Monitoring strategy adjustment method and device based on quantitative risk assessment

Abstract

The invention relates to a monitoring strategy adjustment method and device based on quantitative risk assessment. The method comprises the following steps: performing risk detection on a target scene based on real-time monitoring data; based on the detected risk event, obtaining a quantitative parameter; calculating a comprehensive risk value of the security event based on the quantitative parameter; the quantitative parameters comprise a prior probability of occurrence of a security event, a probability of occurrence of a risk event when the security event occurs and a probability of occurrence of a historical risk event; calculating monitoring strategy parameters based on the comprehensive risk value; the monitoring equipment in the target scene is controlled based on the monitoring strategy parameters, the problems of single monitoring strategy and lack of flexibility are solved, quantitative evaluation can be performed on the detected risk event, the comprehensive risk of the security event is analyzed, dynamic strategy adjustment is performed based on the quantitative evaluation result, and the safety of the security event is improved. And the efficiency of the monitoring system in the aspect of preventing safety problems is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and computer vision technology, and in particular to a monitoring strategy adjustment method and device based on quantitative risk assessment. Background Art

[0002] The monitoring system uses video technology to monitor the defense area and display it in real time. It is widely used in public safety, business management, industrial production, personal life and other aspects. For example, with the improvement of food safety awareness, the monitoring of kitchen environment has become an important part of the catering industry. At present, the mainstream solution in the industry is to monitor the environment and personnel behavior in the kitchen through cameras and other equipment. It can detect smoking, making phone calls, not wearing masks, not wearing work clothes, not wearing work hats, not covering trash cans, rodent infestation and other behaviors and issue early warnings in time. These monitoring methods have improved the transparency and safety of kitchen management to a certain extent.

[0003] However, the current monitoring strategy still has shortcomings in practical applications. For example, the existing early warning mechanism is usually triggered based on preset rules. Once the system detects a violation, no matter how high or low the risk of the violation is, an alarm message will be generated and sent to the management personnel. Frequent alarm messages interfere with the management personnel, making it difficult for them to distinguish which are high-risk events that really need to be handled immediately and which are low-risk events that can be handled later. For another example, the monitoring system is usually based on preset monitoring frequencies and preset equipment, resulting in insufficient monitoring of high-risk situations and failure to make flexible adjustments based on the actual risk size.

[0004] In summary, in existing monitoring solutions, the monitoring strategy is single and lacks flexibility, which limits the effectiveness of the monitoring system in preventing security issues. Summary of the invention

[0005] In this embodiment, a monitoring strategy adjustment method and device based on quantitative risk assessment are provided to solve the problem of single monitoring strategy and lack of flexibility in related technologies.

[0006] In a first aspect, the present application provides a monitoring strategy adjustment method based on quantitative risk assessment, the method comprising:

[0007] Conduct risk detection on target scenarios based on real-time monitoring data;

[0008] Based on the detected risk events, quantitative parameters are obtained; based on the quantitative parameters, a comprehensive risk value of the security event is calculated; the quantitative parameters include a priori probability of the security event occurring, the probability of the risk event occurring when the security event occurs, and the probability of the historical risk event occurring;

[0009] Based on the comprehensive risk value, monitoring strategy parameters are calculated; and based on the monitoring strategy parameters, monitoring equipment within the target scene is controlled.

[0010] In some of the embodiments, calculating the comprehensive risk value of the security event based on the quantitative parameters includes:

[0011] When at least two of the risk events are detected, a multi-conditional Bayesian analysis is performed based on the quantitative parameters of all the risk events detected to obtain a comprehensive risk value of the security event.

[0012] In some of the embodiments, before obtaining the quantization parameter, the method further includes:

[0013] Based on an artificial intelligence algorithm, the quantization parameter is updated within a preset statistical period.

[0014] In some of the embodiments, based on an artificial intelligence algorithm, updating the quantization parameter within a preset statistical period includes:

[0015] At the end of the latest statistical period, the latest statistical data is obtained; the latest statistical data includes: security event data occurring during the statistical period and risk event data collected by the monitoring device during the statistical period;

[0016] Based on the latest statistical data, update the parameters of the target prior probability calculation model;

[0017] The latest statistical data is input into the updated target prior probability calculation model to obtain the latest prior probability of the security event occurring, and the prior probability of the security event occurring stored at the end of the previous statistical period is replaced based on the latest prior probability of the security event occurring.

[0018] In some of the embodiments, the method for generating the target prior probability calculation model includes:

[0019] Obtaining an initial prior probability calculation model;

[0020] Acquire historical event data; the historical event data includes historical safety event data and historical risk event data;

[0021] Based on the historical event data, the initial prior probability calculation model is trained to obtain a target prior probability calculation model.

[0022] In some embodiments, based on the comprehensive risk value, the monitoring strategy parameters are calculated, including:

[0023] Calculate the current monitoring frequency in the monitoring strategy parameters based on the comprehensive risk value and the basic monitoring frequency;

[0024] Based on the comprehensive risk value and the warning threshold, the current number of warnings in the monitoring strategy parameters is calculated.

[0025] In some embodiments, based on the comprehensive risk value, the monitoring strategy parameters are calculated, including:

[0026] When it is determined that the comprehensive risk value exceeds a preset high risk threshold, an activation signal is generated; the activation signal is used to control the start of monitoring extension resources.

[0027] In a second aspect, a monitoring strategy adjustment device based on quantitative risk assessment is provided in this embodiment, and the device includes:

[0028] Risk detection module, used to perform risk detection on target scenarios based on real-time monitoring data;

[0029] A comprehensive quantitative assessment module is used to obtain quantitative parameters based on the detected risk events; the quantitative parameters include the prior probability of the occurrence of the security event, the probability of the risk event occurring when the security event occurs, and the probability of the occurrence of historical risk events; based on the quantitative parameters, the comprehensive risk value of the security event is calculated;

[0030] A monitoring strategy adjustment module is used to calculate monitoring strategy parameters based on the comprehensive risk value; and control the monitoring equipment in the target scene based on the monitoring strategy parameters.

[0031] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the monitoring strategy adjustment method based on quantitative risk assessment described in the first aspect is implemented.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the monitoring strategy adjustment method based on quantitative risk assessment described in the first aspect is implemented.

[0033] Compared with the related art, the monitoring strategy adjustment method and device based on quantitative risk assessment provided in this embodiment perform risk detection on the target scene based on real-time monitoring data; obtain quantitative parameters based on the detected risk events; calculate the comprehensive risk value of the security event based on the quantitative parameters; the quantitative parameters include the prior probability of the occurrence of the security event, the probability of the risk event occurring when the security event occurs, and the probability of the occurrence of historical risk events; calculate the monitoring strategy parameters based on the comprehensive risk value; control the monitoring equipment in the target scene based on the monitoring strategy parameters, solve the problem of single monitoring strategy and lack of flexibility, can perform quantitative assessment on the detected risk events, analyze the comprehensive risk of the security event, and perform dynamic strategy adjustment based on the quantitative assessment results, thereby improving the effectiveness of the monitoring system in preventing security problems.

[0034] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0036] Figure 1 The hardware structure block diagram of a terminal of a monitoring strategy adjustment method based on quantitative risk assessment in one embodiment;

[0037] Figure 2 A schematic diagram of a flow chart of a monitoring strategy adjustment method based on quantitative risk assessment in one embodiment;

[0038] Figure 3 A schematic diagram of a flow chart of a monitoring strategy adjustment method based on quantitative risk assessment in a preferred embodiment;

[0039] Figure 4 A schematic diagram of a quantitative analysis process in a preferred embodiment;

[0040] Figure 5 A schematic diagram of adaptively adjusting the monitoring strategy in a preferred embodiment;

[0041] Figure 6 It is a structural block diagram of a monitoring strategy adjustment device based on quantitative risk assessment in one embodiment.

[0042] Figure numerals: 102, processor; 104, memory; 106, transmission device; 108, input and output device; 61, risk detection module; 62, comprehensive quantitative evaluation module; 63, monitoring strategy adjustment module. DETAILED DESCRIPTION

[0043] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0044] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0045] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 : is a hardware structure block diagram of a terminal of the monitoring strategy adjustment method based on quantitative risk assessment of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0046] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the monitoring strategy adjustment method based on quantitative risk assessment in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0047] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0048] In this embodiment, a monitoring strategy adjustment method based on quantitative risk assessment is provided. Figure 2 This is a flow chart of the monitoring strategy adjustment method based on quantitative risk assessment of this embodiment. This embodiment can be applied to any monitoring scenario, such as food processing, catering kitchens, community security, supermarket retail, etc., to achieve risk prediction and early warning of security incidents that may occur in the corresponding scenario and adjustment of monitoring strategies. Figure 2 As shown, the process includes the following steps:

[0049] Step S210: Perform risk detection on the target scene based on real-time monitoring data.

[0050] Specifically, monitoring equipment, such as cameras, temperature and humidity sensors, air quality sensors, etc., are set in each monitoring area of ​​the target scene. The monitoring equipment collects monitoring data such as environmental data and personnel behavior data in the target scene in real time. Based on intelligent analysis, risk detection is performed on whether there are risk events in the monitoring data. Risk events are pre-set based on specific target scenes. For example, in the catering kitchen scene, risk events include: temperature exceeds the standard, the temperature in the kitchen exceeds the set safety range; air pollution exceeds the standard, the air quality index exceeds the safety standard; smoking behavior, employees are detected to be smoking in the kitchen; calling behavior, employees are detected to be calling in the kitchen; not wearing a mask, employees are detected not wearing a mask; not wearing work clothes, employees are detected not wearing work clothes; not wearing a work hat, employees are detected not wearing a work hat and other specific events. The above risk events are used to evaluate whether the kitchen environment is in an ideal state and whether the staff complies with hygiene regulations. In one embodiment, the result of risk monitoring is the result of regional detection. When adjusting the monitoring strategy, regional adjustment is performed based on the monitoring area.

[0051] Furthermore, the acquired real-time monitoring data is preprocessed, including data clarification and standardization, etc., and intelligent analysis is performed based on the preprocessed real-time monitoring data to obtain risk detection results, which are used to indicate currently existing risk events.

[0052] Step S220, based on the detected risk events, obtain quantitative parameters; based on the quantitative parameters, calculate the comprehensive risk value of the security event; the quantitative parameters include the prior probability of the security event occurring, the probability of the risk event occurring when the security event occurs, and the probability of the historical risk event occurring.

[0053] Specifically, if only one risk event A is detected, the probability P(B|A) of security event B occurring when risk event A occurs can be calculated, that is, the comprehensive risk value of the security event. If multiple risk events An (n=1,2,3,...) are detected, since An are independent events and do not affect each other, based on multi-conditional Bayesian analysis, the probability P(B|A1,A2,...An) of security event B occurring when all risk events An occur can be calculated, that is, the comprehensive risk value of the security event.

[0054] Step S230, calculating monitoring strategy parameters based on the comprehensive risk value; and controlling monitoring equipment in the target scene based on the monitoring strategy parameters.

[0055] Specifically, based on the quantitative risk assessment results, that is, the comprehensive risk value, the monitoring strategy is adaptively adjusted, including but not limited to adaptive adjustment of the monitoring frequency, dynamic adjustment of the number of warnings, and dynamic scheduling and activation of monitoring resources in key areas with high risks, so as to further enhance the monitoring efforts.

[0056] In this embodiment, a monitoring strategy adjustment method based on quantitative risk assessment performs risk detection on a target scenario based on real-time monitoring data; obtains quantitative parameters based on detected risk events; calculates a comprehensive risk value of a security event based on the quantitative parameters; the quantitative parameters include a priori probability of a security event occurring, the probability of a risk event occurring when a security event occurs, and the probability of a historical risk event occurring; calculates monitoring strategy parameters based on the comprehensive risk value; and controls monitoring equipment within the target scenario based on the monitoring strategy parameters, which solves the problem of a single monitoring strategy and lack of flexibility, can perform quantitative assessments on detected risk events, analyze the comprehensive risks of security events, and perform dynamic strategy adjustments based on the quantitative assessment results, thereby improving the effectiveness of the monitoring system in preventing security issues.

[0057] In some of the embodiments, a comprehensive risk value of a security event is calculated based on quantitative parameters, including: when at least two risk events are detected, a multi-conditional Bayesian analysis is performed based on the quantitative parameters of all detected risk events to obtain a comprehensive risk value of the security event.

[0058] Specifically, obtain the prior probability P(B) of the occurrence of a security incident. For each detected risk event, calculate the probability P(An|B) of the corresponding risk event when the security incident occurred in history. For each detected risk event, obtain the probability P(An) (n=1,2,3,4...) of the occurrence of historical risk events. A1, A2...An are independent events that do not affect each other. Based on these data, conduct summary analysis to evaluate the comprehensive risk of security incidents, and quantify the overall risk of security incidents through the occurrence of risk events. The formula for calculating the comprehensive risk value is as follows:

[0059] P(B|A1,A2,A3...An)=(P(A1|B)×P(A2|B)×P(A3|B)...×P(An|B)×P(B)) / (P(A1)×P(A2)×P(A3)...×P(An)).

[0060] In this embodiment, multiple risk events can be jointly analyzed to obtain the connection between the occurrence of risk events and security implementation, and obtain more accurate quantitative results of security event risks.

[0061] In some of the embodiments, before obtaining the quantization parameter, the method further includes: updating the quantization parameter within a preset statistical period based on an artificial intelligence algorithm.

[0062] Specifically, the quantitative parameters set based on expert experience or assumptions are susceptible to subjectivity, thereby reducing the objectivity and accuracy of the evaluation results. In this example, the artificial intelligence algorithm continuously and dynamically adjusts the quantitative parameters to make them consistent with the current application scenario.

[0063] In some of the embodiments, based on the artificial intelligence algorithm, the quantization parameter is updated within a preset statistical period, including:

[0064] Step S240, at the end of the latest statistical period, obtain the latest statistical data; the latest statistical data includes: security event data occurring within the statistical period and risk event data collected by the monitoring device within the statistical period.

[0065] Specifically, the statistical cycle can be set in units of weeks or months, so as to obtain real-time updated security event data and risk event data. Among them, the security event data includes information such as the type and number of security events, and the risk event data includes information such as the type and number of collected risk events. In one non-limiting embodiment, the latest statistical data can use risk event data; in other non-limiting embodiments, the latest statistical data can use both security event data and risk event data.

[0066] Step S250, based on the latest statistical data, update the parameters of the target prior probability calculation model.

[0067] Step S260, input the latest statistical data into the updated target prior probability calculation model to obtain the latest prior probability of security event occurrence, and replace the prior probability of security event occurrence stored at the end of the previous statistical period based on the latest prior probability of security event occurrence.

[0068] Specifically, the target prior probability calculation model is a pre-trained large model that can predict the probability of a security incident. In order to improve the objectivity and accuracy of the prior probability, the parameters of the large model are optimized, and the prior probability of a security incident is dynamically updated based on the updated large model.

[0069] In some of the embodiments, a method for generating a target prior probability calculation model includes:

[0070] Step S310, obtaining an initial prior probability calculation model.

[0071] Specifically, a machine learning model such as a recurrent neural network, a long short-term memory network, a regression model or a hidden Markov model can be pre-built as an initial prior probability calculation model.

[0072] Step S320, obtaining historical event data; the historical event data includes historical security event data and historical risk event data.

[0073] Specifically, historical event data can be obtained from the new network web page or event database.

[0074] Step S330, based on the historical event data, train the initial prior probability calculation model to obtain the target prior probability calculation model.

[0075] In this embodiment, the prior probability calculation model is trained by using historical event data, thereby improving the accuracy of the prior probability calculation.

[0076] In some embodiments, the monitoring strategy parameters are calculated based on the comprehensive risk value, including:

[0077] Step S230, calculating the current monitoring frequency in the monitoring strategy parameters based on the comprehensive risk value and the basic monitoring frequency.

[0078] Specifically, the current monitoring frequency fn is calculated as follows:

[0079] fn=(1+P)×f, where P is the comprehensive risk value and f is the basic monitoring frequency. Increase the monitoring frequency in high-risk situations and reduce the monitoring frequency in low-risk situations to optimize resource allocation.

[0080] Step S230, based on the comprehensive risk value and the warning threshold, calculate the current warning number in the monitoring strategy parameters.

[0081] Specifically, the calculation formula for the current warning number M is as follows:

[0082] M = P / m, where m is the warning threshold and P is the comprehensive risk value. For example, if m is set to 0.2, if P = 0.8, then 4 warnings will be issued; if P = 0.4, then 2 warnings will be issued; if P = 0.15, then 1 warning will be issued after accumulating 2 warnings, thus achieving the effect of more warnings for high risks and fewer warnings for low risks.

[0083] Step S230, when it is determined that the comprehensive risk value exceeds the preset high risk threshold, an activation signal is generated; the activation signal is used to control the start of the monitoring extension resource.

[0084] Specifically, the system dynamically dispatches and activates key area monitoring resources for high-risk areas to further enhance monitoring efforts. For example, when an area in the target scenario is assessed to be high risk, the system will increase the monitoring frequency of the area and activate additional monitoring equipment, such as high-definition cameras and thermal imagers, to further enhance monitoring efforts.

[0085] Among them, the above three functions, namely adjusting the current number of warnings, adjusting the current monitoring frequency and expanding resources, can be configured in the monitoring system so that all functions can be enabled, or some functions can be selectively enabled.

[0086] The present embodiment is described and illustrated below through a preferred embodiment. The present preferred embodiment is applied to the bright kitchen and bright stove monitoring scenario, and its main method flow is as follows: Figure 3 As shown, see Figure 3 , the steps of this preferred embodiment include:

[0087] S1, Environmental data and behavioral data collection: Collect environmental data inside and outside the kitchen and behavioral data of staff. Environmental data includes internal environmental data temperature, external environmental data air quality (PM2.5), etc.; behavioral data includes smoking, making phone calls, not wearing masks, not wearing work clothes, not wearing work hats, not covering trash cans, etc. The specific collection methods include: using temperature and humidity sensors, air quality sensors, cameras and other equipment to collect environmental data inside and outside the kitchen and behavioral data of staff in real time.

[0088] S2, data statistical analysis: pre-process the collected environmental data and behavioral data, including data cleaning and standardization. Analyze the pre-processed data to identify factors that may affect food safety, such as excessive temperature, air pollution, and employees not complying with hygiene regulations. And count and record food safety incidents that have occurred and the probability of risk events occurring in the kitchen.

[0089] S3, event monitoring alarm: alarm information is generated based on the identified influencing factors, and risk assessment is performed on the alarm information to obtain risk events. For example, temperature exceeds the standard, the temperature in the kitchen exceeds the set safety range; air pollution exceeds the standard, the air quality index exceeds the safety standard; smoking behavior, it is detected that an employee is smoking in the kitchen; phone call behavior, it is detected that an employee is making a phone call in the kitchen; not wearing a mask, it is detected that an employee is not wearing a mask; not wearing work clothes, it is detected that an employee is not wearing work clothes; not wearing a work hat, it is detected that an employee is not wearing a work hat.

[0090] S4, Combined with dynamic prior distribution selection for multi-conditional Bayesian comprehensive quantitative risk assessment: see Figure 4Through machine learning algorithms, combined with historical data and real-time data, the prior distribution probability P(B) of food safety occurrence is dynamically obtained and updated to solve the problem that the prior distribution is not objective enough. For each risk event, the probability of the corresponding risk event occurring when a food safety incident occurred in history is statistically analyzed P(An|B); for each risk event (temperature exceeding the standard, air quality exceeding the standard, smoking...), the probability of the historical risk event occurring is statistically obtained P(An)(n=1,2,3,4...), A1, A2...An are independent events and do not affect each other. Based on these statistical data, a summary analysis is conducted to assess the comprehensive risk of food safety as P(B|A1,A2,A3...An)=(P(A1|B)×P(A2|B)×P(A3|B)...×P(An|B)×P(B)) / (P(A1)×P(A2)×P(A3)...×P(An)), and the overall probability of food safety problems occurring when multiple risk events occur within a period of time is calculated P(B|A1,A2,A3...An), so as to quantify the overall risk of food safety through the occurrence of risk events.

[0091] S5, adaptively adjust the monitoring strategy based on comprehensive quantitative risk assessment: 1) adaptively adjust the monitoring frequency (1+P(B|A1,A2,A3...An))×f, where f is the basic monitoring frequency, to achieve the effect of increasing the monitoring frequency for high risk and submitting a lower monitoring frequency for low risk; 2) dynamically adjust the number of warnings P(B|A1,A2,A3...An)) / m, where m is the threshold. For example, if it is set to 0.2, when P=0.8, there will be 4 warnings, when P=0.4, there will be 2 warnings, and when P=0.15, there will be one warning after two cumulative warnings, to achieve the effect of more warnings for high risk and fewer warnings for low risk; 3) dynamically dispatch and activate monitoring resources in key areas for high risk to further enhance monitoring efforts. For details, please refer to Figure 5 .

[0092] The implementation process of this preferred embodiment is as follows:

[0093] 1. System design.

[0094] 1.1. Clarify the functions of each module: including but not limited to data collection (environmental data, behavioral data), data processing (cleaning, standardization), data analysis, risk assessment (risk probability calculation based on historical data), and early warning processing (early warning mechanism based on risk level).

[0095] 1.2. Design software architecture: Adopt microservice architecture, where each module acts as an independent service and communicates through API to facilitate modular management and expansion.

[0096] 1.3. Database design: Design the database structure to ensure efficient access to data, especially statistical analysis of historical data and risk assessment of real-time data.

[0097] 2. Function implementation.

[0098] 2.1. Data preprocessing: Write scripts or tools to clean the data, remove invalid or abnormal data, and ensure the quality of subsequent analysis.

[0099] 2.2. Data analysis: Develop algorithms to extract key features, such as whether the temperature exceeds the standard, whether the air quality meets the standard, etc.

[0100] 2.3. Risk assessment: Based on the assessment formula model, the probability of occurrence of each alarm event is assessed in real time, and the overall risk level is calculated.

[0101] 2.4. Early warning processing: Develop an early warning processing module to trigger different early warning mechanisms according to the risk level, such as sending emails, text messages or APP push.

[0102] 3. Test verification:

[0103] 3.1. Unit testing: Test the functions of each module separately to ensure that each part can run correctly.

[0104] 3.2. Integration test: simulate the actual usage environment to test whether the entire system can work together, including data transmission, risk assessment, early warning triggering, etc.

[0105] 3.2. Performance testing: Test the system's performance under high concurrent access and large-scale data processing to ensure that the system is stable and reliable.

[0106] 3.4. Security testing: Test the security of the system to prevent data leakage, illegal access and other problems.

[0107] 3.5. User experience testing: Invite users to try the system, collect feedback, and optimize the user experience.

[0108] 4. Service launch:

[0109] 4.1. Deployment preparation: Ensure that all software and hardware are ready and conduct a final comprehensive test.

[0110] 4.2. Online deployment: Deploy the system to the production environment within the predetermined time window.

[0111] 4.3. Monitoring and maintenance: Set up a monitoring system, continuously monitor the system operation status, back up data regularly, and perform necessary system maintenance.

[0112] The above process covers the complete cycle from design to launch, ensuring that the system not only meets the initial requirements but also has good scalability and maintainability.

[0113] This preferred embodiment is based on the comprehensive quantitative food safety risk assessment through Bayesian analysis under the condition that multiple independent events occur at the same time. Through the dynamic prior distribution selection technology, the prior distribution is dynamically adjusted to reduce the subjectivity caused by human settings and improve the objectivity and accuracy of risk assessment; and according to the comprehensive quantitative risk assessment results, the monitoring strategy is adaptively adjusted to achieve adaptive adjustment of monitoring frequency, dynamic adjustment of the number of warnings, and dynamic scheduling to activate monitoring resources in key areas, so as to achieve the effect of high-risk, high-monitoring frequency, and multiple warnings. Prioritize the allocation of monitoring resources, further improve the monitoring intensity of high-risk event areas.

[0114] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0115] In this embodiment, a monitoring strategy adjustment device based on quantitative risk assessment is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware of predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0116] Figure 6 is a structural block diagram of the monitoring strategy adjustment device based on quantitative risk assessment of this embodiment, such as Figure 6 As shown, the device includes: a risk detection module 61, a comprehensive quantitative evaluation module 62, and a monitoring strategy adjustment module 63.

[0117] The risk detection module 61 is used to perform risk detection on the target scene based on real-time monitoring data.

[0118] The comprehensive quantitative assessment module 62 is used to obtain quantitative parameters based on the detected risk events; the quantitative parameters include the prior probability of the occurrence of a security event, the probability of the risk event occurring when the security event occurs, and the probability of the occurrence of historical risk events; based on the quantitative parameters, the comprehensive risk value of the security event is calculated.

[0119] The monitoring strategy adjustment module 63 is used to calculate monitoring strategy parameters based on the comprehensive risk value; and control the monitoring equipment in the target scene based on the monitoring strategy parameters.

[0120] In some of the embodiments, the comprehensive quantitative assessment module 62 is also used to perform multi-conditional Bayesian analysis based on the quantitative parameters of all risk events to obtain a comprehensive risk value of the security event when at least two risk events are detected.

[0121] In some of the embodiments, a quantization parameter updating module is further included, which is used to update the quantization parameter within a preset statistical period based on an artificial intelligence algorithm.

[0122] In some of the embodiments, the quantitative parameter update module is also used to obtain the latest statistical data at the end of the latest statistical period; the latest statistical data includes: security event data occurring within the statistical period and risk event data collected by the monitoring equipment within the statistical period; based on the latest statistical data, the parameters of the target prior probability calculation model are updated; the latest statistical data are input into the updated target prior probability calculation model to obtain the latest prior probability of the occurrence of security events, and the prior probability of the occurrence of security events stored at the end of the previous statistical period is replaced based on the latest prior probability of the occurrence of security events.

[0123] In some of the embodiments, the quantization parameter update module is also used to obtain historical event data; the historical event data includes historical security event data and historical risk event data; based on the historical event data, an initial prior probability calculation model is trained to obtain a target prior probability calculation model.

[0124] In some of the embodiments, the monitoring strategy adjustment module 63 is also used to calculate the current monitoring frequency in the monitoring strategy parameters based on the comprehensive risk value and the basic monitoring frequency; and calculate the current number of warnings in the monitoring strategy parameters based on the comprehensive risk value and the warning threshold.

[0125] In some of the embodiments, the monitoring strategy adjustment module 63 is further used to generate an activation signal when it is determined that the comprehensive risk value exceeds a preset high risk threshold; the activation signal is used to control the activation of the monitoring extension resource.

[0126] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0127] In this embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0128] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0129] In addition, in combination with the monitoring strategy adjustment method based on quantitative risk assessment provided in the above embodiments, a storage medium can also be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by a processor, any one of the monitoring strategy adjustment methods based on quantitative risk assessment in the above embodiments is implemented.

[0130] It should be understood that the specific embodiments described here are only used to explain this application, rather than to limit it. According to the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0131] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0132] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0133] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A monitoring strategy adjustment method based on quantitative risk assessment, characterized in that: The method comprises: Conduct risk detection on target scenarios based on real-time monitoring data; Based on the detected risk events, quantitative parameters are obtained; based on the quantitative parameters, a comprehensive risk value of the security event is calculated; the quantitative parameters include a priori probability of the security event occurring, the probability of the risk event occurring when the security event occurs, and the probability of the historical risk event occurring; Based on the comprehensive risk value, monitoring strategy parameters are calculated; and based on the monitoring strategy parameters, monitoring equipment within the target scene is controlled.

2. The monitoring strategy adjustment method based on quantitative risk assessment according to claim 1 is characterized in that: Based on the quantitative parameters, the comprehensive risk value of the security incident is calculated, including: When at least two of the risk events are detected, a multi-conditional Bayesian analysis is performed based on the quantitative parameters of all the risk events detected to obtain a comprehensive risk value of the security event.

3. The monitoring strategy adjustment method based on quantitative risk assessment according to claim 1 is characterized in that: Before obtaining the quantization parameter, the method further includes: Based on an artificial intelligence algorithm, the quantization parameter is updated within a preset statistical period.

4. The monitoring strategy adjustment method based on quantitative risk assessment according to claim 3 is characterized in that: Based on the artificial intelligence algorithm, the quantitative parameters are updated within a preset statistical period, including: At the end of the latest statistical period, the latest statistical data is obtained; the latest statistical data includes: security event data occurring during the statistical period and risk event data collected by the monitoring device during the statistical period; Based on the latest statistical data, update the parameters of the target prior probability calculation model; The latest statistical data is input into the updated target prior probability calculation model to obtain the latest prior probability of the security event occurring, and the prior probability of the security event occurring stored at the end of the previous statistical period is replaced based on the latest prior probability of the security event occurring.

5. The monitoring strategy adjustment method based on quantitative risk assessment according to claim 4 is characterized in that: The method for generating the target prior probability calculation model comprises: Obtaining an initial prior probability calculation model; Acquire historical event data; the historical event data includes historical safety event data and historical risk event data; Based on the historical event data, the initial prior probability calculation model is trained to obtain a target prior probability calculation model.

6. The monitoring strategy adjustment method based on quantitative risk assessment according to claim 1 is characterized in that: Based on the comprehensive risk value, the monitoring strategy parameters are calculated, including: Calculate the current monitoring frequency in the monitoring strategy parameters based on the comprehensive risk value and the basic monitoring frequency; Based on the comprehensive risk value and the warning threshold, the current number of warnings in the monitoring strategy parameters is calculated.

7. The monitoring strategy adjustment method based on quantitative risk assessment according to claim 1 is characterized in that: Based on the comprehensive risk value, the monitoring strategy parameters are calculated, including: When it is determined that the comprehensive risk value exceeds a preset high risk threshold, an activation signal is generated; the activation signal is used to control the start of monitoring extension resources.

8. A monitoring strategy adjustment device based on quantitative risk assessment, characterized in that: The device comprises: Risk detection module, used to perform risk detection on target scenarios based on real-time monitoring data; A comprehensive quantitative assessment module is used to obtain quantitative parameters based on the detected risk events; the quantitative parameters include the prior probability of the occurrence of the security event, the probability of the risk event occurring when the security event occurs, and the probability of the occurrence of historical risk events; based on the quantitative parameters, the comprehensive risk value of the security event is calculated; A monitoring strategy adjustment module is used to calculate monitoring strategy parameters based on the comprehensive risk value; and control the monitoring equipment in the target scene based on the monitoring strategy parameters.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images