Industrial product quality safety risk monitoring and analyzing platform

Abstract

The invention relates to the technical field of industrial product risk monitoring, and particularly discloses an industrial product quality safety risk monitoring analysis platform, which is characterized in that human risk data, enterprise specification risk data and potential risk data of an industrial product in a production and processing process are acquired through a production risk monitoring module; the risks of the industrial products in the production and processing process are evaluated according to the data, the risk levels of the industrial products in the production and processing process are divided according to the analysis result, and early warning is performed in time; risk occurrence probability data, influence degree data after risk occurrence and risk identification difficulty data after the industrial products enter the market are obtained through the market risk monitoring module, and the market risks of the industrial products are graded according to the data, so that an objective data basis is provided for decision making in the field of industrial product quality.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial product risk monitoring, and specifically to an industrial product quality and safety risk monitoring and analysis platform. Background Art

[0002] Industrial products are closely related to people's production and life, and the quality and safety of industrial products have also attracted much attention. However, for market supervision and management units, due to the lack of support for data related to industrial product quality and safety, it is difficult to form a systematic supervision plan for related products and industries; for production enterprises, due to the lack of a systematic understanding of their own and similar product safety situations, it is difficult to quickly respond and propose targeted improvement plans; for consumers, due to the lack of reliable product quality data guidance, personal rights and interests are easily damaged when purchasing and using industrial products. Therefore, the present invention provides an industrial product quality and safety risk monitoring and analysis platform.

[0003] Most of the existing industrial product quality and safety risk monitoring and analysis platforms focus on monitoring various process parameters during the processing of industrial products, lacking the monitoring of enterprises, human factors, and potential risks in the industrial production process, and also lacking the monitoring of market information after industrial products enter the market. As a result, they cannot provide risk auxiliary decision-making basis for industrial product supervisors and reduce the occurrence of risk events. Summary of the Invention

[0004] The purpose of the present invention is to provide an industrial product quality and safety risk monitoring and analysis platform to solve the above technical problems:

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] An industrial product quality and safety risk monitoring and analysis platform, characterized in that the platform includes: a production risk monitoring module, a market risk monitoring module, a data processing module, and a system database;

[0007] The production risk monitoring module includes a production data input module and a production data query module;

[0008] The production data input module is used to input production data information during the production process of industrial products into the platform and store it in the system database;

[0009] The production data query module is used to return the historical latest production data in the system database when a query request is received;

[0010] The market risk monitoring module includes a market data input module and a market data query module;

[0011] The market data input module is used to input the latest market information of industrial products into the platform and store it in the system database;

[0012] The market data query module is used to return the latest historical data in the system database when receiving a query request;

[0013] The data processing module is used to process the data information in the system database to facilitate users to obtain the most intuitive information;

[0014] The data analysis module is used to analyze the processed data and conduct production risk analysis and market risk analysis on industrial products.

[0015] As a further description of the solution of the present invention, the process of the production risk analysis is as follows:

[0016] Based on big data, production data in the production process of the i-th type of industrial product is obtained, and the production data includes the human risk coefficient A i , the enterprise standard risk coefficient C i and the potential risk coefficient P i ;

[0017] The production risk assessment index ρ of the i-th type of industrial product is calculated by the following formula i :

[0018]

[0019] The production risk assessment index ρ of the i-th type of industrial product i is sorted according to the size, and a production risk warning is issued for the i-th type of industrial product according to the sorting result;

[0020] If the production risk assessment index ρ of the i-th type of industrial product i ranks in the top 1 / 3, a high production risk warning is issued. If the production risk assessment index ρ of the i-th type of industrial product i ranks in the middle 1 / 3, a medium production risk warning is issued. If the production risk assessment index ρ of the i-th type of industrial product i ranks in the bottom 1 / 3, a low production risk warning is issued.

[0021] As a further description of the solution of the present invention, the acquisition process of the human risk coefficient A i includes:

[0022] Based on big data, the human risk data of the i-th type of industrial product is obtained. If the i-th type of industrial product is illegally produced, then A i = 1; if the i-th type of industrial product is produced beyond the scope, then A i = 0.5; if the i-th type of industrial product is legally produced, then A i = 0.

[0023] As a further description of the solution of the present invention, the enterprise standard risk coefficient C iThe acquisition process includes:

[0024] Based on big data, obtain the enterprise standard risk data of the i-th type of industrial product. If the product inspection pass rate of the i-th type of industrial product is lower than 95%, then C i = 1; if the product inspection pass rate of the i-th type of industrial product is higher than 95% and lower than 100%, then C i = 0.5; if the product inspection pass rate of the i-th type of industrial product is 100%, then C i = 0.

[0025] As a further description of the solution of the present invention, the acquisition process of the potential risk coefficient P i includes:

[0026] Based on big data, obtain the potential risk data of the i-th type of industrial product. If the i-th type of industrial product is a high-risk product, then P i = 1; if the i-th type of industrial product is a medium-risk product, then P i = 0.5; if the i-th type of industrial product is a low-risk product, then P i = 0.

[0027] As a further description of the solution of the present invention, the process of the market risk analysis is:

[0028] Based on big data, obtain the market data of the i-th type of industrial product. The market data includes the risk occurrence probability coefficient X i , the impact degree coefficient Y i after the risk occurs, and the risk identification difficulty coefficient Z i ;

[0029] Substitute the obtained data into the following formula to calculate the market risk assessment index σ i of the i-th type of industrial product:

[0030] σ i = X i 2 + 2 * Y i + Z i ;

[0031] Sort the market risk assessment index σ i of the i-th type of industrial product according to the size, and issue a market risk warning for the i-th type of industrial product according to the sorting result;

[0032] If the market risk assessment index σ i of the i-th type of industrial product ranks in the top 1 / 3, then issue a high market risk warning. If the market risk assessment index σ i of the i-th type of industrial product ranks in the middle 1 / 3, then issue a medium market risk warning. If the market risk assessment index σ i of the i-th type of industrial product ranks in the bottom 1 / 3, then issue a low market risk warning.

[0033] As a further description of the solution of the present invention, the risk occurrence probability coefficient X i is obtained as follows:

[0034] Based on big data, obtain the data of the market risk events of the i-th type of industrial product. If the probability of the occurrence of the market risk event is very high and exceeds the expected probability interval, then X i = 5; if the probability of the occurrence of the market risk event is relatively high and falls within the expected probability interval, then X i = 3; if the probability of the occurrence of the market risk event is relatively low and is lower than the expected probability interval, then X i = 1.

[0035] As a further description of the solution of the present invention, the influence degree coefficient Y i is obtained as follows:

[0036] Based on big data, obtain the data of the market risk events of the i-th type of industrial product. If most of the market risk events have a serious impact on the industrial product and will affect the subsequent production batches, then Y i = 5; if most of the market risk events have a high impact on the industrial product and will affect the current production batch, then Y i = 3; if most of the market risk events have a low impact on the industrial product and will affect some products of the current production batch, then Y i = 1.

[0037] As a further description of the solution of the present invention, the risk identification difficulty coefficient Z i is obtained as follows:

[0038] Based on big data, obtain the data of the market risk events of the i-th type of industrial product. If most of the market risk events are relatively difficult to identify and require complex mathematical calculations and the aid of tools, then Z i = 5; if most of the market risk events are of medium difficulty to identify and require general mathematical calculations, then Z i = 3; if most of the market risk events are relatively easy to identify and do not require other identification methods, then Z i = 1.

[0039] As a further description of the solution of the present invention, the platform further includes market risk characteristic analysis:

[0040] Based on big data, obtain the market risk assessment index σ i of each month of the i-th type of industrial product in the previous year, and fit the curve σ i of the market risk assessment index σ i (t) varying with time;

[0041] Let Find the value of t and substitute the found value of t into the curve σ i (t), we can get max[σ i (t)], the max[σ i (t)] is σ i (t) maximum value, σ i (t) = max[σ i (t)], the corresponding t value is the target month;

[0042] The target month is the best month for spot checking and querying market risk event data.

[0043] Beneficial effects of the present invention:

[0044] 1. The present invention obtains production data in the production process of the i-th industrial product, and the production data includes the human risk coefficient A i 、Enterprise Standard Risk Factor C i and potential risk factor P i , through mathematical models Calculate the production risk assessment index ρ of the i-th industrial product i Then, the production risk assessment index ρ of the i-th industrial product is i Sort by size, and issue a production risk warning for the i-th industrial product based on the sorting result; if the i-th industrial product production risk assessment index ρ i If the ranking is in the top 1 / 3, a high-risk production warning is issued. If the production risk assessment index of the i-th industrial product is i If the ranking is in the middle 1 / 3, a production risk warning is issued. If the production risk assessment index ρ of the i-th category industrial product is i Those ranked in the bottom 1 / 3 will be issued a low-risk production warning;

[0045] 2. The present invention obtains market data after the i-th type of industrial products enter the market, and the market data includes the risk probability coefficient X i , Impact coefficient after the risk occurs / i and risk identification difficulty coefficient Z i ; Through the mathematical model σ i =X i 2 +2*Y i +Z i Calculate the market risk assessment index σ of the i-th category industrial product i Then, the market risk assessment index σ of the i-th industrial product is i Sort by size and issue a market risk warning for the i-th industrial product based on the sorting results; if the market risk assessment index σ i If the market risk assessment index of the i-th industrial product market is σi If the ranking is in the middle 1 / 3, a medium market risk warning is issued. If the market risk assessment index σ of the i-th type of industrial product i If the ranking is in the last 1 / 3, a low market risk warning is issued.

[0046] 3. Based on big data, the market risk assessment index σ of each month of the i-th type of industrial product in the previous year is obtained in the present invention i , and the market risk assessment index σ is fitted i The curve σ of the change with time i (t), the derivative of σ i (t) is calculated, and let The value of t is obtained, and the obtained value of t is substituted into the curve σ i (t) to obtain max[σ i (t)]. The max[σ i (t)] is the maximum value of σ i (t). The value of t corresponding to σ i (t) = max[σ i (t)] is the target month. When conducting the investigation, the target month is the best month for randomly checking and querying the market risk event data, and the obtained data is more accurate, which not only reduces the investigation difficulty, but also provides a more accurate data basis for decision-making in the field of industrial product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The present invention will be further described below with reference to the accompanying drawings.

[0048] Figure 1 FIG. is a schematic structural diagram of the industrial product quality and safety risk monitoring and analysis platform of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0049] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0050] Please refer to Figure 1 As shown in the figure, the present invention provides an industrial product quality and safety risk monitoring and analysis platform, which is characterized in that the platform includes: a production risk monitoring module, a market risk monitoring module, a data processing module, and a system database;

[0051] The production risk monitoring module includes a production data input module and a production data query module;

[0052] The production data input module is used to input the production data information in the industrial product production process into the platform and store it in the system database;

[0053] The production data query module is used to return the latest historical production data in the system database when a query request is received;

[0054] The market risk monitoring module includes a market data input module and a market data query module;

[0055] The market data input module is used to input the latest market information of industrial products into the platform and store it in the system database;

[0056] The market data query module is used to return the latest historical data in the system database when a query request is received;

[0057] The data processing module is used to process the data information in the system database to facilitate users to obtain the most intuitive information;

[0058] The data analysis module is used to analyze the processed data and conduct production risk analysis and market risk analysis on industrial products.

[0059] Through the above technical solutions, the present invention obtains the human risk data, enterprise standard risk data, and potential risk data of industrial products in the production and processing process through the production risk monitoring module, evaluates the risks of industrial products in the production and processing process based on these data, classifies the risk levels in the industrial product production and processing process according to the analysis results, and gives early warnings in a timely manner. The present invention obtains the risk occurrence probability data, the impact degree data after the risk occurs, and the risk identification difficulty data of industrial products after entering the market through the market risk monitoring module, classifies the market risks of industrial products based on these data, and provides an objective data basis for decision-making in the field of industrial product quality.

[0060] The process of the production risk analysis is as follows:

[0061] Based on big data, obtain the production data in the production process of the i-th type of industrial product. The production data includes the human risk coefficient A i 、the enterprise standard risk coefficient C i and the potential risk coefficient P i ;

[0062] Calculate the production risk assessment index ρ of the i-th type of industrial product through the following formula i :

[0063]

[0064] The production risk assessment index ρ of the i-th type of industrial product iSort by size and issue a production risk warning for the i-th category of industrial products according to the sorting result;

[0065] If the production risk assessment index ρ of the i-th category of industrial products i ranks in the top 1 / 3, a high production risk warning is issued. If the production risk assessment index ρ of the i-th category of industrial products i ranks in the middle 1 / 3, a medium production risk warning is issued. If the production risk assessment index ρ of the i-th category of industrial products i ranks in the bottom 1 / 3, a low production risk warning is issued.

[0066] The process of obtaining the human risk coefficient A i includes:

[0067] Based on big data, obtain the human risk data of the i-th category of industrial products. If the i-th category of industrial products is illegally produced, then A i = 1; if the i-th category of industrial products is produced beyond the scope, then A i = 0.5; if the i-th category of industrial products is legally produced, then A i = 0.

[0068] The process of obtaining the enterprise standard risk coefficient C i includes:

[0069] Based on big data, obtain the enterprise standard risk data of the i-th category of industrial products. If the product inspection pass rate of the i-th category of industrial products is lower than 95%, then C i = 1; if the product inspection pass rate of the i-th category of industrial products is higher than 95% and lower than 100%, then C i = 0.5; if the product inspection pass rate of the i-th category of industrial products is 100%, then C i = 0.

[0070] The process of obtaining the potential risk coefficient P i includes:

[0071] Based on big data, obtain the potential risk data of the i-th category of industrial products. If the i-th category of industrial products is a high-risk product, then P i = 1; if the i-th category of industrial products is a medium-risk product, then P i = 0.5; if the i-th category of industrial products is a low-risk product, then P i = 0.

[0072] Through the above technical solution, this embodiment obtains the production data in the production process of the i-th category of industrial products. The production data includes the human risk coefficient A i , the enterprise standard risk coefficient C i and the potential risk coefficient P i , and calculates the production risk assessment index ρ of the i-th category of industrial products through a mathematical model ​i , then, sort the production risk assessment indicators ρ of the i-th type of industrial products i in descending order, and issue a production risk warning for the i-th type of industrial products according to the sorting result; if the production risk assessment indicator ρ of the i-th type of industrial products i ranks in the top 1 / 3, a high production risk warning is issued. If the production risk assessment indicator ρ of the i-th type of industrial products i ranks in the middle 1 / 3, a medium production risk warning is issued. If the production risk assessment indicator ρ of the i-th type of industrial products i ranks in the bottom 1 / 3, a low production risk warning is issued.

[0073] In this embodiment, three-dimensional indicators of industrial products during the production and processing process are constructed through investigation, namely the human risk coefficient A i , the enterprise standard risk coefficient C i , and the potential risk coefficient P i . According to the actual investigation results, the specific values of the human risk coefficient A i , the enterprise standard risk coefficient C i , and the potential risk coefficient P i are obtained, and the specific values are substituted into the mathematical model.

[0074] The process of the market risk analysis is as follows:

[0075] Based on big data, the market data of the i-th type of industrial products is obtained. The market data includes the risk occurrence probability coefficient X i , the impact degree coefficient Y after the risk occurs i , and the risk identification difficulty coefficient Z i ;

[0076] Substitute the obtained data into the following formula to calculate the market risk assessment indicator σ of the i-th type of industrial products i :

[0077] σ i =X i 2 +2*Y i +Z i ;

[0078] Sort the market risk assessment indicator σ of the i-th type of industrial products i in descending order, and issue a market risk warning for the i-th type of industrial products according to the sorting result;

[0079] If the market risk assessment indicator σ of the i-th type of industrial products i ranks in the top 1 / 3, a high market risk warning is issued. If the market risk assessment indicator σ of the i-th type of industrial products i ranks in the middle 1 / 3, a medium market risk warning is issued. If the market risk assessment indicator σ of the i-th type of industrial productsi If the ranking is in the bottom 1 / 3, a low market risk warning is issued.

[0080] The risk occurrence probability coefficient X i The acquisition process includes:

[0081] Based on big data, obtain the market risk event data of the i-th type of industrial product. If the probability of the market risk event occurring is very high and exceeds the expected probability interval, then X i = 5; if the probability of the market risk event occurring is relatively high and within the expected probability interval, then X i = 3; if the probability of the market risk event occurring is low and below the expected probability interval, then X i = 1.

[0082] The impact degree coefficient Y i The acquisition process includes:

[0083] Based on big data, obtain the market risk event data of the i-th type of industrial product. If most of the market risk events have a serious impact on the industrial product and will affect subsequent production batches, then Y i = 5; if most of the market risk events have a high impact on the industrial product and will affect the current production batch, then Y i = 3; if most of the market risk events have a low impact on the industrial product and will affect some products of the current production batch, then Y i = 1.

[0084] The risk identification difficulty coefficient Z i The acquisition process includes:

[0085] Based on big data, obtain the market risk event data of the i-th type of industrial product. If most of the market risk events are relatively difficult to identify and require complex mathematical calculations and the aid of tools such as magic images, then Z i = 5; if most of the market risk events are of medium difficulty to identify and require general mathematical calculations, then Z i = 3; if most of the market risk events are relatively easy to identify and do not require other identification methods, then Z i = 1.

[0086] Through the above technical solution, this embodiment obtains the market data after the i-th type of industrial product enters the market. The market data includes the risk occurrence probability coefficient X i , the impact degree coefficient Y after the risk occurs i and the risk identification difficulty coefficient Z i ; through the mathematical model σ i = X i 2 + 2 * Y i + Z iCalculate the market risk assessment index σ of the i-th type of industrial product i , and then sort the market risk assessment index σ of the i-th type of industrial product i in descending order, and issue a market risk warning for the i-th type of industrial product according to the sorting result; if the market risk assessment index σ of the i-th type of industrial product i ranks in the top 1 / 3, a high market risk warning is issued. If the market risk assessment index σ of the i-th type of industrial product i ranks in the middle 1 / 3, a medium market risk warning is issued. If the market risk assessment index σ of the i-th type of industrial product i ranks in the bottom 1 / 3, a low market risk warning is issued.

[0087] In this embodiment, three-dimensional indexes after the industrial product enters the market are constructed through investigation, namely the risk occurrence probability coefficient X i , the impact degree coefficient Y i after the risk occurs, and the risk identification difficulty coefficient Z i . According to the actual investigation results, the specific values of the risk occurrence probability coefficient X i , the impact degree coefficient Y i after the risk occurs, and the risk identification difficulty coefficient Z i are obtained, and the specific values are substituted into the mathematical model.

[0088] The platform also includes market risk characteristic analysis:

[0089] Based on big data, the market risk assessment index σ of each month of the i-th type of industrial product in the previous year is obtained i , and the curve σ i of the market risk assessment index σ changing with time is fitted i (t);

[0090] Let Find the value of t, substitute the obtained value of t into the curve σ i (t), and obtain max[σ i (t)]. The max[σ i (t)] is the maximum value of σ i (t), and the value of t corresponding to σ i (t) = max[σ i (t)] is the target month;

[0091] The target month is the best sampling query month for market risk event data.

[0092] Through the above technical solution, in this embodiment, based on big data, the market risk assessment index σ of each month of the i-th type of industrial product in the previous year is obtained i , and the curve σ i of the market risk assessment index σ changing with time is fittedi (t), differentiate σ i (t), and let Find the value of t, substitute the obtained value of t into the curve σ i (t), and obtain max[σ i (t)], where the max[σ i (t)] is the maximum value of σ i (t), and the t value corresponding to σ i (t) = max[σ i (t)] is the target month. When conducting the investigation, the target month is the best sampling query month for market risk event data, and the obtained data is more accurate. This not only reduces the difficulty of the investigation, but also provides a more accurate data basis for decision-making in the field of industrial product quality.

[0093] The above has described an embodiment of the present invention in detail, but the described content is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the present invention application shall still fall within the scope covered by the patent of the present invention.

Claims

1. An industrial product quality and safety risk monitoring and analysis platform, characterized in that, The platform includes: a production risk monitoring module, a market risk monitoring module, a data processing module, and a system database; The production risk monitoring module includes a production data input module and a production data query module; The production data input module is used to input the production data information in the industrial product production process into the platform and store it in the system database; The production data query module is used to return the historical latest production data in the system database when a query request is received; The market risk monitoring module includes a market data input module and a market data query module; The market data input module is used to input the latest market information of industrial products into the platform and store it in the system database; The market data query module is used to return the historical latest data in the system database when a query request is received; The data processing module is used to process the data information in the system database to facilitate users to obtain the most intuitive information; The data analysis module is used to analyze the processed data and conduct production risk analysis and market risk analysis on industrial products.

2. The industrial product quality and safety risk monitoring and analysis platform according to claim 1, characterized in that The process of the production risk analysis is as follows: Obtain production data in the production process of the i-th type of industrial product based on big data, where the production data includes the human risk coefficient A i , the enterprise standard risk coefficient C i , and the potential risk coefficient P i ; Calculate the risk assessment index ρ of the i-th type of industrial product production through the following formula i : Sort the risk assessment indicators ρ of industrial product category i i by size, and issue a production risk warning for industrial products of category i according to the sorting result; If the production risk assessment index ρ of the i-th type of industrial product i ranks in the top 1 / 3, a high production risk warning is issued. If the production risk assessment index ρ of the i-th type of industrial product i ranks in the middle 1 / 3, a medium production risk warning is issued. If the production risk assessment index ρ of the i-th type of industrial product i ranks in the bottom 1 / 3, a low production risk warning is issued.

3. An industrial product quality and safety risk monitoring and analysis platform according to claim 2, characterized in that, The human risk coefficient A i The acquisition process includes: Obtain the human risk data of the i-th type of industrial product based on big data. If the i-th type of industrial product is illegally produced, then A i = 1; if the i-th type of industrial product is produced beyond the scope, then A i = 0.5; if the i-th type of industrial product is legally produced, then A i = 0.

4. The industrial product quality and safety risk monitoring and analysis platform according to claim 2, characterized in that The enterprise standard risk coefficient C i The acquisition process includes: Obtain the enterprise standard risk data of the i-th type of industrial products based on big data. If the product inspection pass rate of the i-th type of industrial products is lower than 95%, then C i = 1; if the product inspection pass rate of the i-th type of industrial products is higher than 95% and lower than 100%, then C i = 0.5; if the product inspection pass rate of the i-th type of industrial products is 100%, then C i = 0.

5. The industrial product quality and safety risk monitoring and analysis platform according to claim 2, characterized in that, The potential risk coefficient P i is obtained through the following process: Based on big data, obtain the potential risk data of the i-th type of industrial product. If the i-th type of industrial product is a high-risk product, then P i = 1; if the i-th type of industrial product is a medium-risk product, then P i = 0.5; if the i-th type of industrial product is a low-risk product, then P i = 0.

6. The industrial product quality and safety risk monitoring and analysis platform according to claim 1, wherein The process of the market risk analysis is as follows: Obtain the market data of the i-th type of industrial products based on big data, where the market data includes the risk occurrence probability coefficient X i , the impact degree coefficient Y after the risk occurs i and the risk identification difficulty coefficient Z i ; Substitute the obtained data into the following formula to calculate the market risk assessment index σ of the i-th type of industrial product i : σ i = X i 2 + 2*Y i + Z i ; Evaluate the market risk assessment index σ of industrial products of the i-th category i Sort them by size and issue a market risk warning for industrial products of the i-th category according to the sorting results; If the market risk assessment index σ of industrial products of type i i ranks in the top 1 / 3, a market high-risk warning is issued. If the market risk assessment index σ of industrial products of type i i ranks in the middle 1 / 3, a market medium-risk warning is issued. If the market risk assessment index σ of industrial products of type i i ranks in the bottom 1 / 3, a market low-risk warning is issued.

7. The industrial product quality and safety risk monitoring and analysis platform according to claim 6, wherein, The risk occurrence probability coefficient X i The acquisition process includes: Obtain the data of the market risk events of the i-th type of industrial products based on big data. If the probability of the market risk event occurring is very high and exceeds the expected probability interval, then X i = 5; if the probability of the market risk event occurring is relatively high and conforms to the expected probability interval, then X i = 3; if the probability of the market risk event occurring is low and is lower than the expected probability interval, then X i = 1.

8. An industrial product quality and safety risk monitoring and analysis platform according to claim 6, characterized in that The influence degree coefficient Y i The acquisition process includes: Obtain the data of the market risk events of the i-th type of industrial products based on big data. If most of the market risk events have a serious impact on the industrial products and will affect the subsequent production batches, then Y i = 5; if most of the market risk events have a high impact on the industrial products and will affect the current production batch, then Y i = 3; if most of the market risk events have a low impact on the industrial products and will affect some of the products in the current production batch, then Y i = 1.

9. An industrial product quality and safety risk monitoring and analysis platform according to claim 6, characterized in that, The risk identification difficulty coefficient Z i The acquisition process includes: Obtain the data of market risk events of the i-th type of industrial products based on big data. If most of the market risk events are relatively difficult to identify and require complex mathematical calculations and the aid of a tool golem, then Z i = 5; if most of the market risk events are of medium difficulty to identify and require general mathematical calculations, then Z i = 3; if most of the market risk events are relatively easy to identify and do not require other identification methods, then Z i = 1.

10. The industrial product quality and safety risk monitoring and analysis platform according to claim 9, characterized in that The platform also includes market risk characteristic analysis: Obtain the monthly market risk assessment index σ of the i-th type of industrial product in the previous year based on big data i , and fit the market risk assessment index σ i with the time-varying curve σ i (t); Let Find the value of t, and substitute the obtained value of t into the curve σ i (t) to obtain max[σ i (t)], where max[σ i (t)] is the maximum value of σ i (t), and the value of t corresponding to σ i (t) = max[σ i (t)] is the target month; The target month is the best sampling query month for market risk event data.

Images