Simulation model implementation method and device

Abstract

The invention discloses a simulation model implementation method and device. The method comprises the following steps: acquiring simulation information; processing the simulation information to obtain simulation instruction information; and processing the simulation instruction information to obtain target simulation result information. Wherein the step of processing the simulation information to obtain the simulation instruction information comprises the substeps of processing the simulation information to obtain simulation script information; analyzing and processing the simulation script information to obtain simulation script syntax tree information; and processing the simulation script syntax tree information to obtain simulation instruction information. It can be seen that the simulation script code can be automatically generated, execution and evaluation of the simulation model can be rapidly carried out, and the accuracy and reliability of the simulation model can be improved.

Description

Technical Field

[0001] The present invention relates to the field of simulation, and in particular to a simulation model realization method and device. Background Art

[0002] In the field of simulation, scenarios are an important cornerstone for building virtual environments and simulating simulation processes. Scenario design is often based on training topics and details the strategic intentions, current situations, and future developments of simulation participants. As a specific manifestation of scenarios in the field of simulation, simulation scenarios further refine key simulation factors such as the configuration of participating entities, simulation processes, types and quantities of simulations, simulation environment deployment, and simulation systems. These elements are standardized and formatted, and are important inputs that drive the efficient operation of simulation systems.

[0003] However, current simulation systems use a variety of description methods to describe simulation elements, including text language description, formalized abstract expression, etc. Although these methods have their own advantages, they also expose some problems: traditional simulation model creation often involves tedious code writing, debugging and verification processes, which is not only time-consuming, but also requires high professional skills. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a simulation model implementation method and device, which can automatically generate simulation script code and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0005] In order to solve the above technical problems, a first aspect of an embodiment of the present invention discloses a simulation model implementation method, the method comprising:

[0006] S1, obtain simulation information;

[0007] S2, processing the simulation information to obtain simulation instruction information;

[0008] S3, processing the simulation instruction information to obtain target simulation result information.

[0009] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the processing of the simulation information to obtain the simulation instruction information includes:

[0010] S21, processing the simulation information to obtain simulation script information;

[0011] S22, analyzing and processing the simulation script information to obtain simulation script syntax tree information;

[0012] S23, processing the simulation script syntax tree information to obtain simulation instruction information.

[0013] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the processing of the simulation information to obtain the simulation script information includes:

[0014] S211, performing data cleaning processing on the simulation information to obtain first simulation information;

[0015] S212, performing word segmentation processing on the first simulation information to obtain second simulation information;

[0016] S213, performing data enhancement processing on the second simulation information to obtain pre-processed simulation information;

[0017] S214, processing the pre-processed simulation information to obtain simulation script information.

[0018] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the processing of the preprocessed simulation information to obtain the simulation script information includes:

[0019] S2141, training the initial simulation model to obtain a simulation result model;

[0020] S2142: Using the simulation result model, process the pre-processed simulation information to obtain simulation script information.

[0021] As an optional implementation, in the first aspect of the embodiment of the present invention, the training process of the initial simulation model to obtain the simulation result model includes:

[0022] S21411, obtaining a simulation training sample set; the simulation training sample set includes a plurality of simulation training samples;

[0023] S21412, performing labeling processing on the simulation training sample set to obtain a simulation training labeled sample set; the simulation training labeled sample set includes a plurality of simulation training labeled samples;

[0024] S21413, preset s=1;

[0025] S21414, using the sth simulation training labeled sample in the simulation training labeled sample set to train the simulation initial model to obtain training result information and a simulation training model;

[0026] S21415, processing the training result information and the label information corresponding to the training result information to obtain a loss function value;

[0027] S21416, calculating and processing the training result information and the label information to obtain a simulation matching value;

[0028] S21417, using a first simulation calculation model, calculating and processing the loss function value and the simulation matching degree value to obtain a target loss function value;

[0029] Wherein, the first simulation calculation model is:

[0030] SS=δ1·(1-PPDZ)+δ2·DYSS+ε;

[0031] δ1+δ2=1;

[0032] 0≤δ1,δ2≤1;

[0033] -0.1≤ε≤0.1;

[0034] Wherein, SS is the target loss function value, DYSS is the loss function value, PPDZ is the simulation matching value, δ1 and δ2 are the first weight parameter and the second weight parameter respectively, and ε is the first constant coefficient;

[0035] S21418, determining whether the target loss function value is less than a preset loss function threshold, and obtaining a first determination result;

[0036] When the first judgment result is no, judging whether s is equal to the number of the simulation training labeled samples in the simulation training labeled sample set, and obtaining a second judgment result;

[0037] When the second judgment result is no, increase s by 1, determine that the simulation training model is the simulation initial model, and execute S21414;

[0038] When the second judgment result is yes, determining that the simulation training model is a simulation result model;

[0039] When the first judgment result is yes, the simulation training model is determined to be the simulation result model.

[0040] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the calculating and processing the training result information and the label information to obtain the simulation matching value includes:

[0041] Using a second simulation calculation model, the training result information and the label information are calculated and processed to obtain a simulation matching value;

[0042] Wherein, the second simulation calculation model is:

[0043]

[0044] Where PPDZ is the simulation matching value, XD is the length of the label information, XZ is the length of the training result information, PN n is the n-gram accuracy, δ3 is the third weight parameter, and N is the simulated matching length value.

[0045] As an optional implementation, in the first aspect of the embodiment of the present invention, the analysis and processing of the simulation script information to obtain the simulation script syntax tree information includes:

[0046] S221, performing lexical analysis on the simulation script information to obtain simulation script lexical information;

[0047] S222, performing grammatical analysis on the simulation script lexical information to obtain simulation script grammatical information;

[0048] S223, performing semantic analysis on the simulation script syntax information to obtain simulation script syntax tree information.

[0049] A second aspect of an embodiment of the present invention discloses a simulation model implementation device, the device comprising:

[0050] An acquisition module, used for acquiring simulation information;

[0051] A first analysis module, used for processing the simulation information to obtain simulation instruction information;

[0052] The second analysis module is used to process the simulation instruction information to obtain target simulation result information.

[0053] A third aspect of an embodiment of the present invention discloses another simulation model implementation device, the device comprising:

[0054] processor;

[0055] a memory coupled to the processor and storing executable program code;

[0056] The processor calls the executable program code stored in the memory to execute part or all of the steps of the simulation model implementation method disclosed in the first aspect of the embodiment of the present invention.

[0057] The fourth aspect of an embodiment 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 part or all of the steps of the simulation model implementation method disclosed in the first aspect of the embodiment of the present invention.

[0058] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0059] In an embodiment of the present invention, simulation information is obtained; the simulation information is processed to obtain simulation instruction information; the simulation instruction information is processed to obtain target simulation result information. Wherein, the processing of the simulation information to obtain simulation instruction information includes: processing the simulation information to obtain simulation script information; analyzing and processing the simulation script information to obtain simulation script syntax tree information; processing the simulation script syntax tree information to obtain simulation instruction information. It can be seen that the present application can automatically generate simulation script code, and quickly execute and evaluate the simulation model, which is conducive to improving the accuracy and reliability of the simulation model. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] 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.

[0061] Figure 1 A schematic diagram of a flow chart of a simulation model implementation method disclosed in an embodiment of the present invention;

[0062] Figure 2 A schematic diagram of the structure of a simulation model implementation device disclosed in an embodiment of the present invention;

[0063] Figure 3 The present invention is a schematic diagram of the structure of another simulation model implementation device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in 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 creative work are within the scope of protection of the present invention.

[0065] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0066] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0067] The present invention discloses a simulation model implementation method and device, which can automatically generate simulation script code and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model. Detailed descriptions are given below.

[0068] Embodiment 1

[0069] See also Figure 1 , Figure 1 : is a flow chart of a simulation model implementation method disclosed in an embodiment of the present invention. Figure 1 The simulation model implementation method described is applied to a simulation model implementation device, such as a local server or cloud server for optimizing the management of the simulation model, and the embodiments of the present invention do not limit this. Figure 1 As shown, the simulation model implementation method may include the following operations:

[0070] S1, obtain simulation information;

[0071] S2, processing the simulation information to obtain simulation instruction information;

[0072] S3, processing the simulation instruction information to obtain target simulation result information.

[0073] It should be noted that the simulation information includes simulation environment information, simulation resource information, simulation task information, simulation entity information and simulation logic information; the simulation entity information includes several simulation entities; among them, the simulation logic information is used to perform logical control on the simulation environment information, simulation resource information, simulation task information and simulation entity information in the simulation script information when training the model, so as to form a complete simulation execution logic.

[0074] It can be seen that the simulation model realization method described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0075] In an optional embodiment, the simulation information is processed to obtain simulation instruction information, including:

[0076] S21, processing the simulation information to obtain simulation script information;

[0077] S22, analyzing and processing the simulation script information to obtain the simulation script syntax tree information;

[0078] S23, processing the simulation script syntax tree information to obtain simulation instruction information.

[0079] It should be noted that the simulation script information in the embodiment of the present invention is written in a scripting language, and the scripting language may be Python, Lua, JavaScript, or a user-defined scripting language, which is not limited in the specific embodiment of the present invention;

[0080] It should be noted that the simulation script information is analyzed and processed to obtain the simulation script syntax tree information, which is analyzed and processed by an interpreter. The interpreter can be CPython (the corresponding script language is Python), Lua interpreter (the corresponding script language is Lua), Node.js (the corresponding script language is JavaScript) or an interpreter corresponding to a user-defined script language, which is not specifically limited in the embodiments of the present invention.

[0081] It should be noted that the above-mentioned analysis and processing of the simulation script information to obtain the simulation script syntax tree information and processing of the simulation script syntax tree information to obtain the simulation instruction information are both processed by the interpreter, and the specific embodiments of the present invention are not limited thereto.

[0082] It can be seen that the simulation model realization method described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0083] In another optional embodiment, the simulation information is processed to obtain simulation script information, including:

[0084] S211, performing data cleaning processing on the simulation information to obtain first simulation information;

[0085] S212, performing word segmentation processing on the first simulation information to obtain second simulation information;

[0086] S213, performing data enhancement processing on the second simulation information to obtain pre-processed simulation information;

[0087] S214, processing the pre-processed simulation information to obtain simulation script information.

[0088] It should be noted that, the simulation information is cleaned and processed to obtain the first simulation information, and one of Pandas or NumPy can be used for data cleaning. Specifically, the embodiment of the present invention does not limit this.

[0089] It should be noted that the first simulation information is segmented to obtain the second simulation information, which can be segmented by tools or libraries such as Jieba, THULAC or HanLP, etc., which is not limited in the embodiments of the present invention.

[0090] It should be noted that the second simulation information is subjected to data enhancement processing to obtain preprocessed simulation information, and data enhancement processing can be performed through tools or libraries such as nlpaug, TextAttack or Transformers, etc., which is not limited in the embodiments of the present invention.

[0091] It should be noted that data cleaning, word segmentation and data enhancement processing can improve data availability, help text information to achieve more effective vectorization and feature extraction, and reduce the computational overhead when processing complex text information.

[0092] It can be seen that the simulation model realization method described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0093] In yet another optional embodiment, the preprocessing simulation information is processed to obtain simulation script information, including:

[0094] S2141, training the initial simulation model to obtain a simulation result model;

[0095] S2142, using the simulation result model, processing the pre-processed simulation information to obtain simulation script information.

[0096] It should be noted that the above-mentioned simulation initial model is a Transformer model, and deep learning models such as CNN and RNN may also be used. Specifically, the embodiments of the present invention do not limit this.

[0097] It should be noted that the simulation result model is used to process the pre-processed simulation information to obtain the simulation script information, which is to use the pre-processed simulation information as the input of the simulation result model, and use the simulation result model to calculate and output the simulation script information.

[0098] It can be seen that the simulation model realization method described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0099] In an optional embodiment, training the initial simulation model to obtain a simulation result model includes:

[0100] S21411, obtaining a simulation training sample set; the simulation training sample set includes a plurality of simulation training samples;

[0101] S21412, performing labeling processing on the simulation training sample set to obtain a simulation training labeling sample set; the simulation training labeling sample set includes a plurality of simulation training labeling samples;

[0102] It should be noted that the simulation training sample set is labeled to obtain the simulation training labeled sample set, which can be labeled by Label Studio, Prodigy or Doccano, and the specific embodiment of the present invention does not limit this.

[0103] S21413, preset s=1;

[0104] S21414, using the sth simulation training labeled sample in the simulation training labeled sample set, training the simulation initial model to obtain training result information and the simulation training model;

[0105] S21415, processing the training result information and the label information corresponding to the training result information to obtain a loss function value;

[0106] It should be noted that the training result information and the label information corresponding to the training result information are processed to obtain the loss function value, which can be calculated and processed using the cross entropy loss function or other loss functions in the deep learning model. The specific embodiment of the present invention is not limited thereto.

[0107] It should be noted that the label information corresponding to the above training result information is the actual output information corresponding to the training result information, and is used to measure the difference between the model training results and the actual results together with the training result information.

[0108] It should be noted that the tag information may be set by a user or acquired based on historical data, which is not limited in the embodiment of the present invention.

[0109] S21416, calculating and processing the training result information and the label information to obtain a simulation matching value;

[0110] S21417, using the first simulation calculation model, calculating and processing the loss function value and the simulation matching value to obtain a target loss function value;

[0111] Among them, the first simulation calculation model is:

[0112] SS=δ1·(1-PPDZ)+δ2·DYSS+ε;

[0113] δ1+δ2=1;

[0114] 0≤δ1,δ2≤1;

[0115] -0.1≤ε≤0.1;

[0116] Where SS is the target loss function value, DYSS is the loss function value, PPDZ is the simulation matching value, δ1 and δ2 are the first weight parameter and the second weight parameter respectively, and ε is the first constant coefficient;

[0117] It should be noted that the first weight parameter, the second weight parameter and the first constant coefficient may be set by a user or may be obtained based on historical data, which is not limited in the embodiment of the present invention.

[0118] It should be noted that by adjusting the simulation matching value, the loss function value and the first constant coefficient through the first weight parameter and the second weight parameter, the accuracy, flexibility and stability of the simulation optimization are improved, so that the model can better match the target, control the error, and have good adjustment performance to meet the needs of different application scenarios.

[0119] It should be noted that the simulation match value is used to reflect the n-gram matching of vocabulary combinations. The simulation match value ranges from [0,1]. The larger the simulation match value, the better the language fluency and local expression.

[0120] S21418, determining whether the target loss function value is less than a preset loss function threshold, and obtaining a first determination result;

[0121] When the first judgment result is no, determine whether s is equal to the number of simulation training labeled samples in the simulation training labeled sample set to obtain a second judgment result;

[0122] When the second judgment result is no, s is increased by 1, the simulation training model is determined to be the simulation initial model, and S21414 is executed;

[0123] When the second judgment result is yes, determining the simulation training model as the simulation result model;

[0124] When the first judgment result is yes, the simulation training model is determined to be the simulation result model.

[0125] It should be noted that the preset loss function threshold value range is between [0, 0.03], and is not limited in the embodiment of the present invention.

[0126] It should be noted that the number of simulation training annotated samples in the simulation training annotated sample set is greater than 50,000, and the specific embodiment of the present invention does not limit this.

[0127] It can be seen that the simulation model realization method described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0128] In an optional embodiment, the training result information and the label information are calculated and processed to obtain a simulation matching value, including:

[0129] Using the second simulation calculation model, the training result information and the label information are calculated and processed to obtain a simulation matching value;

[0130] Among them, the second simulation calculation model is:

[0131]

[0132] Where PPDZ is the simulation matching value, XD is the length of the label information, XZ is the length of the training result information, and PN n is the n-gram accuracy, δ3 is the third weight parameter, and N is the simulated matching length value.

[0133] It should be noted that the third weight parameter may be set by a user or obtained based on historical data, and this is not limited in the embodiment of the present invention.

[0134] It should be noted that the simulation matching degree value ranges from a positive integer between [1, 5], and is not specifically limited in the embodiment of the present invention.

[0135] It should be noted that n-gram accuracy refers to how many n-grams (i.e., sequences consisting of n consecutive words) in the training result information match the n-grams in the tag information. N-grams can be 1-grams, 2-grams, 3-grams, etc., and n specifically represents the number of consecutive words. For example:

[0136] 1-gram: a single word;

[0137] 2-gram: two consecutive words;

[0138] 3-gram: three consecutive words.

[0139] It can be seen that the simulation model realization method described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0140] In an optional embodiment, the simulation script information is analyzed and processed to obtain the simulation script syntax tree information, including:

[0141] S221, performing lexical analysis on the simulation script information to obtain simulation script lexical information;

[0142] S222, performing grammatical analysis on the lexical information of the simulation script to obtain grammatical information of the simulation script;

[0143] S223, performing semantic analysis on the simulation script syntax information to obtain the simulation script syntax tree information.

[0144] It should be noted that the above-mentioned lexical analysis, grammatical analysis and semantic analysis are all processed by an interpreter, and the specific details are not limited in the embodiment of the present invention.

[0145] It can be seen that the simulation model realization method described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0146] In an optional embodiment, the simulation instruction information is processed to obtain target simulation result information, including:

[0147] S31, executing the simulation instruction information to obtain simulation result information; the simulation result information includes performance data information and validity data information;

[0148] It should be noted that the simulation instruction information is executed to obtain the simulation result information by using a simulation system to execute the simulation instruction information, such as the XSimStudioV5 series simulation platform software products. Specifically, the embodiments of the present invention do not limit this.

[0149] S32, analyzing and processing the performance data information to obtain a performance score value;

[0150] S33, analyzing and processing the effectiveness data information to obtain an effectiveness score value;

[0151] S34, processing the performance score value and the effectiveness score value to obtain target simulation result information.

[0152] It can be seen that the simulation model realization method described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0153] In an optional embodiment, the performance data information is analyzed and processed to obtain a performance score value, including:

[0154] S321, using the first simulation scoring model, processing the performance data information to obtain a performance score preprocessing value;

[0155] Among them, the first simulation scoring model is:

[0156]

[0157] Where XN′ is the preprocessing value of the performance score, SJ i1 is the response time of the i1th simulation task in the performance data information, D i1 is the input data volume of the performance data information of the i1th simulation task, C i1 is the task complexity value of the i1th simulation task in the performance data information, τ1 and τ2 are the first weighting coefficient and the second weighting coefficient respectively, and M1 is the number of simulation tasks;

[0158] It should be noted that the first weighting coefficient and the second weighting coefficient may be set by a user or obtained based on historical data, which is not limited in the embodiment of the present invention.

[0159] S322, obtaining the maximum response time and the minimum response time of the simulation task;

[0160] S323, using the simulation normalization calculation model, calculating and processing the performance score preprocessing value, the simulation task maximum response time and the simulation task minimum response time to obtain a performance score value.

[0161] Among them, the simulation normalization calculation model is:

[0162]

[0163] In the formula, XN is the performance score value, XN′ is the performance score preprocessing value, and XN max is the maximum response time of the simulation task, XN min is the minimum response time of the simulation task;

[0164] It should be noted that XN′ is less than or equal to XN max and greater than or equal to XN min , the final value of XN is in the range of [0,1].

[0165] It should be noted that the above calculation process may also be processed using methods such as Z-score normalization and maximum absolute value normalization, which are not specifically limited in the embodiments of the present invention.

[0166] It can be seen that the simulation model realization method described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0167] In an optional embodiment, the effectiveness data information is analyzed and processed to obtain an effectiveness score value, including:

[0168] Using the second simulation scoring model, the effectiveness data information is processed to obtain an effectiveness scoring value;

[0169] Among them, the second simulation scoring model is:

[0170]

[0171] Where ZQ is the effectiveness score, TP is the number of successful executions of simulation tasks in the effectiveness data information, and M1 is the number of simulation tasks.

[0172] It can be seen that the simulation model realization method described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0173] In an optional embodiment, the performance score value and the effectiveness score value are processed to obtain target simulation result information, including:

[0174] S341, using a third simulation scoring model, processing the performance scoring value and the effectiveness scoring value to obtain a target scoring value;

[0175] Among them, the third simulation scoring model is:

[0176] PF = δ4·XN+δ5·ZQ;

[0177] δ4+δ5=100;

[0178] 0≤δ4,δ5≤100;

[0179] Where PF is the target score, XN is the performance score, ZQ is the effectiveness score, δ4 and δ5 are the fourth and fifth weight parameters;

[0180] It should be noted that the fourth weight parameter and the fifth weight parameter are set by the user, and may also be obtained based on historical data, which is not specifically limited in the embodiment of the present invention.

[0181] S342, determining whether the target score value is greater than a preset first score threshold, and obtaining a third determination result;

[0182] When the third judgment result is yes, determining excellent as the target simulation result information;

[0183] When the third judgment result is no, determining whether the target score value is greater than a preset second score threshold value, and obtaining a fourth judgment result;

[0184] When the fourth judgment result is yes, determining medium as the target simulation result information;

[0185] When the fourth judgment result is no, it is determined that poor is the target simulation result information.

[0186] It should be noted that the preset first scoring threshold has a value range of [85, 90], and the preset second scoring threshold has a value range of [70, 75]. Specifically, the embodiment of the present invention does not limit this.

[0187] It should be noted that when the target simulation result information is excellent, the representation simulation model performs very well in terms of performance and accuracy. The model can not only run quickly and efficiently, but also the simulation results are almost consistent with expectations, and the reliability of the model is very high; when the target simulation result information is medium, the representation simulation model can complete basic tasks, but the performance or accuracy is insufficient, and the accuracy of the simulation results needs to be improved; when the target simulation result information is poor, the representation simulation model cannot effectively meet the needs, there may be frequent errors or extremely low performance, and the simulation model needs to be adjusted and optimized on a large scale to meet the usage standards. Such models may not be able to provide meaningful simulation results.

[0188] It can be seen that the simulation model realization method described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0189] Embodiment 2

[0190] See also Figure 2 , Figure 2 Schematic diagram of a simulation model implementation device disclosed in an embodiment of the present invention. Figure 2 The simulation model implementation device described is applied to a simulation model implementation optimization system, such as a local server or cloud server for simulation model implementation, etc., which is not limited in the embodiments of the present invention. Figure 2 As shown, the simulation model implementation device includes:

[0191] An acquisition module 201 is used to acquire simulation information;

[0192] A first analysis module 202 is used to process the simulation information to obtain simulation instruction information;

[0193] The second analysis module 203 is used to process the simulation instruction information to obtain target simulation result information.

[0194] It can be seen that the simulation model implementation device described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0195] Embodiment 3

[0196] See also Figure 3 , Figure 3 is a schematic diagram of the structure of another simulation model implementation device disclosed in an embodiment of the present invention. Figure 3 The simulation model implementation device described is applied to a simulation model implementation optimization system, such as a local server or cloud server for simulation model implementation, etc., which is not limited in the embodiments of the present invention. Figure 3 As shown, the simulation model implementation device includes:

[0197] Processor 301;

[0198] A memory 302 coupled to the processor 301 and storing executable program codes;

[0199] The processor 301 calls the executable program code stored in the memory 302 to execute part or all of the steps of the simulation model implementation method of the first embodiment.

[0200] It can be seen that the simulation model implementation device described in the embodiment of the present invention can automatically generate simulation script codes and quickly execute and evaluate the simulation model, which is beneficial to improving the accuracy and reliability of the simulation model.

[0201] Embodiment 4

[0202] The embodiment 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 part or all of the steps of the simulation model implementation method of the first embodiment.

[0203] Embodiment 5

[0204] 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 part or all of the steps in the simulation model implementation method described in Example 1.

[0205] The system embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative labor.

[0206] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes 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 rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0207] Finally, it should be noted that the simulation model implementation method and device disclosed in the embodiment of the present invention disclose only the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art 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 embodiments of the present invention.

Claims

1. A simulation model implementation method, characterized in that: The method comprises: S1, obtain simulation information; S2, processing the simulation information to obtain simulation instruction information; S3, processing the simulation instruction information to obtain target simulation result information.

2. The simulation model implementation method according to claim 1, characterized in that: The processing of the simulation information to obtain simulation instruction information includes: S21, processing the simulation information to obtain simulation script information; S22, analyzing and processing the simulation script information to obtain simulation script syntax tree information; S23, processing the simulation script syntax tree information to obtain simulation instruction information.

3. The simulation model implementation method according to claim 2, characterized in that: The processing of the simulation information to obtain simulation script information includes: S211, performing data cleaning processing on the simulation information to obtain first simulation information; S212, performing word segmentation processing on the first simulation information to obtain second simulation information; S213, performing data enhancement processing on the second simulation information to obtain pre-processed simulation information; S214, processing the pre-processed simulation information to obtain simulation script information.

4. The method for realizing a simulation model according to claim 3, characterized in that: The step of processing the pre-processed simulation information to obtain simulation script information includes: S2141, training the initial simulation model to obtain a simulation result model; S2142: Using the simulation result model, process the pre-processed simulation information to obtain simulation script information.

5. The method for realizing the simulation model according to claim 4, characterized in that: The training process of the initial simulation model to obtain the simulation result model includes: S21411, obtaining a simulation training sample set; the simulation training sample set includes a plurality of simulation training samples; S21412, performing labeling processing on the simulation training sample set to obtain a simulation training labeled sample set; the simulation training labeled sample set includes a plurality of simulation training labeled samples; S21413, preset s=1; S21414, using the sth simulation training labeled sample in the simulation training labeled sample set to train the simulation initial model to obtain training result information and a simulation training model; S21415, processing the training result information and the label information corresponding to the training result information to obtain a loss function value; S21416, calculating and processing the training result information and the label information to obtain a simulation matching value; S21417, using a first simulation calculation model, calculating and processing the loss function value and the simulation matching degree value to obtain a target loss function value; Wherein, the first simulation calculation model is: SS=δ1·(1-PPDZ)+δ2·DYSS+ε; δ1+δ2=1; 0≤δ1,δ2≤1; -0.1≤ε≤0.1; Wherein, SS is the target loss function value, DYSS is the loss function value, PPDZ is the simulation matching value, δ1 and δ2 are the first weight parameter and the second weight parameter respectively, and ε is the first constant coefficient; S21418, determining whether the target loss function value is less than a preset loss function threshold, and obtaining a first determination result; When the first judgment result is no, judging whether s is equal to the number of the simulation training labeled samples in the simulation training labeled sample set, and obtaining a second judgment result; When the second judgment result is no, increase s by 1, determine that the simulation training model is the simulation initial model, and execute S21414; When the second judgment result is yes, determining that the simulation training model is a simulation result model; When the first judgment result is yes, the simulation training model is determined to be the simulation result model.

6. The method for realizing the simulation model according to claim 5, characterized in that: The calculating and processing the training result information and the label information to obtain a simulation matching value includes: Using a second simulation calculation model, the training result information and the label information are calculated and processed to obtain a simulation matching value; Wherein, the second simulation calculation model is: Where PPDZ is the simulation matching value, XD is the length of the label information, XZ is the length of the training result information, PN n is the n-gram accuracy, δ3 is the third weight parameter, and N is the simulated matching length value.

7. The method for realizing a simulation model according to claim 2, characterized in that: The step of analyzing and processing the simulation script information to obtain the simulation script syntax tree information includes: S221, performing lexical analysis on the simulation script information to obtain simulation script lexical information; S222, performing grammatical analysis on the simulation script lexical information to obtain simulation script grammatical information; S223, performing semantic analysis on the simulation script syntax information to obtain simulation script syntax tree information.

8. A simulation model implementation device, characterized in that: The device comprises: An acquisition module, used for acquiring simulation information; A first analysis module, used for processing the simulation information to obtain simulation instruction information; The second analysis module is used to process the simulation instruction information to obtain target simulation result information.

9. A simulation model implementation device, characterized in that: The device comprises: processor; a memory coupled to the processor and storing executable program code; The processor calls the executable program code stored in the memory to execute the simulation model implementation method according to any one of claims 1 to 7.

10. 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 simulation model implementation method according to any one of claims 1 to 7.

Images