技术领域Technical Field
本申请实施例涉及车辆数据处理的技术领域，尤其涉及一种汽车控制器故障数据存储方法及系统。The embodiments of the present application relate to the technical field of vehicle data processing, and more particularly to a method and system for storing fault data of an automobile controller.
背景技术Background technique
随着汽车工业的飞速发展，尤其是电动汽车和智能网联汽车的兴起，汽车电子控制系统变得日益复杂，对车辆安全性和可靠性提出了更高要求。汽车控制器，作为车辆电子系统的核心组件，负责监控和调节各种传感器输入、执行器动作及动力系统状态，其性能直接关系到车辆运行的安全与效率。然而，在复杂多变的运行环境中，汽车控制器可能会遭遇各种故障，包括硬件损坏、软件错误或外界干扰引起的异常。With the rapid development of the automotive industry, especially the rise of electric vehicles and intelligent connected vehicles, automotive electronic control systems have become increasingly complex, placing higher demands on vehicle safety and reliability. As the core component of the vehicle's electronic system, the automotive controller is responsible for monitoring and regulating various sensor inputs, actuator actions, and power system status. Its performance is directly related to the safety and efficiency of vehicle operation. However, in a complex and changing operating environment, the automotive controller may encounter various faults, including hardware damage, software errors, or abnormalities caused by external interference.
随着数据量的爆炸性增长，如何高效地存储和管理故障数据，确保关键信息不丢失，成为亟待解决的问题。With the explosive growth of data volume, how to efficiently store and manage fault data and ensure that key information is not lost has become an urgent problem to be solved.
当前，汽车电子系统中的数据处理大多仍采用简单的数据记录和事后分析模式，缺乏对数据的实时处理、智能筛选和高效压缩技术，导致大量宝贵的数据资源未能得到充分利用，数据存储和传输成本高昂，且数据安全性、隐私保护能力有限。At present, most data processing in automotive electronic systems still adopts a simple data recording and post-analysis mode, lacking real-time data processing, intelligent screening and efficient compression technology. As a result, a large amount of valuable data resources are not fully utilized, data storage and transmission costs are high, and data security and privacy protection capabilities are limited.
发明内容Summary of the invention
本申请实施例提供一种汽车控制器故障数据存储方法及系统，用以解决汽车控制器故障数据存储的成本较高且效率较低的问题。The embodiments of the present application provide a method and system for storing automobile controller fault data, which are used to solve the problem of high cost and low efficiency of storing automobile controller fault data.
第一方面，本申请实施例中提供了一种汽车控制器故障数据存储，包括：获取汽车控制器的历史故障数据序列，其中，所述历史故障数据序列包括多个历史故障数据，每个历史故障数据中至少包括以下参数：故障代码，系统状态参数，时间戳和所述汽车控制器操作历史记录；利用神经网络模型，对所述历史故障数据序列进行筛选，得到筛选后的历史故障数据序列；利用所述筛选后的历史故障数据序列对VAE模型进行训练，得到训练后的VAE模型，其中，所述VAE模型用于对历史故障数据序列进行压缩；在获取到所述汽车控制器的当前故障数据序列后，利用所述神经网络模型对所述当前故障数据序列进行筛选，得到筛选后的当前故障数据序列；将所述筛选后的当前故障数据序列输入所述训练后的VAE模型，得到压缩后的当前故障数据序列，并将所述压缩后的当前故障数据序列存储至分层存储系统，其中，所述分层存储系统包括：车载边缘计算单元，汽车本地存储器和云端数据中心。In a first aspect, an embodiment of the present application provides a vehicle controller fault data storage, including: obtaining a historical fault data sequence of the vehicle controller, wherein the historical fault data sequence includes multiple historical fault data, and each historical fault data includes at least the following parameters: fault code, system status parameter, timestamp and the vehicle controller operation history record; using a neural network model to filter the historical fault data sequence to obtain a filtered historical fault data sequence; using the filtered historical fault data sequence to train a VAE model to obtain a trained VAE model, wherein the VAE model is used to compress the historical fault data sequence; after obtaining the current fault data sequence of the vehicle controller, using the neural network model to filter the current fault data sequence to obtain a filtered current fault data sequence; inputting the filtered current fault data sequence into the trained VAE model to obtain a compressed current fault data sequence, and storing the compressed current fault data sequence in a hierarchical storage system, wherein the hierarchical storage system includes: an on-board edge computing unit, a vehicle local memory and a cloud data center.
进一步的，利用神经网络模型，对所述历史故障数据序列进行筛选，得到筛选后的历史故障数据序列，包括：将所述历史故障数据序列输入所述神经网络模型，以使所述神经网络模型确定出所述历史故障数据序列中任意两个参数之间的相关系数；将所述相关系数大于预设阈值的两个参数，确定为目标参数；基于所述历史故障数据对应的目标参数，构建所述筛选后的历史故障数据序列；所述相关系数的计算公式为：；其中，为所述相关系数，为第个参数在第次采样时的采样值，为第个参数在第次采样时的采样值，为所述历史故障数据序列中历史故障数据的数量，为所述历史故障数据序列中第个参数的平均值，为所述历史故障数据序列中第个参数的平均值。Furthermore, the historical fault data sequence is screened using a neural network model to obtain a screened historical fault data sequence, including: inputting the historical fault data sequence into the neural network model so that the neural network model determines the correlation coefficient between any two parameters in the historical fault data sequence; determining the two parameters whose correlation coefficients are greater than a preset threshold as target parameters; constructing the screened historical fault data sequence based on the target parameters corresponding to the historical fault data; the calculation formula of the correlation coefficient is: ;in, is the correlation coefficient, For the The parameters in The sampling value at the time of sampling, For the The parameters in The sampling value at the time of sampling, is the number of historical fault data in the historical fault data sequence, is the number in the historical fault data sequence The average value of the parameters, is the number in the historical fault data sequence The average value of the parameters.
进一步的，所述VAE模型包括：编码器，重参数化模块和解码器，利用所述筛选后的历史故障数据序列对VAE模型进行训练，得到训练后的VAE模型，包括：将所述筛选后的历史故障数据序列输入所述编码器中，以使所述编码器将所述筛选后的历史故障数据序列映射至低维隐空间，得到映射后的历史故障数据序列；将所述映射后的历史故障数据序列输入所述重参数化模块，确定出所述映射后的历史故障数据序列的隐变量；将所述映射后的历史故障数据序列的隐变量输入所述解码器中，以使所述解码器对所述映射后的历史故障数据序列的隐变量进行重建，得到重建后的历史故障数据序列；基于所述重建后的历史故障数据序列和筛选后的历史故障数据序列，计算出损失函数值，并基于所述损失函数值对所述VAE模型进行训练，得到所述训练后的VAE模型；所述损失函数值的计算公式为：；其中，为所述损失函数值，为重构损失，为KL散度损失， ，，， 和为超参数，为稀疏性正则化项，为鲁棒性损失，为自适应正则化项，为所述筛选后的历史故障数据序列对应的时间序列一致性损失。Furthermore, the VAE model includes: an encoder, a reparameterization module and a decoder. The VAE model is trained using the screened historical fault data sequence to obtain a trained VAE model, including: inputting the screened historical fault data sequence into the encoder so that the encoder maps the screened historical fault data sequence to a low-dimensional latent space to obtain a mapped historical fault data sequence; inputting the mapped historical fault data sequence into the reparameterization module to determine the latent variables of the mapped historical fault data sequence; inputting the latent variables of the mapped historical fault data sequence into the decoder so that the decoder reconstructs the latent variables of the mapped historical fault data sequence to obtain a reconstructed historical fault data sequence; based on the reconstructed historical fault data sequence and the screened historical fault data sequence, calculating the loss function value, and training the VAE model based on the loss function value to obtain the trained VAE model; the calculation formula of the loss function value is: ;in, is the loss function value, is the reconstruction loss, is the KL divergence loss, , , , and is a hyperparameter, is the sparsity regularization term, is the robustness loss, is the adaptive regularization term, is the time series consistency loss corresponding to the filtered historical fault data series.
进一步的，将所述筛选后的当前故障数据序列输入所述训练后的VAE模型，得到压缩后的当前故障数据序列，包括：将所述筛选后的当前故障数据序列输入所述训练后的VAE模型的编码器，得到映射后的当前故障数据序列；将所述映射后的当前故障数据序列输入所述训练后的VAE模型的重参数化模块，得到所述映射后的当前故障数据序列的隐变量；将所述映射后的当前故障数据序列的隐变量，确定为压缩后的当前故障数据序列。Furthermore, the screened current fault data sequence is input into the trained VAE model to obtain a compressed current fault data sequence, including: inputting the screened current fault data sequence into the encoder of the trained VAE model to obtain a mapped current fault data sequence; inputting the mapped current fault data sequence into the reparameterization module of the trained VAE model to obtain latent variables of the mapped current fault data sequence; and determining the latent variables of the mapped current fault data sequence as the compressed current fault data sequence.
进一步的，将所述压缩后的当前故障数据序列存储至分层存储系统，包括：对所述压缩后的当前故障数据序列进行加密处理，得到加密后的当前故障数据序列；利用实时同步算法，将所述加密后的当前故障数据序列存储至所述分层存储系统。Furthermore, the compressed current fault data sequence is stored in a hierarchical storage system, including: encrypting the compressed current fault data sequence to obtain an encrypted current fault data sequence; and using a real-time synchronization algorithm to store the encrypted current fault data sequence in the hierarchical storage system.
进一步的，对所述压缩后的当前故障数据序列进行加密处理，得到加密后的当前故障数据序列，包括：选择一个256位的密钥；利用AES-256算法对压缩后的当前故障数据序列进行加密处理，得到加密后的当前故障数据序。Furthermore, the compressed current fault data sequence is encrypted to obtain an encrypted current fault data sequence, including: selecting a 256-bit key; and encrypting the compressed current fault data sequence using an AES-256 algorithm to obtain an encrypted current fault data sequence.
进一步的，所述编码器的映射表达式为： ；其中，为带有参数的编码器网络，为所述筛选后的历史故障数据序列，为隐变量的均值，为隐变量的方差；所述重参数化模块的重参数化表达式为：；其中，为隐变量，为标准正态分布中抽样的噪声；所述解码器的数据重建表达式为：；其中，为所述重建后的历史故障数据序列，为带有参数的解码器网络。Furthermore, the mapping expression of the encoder is: ;in, For parameters The encoder network, is the filtered historical fault data sequence, is the mean of the latent variable, is the variance of the latent variable; the reparameterization expression of the reparameterization module is: ;in, is a hidden variable, is the noise sampled from the standard normal distribution; the data reconstruction expression of the decoder is: ;in, is the reconstructed historical fault data sequence, For parameters The decoder network.
第二方面，本申请实施例提供了一种汽车控制器故障数据存储系统，包括：获取单元，用于获取汽车控制器的历史故障数据序列，其中，所述历史故障数据序列包括多个历史故障数据，每个历史故障数据中至少包括以下参数：故障代码，系统状态参数，时间戳和所述汽车控制器操作历史记录；第一筛选单元，用于利用神经网络模型，对所述历史故障数据序列进行筛选，得到筛选后的历史故障数据序列；训练单元，用于利用所述筛选后的历史故障数据序列对VAE模型进行训练，得到训练后的VAE模型，其中，所述VAE模型用于对历史故障数据序列进行压缩；第二筛选单元，在获取到所述汽车控制器的当前故障数据序列后，利用所述神经网络模型对所述当前故障数据序列进行筛选，得到筛选后的当前故障数据序列；压缩存储单元，用于将所述筛选后的当前故障数据序列输入所述训练后的VAE模型，得到压缩后的当前故障数据序列，并将所述压缩后的当前故障数据序列存储至分层存储系统，其中，所述分层存储系统包括：车载边缘计算单元，汽车本地存储器和云端数据中心。In a second aspect, an embodiment of the present application provides a vehicle controller fault data storage system, comprising: an acquisition unit, used to acquire a historical fault data sequence of a vehicle controller, wherein the historical fault data sequence includes multiple historical fault data, and each historical fault data includes at least the following parameters: fault code, system status parameter, timestamp and the vehicle controller operation history record; a first screening unit, used to use a neural network model to screen the historical fault data sequence to obtain a screened historical fault data sequence; a training unit, used to use the screened historical fault data sequence to train a VAE model to obtain a trained VAE model, wherein the VAE model is used to compress the historical fault data sequence; a second screening unit, after acquiring the current fault data sequence of the vehicle controller, uses the neural network model to screen the current fault data sequence to obtain a screened current fault data sequence; a compression storage unit, used to input the screened current fault data sequence into the trained VAE model to obtain a compressed current fault data sequence, and store the compressed current fault data sequence in a hierarchical storage system, wherein the hierarchical storage system includes: an on-board edge computing unit, a vehicle local memory and a cloud data center.
第三方面，本申请实施例提供了一种计算设备，包括处理组件以及存储组件；所述存储组件存储一个或多个计算机指令；所述一个或多个计算机指令用以被所述处理组件调用执行，实现如上述第一方面所述的方法。In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the method described in the first aspect above.
第四方面，本申请实施例提供了一种计算机存储介质，存储有计算机程序，所述计算程序被计算机执行时，实现如上述第一方面所述的方法。In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements the method described in the first aspect above.
在本发明实施例中，通过人工智能的智能筛选机制减少数据冗余，采用多级存储体系和云边协同技术保证数据的可靠性和即时性，同时利用先进的加密技术确保数据的安全性与隐私保护。通过这样的技术革新了优化存储资源，为未来的自动驾驶和远程车辆健康管理奠定坚实基础。In the embodiment of the present invention, the intelligent screening mechanism of artificial intelligence is used to reduce data redundancy, a multi-level storage system and cloud-edge collaborative technology are used to ensure data reliability and immediacy, and advanced encryption technology is used to ensure data security and privacy protection. Such technological innovation optimizes storage resources and lays a solid foundation for future autonomous driving and remote vehicle health management.
本申请的这些方面或其他方面在以下实施例的描述中会更加简明易懂。These and other aspects of the present application will be more clearly understood in the description of the following embodiments.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
图1为本申请实施例提供的一种汽车控制器故障数据存储方法的流程图；FIG1 is a flow chart of a method for storing fault data of an automobile controller provided by an embodiment of the present application;
图2为本申请实施例提供的一种汽车控制器故障数据存储系统的示意图；FIG2 is a schematic diagram of a vehicle controller fault data storage system provided by an embodiment of the present application;
图3为本申请实施例提供的一种计算设备的示意图。FIG3 is a schematic diagram of a computing device provided in an embodiment of the present application.
具体实施方式Detailed ways
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合附图对本发明的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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.
实施例一：Embodiment 1:
根据本发明实施例，提供了一种汽车控制器故障数据存储方法的实施例，需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。According to an embodiment of the present invention, an embodiment of a method for storing fault data of an automobile controller is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
图1是根据本发明实施例的一种汽车控制器故障数据存储方法的流程图，如图1所示，该方法包括如下步骤：FIG. 1 is a flow chart of a method for storing fault data of an automobile controller according to an embodiment of the present invention. As shown in FIG. 1 , the method comprises the following steps:
步骤S102，获取汽车控制器的历史故障数据序列，其中，所述历史故障数据序列包括多个历史故障数据，每个历史故障数据中至少包括以下参数：故障代码，系统状态参数，时间戳和所述汽车控制器操作历史记录；Step S102, obtaining a historical fault data sequence of the automobile controller, wherein the historical fault data sequence includes a plurality of historical fault data, and each historical fault data includes at least the following parameters: a fault code, a system status parameter, a timestamp, and a historical record of the operation of the automobile controller;
在本发明实施例中，首先，从车辆维护记录和实时监控系统中收集过去一年的汽车控制器故障数据序列，每条数据包含故障代码（如P0300代表随机/多缸失火）、系统状态参数（如发动机转速、燃油压力）、时间戳以及控制器的操作历史记录（如执行的故障恢复尝试次数）。In an embodiment of the present invention, first, a series of automobile controller fault data for the past year is collected from vehicle maintenance records and real-time monitoring systems, and each data contains a fault code (such as P0300 representing random/multi-cylinder misfire), system status parameters (such as engine speed, fuel pressure), timestamp, and controller operation history (such as the number of fault recovery attempts performed).
优选的，还可以在获取到历史故障数据序列之后，对数据进行清洗和标准化处理，确保数据格式一致性和数值范围适配模型输入要求。Preferably, after obtaining the historical fault data sequence, the data may be cleaned and standardized to ensure data format consistency and numerical range adaptation to model input requirements.
步骤S104，利用神经网络模型，对所述历史故障数据序列进行筛选，得到筛选后的历史故障数据序列；Step S104, using a neural network model to filter the historical fault data sequence to obtain a filtered historical fault data sequence;
在本发明实施例中，可以设计一个神经网络模型，用于识别并筛选出对故障诊断最为关键的历史故障数据，从而构建筛选后的历史故障数据序列。In an embodiment of the present invention, a neural network model may be designed to identify and filter out historical fault data that is most critical to fault diagnosis, thereby constructing a filtered historical fault data sequence.
利用神经网络对数据进行筛选，可以基于历史数据学习出故障诊断中真正关键的特征，去除无关紧要的信息，提高数据处理的针对性和效率。By using neural networks to filter data, we can learn the truly critical features in fault diagnosis based on historical data, remove irrelevant information, and improve the pertinence and efficiency of data processing.
步骤S106，利用所述筛选后的历史故障数据序列对VAE模型进行训练，得到训练后的VAE模型，其中，所述VAE模型用于对历史故障数据序列进行压缩；Step S106, training a VAE model using the screened historical fault data sequence to obtain a trained VAE model, wherein the VAE model is used to compress the historical fault data sequence;
在本发明实施例中，利用筛选后的历史故障数据序列训练变分自动编码器（VAE），优化编码器和解码器网络结构，确保在保持数据主要特征的同时，实现高效压缩。In an embodiment of the present invention, a variational autoencoder (VAE) is trained using a filtered historical fault data sequence to optimize the encoder and decoder network structures, thereby ensuring efficient compression while maintaining the main features of the data.
训练完成后，VAE模型能够将高维故障数据编码成低维隐向量，显著减少存储空间需求。After training, the VAE model can encode high-dimensional fault data into low-dimensional latent vectors, significantly reducing storage space requirements.
VAE通过学习数据的低维表示，实现了数据的高效压缩，这对于存储资源有限的车载环境尤为重要，同时保持了数据重构的可能性，便于后续分析和诊断。VAE achieves efficient data compression by learning a low-dimensional representation of the data, which is particularly important in a vehicle environment with limited storage resources, while maintaining the possibility of data reconstruction for subsequent analysis and diagnosis.
步骤S108，在获取到所述汽车控制器的当前故障数据序列后，利用所述神经网络模型对所述当前故障数据序列进行筛选，得到筛选后的当前故障数据序列；Step S108, after acquiring the current fault data sequence of the vehicle controller, using the neural network model to filter the current fault data sequence to obtain a filtered current fault data sequence;
在本发明实施例中，当车辆运行中检测到新的故障数据时，先通过已训练的神经网络模型对其进行筛选，去除冗余或不关键的数据。In an embodiment of the present invention, when new fault data is detected during vehicle operation, it is first screened using a trained neural network model to remove redundant or uncritical data.
筛选后的当前故障数据序列送入VAE模型进行压缩，生成低维、高效的压缩数据表示。The filtered current fault data sequence is sent to the VAE model for compression to generate a low-dimensional and efficient compressed data representation.
压缩后的数据首先存储在车载边缘计算单元的高速缓存中，确保在极端情况下数据不丢失。The compressed data is first stored in the cache of the on-board edge computing unit to ensure that the data is not lost in extreme cases.
数据随后异步上传至汽车本地存储器，作为中期备份，并通过加密通道实时同步至云端数据中心，利用区块链技术保证数据的不可篡改性和可追溯性。The data is then asynchronously uploaded to the car's local storage as a mid-term backup and synchronized to the cloud data center in real time through an encrypted channel, using blockchain technology to ensure the data's immutability and traceability.
云端数据中心作为最终存储和分析的场所，支持远程故障诊断、数据分析及预防性维护策略的制定。As the final storage and analysis location, the cloud data center supports remote fault diagnosis, data analysis, and the formulation of preventive maintenance strategies.
步骤S110，将所述筛选后的当前故障数据序列输入所述训练后的VAE模型，得到压缩后的当前故障数据序列，并将所述压缩后的当前故障数据序列存储至分层存储系统，其中，所述分层存储系统包括：车载边缘计算单元，汽车本地存储器和云端数据中心。Step S110, input the screened current fault data sequence into the trained VAE model to obtain a compressed current fault data sequence, and store the compressed current fault data sequence in a hierarchical storage system, wherein the hierarchical storage system includes: an on-board edge computing unit, a local vehicle storage, and a cloud data center.
结合车载边缘计算、本地存储和云端数据中心的分层存储策略，确保了数据的安全性、可靠性和即时可用性，适应车辆在各种网络条件下的数据管理需求。The tiered storage strategy that combines on-board edge computing, local storage, and cloud data centers ensures data security, reliability, and immediate availability, and adapts to vehicle data management needs under various network conditions.
在本发明实施例中，利用神经网络模型，对所述历史故障数据序列进行筛选，得到筛选后的历史故障数据序列，包括：In an embodiment of the present invention, the historical fault data sequence is screened using a neural network model to obtain a screened historical fault data sequence, including:
将所述历史故障数据序列输入所述神经网络模型，以使所述神经网络模型确定出所述历史故障数据序列中任意两个参数之间的相关系数；Inputting the historical fault data sequence into the neural network model so that the neural network model determines the correlation coefficient between any two parameters in the historical fault data sequence;
将所述相关系数大于预设阈值的两个参数，确定为目标参数；Determine the two parameters whose correlation coefficients are greater than a preset threshold as target parameters;
基于所述历史故障数据对应的目标参数，构建所述筛选后的历史故障数据序列；Based on the target parameters corresponding to the historical fault data, construct the filtered historical fault data sequence;
所述相关系数的计算公式为：The calculation formula of the correlation coefficient is:
； ;
其中，为所述相关系数，为第个参数在第次采样时的采样值，为第个参数在第次采样时的采样值，为所述历史故障数据序列中历史故障数据的数量，为所述历史故障数据序列中第个参数的平均值，为所述历史故障数据序列中第个参数的平均值。in, is the correlation coefficient, For the The parameters in The sampling value at the time of sampling, For the The parameters in The sampling value at the time of sampling, is the number of historical fault data in the historical fault data sequence, is the number in the historical fault data sequence The average value of the parameters, is the number in the historical fault data sequence The average value of the parameters.
具体的，上述神经网络模型可以为卷积神经网络或循环神经网络，通过神经网络模型对历史故障数据序列进行筛选后，存储的数据量大幅减少，例如原本需要存储历史故障数据序列为，筛选后仅存储，<1，利用先进的AI算法智能筛选数据，有效优化存储资源，同时确保关键故障信息的准确获取，体现了自适应数据捕获与智能筛选的核心价值。Specifically, the neural network model can be a convolutional neural network or a recurrent neural network. After the historical fault data sequence is screened by the neural network model, the amount of stored data is greatly reduced. For example, the historical fault data sequence originally required to be stored is , after filtering, only store , <1. Using advanced AI algorithms to intelligently filter data, effectively optimizing storage resources while ensuring accurate acquisition of key fault information, embodying the core value of adaptive data capture and intelligent filtering.
在本发明实施例中，所述VAE模型包括：编码器，重参数化模块和解码器，利用所述筛选后的历史故障数据序列对VAE模型进行训练，得到训练后的VAE模型，包括：In an embodiment of the present invention, the VAE model includes: an encoder, a reparameterization module and a decoder. The VAE model is trained using the filtered historical fault data sequence to obtain a trained VAE model, including:
将所述筛选后的历史故障数据序列输入所述编码器中，以使所述编码器将所述筛选后的历史故障数据序列映射至低维隐空间，得到映射后的历史故障数据序列；Inputting the filtered historical fault data sequence into the encoder, so that the encoder maps the filtered historical fault data sequence to a low-dimensional latent space to obtain a mapped historical fault data sequence;
将所述映射后的历史故障数据序列输入所述重参数化模块，确定出所述映射后的历史故障数据序列的隐变量；Inputting the mapped historical fault data sequence into the re-parameterization module to determine the latent variables of the mapped historical fault data sequence;
将所述映射后的历史故障数据序列的隐变量输入所述解码器中，以使所述解码器对所述映射后的历史故障数据序列的隐变量进行重建，得到重建后的历史故障数据序列；Inputting the latent variables of the mapped historical fault data sequence into the decoder, so that the decoder reconstructs the latent variables of the mapped historical fault data sequence to obtain a reconstructed historical fault data sequence;
基于所述重建后的历史故障数据序列和筛选后的历史故障数据序列，计算出损失函数值，并基于所述损失函数值对所述VAE模型进行训练，得到所述训练后的VAE模型；Based on the reconstructed historical fault data sequence and the screened historical fault data sequence, a loss function value is calculated, and the VAE model is trained based on the loss function value to obtain the trained VAE model;
所述损失函数值的计算公式为：The calculation formula of the loss function value is:
； ;
其中，为所述损失函数值，为重构损失，为KL散度损失，，，，和为超参数，为稀疏性正则化项，为鲁棒性损失，为自适应正则化项，为所述筛选后的历史故障数据序列对应的时间序列一致性损失。in, is the loss function value, is the reconstruction loss, is the KL divergence loss, , , , and is a hyperparameter, is the sparsity regularization term, is the robustness loss, is the adaptive regularization term, is the time series consistency loss corresponding to the filtered historical fault data series.
具体的，所述编码器的映射表达式为：Specifically, the mapping expression of the encoder is:
； ;
其中，为带有参数的编码器网络，为所述筛选后的历史故障数据序列，为隐变量的均值，为隐变量的方差；in, For parameters The encoder network, is the filtered historical fault data sequence, is the mean of the latent variable, is the variance of the latent variable;
所述重参数化模块的重参数化表达式为：The reparameterization expression of the reparameterization module is:
； ;
其中，为隐变量，为标准正态分布中抽样的噪声；in, is a hidden variable, is the noise sampled from the standard normal distribution;
所述解码器的数据重建表达式为：The data reconstruction expression of the decoder is:
； ;
其中，为所述重建后的历史故障数据序列，为带有参数的解码器网络。in, is the reconstructed historical fault data sequence, For parameters The decoder network.
衡量解码后的历史故障数据序列与原始历史故障数据序列之间的差异，例如使用均方误差(MSE)或交叉熵损失。 The difference between the decoded historical fault data sequence and the original historical fault data sequence is measured, for example, using mean square error (MSE) or cross entropy loss.
用于保持隐变量分布与先验分布的接近度，控制模型的复杂度。It is used to keep the distribution of latent variables close to the prior distribution and control the complexity of the model.
鼓励隐变量中的元素尽可能为零。这有助于提高历史故障数据序列压缩效率，因为零值可以不存储或以更高效的方式存储。 Encourage hidden variables The elements in are as zero as possible. This helps improve the efficiency of historical fault data series compression, because zero values can be not stored or stored in a more efficient way.
针对可能存在的噪声或异常值。可以通过最小化数据点到其所在类别的原型（如聚类中心）的距离来实现，增强模型对异常值的容忍度。 For possible noise or outliers, this can be achieved by minimizing the distance between the data point and the prototype of its category (such as the cluster center), thereby enhancing the model's tolerance to outliers.
在本发明实施例中，VAE不仅提供了高效的压缩方案，还具备自适应学习能力，可以根据故障数据的特性和分布进行优化，从而在保证数据压缩效率的同时，最大化重构质量，非常适合处理复杂且多样化的汽车控制器故障数据。In the embodiment of the present invention, VAE not only provides an efficient compression solution, but also has adaptive learning capabilities, and can be optimized according to the characteristics and distribution of fault data, thereby maximizing the reconstruction quality while ensuring data compression efficiency. It is very suitable for processing complex and diverse automotive controller fault data.
通过上述方式得到的训练后的VAE模型仅不仅考虑了基本的重构质量和模型复杂度，还深入考虑了数据的特殊性质，如时间序列的连续性、数据的不确定性及变化性，从而使得模型更加精准、高效且适应性强，更适合处理汽车控制器故障数据这类复杂应用场景。The trained VAE model obtained in the above way not only considers the basic reconstruction quality and model complexity, but also deeply considers the special properties of the data, such as the continuity of the time series, the uncertainty and variability of the data, so that the model is more accurate, efficient and adaptable, and more suitable for processing complex application scenarios such as automotive controller fault data.
在本发明实施例中，将所述压缩后的当前故障数据序列存储至分层存储系统，包括：In an embodiment of the present invention, storing the compressed current fault data sequence in a hierarchical storage system includes:
对所述压缩后的当前故障数据序列进行加密处理，得到加密后的当前故障数据序列；Encrypting the compressed current fault data sequence to obtain an encrypted current fault data sequence;
利用实时同步算法，将所述加密后的当前故障数据序列存储至所述分层存储系统。The encrypted current fault data sequence is stored in the hierarchical storage system using a real-time synchronization algorithm.
在本发明实施例中，得到压缩后的当前故障数据序列后，使用AES-256进行加密，选择一个256位的密钥然后应用AES-256算法对压缩后的当前故障数据序列进行加密，得到加密后的当前故障数据序列。In an embodiment of the present invention, after obtaining the compressed current fault data sequence, AES-256 is used for encryption, a 256-bit key is selected and then the AES-256 algorithm is applied to encrypt the compressed current fault data sequence to obtain an encrypted current fault data sequence.
得到加密后的当前故障数据序列既经过了压缩处理，又进行了高强度的加密，有效保护了数据的安全性和隐私性。The encrypted current fault data sequence has been compressed and highly encrypted, effectively protecting the security and privacy of the data.
在得到加密后的当前故障数据序列后，采用时间戳同步技术，确保边缘计算单元与云端数据的时间一致性，确保密后的当前故障数据序列的可靠存储与传输，有效提升了智能汽车数据管理的稳定性和安全性。After obtaining the encrypted current fault data sequence, timestamp synchronization technology is used to ensure the time consistency between the edge computing unit and the cloud data, and to ensure the reliable storage and transmission of the encrypted current fault data sequence, effectively improving the stability and security of smart car data management.
实施例二：Embodiment 2:
本发明实施例还提供了一种汽车控制器故障数据存储系统，该汽车控制器故障数据存储系统用于执行本发明实施例上述内容所提供的汽车控制器故障数据存储系统，以下是本发明实施例提供的汽车控制器故障数据存储系统的具体介绍。An embodiment of the present invention also provides an automobile controller fault data storage system, which is used to execute the automobile controller fault data storage system provided by the above content of the embodiment of the present invention. The following is a specific introduction to the automobile controller fault data storage system provided by the embodiment of the present invention.
如图2所示，图2为上述汽车控制器故障数据存储系统的示意图，该汽车控制器故障数据存储系统包括：As shown in FIG. 2 , FIG. 2 is a schematic diagram of the above-mentioned automobile controller fault data storage system, and the automobile controller fault data storage system includes:
获取单元10，用于获取汽车控制器的历史故障数据序列，其中，所述历史故障数据序列包括多个历史故障数据，每个历史故障数据中至少包括以下参数：故障代码，系统状态参数，时间戳和所述汽车控制器操作历史记录；An acquisition unit 10 is used to acquire a historical fault data sequence of an automobile controller, wherein the historical fault data sequence includes a plurality of historical fault data, and each historical fault data includes at least the following parameters: a fault code, a system status parameter, a timestamp, and a historical record of operation of the automobile controller;
第一筛选单元20，用于利用神经网络模型，对所述历史故障数据序列进行筛选，得到筛选后的历史故障数据序列；A first screening unit 20, configured to screen the historical fault data sequence using a neural network model to obtain a screened historical fault data sequence;
训练单元30，用于利用所述筛选后的历史故障数据序列对VAE模型进行训练，得到训练后的VAE模型，其中，所述VAE模型用于对历史故障数据序列进行压缩；A training unit 30, used to train a VAE model using the filtered historical fault data sequence to obtain a trained VAE model, wherein the VAE model is used to compress the historical fault data sequence;
第二筛选单元40，在获取到所述汽车控制器的当前故障数据序列后，利用所述神经网络模型对所述当前故障数据序列进行筛选，得到筛选后的当前故障数据序列；A second screening unit 40, after acquiring the current fault data sequence of the vehicle controller, screens the current fault data sequence using the neural network model to obtain a screened current fault data sequence;
压缩存储单元50，用于将所述筛选后的当前故障数据序列输入所述训练后的VAE模型，得到压缩后的当前故障数据序列，并将所述压缩后的当前故障数据序列存储至分层存储系统，其中，所述分层存储系统包括：车载边缘计算单元，汽车本地存储器和云端数据中心。The compression storage unit 50 is used to input the screened current fault data sequence into the trained VAE model to obtain a compressed current fault data sequence, and store the compressed current fault data sequence in a hierarchical storage system, wherein the hierarchical storage system includes: an on-board edge computing unit, a local vehicle memory and a cloud data center.
在本发明实施例中，通过人工智能的智能筛选机制减少数据冗余，采用多级存储体系和云边协同技术保证数据的可靠性和即时性，同时利用先进的加密技术确保数据的安全性与隐私保护。通过这样的技术革新了优化存储资源，为未来的自动驾驶和远程车辆健康管理奠定坚实基础。In the embodiment of the present invention, the intelligent screening mechanism of artificial intelligence is used to reduce data redundancy, a multi-level storage system and cloud-edge collaborative technology are used to ensure data reliability and immediacy, and advanced encryption technology is used to ensure data security and privacy protection. Such technological innovation optimizes storage resources and lays a solid foundation for future autonomous driving and remote vehicle health management.
实施例三：Embodiment three:
本发明实施例还提供了一种计算设备，用于执行上述实施例一中所述方法的程序，如图3所示，该计算设备可以包括存储组件41以及处理组件42；The embodiment of the present invention further provides a computing device for executing the program of the method described in the above embodiment 1. As shown in FIG3 , the computing device may include a storage component 41 and a processing component 42;
所述存储组件41存储一条或多条计算机指令，其中，所述一条或多条计算机指令供所述处理组件42调用执行。The storage component 41 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 42 .
所述处理组件42可以包括一个或多个处理器来执行计算机指令，以完成实施例一的方法中的全部或部分步骤。当然处理组件也可以为一个或多个应用专用集成电路（ASIC）、数字信号处理器（DSP）、数字信号处理设备（DSPD）、可编程逻辑器件（PLD）、现场可编程门阵列（FPGA）、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。The processing component 42 may include one or more processors to execute computer instructions to complete all or part of the steps in the method of embodiment 1. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.
存储组件41被配置为存储各种类型的数据以支持在终端的操作。存储组件可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器（SRAM），电可擦除可编程只读存储器（EEPROM），可擦除可编程只读存储器（EPROM），可编程只读存储器（PROM），只读存储器（ROM），磁存储器，快闪存储器，磁盘或光盘。The storage component 41 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
显示组件43可以为电致发光(EL)元件、液晶显示器或具有类似结构的微型显示器、或者视网膜可直接显示或类似的激光扫描式显示器。The display component 43 may be an electroluminescent (EL) element, a liquid crystal display or a micro display having a similar structure, or a retinal direct display or a similar laser scanning display.
当然，计算设备必然还可以包括其他部件，例如输入/输出接口、通信组件等。Of course, a computing device may also include other components, such as input/output interfaces, communication components, etc.
输入/输出接口为处理组件和外围接口模块之间提供接口，上述外围接口模块可以是输出设备、输入设备等。The input/output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module can be an output device, an input device, etc.
通信组件被配置为便于计算设备和其他设备之间有线或无线方式的通信等。The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.
其中，该计算设备可以为物理设备或者云计算平台提供的弹性计算主机等，此时计算设备即可以是指云服务器，上述处理组件、存储组件等可以是从云计算平台租用或购买的基础服务器资源。Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.
实施例四：Embodiment 4:
本申请实施例还提供了一种计算机存储介质，存储有计算机程序，所述计算机程序被计算机执行时可以实现上述图1所示实施例的方法。The embodiment of the present application further provides a computer storage medium storing a computer program, which can implement the method of the embodiment shown in FIG. 1 when executed by a computer.
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
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单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。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。The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. 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 work.
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，如ROM/RAM、磁碟、光盘等，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。Through the description of the above implementation methods, 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, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM/RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
最后应说明的是：以上实施例仅用以说明本申请的技术方案，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。Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein with 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 application.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410781326.6ACN118363541A (en) | 2024-06-18 | 2024-06-18 | Automobile controller fault data storage method and system |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410781326.6ACN118363541A (en) | 2024-06-18 | 2024-06-18 | Automobile controller fault data storage method and system |
| Publication Number | Publication Date |
|---|---|
| CN118363541Atrue CN118363541A (en) | 2024-07-19 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410781326.6APendingCN118363541A (en) | 2024-06-18 | 2024-06-18 | Automobile controller fault data storage method and system |
| Country | Link |
|---|---|
| CN (1) | CN118363541A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263846A (en)* | 2019-06-18 | 2019-09-20 | 华北电力大学 | The method for diagnosing faults for being excavated and being learnt based on fault data depth |
| CN111666708A (en)* | 2019-03-08 | 2020-09-15 | 富士通株式会社 | Storage medium and data processing method |
| CN112087234A (en)* | 2019-06-12 | 2020-12-15 | 株式会社日立制作所 | Storage system and storage control method |
| CN113822437A (en)* | 2020-06-18 | 2021-12-21 | 辉达公司 | Deep Hierarchical Variational Autoencoders |
| CN116016592A (en)* | 2022-12-27 | 2023-04-25 | 锐兹行(上海)智能科技有限公司 | Automobile signal acquisition method and system based on edge calculation |
| CN116204138A (en)* | 2023-05-05 | 2023-06-02 | 成都三合力通科技有限公司 | Efficient storage system and method based on hierarchical storage |
| CN117131414A (en)* | 2023-07-31 | 2023-11-28 | 国电南瑞科技股份有限公司 | An energy storage safety early warning method and system based on rough sets and neural networks |
| CN117874141A (en)* | 2024-01-18 | 2024-04-12 | 苏州辰瓴光学有限公司 | Management method, system and storage medium for data in cloud primary environment |
| CN117937962A (en)* | 2023-12-13 | 2024-04-26 | 贵州电网有限责任公司 | Predictive configuration method and system for coping with open-circuit faults of AM-MMC change-over switch |
| US20240152756A1 (en)* | 2021-03-27 | 2024-05-09 | Intel Corporation | Streamlined development and deployment of autoencoders |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666708A (en)* | 2019-03-08 | 2020-09-15 | 富士通株式会社 | Storage medium and data processing method |
| CN112087234A (en)* | 2019-06-12 | 2020-12-15 | 株式会社日立制作所 | Storage system and storage control method |
| CN110263846A (en)* | 2019-06-18 | 2019-09-20 | 华北电力大学 | The method for diagnosing faults for being excavated and being learnt based on fault data depth |
| CN113822437A (en)* | 2020-06-18 | 2021-12-21 | 辉达公司 | Deep Hierarchical Variational Autoencoders |
| US20240152756A1 (en)* | 2021-03-27 | 2024-05-09 | Intel Corporation | Streamlined development and deployment of autoencoders |
| CN116016592A (en)* | 2022-12-27 | 2023-04-25 | 锐兹行(上海)智能科技有限公司 | Automobile signal acquisition method and system based on edge calculation |
| CN116204138A (en)* | 2023-05-05 | 2023-06-02 | 成都三合力通科技有限公司 | Efficient storage system and method based on hierarchical storage |
| CN117131414A (en)* | 2023-07-31 | 2023-11-28 | 国电南瑞科技股份有限公司 | An energy storage safety early warning method and system based on rough sets and neural networks |
| CN117937962A (en)* | 2023-12-13 | 2024-04-26 | 贵州电网有限责任公司 | Predictive configuration method and system for coping with open-circuit faults of AM-MMC change-over switch |
| CN117874141A (en)* | 2024-01-18 | 2024-04-12 | 苏州辰瓴光学有限公司 | Management method, system and storage medium for data in cloud primary environment |
| Publication | Publication Date | Title |
|---|---|---|
| US12367423B2 (en) | System and method for ensuring that the results of machine learning models can be audited | |
| CN112508137B (en) | Transformer abnormality detection method and device, computer equipment and storage medium | |
| DE102021207269A1 (en) | METHOD AND SYSTEM FOR LEARNING PERTURBATION QUANTITIES IN MACHINE LEARNING | |
| CN116976441A (en) | Equipment failure prediction model training method, equipment failure prediction method and equipment failure prediction device | |
| CN117216689B (en) | Underground pipeline emission early warning system based on urban water conservancy data | |
| CN113112038B (en) | Intelligent monitoring and diagnostic analysis system, device, electronic equipment and storage medium | |
| CN119494751A (en) | Non-intrusive load monitoring method, device, computer equipment, readable storage medium and program product based on graph neural network | |
| CN115480551A (en) | Fault Diagnosis and Handling System Based on Dynamic Data Monitoring of Diesel Engine | |
| CN118363541A (en) | Automobile controller fault data storage method and system | |
| JP2022535442A (en) | Methods and apparatus for facilitating storage of data from industrial automation control systems or power systems | |
| CN119578608A (en) | A distribution network equipment health prediction method, system, equipment and medium | |
| CN118336687A (en) | Bus load system based on cloud edge cooperation | |
| CN115791241B (en) | A method and device for diagnosing vibration faults of ship equipment based on compressed sensing | |
| CN120582692B (en) | Method, system, device and medium for evaluating fine granularity health degree of optical module | |
| CN120429773A (en) | Converter valve fault identification method, device, computer equipment and readable storage medium | |
| CN119944975B (en) | A control method and system for integrating smart electric meter with real-time monitoring of electric power system | |
| CN120634504A (en) | Hydropower station equipment operation and maintenance method, hydropower station equipment operation and maintenance device, computer equipment, storage medium and computer program product | |
| CN117277555A (en) | Distribution communication network operation and maintenance management and control methods, platforms and devices | |
| CN117135068A (en) | Network traffic prediction method, device, computer equipment and storage medium | |
| CN120653907A (en) | Device operation data processing method and computer device | |
| CN119990087A (en) | A hydroelectric power plant intelligent reporting system, method, server and storage medium | |
| KR20230061864A (en) | Apparatus for imputating greenhouse environment data based on two-dimensional convolutional neural network for data integrity and method thereof | |
| CN119225334A (en) | A production line fault detection method and device based on industrial Internet of Things | |
| CN118568308A (en) | Industrial Internet of things data processing method, device and medium based on low codes | |
| CN115809866A (en) | Wind power plant fault early warning method and device, computer equipment and medium |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20240719 | |
| RJ01 | Rejection of invention patent application after publication |