Waterway transportation safety supervision calculation method and system

Abstract

The invention discloses a waterway transportation safety supervision measurement and calculation method and system, and relates to the technical field of waterway transportation, and the method comprises the steps: collecting and preprocessing multi-dimensional data related to waterway transportation safety supervision, and generating a multi-dimensional feature vector matrix; based on the multi-dimensional feature vector matrix, constructing a multi-dimensional input-output model, calculating safety benefits of each sub-industry, and integrating the safety benefits to obtain total safety benefits of the industry; constructing an economic and ecological network of the waterway transportation industry and upstream and downstream industry chains by using the overall safety benefit of the industry, analyzing the comprehensive benefit of safety supervision on multi-level economic nodes, and generating comprehensive benefit data; by constructing an economic and ecological network of the waterway transportation industry and upstream and downstream industry chains, the diffusion benefit of safety supervision among network nodes and the comprehensive influence of the safety supervision on multi-level economic nodes are quantitatively analyzed, so that the global value of safety supervision on industry ecology is revealed.

Description

Technical Field

[0001] The present invention relates to the technical field of water transport, and in particular to a method and system for monitoring and calculating water transport safety. Background Art

[0002] With the rapid development of the water transport industry, the importance of safety supervision has become increasingly prominent. In recent years, the frequent occurrence of various accidents has not only caused huge losses to the economy, but also had a serious impact on the ecological environment and social stability. In this context, data-driven water transport safety supervision technology has gradually become a research hotspot. By collecting and analyzing multi-dimensional data (such as capital investment, safety technology investment, historical accident records and environmental risk data), it can more comprehensively evaluate the impact of safety supervision on the industry's economic and ecological benefits. However, existing technologies usually only focus on the safety supervision effect of a single dimension, such as accident reduction rate or direct economic benefits, and it is difficult to fully reflect the multi-level benefits of safety supervision in a complex economic ecological network.

[0003] The existing technology has shortcomings in the following aspects: First, it fails to effectively integrate multi-dimensional data to build a dynamic input-output model, resulting in a lack of comprehensiveness in the evaluation of the benefits of safety supervision; second, it lacks an analysis of the economic ecological network of the water transport industry and the upstream and downstream industrial chains, and fails to quantify the diffusion benefits of safety supervision in the industrial chain. In addition, the existing methods are insufficient in the ability to dynamically adjust risk predictions, and are unable to optimize the safety benefit allocation mechanism based on future risk parameters. Therefore, how to comprehensively evaluate the multi-level benefits of safety supervision and optimize the benefit distribution of the upstream and downstream industrial chains through multi-dimensional data analysis and dynamic modeling has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for measuring and supervising water transportation safety to solve the problem of how to dynamically optimize the safety benefits of the water transportation industry and its diffusion benefits in the economic ecological network based on multi-dimensional data and risk prediction.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for measuring and supervising waterway transportation safety, which comprises:

[0008] Collect and pre-process multi-dimensional data related to water transport safety supervision to generate a multi-dimensional feature vector matrix;

[0009] Based on the multi-dimensional eigenvector matrix, a multi-dimensional input-output model is constructed to calculate the safety benefits of each sub-industry and integrate them to obtain the overall safety benefits of the industry;

[0010] By using the overall safety benefits of the industry, we can build an economic ecological network of the water transport industry and the upstream and downstream industrial chains, analyze the comprehensive benefits of safety supervision on multi-level economic nodes, and generate comprehensive benefit data;

[0011] Based on the comprehensive benefit data and risk-related data in multidimensional data, a risk prediction model is constructed to predict future risk parameters;

[0012] Based on the predicted future risk parameters, the safety benefit contribution value of each sub-industry and the multi-level benefit data of the ecological network are dynamically updated to generate the final measurement report on water transport safety supervision.

[0013] As a preferred solution of the water transport safety supervision and calculation method of the present invention, wherein: the multi-dimensional data includes industry input-output data, economic ecological network data and risk-related data;

[0014] The industry input-output data include capital investment, safety technology investment, transportation volume and total output value; the economic ecological network data include capital flow and safety supervision impact data; risk-related data include historical accident records and environmental risk data;

[0015] The preprocessing includes data standardization, data denoising and missing value filling processing;

[0016] Generating a multi-dimensional feature vector matrix refers to transforming the pre-processed data to form a multi-dimensional feature vector matrix.

[0017] As a preferred solution of the water transport safety supervision and calculation method of the present invention, the following steps are included: based on the multidimensional characteristic vector matrix, a multidimensional input-output model is constructed to calculate the safety benefit contribution value of each sub-industry, and the overall safety benefit of the industry is obtained by integration.

[0018] Extracting capital flow data, total output value, security input intensity and transportation volume from the multidimensional eigenvector matrix;

[0019] Based on the extracted capital flow data and total output value, the input coefficient matrix is ​​constructed;

[0020] Integrate the extracted safety input intensity and transportation volume to form a safety supervision input vector;

[0021] Build a demand vector based on historical market demand;

[0022] A multidimensional input-output model is constructed to calculate the total output of the sub-industry based on the input coefficient matrix, safety supervision input vector and demand vector. The expression is:

[0023] X=(IA) -1 (Y+B·S);

[0024] Among them, X represents the total output of the sub-industry, I represents the unit matrix, A represents the input coefficient matrix, B represents the safety supervision input vector, Y represents the demand vector, and S represents the total safety supervision investment;

[0025] According to the total output of the sub-industry, the value-added income is defined as the increase in industry output value due to safety supervision, and the expression is:

[0026] C v =δ v ·(X v -E v );

[0027] Among them, C v represents the added value of the vth sub-industry, δ v represents the value-added coefficient of the vth sub-industry, X v represents the total output of the vth sub-industry under safety supervision, E v represents the benchmark output of the vth sub-industry without safety supervision;

[0028] The loss reduction benefit is defined as the reduction in economic losses caused by accidents due to safety supervision, and the expression is:

[0029]

[0030] Among them, D v represents the impairment income of the vth sub-industry, P k represents the probability of the kth type of accident occurring without safety supervision, F k represents the probability of occurrence of the kth type of accident under safety supervision, represents the average economic loss caused by the kth type of accident to the vth sub-industry, and m represents the total number of accidents;

[0031] Add the added value and reduced value to get the safety benefit contribution of each sub-industry;

[0032] Summarize the safety benefit contribution values ​​of all sub-industries to obtain the overall safety benefit of the industry.

[0033] As a preferred solution of the water transport safety supervision and calculation method of the present invention, wherein: utilizing the overall safety benefits of the industry to construct an economic ecological network of the water transport industry and the upstream and downstream industrial chains includes the following steps:

[0034] Define the water transport sub-industry and major upstream and downstream industries as network nodes;

[0035] According to the network nodes and industry safety benefits, the influence propagation intensity between network nodes in safety supervision is calculated, and the expression is:

[0036]

[0037] Among them, A ij represents the security supervision influence of node i on node j, R i represents the overall safety benefit of node i, represents the diffusion coefficient of safety supervision, and W ij represents the original relationship strength between node i and node j, B k represents the safety benefit contribution value of the kth node;

[0038] Based on the intensity of safety supervision influence between nodes in the network, an adjacency matrix is ​​constructed to form an economic ecological network of the water transport industry and the upstream and downstream industrial chains.

[0039] As a preferred solution of the water transport safety supervision and calculation method of the present invention, wherein: analyzing the comprehensive benefits of safety supervision on multi-level economic nodes and generating comprehensive benefit data includes the following steps:

[0040] Using the network diffusion model, the benefits of safety supervision investment in the economic ecological network are calculated, and the expression is:

[0041]

[0042] in, represents the comprehensive benefit of node j after the tth diffusion, n represents the total number of nodes in the network, α represents the diffusion attenuation coefficient, represents the benefit of node i in the t-1th diffusion, β j represents the self-benefit coefficient of node j, R j represents the overall safety benefit of node j;

[0043] Based on the benefits of safety supervision investment in the economic ecological network, the economic ecological network is divided into direct impact layer, indirect impact layer and external social benefit layer, and the benefits of each layer are calculated;

[0044] Integrate benefits at all levels to obtain comprehensive benefit data for safety supervision.

[0045] As a preferred solution of the water transport safety supervision and calculation method of the present invention, wherein: based on the comprehensive benefit data and risk-related data in the multidimensional data, a risk prediction model is constructed to predict future risk parameters, including the following steps:

[0046] Based on the comprehensive benefit data of safety supervision and the historical accident records and environmental risk data in risk-related data, the comprehensive risk prediction value is calculated, and the expression is:

[0047]

[0048] Among them, H t represents the comprehensive risk prediction value at time t, Pt-1,k represents the historical probability of the kth type of accident occurring at time t-1, L k represents the average economic loss value of the kth type of accident, M represents the comprehensive benefit of safety supervision, Q represents the benchmark safety benefit of the industry, ∈ represents the smoothing coefficient, λ k (t) represents the impact weight of the risk of the k-th accident at time t on the comprehensive risk, φ represents the external environment impact coefficient, G t Represents the environmental risk data at time t.

[0049] As a preferred solution of the water transport safety supervision and calculation method of the present invention, wherein: according to the predicted future risk parameters, the safety benefit contribution value of each sub-industry and the multi-level benefit data of the ecological network are dynamically updated to generate the final calculation report of water transport safety supervision, including the following steps:

[0050] Mapping predicted future risk parameters to input-output models and economic-ecological network models;

[0051] Combined with the dynamic changes of risk parameters, the input coefficients among sub-industries in the input-output model are adjusted in real time to calculate the dynamic contribution of different safety inputs to the economic benefits of the industry;

[0052] Dynamically optimize the distribution mechanism of multi-level benefits in the economic ecological network, and update the comprehensive benefits of the upstream and downstream industrial chains in real time;

[0053] Integrate the results of the dynamically adjusted input-output model and economic ecological network model to generate the final measurement report for water transport safety supervision.

[0054] In a second aspect, the present invention provides a water transport safety supervision and measurement system, comprising:

[0055] The data processing module collects and pre-processes multi-dimensional data related to water transport safety supervision to generate a multi-dimensional feature vector matrix;

[0056] The benefit calculation module builds a multi-dimensional input-output model based on the multi-dimensional feature vector matrix, calculates the safety benefits of each sub-industry, and integrates them to obtain the overall safety benefits of the industry;

[0057] The network analysis module uses the overall safety benefits of the industry to build an economic ecological network of the water transport industry and the upstream and downstream industrial chains, analyzes the comprehensive benefits of safety supervision on multi-level economic nodes, and generates comprehensive benefit data;

[0058] The risk prediction module builds a risk prediction model based on comprehensive benefit data and risk-related data in multidimensional data to predict future risk parameters;

[0059] The dynamic update module dynamically updates the safety benefit contribution value of each sub-industry and the multi-level benefit data of the ecological network according to the predicted future risk parameters, and generates the final measurement report of water transport safety supervision.

[0060] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the water transport safety supervision and measurement method as described in the first aspect of the present invention is implemented.

[0061] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the water transport safety supervision and measurement method as described in the first aspect of the present invention is implemented.

[0062] The beneficial effects of the present invention are as follows: by collecting and preprocessing multidimensional data related to water transport safety supervision, a multidimensional feature vector matrix is ​​generated, which provides a standardized and complete data basis for subsequent modeling; the multidimensional input-output model constructed based on this can not only calculate the safety benefit contribution value of each sub-industry, but also integrate the overall safety benefit of the industry, providing a scientific basis for evaluating the direct economic benefits of safety supervision; by constructing an economic ecological network of the water transport industry and the upstream and downstream industrial chains, the diffusion benefits of safety supervision between network nodes and its comprehensive impact on multi-level economic nodes are quantitatively analyzed, thereby revealing the global value of safety supervision to the industry ecology; a risk prediction model is constructed, which can dynamically predict future risk parameters and optimize the input-output model and the economic ecological network accordingly. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0064] Figure 1 This is a flow chart of the water transport safety supervision and measurement method in Example 1.

[0065] Figure 2 This is a diagram of the water transport safety supervision and measurement system in Example 1. DETAILED DESCRIPTION

[0066] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0067] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0068] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0069] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a method for calculating waterway transportation safety supervision, comprising the following steps:

[0070] S1. Collect and preprocess multidimensional data related to water transport safety supervision to generate a multidimensional feature vector matrix.

[0071] S1.1. Multidimensional data includes industry input-output data, economic ecological network data and risk-related data.

[0072] S1.1.1 Industry input-output data include capital investment, safety technology investment, transportation volume and total output value; economic ecological network data include capital flow and safety supervision impact data; risk-related data include historical accident records and environmental risk data.

[0073] Furthermore, industry input-output data are obtained through statistical yearbooks, industry association reports, and corporate financial statements.

[0074] Economic ecological network data obtains upstream and downstream capital flow and regulatory impact data through inter-enterprise capital flow analysis, supply chain research and safety regulatory policy impact assessment.

[0075] Risk-related data are obtained through historical accident record databases, ship monitoring systems (such as AIS data), and meteorological, tidal, and traffic density data provided by environmental monitoring agencies to obtain historical accident and environmental risk data.

[0076] S1.2. Preprocessing includes data standardization, data denoising and missing value filling; generating a multi-dimensional feature vector matrix refers to transforming the preprocessed data to form a multi-dimensional feature vector matrix.

[0077] Furthermore, standardization is the process of normalizing the data and unifying its units so that data of different dimensions can be used in the same model.

[0078] Data denoising refers to cleaning up outliers and noise to reduce data errors.

[0079] Missing value filling is to fill in the missing values ​​in the data to ensure data integrity.

[0080] S2. Based on the multidimensional eigenvector matrix, a multidimensional input-output model is constructed to calculate the safety benefit contribution value of each sub-industry and integrate them to obtain the overall safety benefit of the industry.

[0081] S2.1. Extract capital flow data, total output value, safety input intensity and transportation volume from the multidimensional feature vector matrix; construct an input coefficient matrix based on the extracted capital flow data and total output value.

[0082] It should be noted that the input coefficient matrix describes the economic connection between sub-industries and provides a basic framework for calculating safety benefits; it clarifies the proportional relationship between capital flow and total output value and quantifies the degree of economic dependence between sub-industries.

[0083] S2.2. Integrate the extracted safety input intensity and transportation volume to form a safety supervision input vector; construct a demand vector based on historical market demand; construct a multidimensional input-output model, and calculate the total output of the sub-industry based on the input coefficient matrix, safety supervision input vector and demand vector. The expression is:

[0084] X=(IA) -1 (Y+B·S);

[0085] Among them, X represents the total output of the sub-industry, I represents the unit matrix, A represents the input coefficient matrix, B represents the safety supervision input vector, Y represents the demand vector, and S represents the total safety supervision investment.

[0086] It should be noted that the safety supervision input vector clearly quantifies the investment intensity of different sub-industries in safety supervision, accurately reflects changes in market demand, provides output estimates based on safety input and market demand, and dynamically reflects the impact of safety supervision on industry output.

[0087] S2.3. Based on the total output of the sub-industry, the value-added income is defined as the increase in industry output value due to safety supervision, expressed as:

[0088] C v =δ v ·(X v -E v );

[0089] Among them, C v represents the added value of the vth sub-industry, δ v represents the value-added coefficient of the vth sub-industry, X vrepresents the total output of the vth sub-industry under safety supervision, E v represents the benchmark output of the vth sub-industry without safety supervision;

[0090] The loss reduction benefit is defined as the reduction in economic losses caused by accidents due to safety supervision, and the expression is:

[0091]

[0092] Among them, D v represents the impairment income of the vth sub-industry, P k represents the probability of the kth type of accident occurring without safety supervision, F k It represents the probability of occurrence of the k-th accident under safety supervision, represents the average economic loss caused by the k-th accident to the v-th sub-industry, and m represents the total number of accidents.

[0093] It should be noted that clarifying the direct economic benefits of safety supervision on the growth of industry output value facilitates the analysis of the positive incentive effect of regulatory policies, and loss reduction benefits intuitively quantify the effect of safety supervision on reducing accident risks.

[0094] S2.4. Add the added value gains and reduced value gains to obtain the safety benefit contribution of each sub-industry.

[0095] Specifically, the expression of the safety benefit contribution value of the sub-industry is:

[0096] B v =C v +D v ;

[0097] Among them, B v Represents the safety benefit contribution value of the vth sub-industry.

[0098] S2.5. Summarize the safety benefit contribution values ​​of all sub-industries to obtain the overall safety benefit of the industry.

[0099] Specifically, the expression of the industry's overall safety benefit is:

[0100]

[0101] Among them, M represents the overall safety benefit of the industry, and n represents the total number of sub-industries.

[0102] S3. Utilize the overall safety benefits of the industry to build an economic ecological network of the water transport industry and the upstream and downstream industrial chains, analyze the comprehensive benefits of safety supervision on multi-level economic nodes, and generate comprehensive benefit data.

[0103] S3.1. Define the water transport sub-industry and major upstream and downstream industries as network nodes; calculate the influence propagation intensity between network nodes in safety supervision based on network nodes and industry safety benefits, and the expression is:

[0104]

[0105] Among them, A ij represents the security supervision influence of node i on node j, R i represents the overall safety benefit of node i, represents the diffusion coefficient of safety supervision, and W ij represents the original relationship strength between node i and node j, B k represents the safety benefit contribution value of the kth node;

[0106] Based on the intensity of safety supervision influence between nodes in the network, an adjacency matrix is ​​constructed to form an economic ecological network of the water transport industry and the upstream and downstream industrial chains.

[0107] It should be noted that the economic ecological network fully describes the economic connections between the water transport industry and its upstream and downstream industries, and provides structured input for subsequent diffusion models; the calculation of network attributes helps to identify core nodes and key connections and optimize safety supervision strategies.

[0108] S3.2. Using the network diffusion model, calculate the benefits of safety supervision investment in the economic ecological network, the expression is:

[0109]

[0110] in, represents the comprehensive benefit of node j after the tth diffusion, N represents the total number of nodes in the network, α represents the diffusion attenuation coefficient, represents the benefit of node i in the t-1th diffusion, β j represents the self-benefit coefficient of node j, R j represents the overall safety benefit of node j.

[0111] Specifically, the network diffusion model is to iteratively calculate the comprehensive benefit value of each node in the network, and the operation is as follows:

[0112] Set the initial benefit of the node to zero and iterate by time step until the final benefit of the node is Convergence, get the comprehensive benefit value of each node in the network.

[0113] It should be noted that the dynamic diffusion model accurately captures the propagation process of safety supervision benefits in the economic ecological network; considering attenuation and self-generated benefits, the model results are closer to the actual economic system.

[0114] S3.3. Based on the benefits of safety supervision investment in the economic ecological network, the economic ecological network is divided into direct impact layer, indirect impact layer and external social benefit layer, and the benefits of each layer are calculated; the benefits of all layers are integrated to obtain the comprehensive benefit data of safety supervision.

[0115] Specifically, the direct impact layer refers to the upstream and downstream industries (such as logistics and energy) that are directly related to the core nodes of the water transport industry.

[0116] The indirect impact layer refers to industries that spread further through the direct impact layer (such as consumer goods and financial services).

[0117] The external social benefit layer refers to the spread to social areas indirectly related to the economic system (such as employment and environmental protection).

[0118] The benefit for each level is calculated as follows:

[0119] The direct impact layer benefit summarizes the comprehensive benefit value of the nodes in this layer.

[0120] The indirect impact layer benefit summarizes the comprehensive benefit value of the nodes in this layer.

[0121] External social benefits quantify the indirect contribution of safety regulation to social benefits, such as reducing damage to the environment and public resources caused by accidents.

[0122] S4. Based on the comprehensive benefit data and risk-related data in multidimensional data, a risk prediction model is constructed to predict future risk parameters.

[0123] S4.1. Based on the comprehensive benefit data of safety supervision and the historical accident records and environmental risk data in the risk-related data, calculate the comprehensive risk prediction value, which is expressed as:

[0124]

[0125] Among them, H t represents the comprehensive risk prediction value at time t, P t-1,k represents the historical probability of the kth type of accident occurring at time t-1, L k represents the average economic loss value of the kth type of accident, M represents the comprehensive benefit of safety supervision, Q represents the benchmark safety benefit of the industry, ∈ represents the smoothing coefficient, λ k (t) represents the impact weight of the risk of the k-th accident at time t on the comprehensive risk, φ represents the external environment impact coefficient, G t Represents the environmental risk data at time t.

[0126] Furthermore, environmental risk data include meteorological conditions (typhoons, heavy rains, etc.), waterway environment (siltation, congestion, etc.) and traffic flow.

[0127] It should be noted that the combination of comprehensive benefits, historical probability of accidents and environmental risks provides a comprehensive data basis for risk prediction.

[0128] S5. Based on the predicted future risk parameters, dynamically update the safety benefit contribution value of each sub-industry and the multi-level benefit data of the ecological network to generate the final measurement report on water transport safety supervision.

[0129] S5.1. Map the predicted future risk parameters to the input-output model and the economic ecological network model; in combination with the dynamic changes of risk parameters, adjust the input coefficients between sub-industries in the input-output model in real time, and calculate the dynamic contribution of different safety inputs to the industry's economic benefits; dynamically optimize the multi-level benefit allocation mechanism in the economic ecological network, and update the comprehensive benefits of the upstream and downstream industrial chains in real time; integrate the results of the dynamically adjusted input-output model and the economic ecological network model to generate the final measurement report for water transport safety supervision.

[0130] It should be noted that by mapping risk parameters to the input model, the key variables of the model are dynamically adjusted to enable it to respond to risk changes in real time; risk-driven dynamic adjustment enhances the flexibility of the model and the accuracy of predictions; the dynamically adjusted input-output model is closer to the actual operating status of the industry and reflects the actual impact of risks on upstream and downstream economic links.

[0131] This embodiment also provides a water transport safety supervision and measurement system, including:

[0132] The data processing module collects and preprocesses multidimensional data related to water transport safety supervision to generate a multidimensional eigenvector matrix; the benefit calculation module constructs a multidimensional input-output model based on the multidimensional eigenvector matrix, calculates the safety benefits of each sub-industry, and integrates them to obtain the overall safety benefits of the industry; the network analysis module uses the overall safety benefits of the industry to construct an economic ecological network of the water transport industry and the upstream and downstream industrial chains, analyzes the comprehensive benefits of safety supervision on multi-level economic nodes, and generates comprehensive benefit data; the risk prediction module constructs a risk prediction model based on the comprehensive benefit data and risk-related data in the multidimensional data to predict future risk parameters; the dynamic update module dynamically updates the safety benefit contribution value of each sub-industry and the multi-level benefit data of the ecological network according to the predicted future risk parameters, and generates the final measurement report on water transport safety supervision.

[0133] This embodiment also provides a computer device, which is applicable to the case of the water transport safety supervision and measurement method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the water transport safety supervision and measurement method proposed in the above embodiment.

[0134] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0135] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing water transport safety supervision and measurement as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0136] In summary, the present invention generates a multidimensional feature vector matrix by collecting and preprocessing multidimensional data related to water transport safety supervision, thereby providing a standardized and complete data foundation for subsequent modeling; the multidimensional input-output model constructed based on this can not only calculate the safety benefit contribution value of each sub-industry, but also integrate the overall safety benefit of the industry, providing a scientific basis for evaluating the direct economic benefits of safety supervision; by constructing an economic ecological network of the water transport industry and the upstream and downstream industrial chains, the diffusion benefits of safety supervision between network nodes and its comprehensive impact on multi-level economic nodes are quantitatively analyzed, thereby revealing the global value of safety supervision to the industry ecology; a risk prediction model is constructed that can dynamically predict future risk parameters and optimize the input-output model and the economic ecological network accordingly.

[0137] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of the water transportation safety supervision and measurement method are provided.

[0138] An experimental scenario based on simulated data was designed, which simulated the performance of the water transport industry under two circumstances:

[0139] No safety supervision model: No safety supervision measures are implemented, and only traditional management models are relied upon.

[0140] Implement a safety supervision model: perform supervision measurement and optimization according to the method of the present invention.

[0141] The details are shown in Table 1 below:

[0142] Table 1 Experimental data of different regulatory modes

[0143]

[0144] It can be seen from the table data that the method of the present invention significantly improves the economic benefits of the water transport industry when implementing safety supervision, and effectively reduces the accident rate, reflecting the following advantages:

[0145] After the implementation of safety supervision, the capital investment and safety technology investment of each sub-industry increased significantly. For example, the capital investment of sub-industry 1 increased from 5 million yuan to 6 million yuan, and the safety technology investment increased from 500,000 yuan to 800,000 yuan. These investments directly led to the growth of transportation volume and total output value. For example, the transportation volume of sub-industry 1 increased from 8 million tons to 8.5 million tons, and the total output value increased from 1 billion yuan to 1.2 billion yuan.

[0146] In the absence of safety supervision mode, the accident rates of all sub-industries were high, such as 5.5% in sub-industry 1 and 4.8% in sub-industry 2. In the implementation of safety supervision mode, the accident rates dropped to 2.8% and 2.5% respectively, which reflects the effectiveness of the method of the present invention in safety management.

[0147] In the absence of safety supervision mode, the value-added income and loss reduction income of all sub-industries are zero. In the implementation of safety supervision mode, the value-added income of sub-industry 1 is 200 million yuan, and the loss reduction income is 150 million yuan; the value-added income of sub-industry 2 is 250 million yuan, and the loss reduction income is 200 million yuan. This shows that the method of the present invention has achieved significant economic benefits by increasing economic output and reducing accident losses.

[0148] This paper analyzes the comprehensive impact of safety supervision on the upstream and downstream industrial chains by constructing an economic ecological network, and calculates the benefits from three dimensions: direct impact layer, indirect impact layer, and external social benefit layer. The experimental results show that after the implementation of safety supervision, the overall safety benefits of the industry have been significantly improved, and its impact has spread to upstream and downstream enterprises through the industrial chain, driving the optimization of the overall economic ecology.

[0149] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for measuring and supervising waterway transportation safety, characterized in that: include, Collect and pre-process multi-dimensional data related to water transport safety supervision to generate a multi-dimensional feature vector matrix; Based on the multi-dimensional eigenvector matrix, a multi-dimensional input-output model is constructed to calculate the safety benefits of each sub-industry and integrate them to obtain the overall safety benefits of the industry; By using the overall safety benefits of the industry, we can build an economic ecological network of the water transport industry and the upstream and downstream industrial chains, analyze the comprehensive benefits of safety supervision on multi-level economic nodes, and generate comprehensive benefit data; Based on the comprehensive benefit data and risk-related data in multidimensional data, a risk prediction model is constructed to predict future risk parameters; Based on the predicted future risk parameters, the safety benefit contribution value of each sub-industry and the multi-level benefit data of the ecological network are dynamically updated to generate the final measurement report on waterway transportation safety supervision; Based on the multidimensional eigenvector matrix, a multidimensional input-output model is constructed to calculate the safety benefit contribution value of each sub-industry and integrate it to obtain the overall safety benefit of the industry. The following steps are included: Extracting capital flow data, total output value, security input intensity and transportation volume from the multidimensional eigenvector matrix; Based on the extracted capital flow data and total output value, the input coefficient matrix is ​​constructed; Integrate the extracted safety input intensity and transportation volume to form a safety supervision input vector; Build a demand vector based on historical market demand; Construct a multi-dimensional input-output model to calculate the total output of the sub-industry based on the input coefficient matrix, safety supervision input vector and demand vector; According to the total output of the sub-industry, define the value-added income and loss reduction income, add the value-added income and loss reduction income together to get the safety benefit contribution of each sub-industry; Summarize the safety benefit contribution values ​​of all sub-industries to obtain the overall safety benefit of the industry.

2. The waterway transportation safety supervision and calculation method according to claim 1, characterized in that: The multidimensional data includes industry input-output data, economic ecological network data and risk-related data; The industry input-output data include capital investment, safety technology investment, transportation volume and total output value; the economic ecological network data include capital flow and safety supervision impact data; risk-related data include historical accident records and environmental risk data; The preprocessing includes data standardization, data denoising and missing value filling processing; Generating a multi-dimensional feature vector matrix refers to transforming the pre-processed data to form a multi-dimensional feature vector matrix.

3. The waterway transportation safety supervision and calculation method according to claim 2 is characterized in that: The expression of the total output of a sub-industry is: 1=(I-A) -1 (Y+B·S); Among them, 1 represents the total output of the sub-industry, I represents the unit matrix, A represents the input coefficient matrix, B represents the safety supervision input vector, Y represents the demand vector, and S represents the total safety supervision investment; The value-added return is defined based on the total output of the sub-industry, and the expression is: C v =d v ·(X v -E v ); Among them, C v represents the added value of the vth sub-industry, δ v represents the value-added coefficient of the vth sub-industry, X v represents the total output of the vth sub-industry under safety supervision, E v represents the benchmark output of the vth sub-industry without safety supervision; Define impairment gain, the expression is: Among them, D v represents the impairment income of the vth sub-industry, P k represents the probability of the kth type of accident occurring without safety supervision, F k It represents the probability of occurrence of the k-th accident under safety supervision, represents the average economic loss caused by the k-th accident to the v-th sub-industry, and m represents the total number of accidents.

4. The waterway transportation safety supervision and calculation method according to claim 3 is characterized in that: Using the overall safety benefits of the industry, building an economic ecological network for the water transport industry and the upstream and downstream industrial chains includes the following steps: Define the water transport sub-industry and major upstream and downstream industries as network nodes; According to the network nodes and industry safety benefits, the influence propagation intensity between network nodes in safety supervision is calculated, and the expression is: Among them, A ij represents the security supervision influence of node i on node j, R i represents the overall safety benefit of node i, represents the diffusion coefficient of safety supervision, and W ij represents the original relationship strength between node i and node j, B k represents the safety benefit contribution value of the kth node; Based on the intensity of safety supervision influence between nodes in the network, an adjacency matrix is ​​constructed to form an economic ecological network of the water transport industry and the upstream and downstream industrial chains.

5. The waterway transportation safety supervision and calculation method according to claim 4, characterized in that: Analyzing the comprehensive benefits of safety supervision on multi-level economic nodes and generating comprehensive benefit data include the following steps: Using the network diffusion model, the benefits of safety supervision investment in the economic ecological network are calculated, and the expression is: in, represents the comprehensive benefit of node j after the tth diffusion, N represents the total number of nodes in the network, α represents the diffusion attenuation coefficient, represents the benefit of node i in the t-1th diffusion, β j represents the self-benefit coefficient of node j, R j represents the overall safety benefit of node j; Based on the benefits of safety supervision investment in the economic ecological network, the economic ecological network is divided into direct impact layer, indirect impact layer and external social benefit layer, and the benefits of each layer are calculated; Integrate benefits at all levels to obtain comprehensive benefit data for safety supervision.

6. The waterway transportation safety supervision and calculation method according to claim 5, characterized in that: Based on comprehensive benefit data and risk-related data in multidimensional data, a risk prediction model is constructed to predict future risk parameters. The following steps are included: Based on the comprehensive benefit data of safety supervision and the historical accident records and environmental risk data in risk-related data, the comprehensive risk prediction value is calculated, and the expression is: Among them, H t represents the comprehensive risk prediction value at time t, P t-1，k represents the historical probability of the kth type of accident occurring at time t-1, L k represents the average economic loss value of the kth type of accident, M represents the comprehensive benefit of safety supervision, Q represents the benchmark safety benefit of the industry, ∈ represents the smoothing coefficient, λ k (t) represents the impact weight of the risk of the k-th accident at time t on the comprehensive risk, φ represents the external environment impact coefficient, G t Represents the environmental risk data at time t.

7. The waterway transportation safety supervision and calculation method according to claim 6, characterized in that: Based on the predicted future risk parameters, the safety benefit contribution value of each sub-industry and the multi-level benefit data of the ecological network are dynamically updated to generate the final calculation report on waterway transportation safety supervision. The following steps are included: Mapping predicted future risk parameters to input-output models and economic-ecological network models; Combined with the dynamic changes of risk parameters, the input coefficients among sub-industries in the input-output model are adjusted in real time to calculate the dynamic contribution of different safety inputs to the economic benefits of the industry; Dynamically optimize the distribution mechanism of multi-level benefits in the economic ecological network, and update the comprehensive benefits of the upstream and downstream industrial chains in real time; Integrate the results of the dynamically adjusted input-output model and economic ecological network model to generate the final measurement report for water transport safety supervision.

8. A water transport safety supervision and calculation system, based on the water transport safety supervision and calculation method according to any one of claims 1 to 7, characterized in that: include, The data processing module collects and pre-processes multi-dimensional data related to water transport safety supervision to generate a multi-dimensional feature vector matrix; The benefit calculation module builds a multi-dimensional input-output model based on the multi-dimensional feature vector matrix, calculates the safety benefits of each sub-industry, and integrates them to obtain the overall safety benefits of the industry; The network analysis module uses the overall safety benefits of the industry to build an economic ecological network of the water transport industry and the upstream and downstream industrial chains, analyzes the comprehensive benefits of safety supervision on multi-level economic nodes, and generates comprehensive benefit data; The risk prediction module builds a risk prediction model based on comprehensive benefit data and risk-related data in multidimensional data to predict future risk parameters; The dynamic update module dynamically updates the safety benefit contribution value of each sub-industry and the multi-level benefit data of the ecological network according to the predicted future risk parameters, and generates the final measurement report of water transport safety supervision.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the water transport safety supervision and measurement method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the water transport safety supervision and measurement method described in any one of claims 1 to 7 are implemented.

Images