[go: up one dir, main page]

CN118504232B - An artificial intelligence-based network equipment operation risk assessment system - Google Patents

An artificial intelligence-based network equipment operation risk assessment system Download PDF

Info

Publication number
CN118504232B
CN118504232B CN202410583060.4A CN202410583060A CN118504232B CN 118504232 B CN118504232 B CN 118504232B CN 202410583060 A CN202410583060 A CN 202410583060A CN 118504232 B CN118504232 B CN 118504232B
Authority
CN
China
Prior art keywords
aging
analysis
coefficient
value
data
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.)
Active
Application number
CN202410583060.4A
Other languages
Chinese (zh)
Other versions
CN118504232A (en
Inventor
王小玲
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.)
Beijing Linghuafeng Communication Technology Co ltd
Original Assignee
Beijing Linghuafeng Communication Technology 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 Beijing Linghuafeng Communication Technology Co ltd filed Critical Beijing Linghuafeng Communication Technology Co ltd
Priority to CN202410583060.4A priority Critical patent/CN118504232B/en
Publication of CN118504232A publication Critical patent/CN118504232A/en
Application granted granted Critical
Publication of CN118504232B publication Critical patent/CN118504232B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/04—Ageing analysis or optimisation against ageing

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Computer And Data Communications (AREA)

Abstract

The invention belongs to the field of network equipment, relates to a data analysis technology, and aims to solve the problem that a network equipment operation risk assessment system in the prior art cannot optimize load according to an aging analysis result of network equipment, in particular to a network equipment operation risk assessment system based on artificial intelligence, which comprises a risk assessment platform, wherein the risk assessment platform is in communication connection with an aging analysis module, a task allocation module, an architecture management module and a storage module; the invention can detect and analyze the aging state of the network equipment, evaluate the aging state of the network equipment according to the aging coefficient, replace the analysis object which does not meet the use requirement and improve the running stability of the network architecture.

Description

Network equipment operation risk assessment system based on artificial intelligence
Technical Field
The invention belongs to the field of network equipment, relates to a data analysis technology, and particularly relates to an artificial intelligence-based network equipment operation risk assessment system.
Background
With the rapid development of information technology, network devices have become an indispensable infrastructure for enterprise operations. However, various risks are faced in the operation process of the network equipment, for example, the stability of the performance of the equipment is the basis of the operation of the network equipment, and if the performance of the equipment is unstable, the problems of network interruption, data transmission delay and the like can be caused, so that the business operation of enterprises is seriously affected.
The network equipment operation risk assessment system in the prior art can only monitor the operation stability of the network equipment, but cannot optimize the load according to the aging analysis result of the network equipment, so that the load of the network equipment cannot realize dynamic balance, and the operation stability of the network equipment is poor.
The application provides a solution to the technical problem.
Disclosure of Invention
The invention aims to provide a network equipment operation risk assessment system based on artificial intelligence, which is used for solving the problem that the network equipment operation risk assessment system in the prior art cannot optimize load according to the aging analysis result of network equipment;
The invention aims to provide an artificial intelligence-based network equipment operation risk assessment system capable of carrying out load optimization according to an aging analysis result of network equipment.
The aim of the invention can be achieved by the following technical scheme:
The network equipment operation risk assessment system based on artificial intelligence comprises a risk assessment platform, wherein the risk assessment platform is in communication connection with an aging analysis module, a task allocation module, an architecture management module and a storage module;
the aging analysis module is used for detecting and analyzing the aging state of the network equipment, namely marking the network equipment covered by the network architecture as an analysis object, generating a detection period, and acquiring life data SM, interrupt data ZD and delay data YC of the analysis object in the detection period;
When the network node receives the data processing task, marking the network device under the network node as an allocation object, marking the data packet memory value of the data processing task which is not completed by the allocation object as the basic value of the allocation object, arranging the allocation object according to the sequence from small to large of the ageing coefficient LH value to obtain an allocation sequence, carrying out decision analysis on the allocation sequence to obtain a processing object, and sending the data processing task to the processing object;
The architecture management module is used for performing management analysis on the network architecture.
The method comprises the steps of marking the difference value between the current system time and the delivery time of an analysis object as operation time length, marking the ratio of the operation time length to the rated service life of the analysis object as service life data SM, marking the number of times of executing a data calculation task by the analysis object in a detection period as a processing value of the analysis object, marking the number of times of causing network interruption by the analysis object in the detection period as an interruption value, marking the ratio of the interruption value to the processing value as interruption data ZD, and marking the number of times of executing a data transmission task by the analysis object in the detection period as a transmission value, marking the number of times of data transmission delay of the analysis object in the detection period as a delay value, and marking the ratio of the delay value to the transmission value as delay data YC.
The specific process for judging whether the aging state of the analysis object meets the requirement or not according to the preferred implementation mode of the invention comprises the steps of acquiring an aging threshold LHmax through a storage module, comparing an aging coefficient LH with the aging threshold LHmax, judging that the aging state of the analysis object meets the requirement if the aging coefficient LH is smaller than the aging threshold LHmax, judging that the aging state of the analysis object does not meet the requirement if the aging coefficient LH is larger than or equal to the aging threshold LHmax, generating an equipment updating signal and sending the equipment updating signal to a risk assessment platform, and sending the equipment updating signal to a mobile phone terminal of a manager after the risk assessment platform receives the equipment updating signal.
The method comprises the steps of selecting first to nth allocation objects ordered in an allocation sequence as objects to be selected, marking the sum of basic values of all the objects to be selected as decision values, marking the sum of the basic values of all the objects to be selected as basic representation values, marking the absolute value of the difference between the decision values and the basic representation values as decision coefficients, acquiring the decision threshold value through a storage module, comparing the decision coefficients with the decision threshold value, marking the object to be selected with the smallest sequence number as a processing object if the decision coefficients are smaller than the decision threshold value, and sending data processing tasks to the processing object, selecting second to n+1th allocation objects ordered in the allocation sequence as objects to be selected if the decision coefficients are larger than or equal to the decision threshold value, recalculating the decision coefficients of the objects to be selected, and so on until the decision coefficients are smaller than the decision threshold value and marking the processing object.
The method comprises the steps of arranging all analysis objects according to the sequence of the aging coefficient LH from small to large to obtain an aging sequence of the network architecture, obtaining the sum of data packet memory values of the analysis objects for executing all data processing tasks in a detection period, marking the sum as a load value of the analysis objects, arranging the analysis objects according to the sequence of the load values from large to small to obtain a load sequence of the network architecture, marking the absolute value of the difference value between the serial numbers of the analysis objects in the aging sequence and the serial numbers in the load sequence as a reasonable value of the analysis objects, summing the reasonable values of all the analysis objects, averaging to obtain a reasonable coefficient of the network architecture, and judging whether the rationality of the network architecture layout meets the requirement or not through the reasonable coefficient.
The specific process for judging whether the rationality of the network architecture layout meets the requirements or not comprises the steps of acquiring a reasonable threshold value through a storage module, comparing a reasonable coefficient with the reasonable threshold value, judging that the rationality of the network architecture layout meets the requirements if the reasonable coefficient is smaller than the reasonable threshold value, judging that the rationality of the network architecture layout does not meet the requirements if the reasonable coefficient is larger than or equal to the reasonable threshold value, generating an architecture optimization signal, sending the architecture optimization signal to a risk assessment platform, and sending the architecture optimization signal to a mobile phone terminal of a manager after the risk assessment platform receives the architecture optimization signal.
As a preferred embodiment of the present invention, the working method of the network equipment operation risk assessment system based on artificial intelligence comprises the following steps:
The method comprises the steps of firstly, detecting and analyzing the aging state of network equipment, namely marking the network equipment covered by a network architecture as an analysis object, generating a detection period, acquiring life data SM, interrupt data ZD and delay data YC of the analysis object in the detection period, performing numerical value calculation to obtain an aging coefficient LH, and judging whether the aging state of the analysis object meets the requirement or not through the aging coefficient LH;
When the network node receives the data processing task, marking the network device under the network node as an allocation object, arranging the allocation object according to the sequence of the aging coefficient LH from small to large to obtain an allocation sequence, and carrying out decision analysis on the allocation sequence to obtain a processing object;
and thirdly, performing management analysis on the network architecture, namely acquiring an aging sequence and a load sequence of the network architecture, performing numerical calculation on sequence numbers of analysis objects in the aging sequence and the load sequence to obtain reasonable coefficients of the network architecture, and judging whether the rationality of the network architecture layout meets the requirement or not through the reasonable coefficients.
The invention has the following beneficial effects:
1. The aging analysis module can detect and analyze the aging state of the network equipment, and statistics and analysis are carried out on various operation parameters of the analysis object in a detection period to obtain an aging coefficient, so that the aging state of the network equipment is estimated according to the aging coefficient, the analysis object which does not meet the use requirement is replaced, and the operation stability of the network architecture is improved;
2. The task allocation module can perform allocation analysis on the data processing tasks of the network equipment, the allocation sequence is obtained by sequencing by taking the ageing coefficient of the allocation object as a standard, decision analysis is performed by combining the ageing state of the allocation object and the memory value of the data packet of the current unfinished data processing task, and the allocation object with the highest comprehensive priority is selected for task processing, so that the data processing efficiency is improved and the fault risk is reduced on the whole;
3. The network architecture can be managed and analyzed through the architecture management module, on the basis of dynamically carrying out task allocation, the aging states and task processing amounts of all allocation objects are comprehensively analyzed and calculated to obtain reasonable coefficients, and on the premise of guaranteeing the task allocation rationality, the network architecture is optimized when the matching degree of the aging states and the task processing amounts of the allocation objects is low, and the network layout is macroscopically adjusted.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a system block diagram of a first embodiment of the present invention;
Fig. 2 is a flowchart of a method according to a second embodiment of the invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in fig. 1, an artificial intelligence-based network device operation risk assessment system includes a risk assessment platform, and the risk assessment platform is communicatively connected with an aging analysis module, a task allocation module, an architecture management module and a storage module.
The aging analysis module is used for detecting and analyzing the aging state of the network equipment, namely marking the network equipment covered by the network architecture as an analysis object, generating a detection period, and acquiring life data SM, interrupt data ZD and delay data YC of the analysis object in the detection period, wherein the acquisition process of the life data SM comprises the steps of marking the difference value between the current system time and the delivery time of the analysis object as running time, and marking the ratio of the running time to the rated life of the analysis object as life data SM; the acquisition process of the interruption data ZD comprises the steps of marking the number of times of executing a data calculation task by an analysis object in a detection period as a processing value of the analysis object, marking the number of times of network interruption caused by the analysis object in the detection period as an interruption value, marking the ratio of the interruption value to the processing value as interruption data ZD, the acquisition process of the delay data YC comprises the steps of marking the number of times of executing a data transmission task by the analysis object in the detection period as a transmission value, marking the number of times of data transmission delay of the analysis object in the detection period as a delay value, marking the ratio of the delay value to the transmission value as delay data YC, obtaining an aging coefficient LH of the analysis object in the detection period through a formula LH=k1+k2+k3, wherein k1, k2 and k3 are all proportional coefficients, and k1> k2> k3>1, obtaining an aging threshold LHmax through a storage module, comparing the aging coefficient LH with an aging threshold LHmax, judging that the aging coefficient LH meets the aging coefficient of the analysis object is smaller than the aging threshold LHmax, if the aging coefficient LH meets the aging coefficient is greater than or equal to LHmax, generating an aging-required signal updating-state-updating-free signal, generating an aging-stage aging-required signal, detecting and analyzing the aging state of the network equipment, and counting and analyzing various operation parameters of the analysis object in a detection period to obtain an aging coefficient, so that the aging state of the network equipment is evaluated according to the aging coefficient, the analysis object which does not meet the use requirement is replaced, and the operation stability of the network architecture is improved.
The task allocation module is used for carrying out allocation analysis on the data processing tasks of the network equipment, when the network node receives the data processing tasks, the network equipment under the network node is marked as an allocation object, the memory value of a data packet of the data processing tasks which are not completed by the allocation object is marked as the basic value of the allocation object, the allocation objects are arranged according to the order of the values of the ageing coefficients LH from small to large to obtain an allocation sequence, the allocation sequence is subjected to decision analysis, the first to n-th allocation objects which are ordered in the allocation sequence are selected as the objects to be selected, the sum value of the basic values of all the objects to be selected is marked as the decision value, the sum value of the basic values of all the allocation objects is marked as the basic value, the absolute value of the difference value of the decision value and the basic value is marked as the decision coefficient, the decision coefficient is obtained through the storage module, the decision coefficient is compared with the decision threshold, the object to be selected with the minimum sequence number is marked as the processing object, if the decision coefficient is larger than or equal to the decision threshold, the second to n+1 allocation object is selected as the decision object in the allocation sequence, the allocation sequence is selected, the coefficient to be selected is calculated, the data processing objects which are distributed in the allocation sequence is not completed by the current data processing object is combined with the decision threshold, the allocation object is subjected to the data processing task allocation data processing module, and the priority is analyzed, and the data allocation task allocation data processing object has the priority, and the priority is obtained, the data processing efficiency is improved and the fault risk is reduced as a whole.
The system comprises a network architecture management module, a storage module, a risk assessment platform, a network architecture management module, a storage module, a management module and a risk assessment platform, wherein the network architecture management module is used for managing and analyzing the network architecture, wherein all analysis objects are arranged according to the order of an aging coefficient LH value from small to large to obtain an aging sequence of the network architecture, the sum of data packet memory values of all data processing tasks executed by the analysis objects in a detection period is marked as a load value of the analysis objects, the analysis objects are arranged according to the order of the load value from large to small to obtain a load sequence of the network architecture, the absolute value of the difference value of the serial numbers of the analysis objects in the aging sequence is marked as a reasonable value of the analysis objects, the reasonable values of all analysis objects are summed and averaged to obtain a reasonable coefficient of the network architecture, the reasonable coefficient of the network architecture is obtained through the storage module, the reasonable coefficient is compared with the reasonable threshold, if the reasonable coefficient is smaller than the reasonable threshold, if the reasonable coefficient is larger than the reasonable threshold, the reasonable coefficient of the network architecture is judged to meet the requirement, the architecture optimization of the architecture is not met, an architecture optimization signal is generated, the architecture optimization signal is sent to the risk assessment platform, the architecture optimization signal is sent to the architecture optimization signal after the architecture optimization signal is received, the architecture optimization signal is sent, the reasonable value, the reasonable value is calculated, the reasonable and the reasonable value is calculated, the reasonable and the condition of the task is calculated, and the reasonable and the condition of the network architecture is calculated and the reasonable to the condition.
Example two
As shown in fig. 2, a network device operation risk assessment method based on artificial intelligence includes the following steps:
The method comprises the steps of firstly, detecting and analyzing the aging state of network equipment, namely marking the network equipment covered by a network architecture as an analysis object, generating a detection period, acquiring life data SM, interrupt data ZD and delay data YC of the analysis object in the detection period, performing numerical value calculation to obtain an aging coefficient LH, and judging whether the aging state of the analysis object meets the requirement or not through the aging coefficient LH;
When the network node receives the data processing task, marking the network device under the network node as an allocation object, arranging the allocation object according to the sequence of the aging coefficient LH from small to large to obtain an allocation sequence, and carrying out decision analysis on the allocation sequence to obtain a processing object;
and thirdly, performing management analysis on the network architecture, namely acquiring an aging sequence and a load sequence of the network architecture, performing numerical calculation on sequence numbers of analysis objects in the aging sequence and the load sequence to obtain reasonable coefficients of the network architecture, and judging whether the rationality of the network architecture layout meets the requirement or not through the reasonable coefficients.
When the network node receives a data processing task, the network equipment under the network node is marked as an allocation object, the allocation object is arranged according to the order of the values of the ageing coefficient LH from small to large to obtain an allocation sequence, decision analysis is carried out on the allocation sequence to obtain a processing object, the ageing sequence and the load sequence of the network architecture are obtained, the sequence number of the analysis object in the ageing sequence and the load sequence is calculated to obtain a reasonable coefficient of the network architecture, and whether the rationality of the network architecture layout meets the requirement is judged through the reasonable coefficient.
The foregoing is merely illustrative of the structures of this invention and various modifications, additions and substitutions for those skilled in the art can be made to the described embodiments without departing from the scope of the invention or from the scope of the invention as defined in the accompanying claims.
The formula is obtained by collecting a large amount of data for software simulation, and selecting a formula close to a true value, wherein coefficients in the formula are set by a person skilled in the art according to actual conditions, such as a formula LH=k1+k2+ZD+k3 YC, a person skilled in the art collects a plurality of groups of sample data and sets a corresponding aging coefficient for each group of sample data;
The size of the coefficient is a specific numerical value obtained by quantizing each parameter, so that the subsequent comparison is convenient, the size of the coefficient depends on the number of sample data and the corresponding aging coefficient preliminarily set for each group of sample data by a person skilled in the art, as long as the proportional relation between the parameter and the quantized numerical value is not influenced, for example, the aging coefficient is in direct proportion to the numerical value of the service life data.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.

Claims (5)

1.一种基于人工智能的网络设备运营风险评估系统，其特征在于，包括风险评估平台，所述风险评估平台通信连接有老化分析模块、任务分配模块、架构管理模块以及存储模块；1. A network equipment operation risk assessment system based on artificial intelligence, characterized in that it includes a risk assessment platform, wherein the risk assessment platform is communicatively connected to an aging analysis module, a task allocation module, an architecture management module and a storage module; 所述老化分析模块用于对网络设备的老化状态进行检测分析：将网络架构覆盖的网络设备标记为分析对象，生成检测周期，获取分析对象在检测周期内的寿命数据SM、中断数据ZD以及延迟数据YC；通过对寿命数据SM、中断数据ZD以及延迟数据YC进行数值计算得到分析对象在检测周期内的老化系数LH；通过老化系数LH对分析对象的老化状态是否满足要求进行判定；The aging analysis module is used to detect and analyze the aging status of network devices: mark the network devices covered by the network architecture as analysis objects, generate a detection cycle, obtain the life data SM, interruption data ZD and delay data YC of the analysis object within the detection cycle; obtain the aging coefficient LH of the analysis object within the detection cycle by numerically calculating the life data SM, interruption data ZD and delay data YC; determine whether the aging status of the analysis object meets the requirements by the aging coefficient LH; 所述任务分配模块用于对网络设备的数据处理任务进行分配分析：在网络节点接收到数据处理任务时，将网络节点下的网络设备标记为分配对象，将分配对象未完成的数据处理任务的数据包内存值标记为分配对象的基础值，将分配对象按照老化系数LH数值由小到大的顺序进行排列得到分配序列，对分配序列进行决策分析得到处理对象，将数据处理任务发送至处理对象；The task allocation module is used to allocate and analyze the data processing tasks of the network devices: when the network node receives the data processing task, the network device under the network node is marked as the allocation object, the data packet memory value of the unfinished data processing task of the allocation object is marked as the basic value of the allocation object, the allocation objects are arranged in the order of the aging coefficient LH value from small to large to obtain the allocation sequence, the allocation sequence is analyzed for decision making to obtain the processing object, and the data processing task is sent to the processing object; 所述架构管理模块用于对网络架构进行管理分析；The architecture management module is used to manage and analyze the network architecture; 对分配序列进行决策分析的具体过程包括：选取分配序列中排序第一至第n个分配对象作为待选对象，将所有待选对象的基础值的和值标记为决策值，将所有分配对象的基础值的和值标记为基础表现值，将决策值与基础表现值差值的绝对值标记为决策系数，通过存储模块获取决策阈值，将决策系数与决策阈值进行比较：若决策系数小于决策阈值，则将序号最小的待选对象标记为处理对象，将数据处理任务发送至处理对象；若决策系数大于等于决策阈值，则选取分配序列中排序第二至第n+1个分配对象作为待选对象，重新计算待选对象的决策系数，以此类推，直至决策系数小于决策阈值并对处理对象进行标记；The specific process of performing decision analysis on the allocation sequence includes: selecting the first to nth allocation objects in the allocation sequence as the objects to be selected, marking the sum of the basic values of all the objects to be selected as the decision value, marking the sum of the basic values of all the objects to be selected as the basic performance value, marking the absolute value of the difference between the decision value and the basic performance value as the decision coefficient, obtaining the decision threshold through the storage module, and comparing the decision coefficient with the decision threshold: if the decision coefficient is less than the decision threshold, marking the object to be selected with the smallest sequence number as the processing object, and sending the data processing task to the processing object; if the decision coefficient is greater than or equal to the decision threshold, selecting the second to n+1th allocation objects in the allocation sequence as the objects to be selected, recalculating the decision coefficient of the objects to be selected, and so on, until the decision coefficient is less than the decision threshold and the processing object is marked; 架构管理模块对网络架构进行管理分析的具体过程包括：将所有的分析对象按照老化系数LH数值由小到大的顺序进行排列得到网络架构的老化序列，获取分析对象在检测周期执行所有数据处理任务的数据包内存值的和值标记为分析对象的负载值，将分析对象按照负载值由大到小的顺序进行排列得到网络架构的负载序列，将分析对象在老化序列中的序号与负载序列中的序号的差值的绝对值标记为分析对象的合理值，对所有分析对象的合理值进行求和取平均值得到网络架构的合理系数，通过合理系数对网络架构布局合理性是否满足要求进行判定。The specific process of the architecture management module managing and analyzing the network architecture includes: arranging all analysis objects in order of the aging coefficient LH value from small to large to obtain the aging sequence of the network architecture, obtaining the sum of the memory values of the data packets of the analysis object performing all data processing tasks in the detection period and marking it as the load value of the analysis object, arranging the analysis objects in order of the load value from large to small to obtain the load sequence of the network architecture, marking the absolute value of the difference between the sequence number of the analysis object in the aging sequence and the sequence number in the load sequence as the reasonable value of the analysis object, summing and averaging the reasonable values of all analysis objects to obtain the reasonable coefficient of the network architecture, and judging whether the rationality of the network architecture layout meets the requirements through the reasonable coefficient. 2.根据权利要求1所述的一种基于人工智能的网络设备运营风险评估系统，其特征在于，寿命数据SM的获取过程包括：将当前系统时间与分析对象出厂时间的差值标记为运行时长，将运行时长与分析对象额定寿命的比值标记为寿命数据SM；中断数据ZD的获取过程包括：将分析对象在检测周期内执行数据计算任务的次数标记为分析对象的处理值，将分析对象在检测周期内引起网络中断的次数标记为中断值，将中断值与处理值的比值标记为中断数据ZD；延迟数据YC的获取过程包括：将分析对象在检测周期内执行数据传输任务的次数标记为传输值，将分析对象在检测周期内出现数据传输延迟的次数标记为延迟值，将延迟值与传输值的比值标记为延迟数据YC。2. According to claim 1, a network equipment operation risk assessment system based on artificial intelligence is characterized in that the process of obtaining life data SM includes: marking the difference between the current system time and the factory time of the analysis object as the operating time, and marking the ratio of the operating time to the rated life of the analysis object as the life data SM; the process of obtaining interruption data ZD includes: marking the number of times the analysis object performs data calculation tasks within the detection period as the processing value of the analysis object, marking the number of times the analysis object causes network interruption within the detection period as the interruption value, and marking the ratio of the interruption value to the processing value as the interruption data ZD; the process of obtaining delay data YC includes: marking the number of times the analysis object performs data transmission tasks within the detection period as the transmission value, marking the number of times the analysis object has data transmission delay within the detection period as the delay value, and marking the ratio of the delay value to the transmission value as the delay data YC. 3.根据权利要求2所述的一种基于人工智能的网络设备运营风险评估系统，其特征在于，对分析对象的老化状态是否满足要求进行判定的具体过程包括：通过存储模块获取到老化阈值LHmax，将老化系数LH与老化阈值LHmax进行比较：若老化系数LH小于老化阈值LHmax，则判定分析对象的老化状态满足要求；若老化系数LH大于等于老化阈值LHmax，则判定分析对象的老化状态不满足要求，生成设备更新信号并将设备更新信号发送至风险评估平台，风险评估平台接收到设备更新信号后将设备更新信号发送至管理人员的手机终端。3. According to claim 2, a network equipment operation risk assessment system based on artificial intelligence is characterized in that the specific process of determining whether the aging status of the analysis object meets the requirements includes: obtaining the aging threshold LHmax through the storage module, and comparing the aging coefficient LH with the aging threshold LHmax: if the aging coefficient LH is less than the aging threshold LHmax, it is determined that the aging status of the analysis object meets the requirements; if the aging coefficient LH is greater than or equal to the aging threshold LHmax, it is determined that the aging status of the analysis object does not meet the requirements, generating a device update signal and sending the device update signal to the risk assessment platform, and after receiving the device update signal, the risk assessment platform sends the device update signal to the mobile phone terminal of the manager. 4.根据权利要求3所述的一种基于人工智能的网络设备运营风险评估系统，其特征在于，对网络架构布局合理性是否满足要求进行判定的具体过程包括：通过存储模块获取到合理阈值，将合理系数与合理阈值进行比较：若合理系数小于合理阈值，则判定网络架构布局合理性满足要求；若合理系数大于等于合理阈值，则判定网络架构布局合理性不满足要求，生成架构优化信号并将架构优化信号发送至风险评估平台，风险评估平台接收到架构优化信号后将架构优化信号发送至管理人员的手机终端。4. According to claim 3, a network equipment operation risk assessment system based on artificial intelligence is characterized in that the specific process of determining whether the rationality of the network architecture layout meets the requirements includes: obtaining a reasonable threshold through a storage module, and comparing a reasonable coefficient with the reasonable threshold: if the reasonable coefficient is less than the reasonable threshold, then it is determined that the rationality of the network architecture layout meets the requirements; if the reasonable coefficient is greater than or equal to the reasonable threshold, then it is determined that the rationality of the network architecture layout does not meet the requirements, and an architecture optimization signal is generated and sent to the risk assessment platform. After receiving the architecture optimization signal, the risk assessment platform sends the architecture optimization signal to the mobile phone terminal of the manager. 5.根据权利要求1-4任一项所述的一种基于人工智能的网络设备运营风险评估系统，其特征在于，该基于人工智能的网络设备运营风险评估系统的工作方法，包括以下步骤：5. According to any one of claims 1 to 4, a network equipment operation risk assessment system based on artificial intelligence is characterized in that the working method of the network equipment operation risk assessment system based on artificial intelligence comprises the following steps: 步骤一：对网络设备的老化状态进行检测分析：将网络架构覆盖的网络设备标记为分析对象，生成检测周期，获取分析对象在检测周期内的寿命数据SM、中断数据ZD以及延迟数据YC并进行数值计算得到老化系数LH，通过老化系数LH对分析对象的老化状态是否满足要求进行判定；Step 1: Detect and analyze the aging status of network devices: mark the network devices covered by the network architecture as analysis objects, generate a detection cycle, obtain the life data SM, interruption data ZD and delay data YC of the analysis object within the detection cycle, and perform numerical calculations to obtain the aging coefficient LH. The aging coefficient LH is used to determine whether the aging status of the analysis object meets the requirements; 步骤二：对网络设备的数据处理任务进行分配分析：在网络节点接收到数据处理任务时，将网络节点下的网络设备标记为分配对象，将分配对象按照老化系数LH数值由小到大的顺序进行排列得到分配序列，对分配序列进行决策分析并得到处理对象；Step 2: Perform allocation analysis on the data processing tasks of the network devices: When a network node receives a data processing task, the network devices under the network node are marked as allocation objects, and the allocation objects are arranged in order from small to large according to the aging coefficient LH values to obtain an allocation sequence, and a decision analysis is performed on the allocation sequence to obtain the processing object; 步骤三：对网络架构进行管理分析：获取网络架构的老化序列与负载序列，对分析对象在老化序列与负载序列中的序号进行数值计算得到网络架构的合理系数，通过合理系数对网络架构布局合理性是否满足要求进行判定。Step 3: Manage and analyze the network architecture: obtain the aging sequence and load sequence of the network architecture, perform numerical calculations on the sequence numbers of the analysis objects in the aging sequence and load sequence to obtain the reasonable coefficient of the network architecture, and use the reasonable coefficient to determine whether the rationality of the network architecture layout meets the requirements.
CN202410583060.4A 2024-05-11 2024-05-11 An artificial intelligence-based network equipment operation risk assessment system Active CN118504232B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410583060.4A CN118504232B (en) 2024-05-11 2024-05-11 An artificial intelligence-based network equipment operation risk assessment system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410583060.4A CN118504232B (en) 2024-05-11 2024-05-11 An artificial intelligence-based network equipment operation risk assessment system

Publications (2)

Publication Number Publication Date
CN118504232A CN118504232A (en) 2024-08-16
CN118504232B true CN118504232B (en) 2025-02-25

Family

ID=92244316

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410583060.4A Active CN118504232B (en) 2024-05-11 2024-05-11 An artificial intelligence-based network equipment operation risk assessment system

Country Status (1)

Country Link
CN (1) CN118504232B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119205951B (en) * 2024-09-04 2025-05-06 明晨云(苏州)数字科技有限公司 A drawing path optimization system and method based on AI
CN119155111B (en) * 2024-11-14 2025-02-11 雅砻江流域水电开发有限公司 Network security intelligent operation method based on artificial intelligence
CN120358253B (en) * 2025-04-18 2025-11-14 东营职业学院 Industrial big data intelligent analysis method and system based on cloud computing

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20220126303A (en) * 2021-03-08 2022-09-16 주식회사 피엠씨지 Facility asset management system via knowledge based intelligence
CN115470493A (en) * 2022-06-24 2022-12-13 徐昊 An information security risk assessment system for industrial control systems

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11334831B2 (en) * 2014-05-21 2022-05-17 X-Act Science, Inc. Predictive risk assessment in system modeling

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20220126303A (en) * 2021-03-08 2022-09-16 주식회사 피엠씨지 Facility asset management system via knowledge based intelligence
CN115470493A (en) * 2022-06-24 2022-12-13 徐昊 An information security risk assessment system for industrial control systems

Also Published As

Publication number Publication date
CN118504232A (en) 2024-08-16

Similar Documents

Publication Publication Date Title
CN118504232B (en) An artificial intelligence-based network equipment operation risk assessment system
CN117591850B (en) Data processing method, device, electronic device and medium based on expansion dock
WO2023066084A1 (en) Computing power distribution method and apparatus, and computing power server
WO2023125272A1 (en) Full-link stress testing method and apparatus in radius environment, computer device and storage medium
CN105141446A (en) Network equipment health degree assessment method determined based on objective weight
CN104581749A (en) Method and device for predicting traffic volume of mobile network data services
CN119892905B (en) Micro-service scheduling method, device, equipment and storage medium under k8s cluster
CN116366497A (en) Big data-based Internet of things card time sequence anomaly detection system
CN113918303A (en) Multitask distribution scheduling system based on microservice
CN117667602B (en) Cloud computing-based online service computing power optimization method and device
CN112261120A (en) Cloud-side cooperative task unloading method and device for power distribution internet of things
CN111901134B (en) Method and device for predicting network quality based on recurrent neural network model (RNN)
CN119863035B (en) Intelligent operation and maintenance management system, method and device for model simulation and data optimization
CN120146445A (en) System operation and maintenance method, device, equipment and storage medium based on deep learning
CN119271675B (en) Production data management method, system, equipment and medium based on industrial Internet of things
CN119379239B (en) Operation control system for power frequency transformer
CN114727309A (en) Network optimization method and device
CN119093367B (en) Automatic optimization method of distribution network based on multi-source data fusion
CN121442220A (en) A PON port intelligent switching system based on link state awareness
CN117971627B (en) Server host power-off test analysis system based on data analysis
CN119629067B (en) Lossless network construction method under multiple scenes of supporting electric power
CN112637960B (en) A power control method for network nodes based on GNSS
CN115914240B (en) Cross-chain transaction template management system based on DNS analysis
CN118446468A (en) Lithium battery diaphragm production plan scheduling management system based on data acquisition and analysis
CN119341990A (en) A multi-convergence and diversion equipment cluster management system and method

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
GR01 Patent grant
GR01 Patent grant