Risk assessment method and device based on artificial intelligence, computer equipment and medium

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to an artificial intelligence-based risk assessment method and device, computer equipment and a storage medium, which are applied to the field of financial risk control businesses, and the method comprises the steps: obtaining marine environment data collected by a remote sensing satellite, and obtaining local marine environment data collected by local monitoring equipment; integrating the marine environment data and the local marine environment data to obtain target marine environment data; performing environment analysis on the target marine environment data to obtain environment parameters; performing biological monitoring on the target marine environment data to obtain a biological monitoring result; performing risk identification on the environmental parameters and the biological monitoring result to obtain a target risk factor; performing risk assessment on the target risk factor to obtain a risk assessment result; and generating a target risk level corresponding to the target risk factor based on the risk assessment result. In addition, the target risk level may be stored in a blockchain. According to the invention, the processing efficiency and processing accuracy of risk assessment processing are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence development technology, and in particular to artificial intelligence-based risk assessment methods, devices, computer equipment and storage media. Background Art

[0002] In the field of aquaculture, especially for marine aquaculture enterprises, the assessment and approval process of insurance policies and loan applications faces many special difficulties and challenges for financial insurance companies. This is mainly due to the wide variety of aquaculture products in my country, the complex and diverse production methods, and the susceptibility to multiple risks such as natural disasters, diseases and human factors.

[0003] At present, risk assessment of marine environmental data is mostly done manually, which has problems such as low efficiency and low accuracy. Manual assessment is not only time-consuming and labor-intensive, but also difficult to achieve real-time and accurate monitoring and analysis of large amounts of environmental data. In addition, manual assessment is easily affected by subjective factors, resulting in instability and unreliability of assessment results. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a risk assessment method, device, computer equipment and storage medium based on artificial intelligence to solve the technical problems of low processing efficiency and low accuracy of the existing manual method for risk assessment of marine environmental data.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a risk assessment method based on artificial intelligence, which adopts the following technical solutions:

[0006] Obtaining marine environmental data collected by remote sensing satellites, and obtaining local marine environmental data collected by local monitoring equipment;

[0007] Integrate the marine environment data with the local marine environment data to obtain corresponding target marine environment data;

[0008] Performing environmental analysis on the target marine environmental data to obtain corresponding environmental parameters;

[0009] Performing biological monitoring processing on the target marine environment data to obtain corresponding biological monitoring results;

[0010] Performing risk identification on the environmental parameters and the biological monitoring results to obtain corresponding target risk factors;

[0011] Performing risk assessment on the target risk factor to obtain a corresponding risk assessment result;

[0012] A target risk level corresponding to the target risk factor is generated based on the risk assessment result.

[0013] Furthermore, the step of integrating the marine environment data with the local marine environment data to obtain corresponding target marine environment data specifically includes:

[0014] Obtain preset time-space matching strategy and data fusion strategy;

[0015] Perform matching processing on the marine environment data and the local marine environment data based on the spatiotemporal matching strategy to obtain corresponding matching data;

[0016] Based on the data fusion strategy, the matching data is fused to obtain corresponding fused data;

[0017] Preprocessing the fused data to obtain corresponding processed data;

[0018] The processed data is used as the target ocean environment data.

[0019] Furthermore, the step of performing environmental analysis on the target marine environmental data to obtain corresponding environmental parameters specifically includes:

[0020] Performing water quality analysis on the target marine environment data to obtain corresponding water quality parameters;

[0021] Performing temperature analysis on the target ocean environment data to obtain corresponding temperature parameters;

[0022] Performing chlorophyll analysis on the target marine environment data to obtain corresponding chlorophyll concentration parameters;

[0023] The environmental parameter is generated based on the water quality parameter, the temperature parameter, and the chlorophyll concentration parameter.

[0024] Furthermore, the step of performing biological monitoring processing on the target marine environment data to obtain corresponding biological monitoring results specifically includes:

[0025] Performing plankton identification processing on the target marine environment data to obtain corresponding identification results;

[0026] Performing fish school monitoring processing on the target marine environment data to obtain corresponding monitoring results;

[0027] The biological monitoring result is generated based on the identification result and the monitoring result.

[0028] Furthermore, the step of performing risk identification on the environmental parameters and the biological monitoring results to obtain corresponding target risk factors specifically includes:

[0029] Performing data integration on the environmental parameters and the biological monitoring results to obtain a corresponding comprehensive data set;

[0030] Extracting features related to the risks of farming activities from the comprehensive dataset;

[0031] Calling the preset risk identification algorithm;

[0032] Perform risk identification on the feature based on the risk identification algorithm to obtain a corresponding initial risk factor;

[0033] Get preset feedback information;

[0034] Adjusting the initial risk factor based on the feedback information to obtain an adjusted initial risk factor;

[0035] The adjusted initial risk factor is used as the target risk factor.

[0036] Furthermore, the step of performing risk assessment on the target risk factor to obtain a corresponding risk assessment result specifically includes:

[0037] Obtain preset probability estimation strategies and impact assessment strategies;

[0038] Based on the probability estimation strategy, the target risk factor is evaluated for the probability of occurrence to obtain the corresponding target probability of occurrence;

[0039] Get the preset target impact dimension;

[0040] Performing an impact assessment process on the target risk factor based on the impact assessment strategy to obtain a target impact degree of the target risk factor on the target impact dimension;

[0041] The risk assessment result is generated based on the target occurrence probability and the target impact degree.

[0042] Furthermore, the step of generating a target risk level corresponding to the target risk factor based on the risk assessment result specifically includes:

[0043] Call the preset level mapping table;

[0044] Mapping the target occurrence probability based on the level mapping table to obtain a corresponding designated level;

[0045] Get the preset risk level mapping strategy;

[0046] Performing a level mapping process on the designated level and the target impact degree based on the risk level mapping strategy to obtain a corresponding designated risk level;

[0047] The designated risk level is used as the target risk level.

[0048] In order to solve the above technical problems, the embodiment of the present application also provides a risk assessment device based on artificial intelligence, which adopts the following technical solution:

[0049] An acquisition module is used to acquire ocean environment data collected by remote sensing satellites and to acquire local ocean environment data collected by local monitoring equipment;

[0050] An integration module, used for integrating the marine environment data with the local marine environment data to obtain corresponding target marine environment data;

[0051] An analysis module is used to perform environmental analysis on the target marine environmental data to obtain corresponding environmental parameters;

[0052] A monitoring module, used to perform biological monitoring processing on the target marine environment data to obtain corresponding biological monitoring results;

[0053] An identification module, used to perform risk identification on the environmental parameters and the biological monitoring results to obtain corresponding target risk factors;

[0054] An assessment module, used to perform risk assessment on the target risk factor and obtain a corresponding risk assessment result;

[0055] A generating module is used to generate a target risk level corresponding to the target risk factor based on the risk assessment result.

[0056] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0057] The computer device includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the artificial intelligence-based risk assessment methods proposed in the embodiments of the present application are implemented.

[0058] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0059] The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of any one of the artificial intelligence-based risk assessment methods proposed in the embodiments of the present application are implemented.

[0060] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0061] The present application first obtains marine environmental data collected by remote sensing satellites, and obtains local marine environmental data collected by local monitoring equipment; then integrates the marine environmental data and the local marine environmental data to obtain corresponding target marine environmental data; then performs environmental analysis processing on the target marine environmental data to obtain corresponding environmental parameters; and performs biological monitoring processing on the target marine environmental data to obtain corresponding biological monitoring results; subsequently, performs risk identification on the environmental parameters and the biological monitoring results to obtain corresponding target risk factors; further performs risk assessment on the target risk factors to obtain corresponding risk assessment results; finally, generates a target risk level corresponding to the target risk factor based on the risk assessment results. The present application obtains target marine environmental data through the use of remote sensing satellites and local monitoring equipment, then performs environmental analysis processing and biological monitoring processing on the target marine environmental data to obtain corresponding environmental parameters and monitoring results, subsequently obtains target risk factors through risk identification of the environmental parameters and the biological monitoring results, and then performs risk assessment on the target risk factors to obtain risk assessment results, and generates a target risk level corresponding to the target risk factor based on the risk assessment results, thereby achieving automatic and accurate completion of risk assessment processing for marine environmental data and generating corresponding target risk levels, thereby improving the processing efficiency and accuracy of risk assessment processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0063] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0064] Figure 2 A flowchart of an embodiment of an artificial intelligence-based risk assessment method according to the present application;

[0065] Figure 3 is a schematic structural diagram of an embodiment of an artificial intelligence-based risk assessment device according to the present application;

[0066] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0068] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0069] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0070] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0071] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0072] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, the tablet computer 1012 or the mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer, a desktop computer, etc.

[0073] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0074] It should be noted that the artificial intelligence-based risk assessment method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based risk assessment device is generally set in the server / terminal device.

[0075] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0076] Continue to refer Figure 2 , showing a flow chart of an embodiment of an artificial intelligence-based risk assessment method according to the present application. According to different needs, the order of the steps in the flow chart can be changed, and some steps can be omitted. The artificial intelligence-based risk assessment method provided in the embodiment of the present application can be applied to any scenario that requires risk assessment, and the artificial intelligence-based risk assessment method can be applied to products in these scenarios, for example, risk analysis of marine aquaculture in the field of finance and insurance. The artificial intelligence-based risk assessment method comprises the following steps:

[0077] Step S201, obtaining ocean environment data collected by remote sensing satellites, and obtaining local ocean environment data collected by local monitoring equipment.

[0078] In this embodiment, the electronic device (e.g. Figure 1The server / terminal device shown in the figure) can obtain the above-mentioned marine environment data and the above-mentioned local marine environment data through a wired connection method or a wireless connection method. It should be pointed out that the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, Wi-Fi connection, Bluetooth connection, Wi MAX connection, Zigbee connection, UWB (ultra wi deband) connection, and other wireless connection methods currently known or to be developed in the future. The execution subject of this application is based on a multi-level smart fishery system that can be based on the nebula edge.

[0079] Specifically, the multi-level smart fishery system based on the Nebula edge is divided from bottom to top into the device end, edge control center, cloud control center and remote sensing satellite.

[0080] 1. Equipment side (i.e. the above-mentioned local monitoring equipment): including the installation of water quality monitors, underwater cameras, lighting, various sensor modules, sonar detection devices, automatic feeding and other equipment in deep-sea aquaculture areas.

[0081] 2. Edge control center: Deployed on the breeding platform, it realizes data access of sensors, robots, and automation equipment at the local device layer of the cage platform, provides data collection and data processing services, and makes intelligent decisions based on data analysis results to control on-site equipment, such as intelligent feeding, fish fry release, live fish capture, air supply and breeding, cage cleaning, etc. Local data processing is performed through edge nodes, which reduces data processing and transmission delays, thereby improving real-time performance and the accuracy of the control system. In addition, the edge control center also needs to communicate with the cloud control center, upload information on the edge end, and receive control from the cloud center. In places with poor network, important information can also be sent to the cloud control center via satellite communication.

[0082] 3. Cloud control center: realize two-way communication with the cage platform, connect the edge side to the cloud, realize data access of a large number of distributed sensors, automation equipment and robots, build a fishery aquaculture big data platform based on aquaculture models, realize remote status monitoring, equipment management, energy management, fault diagnosis, data visualization, decision support and other services in the cloud, form a cloud control center integrating data, algorithms, models and services for deep-sea intelligent aquaculture, and enhance the data calculation and processing capabilities of the control system. The system realizes automatic identification and classification of underwater fish through high-definition cameras and AI intelligent models, helping farm owners to monitor the fish conditions in the aquaculture area in real time, such as the number, size, species, individual daily activities, feeding conditions, disease occurrence, etc.; at the same time, the system is linked with water quality monitoring equipment to automatically analyze water quality data, such as dissolved oxygen, salinity, pH value and other key indicators of aquaculture.

[0083] 4. Remote sensing satellites: Underwater cameras and sensors can only detect data changes in a small area, while satellite remote sensing can obtain marine environmental data over a large area, for a long time, and in near real time. Satellite remote sensing images can be used to analyze the status of marine aquaculture organisms. Remote sensing satellites are used to collect marine environmental data regularly or on demand, including water quality (such as transparency, suspended matter concentration), ocean temperature, chlorophyll concentration, plankton distribution, and fish monitoring.

[0084] In the marine aquaculture industry, satellite remote sensing combined with local monitoring equipment can provide more comprehensive information and decision support. Compared with limited-range sensors, cameras and other equipment, satellite remote sensing can obtain marine environmental data over a large area, for a long time, and in near real time, which is more helpful for analyzing potential risks and making timely responses to reduce losses.

[0085] Step S202, integrating the marine environment data with the local marine environment data to obtain corresponding target marine environment data.

[0086] In this embodiment, the above-mentioned specific implementation process of integrating the marine environment data with the local marine environment data to obtain the corresponding target marine environment data will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0087] Step S203, performing environmental analysis processing on the target ocean environmental data to obtain corresponding environmental parameters.

[0088] In this embodiment, the above-mentioned specific implementation process of performing environmental analysis on the target ocean environmental data to obtain corresponding environmental parameters will be described in further detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0089] Step S204, performing biological monitoring processing on the target marine environment data to obtain corresponding biological monitoring results.

[0090] In this embodiment, the above-mentioned biological monitoring processing of the target marine environment data to obtain the corresponding biological monitoring results is a specific implementation process, which will be further described in detail in subsequent specific embodiments of this application and will not be elaborated in detail here.

[0091] Step S205: performing risk identification on the environmental parameters and the biological monitoring results to obtain corresponding target risk factors.

[0092] In this embodiment, the above-mentioned specific implementation process of risk identification of the environmental parameters and the biological monitoring results to obtain the corresponding target risk factors will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0093] Step S206: perform risk assessment on the target risk factor to obtain a corresponding risk assessment result.

[0094] In this embodiment, the above-mentioned specific implementation process of performing risk assessment on the target risk factor to obtain the corresponding risk assessment result will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated in detail here.

[0095] Step S207: generating a target risk level corresponding to the target risk factor based on the risk assessment result.

[0096] In this embodiment, the specific implementation process of generating the target risk level corresponding to the target risk factor based on the risk assessment result will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0097] The present application obtains target marine environmental data through the use of remote sensing satellites and local monitoring equipment, then performs environmental analysis processing and biological monitoring processing on the target marine environmental data to obtain corresponding environmental parameters and monitoring results, subsequently obtains target risk factors through risk identification of the environmental parameters and the biological monitoring results, and then performs risk assessment on the target risk factors to obtain risk assessment results, and generates a target risk level corresponding to the target risk factor based on the risk assessment results, thereby achieving automatic and accurate completion of risk assessment processing for marine environmental data and generating corresponding target risk levels, thereby improving the processing efficiency and accuracy of risk assessment processing.

[0098] In some optional implementations, step S202 includes the following steps:

[0099] Get the preset space-time matching strategy and data fusion strategy.

[0100] In this embodiment, the strategy content of the above-mentioned spatiotemporal matching strategy includes: first extract the timestamp information in the satellite remote sensing data (i.e., marine environment data) and the local data (local marine environment data). Then the timestamp is normalized to ensure the consistency of time (such as unified to UTC time). Then spatial position matching is performed. By determining the spatial position information (such as longitude and latitude) of the satellite remote sensing data and the local data, the satellite remote sensing data and the local data are spatially matched using GIS (geographic information system) technology or spatial matching algorithm. Synchronicity verification is performed subsequently. The matched data is subjected to synchronization verification to check the continuity and consistency of the data in time. And the data that does not meet the requirements is screened or corrected.

[0101] The data fusion strategy mentioned above includes data integration processing and data quality inspection processing. Among them: data integration processing includes: integrating the matched satellite remote sensing data and local data into a comprehensive data set, and ensuring the accuracy and consistency of each field in the data set. Data quality inspection processing includes: conducting a comprehensive quality check on the fused data, including completeness, accuracy, consistency, etc., and timely processing and correction of the problems found. In addition, the data can also be pre-processed and formatted according to the needs of subsequent analysis or application.

[0102] The ocean environment data and the local ocean environment data are matched based on the time-space matching strategy to obtain corresponding matching data.

[0103] In this embodiment, the ocean environment data and the local ocean environment data may be matched according to the strategy content of the above-mentioned spatiotemporal matching strategy, so as to obtain corresponding matching data.

[0104] The matching data is fused based on the data fusion strategy to obtain corresponding fused data.

[0105] In this embodiment, the matching data may be fused according to the policy content of the above data fusion policy to obtain corresponding fused data.

[0106] The fused data is preprocessed to obtain corresponding processed data.

[0107] In this embodiment, the preprocessing may include noise removal, outlier processing, and data normalization processing.

[0108] The processed data is used as the target ocean environment data.

[0109] The present application obtains a preset space-time matching strategy and a data fusion strategy; then matches the marine environment data with the local marine environment data based on the space-time matching strategy to obtain corresponding matching data; then fuses the matching data based on the data fusion strategy to obtain corresponding fused data; subsequently pre-processes the fused data to obtain corresponding processed data, and uses the processed data as the target marine environment data. The present application uses a preset space-time matching strategy and a data fusion strategy to match and fuse the marine environment data with the local marine environment data based on the space-time matching strategy to obtain fused data, and then pre-processes the fused data, thereby completing the corresponding data integration processing and obtaining the target marine environment data, thereby ensuring the accuracy of the obtained target marine environment data. And the obtained target marine environment data can provide more comprehensive information and decision support.

[0110] In some optional implementations of this embodiment, step S203 includes the following steps:

[0111] The target marine environment data is subjected to water quality analysis and processing to obtain corresponding water quality parameters.

[0112] In this embodiment, the transparency and suspended matter concentration in the target marine environment data can be analyzed to evaluate the water quality of the marine aquaculture area and detect the water quality parameters of the detected ocean, such as turbidity, dissolved oxygen, salinity, etc. In addition, the changing trend of water quality parameters can be identified by using time series analysis techniques (such as ARIMA model, seasonal decomposition, etc.).

[0113] The target ocean environment data is subjected to temperature analysis and processing to obtain corresponding temperature parameters.

[0114] In this embodiment, the temperature parameter may specifically refer to sea surface temperature information. Sea surface temperature information helps determine the suitability of different ocean regions and whether a particular type of cultured organism is in ideal environmental conditions. In addition, a temperature map of the ocean surface may be generated using GIS software or programming tools. By analyzing the temperature map, abnormal temperature areas (such as hot spots or cold spots) are identified and their possible impact on cultured organisms is assessed. Alternatively, the correlation between temperature and other water quality parameters (such as dissolved oxygen, pH value) is further explored to more fully understand the environmental conditions.

[0115] The target marine environment data is subjected to chlorophyll analysis and processing to obtain corresponding chlorophyll concentration parameters.

[0116] In this embodiment, the chlorophyll concentration parameter refers to the chlorophyll concentration in the ocean. The chlorophyll concentration can reflect the amount of phytoplankton biomass in the ocean, and there is a food relationship between phytoplankton, zooplankton, and fish. Specifically, the process of calculating the chlorophyll concentration includes: using the red light and near-infrared band information in the target ocean environment data, and calculating the chlorophyll concentration through a specific algorithm (such as the OC4 algorithm). In addition, based on the chlorophyll concentration data, the change of phytoplankton biomass can be evaluated and its impact on the marine ecosystem can be predicted.

[0117] The environmental parameter is generated based on the water quality parameter, the temperature parameter, and the chlorophyll concentration parameter.

[0118] In this embodiment, the environmental parameters may be obtained by integrating the water quality parameters, the temperature parameters, and the chlorophyll concentration parameters.

[0119] The present application performs water quality analysis on the target marine environment data to obtain corresponding water quality parameters; performs temperature analysis on the target marine environment data to obtain corresponding temperature parameters; performs chlorophyll analysis on the target marine environment data to obtain corresponding chlorophyll concentration parameters; and subsequently generates the environmental parameters based on the water quality parameters, the temperature parameters, and the chlorophyll concentration parameters. The present application performs water quality analysis, temperature analysis, and chlorophyll analysis on the target marine environment data, and then generates corresponding environmental parameters based on the obtained water quality parameters, temperature parameters, and chlorophyll concentration parameters, thereby ensuring the accuracy and richness of the obtained environmental parameters.

[0120] In some optional implementations, step S204 includes the following steps:

[0121] The target marine environment data is subjected to plankton identification processing to obtain corresponding identification results.

[0122] In this embodiment, the process of plankton identification includes: extracting spectral features (such as reflectivity, absorptivity, etc.) from the target marine environment data for subsequent classification. Then, the plankton is classified using classification algorithms such as support vector machine (SVM) and random forest. After that, the classification results are post-processed, including removing misclassifications, merging similar categories, etc., and finally counting the number of plankton. Among them, the above classification algorithm requires a training data set to optimize parameters and models.

[0123] The target marine environment data is subjected to fish school monitoring processing to obtain corresponding monitoring results.

[0124] In this embodiment, the above-mentioned fish school monitoring process includes: using a deep learning framework, such as TensorFlow, PyTorch's target detection algorithm (such as YOLO, Faster R-CNN) to locate the fish school. And, for continuous frame image data, use a target tracking algorithm (such as SORT, DeepSORT) to track the movement trajectory of the fish school. Subsequently, based on the tracking results, the migration pattern, aggregation behavior, etc. of the fish school are analyzed to obtain corresponding monitoring results to provide decision support for aquaculture management. Among them, the above-mentioned target detection algorithm can specifically adopt algorithms such as YOLO and Faster R-CNN. The above-mentioned target tracking algorithm can specifically adopt algorithms such as SORT and DeepSORT.

[0125] The biological monitoring result is generated based on the identification result and the monitoring result.

[0126] In this embodiment, the above-mentioned biological monitoring result can be obtained by integrating the recognition result and the monitoring result.

[0127] The present application performs plankton recognition processing on the target marine environment data to obtain corresponding recognition results; and performs fish school monitoring processing on the target marine environment data to obtain corresponding monitoring results; and subsequently generates the biological monitoring results based on the recognition results and the monitoring results. The present application performs plankton recognition processing and fish school monitoring processing on the target marine environment data to obtain corresponding biological monitoring results based on the obtained recognition results and the monitoring results, thereby ensuring the accuracy and diversity of the obtained biological monitoring results.

[0128] In some optional implementations, step S205 includes the following steps:

[0129] The environmental parameters and the biological monitoring results are integrated to obtain a corresponding comprehensive data set.

[0130] In this embodiment, the above-mentioned comprehensive data set is obtained by integrating the environmental parameters (water quality parameters, temperature parameters, chlorophyll concentration parameters) and the biological monitoring results (plankton identification results, fish school monitoring results) into a unified data set.

[0131] Features associated with the risks of farming activities are extracted from the comprehensive dataset.

[0132] In this embodiment, feature extraction can be performed on the comprehensive data set to extract features related to the risks of aquaculture activities, such as water quality deterioration indicators, temperature anomaly thresholds, plankton density changes, fish migration patterns, and other features.

[0133] Call the preset risk identification algorithm.

[0134] In this embodiment, the risk identification algorithm may specifically adopt a statistical analysis algorithm or a machine learning algorithm. The machine learning algorithm may include cluster analysis, decision tree and other algorithms.

[0135] Based on the risk identification algorithm, risk identification is performed on the feature to obtain a corresponding initial risk factor.

[0136] In this embodiment, the risk identification algorithm is applied to automatically identify potential risk factors based on the features extracted from the comprehensive data set. For example, risk factors may include water pollution, temperature changes, harmful algal blooms, fish escaping from the breeding area, etc.

[0137] Get preset feedback information.

[0138] In this embodiment, experts in the fields of marine biology, aquaculture, environmental science, etc. may be invited to participate in the risk assessment process according to the needs of the research field. The comprehensive data set and automatically identified risk factors are presented to the experts, and expert meetings or seminars are organized to discuss and verify the identification of risk factors, and feedback from experts is collected. The automatically identified risk factors are supplemented, corrected, or confirmed to ensure the comprehensiveness and accuracy of risk identification. The above feedback information refers to the feedback from experts.

[0139] The initial risk factor is adjusted based on the feedback information to obtain an adjusted initial risk factor.

[0140] In this embodiment, the automatically identified risk factors are supplemented, corrected or confirmed based on the above feedback information to ensure the comprehensiveness and accuracy of risk identification.

[0141] The adjusted initial risk factor is used as the target risk factor.

[0142] The present application obtains a corresponding comprehensive data set by integrating the environmental parameters and the biological monitoring results; then extracts features related to the risks of aquaculture activities from the comprehensive data set; then calls a preset risk identification algorithm, and performs risk identification on the features based on the risk identification algorithm to obtain a corresponding initial risk factor; subsequently obtains preset feedback information, and adjusts the initial risk factor based on the feedback information to obtain an adjusted initial risk factor; finally, the adjusted initial risk factor is used as the target risk factor. The present application obtains a comprehensive data set by integrating the environmental parameters and the biological monitoring results, and extracts features related to the risks of aquaculture activities from the comprehensive data set, and then performs risk identification on the features based on the risk identification algorithm to obtain an initial risk factor, and subsequently intelligently adjusts the initial risk factor based on the feedback information obtained, thereby accurately generating the corresponding target risk factor, effectively ensuring the comprehensiveness and accuracy of the target risk factor obtained.

[0143] In some optional implementations of this embodiment, step S206 includes the following steps:

[0144] Get the preset probability estimation strategy and impact assessment strategy.

[0145] In this embodiment, the strategy content of the above-mentioned probability estimation strategy includes: collecting historical data related to risk factors, including the frequency of event occurrence, the changing trend of related factors, etc. Then, according to the data type and available resources, select a suitable probability assessment method. Among them, if the historical data is sufficient, statistical models (such as time series analysis, regression analysis) can be used to estimate the probability. If the data is limited, expert judgment or probability models (such as Bayesian networks) can be relied on for estimation. The selected method is subsequently applied to calculate the probability of occurrence of risk factors. If a statistical model is used, the parameters of the model need to be determined and verified. If expert judgment is used, it is necessary to organize an expert meeting and record expert opinions.

[0146] The above impact assessment strategy includes: first, clarify the dimensions that need to be considered when assessing the impact, such as economic losses, biological health impacts, environmental damage, etc. Then, formulate quantitative standards for each impact dimension so that the impact can be converted into comparable values. For example, economic losses can be expressed in monetary units, and biological health impacts can be expressed in mortality or disease incidence. Then, the impact of risk factors on each impact dimension is assessed according to the quantitative standards. Among them, additional data can be collected or field surveys can be conducted. Finally, the assessment results of each impact dimension are combined to obtain the overall impact of risk factors on aquaculture activities.

[0147] Based on the probability estimation strategy, the target risk factor is evaluated for its probability of occurrence to obtain a corresponding target probability of occurrence.

[0148] In this embodiment, the target risk factor may be evaluated for its probability of occurrence according to the policy content of the above-mentioned probability estimation policy to obtain a corresponding target probability of occurrence.

[0149] Gets the preset target impact dimension.

[0150] In this embodiment, the above-mentioned target impact dimensions may specifically include economic losses, biological health impacts, environmental damage and other dimensions.

[0151] An impact assessment process is performed on the target risk factor based on the impact degree assessment strategy to obtain the target impact degree of the target risk factor on the target impact dimension.

[0152] In this embodiment, the target risk factor may be subjected to impact assessment processing according to the policy content of the impact assessment policy, so as to obtain the target impact degree of the target risk factor on the target impact dimension.

[0153] The risk assessment result is generated based on the target occurrence probability and the target impact degree.

[0154] In this embodiment, the target occurrence probability and the target impact degree may be integrated to obtain a corresponding risk assessment result, wherein the risk assessment result includes the target occurrence probability and the target impact degree.

[0155] The present application obtains a preset probability estimation strategy and an impact degree assessment strategy; then, based on the probability estimation strategy, the target risk factor is evaluated for the probability of occurrence to obtain the corresponding target occurrence probability; then, a preset target impact dimension is obtained, and based on the impact degree assessment strategy, an impact assessment is performed on the target risk factor to obtain the target impact degree of the target risk factor on the target impact dimension; subsequently, the risk assessment result is generated based on the target occurrence probability and the target impact degree. The present application obtains a preset probability estimation strategy and an impact estimation strategy; then, based on the impact degree assessment strategy, an impact assessment is performed on the target risk factor to obtain the target impact degree of the target risk factor on the target impact dimension; then, based on the target occurrence probability and the target impact degree, the corresponding risk assessment result can be automatically and intelligently generated, thereby improving the efficiency of generating risk assessment results and ensuring the data accuracy of the obtained risk assessment results.

[0156] In some optional implementations of this embodiment, step S207 includes the following steps:

[0157] Call the preset level mapping table.

[0158] In this embodiment, the level mapping table is a pre-constructed data table storing a one-to-one correspondence between occurrence probability and level, wherein three levels of occurrence probability are pre-defined based on historical data, expert opinions or industry standards - "low", "medium" and "high", and corresponding probability ranges or percentages are set.

[0159] In addition, three levels of impact are clearly defined based on historical data, expert opinions or industry standards - "minor", "moderate" and "serious", and specific standards or thresholds are set for each level of impact. For example, economic losses below a certain amount are "minor", those exceeding a certain amount but not reaching another higher amount are "moderate", and those exceeding the higher amount are "serious".

[0160] The target occurrence probability is mapped based on the level mapping table to obtain a corresponding designated level.

[0161] In this embodiment, the level mapping table may be subjected to level matching processing by using the target occurrence probability to obtain a designated level corresponding to the target occurrence probability.

[0162] Get the preset risk level mapping strategy.

[0163] In this embodiment, the risk level mapping strategy is a pre-constructed strategy that includes a mapping relationship between the level, the degree of impact and the risk level. Specifically, the risk level mapping strategy includes: if the level is "high" or the degree of impact is "serious", the risk level corresponding to the level and the degree of impact is determined to be high risk; if the level is "low" and the degree of impact is "slight", the risk level corresponding to the level and the degree of impact is determined to be low risk; and the risk level corresponding to the level and degree of impact of other situations is determined to be medium risk.

[0164] Based on the risk level mapping strategy, a level mapping process is performed on the designated level and the target impact degree to obtain a corresponding designated risk level.

[0165] In this embodiment, the designated level and the target impact degree may be mapped according to the policy content of the risk level mapping policy, thereby obtaining a corresponding designated risk level.

[0166] The designated risk level is used as the target risk level.

[0167] The present application calls a preset level mapping table; then maps the target occurrence probability based on the level mapping table to obtain the corresponding designated level; then obtains a preset risk level mapping strategy, and performs level mapping between the designated level and the target impact degree based on the risk level mapping strategy to obtain the corresponding designated risk level; and subsequently uses the designated risk level as the target risk level. The present application maps the target occurrence probability based on the use of a level mapping table to obtain the corresponding designated level, and then performs level mapping between the designated level and the target impact degree based on the use of a risk level mapping strategy, so as to realize the rapid and accurate generation of the target risk level corresponding to the target risk factor, thereby realizing the automatic and intelligent completion of the risk assessment processing of the marine environment data and the generation of the corresponding target risk level, and improving the processing efficiency and processing intelligence of the risk assessment processing.

[0168] In some optional implementations, the user information obtained is subject to the user's consent and complies with relevant laws and policies.

[0169] In addition, the multi-level smart fishery system based on the Nebula edge in this application can improve aquaculture efficiency, help insurance companies grasp the real aquaculture situation, better understand potential risks, and help financial insurance institutions provide financing, insurance and other financial services faster and better.

[0170] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0171] It should be emphasized that in order to further ensure the privacy and security of the above target risk level, the above target risk level can also be stored in a node of a blockchain.

[0172] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0173] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0174] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0175] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0176] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0177] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a risk assessment device based on artificial intelligence. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0178] like Figure 3 As shown, the risk assessment device 300 based on artificial intelligence in this embodiment includes: an acquisition module 301, an integration module 302, an analysis module 303, a monitoring module 304, an identification module 305, an assessment module 306 and a generation module 307. Among them:

[0179] The acquisition module 301 is used to acquire ocean environment data collected by remote sensing satellites and acquire local ocean environment data collected by local monitoring equipment;

[0180] An integration module 302 is used to integrate the marine environment data with the local marine environment data to obtain corresponding target marine environment data;

[0181] The analysis module 303 is used to perform environmental analysis on the target marine environmental data to obtain corresponding environmental parameters;

[0182] The monitoring module 304 is used to perform biological monitoring processing on the target marine environment data to obtain corresponding biological monitoring results;

[0183] An identification module 305 is used to perform risk identification on the environmental parameters and the biological monitoring results to obtain corresponding target risk factors;

[0184] An evaluation module 306 is used to perform risk evaluation on the target risk factor to obtain a corresponding risk evaluation result;

[0185] The generating module 307 is used to generate a target risk level corresponding to the target risk factor based on the risk assessment result.

[0186] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based risk assessment method in the aforementioned implementation mode, and will not be repeated here.

[0187] In some optional implementations of this embodiment, the integration module 302 includes:

[0188] The first acquisition submodule is used to acquire a preset spatiotemporal matching strategy and a data fusion strategy;

[0189] A matching submodule, used for matching the marine environment data with the local marine environment data based on the spatiotemporal matching strategy to obtain corresponding matching data;

[0190] A fusion submodule, used for fusing the matching data based on the data fusion strategy to obtain corresponding fused data;

[0191] A preprocessing submodule, used for preprocessing the fused data to obtain corresponding processed data;

[0192] The first determining submodule is used to use the processed data as the target ocean environment data.

[0193] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based risk assessment method in the aforementioned implementation mode, and will not be repeated here.

[0194] In some optional implementations of this embodiment, the analysis module 303 includes:

[0195] The first analysis submodule is used to perform water quality analysis on the target marine environment data to obtain corresponding water quality parameters;

[0196] The second analysis submodule is used to perform temperature analysis on the target ocean environment data to obtain corresponding temperature parameters;

[0197] The third analysis submodule is used to perform chlorophyll analysis on the target marine environment data to obtain corresponding chlorophyll concentration parameters;

[0198] The second determination submodule is used to generate the environmental parameter based on the water quality parameter, the temperature parameter and the chlorophyll concentration parameter.

[0199] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based risk assessment method in the aforementioned implementation mode, and will not be repeated here.

[0200] In some optional implementations of this embodiment, the monitoring module 304 includes:

[0201] The first processing submodule is used to perform plankton recognition processing on the target marine environment data to obtain corresponding recognition results;

[0202] The second processing submodule is used to perform fish school monitoring processing on the target marine environment data to obtain corresponding monitoring results;

[0203] The third determination submodule is used to generate the biological monitoring result based on the recognition result and the monitoring result.

[0204] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based risk assessment method in the aforementioned implementation mode, and will not be repeated here.

[0205] In some optional implementations of this embodiment, the identification module 305 includes:

[0206] An integration submodule, used to integrate the environmental parameters and the biological monitoring results to obtain a corresponding comprehensive data set;

[0207] An extraction submodule, for extracting features related to the risks of aquaculture activities from the comprehensive data set;

[0208] The first calling submodule is used to call a preset risk identification algorithm;

[0209] An identification submodule, used to perform risk identification on the feature based on the risk identification algorithm to obtain a corresponding initial risk factor;

[0210] The second acquisition submodule is used to obtain preset feedback information;

[0211] An adjustment submodule, configured to adjust the initial risk factor based on the feedback information to obtain an adjusted initial risk factor;

[0212] The fourth determination submodule is configured to use the adjusted initial risk factor as the target risk factor.

[0213] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based risk assessment method in the aforementioned implementation mode, and will not be repeated here.

[0214] In some optional implementations of this embodiment, the evaluation module 306 includes:

[0215] The third acquisition submodule is used to acquire a preset probability estimation strategy and impact assessment strategy;

[0216] A third processing submodule is used to evaluate the occurrence probability of the target risk factor based on the probability estimation strategy to obtain a corresponding target occurrence probability;

[0217] The fourth acquisition submodule is used to acquire a preset target impact dimension;

[0218] A fourth processing submodule is used to perform an impact assessment process on the target risk factor based on the impact assessment strategy to obtain a target impact degree of the target risk factor on the target impact dimension;

[0219] A generating submodule is used to generate the risk assessment result based on the target occurrence probability and the target impact degree.

[0220] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based risk assessment method in the aforementioned implementation mode, and will not be repeated here.

[0221] In some optional implementations of this embodiment, the generating module 307:

[0222] The second calling submodule is used to call a preset level mapping table;

[0223] A first mapping submodule, configured to perform mapping processing on the target occurrence probability based on the level mapping table to obtain a corresponding designated level;

[0224] The fifth acquisition submodule is used to acquire a preset risk level mapping strategy;

[0225] A second mapping submodule is used to perform a level mapping process on the designated level and the target impact degree based on the risk level mapping strategy to obtain a corresponding designated risk level;

[0226] The fifth determination submodule is configured to use the designated risk level as the target risk level.

[0227] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based risk assessment method in the aforementioned implementation mode, and will not be repeated here.

[0228] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0229] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.

[0230] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0231] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of a risk assessment method based on artificial intelligence, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0232] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions or process data stored in the memory 41, such as computer-readable instructions for running the artificial intelligence-based risk assessment method.

[0233] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0234] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned artificial intelligence-based risk assessment method.

[0235] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0236] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A risk assessment method based on artificial intelligence, characterized in that: The steps include: Obtain marine environmental data collected by remote sensing satellites, and obtain local marine environmental data collected by local monitoring equipment; Integrate the marine environment data with the local marine environment data to obtain corresponding target marine environment data; Performing environmental analysis on the target marine environmental data to obtain corresponding environmental parameters; Performing biological monitoring processing on the target marine environment data to obtain corresponding biological monitoring results; Performing risk identification on the environmental parameters and the biological monitoring results to obtain corresponding target risk factors; Performing risk assessment on the target risk factor to obtain a corresponding risk assessment result; A target risk level corresponding to the target risk factor is generated based on the risk assessment result.

2. The artificial intelligence-based risk assessment method according to claim 1, characterized in that: The step of integrating the marine environment data with the local marine environment data to obtain corresponding target marine environment data specifically includes: Obtain preset time-space matching strategy and data fusion strategy; Perform matching processing on the marine environment data and the local marine environment data based on the spatiotemporal matching strategy to obtain corresponding matching data; Based on the data fusion strategy, the matching data is fused to obtain corresponding fused data; Preprocessing the fused data to obtain corresponding processed data; The processed data is used as the target ocean environment data.

3. The artificial intelligence-based risk assessment method according to claim 1, characterized in that: The step of performing environmental analysis on the target marine environmental data to obtain corresponding environmental parameters specifically includes: Performing water quality analysis on the target marine environment data to obtain corresponding water quality parameters; Performing temperature analysis on the target ocean environment data to obtain corresponding temperature parameters; Performing chlorophyll analysis on the target marine environment data to obtain corresponding chlorophyll concentration parameters; The environmental parameter is generated based on the water quality parameter, the temperature parameter, and the chlorophyll concentration parameter.

4. The artificial intelligence-based risk assessment method according to claim 1, characterized in that: The step of performing biological monitoring processing on the target marine environment data to obtain corresponding biological monitoring results specifically includes: Performing plankton identification processing on the target marine environment data to obtain corresponding identification results; Performing fish school monitoring processing on the target marine environment data to obtain corresponding monitoring results; The biological monitoring result is generated based on the identification result and the monitoring result.

5. The artificial intelligence-based risk assessment method according to claim 1, characterized in that: The step of performing risk identification on the environmental parameters and the biological monitoring results to obtain corresponding target risk factors specifically includes: Performing data integration on the environmental parameters and the biological monitoring results to obtain a corresponding comprehensive data set; Extracting features related to the risks of farming activities from the comprehensive dataset; Calling the preset risk identification algorithm; Perform risk identification on the feature based on the risk identification algorithm to obtain a corresponding initial risk factor; Get preset feedback information; Adjusting the initial risk factor based on the feedback information to obtain an adjusted initial risk factor; The adjusted initial risk factor is used as the target risk factor.

6. The artificial intelligence-based risk assessment method according to claim 1, characterized in that: The step of performing risk assessment on the target risk factor to obtain a corresponding risk assessment result specifically includes: Obtain preset probability estimation strategies and impact assessment strategies; Based on the probability estimation strategy, the target risk factor is evaluated for the probability of occurrence to obtain the corresponding target probability of occurrence; Get the preset target impact dimension; Performing an impact assessment process on the target risk factor based on the impact assessment strategy to obtain a target impact degree of the target risk factor on the target impact dimension; The risk assessment result is generated based on the target occurrence probability and the target impact degree.

7. The artificial intelligence-based risk assessment method according to claim 6, characterized in that: The step of generating a target risk level corresponding to the target risk factor based on the risk assessment result specifically includes: Call the preset level mapping table; Mapping the target occurrence probability based on the level mapping table to obtain a corresponding designated level; Get the preset risk level mapping strategy; Performing a level mapping process on the designated level and the target impact degree based on the risk level mapping strategy to obtain a corresponding designated risk level; The designated risk level is used as the target risk level.

8. A risk assessment device based on artificial intelligence, characterized in that: include: An acquisition module is used to acquire ocean environment data collected by remote sensing satellites and to acquire local ocean environment data collected by local monitoring equipment; An integration module, used for integrating the marine environment data with the local marine environment data to obtain corresponding target marine environment data; An analysis module is used to perform environmental analysis on the target marine environmental data to obtain corresponding environmental parameters; A monitoring module, used to perform biological monitoring processing on the target marine environment data to obtain corresponding biological monitoring results; An identification module, used to perform risk identification on the environmental parameters and the biological monitoring results to obtain corresponding target risk factors; An assessment module, used to perform risk assessment on the target risk factor and obtain a corresponding risk assessment result; A generating module is used to generate a target risk level corresponding to the target risk factor based on the risk assessment result.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the risk assessment method based on artificial intelligence as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the artificial intelligence-based risk assessment method according to any one of claims 1 to 7.

Images