation at different times; The step of analyzing and processing the pending simulation task information to obtain target simulation requirement information includes: Decomposing the to-be-processed simulation task information to obtain time-series simulation task information; the time-series simulation task information includes M simulation tasks arranged in simulation execution time sequence; Determining target simulation requirement information based on the timing simulation task information; The step of determining target simulation requirement information based on the timing simulation task information includes: Determining initial simulation requirement information based on the timing simulation task information; the initial simulation requirement information includes M initial simulation requirement values; Determining target simulation requirement information based on the initial simulation requirement information; The step of determining target simulation requirement information based on the initial simulation requirement information includes: For any of the initial simulation requirement values ​​in the initial simulation requirement information, converting the initial simulation requirement value to obtain an initial resolution level corresponding to the initial simulation requirement value; Determine whether the distribution order of the initial simulation demand value is the first order, and obtain a order determination result; whether the distribution order of the initial simulation demand value is the first order indicates whether the simulation time sequence corresponding to the initial simulation demand value is the first; When the sorting judgment result is yes, the initial resolution level is determined as the target resolution level corresponding to the initial simulation requirement value; When the ranking judgment result is no, it is determined that the level difference between the initial resolution level corresponding to the initial simulation requirement value and the target resolution level corresponding to an initial simulation requirement value whose distribution ranking is before the initial simulation requirement value is within 1 level difference unit, and a level judgment result is obtained; When the level judgment result is yes, the initial resolution level is determined as the target resolution level corresponding to the initial simulation requirement value; When the level judgment result is no, adjusting the initial resolution level corresponding to the initial simulation requirement value to a level difference unit different from the target resolution level corresponding to the initial simulation requirement value before the initial simulation requirement value, to obtain an updated initial resolution level corresponding to the initial simulation requirement value; Determining the updated initial resolution level corresponding to the initial simulation requirement value as the target resolution level corresponding to the initial simulation requirement value; Vector conversion is performed on the target resolution level to obtain a target simulation requirement representation corresponding to the initial simulation requirement value.

2. The data processing method based on multi-resolution simulation object according to claim 1, characterized in that: Determining initial simulation requirement information based on the timing simulation task information includes: For any simulation task in the timing simulation task information, evaluating and analyzing the simulation accuracy corresponding to the simulation task to obtain a first demand evaluation value corresponding to the simulation task; Evaluate and analyze the simulation time corresponding to the simulation task to obtain a second demand evaluation value corresponding to the simulation task; Evaluate and analyze the simulation complexity corresponding to the simulation task to obtain a third requirement evaluation value corresponding to the simulation task; Calculating the first demand evaluation value, the second demand evaluation value, and the third demand evaluation value using a demand calculation model to obtain the initial simulation demand value corresponding to the simulation task; The demand calculation model is: Initial simulation demand value=first coefficient·first demand evaluation value+second coefficient·second demand evaluation value+third coefficient·third demand evaluation value.

3. The data processing method based on multi-resolution simulation object according to claim 2, characterized in that: The evaluating and analyzing the simulation complexity corresponding to the simulation task to obtain a third requirement evaluation value corresponding to the simulation task includes: Calculate the ratio of the memory required for the simulation task to the basic memory to obtain the memory ratio corresponding to the simulation task; Calculate the ratio of GPU required for the simulation task to the basic GPU, and obtain the GPU ratio corresponding to the simulation task; Determine whether the memory ratio and the GPU ratio are both less than or equal to a first ratio threshold, and obtain a ratio determination result; When the proportion judgment result is yes, the first preset evaluation value is determined as the third demand evaluation value corresponding to the simulation task; When the proportion judgment result is no, the second preset evaluation value is determined as the third demand evaluation value corresponding to the simulation task.

4. The data processing method based on multi-resolution simulation objects according to claim 1, characterized in that: The step of selecting and processing the target simulation requirement information using the multi-resolution simulation object information to obtain the target simulation object information includes: For any target simulation requirement representation in the target simulation requirement information, using a requirement matching model to perform calculation processing on a first requirement vector in the target simulation requirement representation and a simulation object set in the multi-resolution simulation object information to obtain a plurality of object set matching values; Wherein, the demand matching model is: Wherein, PPZ represents the object set matching value; X represents the first requirement vector in the target simulation requirement representation; Y represents the simulation object set; Determine the simulation object set corresponding to the largest object set matching value as the target simulation object set; Using a demand matching model, calculating and processing the basic simulation object representation in the target simulation object set and the second demand vector in the target simulation demand representation to obtain a plurality of object representation matching values; The basic simulation object representation corresponding to the largest object representation matching value is determined as the target simulation object representation corresponding to the target simulation requirement representation.

5. A data processing device based on a multi-resolution simulation object, characterized in that: The device comprises: An acquisition module is configured to acquire information about simulation tasks to be processed and information about multi-resolution simulation objects; the multi-resolution simulation object information includes a plurality of simulation object sets; the simulation object sets include a plurality of basic simulation object representations; the simulation object sets represent a collection of simulation models at the same resolution level; the basic simulation object representations represent simulation models corresponding to the simulation objects; A first processing module is configured to analyze and process the simulation task information to be processed to obtain target simulation requirement information; the target simulation requirement information includes M target simulation requirement representations; the target simulation requirement representations include a first requirement vector and a second requirement vector; a second processing module, configured to select and process the target simulation requirement information using the multi-resolution simulation object information to obtain target simulation object information; the target simulation object information includes M target simulation object representations; the target simulation object representations are used to schedule corresponding simulation models for simulation at different times; The step of analyzing and processing the pending simulation task information to obtain target simulation requirement information includes: Decomposing the to-be-processed simulation task information to obtain time-series simulation task information; the time-series simulation task information includes M simulation tasks arranged in simulation execution time sequence; Determining target simulation requirement information based on the timing simulation task information; The step of determining target simulation requirement information based on the timing simulation task information includes: Determining initial simulation requirement information based on the timing simulation task information; the initial simulation requirement information includes M initial simulation requirement values; Determining target simulation requirement information based on the initial simulation requirement information; The step of determining target simulation requirement information based on the initial simulation requirement information includes: For any of the initial simulation requirement values ​​in the initial simulation requirement information, converting the initial simulation requirement value to obtain an initial resolution level corresponding to the initial simulation requirement value; Determine whether the distribution order of the initial simulation demand value is the first order, and obtain a order determination result; whether the distribution order of the initial simulation demand value is the first order indicates whether the simulation time sequence corresponding to the initial simulation demand value is the first; When the sorting judgment result is yes, the initial resolution level is determined as the target resolution level corresponding to the initial simulation requirement value; When the ranking judgment result is no, it is determined that the level difference between the initial resolution level corresponding to the initial simulation requirement value and the target resolution level corresponding to an initial simulation requirement value whose distribution ranking is before the initial simulation requirement value is within 1 level difference unit, and a level judgment result is obtained; When the level judgment result is yes, the initial resolution level is determined as the target resolution level corresponding to the initial simulation requirement value; When the level judgment result is no, adjusting the initial resolution level corresponding to the initial simulation requirement value to a level difference unit different from the target resolution level corresponding to the initial simulation requirement value before the initial simulation requirement value, to obtain an updated initial resolution level corresponding to the initial simulation requirement value; Determining the updated initial resolution level corresponding to the initial simulation requirement value as the target resolution level corresponding to the initial simulation requirement value; Vector conversion is performed on the target resolution level to obtain a target simulation requirement representation corresponding to the initial simulation requirement value.

6. A data processing device based on a multi-resolution simulation object, characterized in that: The device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the data processing method based on a multi-resolution simulation object according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the data processing method based on multi-resolution simulation objects according to any one of claims 1 to 4.

Images