WO2019200625A1 - 基于人工智能的电子产品建模系统及方法 - Google Patents

基于人工智能的电子产品建模系统及方法 Download PDF

Info

Publication number
WO2019200625A1
WO2019200625A1 PCT/CN2018/085639 CN2018085639W WO2019200625A1 WO 2019200625 A1 WO2019200625 A1 WO 2019200625A1 CN 2018085639 W CN2018085639 W CN 2018085639W WO 2019200625 A1 WO2019200625 A1 WO 2019200625A1
Authority
WO
WIPO (PCT)
Prior art keywords
modeling
electronic product
model
modeled
sample
Prior art date
Application number
PCT/CN2018/085639
Other languages
English (en)
French (fr)
Inventor
陈志熙
刘洁
石佳
Original Assignee
石家庄创天电子科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 石家庄创天电子科技有限公司 filed Critical 石家庄创天电子科技有限公司
Publication of WO2019200625A1 publication Critical patent/WO2019200625A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/18—Manufacturability analysis or optimisation for manufacturability

Definitions

  • the embodiments of the present application relate to the field of electronic product modeling, and in particular, to an electronic product modeling system and method based on artificial intelligence.
  • the existing electronic product model design has the following problems: First, the modeling work of the electronic product uses a well-known computer simulation design tool. However, typical product design flows are fragmented and are implemented by manual execution. Secondly, the current electronic product modeling process mainly includes receiving product shape and design requirements, establishing models in one or more computer design tools, adjusting models, etc., and generating highly correlated each step performed. data. However, there is currently no system or method that automatically learns the relevant data generated in the model design.
  • the main object of the present invention is to provide an artificial intelligence-based electronic product modeling system and method with high modeling efficiency and more robustness.
  • the embodiment of the present application provides an electronic product modeling system based on artificial intelligence, comprising: a receiving module, configured to receive a sample model; and a sensing module, configured to simulate running the sample model to generate a simulation running result. a cognitive module for analyzing an intrinsic relationship between the sample model and the simulation running result thereof, thereby generating an analysis result; and a modeling module for providing an input parameter parameter to be modeled, and according to the The analysis result performs a modeling operation to automatically establish an electronic product model that conforms to the parameter parameters to be modeled.
  • the receiving module is configured to receive a different type of sample model
  • the modeling module further includes a fusion unit, configured to analyze the input to be modeled When the indicator parameters are from different types of the sample models, extract part of the models that meet the index parameters to be modeled from each of the sample models, and fuse the extracted partial models to establish the electronic Product model.
  • the indicator parameter to be modeled includes a product performance parameter, an operating environment parameter, and a specification parameter
  • the cognitive module further includes the sample model according to the analyzed The intrinsic relationship between the simulation operation results is obtained, and performance parameters, operating environment parameters and specification parameters of each electronic component in the sample model are obtained.
  • the modeling module further includes generating a modeling rule according to the analysis result, and establishing the electronic product model based on the modeling rule.
  • the system further includes an optimization module, configured to analyze whether the electronic product model established by the modeling module meets the indicator parameter to be modeled, and The modeling rules of the modeling module are continuously optimized according to the analysis results.
  • the present application also provides an artificial intelligence-based electronic product modeling method, comprising: performing a sensing step to receive a sample model, and simulating running the sample model to generate a simulation running result; performing a cognitive step, And analyzing the intrinsic relationship between the sample model and the simulation running result, thereby generating an analysis result; and performing a modeling step to input an indicator parameter to be modeled, and performing a modeling operation according to the analysis result, To automatically establish an electronic product model that conforms to the index parameters to be modeled.
  • the sensing step is configured to receive different types of sample models
  • the modeling step further includes: when the analyzed input parameter parameters to be modeled are from different types
  • a partial model that meets the index parameter to be modeled is extracted from each of the sample models, and the extracted partial model is merged to establish the electronic product model.
  • the indicator parameter to be modeled includes a product performance parameter, an operating environment parameter, and a specification parameter
  • the cognitive step further includes: according to the analyzed sample model and The intrinsic relationship between the simulation operation results obtains performance parameters, operating environment parameters and specification parameters of each electronic component in the sample model.
  • the modeling step generates a modeling rule according to the analysis result output by the cognitive step, and establishes the electronic product model based on the modeling rule.
  • the method further includes performing an optimization step of analyzing whether the electronic product model established by the modeling step meets the indicator parameter to be modeled, Updating the modeling rule according to the analysis result, and repeatedly performing the modeling step according to the updated modeling rule to finally establish an electronic product model that conforms to the indicator parameter to be modeled.
  • the artificial intelligence-based electronic product modeling system and method provided by the present application generates a modeling rule according to the analysis result by simulating the running of the sample model and analyzing the internal relationship between the sample model and the simulation running result. Therefore, an electronic product model conforming to the index parameter to be modeled can be automatically established according to the input index parameter to be modeled and based on the modeling rule, thereby not only being able to automate modeling, but also reducing Risks and uncertainties in the design and implementation of the model.
  • FIG. 1 is a schematic diagram of a basic architecture of an artificial intelligence-based electronic product modeling system according to an embodiment of the present application
  • FIG. 2 is a schematic diagram showing different embodiments of the artificial intelligence-based electronic product modeling system of FIG. 1;
  • FIG. 3 is a schematic diagram of a basic flow of an artificial intelligence-based electronic product modeling method according to another embodiment of the present application.
  • FIG. 1 is a schematic diagram of a basic architecture of an artificial intelligence-based electronic product modeling system according to an embodiment of the present application.
  • the artificial intelligence-based electronic product modeling system 10 of the present application mainly includes a receiving module 11, a sensing module 12, a cognitive module 13, and a modeling module 14.
  • the receiving module 11 is configured to receive a sample model.
  • the receiving module 11 can be configured to receive different types of sample models, such as by inputting different types of electronic product data into known modeling tools to obtain a plurality of different types of electronic product models.
  • the sensing module 12 is configured to simulate running the received sample model to generate a corresponding simulation running result.
  • the cognitive module 13 is used to analyze the intrinsic relationship between the sample model and its simulation running results, thereby generating an analysis result.
  • the cognitive module 13 can receive various signals from the sample model to analyze the intrinsic link between the sample model and its simulation run results.
  • the indicator parameters to be modeled by the circuit designer include product performance parameters, operating environment parameters, and specification parameters, and the cognitive module 13 can be based on the internal relationship between the analyzed sample model and the simulation operation result. Contact to obtain the performance parameters, operating environment parameters and specification parameters of each electronic component in the sample model.
  • the cognitive module 13 of the present application can analyze and understand the essence of the sample model, and no longer make a simple and mechanical judgment.
  • the modeling module 14 is configured to provide a circuit designer to input the index parameters to be modeled, and perform a modeling operation according to the analysis result of the cognitive module 13 to automatically generate an electronic product model that conforms to the index parameters to be modeled.
  • the modeling module 14 may generate a modeling rule according to the analysis result output by the cognitive module 13, and automatically establish an electronic product model based on the generated modeling rule.
  • FIG. 2 is a schematic diagram showing different embodiments of the artificial intelligence based electronic product modeling system of FIG.
  • the modeling module 14 of the present application further has a fusion unit 141.
  • the receiving module 11 of the present application can receive different types of sample models, and thus, when the analysis circuit designer inputs the to-be-built
  • the fusion unit 141 may separately extract partial models corresponding to the index parameters to be modeled from each sample model, and fuse the extracted partial models to establish a complete match.
  • the electronic product model of the indicator parameters to be modeled may be modeled.
  • the artificial intelligence-based electronic product modeling system 10 of the present application further includes an optimization module 15 for analyzing whether the electronic product model established by the modeling module 14 conforms to the circuit designer's
  • the modeled indicator parameters are used to continuously optimize the modeling rules of the modeling module 14 based on the analysis results.
  • the optimization module 15 is configured to analyze whether the electronic product model established by the modeling module 14 meets the index parameter to be modeled by the circuit designer. When the determination result is not met, the modeling module 14 is further analyzed. Whether the simulation operation result of the established electronic product model is closer to the index parameter to be modeled than the previously established electronic product model, and if the judgment result is yes, a positive feedback signal is output, and vice versa, the negative feedback is output. Signaling, and updating the modeling rules of the modeling module 14 according to the forward feedback signal or the negative feedback signal, so that the interaction between the optimization module 15 and the modeling module 14 causes the modeling module 14 to generate the most Optimized modeling rules.
  • FIG. 3 is a schematic diagram of a basic flow of an artificial intelligence-based electronic product modeling method according to another embodiment of the present application. As shown in the figure, the sensing step of step S31 is first performed to receive the sample model, and the sample model is simulated to run to generate a simulation running result, and then step S32 is performed.
  • Step S32 performing a cognitive step to analyze an intrinsic relationship between the sample model and the simulation running result, thereby generating an analysis result, and then proceeding to step S33.
  • the cognitive step of the present application can obtain performance parameters, operating environment parameters, and specification parameters of each electronic component in the sample model according to the intrinsic relationship between the analyzed sample model and the simulation running result.
  • Step S33 performing a modeling step to input the index parameter to be modeled, and performing a modeling operation according to the analysis result generated in step S32 to automatically establish an electronic product model that conforms to the index parameter to be modeled.
  • the foregoing modeling step may generate a corresponding modeling rule according to the analysis result output by the foregoing cognitive step, and automatically generate an electron according to the index parameter to be modeld based on the generated modeling rule.
  • the indicator parameters to be modeled in the modeling step may include product performance parameters, operating environment parameters, and specification parameters.
  • the present application may receive different types of sample models during the performing of the sensing step, such as by inputting different types of electronic product data into known modeling tools to obtain a plurality of different types of electronic Product model.
  • the modeling step performed by the present application may further include extracting, from each sample model, the indicator parameters that are to be modeled, respectively, when analyzing the input index parameters to be modeled from different types of the sample models. Part of the model, and the extracted partial models are merged to finally establish an electronic product model that fully conforms to the index parameters to be modeled.
  • the method of the present application further includes performing an optimization step of analyzing whether the electronic product model established by the modeling step meets the index parameter to be modeled to update the analysis result according to the analysis result.
  • the module rules, and according to the updated modeling rules, step S33 is repeatedly executed, thereby finally establishing an electronic product model that conforms to the index parameters to be modeled.
  • the optimization step analyzes whether the established electronic product model meets the parameter parameters to be modeled by the circuit designer, and when the judgment result is not met, further analyzes the simulation operation of the currently established electronic product model. Whether the result is closer to the index parameter to be modeled than the previously established electronic product model. If the judgment is yes, a positive feedback signal is output, and vice versa, the negative feedback signal is output, and the output is based on the forward feedback.
  • the signal or negative feedback signal updates the modeling rules to generate optimized modeling rules and ultimately establish an electronic product model that conforms to the metric parameters to be modeled.
  • the artificial intelligence-based electronic product modeling system and method of the present application utilizes the artificial intelligence collaborative electronic product model to generate a design framework, which not only can realize the technical effect of the automatic modeling, but also aims to reduce the model design.
  • the device embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separate, and the components displayed as modules may or may not be physical modules, ie may be located A place, or it can be distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without deliberate labor.
  • a machine-readable medium includes read only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash storage media, electrical, optical, acoustic, or other forms of propagation signals (eg, carrier waves) , an infrared signal, a digital signal, etc., etc., the computer software product comprising instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the various embodiments or portions of the embodiments described Methods.
  • ROM read only memory
  • RAM random access memory
  • magnetic disk storage media e.g., magnetic disks, magnetic disk storage media, optical storage media, flash storage media, electrical, optical, acoustic, or other forms of propagation signals (eg, carrier waves) , an infrared signal, a digital signal, etc., etc.
  • the computer software product comprising instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the various embodiments or portions of the embodiment
  • embodiments of the embodiments of the invention may be provided as a method, apparatus (device), or computer program product.
  • embodiments of the invention may be in the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware.
  • embodiments of the invention may take the form of a computer program product embodied on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • Embodiments of the invention are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus, and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG.
  • These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请实施例提供了一种基于人工智能的电子产品建模系统及方法，包括接收样本模型并仿真运行所述样本模型，以生成仿真运行结果，而后分析所述样本模型及其仿真运行结果之间的内在联系，据以生成分析结果，以供后续可依据所生成的分析结果自动建立符合待建模的指标参数的电子产品模型，借此，本申请可使得电子产品模型的建立更为快速且高效，以及可以提高电子产品建模的鲁棒性。

Description

基于人工智能的电子产品建模系统及方法
本申请要求在2018年4月18日提交中国专利局、申请号为201810350394.1、发明名称为“基于人工智能的电子产品建模系统及方法”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及电子产品建模领域，尤其涉及一种基于人工智能的电子产品建模系统及方法。
背景技术
电子产品是以电能为工作基础的产品，被广泛地应用于国防、科技、民生、工业、农业等技术领域。但是，针对自动搭建电子产品模型的相关技术却鲜有研究。
现有的电子产品模型设计存在以下问题：首先，电子产品的建模作业使用的是众所周知的计算机仿真设计工具。然而，典型的产品设计流程是零散的，并且均是通过手动执行来实现的。其次，当前的电子产品建模过程主要包括接收产品外形及设计要求，在一个或多个计算机设计工具中建立模型，调整模型等步骤，在所执行的每个步骤过程中，会生成高度相关的数据。然而，目前并没有一个系统和方法能够自动学习模型设计中所产生的相关数据。
再者，由于电子产品的种类繁多，具有较高的设计门槛，因此，对于设计经验较少或者几乎没有设计经验的设计师来说，常会发生因受限于设计经验不足而导致难以展开电路设计的困扰。
发明内容
有鉴于此，本发明的主要目的在于提供一种建模效率高且更具稳健性的基于人工智能的电子产品建模系统及方法。
本申请实施例提供了一种基于人工智能的电子产品建模系统，其特征在于，包括：接收模块，用于接收样本模型；感知模块，用于仿真运行所述样本模型， 以生成仿真运行结果；认知模块，用于分析所述样本模型及其所述仿真运行结果之间的内在联系，据以生成分析结果；以及建模模块，用于提供输入待建模的指标参数，并依据所述分析结果执行建模操作，以自动建立符合所述待建模的指标参数的电子产品模型。
可选地，在本申请的任一实施例中，所述接收模块用于接收不同类型的样本模型，且所述建模模块还包括融合单元，用于当分析所输入的所述待建模的指标参数来自不同类型的所述样本模型时，分别从各所述样本模型中提取符合所述待建模的指标参数的部分模型，并融合所提取的所述部分模型，以建立所述电子产品模型。
可选地，在本申请的任一实施例中，所述待建模的指标参数包括产品性能参数、运行环境参数及规格参数，所述认知模块还包括根据所分析的所述样本模型及其所述仿真运行结果之间的内在联系，获得所述样本模型中各电子元件的性能参数、运行环境参数及规格参数。
可选地，在本申请的任一实施例中，所述建模模块还包括依据所述分析结果生成建模规则，并基于所述建模规则建立所述电子产品模型。
可选地，在本申请的任一实施例中，所述系统还包括优化模块，用于分析所述建模模块所建立的所述电子产品模型是否符合所述待建模的指标参数，并依据分析结果不断优化所述建模模块的建模规则。
本申请还提供一种基于人工智能的电子产品建模方法，其特征在于，包括：执行感知步骤，以接收样本模型，并仿真运行所述样本模型，以生成仿真运行结果；执行认知步骤，以分析所述样本模型及所述仿真运行结果之间的内在联系，据以生成分析结果；以及执行建模步骤，以输入待建模的指标参数，并依据所述分析结果执行建模操作，以自动建立符合所述待建模的指标参数的电子产品模型。
可选地，在本申请的任一实施例中，所述感知步骤用于接收不同类型的样本模型，所述建模步骤还包括当分析所输入的所述待建模的指标参数来自不同类型的所述样本模型时，分别从各所述样本模型中提取符合所述待建模的指标参数的部分模型，并融合所提取的所述部分模型，以建立所述电子产品模型。
可选地，在本申请的任一实施例中，所述待建模的指标参数包括产品性能参数、运行环境参数及规格参数，所述认知步骤还包括根据所分析的所述样本模型及所述仿真运行结果之间的内在联系，获得所述样本模型中各电子元件的性能参数、运行环境参数及规格参数。
可选地，在本申请的任一实施例中，所述建模步骤依据所述认知步骤所输出的分析结果生成建模规则，并基于所述建模规则建立所述电子产品模型。
可选地，在本申请的任一实施例中，所述方法还包括执行优化步骤，通过分析所述建模步骤所建立的所述电子产品模型是否符合所述待建模的指标参数，以根据分析结果更新所述建模规则，并依据所述更新后的建模规则，重复执行所述建模步骤，以最终建立符合所述待建模的指标参数的电子产品模型。
由上可知，本申请所提供的基于人工智能的电子产品建模系统及方法，通过仿真运行样本模型并分析样本模型及其仿真运行结果之间的内在联系，以依据分析结果而生成建模规则，从而可依据所输入的待建模的指标参数，并基于所述建模规则而自动建立符合所述待建模的指标参数的电子产品模型，借此，不仅能够自动化建模，且能够减少模型设计和实现过程中存在的风险以及不确定性。
附图说明
后文将参照附图以示例性而非限制性的方式详细描述本申请实施例的一些具体实施例。附图中相同的附图标记标示了相同或类似的部件或部分。本领域技术人员应该理解，这些附图未必是按比例绘制的。附图中：
图1是根据本申请的一实施例所示的基于人工智能的电子产品建模系统的基本架构示意图；
图2是显示图1的基于人工智能的电子产品建模系统的不同实施例示意图；以及
图3是根据本申请的另一实施例所示的基于人工智能的电子产品建模方法的基本流程示意图。
具体实施方式
实施本发明实施例的任一技术方案必不一定需要同时达到以上的所有优点。
为了使本领域的人员更好地理解本发明实施例中的技术方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅是本发明实施例一部分实施例，而不是全部的实施例。基于本发明实施例中的实施例，本领域普通技术人员所获得的所有其他实施例，都应当属于本发明实施例保护的范围。
下面结合本发明实施例附图进一步说明本发明实施例具体实现。
图1是根据本申请的一实施例所示的基于人工智能的电子产品建模系统的基本架构示意图。如图所示，本申请的基于人工智能的电子产品建模系统10主要包括接收模块11、感知模块12、认知模块13、以及建模模块14。
接收模块11用于接收样本模型。于本实施例中，接收模块11可用于接收不同类型的样本模型，例如通过将不同类型的电子产品数据输入已知的建模工具而得到多个不同类型的电子产品模型。
感知模块12用于仿真运行所接收的样本模型，以生成相应的仿真运行结果。
认知模块13用于分析样本模型及其仿真运行结果之间的内在联系，据以生成分析结果。具体而言，认知模块13可接收来自样本模型的各种信号，以分析样本模型及其仿真运行结果之间的内在联系。于本实施例中，电路设计人员所输入的待建模的指标参数包括产品性能参数、运行环境参数及规格参数，认知模块13可根据所分析的样本模型及其仿真运行结果之间的内在联系，获得样本模型中各电子元件的性能参数、运行环境参数及规格参数。借此，本申请的认知模块13可对样本模型的本质进行分析并理解，而不再是单纯、机械的作出判断。
建模模块14用于提供电路设计人员输入待建模的指标参数，并依据认知模块13的分析结果执行建模操作，以自动生成符合待建模的指标参数的电子产品模型。于本实施例中，建模模块14可依据认知模块13输出的分析结果而生成建模规则，并基于所生成的建模规则而自动建立电子产品模型。
图2是显示图1的基于人工智能的电子产品建模系统的不同实施例示意图。
于另一实施例中，本申请的建模模块14还具有融合单元141，如上所述，本申请的接收模块11可接收不同类型的样本模型，因此，当分析电路设计人员所输入的待建模的指标参数中包含了不同类型的样本模型时，融合单元141可分别从各样本模型中分别提取符合待建模的指标参数的部分模型，并融合所提取的各个部分模型，从而建立完全符合待建模的指标参数的电子产品模型。
于另一实施例中，本申请的基于人工智能的电子产品建模系统10还包括有优化模块15，其用于分析建模模块14所建立的电子产品模型是否符合电路设计人员所述的待建模的指标参数，并依据分析结果不断优化建模模块14的建模规则。例如，优化模块15用于分析建模模块14所建立的电子产品模型是否符合电路设计人员所述的待建模的指标参数，当判断结果为不符合时，则进一步分析建模模块14当前所建立的电子产品模型的仿真运行结果是否较前一次所 建立的电子产品模型更为接近待建模的指标参数，若判断结果为是，则输出一正向反馈信号，反之，则输出负向反馈信号，并依据所述的正向反馈信号或负向反馈信号而更新建模模块14的建模规则，以借由优化模块15与建模模块14之间的交互，使得建模模块14生成最优化的建模规则。
图3是根据本申请的另一实施例所示的基于人工智能的电子产品建模方法的基本流程示意图。如图所示，首先进行步骤S31的感知步骤，以接收样本模型，并仿真运行所述样本模型，以生成仿真运行结果，接着进行步骤S32。
步骤S32，执行认知步骤以分析所述样本模型及所述仿真运行结果之间的内在联系，据以生成分析结果，接着进行步骤S33。具体而言，本申请的认知步骤可根据所分析的样本模型及仿真运行结果之间的内在联系，获得样本模型中各电子元件的性能参数、运行环境参数及规格参数。
步骤S33，执行建模步骤，以输入待建模的指标参数，并依据步骤S32所生成的分析结果执行建模操作，以自动建立符合待建模的指标参数的电子产品模型。于本实施例中，前述建模步骤可依据前述认知步骤所输出的分析结果，而生成相应的建模规则，并基于所生成的建模规则，自动建立符合待建模的指标参数的电子产品模型。再者，于建模步骤中所输入的待建模的指标参数可包括产品性能参数、运行环境参数及规格参数。
此外，于其他实施例中，本申请在执行感知步骤的过程中，可接收不同类型的样本模型，例如通过将不同类型的电子产品数据输入已知的建模工具而得到多个不同类型的电子产品模型。有鉴于此，本申请所执行的建模步骤还可包括当分析所输入的待建模的指标参数来自不同类型的所述样本模型时，分别从各样本模型中提取符合待建模的指标参数的部分模型，并融合所提取的各个部分模型，以最终建立完全符合待建模的指标参数的电子产品模型。
再者，于又一实施例中，本申请的方法还包括执行优化步骤，通过分析所述建模步骤所建立的电子产品模型是否符合所述待建模的指标参数，以根据分析结果更新建模规则，并依据更新后的建模规则，重复执行步骤S33，从而最终建立符合待建模的指标参数的电子产品模型。
具体而言，优化步骤通过分析所建立的电子产品模型是否符合电路设计人员所述的待建模的指标参数，当判断结果为不符合时，则进一步分析当前所建立的电子产品模型的仿真运行结果是否较前一次所建立的电子产品模型更为接近待建模的指标参数，若判断为是，则输出一正向反馈信号，反之则输出负向反馈信号，并依据所输出的正向反馈信号或负向反馈信号而更新建模规则，从 而生成最优化的建模规则，并最终建立符合待建模的指标参数的电子产品模型。
综上所述，本申请的基于人工智能的电子产品建模系统及方法，利用人工智能协同电子产品模型生成设计框架，不仅能够实现自动化建模的技术功效，且本申请旨在减少与模型设计相关的决策过程中的复杂性，以利用人工智能方法将多种多样的决策归纳为多个一般化的、同质性的决策，因此，能够减少模型设计和实现过程中存在的风险和不确定性。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，所述计算机可读记录介质包括用于以计算机(例如计算机)可读的形式存储或传送信息的任何机制。例如，机器可读介质包括只读存储器(ROM)、随机存取存储器(RAM)、磁盘存储介质、光存储介质、闪速存储介质、电、光、声或其他形式的传播信号(例如，载波、红外信号、数字信号等)等，该计算机软件产品包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本申请实施例的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。
本领域的技术人员应明白，本发明实施例的实施例可提供为方法、装置(设备)、或计算机程序产品。因此，本发明实施例可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明实施例是参照根据本发明实施例的方法、装置(设备)和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。

Claims (10)

  1. 一种基于人工智能的电子产品建模系统，其特征在于，包括：
    接收模块，用于接收样本模型；
    感知模块，用于仿真运行所述样本模型，以生成仿真运行结果；
    认知模块，用于分析所述样本模型及其所述仿真运行结果之间的内在联系，据以生成分析结果；以及
    建模模块，用于提供输入待建模的指标参数，并依据所述分析结果执行建模操作，以自动建立符合所述待建模的指标参数的电子产品模型。
  2. 根据权利要求1所述的基于人工智能的电子产品建模系统，其特征在于，所述接收模块用于接收不同类型的样本模型，且所述建模模块还包括融合单元，用于当分析所输入的所述待建模的指标参数来自不同类型的所述样本模型时，分别从各所述样本模型中提取符合所述待建模的指标参数的部分模型，并融合所提取的所述部分模型，以建立所述电子产品模型。
  3. 根据权利要求1所述的基于人工智能的电子产品建模系统，其特征在于，所述待建模的指标参数包括产品性能参数、运行环境参数及规格参数，所述认知模块还包括根据所分析的所述样本模型及其所述仿真运行结果之间的内在联系，获得所述样本模型中各电子元件的性能参数、运行环境参数及规格参数。
  4. 根据权利要求1所述的基于人工智能的电子产品建模系统，其特征在于，所述建模模块还包括依据所述分析结果生成建模规则，并基于所述建模规则建立所述电子产品模型。
  5. 根据权利要求4所述的基于人工智能的电子产品建模系统，其特征在于，所述系统还包括优化模块，用于分析所述建模模块所建立的所述电子产品模型是否符合所述待建模的指标参数，并依据分析结果不断优化所述建模模块的建模规则。
  6. 一种基于人工智能的电子产品建模方法，其特征在于，包括：
    执行感知步骤，以接收样本模型，并仿真运行所述样本模型，以生成仿真 运行结果；
    执行认知步骤，以分析所述样本模型及所述仿真运行结果之间的内在联系，据以生成分析结果；以及
    执行建模步骤，以输入待建模的指标参数，并依据所述分析结果执行建模操作，以自动建立符合所述待建模的指标参数的电子产品模型。
  7. 根据权利要求6所述的基于人工智能的电子产品建模方法，其特征在于，所述感知步骤用于接收不同类型的样本模型，所述建模步骤还包括当分析所输入的所述待建模的指标参数来自不同类型的所述样本模型时，分别从各所述样本模型中提取符合所述待建模的指标参数的部分模型，并融合所提取的所述部分模型，以建立所述电子产品模型。
  8. 根据权利要求6所述的基于人工智能的电子产品建模方法，其特征在于，所述待建模的指标参数包括产品性能参数、运行环境参数及规格参数，所述认知步骤还包括根据所分析的所述样本模型及所述仿真运行结果之间的内在联系，获得所述样本模型中各电子元件的性能参数、运行环境参数及规格参数。
  9. 根据权利要求6所述的基于人工智能的电子产品建模方法，其特征在于，所述建模步骤依据所述认知步骤所输出的分析结果生成建模规则，并基于所述建模规则建立所述电子产品模型。
  10. 根据权利要求9所述的基于人工智能的电子产品建模方法，其特征在于，所述方法还包括执行优化步骤，通过分析所述建模步骤所建立的所述电子产品模型是否符合所述待建模的指标参数，以根据分析结果更新所述建模规则，并依据所述更新后的建模规则，重复执行所述建模步骤，以最终建立符合所述待建模的指标参数的电子产品模型。
PCT/CN2018/085639 2018-04-18 2018-05-04 基于人工智能的电子产品建模系统及方法 WO2019200625A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810350394.1A CN108595816B (zh) 2018-04-18 2018-04-18 基于人工智能的电子产品建模系统及方法
CN201810350394.1 2018-04-18

Publications (1)

Publication Number Publication Date
WO2019200625A1 true WO2019200625A1 (zh) 2019-10-24

Family

ID=63611154

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/085639 WO2019200625A1 (zh) 2018-04-18 2018-05-04 基于人工智能的电子产品建模系统及方法

Country Status (2)

Country Link
CN (1) CN108595816B (zh)
WO (1) WO2019200625A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102656090B1 (ko) * 2021-12-29 2024-04-11 주식회사 커넥트시스템 인공지능 모델 통합 관리 및 배포 시스템과 그 방법

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105787558A (zh) * 2016-04-11 2016-07-20 江苏科技大学 基于ads的知识神经网络微带滤波器设计方法
WO2017213857A1 (en) * 2016-06-10 2017-12-14 Apple Inc. System for iteratively training an artificial intelligence using cloud-based metrics
CN107479368A (zh) * 2017-06-30 2017-12-15 北京百度网讯科技有限公司 一种基于人工智能的训练无人机控制模型的方法及系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103279824A (zh) * 2013-05-22 2013-09-04 国家电网公司 一种继电保护整定计算系统的建模方法
CN106126838A (zh) * 2016-06-28 2016-11-16 合肥工业大学 一种徽州建筑智能营造系统
CN107133416B (zh) * 2017-05-24 2020-02-14 西北工业大学 一种uuv多层次混杂式免疫智能体结构建模方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105787558A (zh) * 2016-04-11 2016-07-20 江苏科技大学 基于ads的知识神经网络微带滤波器设计方法
WO2017213857A1 (en) * 2016-06-10 2017-12-14 Apple Inc. System for iteratively training an artificial intelligence using cloud-based metrics
CN107479368A (zh) * 2017-06-30 2017-12-15 北京百度网讯科技有限公司 一种基于人工智能的训练无人机控制模型的方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LI, BOHU ET AL.: "Preliminary study of modeling and simulation technology oriented to neo-type artificial intelligent systems", JOURNAL OF SYSTEM SIMULATION, vol. 30, no. 2, 28 February 2018 (2018-02-28), pages 349 - 360 *

Also Published As

Publication number Publication date
CN108595816A (zh) 2018-09-28
CN108595816B (zh) 2021-05-28

Similar Documents

Publication Publication Date Title
Lu et al. Neural architecture search as multiobjective optimization benchmarks: Problem formulation and performance assessment
CN113792937B (zh) 一种基于图神经网络的社交网络影响力预测方法、装置
CN110390017B (zh) 基于注意力门控卷积网络的目标情感分析方法及系统
CN110362814B (zh) 一种基于改进损失函数的命名实体识别方法及装置
CN108170739A (zh) 问题匹配方法、终端和计算机可读存储介质
US20200265353A1 (en) Intelligent workflow advisor for part design, simulation and manufacture
WO2019200626A1 (zh) 人工智能体训练系统及无源电路优化设计系统及方法
KR20200060238A (ko) 인공 지능 기반 제조 부품 설계
JP2020086566A (ja) 知識補完プログラム、知識補完方法および知識補完装置
WO2019200625A1 (zh) 基于人工智能的电子产品建模系统及方法
CN109255148B (zh) 力学产品设计方法及其系统
CN117574721B (zh) 一种工艺参数概率模型优化方法
JP2011096082A (ja) プログラム解析方法、プログラム解析プログラムおよびプログラム解析装置
CN117313552A (zh) 半导体器件建模方法、系统及电子设备
CN113420150A (zh) 威胁情报知识检测方法、装置、计算设备及存储介质
CN112150279A (zh) 一种基于多方计算的金融风险预测方法及预测系统
CN109657139B (zh) 网络事件传播的模拟方法、装置及设备
JP2018125632A (ja) トラフィック生成装置及びトラフィック生成方法
CN112633559B (zh) 一种基于动态图卷积神经网络的社交关系预测方法及系统
CN112633516B (zh) 性能预测和机器学习编译优化方法及装置
CN110738318B (zh) 网络结构运行时间评估及评估模型生成方法、系统和装置
CN114253853A (zh) 一种基于网络谱的软件故障定位方法
CN112346916A (zh) 测试方法、装置及相关产品
WO2019109589A1 (zh) 基于人工智能进行电路设计的方法及装置
TW202001610A (zh) 技能產生方法、裝置及電子設備

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18915648

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18915648

Country of ref document: EP

Kind code of ref document: A1