A communication pipeline asset intelligent protection method and system

Abstract

The present invention provides a method and system for intelligent protection of communication pipeline assets. The protection method includes: compiling communication pipeline asset risk labels and configuring labels for communication manholes; collecting communication pipeline asset status data; updating communication pipeline asset risk labels based on communication pipeline asset status data; calculating the communication pipeline asset risk probability based on the updated communication pipeline asset risk labels by a pre-built communication pipeline asset risk assessment model; identifying the communication pipeline asset risk probability exceeding a threshold value based on the communication pipeline asset risk probability calculation result; generating early warning information based on the communication manhole identifier exceeding the threshold value; based on the early warning information, maintenance personnel inspect and dispose of the communication manhole exceeding the threshold value, and feedback the early warning disposal result data, and execute the above steps in a loop. The intelligent protection method and system provided by the present invention realize the full-cycle intelligent protection of communication pipeline assets at the management process level, including pre-judgment, in-process warning, and post-event accountability.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, in particular to underground communication pipelines, and specifically to a method and system for intelligent protection of communication pipeline assets. Background Art

[0002] With the development of the internet and cloud computing, information networks have become an indispensable resource for people's lives, urban governance, and the development of various industries. Communication pipelines and optical cables have become essential for ensuring the smooth operation of these networks. At the same time, with the rapid pace of urbanization, communication pipelines, as core assets of operators, are frequently subject to illegal theft and tampering, resulting in significant asset losses. Existing models for communication pipeline asset protection and management include the following: The first is the traditional model, which relies entirely on regular manual inspections by pipeline patrol personnel. The second approach involves installing manhole cover status sensors on manhole covers. These sensors integrate gyroscopes, angle sensors, and vibration sensors to generate alarms for cover displacement and vibration. When the cover status changes, these statuses are transmitted to a management platform via wireless networks. The third approach involves installing electronic locks on manhole covers, which are wirelessly opened and closed, and status changes are transmitted to a management platform via wireless networks.

[0003] However, all three of the aforementioned solutions have flaws and inadequate protection capabilities for communication pipeline assets, failing to effectively protect them. The first solution, relying solely on manual inspections, cannot promptly and accurately detect theft and illegal cable routing. The second solution cannot distinguish between normal construction and illegal operations, making it ineffective asset protection. While the third solution can distinguish between normal construction and illegal operations through authentication of manhole cover locks, it lacks effective intelligent means to predict and provide early warnings of illegal activity. Furthermore, due to the diverse nature of illegal operations, the high false alarm rate of smart manhole covers, and the weak anti-smashing and anti-pry capabilities of the equipment, communication asset protection remains relegated to the post-event discovery and post-event response phase, failing to technically achieve a full-cycle intelligent protection of communication pipeline assets encompassing pre-emptive detection, in-process policing, and post-event accountability. Summary of the Invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method and system for intelligent protection of communication pipeline assets, which solves the problems of various illegal operations in communication manholes, high false alarm rate of smart manhole covers, weak anti-smashing and anti-pry capabilities of equipment, and avoids the protection of communication assets remaining in the post-discovery and post-processing stages. At the management process level, it realizes the full-cycle intelligent protection of communication pipeline assets, including advance prediction, in-process warning, and post-event accountability.

[0005] The technical solutions of the present invention are as follows:

[0006] The present invention provides a method for intelligent protection of communication pipeline assets, comprising the following steps:

[0007] Prepare risk labels for communication pipeline assets and configure labels for communication manholes;

[0008] Real-time collection of communication pipeline asset status data;

[0009] Update the risk label of communication pipeline assets based on the communication pipeline asset status data;

[0010] Based on the updated communication pipeline asset risk label, the communication pipeline asset risk probability is calculated by the pre-built communication pipeline asset risk assessment model;

[0011] Based on the calculation results of the communication pipeline asset risk probability, identify the communication manhole marks where the communication pipeline asset risk probability exceeds the threshold;

[0012] Generate warning information based on communication manhole identification exceeding the threshold;

[0013] According to the early warning information, maintenance personnel inspect and handle the communication manholes that exceed the threshold, and feedback the early warning treatment result data, and repeat the above steps.

[0014] In some achievable embodiments, compiling a communication pipeline asset risk tag includes:

[0015] Nine risk indicators related to communication pipeline asset risks were established based on the expert decision-making method, including: regional market popularity, communication pipeline asset value, existing maintenance capabilities, manhole accessibility, on-site operation difficulty, manhole resource leasing factors, time factors, event factors, and illegal occupation factors;

[0016] The nine risk indicators are quantified according to quantifiable assessment factors, and the communication pipeline asset risk label is compiled based on the quantification results.

[0017] In some feasible embodiments, the communication pipeline asset status data includes one or more of pipeline asset illegal occupation data, pipeline resource data, pipeline lease data, and event data.

[0018] In some achievable embodiments, calculating the communication pipeline asset risk probability using a pre-built communication pipeline asset risk assessment model includes:

[0019] Determine the number of neurons in the input layer of the BP neural network model based on the number of parameters contained in the communication pipeline asset risk label;

[0020] Construct a BP neural network model based on the number of input layer neurons, the preset hidden layer function and the preset output function;

[0021] Obtain a training set, train the BP neural network model using training samples and preset training functions, and obtain a communication pipeline asset risk assessment model;

[0022] The communication pipeline asset risk label is input into the communication pipeline asset risk assessment model to evaluate the communication pipeline asset risk probability.

[0023] In some feasible embodiments, the BP neural network model includes two hidden layers; the structure of the double-hidden-layer BP neural network is 9-9-1-1, that is, the number of the first hidden layer is 9, and the number of the second hidden layer is 1.

[0024] In some possible embodiments, the number of neurons in the input layer of the BP neural network model is 9, the number of neurons in the output layer is 1, and the number of neurons in the hidden layer is G; the number of neurons in any input layer is f i , i∈(1, 2…9); any hidden layer neuron is G j , j∈(1, 2…G); any output layer neuron is h k , k∈(1, 2);

[0025] The number of neurons G in the hidden layer is calculated as follows:

[0026]

[0027] Where f is the number of neurons in the input layer, h is the number of neurons in the output layer, and a is a constant, rounded between 1 and 10, and satisfies the value range of the number of neurons G in the hidden layer between 4 and 14.

[0028] In some feasible embodiments, the transfer function from the input layer to the first hidden layer adopts the Sigmoid function, the transfer function from the first hidden layer to the second hidden layer adopts the Purelin function, and the transfer function from the second hidden layer to the output layer adopts the Purelin function.

[0029] In some achievable embodiments, the training set includes: a certain amount of training samples and communication pipeline asset risk labels corresponding to the training samples.

[0030] In some achievable embodiments, determining the risk probability of communication pipeline assets through risk factor analysis includes:

[0031] Obtaining a risk factor indicator, where the risk factor indicator is a risk indicator with a cumulative variance contribution rate of more than 80% among the nine risk indicators in the training set;

[0032] The score coefficient matrix of the risk main cause indicator is used to calculate the score of the risk main cause indicator, and the weight of the risk main cause indicator is determined by the proportion of the risk main cause indicator to the cumulative variance contribution rate;

[0033] The comprehensive score of the main risk factors is calculated based on the weights and scores of the main risk factor indicators, which is the risk probability of communication pipeline assets.

[0034] The present invention also provides a communication pipeline asset intelligent protection system for the above protection method, comprising:

[0035] Communication pipeline asset intelligent protection device, used to collect data on illegal occupation of communication pipeline assets and push it to the communication pipeline asset intelligent monitoring platform;

[0036] The communication pipeline asset intelligent monitoring platform is used to receive communication pipeline asset status data reported by the communication pipeline asset intelligent protection device to update the communication pipeline asset risk tag. The communication pipeline asset intelligent monitoring platform also generates early warning information based on communication manhole identification exceeding the risk probability threshold and pushes it to the maintenance terminal;

[0037] The communication pipeline asset risk assessment platform is used to receive the updated communication pipeline asset risk tags pushed by the communication pipeline asset intelligent monitoring platform, calculate the communication pipeline asset risk probability through the communication pipeline asset risk assessment model, and push the communication manhole identifiers that exceed the risk probability threshold to the communication pipeline asset intelligent monitoring platform;

[0038] Maintenance terminal, used to receive early warning information pushed by the communication pipeline asset intelligent monitoring platform and display it to maintenance personnel;

[0039] A third-party system is used to push communication pipeline asset status data to the communication pipeline asset intelligent monitoring platform according to a pre-set mode;

[0040] Maintenance personnel will inspect and handle communication manholes that exceed the risk probability threshold, and report the early warning and disposal result data to the communication pipeline asset intelligent monitoring platform through the maintenance terminal.

[0041] The present invention has the following advantages over existing technologies: It provides a method and system for intelligent protection of communication pipeline assets. By integrating the functions of communication pipeline asset risk tags, communication pipeline asset protection devices, communication pipeline asset intelligent monitoring platforms, and communication pipeline asset risk assessment platforms, it achieves full-cycle intelligent protection of communication pipeline assets at the management process level, including pre-judgment, in-process warning, and post-event accountability. Specific advantages include at least one or more of the following:

[0042] (1) The intelligent protection method for communication pipeline assets provided by the present invention proposes risk labels for communication pipeline assets and divides and scores them. The risk assessment label division and scoring proposes practical risk assessment quantitative data for communication manholes, which can effectively realize risk assessment and then make standardized judgments on the risk level of communication pipeline assets.

[0043] (2) The intelligent protection method for communication pipeline assets provided by the present invention constructs a communication pipeline asset risk assessment model and realizes the quantitative prediction of the communication pipeline asset risk probability by using the BP neural network model. The result is more objective and avoids prediction errors caused by human judgment.

[0044] (3) The intelligent protection method for communication pipeline assets provided by the present invention adopts a double-hidden-layer BP neural network in constructing a communication pipeline asset risk assessment model, and determines the number of neurons in the input layer, output layer, and hidden layer according to the communication pipeline asset risk label, and selects a transfer function so that the model can achieve the best prediction effect.

[0045] (4) The intelligent protection method for communication pipeline assets provided by the present invention calculates the risk probability of communication pipeline assets by analyzing the main risk factors in combination with the risk labels (9) of communication pipeline assets during model training. The calculation results are more practical and feasible.

[0046] (5) The intelligent protection system for communication pipeline assets constructed by the present invention realizes intelligent perception of external force damage to communication pipeline assets based on intelligent protection devices, timely processing and evaluation updates of communication pipeline asset alarm information based on intelligent monitoring platforms and risk assessment platforms, and on-site dispatch and processing of alarm information based on maintenance terminals. The intelligent protection system can effectively realize dynamic assessment and precise maintenance of risky assets in application scenarios.

[0047] It should be understood that the implementation of any embodiment of the present invention does not mean that multiple or all of the above-mentioned beneficial effects must be possessed or achieved at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and those skilled in the art can, without inventive effort, derive other implementation drawings based on the provided drawings.

[0049] The structures, proportions, sizes, etc. illustrated in this specification are intended solely to complement the contents disclosed herein and to facilitate understanding and reading by persons skilled in the art. They are not intended to limit the conditions under which the present invention may be implemented and therefore have no substantive technical significance. Any structural modifications, changes in proportions, or adjustments in sizes, provided they do not affect the efficacy and objectives of the present invention, shall remain within the scope of the technical contents disclosed herein.

[0050] Figure 1 This is a schematic diagram of the overall process of a method for intelligent protection of communication pipeline assets according to one embodiment of the present invention;

[0051] Figure 2 This is a flow chart of a method for constructing a communication pipeline asset risk assessment model according to one embodiment of the present invention;

[0052] Figure 3 This is a schematic diagram of an application scenario of a communication pipeline asset intelligent protection system according to an embodiment of the present invention.

[0053] Markings in the figure:

[0054] 100. Intelligent protection method for communication pipeline assets;

[0055] 300. Communication pipeline asset intelligent protection system; 310. Communication pipeline asset risk assessment platform; 320. Communication pipeline asset intelligent monitoring platform; 330. Maintenance terminal; 340. Communication pipeline asset intelligent protection device; 350. Maintenance personnel; 360. Third-party system.

[0056] The same or corresponding symbols in the drawings indicate the same or corresponding parts. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in conjunction with the embodiments and drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0058] In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "connect," "fixed," etc. should be understood broadly. For example, they may refer to fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0059] It should be understood that the terms "comprises / comprising," "consisting of," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a product, apparatus, process, or method that includes a list of elements includes not only those elements but also, if necessary, other elements not explicitly listed, or elements inherent to such product, apparatus, process, or method. In the absence of further limitations, elements defined by the phrases "comprises / comprising," "consisting of," do not preclude the presence of additional identical elements in the product, apparatus, process, or method that includes the elements.

[0060] It should also be understood that terms such as "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device, component or structure referred to must have a specific direction, be constructed or operate in a specific direction, and should not be understood as limiting the present invention.

[0061] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0062] Currently, the protection of communication manhole assets remains at the post-event disposal stage, lacking the ability to anticipate illegal encroachment, making it impossible to conduct pre-judgment, in-process disposal, and post-event accountability. In view of this, and to achieve the goal of full-cycle intelligent protection of communication pipeline assets, including pre-judgment, in-process policing, and post-event accountability, the present invention provides a method and system for intelligent protection of communication pipeline assets to address existing problems and meet engineering needs.

[0063] The implementation of the present invention is described in detail below in conjunction with preferred embodiments.

[0064] See also Figure 1 As shown in the flowchart, the communication pipeline asset intelligent protection method 100 includes the following steps: S10, compiling a communication pipeline asset risk label and configuring the label for the communication manhole; S11, collecting communication pipeline asset status data; S12, updating the communication pipeline asset risk label based on the communication pipeline asset status data; S13, calculating the communication pipeline asset risk probability based on the updated communication pipeline asset risk label using a pre-built communication pipeline asset risk assessment model; S14, identifying the communication manhole identifiers whose communication pipeline asset risk probability exceeds a threshold based on the communication pipeline asset risk probability calculation result; S15, generating an early warning message based on the communication manhole identifiers that exceed the threshold; S16, based on the early warning message, maintenance personnel inspect and handle the communication manholes that exceed the threshold, and feedback the early warning handling result data, and repeat step S11. The intelligent protection method provided by the present invention realizes the full-cycle intelligent protection of communication pipeline assets at the management process level, including pre-judgment, in-process warning, and post-event accountability.

[0065] The specific implementation of the method steps of the present invention is described in detail below.

[0066] S10: Prepare risk labels for communication pipeline assets and configure labels for communication manholes.

[0067] It should be noted that the risk of communication pipeline assets is related to the following nine parameters: regional market heat, communication pipeline asset value, existing maintenance capabilities, manhole accessibility, difficulty of on-site operations, resource leasing factors in manholes, time factors, event factors, and illegal occupation factors.

[0068] Therefore, the preparation of risk labels for communication pipeline assets includes:

[0069] Based on the expert decision-making method, nine risk indicators related to communication pipeline asset risks were established, including: regional market popularity, communication pipeline asset value, existing maintenance capabilities, manhole accessibility, on-site operation difficulty, manhole resource leasing factors, time factors, event factors, and illegal occupation factors;

[0070] The nine risk indicators are quantified according to quantifiable assessment factors, and the communication pipeline asset risk label is compiled based on the quantification results.

[0071] When performing quantitative processing, for example, scoring can be performed based on experience. In an embodiment of the present invention, communication pipeline asset risk label data is compiled based on the quantitative processing results. The quantification process is converted using a scoring table, which is shown in Table 1 below.

[0072] Table 1 Communication pipeline asset risk label scoring table

[0073]

[0074] For example: A community with more than 10,000 households is defined as a large community. 10,000 to 15,000 households will be given 8 points, 15,000 to 20,000 households will be given 9 points, and more than 20,000 households will be given 10 points.

[0075] S11, collect communication pipeline asset status data through the communication pipeline asset intelligent monitoring platform.

[0076] It should be noted that the communication pipeline asset status data includes: illegal occupation of pipeline assets data, communication pipeline resource data, pipeline leasing data, special event data, etc.

[0077] In this step, intelligent protection devices for communication pipeline assets are installed on communication manholes to collect real-time data on illegal use of communication pipeline assets. Manual inspections are also used to collect data on illegal use of communication pipeline assets in communication manholes without intelligent protection devices. Synchronization with third-party systems also provides access to communication pipeline resource data, pipeline lease data, special event data, and more.

[0078] S12, after the communication pipeline asset intelligent monitoring platform receives the communication pipeline asset status data, it updates the communication pipeline asset risk label and pushes it to the communication pipeline asset risk assessment platform.

[0079] S13, the communication pipeline asset risk assessment platform has pre-built a communication pipeline asset risk assessment model, which calculates the communication pipeline asset risk probability based on the communication pipeline asset risk label.

[0080] In this step, a BP neural network model is constructed. A BP (back propagation) neural network is a multi-layer feedforward neural network trained using the back propagation error algorithm. It is widely used in artificial intelligence network models. Its basic concept is the gradient descent method, which uses gradient search techniques to minimize the mean square error between the network's actual output and the expected output. The BP neural network model consists of an input layer, a hidden layer, and an output layer, where the hidden layer can include multiple sublayers.

[0081] A neuron is a simple abstraction of a biological neuron. It has multiple inputs, each with a corresponding weight. The neuron multiplies the inputs by the weights, sums the results, and then processes them through an activation function to produce an output. This output can then serve as input for other neurons, forming a neural network.

[0082] In some embodiments, as Figure 2 As shown in FIG, a communication pipeline asset risk assessment model based on the BP neural network model is constructed, which can be specifically carried out as follows:

[0083] S130, develop risk labels for communication pipeline assets;

[0084] The communication pipeline asset risk assessment model constructed by the present invention adopts a BP neural network model, and the model is closely related to the communication pipeline asset risk label. Therefore, it is easy to understand that the communication pipeline asset risk label is formulated here. This is the same as the aforementioned S10. The label has been formulated before and there is no need to formulate it again. It can be used directly according to the label.

[0085] S131, determining the number of neurons in the input layer of the BP neural network model according to the number of parameters contained in the communication pipeline asset risk label;

[0086] In this embodiment, the communication pipeline asset risk label includes nine parameters, including regional market popularity, communication pipeline asset value, existing maintenance capabilities, manhole accessibility, on-site operation difficulty, resource leasing factors in the manhole, time factors, event factors, and illegal occupation factors. Therefore, the number of neurons in the input layer of the BP neural network model to be established is nine.

[0087] S132, constructing a BP neural network model according to the number of input layer neurons, the preset hidden layer function, and the preset output function;

[0088] In this embodiment, the BP neural network model can only receive input data having the same number as the input nodes, and calculates the mathematical model of the output data through the preset hidden layer function and the preset output function.

[0089] Considering that the number of hidden layers significantly impacts the recognition performance of the BP neural network model, too few hidden layers can result in low neural network recognition accuracy. Generally speaking, a neural network with two hidden layers can represent any nonlinear decision program. However, too many hidden layers increase training complexity and can also lead to overfitting. Therefore, in this embodiment, two hidden layers are selected.

[0090] In this embodiment, the number of neurons in the input layer of the BP neural network model is 9, the number of neurons in the output layer is 1, and the number of neurons in the hidden layer is G; the number of neurons in any input layer is f i , i∈(1, 2…9); any hidden layer neuron is G j , j∈(1, 2…G); any output layer neuron is h k , k∈(1, 2);

[0091] The number of neurons G in the hidden layer is calculated as follows:

[0092]

[0093] Where f is the number of neurons in the input layer, h is the number of neurons in the output layer, and a is a constant, rounded between 1 and 10, and satisfies the value range of the number of neurons G in the hidden layer between 4 and 14.

[0094] Based on multiple experiments, the best prediction results were achieved when the number of first hidden layers was 9 and the number of second hidden layers was 1. Therefore, the structure of the two-hidden-layer BP neural network was determined to be 9-9-1-1, meaning 9 input layer neurons, 9 first hidden layer neurons, 1 second hidden layer neuron, and 1 output data point, namely the risk probability of communication pipeline assets.

[0095] In this embodiment, the transfer function from the input layer to the first hidden layer uses a nonlinear transformation function, namely, a sigmoid function. The transfer function from the first hidden layer to the second hidden layer is a purelin function. The transfer function from the second hidden layer to the output layer is also a purelin function. In this case, the BP neural network model achieves the best prediction results.

[0096] In this embodiment, the BP neural network model obtains an output data according to a preset output function, that is, the risk probability of the communication pipeline asset.

[0097] S133, obtaining a training set, and training a BP neural network model using the training samples and a preset training function to obtain a communication pipeline asset risk assessment model;

[0098] In this embodiment, the training set includes: a certain number of training samples and communication pipeline asset risk labels corresponding to the training samples. The BP neural network model is trained using the training samples and the preset training function to obtain a communication pipeline asset risk assessment model.

[0099] In this embodiment, the BP neural network model is iteratively trained through training samples, and ultimately the optimal values ​​of the unknown mathematical parameters in the BP neural network model are obtained.

[0100] S134: Input the communication pipeline asset risk tag into the communication pipeline asset risk assessment model to evaluate and obtain the communication pipeline asset risk probability.

[0101] In this embodiment, the sample risk probability is determined by risk factor analysis, which includes the following steps:

[0102] (1) Obtaining the main risk factor indicator, which is the risk indicator with a cumulative variance contribution rate of more than 80% among the 9 risk indicators in the training set;

[0103] (2) Calculate the score of the main risk factor indicator using the score coefficient matrix of the main risk factor indicator, and determine the weight of the main risk factor indicator by the proportion of the main risk factor indicator in the cumulative variance contribution rate;

[0104] (3) Calculate the comprehensive score of the main risk factors based on the weights and scores of the main risk factor indicators, which is the risk probability of the communication pipeline assets.

[0105] By inputting the acquired communication pipeline asset risk tags into the established communication pipeline asset risk assessment model, the communication pipeline asset risk probability can be obtained through risk main cause analysis.

[0106] S135, determining whether the communication pipeline asset risk probability exceeds a threshold.

[0107] S14, based on the calculation result of the communication pipeline asset risk probability, identifying the communication manhole identifier whose communication pipeline asset risk probability exceeds a threshold.

[0108] During the entire modeling process, the communication pipeline asset risk assessment platform constructs a communication pipeline asset risk assessment model through a communication pipeline asset risk assessment algorithm based on the BP neural network algorithm, dynamically calculates the communication pipeline asset risk assessment value (risk probability) of all manholes, and pushes the communication manhole identifiers whose asset risk assessment value (risk probability) exceeds the threshold to the communication pipeline asset intelligent monitoring platform.

[0109] It should be noted that the threshold value is the risk probability limit value, and in the embodiment of the present invention, it is set to 0.7.

[0110] S15, generating warning information according to the communication manhole identification exceeding the threshold.

[0111] The communication pipeline asset risk assessment platform pushes the communication manhole identification of the communication pipeline asset risk probability exceeding the threshold to the communication pipeline asset intelligent monitoring platform. The communication pipeline asset intelligent monitoring platform generates early warning information based on the received communication manhole identification, pushes it to the maintenance terminal and displays it.

[0112] It should be noted that the warning information includes: communication manhole identification, warning time, etc.

[0113] The maintenance terminal is the terminal equipment of pipeline maintenance personnel. Pipeline maintenance personnel can check early warning information in time and perform fixed-point maintenance based on the early warning information.

[0114] S16, based on the warning information, the maintenance personnel inspect and handle the communication manholes that exceed the threshold, and feedback the warning handling result data, and repeat step S11.

[0115] According to the warning information received from the maintenance terminal, the maintenance personnel inspect and handle the abnormal communication manhole, and report the warning handling result data to the communication pipeline asset intelligent monitoring platform, and repeat step S11.

[0116] It should be noted that the early warning and disposal results include: whether the communication pipeline assets have been encroached upon; if so, the name of the encroaching party, etc.

[0117] Pipeline maintenance personnel inspect and address abnormal communication manholes based on the risk characteristics identified in the early warning information. They then report these findings to the intelligent monitoring platform for communication pipeline assets via the maintenance terminal. The intelligent monitoring platform then pushes these findings to the risk assessment platform. The risk assessment platform then feeds these findings into a neural network for model training, improving prediction accuracy through the model's self-learning mechanism.

[0118] The present invention also provides a communication pipeline asset intelligent protection system, such as Figure 3 As shown, the communication pipeline asset intelligent protection system 300 includes:

[0119] The communication pipeline asset intelligent monitoring platform 320 is used to receive the communication pipeline asset status data reported by the communication pipeline asset intelligent protection device 340, update the communication pipeline asset risk label, and generate early warning information for the communication manhole identification that exceeds the risk probability threshold and push it to the maintenance terminal 330.

[0120] The communication pipeline asset risk assessment platform 310 is configured to receive communication pipeline asset status data pushed by the communication pipeline asset intelligent monitoring platform 320, calculate the communication pipeline asset risk probability using the communication pipeline asset risk assessment model, and push communication manhole identifiers exceeding the risk probability threshold to the communication pipeline asset intelligent monitoring platform 320. The communication pipeline asset intelligent monitoring platform 320 generates warning information for communication manhole identifiers exceeding the risk probability threshold and pushes it to the maintenance terminal 330.

[0121] The communication pipeline asset intelligent protection device 340 is used to protect assets in the communication manhole. When facing external force impact, external prying, or cutting, it generates an alarm and collects real-time status data of the communication pipeline assets and pushes it to the communication pipeline asset intelligent monitoring platform 320.

[0122] The maintenance terminal 330 is used to receive the warning information pushed by the communication pipeline asset intelligent monitoring platform 320 and display it to the maintenance personnel 350.

[0123] The third-party system 360 is used to push the communication pipeline asset status data to the communication pipeline asset intelligent monitoring platform 320 according to a pre-set mode.

[0124] Maintenance personnel 350 inspect and handle communication manholes that exceed the risk probability threshold, and report the warning and handling results to the communication pipeline asset intelligent monitoring platform 320 via the maintenance terminal 330.

[0125] It is easy for those skilled in the art to understand that, under the premise of no conflict, the above preferred solutions can be freely combined and superimposed.

[0126] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A communication pipeline asset intelligent protection method, characterized in that: The steps include: Prepare risk labels for communication pipeline assets and configure labels for communication manholes; Real-time collection of communication pipeline asset status data; Update the risk label of communication pipeline assets based on the communication pipeline asset status data; Based on the updated communication pipeline asset risk label, the communication pipeline asset risk probability is calculated by the pre-built communication pipeline asset risk assessment model; Based on the calculation results of the communication pipeline asset risk probability, identify the communication manhole marks where the communication pipeline asset risk probability exceeds the threshold; Generate warning information based on communication manhole identification exceeding the threshold; According to the warning information, maintenance personnel will check and deal with the communication manholes that exceed the threshold, and feedback the warning and treatment result data, and repeat the above steps; in The preparation of communication pipeline asset risk labels includes: Nine risk indicators related to communication pipeline asset risks were established based on the expert decision-making method, including: regional market popularity, communication pipeline asset value, existing maintenance capabilities, manhole accessibility, on-site operation difficulty, manhole resource leasing factors, time factors, event factors, and illegal occupation factors; Quantify the nine risk indicators according to quantifiable assessment factors and compile a communication pipeline asset risk label based on the quantification results; and The communication pipeline asset status data includes: one or more of pipeline asset illegal occupation data, pipeline resource data, pipeline lease data, and event data.

2. The protection method according to claim 1, characterized in that: The calculation of the communication pipeline asset risk probability using the pre-built communication pipeline asset risk assessment model includes: Determine the number of neurons in the input layer of the BP neural network model based on the number of parameters contained in the communication pipeline asset risk label; Construct a BP neural network model based on the number of input layer neurons, the preset hidden layer function and the preset output function; Obtain a training set, train the BP neural network model using training samples and preset training functions, and obtain a communication pipeline asset risk assessment model; The communication pipeline asset risk label is input into the communication pipeline asset risk assessment model to evaluate the communication pipeline asset risk probability.

3. The protection method according to claim 2, characterized in that: The BP neural network model includes two hidden layers; the structure of the double-hidden-layer BP neural network is 9-9-1-1, that is, the number of the first hidden layer is 9, and the number of the second hidden layer is 1.

4. The protection method according to claim 3, characterized in that: The number of neurons in the input layer of the BP neural network model is 9, the number of neurons in the output layer is 1, and the number of neurons in the hidden layer is G; the number of neurons in any input layer is f i , i∈(1, 2…9); any hidden layer neuron is G j , j∈(1, 2…G); any output layer neuron is h k , k∈(1, 2); The number of neurons G in the hidden layer is calculated as follows: ； in, f is the number of neurons in the input layer, h is the number of neurons in the output layer, a is a constant, rounded between 1 and 10, and satisfies the value range of the number of hidden layer neurons G between 4 and 14.

5. The protection method according to claim 4, characterized in that: The transfer function from the input layer to the first hidden layer adopts the Sigmoid function, the transfer function from the first hidden layer to the second hidden layer adopts the Purelin function, and the transfer function from the second hidden layer to the output layer adopts the Purelin function.

6. The protection method according to claim 2, characterized in that: The training set includes: a certain amount of training samples and communication pipeline asset risk labels corresponding to the training samples.

7. The protection method according to claim 2, characterized in that: Determine the risk probability of communication pipeline assets through risk factor analysis, including: Obtaining a risk factor indicator, where the risk factor indicator is a risk indicator with a cumulative variance contribution rate of more than 80% among the nine risk indicators in the training set; The score coefficient matrix of the risk main cause indicator is used to calculate the score of the risk main cause indicator, and the weight of the risk main cause indicator is determined by the proportion of the risk main cause indicator to the cumulative variance contribution rate; The comprehensive score of the main risk factors is calculated based on the weights and scores of the main risk factor indicators, which is the risk probability of communication pipeline assets.

8. A communication pipeline asset intelligent protection system for the protection method according to any one of claims 1 to 7, characterized in that: include: Communication pipeline asset intelligent protection device, used to collect data on illegal occupation of communication pipeline assets and push it to the communication pipeline asset intelligent monitoring platform; The communication pipeline asset intelligent monitoring platform is used to receive communication pipeline asset status data reported by the communication pipeline asset intelligent protection device to update the communication pipeline asset risk tag. The communication pipeline asset intelligent monitoring platform also generates early warning information based on communication manhole identification exceeding the risk probability threshold and pushes it to the maintenance terminal; The communication pipeline asset risk assessment platform is used to receive the updated communication pipeline asset risk tags pushed by the communication pipeline asset intelligent monitoring platform, calculate the communication pipeline asset risk probability through the communication pipeline asset risk assessment model, and push the communication manhole identifiers that exceed the risk probability threshold to the communication pipeline asset intelligent monitoring platform; Maintenance terminal, used to receive early warning information pushed by the communication pipeline asset intelligent monitoring platform and display it to maintenance personnel; A third-party system is used to push communication pipeline asset status data to the communication pipeline asset intelligent monitoring platform according to a pre-set mode; Maintenance personnel will inspect and handle communication manholes that exceed the risk probability threshold, and report the early warning and disposal result data to the communication pipeline asset intelligent monitoring platform through the maintenance terminal.

Images