An Automatic Monitoring Method for Port Safety Hazards and Insurance Rate Adjustment Method and System

Abstract

The present invention discloses an automatic monitoring method and system for port safety hazards and insurance rate adjustment, including collecting safety monitoring data and image data of the port, and preprocessing the safety monitoring data and the image data; performing a safety assessment on the safety monitoring data to obtain a risk score, and correcting the risk score by using the image data to obtain a safety risk value; adjusting the protection rate according to the safety risk value to obtain an adjustment ratio, and constructing a port safety monitoring insurance rate adjustment model according to the adjustment ratio; optimizing the port safety monitoring insurance rate adjustment model, inputting the data to be adjusted into the port safety monitoring insurance rate adjustment model, and outputting an adjustment result. This method can not only improve the accuracy of automatic monitoring of port safety hazards and insurance rate adjustment, but also has good interpretability and can be directly applied to the insurance rate adjustment system.

Description

Technical Field

[0001] The present invention relates to the field of monitoring and adjustment, and particularly to an automatic monitoring method and system for port safety hazards and insurance rate adjustment. Background Art

[0002] With the continuous development of global trade, ports, as important hubs of international trade, the importance of their safe operation has become increasingly prominent. However, there are many safety hazards in port operations, including but not limited to equipment and facility failures, human operation errors, imperfect management, and poor operating environments. These hazards may not only lead to interruptions in port operations but also trigger highly harmful accidents, causing significant property losses and casualties. Traditional port safety management methods mainly rely on manual inspections and experience judgments. This method is not only inefficient but also difficult to comprehensively and accurately capture and analyze potential safety hazards in port operations. In recent years, with the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, port safety monitoring has gradually transformed towards intelligence and automation.

[0003] Currently, some ports have begun to attempt to collect safety monitoring data and image data of ports using devices such as sensors and cameras. However, these data often have problems such as noise and redundancy, and directly using them for safety assessment may lead to inaccurate results. In addition, although the risk can be evaluated by preliminarily analyzing the safety monitoring data, simply relying on the data is often difficult to comprehensively reflect the actual situation of port production safety. Especially for some emergencies or complex scenarios, it is necessary to combine image data for comprehensive judgment.

[0004] In the insurance field, traditional port insurance rates are usually set statically based on factors such as port scale and historical accident records. This method cannot reflect the changes in the port production safety status in real time, nor can it be dynamically adjusted according to the safety risks in the actual operation of the port. Therefore, it is necessary to develop a mechanism that can adjust the insurance rate in real time according to the port safety status to encourage port enterprises to strengthen safety management and reduce accident risks. Summary of the Invention

[0005] The purpose of the present invention is to provide an automatic monitoring method for port safety hazards and insurance rate adjustment.

[0006] To achieve the above object, the present invention is implemented according to the following technical solution:

[0007] The present invention includes the following steps:

[0008] Collect safety monitoring data and image data of the port, and preprocess the safety monitoring data and the image data;

[0009] Perform a security assessment on the security monitoring data to obtain a risk score, and correct the risk score using the image data to obtain a security risk value;

[0010] Adjust the protection rate according to the security risk value to obtain an adjustment ratio, and construct a port security monitoring insurance rate adjustment model based on the adjustment ratio;

[0011] Optimize the port security monitoring insurance rate adjustment model, input the data to be adjusted into the port security monitoring insurance rate adjustment model, and output the adjustment result.

[0012] Furthermore, the method for performing a security assessment on the security monitoring data to obtain a risk score includes:

[0013] Extract risk features from the security monitoring data through a machine learning algorithm, and perform a security assessment based on the risk features;

[0014] Calculate the risk score according to the risk features:

[0015]

[0016] Where the change amount of the i-th risk feature from the s-th moment to the s + 1-th moment is The i-th risk feature is h i , the probability of the i-th risk feature occurring is P(h i ), the i-th largest satisfactory deviation value is The i-th smallest change amount is The proportional control coefficient is The change constant is The risk score is The maintenance cost is S.

[0017] Furthermore, the method for correcting the risk score using the image data to obtain a security risk value includes:

[0018] Perform risk identification on the image data to obtain risk data, perform a security assessment on the risk data to obtain a real-time risk score, and calculate the offset between the real-time risk score and the risk score:

[0019]

[0020] Where the -th risk data is The threshold of the risk data is k o , the bandwidth parameter is The number of risk data is The natural constant is e, the kernel density estimation function is Y(·), the norm is ||·||, and the real-time risk score at the s-th moment is The risk score is The upper limit of the monitoring time is N, and the real-time risk score and the offset of the risk score are used to correct the risk score according to the offset, and the expression is:

[0021] where the safety risk value of the q-th monitoring is

[0022]

[0023] the regulation coefficient of the q-th monitoring is the risk score of the q-th monitoring is the offset of the q-th monitoring is

[0024] Introduce a particle swarm, calculate the mean square error between the predicted risk score and the actual risk score, take the minimum mean square error as the search strategy, and search for the regulation coefficient according to the search strategy;

[0025] Take the particle position with the minimum mean square error as the target position, and calculate the particle position:

[0026]

[0027] where the position of the c-th particle in the u-th direction at the y-th dimension is the position of the c-th particle at the y-th dimension is V cy , the step factor is η, the maximum dimension is max y , the minimum dimension is min y , the number of dimensions is N y , the wandering parameter of the y-th dimension is l y , the target position is V aim ;

[0028] Update the particle position using the inertia weight to obtain the inertia position, and the expression is:

[0029]

[0030] where the inertia position of the c-th particle at the y-th dimension in the (t + 1)-th iteration is the position of the c-th particle at the y-th dimension in the t-th iteration is the position of the particle at the y-th dimension in the t-th iteration is the step coefficient is η, and the inertia weight in the t-th iteration is χ t ;

[0031] Update the inertia weight, and the expression is:

[0032] ​

[0033] where the inertia weight at the (t + 1)-th iteration is χ t+1 , and the maximum number of iterations is t max , the maximum value of the inertia weight is χ max , and the minimum value of the inertia weight is χ min ;

[0034] Calculate the mean square error of the particle after updating the position. If it is less than the target position, replace the target position, and continuously iterate until the minimum mean square error is reached;

[0035] Correct the risk score according to the regulation coefficient of the minimum mean square error and output it as the safety risk value.

[0036] Furthermore, a method for adjusting the protection rate according to the safety risk value to obtain an adjustment ratio includes:

[0037] Calculate the insurance ratio according to the claim record, safety risk value and protection rate of the port:

[0038]

[0039] where the insurance ratio of the port at the a-th time is H a , the claim record at the z-th time is K z , the importance degree of the port at the a-th time is ψ a , the safety risk value of the port at the a-th time is ε a , the protection rate of the port at the a-th time is the value of the protected object of the port at the a-th time is E a , and the number of claim records is n z ;

[0040] Adopt an offset correction strategy to search for an adaptive weight, update the velocity and position of the particle, and the expression is:

[0041] D jy (t + 1) = θ(t)·D jy (t) + c1b1(X bs - D jy (t)) + c2b2(A bs - D jy (t))

[0042] X jy (t + 1) = D jy (t + 1) + X jy (t)

[0043] where the dimension of the particle is y, the number of iterations is t, and the velocity of the j-th particle dimension y at the (t + 1)-th iteration is D jy (t + 1), and the velocity of the j-th particle dimension y at the t-th iteration is The first acceleration factor is c1, the second acceleration factor is c2, the random numbers from 0 to 1 are b1 and b2, and the position of the j-th particle dimension y at the (t + 1)-th iteration is X jy (t + 1), and the position of the j-th particle dimension y at the t-th iteration is X jy (t), the individual optimal position of the particle is X bs , and the global optimal position of the particle is A bs , and the adaptive weight at the t-th iteration is θ;

[0044] Update the adaptive weight, and the expression is:

[0045]

[0046] Among them, the initial value of the genetic weight for dimension y is The final value of the genetic weight for the iteration number t is The final value of the genetic weight for dimension y is The initial value of the genetic weight for the iteration number t is The maximum number of iterations is t max , the dimension weight is ζ, the iteration number is t, and the rotation parameter is c,

[0047] Perform a perturbation on the protection rate, and the expression is:

[0048]

[0049] Among them, the updated position of the j-th particle dimension y at the (t + 1)-th iteration is The position of the protection rate of the t-th generation population in dimension y is The perturbation step size is γ o , the perturbation coefficient α at the t-th iteration t , the maximum dimension is max u , the minimum dimension is min u ;

[0050] Update the particle position according to the offset of the insurance ratio to obtain the corrected position, and the expression is:

[0051]

[0052] ΔH = |H a - H o |

[0053] Among them, the corrected position of the j-th particle dimension y at the (t + 1)-th iteration is The threshold of the insurance ratio is H o , and the updated position of the j-th particle dimension y at the t-th iteration is The offset of the insurance ratio is ΔH;

[0054] Iterate continuously until the offset of the insurance coverage ratio is less than 0.175, and output the insurance coverage ratio as the adjusted ratio; otherwise, update the adaptive weight.

[0055] Furthermore, a method for constructing a port safety monitoring insurance rate adjustment model according to the adjusted ratio includes:

[0056] Construct an objective function according to the adjusted ratio, and the expression is:

[0057]

[0058] where the objective function is The actual adjusted ratio is ξ, and the predicted adjusted ratio is The value of the protected object is E, the actual protection cost is ξ·E, and the predicted protection cost is The error between the actual protection cost and the predicted protection cost is

[0059] The port safety monitoring insurance rate adjustment model includes a convolutional neural network algorithm, a time series analysis algorithm, and a machine learning algorithm;

[0060] The convolutional neural network algorithm captures patterns in space and time through convolution, extracts risk features from the input image data, and obtains time series risk features;

[0061] The time series analysis algorithm performs trend analysis on the time series risk features and the insurance ratio according to time to obtain the change trend;

[0062] The machine learning algorithm analyzes the time series risk features and the change trend of the input data, learns and predicts future risk changes, and automatically adjusts the insurance rate according to the insurance ratio based on the risk changes.

[0063] Furthermore, a method for optimizing the port safety monitoring insurance rate adjustment model includes:

[0064] Introduce a search sub-population and perform a chaotic mapping on the search sub, and the expression is:

[0065]

[0066] where the initial position sequence of the search sub is R b , and the chaotic mapping sequence of the search sub is R b+1 , and the mapping coefficient is α;

[0067] Calculate the position of the search sub:

[0068]

[0069] where the upper bound of the search area is U max , and the lower bound of the search area is U min, the random function is rand(·), and the position of the w-th search agent is

[0070] Update the position of the search agent according to the density factor to obtain the density position, and the expression is:

[0071]

[0072] where the target position is The density position of the w-th search agent at the (t + 1)-th iteration is The position of the w-th search agent at the t-th iteration is The maximum number of iterations is t max , the current number of iterations is t, the random numbers from 0 to 1 are r1, r2, and r3 respectively, the density factor is ζ, the control coefficient is β, the density coefficient is ω, and the position of the (w + 1)-th search agent is

[0073] Update the position of the search agent according to the adaptive inertia weight to obtain the inertia position, and the expression is:

[0074]

[0075] where the inertia position of the w-th search agent at the (t + 1)-th iteration is The adaptive inertia weight at the t-th iteration is λ(t), and the maximum value of the adaptive inertia weight is λ max , the minimum value of the adaptive inertia weight is λ min ;

[0076] Iterate continuously until the maximum number of iterations is reached, otherwise update the adaptive inertia weight.

[0077] In a second aspect, a port safety hazard automatic monitoring and insurance rate adjustment system includes:

[0078] Data acquisition module: used to collect port safety monitoring data and image data, and preprocess the safety monitoring data and the image data;

[0079] Evaluation and correction module: used to perform safety evaluation on the safety monitoring data to obtain a risk score, and correct the risk score using the image data to obtain a safety risk value;

[0080] Adjustment and construction module: used to adjust the protection rate according to the safety risk value to obtain an adjustment ratio, and construct a port safety monitoring insurance rate adjustment model according to the adjustment ratio;

[0081] Optimization and output module: used to optimize the port safety monitoring insurance rate adjustment model, input the data to be adjusted into the port safety monitoring insurance rate adjustment model, and output the adjustment result.

[0082] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0083] a processor; and a memory arranged to store computer-executable instructions, the executable instructions, when executed, causing the processor to execute the method steps described in the first aspect.

[0084] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium storing one or more programs, the one or more programs, when executed by an electronic device including a plurality of application programs, causing the electronic device to execute the method steps described in the first aspect.

[0085] The beneficial effects of the present invention are:

[0086] The present invention is a method and system for automatically monitoring port safety hazards and adjusting insurance rates. Compared with the prior art, the present invention has the following technical effects:

[0087] Through steps of preprocessing, safety assessment, risk correction, rate adjustment, model construction, and model optimization, the present invention can improve the accuracy of automatically monitoring port safety hazards and adjusting insurance rates, thereby improving the precision of automatically monitoring and adjusting insurance rates for multiple port safety hazards. Optimizing the automatic monitoring of port safety hazards and adjusting insurance rates can greatly save resources and improve work efficiency. It can achieve automatic adjustment of the automatic monitoring of port safety hazards and insurance rates, perform multi-data fusion and risk correction on the automatic monitoring of port safety hazards and insurance rates in real time, which is of great significance for the automatic monitoring of port safety hazards and insurance rate adjustment, and can adapt to different standards of automatic monitoring of port safety hazards and insurance rate adjustment, different requirements for automatic monitoring of port safety hazards and insurance rate adjustment, and has a certain universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] Figure 1 is a flowchart of the steps of a method for automatically monitoring port safety hazards and adjusting insurance rates according to the present invention;

[0089] Figure 2 is a schematic structural diagram of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0090] The present invention will be further described below through specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention, but do not limit the present invention.

[0091] A method and system for automatically monitoring port safety hazards and adjusting insurance rates according to the present invention include the following steps:

[0092] AsFigure 1 As shown in the figure, in this embodiment, the following steps are included:

[0093] Collect the safety monitoring data and image data of the port, and preprocess the safety monitoring data and the image data;

[0094] In the actual evaluation, take the storage tank area of XXX Port as the research object. The safety monitoring data includes real-time liquid level, liquid level change trend, liquid level alarm threshold, liquid level height, temperature, temperature change trend, temperature alarm threshold, real-time pressure, pressure change trend, pressure alarm threshold, density values at different liquid levels, real-time concentration of combustible gas, combustible gas concentration change trend, combustible gas concentration alarm threshold, real-time concentration of toxic gas, toxic gas concentration change trend, toxic gas concentration alarm threshold, equipment operation parameters, fault alarm information, number of times the safety valve is opened, and combustion condition of the flare system;

[0095] Conduct a safety assessment on the safety monitoring data to obtain a risk score, and correct the risk score using the image data to obtain a safety risk value;

[0096] In the actual evaluation, the risk score is 0.5784, and the safety risk value is 0.6091;

[0097] Adjust the protection rate according to the safety risk value to obtain an adjustment ratio, and construct a port safety monitoring insurance rate adjustment model based on the adjustment ratio;

[0098] In the actual evaluation, the adjustment ratio is 0.216;

[0099] Optimize the port safety monitoring insurance rate adjustment model, input the data to be adjusted into the port safety monitoring insurance rate adjustment model, and output the adjustment result.

[0100] In this embodiment, the method for conducting a safety assessment on the safety monitoring data to obtain a risk score includes:

[0101] Extract risk features from the safety monitoring data through a machine learning algorithm, and conduct a safety assessment based on the risk features;

[0102] Calculate the risk score according to the risk features:

[0103]

[0104] Where the change amount of the i-th risk feature from the s-th moment to the s + 1-th moment is The i-th risk feature is h i , the probability of the i-th risk feature occurring is P(h i ), and the i-th largest satisfactory deviation value is The i-th smallest change amount is The proportional regulation coefficient is The change constant is The risk score is The maintenance cost is S.

[0105] In this embodiment, the method for correcting the risk score with the image data to obtain a safety risk value includes:

[0106] Performing risk identification on the image data to obtain risk data, performing safety assessment on the risk data to obtain a real-time risk score, and calculating the offset between the real-time risk score and the risk score:

[0107]

[0108] Where the th risk data is The threshold of the risk data is k o , and the bandwidth parameter is The number of risk data is The natural constant is e, the kernel density estimation function is Y(·), the norm is ||·||, and the real-time risk score at the s-th moment is The risk score is The upper limit of the monitoring time is N, and the real-time risk score and the risk score offset

[0109] Correct the risk score according to the offset, and the expression is:

[0110]

[0111] Where the safety risk value of the q-th monitoring is The regulation coefficient of the q-th monitoring is The risk score of the q-th monitoring is The offset of the q-th monitoring

[0112] Introduce a particle population, calculate the mean square error between the predicted risk score and the actual risk score, take the minimum mean square error as the search strategy, and search for the regulation coefficient according to the search strategy;

[0113] Take the particle position with the minimum mean square error as the target position and calculate the position of the particle:

[0114]

[0115] Where the position of the c-th particle in the u-th direction in the y-th dimension is The position of the c-th particle in the y-th dimension is V cy, the step factor is η, and the maximum dimension is max y , the minimum dimension is min y , the number of dimensions is N y , the wandering parameter of the y-th dimension is l y , the target position is V aim ;

[0116] The inertial position of the particle is obtained by updating the particle position with the inertial weight, and the expression is:

[0117]

[0118] Among them, the inertial position of the c-th particle in the y-th dimension at the (t + 1)-th iteration is The position of the c-th particle in the y-th dimension at the t-th iteration is The position of the particle in the y-th dimension at the t-th iteration is The step coefficient is η, and the inertial weight at the t-th iteration is χ t ;

[0119] Update the inertial weight, and the expression is:

[0120]

[0121] Among them, the inertial weight at the (t + 1)-th iteration is χ t+1 , the maximum number of iterations is t max , the maximum value of the inertial weight is χ max , the minimum value of the inertial weight is χ min ;

[0122] Calculate the mean square error of the particle after updating the position. If it is less than the target position, replace the target position and iterate continuously until the minimum mean square error is reached;

[0123] Correct the risk score according to the regulation coefficient of the minimum mean square error and output it as the safety risk value.

[0124] In this embodiment, the method for adjusting the protection rate according to the safety risk value to obtain the adjustment ratio includes:

[0125] Calculate the insurance ratio according to the claim record, safety risk value and protection rate of the port:

[0126]

[0127] Among them, the insurance ratio of the a-th port is H a , the z-th claim record is K z , the importance degree of the a-th port is ψ a , the safety risk value of the a-th port is ε a , the protection rate of the a-th port is The value of the protected object at the a-th port is E a , and the number of claim records is n z ;

[0128] Adopt an offset correction strategy to search for the adaptive weight, and update the velocity and position of the particle. The expression is:

[0129] D jy (t + 1)=θ(t)·D jy (t)+c1b1(X bs -D jy (t))+c2b2(A bs -D jy (t))

[0130] X jy (t + 1)=D jy (t + 1)+X jy (t)

[0131] Among them, the dimension of the particle is y, the number of iterations is t, the velocity of the j-th particle dimension y at the (t + 1)-th iteration is D jy (t + 1), and the velocity of the j-th particle dimension y at the t-th iteration is The first acceleration factor is c1, the second acceleration factor is c2, the random numbers from 0 to 1 are b1 and b2, the position of the j-th particle dimension y at the (t + 1)-th iteration is X jy (t + 1), the position of the j-th particle dimension y at the t-th iteration is X jy (t), the individual optimal position of the particle is X bs , the global optimal position of the particle is A bs , and the adaptive weight at the t-th iteration is θ;

[0132] Update the adaptive weight. The expression is:

[0133]

[0134] Among them, the initial value of the genetic weight with dimension y is The final value of the genetic weight for the number of iterations t is The final value of the genetic weight with dimension y is The initial value of the genetic weight for the number of iterations t is The maximum number of iterations is t max , the dimension weight is ζ, the number of iterations is t, and the rotation parameter is c

[0135] Perform a tension perturbation on the protection rate. The expression is:

[0136]

[0137] The updated position of the j-th particle dimension y in the (t + 1)-th iteration is The position of the protection rate of the t-th generation population in dimension y is The perturbation step size is γ o , the perturbation coefficient α in the t-th iteration t , the maximum dimension is max u , the minimum dimension is min u ;

[0138] Update the particle position according to the offset of the insurance ratio to obtain the corrected position, and the expression is:

[0139]

[0140] ΔH = |H a - H o |

[0141] The corrected position of the j-th particle dimension y in the (t + 1)-th iteration is The threshold of the insurance ratio is H o , the updated position of the j-th particle dimension y in the t-th iteration is The offset of the insurance ratio is ΔH;

[0142] Iterate continuously until the offset of the insurance ratio is less than 0.175, and output the insurance ratio as the adjustment ratio, otherwise update the adaptive weight.

[0143] In this embodiment, the method for constructing a port safety monitoring insurance rate adjustment model according to the adjustment ratio includes:

[0144] Construct an objective function according to the adjustment ratio, and the expression is:

[0145]

[0146] Where the objective function is The actual adjustment ratio is ξ, and the predicted adjustment ratio is The value of the protected object is E, the actual protection cost is ξ·E, and the predicted protection cost is The error between the actual protection cost and the predicted protection cost is

[0147] The port safety monitoring insurance rate adjustment model includes a convolutional neural network algorithm, a time series analysis algorithm, and a machine learning algorithm;

[0148] The convolutional neural network algorithm captures patterns in space and time through convolution, extracts risk features from the input image data, and obtains time series risk features;

[0149] The timing analysis algorithm conducts a trend analysis on the timing risk characteristics and insurance ratio according to time to obtain the change trend;

[0150] The machine learning algorithm analyzes the timing risk characteristics and change trend of the input data, learns and predicts the future risk changes, and automatically adjusts the insurance rate according to the insurance ratio based on the risk changes.

[0151] In this embodiment, the method for optimizing the insurance rate adjustment model for port safety monitoring includes:

[0152] Introduce a search sub-population and perform a chaotic mapping on the search sub, and the expression is:

[0153]

[0154] where the initial position sequence of the search sub is R b , the chaotic mapping sequence of the search sub is R b+1 , and the mapping coefficient is α;

[0155] Calculate the position of the search sub:

[0156]

[0157] where the upper bound of the search area is U max , the lower bound of the search area is U min , the random function is rand(·), and the position of the w-th search sub is

[0158] Update the position of the search sub according to the density factor to obtain the density position, and the expression is:

[0159]

[0160] where the target position is The density position of the w-th search sub at the (t + 1)-th iteration is The position of the w-th search sub at the t-th iteration is The maximum number of iterations is t max , the current number of iterations is t, the random numbers from 0 to 1 are r1, r2, r3 respectively, the density factor is ζ, the control coefficient is β, the density coefficient is ω, and the position of the (w + 1)-th search sub is

[0161] Update the position of the search sub according to the adaptive inertia weight to obtain the inertia position, and the expression is:

[0162]

[0163] where the inertia position of the w-th search sub at the (t + 1)-th iteration is The adaptive inertia weight for the t-th iteration is λ(t), the maximum value of the adaptive inertia weight is λ max , and the minimum value of the adaptive inertia weight is λ min ;

[0164] Iterate continuously until the maximum number of iterations is reached, otherwise update the adaptive inertia weight.

[0165] In a second aspect, an automatic monitoring and insurance rate adjustment system for port safety hazards includes:

[0166] A data acquisition module: used to collect port safety monitoring data and image data, and preprocess the safety monitoring data and the image data;

[0167] An evaluation and correction module: used to perform a safety assessment on the safety monitoring data to obtain a risk score, and correct the risk score using the image data to obtain a safety risk value;

[0168] An adjustment and construction module: used to adjust the protection rate according to the safety risk value to obtain an adjustment ratio, and construct a port safety monitoring insurance rate adjustment model according to the adjustment ratio;

[0169] An optimization and output module: used to optimize the port safety monitoring insurance rate adjustment model, input the data to be adjusted into the port safety monitoring insurance rate adjustment model, and output the adjustment result.

[0170] Figure 2 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 2 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0171] The processor, network interface, and memory can be interconnected through an internal bus, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2It is represented by only one bidirectional arrow, but it does not mean that there is only one bus or one type of bus.

[0172] A memory for storing programs. Specifically, the program may include program codes, and the program codes include computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0173] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an automatic monitoring device for port security hazards and an insurance rate adjustment device at the logical level. The processor executes the program stored in the memory, and is specifically used to execute any one of the foregoing automatic monitoring methods for port security hazards and insurance rate adjustment methods.

[0174] The above as in the present application Figure 1 An automatic monitoring method for port security hazards and an insurance rate adjustment method disclosed in the embodiments shown in the present application can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor or by instructions in the form of software. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register and other mature storage media in the art. The storage media is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0175] The electronic device can also execute Figure 1 an automatic monitoring method for port security hazards and an insurance rate adjustment method in the present application, and implement Figure 1The functions of the illustrated embodiments are not elaborated herein for the embodiments of this application.

[0176] Embodiments of this application also propose a computer-readable storage medium storing one or more programs, where the one or more programs include instructions that, when executed by an electronic device including multiple application programs, perform any of the aforementioned automatic monitoring and insurance rate adjustment methods for port safety hazards.

[0177] Those skilled in the art should understand that the embodiments of this application can be provided as a method, a system, or a computer program product. Therefore, this application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0178] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0179] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0180] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0181] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0182] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0183] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0184] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0185] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0186] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for automatically monitoring potential safety hazards in ports and adjusting insurance premium rates, characterized in that: The following steps are involved: Collecting safety monitoring data and image data of the port, and preprocessing the safety monitoring data and the image data; Performing a safety assessment on the safety monitoring data to obtain a risk score, and using the image data to correct the risk score to obtain a safety risk value; comprising: Perform risk identification on image data to obtain risk data, perform security assessment on risk data to obtain real-time risk score, and calculate the offset between real-time risk score and risk score: Among them The risk data is , the threshold of risk data is , the bandwidth parameter is , the number of risk data is , the natural constant is e, and the kernel density estimation function is , the norm is , the real-time risk score at time s is , the risk score is The upper limit of monitoring time is , real-time risk score and risk score The offset is ; The risk score is corrected according to the offset and the expression is: The safety risk value of the qth monitoring is , the control coefficient of the qth monitoring is , the risk score for the qth monitoring is , the offset of the qth monitoring is ; Introduce particle population, calculate the mean square error between the predicted risk score and the actual risk score, take the minimum mean square error as the search strategy, and search for the control coefficient according to the search strategy; Take the particle position with the smallest mean square error as the target position and calculate the particle position: The first The position of a particle in the yth dimension is , No. The position of a particle in the yth dimension is , the step size factor is , the maximum search dimension is , the minimum search dimension is , the number of dimensions is , the walk parameter of the yth dimension is , the target location is ; Use the inertia weight to update the particle position to obtain the inertial position. The expression is: The t+1th iteration The inertial position of a particle in the yth dimension is , the tth iteration The position of a particle in the yth dimension is , the position of the particle in the y dimension at the tth iteration is , the step size factor is , the inertia weight of the tth iteration is ; Update the inertia weight, the expression is: The inertia weight of the t+1th iteration is , the maximum number of iterations is , the maximum value of inertia weight is , the minimum value of inertia weight is ; Calculate the mean square error of the particle after updating the position. If it is less than the target position, replace the target position and continue iterating until the minimum mean square error is reached. The risk score is corrected according to the control coefficient of the minimum mean square error and output as a safety risk value; The protection premium rate is adjusted according to the safety risk value to obtain an adjustment ratio, and a port safety monitoring insurance premium rate adjustment model is constructed according to the adjustment ratio; Optimize the port safety monitoring insurance premium rate adjustment model, input the data to be adjusted into the port safety monitoring insurance premium rate adjustment model, and output the adjustment result.

2. According to claim 1, a method for automatically monitoring potential safety hazards in ports and adjusting insurance premium rates is characterized in that: The method of performing safety assessment on the safety monitoring data to obtain a risk score includes: Extract risk features from safety monitoring data through machine learning algorithms and conduct safety assessments based on risk features; Calculate the risk score based on the risk characteristics: The change of the i-th risk feature from the sth moment to the s+1th moment is , the i-th risk feature is , the probability of the i-th risk feature appearing is , No. The maximum change in a risk feature is , No. The minimum change in a risk feature is , the proportional control coefficient is , the constant of change is , the risk score is The maintenance cost is .

3. According to claim 1, a method for automatically monitoring potential safety hazards in ports and adjusting insurance premium rates, characterized in that: The method for adjusting the protection fee rate according to the security risk value to obtain the adjustment ratio includes: The insurance ratio is calculated based on the port's claim record, safety risk value and protection premium rate: The insurance ratio of the ath port is , the zth claim record is , the importance of the ath port is , the safety risk value of the a-th port is The protection fee for the ath port is , the protection value of the ath port is , the number of claim records is ; The offset correction strategy is used to search for adaptive weights and update the velocity and position of the particle. The expression is: The dimension of the particle is y, the number of iterations is t, and the speed of the jth particle of dimension y in the t+1th iteration is , the velocity of the j-th particle in dimension y at the t-th iteration is , the first acceleration factor is , the second acceleration factor is , a random number from 0 to 1 is , , the position of the jth particle with dimension y at the t+1th iteration is , the position of the jth particle in dimension y at the tth iteration is , the optimal position of individual particles is , the global optimal position of the particle is , the adaptive weight of the tth iteration is ; Update the adaptive weight, the expression is: The initial value of the genetic weight of dimension y is The final value of the genetic weight for iteration number t is , the final value of the genetic weight of dimension y is The initial value of the genetic weight for iteration number t is , the maximum number of iterations is , the dimension weight is , the number of iterations is t, the rotation parameter is c, For the protection rate tension disturbance, the expression is: The updated position of the jth particle dimension y in the t+1th iteration is , the protection fee rate of the tth generation group in dimension y is , the perturbation step length is , the perturbation coefficient of the tth iteration , the maximum perturbation dimension is , the minimum perturbation dimension is ; Update the particle position according to the offset of the insurance ratio to obtain the corrected position. The expression is: The corrected position of the jth particle dimension y at the t+1th iteration is The threshold of insurance ratio is , the updated position of the jth particle dimension y in the tth iteration is , the offset of the insurance ratio is ; Iterate continuously until the offset of the risk-to-insurance ratio is less than 0.175, and output the risk-to-insurance ratio as the adjustment ratio, otherwise update the adaptive weight.

4. According to claim 1, a method for automatically monitoring potential safety hazards in ports and adjusting insurance premium rates is characterized in that: The method for constructing a port safety monitoring insurance premium rate adjustment model according to the adjustment ratio includes: The objective function is constructed according to the adjustment ratio, and the expression is: The objective function is The actual adjustment ratio is , the predicted adjustment ratio is The value of the protected object is The actual protection cost is , the predicted protection cost is , the error between the actual protection cost and the predicted protection cost is ; The port safety monitoring insurance premium rate adjustment model includes convolutional neural network algorithm, time series analysis algorithm, and machine learning algorithm; The convolutional neural network algorithm captures spatial and temporal patterns through convolution, extracts risk features from input image data, and obtains temporal risk features; The time series analysis algorithm performs trend analysis on time series risk characteristics and insurance ratios according to time to obtain the changing trend; The machine learning algorithm analyzes the time-series risk characteristics and changing trends of the input data, learns and predicts future risk changes, and automatically adjusts the insurance premium rate according to the insurance ratio based on the risk changes.

5. According to claim 1, a method for automatically monitoring potential safety hazards in ports and adjusting insurance premium rates is characterized in that: The method for optimizing the port safety monitoring insurance premium rate adjustment model comprises: Introduce the search sub-population and perform chaotic mapping on the search sub-population. The expression is: The initial position sequence of the searcher is , the chaotic mapping sequence of the searcher is , the mapping coefficient is ; Compute the position of the searcher: The upper bound of the search area is , the lower bound of the search area is , the random function is , the position of the w-th searcher is ; Update the searcher's position according to the density factor to obtain the density position. The expression is: The target location is , the density position of the w-th searcher in the t+1th iteration is , the position of the w-th searcher in the t-th iteration is , the maximum number of iterations is , the current iteration number is t, and the random numbers from 0 to 1 are , , , the density factor is , the control coefficient is , the density coefficient is , the position of the w+1th searcher is ; Update the position of the searcher according to the adaptive inertia weight to obtain the inertia position. The expression is: The inertial position of the w-th searcher at the t+1th iteration is , the adaptive inertia weight of the tth iteration is , the maximum value of the adaptive inertia weight is , the minimum value of the adaptive inertia weight is ; Continue to iterate until the maximum number of iterations is reached, otherwise update the adaptive inertia weight.

6. A port safety hazard automatic monitoring and insurance premium rate adjustment system, used to implement any of the methods described in claims 1-5, characterized in that: include: Data acquisition module: used to collect the safety monitoring data and image data of the port, and pre-process the safety monitoring data and the image data; An assessment and correction module: used for performing a safety assessment on the safety monitoring data to obtain a risk score, and using the image data to correct the risk score to obtain a safety risk value; An adjustment construction module: used to adjust the protection premium rate according to the safety risk value to obtain an adjustment ratio, and to construct a port safety monitoring insurance premium rate adjustment model according to the adjustment ratio; Optimization output module: used to optimize the port safety monitoring insurance premium rate adjustment model, input the data to be adjusted into the port safety monitoring insurance premium rate adjustment model, and output the adjustment result.

7. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 5.

8. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the method according to any one of claims 1 to 5.

Images