Port potential safety hazard automatic monitoring and premium rate adjusting method and system

Abstract

The invention discloses a port potential safety hazard automatic monitoring and insurance rate adjusting method and system, and the method comprises the steps: collecting safety monitoring data and image data of a port, and carrying out the preprocessing of the safety monitoring data and the image data; performing 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 a protection rate according to the safety risk value to obtain an adjustment proportion, and constructing a port safety monitoring insurance rate adjustment model according to the adjustment proportion; and optimizing the port safety monitoring premium rate adjustment model, inputting to-be-adjusted data into the port safety monitoring premium rate adjustment model, and outputting an adjustment result. The method not only can improve the precision of port potential safety hazard automatic monitoring and premium rate adjustment, but also has good interpretability, and can be directly applied to a premium rate adjustment system.

Description

Technical Field

[0001] The present invention relates to the field of monitoring and adjustment, and in particular to a method and system for automatically monitoring potential safety hazards at ports and adjusting insurance premium rates. Background Art

[0002] With the continuous development of global trade, ports, as important hubs for international trade, are becoming increasingly important for safe operation. However, port operations face many potential safety hazards, including but not limited to equipment and facility failures, personnel operating errors, imperfect management, and poor operating environment. These hazards may not only lead to interruptions in port operations, but may also cause highly hazardous accidents, resulting in significant property losses and casualties. Traditional port safety management methods mainly rely on manual inspections and empirical judgments. This method is not only inefficient, but also difficult to fully 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 begun to gradually transform towards intelligence and automation.

[0003] At present, some ports have begun to try to use sensors, cameras and other equipment to collect port safety monitoring data and image data, but these data often have problems such as noise and redundancy, and direct use for safety assessment may lead to inaccurate results. In addition, although risks can be assessed through preliminary analysis of safety monitoring data, relying solely on data is often difficult to fully reflect the actual situation of port safety production, especially for some emergencies or complex scenarios, which require comprehensive judgment in combination with image data.

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

[0005] The purpose of the present invention is to provide a method for automatically monitoring potential safety hazards in a port and adjusting insurance premium rates.

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

[0007] The present invention comprises the following steps:

[0008] Collecting safety monitoring data and image data of the port, and preprocessing the safety monitoring data and the image data;

[0009] 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;

[0010] 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;

[0011] 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.

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

[0013] Extract risk features from safety monitoring data through machine learning algorithms and conduct safety assessments based on risk features;

[0014] Calculate the risk score based on the risk characteristics:

[0015]

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

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

[0018] 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:

[0019]

[0020] Among them The risk data is The threshold of risk data is k o , the bandwidth parameter is The amount 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 sth moment is The risk score is The upper limit of monitoring time is N, and the real-time risk score and risk score The offset

[0021] The risk score is corrected according to the offset and the expression is:

[0022]

[0023] 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

[0024] 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;

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

[0026]

[0027] The position of the cth particle in the uth direction in the yth dimension is The position of the cth particle in the yth 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 walk parameter of the yth dimension is l y , the target position is V aim ;

[0028] Use the inertia weight to update the particle position to obtain the inertial position. The expression is:

[0029]

[0030] The inertial position of the cth particle in the yth dimension at the t+1th iteration is The position of the cth particle in the yth dimension at the tth iteration is The position of the particle in the y dimension at the tth iteration is The step size coefficient is η, and the inertia weight of the tth iteration is χ t ;

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

[0032]

[0033] The inertia weight of the t+1th iteration is χ t+1 , the maximum number of iterations is t max , the maximum value of the inertia weight is χ max , 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 continue iterating until the minimum mean square error is reached.

[0035] The risk score is corrected according to the control coefficient of the minimum mean square error and output as a safety risk value.

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

[0037] The insurance ratio is calculated based on the port's claim record, safety risk value and protection premium rate:

[0038]

[0039] The insurance ratio of the ath port is H a , the zth claim record is K z , the importance of the a-th port is ψ a , the safety risk value of the a-th port is ε a The protection fee for the ath port is The value of the protected object of the ath port is E a , the number of claim records is n z ;

[0040] The offset correction strategy is used to search for adaptive weights and update the velocity and position of the particle. 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] The dimension of the particle is y, the number of iterations is t, and the speed of the j-th particle of dimension y in the t+1th iteration is D jy (t+1), the velocity of the jth particle in dimension y at the tth 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 jth particle with dimension y at the t+1th iteration is X jy (t+1), the position of the jth particle in dimension y at the tth iteration is X jy (t), the optimal position of the individual particle is X bs , the global optimal position of the particle is A bs , the adaptive weight of the tth iteration is θ;

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

[0045]

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

[0047] For the protection rate tension disturbance, the expression is:

[0048]

[0049] 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 size is γ o , the perturbation coefficient α of the tth 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. The expression is:

[0051]

[0052] ΔH=|H a -H o |

[0053] The corrected position of the jth particle dimension y at the t+1th iteration is The threshold of insurance ratio is H o , the updated position of the jth particle dimension y in the tth iteration is The offset of the insurance ratio is ΔH;

[0054] 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.

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

[0056] The objective function is constructed according to the adjustment ratio, and the expression is:

[0057]

[0058] 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

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

[0060] The convolutional neural network algorithm captures spatial and temporal patterns through convolution, extracts risk features from input image data, and obtains temporal risk features;

[0061] The time series analysis algorithm performs trend analysis on time series risk characteristics and insurance ratios according to time to obtain the changing trend;

[0062] 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.

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

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

[0065]

[0066] The initial position sequence of the searcher is R b , the chaotic map sequence of the searcher is R b+1 , the mapping coefficient is α;

[0067] Compute the position of the searcher:

[0068]

[0069] 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 searcher is

[0070] Update the searcher's position according to the density factor to obtain the density position. The expression is:

[0071]

[0072] 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 t max , the current iteration number is t, the random numbers from 0 to 1 are r1, r2, r3, the density factor is ζ, the control coefficient is β, the density coefficient is ω, and the position of the w+1th searcher is

[0073] Update the position of the searcher according to the adaptive inertia weight to obtain the inertia position. The expression is:

[0074]

[0075] The inertial position of the w-th searcher at the t+1th iteration is The adaptive inertia weight of the tth 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] Continue to iterate until the maximum number of iterations is reached, otherwise update the adaptive inertia weight.

[0077] Second, a port safety hazard automatic monitoring and insurance premium rate adjustment system, including:

[0078] 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;

[0079] 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;

[0080] 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;

[0081] 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.

[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, which when executed cause the processor to perform 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, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes 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 potential safety hazards in ports and adjusting insurance premium rates. Compared with the prior art, the present invention has the following technical effects:

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

[0088] Figure 1 A flowchart of the steps of a method for automatically monitoring potential safety hazards in ports and adjusting insurance premium rates according to the present invention;

[0089] Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0090] The present invention is further described below by means of specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0091] The present invention provides a method and system for automatically monitoring potential safety hazards in ports and adjusting insurance premium rates, comprising the following steps:

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

[0093] Collecting safety monitoring data and image data of the port, and preprocessing the safety monitoring data and the image data;

[0094] In the actual evaluation, the storage tank area of ​​XXX Port was taken as the research object, and the safety monitoring data included 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 value 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, safety valve opening times, and flare system combustion conditions;

[0095] 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;

[0096] In the actual assessment, the risk score was 0.5784 and the safety risk value was 0.6091;

[0097] 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;

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

[0099] 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.

[0100] In this embodiment, the method of performing security assessment on the security monitoring data to obtain a risk score includes:

[0101] Extract risk features from safety monitoring data through machine learning algorithms and conduct safety assessments based on risk features;

[0102] Calculate the risk score based on the risk characteristics:

[0103]

[0104] The change of the i-th risk feature from the sth moment to the s+1th moment is The i-th risk characteristic is h i , the probability of the occurrence of the i-th risk feature is P(h i ), the i-th maximum satisfactory deviation value is The i-th smallest change is The proportional control coefficient is The constant of change is The risk score is The maintenance cost is S.

[0105] In this embodiment, the method of using the image data to correct the risk score to obtain a security risk value includes:

[0106] 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:

[0107]

[0108] Among them The risk data is The threshold of risk data is k o , the bandwidth parameter is The amount 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 sth moment is The risk score is The upper limit of monitoring time is N, and the real-time risk score and risk score The offset

[0109] The risk score is corrected according to the offset and the expression is:

[0110]

[0111] 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

[0112] 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;

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

[0114]

[0115] The position of the cth particle in the uth direction in the yth dimension is The position of the cth particle in the yth 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 walk parameter of the yth dimension is l y , the target position is V aim ;

[0116] Use the inertia weight to update the particle position to obtain the inertial position. The expression is:

[0117]

[0118] The inertial position of the cth particle in the yth dimension at the t+1th iteration is The position of the cth particle in the yth dimension at the tth iteration is The position of the particle in the y dimension at the tth iteration is The step size coefficient is η, and the inertia weight of the tth iteration is χ t ;

[0119] Update the inertia weight, the expression is:

[0120]

[0121] The inertia weight of the t+1th iteration is χ t+1 , the maximum number of iterations is t max , the maximum value of the inertia weight is χ max , the minimum value of the inertia 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 continue iterating until the minimum mean square error is reached.

[0123] The risk score is corrected according to the control coefficient of the minimum mean square error and output as a safety risk value.

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

[0125] The insurance ratio is calculated based on the port's claim record, safety risk value and protection premium rate:

[0126]

[0127] The insurance ratio of the ath port is H a , the zth claim record is K z , the importance of the a-th port is ψ a , the safety risk value of the a-th port is ε a The protection fee for the ath port is The value of the protected object of the ath port is E a , the number of claim records is n z ;

[0128] The offset correction strategy is used to search for adaptive weights 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] The dimension of the particle is y, the number of iterations is t, and the speed of the j-th particle of dimension y in the t+1th iteration is D jy (t+1), the velocity of the jth particle in dimension y at the tth 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 jth particle with dimension y at the t+1th iteration is X jy (t+1), the position of the jth particle in dimension y at the tth iteration is X jy (t), the optimal position of the individual particle is X bs , the global optimal position of the particle is A bs , the adaptive weight of the tth iteration is θ;

[0132] Update the adaptive weight, the expression is:

[0133]

[0134] The initial value of the genetic weight of dimension y is The final value of the genetic weight after iteration 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 t max , the dimension weight is ζ, the number of iterations is t, the rotation parameter is c,

[0135] For the protection rate tension disturbance, the expression is:

[0136]

[0137] 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 size is γ o , the perturbation coefficient α of the tth 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. The expression is:

[0139]

[0140] ΔH=|H a -H o |

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

[0142] 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.

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

[0144] The objective function is constructed according to the adjustment ratio, and the expression is:

[0145]

[0146] 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 premium rate adjustment model includes convolutional neural network algorithm, time series analysis algorithm, and machine learning algorithm;

[0148] The convolutional neural network algorithm captures spatial and temporal patterns through convolution, extracts risk features from input image data, and obtains temporal risk features;

[0149] The time series analysis algorithm performs trend analysis on time series risk characteristics and insurance ratios according to time to obtain the changing trend;

[0150] 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.

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

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

[0153]

[0154] The initial position sequence of the searcher is R b , the chaotic map sequence of the searcher is R b+1 , the mapping coefficient is α;

[0155] Compute the position of the searcher:

[0156]

[0157] 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 searcher is

[0158] Update the searcher's position according to the density factor to obtain the density position. The expression is:

[0159]

[0160] 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 t max , the current iteration number is t, the random numbers from 0 to 1 are r1, r2, r3, the density factor is ζ, the control coefficient is β, the density coefficient is ω, and the position of the w+1th searcher is

[0161] Update the position of the searcher according to the adaptive inertia weight to obtain the inertia position. The expression is:

[0162]

[0163] The inertial position of the w-th searcher at the t+1th iteration is The adaptive inertia weight of the tth 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 ;

[0164] Continue to iterate until the maximum number of iterations is reached, otherwise update the adaptive inertia weight.

[0165] Second, a port safety hazard automatic monitoring and insurance premium rate adjustment system, including:

[0166] 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;

[0167] 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;

[0168] 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;

[0169] 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.

[0170] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. 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. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

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

[0172] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides 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 a port safety hazard automatic monitoring and insurance premium rate adjustment device at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the above-mentioned port safety hazard automatic monitoring and insurance premium rate adjustment methods.

[0174] The above application Figure 1 The method for automatically monitoring and adjusting insurance premiums for port safety hazards disclosed in the illustrated embodiment 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 an integrated logic circuit of hardware in the processor or by instructions in the form of software. The above 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 gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. 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 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 a decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0175] The electronic device may also perform Figure 1 A method for automatically monitoring port safety hazards and adjusting insurance premium rates, and realizing Figure 1The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0176] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple application programs, any one of the aforementioned port safety hazard automatic monitoring and insurance premium adjustment methods is executed.

[0177] 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 in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

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

[0179] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0180] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[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 description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in 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; 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 characteristic is h i , the probability of the occurrence of the i-th risk feature is P(h i ), the i-th maximum satisfactory deviation value is The i-th smallest change is The proportional control coefficient is The constant of change is The risk score is The maintenance cost is S.

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 of using the image data to correct the risk score to obtain a safety risk value comprises: 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 k o , the bandwidth parameter is The amount 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 sth moment is The risk score is The upper limit of monitoring time is N, and the real-time risk score and risk score The offset 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 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 position of the cth particle in the uth direction in the yth dimension is The position of the cth particle in the yth 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 walk parameter of the yth dimension is l y , the target position is V aim ; Use the inertia weight to update the particle position to obtain the inertial position. The expression is: The inertial position of the cth particle in the yth dimension at the t+1th iteration is The position of the cth particle in the yth dimension at the tth iteration is The position of the particle in the y dimension at the tth iteration is The step size coefficient is η, and the inertia weight of the tth iteration is χ t ; Update the inertia weight, the expression is: The inertia weight of the t+1th iteration is χ t+1 , the maximum number of iterations is t max , the maximum value of the inertia weight is χ max , the minimum value of the inertia weight is χ min ; 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.

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 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 H a , the zth claim record is K z , the importance of the a-th port is ψ a , the safety risk value of the a-th port is ε a The protection fee for the ath port is The protection value of the ath port is E a , the number of claim records is n z ; The offset correction strategy is used to search for adaptive weights and update the velocity and position of the particle. The expression is: D jy (t+1)=θ(t)·D jy (t)+c1b1(X bs -D jy (t))+c2b2(A bs -D jy (t)) X jy (t+1)=D jy (t+1)+X jy (t) The dimension of the particle is y, the number of iterations is t, and the speed of the j-th particle of dimension y in the t+1th iteration is D jy (t+1), the velocity of the jth particle in dimension y at the tth 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 jth particle with dimension y at the t+1th iteration is X jy (t+1), the position of the jth particle in dimension y at the tth iteration is X jy (t), the optimal position of the individual particle is X bs , the global optimal position of the particle is A bs , the adaptive weight of the tth iteration is θ; 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 after iteration 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 t max , the dimension weight is ζ, 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 size is γ o , the perturbation coefficient α of the tth iteration t , the maximum dimension is max u , the minimum dimension is min u ; Update the particle position according to the offset of the insurance ratio to obtain the corrected position. The expression is: ΔH=|H a -H o | The corrected position of the jth particle dimension y at the t+1th iteration is The threshold of insurance ratio is H o , the updated position of the jth particle dimension y in the tth iteration is The offset of the insurance ratio is ΔH; Continue to iterate 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.

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 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 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 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.

6. 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 R b , the chaotic map sequence of the searcher is R b+1 , the mapping coefficient is α; Compute the position of the searcher: 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 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 t max , the current iteration number is t, the random numbers from 0 to 1 are r1, r2, r3, the density factor is ζ, the control coefficient is β, the density coefficient is ω, and 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 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 ; Continue to iterate until the maximum number of iterations is reached, otherwise update the adaptive inertia weight.

7. A port safety hazard automatic monitoring and insurance premium rate adjustment system, used to implement any of the methods described in claims 1-6, 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.

8. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the method according to any one of claims 1 to 6.

9. 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 6.

Images