CN113849203A - Internet of things terminal upgrade system and method - Google Patents

Internet of things terminal upgrade system and method Download PDF

Info

Publication number
CN113849203A
CN113849203A CN202110150873.0A CN202110150873A CN113849203A CN 113849203 A CN113849203 A CN 113849203A CN 202110150873 A CN202110150873 A CN 202110150873A CN 113849203 A CN113849203 A CN 113849203A
Authority
CN
China
Prior art keywords
data
terminal
model
upgrade
internet
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN202110150873.0A
Other languages
Chinese (zh)
Inventor
王祥
武占侠
魏本海
洪海敏
吴在军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Information and Telecommunication Co Ltd
China Gridcom Co Ltd
Original Assignee
State Grid Information and Telecommunication Co Ltd
China Gridcom Co Ltd
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 State Grid Information and Telecommunication Co Ltd, China Gridcom Co Ltd filed Critical State Grid Information and Telecommunication Co Ltd
Priority to CN202110150873.0A priority Critical patent/CN113849203A/en
Publication of CN113849203A publication Critical patent/CN113849203A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/60—Software deployment
    • G06F8/65—Updates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/906—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Security & Cryptography (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

本发明提供物联网终端升级策略的方法，涉及物联网技术领域，若干个物联网终端定时采集数据并实时将数据发送给物联管理平台；物联管理平台接收若干个所述物联网终端发送的数据进行过滤并以物联网的终端ID为计算目标分类整理成格式化数据存储至模型训练平台的数据库中；模型训练平台调用数据库中格式化数据作为样本数据集执行训练任务，并将完成训练的升级模型发送至物联管理平台；物联管理平台将升级模型发布给各个物联网终端进行升级，并将升级日志传输至物联管理平台。本发明基于线性回归分析算法，训练出升级模型，升级模型可通过不断自学习进行优化完善，同时与平台进行交互，实现每个物联网终端由各自独立升级策略。

Figure 202110150873

The invention provides a method for upgrading a terminal of the Internet of Things, and relates to the technical field of the Internet of Things. Several Internet of Things terminals regularly collect data and send the data to an Internet of Things management platform in real time; The data is filtered and sorted into formatted data with the terminal ID of the Internet of Things as the calculation target and stored in the database of the model training platform; the model training platform calls the formatted data in the database as a sample data set to perform training tasks, and will complete the training. The upgrade model is sent to the IoT management platform; the IoT management platform releases the upgrade model to each IoT terminal for upgrade, and transmits the upgrade log to the IoT management platform. Based on the linear regression analysis algorithm, the invention trains an upgrade model, and the upgrade model can be optimized and perfected through continuous self-learning, and interacts with the platform at the same time to realize the independent upgrade strategy of each Internet of Things terminal.

Figure 202110150873

Description

Internet of things terminal upgrading system and method
Technical Field
The disclosure relates to the technical field of internet of things, in particular to a system and a method for upgrading a terminal of the internet of things.
Background
With the development of the internet of things industry and the exponential increase of application software of the internet of things terminal, terminal services are continuously increased, software installation and upgrading become an urgent need, and a large batch of software upgrading needs to have high concurrency capability of the system. The existing technology is mainly based on an upgrading strategy of manually setting fixed time, occupies larger bandwidth in the upgrading process, causes certain influence on a system, and can cause service interruption of the operation of the terminal of the internet of things and fail to formulate personalized upgrading strategies aiming at different terminals.
Disclosure of Invention
The invention provides a method for upgrading a strategy of an Internet of things terminal aiming at the problems.
In order to solve at least one of the above technical problems, the present disclosure proposes the following technical solutions: the Internet of things terminal upgrading method comprises the following steps:
the method comprises the following steps that a plurality of internet of things terminals collect data regularly and send the data to an internet of things management platform in real time;
the Internet of things management platform receives data sent by a plurality of Internet of things terminals, filters the data, classifies and arranges the data into formatted data by taking terminal IDs of the Internet of things as calculation targets, and stores the formatted data into a database of the model training platform; the formatted data comprises a terminal ID, transmission time, a service data type, network delay time and a data packet size;
the model training platform calls formatted data in the database as a sample data set to execute a training task, and sends an upgrade model which completes training to the Internet of things management platform;
and the Internet of things management platform issues the upgrading model to each Internet of things terminal for processing, the Internet of things terminals use the upgrading model for upgrading, and the upgrading logs are transmitted to the Internet of things management platform.
In some embodiments, the method for filtering the data sent by the terminals of the internet of things by the internet of things management platform comprises the following steps of:
the method comprises the steps that an Internet of things management platform receives running log data of each Internet of things terminal;
the method comprises the steps that an Internet of things management platform collects self interactive log data and interactive network flow data with an Internet of things terminal;
performing matching association according to the running log data, the interactive network traffic data and the interactive log data so as to obtain a terminal ID required by a model training platform, and time, service type, network delay time and data packet size corresponding to the terminal ID;
and storing the acquired terminal ID, the transmission time corresponding to the terminal ID, the service data type, the network delay time and the data packet size into a database of a model training platform.
In some embodiments, the model training platform calls formatted data in the database as training data to perform a training task, comprising the steps of:
taking formatted data stored in a database as a sample data set, and dividing the data into independent variable data and dependent variable data, wherein the independent variable data comprises a terminal ID and a data packet size, a service data type and transmission time of each transmission corresponding to the terminal ID, and the dependent variable is network delay time;
selecting a plurality of data from the independent variable data and the dependent variable data as a training set, and using the rest data as a test set;
selecting a multiple linear regression analysis model, wherein the multiple linear regression analysis model is as follows:
Y＝b0+b1X1+b2X2+b3X3+b4X4+e
wherein, Y is set as a dependent variable network delay time, X1、X2、X3、X4Is independent variable, respectively terminal ID and data packet size, service data type and transmission time of each transmission corresponding to the terminal ID, and the independent variable and dependent variable are in linear relation, b0、b1、b2、b3、b4E is an error term for the parameter to be estimated;
training the multiple linear regression analysis model by using training set data to obtain a parameter b to be estimated0、b1、b2、b3、b4And the numerical value of the error item, and generating an upgrading model;
and verifying the upgrade model by adopting the data of the test set, if the upgrade model is a valid model, archiving, and otherwise finishing training.
In some embodiments, the method for processing the upgrade model by the internet of things management platform includes the following steps:
each Internet of things terminal receives an upgrading model issued by the Internet of things management platform and updates a terminal upgrading module according to the upgrading model;
after the updating is finished, informing the Internet of things management platform to release a terminal upgrading task to the Internet of things terminal for terminal upgrading;
and after the terminal finishes upgrading, uploading the upgrading log to an internet of things management platform for processing.
In some embodiments, after the terminal finishes upgrading, the upgrade log is uploaded to an internet of things management platform for processing, and the method includes the following steps:
the method comprises the steps that an Internet of things management platform receives an upgrade log uploaded by an Internet of things terminal in real time;
filtering and analyzing the data fed back from the upgrade log;
deciding whether to start an upgrade model update task by analyzing the accuracy data and the performance data; if the training task needs to be updated, starting a new training task, and if the training task does not need to be updated, terminating the feedback;
the updating specific implementation method comprises the following steps:
collecting accuracy data and performance data of the model application;
pushing the collected data, filtering the integrity and effectiveness of the data, and then performing classification, aggregation and statistical analysis;
according to the analysis result, a part of data is used for generating a user use report, and a part of available data is used for generating sample data;
and directly feeding back a user report, verifying the sample data according to the requirements of a formal sample, expanding the sample data to a sample data set after the sample data passes the requirements of the formal sample, and finally feeding back the data.
The invention also provides an Internet of things terminal upgrading system, which comprises an Internet of things management platform, a model training platform and at least one Internet of things terminal, wherein the at least one Internet of things terminal can be any Internet of things equipment which can be accessed to a network,
the Internet of things management platform is used for receiving data sent by the Internet of things terminal, filtering the data, classifying and sorting the data into formatted data by taking the terminal ID of the Internet of things as a calculation target, and storing the formatted data into a database of the model training platform; meanwhile, an upgrading model is issued to at least one Internet of things terminal, and an upgrading log of the Internet of things terminal is received for processing;
the Internet of things terminal sends data to the Internet of things management platform at regular time, receives an upgrade model issued by the Internet of things management platform at the same time, and feeds an upgrade result back to the Internet of things management platform;
the model training platform is configured to perform specific execution training tasks, train the model according to the formatted data of the IOT management platform to form an optimized upgrade model and send the optimized upgrade model to the IOT management platform.
In some embodiments, the internet of things management platform comprises:
the data collection module is used for completing data collection of the terminal of the Internet of things;
the data processing module is used for cleaning, filtering, analyzing and summarizing the acquired data, generating formatted data, storing the formatted data serving as a sample data set into a database of the model training platform and completing data preparation work;
and the model issuing module is used for receiving the model output by the model training platform, rapidly issuing the model and distributing the model to each Internet of things terminal.
In some embodiments, the internet of things terminal includes:
the terminal processing module is used for communicating with the Internet of things management platform and carrying out upgrade control on the Internet of things terminal according to the received information sent by the Internet of things management platform; the method comprises the following steps of updating a terminal upgrading module according to a model of a model publishing module, receiving a feedback message of the terminal upgrading module and sending the feedback message to a task publishing module of an Internet of things management platform;
the task issuing module is used for issuing the terminal upgrading task to the terminal processing module after receiving the message that the terminal upgrading module completes updating, and then the terminal processing module executes the upgrading task.
In some embodiments, the model training platform comprises a platform processing module and a database in communication connection with the platform processing module, the processing module comprises a training unit, a verification unit and a database, the training unit is used for calling a part of sample data sets stored in the database to process the sample data sets to obtain a training data set, and an upgrade model is established according to the training data set;
and the verification unit is used for verifying the upgrade model by using data which is not acquired by the training module as a test data set, if the upgrade model is an effective model, archiving the upgrade model, and otherwise finishing the training.
In some embodiments, the specific method of building an upgrade model from the training data set comprises:
dividing a training data set into independent variable data and dependent variable data;
selecting a multiple linear regression analysis model, wherein the multiple linear regression analysis model is as follows:
Y＝b0+b1X1+b2X2+b3X3+b4X4+e
wherein, Y is set as a dependent variable network delay time, X1、X2、X3、X4As independent variables, respectively terminal ID and packet size, service data type and transmission time of each transmission corresponding to the terminal ID, and the independent variables and dependent variables are in linear relation, b0、b1、b2、b3、b4E is an error term for the parameter to be estimated;
training the multiple linear regression analysis model by using training set data to obtain a parameter b to be estimated0、b1、b2、b3、b4And the numerical value of the error term, and generating an upgrade model.
The beneficial effects of this disclosure are: the method is based on a linear regression analysis algorithm, an upgrading model is trained, the upgrading model can be optimized and perfected through continuous self-learning, and meanwhile, the upgrading model interacts with a platform, and the independent upgrading strategy of each internet of things terminal is achieved.
In addition, in the technical solutions of the present disclosure, the technical solutions can be implemented by adopting conventional means in the art, unless otherwise specified.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic structural diagram of an internet of things terminal upgrading system according to the present application;
fig. 2 is a flowchart of the internet of things terminal upgrading method.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below with reference to the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are merely illustrative of some, but not all, embodiments of the disclosure and are not to be considered as limiting the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1:
as shown in fig. 1-2, the method for upgrading the internet of things terminal includes the following steps:
s100, a plurality of Internet of things terminals acquire data regularly and send the data to an Internet of things management platform in real time;
s200, the Internet of things management platform receives data sent by a plurality of Internet of things terminals, filters the data, classifies and arranges the data into formatted data by taking terminal IDs of the Internet of things as calculation targets, and stores the formatted data into a database of a model training platform; the formatted data comprises a terminal ID, transmission time, a service data type, network delay time and a data packet size; specifically, the method takes the terminal ID as a calculation target, and arranges the start time, the end time, the network delay time, the service type of the transmission data and the size of the single transmission data packet.
S300, the model training platform calls formatted data in a database as a sample data set to execute a training task, and sends an upgrade model which completes training to the Internet of things management platform;
s400, the Internet of things management platform issues the upgrading model to each Internet of things terminal for processing, the Internet of things terminals use the upgrading model for upgrading, and the upgrading logs are transmitted to the Internet of things management platform.
Specifically, in step s200, the internet of things management platform receives data sent by a plurality of terminals of the internet of things, filters the data, classifies and arranges the data into formatted data by using terminal IDs of the internet of things as calculation targets, and stores the formatted data in a database of the model training platform, and the method includes the following steps:
s201, receiving running log data of each Internet of things terminal by an Internet of things management platform;
s202, receiving interactive network flow data and interactive log data by the Internet of things management platform;
s203, performing matching association according to the running log data, the interactive network flow data and the interactive log data so as to obtain a terminal ID required by a model training platform, and time, service type, network delay time and data packet size corresponding to the terminal ID;
and S204, storing the acquired terminal ID, the transmission time corresponding to the terminal ID, the service data type, the network delay time and the data packet size into a database of a model training platform. Therefore, the generated formatted data are imported into a model training platform, model parameter packaging is carried out on the extracted formatted data, model training parameters are built based on a linear regression kernel building principle, and an upgrading model related to the time period and the flow of terminal ID upgrading is analyzed.
Specifically, in step S300, the model training platform calls formatted data in the database as training data to execute a training task, including the following steps:
s301, taking formatted data stored in a database as a sample data set, and dividing the data into independent variable data and dependent variable data, wherein the independent variable data comprises a terminal ID, and the size, the type and the transmission time of a data packet which is transmitted every time and corresponds to the terminal ID, and the dependent variable is network delay time;
s302, selecting a plurality of data from the independent variable data and the dependent variable data as training sets, and using the rest data as test sets;
s303, selecting a multiple linear regression analysis model, wherein the multiple linear regression analysis model is as follows:
Y＝b0+b1X1+b2X2+b3X3+b4X4+e
wherein, Y is set as a dependent variable network delay time, X1、X2、X3、X4Is independent variable, respectively terminal ID and data packet size, service data type and transmission time of each transmission corresponding to the terminal ID, and the independent variable and dependent variable are in linear relation, b0、b1、b2、b3、b4E is an error term for the parameter to be estimated;
s304, training the multiple linear regression analysis model by using training set data to obtain a parameter b to be estimated0、b1、b2、b3、b4And the numerical value of the error item, and generating an upgrading model;
s305, verifying the upgrade model by adopting the data of the test set, if the upgrade model is a valid model, archiving, and otherwise, finishing training.
Specifically, in step S200, the internet of things management platform issues an upgrade model to each internet of things terminal for processing, the internet of things terminal uses the upgrade model for upgrading, and transmits an upgrade log to the internet of things management platform, including the following steps:
s401, each Internet of things terminal receives an upgrading model issued by an Internet of things management platform and updates a terminal upgrading module according to the upgrading model;
s402, after the updating is completed, informing the Internet of things management platform to release a terminal upgrading task to the Internet of things terminal for terminal upgrading;
and S403, after the terminal is upgraded, uploading the upgrade log to an internet of things management platform for processing.
In this embodiment, after the terminal finishes upgrading, the upgrade log is uploaded to the internet of things management platform for processing, which includes the following steps:
the method comprises the steps that an Internet of things management platform receives an upgrade log uploaded by an Internet of things terminal in real time;
filtering and analyzing the upgrade log;
deciding whether to start an upgrade model update task by analyzing the accuracy data and the performance data; if the training task needs to be updated, starting a new training task, and if the training task does not need to be updated, terminating the feedback;
the updating specific implementation method comprises the following steps:
collecting accuracy data and performance data of the model application;
pushing the collected data, filtering the integrity and effectiveness of the data, and then performing classification, aggregation and statistical analysis;
according to the analysis result, a part of data is used for generating a user use report, and a part of available data is used for generating sample data;
and directly feeding back a user report, verifying the sample data according to the requirements of a formal sample, expanding the sample data to a sample data set after the sample data passes the requirements of the formal sample, and finally feeding back the data.
Example 2
As shown in fig. 2, the present invention further provides an internet of things terminal upgrading system, which includes an internet of things management platform, a model training platform, and at least one internet of things terminal, where the at least one internet of things terminal may be any internet of things device capable of accessing a network,
the Internet of things management platform is used for receiving data sent by the Internet of things terminal, filtering the data, classifying and sorting the data into formatted data by taking the terminal ID of the Internet of things as a calculation target, and storing the formatted data into a database of the model training platform; meanwhile, an upgrading model is issued to at least one Internet of things terminal, and an upgrading log of the Internet of things terminal is received for processing;
the Internet of things terminal sends data to the Internet of things management platform at regular time, receives an upgrade model issued by the Internet of things management platform at the same time, and feeds an upgrade result back to the Internet of things management platform;
the model training platform is configured to perform specific execution training tasks, train the model according to the formatted data of the IOT management platform to form an optimized upgrade model and send the optimized upgrade model to the IOT management platform.
The thing allies oneself with management platform includes:
the data collection module is used for completing data collection of the terminal of the Internet of things;
the data processing module is used for cleaning, filtering, analyzing and summarizing the acquired data, generating formatted data, storing the formatted data serving as a sample data set into a database of the model training platform and completing data preparation work;
and the model issuing module is used for receiving the model output by the model training platform, rapidly issuing the model and distributing the model to each Internet of things terminal.
In this embodiment, the internet of things terminal includes:
the terminal processing module is used for communicating with the Internet of things management platform and carrying out upgrade control on the Internet of things terminal according to the received information sent by the Internet of things management platform; the method comprises the following steps of updating a terminal upgrading module according to a model of a model publishing module, receiving a feedback message of the terminal upgrading module and sending the feedback message to a task publishing module of an Internet of things management platform;
the task issuing module is used for receiving a message whether the terminal upgrading module fed back by the terminal of the Internet of things completes updating or not, deciding whether the terminal upgrading task needs to be issued or not according to the received message, and informing the terminal processing module of the terminal of the Internet of things to execute the upgrading task if necessary.
Therefore, the upgrading model is issued to the Internet of things terminal through the Internet of things management platform, the task issuing module is configured in the Internet of things management platform, the upgrading task is issued to the Internet of things terminal, and the Internet of things terminal upgrades the terminal according to the upgrading task. In the process, the internet of things management platform collects network flow data and related log data information in the running process of the internet of things terminal in real time.
Preferably, the model training platform comprises a platform processing module and a database in communication connection with the platform processing module, the processing module comprises a training unit, a verification unit and a database, the training unit is used for calling part of sample data sets stored in the database to process the sample data sets to obtain training data sets, and an upgrade model is established according to the training data sets;
and the verification unit is used for verifying the upgrade model by using data which is not acquired by the training module as a test data set, if the upgrade model is an effective model, archiving the upgrade model, and otherwise finishing the training.
Specifically, the specific method for establishing the upgrade model according to the training data set includes:
dividing a training data set into independent variable data and dependent variable data;
selecting a multiple linear regression analysis model, wherein the multiple linear regression analysis model is as follows:
Y＝b0+b1X1+b2X2+b3X3+b4X4+e
wherein, Y is set as a dependent variable network delay time, X1、X2、X3、X4As independent variables, respectively terminal ID and packet size, service data type and transmission time of each transmission corresponding to the terminal ID, and the independent variables and dependent variables are in linear relation, b0、b1、b2、b3、b4E is an error term for the parameter to be estimated;
training the multiple linear regression analysis model by using training set data to obtain a parameter b to be estimated0、b1、b2、b3、b4And the numerical value of the error term, and generating an upgrade model.
The method is based on a linear regression analysis algorithm, an upgrading model is trained, the upgrading model can be optimized and perfected through continuous self-learning, and meanwhile, the upgrading model interacts with a platform, and the independent upgrading strategy of each internet of things terminal is achieved.
It should be noted that: the sequence of the embodiments in this specification is merely for description, and does not represent the advantages or disadvantages of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the device and the storage medium, since they are substantially similar to the method embodiments, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiments.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent replacements, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1.物联网终端升级方法，其特征在于，包括以下步骤：1. A method for upgrading an Internet of Things terminal, comprising the following steps: 若干个物联网终端定时采集数据并实时将数据发送给物联管理平台；Several IoT terminals regularly collect data and send the data to the IoT management platform in real time; 物联管理平台接收若干个所述物联网终端发送的数据进行过滤并以物联网的终端ID为计算目标分类整理成格式化数据存储至模型训练平台的数据库中；The IoT management platform receives and filters the data sent by several IoT terminals, sorts and sorts the data into formatted data with the terminal ID of the IoT as the calculation target, and stores the data in the database of the model training platform; 模型训练平台调用数据库中格式化数据作为样本数据集执行训练任务，并将完成训练的升级模型发送至物联管理平台；The model training platform invokes the formatted data in the database as a sample data set to perform the training task, and sends the upgraded model after training to the IoT management platform; 物联管理平台将升级模型发布给各个物联网终端进行处理，由物联网终端使用所述升级模型进行升级，并将升级日志传输至物联管理平台。The IoT management platform publishes the upgrade model to each IoT terminal for processing, and the IoT terminal uses the upgrade model to upgrade, and transmits the upgrade log to the IoT management platform. 2.根据权利要求1的物联网终端升级策略的方法，其特征在于，物联管理平台接收若干个所述物联网终端发送的数据进行过滤并以物联网的终端ID为计算目标分类整理成格式化数据存储至模型训练平台的数据库中，其中，所述格式化数据包括终端ID、传输时间、业务数据类型、网络延时时间、数据包大小；并包括以下步骤：2. the method for the Internet of Things terminal upgrade strategy according to claim 1, is characterized in that, the data sent by several described Internet of Things terminals are received by the Internet of Things management platform to filter and take the terminal ID of the Internet of Things as the calculation target classification and organize into a format The formatted data is stored in the database of the model training platform, wherein the formatted data includes terminal ID, transmission time, service data type, network delay time, and data packet size; and includes the following steps: 物联管理平台接收各个物联网终端自身运行日志数据；The IoT management platform receives the operating log data of each IoT terminal; 物联管理平台采集自身与物联网终端交互日志数据以及交互网络流量数据；The IoT management platform collects the log data of the interaction between itself and the IoT terminal and the interactive network traffic data; 根据运行日志数据、交互网络流量数据以及交互日志数据进行匹配关联从而获取模型训练平台需求的终端ID以及所述终端ID对应的时间、业务类型、网络延时时间、数据包大小；According to the operation log data, the interactive network traffic data and the interactive log data, matching and association is performed to obtain the terminal ID required by the model training platform and the time, service type, network delay time, and data packet size corresponding to the terminal ID; 将获取的终端ID以及所述终端ID对应的传输时间、业务数据类型、网络延时时间、数据包大小存储至模型训练平台的数据库中。The acquired terminal ID and the corresponding transmission time, service data type, network delay time, and data packet size of the terminal ID are stored in the database of the model training platform. 3.根据权利要求2的物联网终端升级策略的方法，其特征在于，3. the method for the Internet of Things terminal upgrade strategy according to claim 2, is characterized in that, 模型训练平台调用数据库中格式化数据作为训练数据执行训练任务，包括以下步骤：The model training platform invokes the formatted data in the database as training data to perform training tasks, including the following steps: 将存储在数据库中格式化数据作为样本数据集，并分成自变量数据和因变量数据，所述自变量数据包括终端ID以及与终端ID对应的每次传输的数据包大小、业务数据类型和传输时间，因变量为网络延时时间；The formatted data stored in the database is used as a sample data set, and divided into independent variable data and dependent variable data, and the independent variable data includes the terminal ID and the data packet size of each transmission corresponding to the terminal ID, business data type and transmission time, the dependent variable is the network delay time; 从所述自变量数据和因变量数据中选取多个数据作为训练集，剩余数据作为测试集；Select multiple data from the independent variable data and dependent variable data as a training set, and the remaining data as a test set; 选择多元线性回归分析模型，多元线性回归分析模型为：Select the multiple linear regression analysis model. The multiple linear regression analysis model is: Y＝b0+b1X1+b2X2+b3X3+b4X4+eY=b 0 +b 1 X 1 +b 2 X 2 +b 3 X 3 +b 4 X 4 +e 其中，设置Y为因变量网络延时时间，X1、X2、X3、X4为自变量，分别为终端ID以及与终端ID对应的每次传输的数据包大小、业务数据类型和传输时间，并且自变量和因变量为线性关系，b0、b1、b2、b3、b4为待估计的参数，e为误差项；Among them, set Y as the dependent variable network delay time, X 1 , X 2 , X 3 , and X 4 as independent variables, which are the terminal ID and the data packet size, service data type and transmission of each transmission corresponding to the terminal ID respectively. time, and the independent variable and dependent variable have a linear relationship, b 0 , b 1 , b 2 , b 3 , b 4 are parameters to be estimated, and e is an error term; 采用训练集数据对所述多元线性回归分析模型进行训练，获取待估计的参数b0、b1、b2、b3、b4以及误差项的数值，并生成升级模型；Use the training set data to train the multiple linear regression analysis model, obtain the values of the parameters to be estimated b 0 , b 1 , b 2 , b 3 , b 4 and the error term, and generate an upgraded model; 采用测试集的数据来对升级模型进行验证，如果是有效模型则进行存档，否则结束训练。Use the data of the test set to verify the upgraded model, if it is a valid model, archive it, otherwise end the training. 4.根据权利要求1的物联网终端升级策略的方法，其特征在于，物联管理平台将升级模型发布给各个物联网终端进行处理，由物联网终端使用所述升级模型进行升级，并将升级日志传输至物联管理平台，包括以下步骤：4. The method for an Internet of Things terminal upgrade strategy according to claim 1, wherein the Internet of Things management platform releases the upgrade model to each Internet of Things terminal for processing, and the Internet of Things terminal uses the upgrade model to upgrade, and upgrades the upgrade model. The log is transmitted to the IoT management platform, including the following steps: 各个物联网终端接收物联管理平台发布的升级模型，并根据升级模型对终端升级模块进行更新；Each IoT terminal receives the upgrade model released by the IoT management platform, and updates the terminal upgrade module according to the upgrade model; 更新完成后，通知物联管理平台发布终端升级任务至物联网终端进行终端升级；After the update is completed, notify the IoT management platform to release the terminal upgrade task to the IoT terminal for terminal upgrade; 终端升级完成后将升级日志上传至物联管理平台进行处理。After the terminal upgrade is completed, upload the upgrade log to the IoT management platform for processing. 5.根据权利要求1的物联网终端升级策略的方法，其特征在于，终端升级完成后将升级日志上传至物联管理平台进行处理，包括以下步骤：5. The method for an Internet of Things terminal upgrade strategy according to claim 1, wherein after the terminal upgrade is completed, the upgrade log is uploaded to the IoT management platform for processing, comprising the following steps: 物联管理平台实时接收物联网终端上传的升级日志；The IoT management platform receives the upgrade log uploaded by the IoT terminal in real time; 对升级日志进行过滤分析；Filter and analyze the upgrade log; 通过分析准确率数据和性能数据决策是否启动升级模型更新任务；如果需要更新则启动新的训练任务，如果不需要则终止本次反馈；Determine whether to start the upgrade model update task by analyzing the accuracy data and performance data; if it needs to be updated, start a new training task, if not, terminate the feedback; 其中，更新的具体实施方法，包括以下步骤：Wherein, the specific implementation method of the update includes the following steps: 收集模型应用的准确率数据和性能数据；Collect accuracy data and performance data of model applications; 将收集到的数据推送，进行数据完整性、有效性的过滤，然后进行分类汇总和统计分析；Push the collected data, filter the data for completeness and validity, and then perform classification summary and statistical analysis; 根据分析结果，一部分数据用来生成用户使用报告，一部分可用数据用来生成样本数据；According to the analysis results, part of the data is used to generate user usage reports, and part of the available data is used to generate sample data; 对于用户报告直接进行反馈，对于样本数据扩充到样本数据集，最后进行数据反馈。Feedback is directly performed for user reports, expanded to sample data sets for sample data, and finally data feedback is performed. 6.物联网终端升级系统，其特征在于，包括物联管理平台、模型训练平台以及至少一个物联网终端，所述至少一个物联网终端可以是任何可以接入网络的物联网设备，6. An Internet of Things terminal upgrading system, characterized in that it includes an Internet of Things management platform, a model training platform and at least one Internet of Things terminal, and the at least one Internet of Things terminal can be any Internet of Things device that can access a network, 所述物联管理平台，用于接收所述物联网终端发送的数据进行过滤并以物联网的终端ID为计算目标分类整理成格式化数据存储至模型训练平台的数据库中；同时将升级模型发布给至少一个所述物联网终端，并接收物联网终端的升级日志进行处理；The IOT management platform is used to receive the data sent by the IOT terminal, filter it, and use the IOT terminal ID as the calculation target to classify and sort it into formatted data and store it in the database of the model training platform; at the same time, the upgraded model is released. to at least one of the IoT terminals, and receive the upgrade log of the IoT terminal for processing; 物联网终端定时将数据发送给物联管理平台，同时接收物联网管理平台下发的升级模型，并将升级结果反馈至物联管理平台；The IoT terminal regularly sends data to the IoT management platform, receives the upgrade model issued by the IoT management platform, and feeds back the upgrade results to the IoT management platform; 模型训练平台被配置为进行具体执行训练任务，根据物联管理平台的格式化数据训练所述模型形成优化的升级模型发送给物联管理平台。The model training platform is configured to perform specific training tasks, train the model according to the formatted data of the IoT management platform to form an optimized upgrade model and send it to the IoT management platform. 7.根据权利要求6的物联网终端升级系统，其特征在于，7. The Internet of Things terminal upgrading system according to claim 6, characterized in that, 所述物联管理平台包括：The IoT management platform includes: 数据收集模块，用于完成物联网终端的数据的采集；The data collection module is used to complete the data collection of the IoT terminal; 数据处理模块，用于将采集到的数据进行清洗过滤、分析汇总，并生成格式化数据，作为样本数据集存储至模型训练平台的数据库中，完成数据的准备工作；The data processing module is used to clean, filter, analyze and summarize the collected data, and generate formatted data, which is stored in the database of the model training platform as a sample data set to complete the data preparation; 模型发布模块，用于接收模型训练平台训练输出的模型，并进行快速发布，分发到各个物联网终端。The model publishing module is used to receive the model training output from the model training platform, publish it quickly, and distribute it to each IoT terminal. 8.根据权利要求7的物联网终端升级系统，其特征在于，物联网终端包括：8. The Internet of Things terminal upgrading system according to claim 7, wherein the Internet of Things terminal comprises: 终端处理模块，用于与所述物联管理平台通信，并根据接收物联管理平台发送信息对物联网终端进行升级控制；包括根据模型发布模块的模型对终端升级模块进行更新并接收其反馈消息发送至物联管理平台的任务发布模块；The terminal processing module is used for communicating with the IoT management platform, and performing upgrade control on the IoT terminal according to the information sent by the IoT management platform; including updating the terminal upgrade module according to the model of the model publishing module and receiving its feedback message The task release module sent to the IoT management platform; 任务发布模块用于接收终端升级模块完成更新的消息后发布终端升级任务至终端处理模块，终端处理模块继而执行升级任务。The task issuing module is configured to receive a message that the terminal upgrade module completes the update and issue the terminal upgrade task to the terminal processing module, and the terminal processing module then executes the upgrade task. 9.根据权利要求6的物联网终端升级系统，其特征在于，模型训练平台包括平台处理模块以及和平台处理模块通信连接的数据库，处理模块包括训练单元、验证单元以及数据库，所述训练单元用于调用数据库存储的部分样本数据集进行处理得到训练数据集，并根据所述训练数据集建立升级模型；9. The Internet of Things terminal upgrading system according to claim 6, wherein the model training platform comprises a platform processing module and a database that is communicatively connected with the platform processing module, and the processing module comprises a training unit, a verification unit and a database, and the training unit uses Part of the sample data set stored in the calling database is processed to obtain a training data set, and an upgrade model is established according to the training data set; 所述验证单元用于采用训练模块未采集的数据作为测试数据集来对升级模型进行验证，如果是有效模型则进行存档，否则结束训练。The verification unit is configured to use the data not collected by the training module as a test data set to verify the upgraded model, and if it is a valid model, archive it, otherwise end the training. 10.根据权利要求7的物联网终端升级系统，其特征在于，根据所述训练数据集建立升级模型的具体方法包括：10. The Internet of Things terminal upgrade system according to claim 7, wherein the specific method for establishing an upgrade model according to the training data set comprises: 将训练数据集分为自变量数据和因变量数据；Divide the training data set into independent variable data and dependent variable data; 选择多元线性回归分析模型，多元线性回归分析模型为：Select the multiple linear regression analysis model. The multiple linear regression analysis model is: Y＝b0+b1X1+b2X2+b3X3+b4X4+eY=b 0 +b 1 X 1 +b 2 X 2 +b 3 X 3 +b 4 X 4 +e 其中，设置Y为因变量网络延时时间，X1、X2、X3、X4为自变量，分别是终端ID以及与终端ID对应的每次传输的数据包大小、业务数据类型和传输时间，并且自变量和因变量为线性关系，b0、b1、b2、b3、b4为待估计的参数，e为误差项；Among them, set Y as the dependent variable network delay time, X 1 , X 2 , X 3 , and X 4 as independent variables, which are the terminal ID and the data packet size, service data type and transmission of each transmission corresponding to the terminal ID respectively. time, and the independent variable and dependent variable have a linear relationship, b 0 , b 1 , b 2 , b 3 , b 4 are parameters to be estimated, and e is an error term; 采用训练集数据对所述多元线性回归分析模型进行训练，获取待估计的参数b0、b1、b2、b3、b4以及误差项的数值，并生成升级模型。The multiple linear regression analysis model is trained by using the training set data, the values of the parameters to be estimated b 0 , b 1 , b 2 , b 3 , b 4 and the error term are obtained, and an upgraded model is generated.
CN202110150873.0A 2021-02-03 2021-02-03 Internet of things terminal upgrade system and method Pending CN113849203A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110150873.0A CN113849203A (en) 2021-02-03 2021-02-03 Internet of things terminal upgrade system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110150873.0A CN113849203A (en) 2021-02-03 2021-02-03 Internet of things terminal upgrade system and method

Publications (1)

Publication Number Publication Date
CN113849203A true CN113849203A (en) 2021-12-28

Family

ID=78972861

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110150873.0A Pending CN113849203A (en) 2021-02-03 2021-02-03 Internet of things terminal upgrade system and method

Country Status (1)

Country Link
CN (1) CN113849203A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113885900A (en) * 2021-04-14 2022-01-04 深圳市国电科技通信有限公司 Internet of things terminal upgrading system and method
CN114297215A (en) * 2021-12-31 2022-04-08 天翼物联科技有限公司 Internet of things terminal object model standardization processing method and device, computer equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170235564A1 (en) * 2014-10-14 2017-08-17 Huawei Technologies Co., Ltd. Software upgrade method and device
WO2017190401A1 (en) * 2016-05-05 2017-11-09 深圳前海大数点科技有限公司 Internet of things service system
US20200092396A1 (en) * 2018-09-14 2020-03-19 Cisco Technology, Inc. Firmware/software over the air (fota) scheduling for connected vehicles
CN111510323A (en) * 2020-03-24 2020-08-07 中国科学院上海微系统与信息技术研究所 Firmware upgrading method, device and system for Internet of things equipment and storage medium
CN111831298A (en) * 2019-06-06 2020-10-27 北京骑胜科技有限公司 Firmware upgrading method and device, electronic equipment and storage medium
CN111917583A (en) * 2020-07-31 2020-11-10 中国联合网络通信集团有限公司 Internet of things terminal, software upgrading method thereof and Internet of things platform
US10841791B1 (en) * 2019-08-27 2020-11-17 Verizon Patent And Licensing Inc. Dynamic firmware over-the-air system for IoT devices

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170235564A1 (en) * 2014-10-14 2017-08-17 Huawei Technologies Co., Ltd. Software upgrade method and device
WO2017190401A1 (en) * 2016-05-05 2017-11-09 深圳前海大数点科技有限公司 Internet of things service system
US20200092396A1 (en) * 2018-09-14 2020-03-19 Cisco Technology, Inc. Firmware/software over the air (fota) scheduling for connected vehicles
CN111831298A (en) * 2019-06-06 2020-10-27 北京骑胜科技有限公司 Firmware upgrading method and device, electronic equipment and storage medium
US10841791B1 (en) * 2019-08-27 2020-11-17 Verizon Patent And Licensing Inc. Dynamic firmware over-the-air system for IoT devices
CN111510323A (en) * 2020-03-24 2020-08-07 中国科学院上海微系统与信息技术研究所 Firmware upgrading method, device and system for Internet of things equipment and storage medium
CN111917583A (en) * 2020-07-31 2020-11-10 中国联合网络通信集团有限公司 Internet of things terminal, software upgrading method thereof and Internet of things platform

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113885900A (en) * 2021-04-14 2022-01-04 深圳市国电科技通信有限公司 Internet of things terminal upgrading system and method
CN114297215A (en) * 2021-12-31 2022-04-08 天翼物联科技有限公司 Internet of things terminal object model standardization processing method and device, computer equipment and storage medium

Similar Documents

Publication Publication Date Title
US20090182794A1 (en) Error management apparatus
CN113360554A (en) Method and equipment for extracting, converting and loading ETL (extract transform load) data
CN110362473B (en) Method and device for optimizing test environment, storage medium, and terminal
CN105631026A (en) Security data analysis system
CN110457175B (en) Service data processing method and device, electronic equipment and medium
CN113704077B (en) Test case generation method and device
CN113485999B (en) Data cleaning method, device and server
CN113448812A (en) Monitoring alarm method and device under micro-service scene
CN113849203A (en) Internet of things terminal upgrade system and method
CN108304286A (en) A kind of system and method carrying out automatic test to transcoding server concurrency performance
CN113242159B (en) Application access relation determining method and device
CN108108445A (en) A kind of data intelligence processing method and system
US20230004478A1 (en) Systems and methods of continuous stack trace collection to monitor an application on a server and resolve an application incident
CN107203464B (en) Method and device for positioning service problem
CN113885900A (en) Internet of things terminal upgrading system and method
CN113609393A (en) Digital platform based on data service and data management
CN118585297A (en) A task execution method and related equipment
CN111523921A (en) Funnel analysis method, analysis device, electronic device, and readable storage medium
CN111277427A (en) A kind of inspection method and system for data center network equipment
CN107222368B (en) Data playback method and device
CN106528795B (en) Data mining method and device
CN112765010A (en) Method, device, equipment and storage medium for centralized management of service parameters
CN114968508A (en) Task processing method, device, equipment and storage medium
CN113723800A (en) Risk identification model training method and device and risk identification method and device
CN113570333B (en) Process design method suitable for integration

Legal Events

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