Intelligent supervision system and method for food safety information tracing

Abstract

The invention relates to the technical field of supervision data processing, and particularly discloses an intelligent supervision system and method for food safety information traceability, and the system carries out the intelligent matching of an optimal mapping rate through the real-time monitoring of a target platform instruction processing parameter and the initialization of a mapping process, and combines a data collection and dynamic parameter analysis technology. Meanwhile, key indexes of the mapping process can be accurately evaluated, an adjustment mechanism is automatically triggered to ensure efficient operation, timeliness and accuracy of food safety tracing are remarkably improved, hysteresis and error risks of traditional manual supervision are effectively reduced, meanwhile, dynamic optimization of a mapping strategy can balance data processing efficiency and resource consumption, and the method is suitable for large-scale popularization and application. The integrity of a tracing chain is guaranteed, the operation cost is reduced, and technical support is provided for constructing an intelligent food safety information tracing system.

Description

Technical Field

[0001] The present invention relates to the technical field of regulatory data processing, and specifically to an intelligent supervision system and method for food safety information traceability. Background Art

[0002] With the rapid development of information technology, especially the wide application of technologies such as the Internet of Things, big data, and cloud computing, it provides strong technical support for food safety information traceability. By applying these technologies, it is possible to achieve real-time monitoring and data collection of the entire food supply chain, improving the accuracy and efficiency of food safety traceability.

[0003] For example, the invention patent with the publication number CN107767143B discloses a food safety electronic traceability method directly using domain names and URLs, including: 1) encoding products using the URL of the enterprise domain name of the production enterprise to obtain product codes, and attaching labels carrying the product codes to the products or their packages; 2) using the URL corresponding to the product code as the information service entry for the product, and adding event information occurring in all links of the entire life cycle of the food to the information resources corresponding to this URL; 3) the client obtains food safety traceability information by scanning the label carrying the product code on the product or its package.

[0004] For example, the invention patent with the publication number CN116934359B discloses an Internet-based full-process supervision system for food safety. By monitoring the temperature, humidity, shelf life, and batch information of the target food through the monitoring unit, it can perform intelligent processing and analysis on the collected data, and by collecting the QR code or RFID identifier of the food, the system can accurately track the path of the food in the supply chain, realizing the full-process traceability and supervision instructions of the food.

[0005] However, in the process of implementing the embodiments of the present application, it is found that the above technologies have at least the following technical problems: Food safety information traceability needs to cover the entire chain of information from raw material procurement, production and processing, warehousing and transportation to sales and circulation. The existing technologies mostly adopt static data warehouse solutions and lack a dynamic mapping engine for the characteristics of the food supply chain, resulting in a non-linear decline in response efficiency as the data volume increases. Summary of the Invention

[0006] Aiming at the deficiencies of the prior art, the present invention provides an intelligent supervision system and method for food safety information traceability, which can effectively solve the problems involved in the above background art.

[0007] To achieve the above objectives, the present invention is realized through the following technical solutions: In the first aspect of the present invention, an intelligent supervision system for food safety information traceability is provided, including: a parameter initialization module, which is used to mark the food safety information traceability platform as the target platform, monitor and analyze the instruction processing process parameters of the target platform, and initialize the mapping process of the target platform; a speed matching module, which is used to collect and analyze the data reception process parameters of the target platform, and intelligently match the data mapping speed of the target platform; a parameter adjustment module, which is used to supervise and evaluate the mapping parameters of the target platform, so as to determine whether to adjust the mapping process of the target platform.

[0008] As a further solution, initializing the mapping process of the target platform specifically means: analyzing the instruction processing process parameters of the target platform to obtain the processing efficiency index of the target platform in the first cycle; obtaining the processing efficiency index of the target platform in the historical first cycle, performing a difference processing on the processing efficiency index of the target platform in the first cycle and the processing efficiency index of the target platform in the historical first cycle to obtain the processing efficiency deviation value of the target platform in the first cycle, and initializing the concurrent mapping data volume of the target platform based on the processing efficiency deviation value of the target platform in the first cycle.

[0009] As a further solution, the specific matching process for matching the data mapping speed of the target platform is: by analyzing the data reception process parameters of the target platform, obtaining the data complexity factor of the target platform in the first cycle; based on the data mapping speeds corresponding to each data complexity factor interval stored in the information database, analyzing the interval to which the data complexity factor of the target platform in the first cycle belongs, and recording the data mapping speed corresponding to this data complexity factor interval as the data mapping speed of the target platform; obtaining the data mapping speed of the target platform in the historical first cycle, performing difference and absolute value processing on it in sequence with the data mapping speed of the target platform, and performing a ratio processing on the processing result with the data mapping speed of the target platform in the historical first cycle to finally obtain the data mapping speed deviation value of the target platform, and comparing it with the defined data mapping speed deviation value. If the data mapping speed deviation value of the target platform is greater than the defined data mapping speed deviation value, then adjust the data mapping speed of the target platform until the data mapping speed deviation value of the target platform is equal to or less than the defined data mapping speed deviation value; at the same time, compare the data complexity factor of the target platform in the first cycle with the data complexity threshold. If the data complexity factor of the target platform in the first cycle is less than or equal to the data complexity threshold, then select the first mapping method for data mapping. If the data complexity factor of the target platform in the first cycle is greater than the data complexity threshold, then select the second mapping method for data mapping.

[0010] As a further solution, the mapping process of the target platform is adjusted. The specific adjustment process is as follows: If the mapping stability coefficient of the target platform within the mapping supervision period is greater than the maximum value of the mapping stability coefficient reference interval, then the difference between the mapping stability coefficient of the target platform within the mapping supervision period and the maximum value of the mapping stability coefficient reference interval is processed. The processing result is processed by taking the ratio with the maximum value of the mapping stability coefficient reference interval. Finally, the first mapping stability coefficient deviation value of the target platform within the mapping supervision period is obtained, and the second increase coefficient is matched from the information database. The concurrent mapping data volume of the target platform is increased and adjusted, and at the same time, the duration corresponding to the mapping supervision period is increased and adjusted according to the second increase coefficient; If the mapping stability coefficient of the target platform within the mapping supervision period is less than the minimum value of the mapping stability coefficient reference interval, then the mapping data of the target platform within the mapping supervision period is withdrawn. At the same time, the difference between the minimum value of the mapping stability coefficient reference interval and the mapping stability coefficient of the target platform within the mapping supervision period is processed. The processing result is processed by taking the ratio with the minimum value of the mapping stability coefficient reference interval. Finally, the second mapping stability coefficient deviation value of the target platform within the mapping supervision period is obtained, and the second decrease coefficient is matched from the information database. The concurrent mapping data volume of the target platform is decreased and adjusted, and the duration corresponding to the mapping supervision period is decreased and adjusted according to the second decrease coefficient. At the same time, according to the second mapping stability coefficient deviation value of the target platform within the mapping supervision period, the data cleaning volume of the target platform is obtained for cleaning, so as to remap the mapping data of the target platform within the mapping supervision period.

[0011] The second aspect of the present invention provides an intelligent supervision method for food safety information traceability, including: Step 1: Mark the food safety information traceability platform as the target platform, monitor and analyze the instruction processing process parameters of the target platform, and initialize the mapping process of the target platform; Step 2: Collect and analyze the data reception process parameters of the target platform, and intelligently match the data mapping speed of the target platform; Step 3: Supervise and evaluate the mapping parameters of the target platform, so as to determine whether to adjust the mapping process of the target platform.

[0012] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0013] (1) The present invention provides an intelligent supervision system and method for food safety information traceability. By real-time monitoring the target platform's instruction processing parameters and initializing the mapping process, combining data acquisition and dynamic parameter analysis technologies, it can intelligently match the optimal mapping rate, accurately evaluate the key indicators of the mapping process, automatically trigger the adjustment mechanism to ensure efficient operation, significantly improve the timeliness and accuracy of food safety traceability, effectively reduce the lag and error risks of traditional manual supervision. At the same time, the dynamically optimized mapping strategy can balance data processing efficiency and resource consumption, ensuring the integrity of the traceability chain while reducing operating costs, providing technical support for building an intelligent food safety information traceability system.

[0014] (2) The present invention realizes intelligent resource allocation through a dynamic efficiency calibration mechanism. Its core lies in extracting the processing efficiency benchmark value of the target platform's historical cycle, performing a differential operation with the real-time efficiency data of the current cycle, accurately quantifying the amplitude of efficiency fluctuations, and then automatically expanding the processing channels to make full use of resources when the efficiency improves, and intelligently shrinking the mapping volume to avoid overload when the efficiency decreases, forming a closed-loop optimization chain.

[0015] (3) The present invention can significantly improve the stability and resource utilization rate of the food safety information traceability platform. When the mapping stability coefficient is abnormal, it automatically triggers a dynamic calibration program: when it exceeds the threshold, an incremental algorithm is used to expand the processing capacity to ensure smooth operation during peak hours; when it is below the threshold, a data cleaning and reconstruction process is started to quickly restore the platform to a healthy state. This mechanism accurately quantifies the adjustment amplitude through the deviation ratio, avoids overcompensation, dynamically expands and contracts the supervision cycle to match the real-time load demand, and performs closed-loop data processing to eliminate cumulative errors at the source. Description of the Drawings

[0016] The present invention is further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the following drawings.

[0017] Figure 1 It is a schematic diagram of the connection of the system modules of the present invention.

[0018] Figure 2 It is a schematic diagram of the method step flow of the present invention. Detailed Embodiments

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with 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 of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0020] Referring to Figure 1 as shown, the first aspect of the present invention provides an intelligent supervision system for food safety information traceability, including: a parameter initialization module, a speed matching module, a parameter adjustment module, and an information database.

[0021] The information database is used to store the parameters required for an intelligent supervision system for food safety information traceability.

[0022] The parameter initialization module is connected to the speed matching module, the speed matching module is connected to the parameter adjustment module, and the parameter initialization module, the speed matching module, and the parameter adjustment module are all connected to the information database.

[0023] The parameter initialization module is used to mark the food safety information traceability platform as the target platform, monitor and analyze the instruction processing process parameters of the target platform, and initialize the mapping process of the target platform.

[0024] The above-mentioned food safety information traceability platform is a comprehensive system for storing and managing food safety-related information. The platform receives food data submitted from all parties, such as key information like production date, batch number, manufacturer, and quality inspection report, and accurately maps this information to various pre-set database tables. In this way, during subsequent query processes, the platform can efficiently retrieve the required data from these classified and stored tables, thereby achieving comprehensive traceability and accurate query of food safety information.

[0025] Specifically, the mapping process of initializing the target platform specifically refers to: analyzing the instruction processing process parameters of the target platform to obtain the processing efficiency index of the target platform in the first cycle; obtaining the processing efficiency index of the target platform in the historical first cycle, performing a difference processing on the processing efficiency index of the target platform in the first cycle and the processing efficiency index of the target platform in the historical first cycle to obtain the processing efficiency deviation value of the target platform in the first cycle, and initializing the concurrent mapping data volume of the target platform based on the processing efficiency deviation value of the target platform in the first cycle; the above-mentioned first cycle refers to the time period for monitoring the instruction processing process of the target platform, and the specific duration is formulated by the data analyst; the above-mentioned instruction processing mainly includes the following specific links: first, receiving traceability requests from regulatory agencies, production enterprises or consumers, and secondly, quickly locating and retrieving relevant food safety data in the platform's database according to the information in the requests. These data are scattered and stored in multiple specially designed tables, covering the entire chain of information from the production source to the sales terminal; finally, integrating and analyzing the retrieved data and feeding it back to the requester in an intuitive and easy-to-understand manner to complete the entire instruction processing and traceability process; the above-mentioned historical first cycle refers to the first cycle that is adjacent to the current first cycle in the time series and is already in the past tense; the above-mentioned processing efficiency deviation value is used to quantify the deviation degree between the processing efficiency index of the target platform in the first cycle and the processing efficiency index of the target platform in the historical first cycle.

[0026] In a specific embodiment, the present invention realizes intelligent resource allocation through a dynamic efficiency calibration mechanism. The core lies in extracting the processing efficiency benchmark value of the target platform's historical cycle, performing a differential operation with the real-time efficiency data of the current cycle, accurately quantifying the amplitude of efficiency fluctuations, and then automatically expanding the processing channel to make full use of resources when the efficiency is improved, and intelligently shrinking the mapping volume to avoid overload when the efficiency drops, forming a closed-loop optimization chain.

[0027] Specifically, the processing efficiency index of the target platform in the first cycle is analyzed as follows: The instruction processing process parameters of the target platform include the thread pool saturation rate of the target platform in the first cycle, the average trace response duration of the target platform in the first cycle, and the buffer hit rate of the target platform in the first cycle. The above thread pool saturation rate refers to the usage of the thread pool when the target platform processes instructions. Obtain the average number of active threads in the first cycle, that is, the number of threads processing tasks on average in the first cycle, and obtain the maximum number of threads, that is, the maximum number of threads that the thread pool can accommodate. Calculate the thread pool utilization rate, that is, the number of active threads divided by the maximum number of threads, which is recorded as the thread pool saturation rate. The above average trace response duration refers to the average time consumed by the target platform from receiving an instruction to returning a trace result. The above buffer hit rate refers to the proportion of directly obtaining the required data from the buffer when the target platform processes instructions. The buffer hit rate can be calculated by counting the number of buffer hits and the total number of accesses. The specific method includes: recording the number of hits for each time of obtaining data from the buffer, recording the total number of data accesses each time, and calculating the buffer hit rate, that is, the number of hits divided by the total number of accesses. Among them, the thread pool saturation rate, the average trace response duration, and the buffer hit rate can all be monitored by a performance monitoring tool (such as Application Dynamics).

[0028] By introducing weights to quantify the influence degrees of the thread pool saturation rate component, the average trace response duration component, and the buffer hit rate component on the processing efficiency index respectively, and summing up each influence degree, the processing efficiency index is obtained. The above processing efficiency index of the target platform in the first cycle is used to quantify the efficiency of the target platform in processing trace instructions in the first cycle. The specific expression is:

[0029] DSH = (c + FL_BD × gf1 + FL_GTU × gf2) -1 + FL_MZ × gf3;

[0030]

[0031] Wherein, DSH is the processing efficiency index of the target platform in the first cycle, FL_BD is the thread pool saturation component, FL_GTU is the average trace response duration component, FL_MZ is the buffer hit rate component, BD is the thread pool saturation of the target platform in the first cycle, JBD is the defined thread pool saturation preset in the information database, GTU is the average trace response duration of the target platform in the first cycle, J_GTU is the defined average trace response duration preset in the information database, MZ is the buffer hit rate of the target platform in the first cycle, J_MZ is the defined buffer hit rate preset in the information database, gf1 is the weight corresponding to the thread pool saturation component preset in the information database, gf2 is the weight corresponding to the average trace response duration component preset in the information database, gf3 is the weight corresponding to the buffer hit rate component preset in the information database, and c is a constant, where c > 0.

[0032] The above-mentioned thread pool saturation component refers to the proportional coefficient (i.e., ratio) between the thread pool saturation and the defined thread pool saturation; the above-mentioned average trace response duration component refers to the proportional coefficient (i.e., ratio) between the average trace response duration and the defined average trace response duration; the above-mentioned buffer hit rate component refers to the proportional coefficient (i.e., ratio) between the buffer hit rate and the defined buffer hit rate; the above-mentioned defined thread pool saturation represents the maximum allowable value of the thread pool saturation; the above-mentioned defined average trace response duration represents the maximum allowable value of the average trace response duration; the above-mentioned defined buffer hit rate represents the minimum allowable value of the buffer hit rate.

[0033] It should be explained that introducing the constant c can ensure the effectiveness and rationality of data analysis.

[0034] The weight corresponding to the above-mentioned thread pool saturation component represents the proportion of the thread pool saturation component in the processing efficiency index; the weight corresponding to the above-mentioned average trace response duration component represents the proportion of the average trace response duration component in the processing efficiency index; the weight corresponding to the above-mentioned buffer hit rate component represents the proportion of the buffer hit rate component in the processing efficiency index. The information database stores the corresponding relationships between the thread pool saturation component, the average trace response duration component, and the buffer hit rate component and their corresponding weights. For example, when the thread pool saturation component, the average trace response duration component, and the buffer hit rate component are input into the information database, the information database can match the weights corresponding to the thread pool saturation component, the average trace response duration component, and the buffer hit rate component, and their value ranges are all between 0 and 1.

[0035] It should be noted that the thread pool saturation component reflects the proportion of busy threads in the thread pool. When this proportion is relatively high, it means that the thread pool is close to full load, and the ability to process requests may be limited, resulting in an increase in the average trace response duration component, that is, the time required for the platform to respond to requests becomes longer. On the other hand, the buffer hit rate reflects the effective utilization degree of the platform's cache resources. A high hit rate means that more requests can directly obtain data from the cache, reducing the number of accesses, and thus helping to shorten the average trace response duration. However, when the thread pool saturation is too high, buffer overflow may occur due to requests that cannot be processed in time, thereby reducing the buffer hit rate. In summary, the thread pool saturation component indirectly affects the processing efficiency index by influencing the average trace response duration component and the buffer hit rate. High saturation may lead to an increase in response duration and a decrease in hit rate, thus reducing the overall processing efficiency.

[0036] Furthermore, initialize the concurrent mapping data volume of the target platform based on the processing efficiency deviation value of the target platform in the first cycle. The specific initialization process is as follows: Obtain the concurrent mapping data volume of the target platform in the historical first cycle; the above-mentioned concurrent mapping data volume refers to the data mapping volume that the target platform can process simultaneously and can be extracted from the log file of the target platform.

[0037] If the processing efficiency deviation value of the target platform in the first cycle is less than the reference processing efficiency deviation value, then match the first reduction coefficient from the information database according to the processing efficiency deviation value of the target platform in the first cycle, and adjust the concurrent mapping data volume of the target platform in the historical first cycle. Re-initialize the concurrent mapping data volume of the target platform based on the adjusted concurrent mapping data volume; the above-mentioned reference processing efficiency deviation value represents the reference value of the processing efficiency deviation value and is extracted from the information database; the above-mentioned first reduction coefficient refers to the proportional value that dynamically reduces the concurrent mapping data volume according to the processing efficiency deviation value, and the first reduction coefficient is a value less than 1. The specific matching process is as follows: The information database stores the first reduction coefficients corresponding to each processing efficiency deviation value interval. Query the processing efficiency deviation value interval to which the processing efficiency deviation value of the target platform in the first cycle belongs. The first reduction coefficient corresponding to this processing efficiency deviation value interval is the matched first reduction coefficient. Multiply the first reduction coefficient by the concurrent mapping data volume of the target platform in the historical first cycle, and the product result is the adjusted concurrent mapping data volume, which is initialized as the concurrent mapping data volume of the target platform.

[0038] If the processing efficiency deviation value of the target platform in the first cycle is equal to the reference processing efficiency deviation value, then initialize based on the concurrent mapping data volume of the target platform in the historical first cycle, that is, do not make any adjustment to the concurrent mapping data volume of the target platform in the historical first cycle and directly initialize it as the concurrent mapping data volume of the target platform.

[0039] If the processing efficiency deviation value of the target platform in the first period is greater than the reference processing efficiency deviation value, then a first increase coefficient is matched from the information database according to the processing efficiency deviation value of the target platform in the first period, and the concurrent mapping data volume of the target platform in the historical first period is adjusted. The concurrent mapping data volume of the target platform is re-initialized based on the adjusted concurrent mapping data volume; the above-mentioned first increase coefficient refers to the proportional value for dynamically increasing the concurrent mapping data volume according to the processing efficiency deviation value, and the first increase coefficient is a value greater than 1. The specific matching process is as follows: The first increase coefficients corresponding to each processing efficiency deviation value interval are stored in the information database. Query the processing efficiency deviation value interval to which the processing efficiency deviation value of the target platform in the first period belongs. The first increase coefficient corresponding to this processing efficiency deviation value interval is the matched first increase coefficient. Multiply the first increase coefficient by the concurrent mapping data volume of the target platform in the historical first period. The product result is the adjusted concurrent mapping data volume, which is initialized as the concurrent mapping data volume of the target platform.

[0040] It should be noted that the first increase coefficients corresponding to each processing efficiency deviation value interval and the first decrease coefficients corresponding to each processing efficiency deviation value interval are independent of each other, that is, there is no overlapping part between them. Specifically, each processing efficiency deviation value is strictly divided into a certain specific interval, and this interval uniquely corresponds to a first increase coefficient or a first decrease coefficient.

[0041] The speed matching module is used to collect and analyze the data reception process parameters of the target platform and intelligently match the data mapping speed of the target platform.

[0042] Specifically, the data mapping speed of the target platform is matched. The specific matching process is as follows: By analyzing the data reception process parameters of the target platform, the data complexity factor of the target platform in the first period is obtained; based on the data mapping speeds corresponding to each data complexity factor interval stored in the information database, the interval to which the data complexity factor of the target platform in the first period belongs is analyzed, and the data mapping speed corresponding to this data complexity factor interval is recorded as the data mapping speed of the target platform; the above-mentioned data mapping speed refers to the speed at which the target platform converts data from one format or structure to another format or structure when processing data. This conversion is usually to meet the needs of data storage, analysis, or display.

[0043] Obtain the data mapping speed of the target platform in the historical first period, perform difference and absolute value processing on it and the data mapping speed of the target platform in sequence, perform ratio processing on the processing result and the data mapping speed of the target platform in the historical first period, finally obtain the data mapping speed deviation value of the target platform, and compare it with the defined data mapping speed deviation value. If the data mapping speed deviation value of the target platform is greater than the defined data mapping speed deviation value, adjust the data mapping speed of the target platform until the data mapping speed deviation value of the target platform is equal to or less than the defined data mapping speed deviation value; the data mapping speed of the target platform in the historical first period can be found from the log file of the target platform; the data mapping speed deviation value is used to quantify the deviation degree between the data mapping speed of the target platform in the historical first period and the data mapping speed of the target platform, and is extracted from the information database; if the data mapping speed deviation value of the target platform is greater than the defined data mapping speed deviation value, if the data mapping speed of the target platform is greater than the data mapping speed of the target platform in the historical first period, then reduce the data mapping speed of the target platform until the data mapping speed deviation value of the target platform is equal to or less than the defined data mapping speed deviation value, and vice versa if the data mapping speed of the target platform is less than the data mapping speed of the target platform in the historical first period, then increase the data mapping speed of the target platform until the data mapping speed deviation value of the target platform is equal to or less than the defined data mapping speed deviation value.

[0044] At the same time, compare the data complexity factor of the target platform in the first period with the data complexity threshold. If the data complexity factor of the target platform in the first period is less than or equal to the data complexity threshold, select the first mapping method for data mapping. If the data complexity factor of the target platform in the first period is greater than the data complexity threshold, select the second mapping method for data mapping; the data complexity threshold is data used to distinguish the data mapping method of the target platform and is extracted from the information database; in an exemplary embodiment, the first mapping method refers to the enumeration mapping method; the second mapping method refers to the distributed mapping method.

[0045] Further, the specific analysis process of the data complexity factor of the target platform in the first period is as follows: The data reception process parameters of the target platform include the protocol entropy value of the target platform in the first period, the graph calculation complexity of the target platform in the first period, and the data volume growth rate of the target platform in the first period; the specific expression of the protocol entropy value is: i is the number of various data communication protocols received by the target platform in the first period, i = {1, 2, 3,..., k}, k is the total number of types of data communication protocols received by the target platform in the first period, P iThe proportion of various data communication protocols received within the first cycle for the target platform; the above-mentioned graph calculation complexity refers to the amount of storage space required by the target platform when processing graph data; the above-mentioned data volume growth rate quantifies the growth trend of the data volume received by the target platform. A high data volume growth rate means that the amount of data that the target platform needs to process is constantly increasing. It can be obtained by taking the difference between the data volume at the end time point of the first cycle of the target platform and the data volume at the start time point of the first cycle of the target platform, and then taking the ratio of the processing result to the data volume at the start time point of the first cycle of the target platform. Finally, the data volume growth rate is obtained. Among them, the protocol entropy value, the graph calculation complexity, and the data volume growth rate can all be monitored through a performance monitoring tool (such as Application Dynamics).

[0046] Summarize the influence degree of the ratio between the protocol entropy value and the defined protocol entropy value on the data complexity factor, the influence degree of the ratio between the graph calculation complexity and the defined graph calculation complexity on the data complexity factor, and the influence degree of the ratio between the data volume growth rate and the defined data volume growth rate on the data complexity factor. At the same time, introduce the processing efficiency index for the influence degree on the data complexity factor and conduct a secondary summary to obtain the data complexity factor; the data complexity factor of the target platform within the first cycle characterizes the complexity of the data received by the target platform within the first cycle. The specific expression is:

[0047] SWP = DSH × cd1 + PYU × cd2;

[0048]

[0049] In the formula, SWP is the data complexity factor of the target platform within the first cycle, DSH is the processing efficiency index of the target platform within the first cycle, cd1 is the influence factor corresponding to the processing efficiency index preset in the information database, PYU is the data complexity factor component of the target platform within the first cycle, cd2 is the influence factor corresponding to the data complexity factor component preset in the information database, GP is the protocol entropy value of the target platform within the first cycle, J_GP is the defined protocol entropy value preset in the information database, HO is the graph calculation complexity of the target platform within the first cycle, J_HO is the defined graph calculation complexity preset in the information database, FY is the data volume growth rate of the target platform within the first cycle, J_FY is the defined data volume growth rate preset in the information database, xa1 is the influence factor corresponding to the protocol entropy value preset in the information database, xa2 is the influence factor corresponding to the graph calculation complexity preset in the information database, and xa3 is the influence factor corresponding to the data volume growth rate preset in the information database.

[0050] The above-defined protocol entropy value represents the maximum allowable value of the protocol entropy value; the above-defined graph calculation complexity represents the maximum allowable value of the graph calculation complexity; the above-defined data volume growth rate represents the maximum allowable value of the data volume growth rate; the above data complexity factor component is used to quantify the comprehensive impact of the protocol entropy value, graph calculation complexity, and data volume growth rate on the data complexity factor.

[0051] The influencing factor corresponding to the above processing efficiency index represents the degree of influence of the unit value after removing the unit of the processing efficiency index on the data complexity factor; the influencing factor corresponding to the above data complexity factor component represents the degree of influence of the unit value after removing the unit of the data complexity factor component on the data complexity factor; the influencing factor corresponding to the above protocol entropy value represents the degree of influence of the unit value of the protocol entropy value on the data complexity factor component; the influencing factor corresponding to the above graph calculation complexity represents the degree of influence of the unit value of the graph calculation complexity on the data complexity factor component; the influencing factor corresponding to the above data volume growth rate represents the degree of influence of the unit value of the data volume growth rate on the data complexity factor component. The information database stores the corresponding relationships between the processing efficiency index, data complexity factor component, protocol entropy value, graph calculation complexity, and data volume growth rate and their corresponding influencing factors. For example, when the processing efficiency index, data complexity factor component, protocol entropy value, graph calculation complexity, and data volume growth rate are input into the information database, the information database can match the influencing factors corresponding to the processing efficiency index, data complexity factor component, protocol entropy value, graph calculation complexity, and data volume growth rate, and their value ranges are all between 0 and 1.

[0052] It should be noted that when the processing efficiency index is high, it means that the target platform can complete the data processing task in a shorter time, thus reducing the data processing delay. However, with the increase in the data volume growth rate, that is, the continuous expansion of the data scale, the processing efficiency index may be challenged because a larger data volume often requires higher computing resources and more complex processing processes, which may lead to an extension of the processing time and a decline in efficiency. The protocol entropy value reflects the redundancy degree of information in the data transmission or communication protocol. A protocol with a low entropy value means more efficient data transmission because there is less redundant information. However, when the graph computing complexity increases, that is, when the data processing task becomes more complex, more information may need to be transmitted or more data exchanges may be required, which may lead to an increase in the protocol entropy value because complex data processing tasks are often accompanied by more redundant information and data transmission requirements. With the growth of the data volume and the complexity of the data processing task, the graph computing complexity may increase significantly, which requires the target platform to have higher computing power and more optimized processing strategies. At the same time, the increase in the graph computing complexity may also lead to a decline in the processing efficiency index and an increase in the protocol entropy value because complex data processing tasks require more computing resources and more frequent data transmissions. The data volume growth rate is one of the key factors driving these parameter changes. With the continuous growth of the data volume, the processing efficiency index may be challenged, the protocol entropy value may increase, and the graph computing complexity may increase. These factors work together to lead to an increase in the data complexity factor, that is, the data processing task becomes more complex. In summary, there is a relationship of mutual influence and restriction among the processing efficiency index, the protocol entropy value, the graph computing complexity, and the data volume growth rate. The increase in the data volume growth rate may lead to a decline in the processing efficiency index, an increase in the protocol entropy value, and an increase in the graph computing complexity, and these factors work together to increase the level of the data complexity factor.

[0053] The parameter adjustment module is used to monitor and evaluate the mapping parameters of the target platform, so as to determine whether to adjust the mapping process of the target platform.

[0054] In a specific embodiment, the present invention can significantly improve the stability and resource utilization rate of the food safety information traceability platform. When the mapping stability coefficient is abnormal, a dynamic calibration program is automatically triggered: when it exceeds the threshold, an incremental algorithm is used to expand the processing capacity to ensure smooth operation during peak hours; when it is lower than the threshold, a data cleaning and reconstruction process is started to quickly restore the healthy state of the platform. This mechanism accurately quantifies the adjustment range through the deviation ratio, avoids overcompensation, and at the same time dynamically expands and contracts the monitoring period to match the real-time load requirements, as well as closed-loop data processing to eliminate cumulative errors from the root.

[0055] Specifically, to determine whether to adjust the mapping process of the target platform, the specific determination process is as follows: By evaluating the mapping parameters of the target platform, the mapping stability coefficient of the target platform within the mapping supervision period is obtained and compared with the reference interval of the mapping stability coefficient. If the mapping stability coefficient of the target platform within the mapping supervision period belongs to the reference interval of the mapping stability coefficient, it is determined not to adjust the mapping process of the target platform; if the mapping stability coefficient of the target platform within the mapping supervision period does not belong to the reference interval of the mapping stability coefficient, it is determined to adjust the mapping process of the target platform; the above reference interval of the mapping stability coefficient refers to the reasonable range of the mapping stability coefficient of the target platform within the mapping supervision period, which is extracted from the information database.

[0056] Specifically, the process of evaluating the mapping stability coefficient of the target platform within the mapping supervision period is as follows: The mapping parameters of the target platform include the parallel efficiency of the target platform within the mapping supervision period, the data mapping speed deviation value of the target platform within the mapping supervision period, and the average data mapping delay duration of the target platform within the mapping supervision period; the above mapping supervision period refers to the time period for monitoring the mapping adjustment process of the target platform, which can be obtained from the log file of the target platform; the above parallel efficiency is a measure of the ability of the target platform to complete the data mapping task using parallel processing technology within the mapping supervision period, and the specific formula is: Parallel efficiency = Parallel computing duration / Serial computing duration; the above data mapping speed deviation value refers to the absolute value of the difference between the actual data mapping speed of the target platform within the mapping supervision period and the data mapping speed of the target platform intelligently matched; the above average data mapping delay duration refers to the difference between the average data mapping duration of the target platform within the mapping supervision period and the reference average data mapping duration, where the reference average data mapping duration represents the reference value of the average data mapping duration, which is extracted from the information database; the parallel efficiency, the data mapping speed deviation value, and the average data mapping delay duration can all be monitored through a performance monitoring tool (such as Application Dynamics).

[0057] Obtain the processing efficiency index of the target platform within the mapping supervision period and the data complexity factor of the target platform within the mapping supervision period; among them, the processing efficiency index of the target platform within the mapping supervision period is the same as the acquisition method and meaning of the processing efficiency index of the target platform within the first period, only with a difference in parameter time; the data complexity factor of the target platform within the mapping supervision period is the same as the acquisition method and meaning of the data complexity factor of the target platform within the first period, only with a difference in parameter time.

[0058] Summarize once the influence degree of the ratio between the parallel efficiency and the defined parallel efficiency on the mapping stability coefficient, the influence degree of the ratio between the data mapping speed deviation value and the defined data mapping speed deviation value on the mapping stability coefficient, and the influence degree of the ratio between the average data mapping delay duration and the defined average data mapping delay duration on the mapping stability coefficient. Summarize twice the influence degree of the processing efficiency index on the mapping stability coefficient and the influence degree of the data complexity factor on the mapping stability coefficient. Finally, couple the results of the first summary and the second summary to obtain the mapping stability coefficient. The mapping stability coefficient of the target platform within the mapping supervision period represents the mapping stability degree of the target platform within the mapping supervision period, and the specific expression is:

[0059] QSC = JU × xp1 + SET × xp2;

[0060]

[0061]

[0062] In the formula, QSC is the mapping stability coefficient of the target platform within the mapping supervision period, JU is the first mapping stability component of the target platform within the mapping supervision period, SET is the second mapping stability component of the target platform within the mapping supervision period, xp1 is the influence weight corresponding to the first mapping stability component preset in the information database, xp2 is the influence weight corresponding to the second mapping stability component preset in the information database, X_DSH is the processing efficiency index of the target platform within the mapping supervision period, X_SWP is the data complexity factor of the target platform within the mapping supervision period, bu1 is the influence weight corresponding to the processing efficiency index preset in the information database, bu2 is the influence weight corresponding to the data complexity factor preset in the information database, MA is the parallel efficiency of the target platform within the mapping supervision period, J_MA is the defined parallel efficiency preset in the information database, SK is the data mapping speed deviation value of the target platform within the mapping supervision period, J_SK is the defined data mapping speed deviation value preset in the information database, FTP is the average data mapping delay duration of the target platform within the mapping supervision period, J_FTP is the defined average data mapping delay duration preset in the information database, tu1 is the influence weight corresponding to the parallel efficiency preset in the information database, tu2 is the influence weight corresponding to the data mapping speed deviation value preset in the information database, tu3 is the influence weight corresponding to the average data mapping delay duration preset in the information database, and m is a constant, where m > 0.

[0063] It should be noted that introducing the constant m can ensure the effectiveness and rationality of data analysis.

[0064] The above mapping stabilizes the first component, which is used to quantify the comprehensive influence of the processing efficiency index and the data complexity factor on the mapping stability coefficient; the above mapping stabilizes the second component, which is used to quantify the comprehensive influence of the parallel efficiency, the data mapping speed deviation value, and the average data mapping delay duration on the mapping stability coefficient; the above-defined parallel efficiency represents the minimum allowable value of the parallel efficiency; the above-defined data mapping speed deviation value represents the maximum allowable value of the data mapping speed deviation value; the above-defined average data mapping delay duration represents the maximum allowable value of the average data mapping delay duration.

[0065] The influence weight corresponding to the above mapping stable first component represents the proportion of the mapping stable first component after removing the unit in the mapping stability coefficient; the influence weight corresponding to the above mapping stable second component represents the proportion of the mapping stable second component after removing the unit in the mapping stability coefficient; the influence weight corresponding to the above processing efficiency index represents the proportion of the unit value after removing the unit of the processing efficiency index in the mapping stable first component; the influence weight corresponding to the above data complexity factor represents the proportion of the unit value after removing the unit of the data complexity factor in the mapping stable first component; the influence weight corresponding to the above parallel efficiency represents the degree of influence of the unit value of the parallel efficiency on the mapping stable second component; the influence weight corresponding to the above data mapping speed deviation value represents the degree of influence of the unit value of the data mapping speed deviation value on the mapping stable second component; the influence weight corresponding to the above average data mapping delay duration represents the degree of influence of the unit value of the average data mapping delay duration on the mapping stable second component. The information database stores the corresponding relationships between the mapping stable first component, the mapping stable second component, the processing efficiency index, the data complexity factor, the parallel efficiency, the data mapping speed deviation value, the average data mapping delay duration, and their corresponding influence weights. For example, when the mapping stable first component, the mapping stable second component, the processing efficiency index, the data complexity factor, the parallel efficiency, the data mapping speed deviation value, and the average data mapping delay duration are input into the information database, the information database can match the influence weight corresponding to the mapping stable first component, the influence weight corresponding to the mapping stable second component, the influence weight corresponding to the processing efficiency index, the influence weight corresponding to the data complexity factor, the influence weight corresponding to the parallel efficiency, the influence weight corresponding to the data mapping speed deviation value, and the influence weight corresponding to the average data mapping delay duration, and their value ranges are all between 0 and 1.

[0066] It should be noted that the processing performance index is a key indicator for measuring the efficiency of the target platform in processing tasks. When the data complexity factor increases, that is, the structure, type, scale, and correlation of the data become more complex, the processing performance index often decreases because complex data requires more computing resources and time to process. The improvement of parallel efficiency, that is, the enhanced ability of the target platform to efficiently process multiple tasks simultaneously, can partially offset the negative impact brought by the data complexity factor and improve the processing performance index. However, the increase in the deviation value of the data mapping speed, that is, the difference between the actual mapping speed and the matched speed becomes larger, will reduce the parallel efficiency because the unstable mapping speed may lead to waiting and synchronization problems between tasks. At the same time, the increase in the average latency of data mapping, that is, the data mapping process becomes slower, will further affect the parallel efficiency because the latency will increase the total execution time of the tasks. The changes in these parameters, especially the decrease in the processing performance index, the reduction of parallel efficiency, the increase in the deviation value of the data mapping speed, and the increase in the average latency of data mapping, will all lead to a decrease in the mapping stability coefficient, that is, it is more difficult for the data mapping process to maintain stability after being disturbed.

[0067] Further, adjust the mapping process of the target platform. The specific adjustment process is as follows: If the mapping stability coefficient of the target platform within the mapping supervision period is greater than the maximum value of the mapping stability coefficient reference interval, then perform a difference operation on the mapping stability coefficient of the target platform within the mapping supervision period and the maximum value of the mapping stability coefficient reference interval. Then, perform a ratio operation on the processing result and the maximum value of the mapping stability coefficient reference interval to finally obtain the first mapping stability coefficient deviation value of the target platform within the mapping supervision period. Then, match the second increase coefficient from the information database and increase and adjust the concurrent mapping data volume of the target platform. At the same time, increase and adjust the duration corresponding to the mapping supervision period according to the second increase coefficient. The above first mapping stability coefficient deviation value refers to the deviation degree between the mapping stability coefficient and the maximum value of the mapping stability coefficient reference interval when the mapping stability coefficient of the target platform within the mapping supervision period is greater than the maximum value of the mapping stability coefficient reference interval. The above second increase coefficient refers to the proportional value for dynamically increasing the concurrent mapping data volume according to the first mapping stability coefficient deviation value. The second increase coefficient is a value greater than 1. The specific matching process is as follows: The information database stores the second increase coefficients corresponding to each first mapping stability coefficient deviation value interval. Query the first mapping stability coefficient deviation value interval to which the first mapping stability coefficient deviation value of the target platform within the mapping supervision period belongs. The second increase coefficient corresponding to this first mapping stability coefficient deviation value interval is the matched second increase coefficient. Multiply the second increase coefficient by the concurrent mapping data volume of the target platform. The product result is the concurrent mapping data volume after the increase and adjustment. The above increase and adjustment of the duration corresponding to the mapping supervision period according to the second increase coefficient specifically means multiplying the second increase coefficient by the duration corresponding to the mapping supervision period. The processing result is the duration corresponding to the mapping supervision period after the increase and adjustment.

[0068] If the mapping stability coefficient of the target platform within the mapping supervision period is less than the minimum value of the mapping stability coefficient reference interval, the mapping data of the target platform within the mapping supervision period shall be withdrawn. At the same time, the difference between the minimum value of the mapping stability coefficient reference interval and the mapping stability coefficient of the target platform within the mapping supervision period shall be processed, and the processing result shall be ratioed with the minimum value of the mapping stability coefficient reference interval to finally obtain the second mapping stability coefficient deviation value of the target platform within the mapping supervision period. Then, the second reduction coefficient shall be matched from the information database, and the concurrent mapping data volume of the target platform shall be reduced and adjusted. The duration corresponding to the mapping supervision period shall be reduced and adjusted according to the second reduction coefficient. At the same time, according to the second mapping stability coefficient deviation value of the target platform within the mapping supervision period, the data cleaning volume of the target platform shall be obtained for cleaning, so as to remap the mapping data of the target platform within the mapping supervision period; the above-mentioned second mapping stability coefficient deviation value refers to the deviation degree between the mapping stability coefficient and the minimum value of the mapping stability coefficient reference interval when the mapping stability coefficient of the target platform within the mapping supervision period is less than the minimum value of the mapping stability coefficient reference interval; the above-mentioned second reduction coefficient refers to the proportional value for dynamically reducing the concurrent mapping data volume according to the second mapping stability coefficient deviation value. The second reduction coefficient is a value less than 1. The specific matching process is as follows: the second reduction coefficients corresponding to each second mapping stability coefficient deviation value interval are stored in the information database. Query the second mapping stability coefficient deviation value interval to which the second mapping stability coefficient deviation value of the target platform within the mapping supervision period belongs. The second reduction coefficient corresponding to this second mapping stability coefficient deviation value interval is the matched second reduction coefficient. Multiply the second reduction coefficient by the concurrent mapping data volume of the target platform, and the product result is the concurrent mapping data volume after reduction and adjustment; the above-mentioned reduction and adjustment of the duration corresponding to the mapping supervision period according to the second reduction coefficient means multiplying the second reduction coefficient by the duration corresponding to the mapping supervision period, and the product result is the duration corresponding to the mapping supervision period after reduction and adjustment; the above-mentioned obtaining the data cleaning volume of the target platform for cleaning specifically means querying the data cleaning volume of the target platform from the information database according to the second mapping stability coefficient deviation value of the target platform within the mapping supervision period, and the target platform cleans the corresponding data volume from the stored expired data.

[0069] In a specific embodiment, the present invention provides an intelligent supervision system and method for food safety information traceability. By monitoring the target platform instruction processing parameters in real time and initializing the mapping process, combining data collection and dynamic parameter analysis technologies, it intelligently matches the optimal mapping rate, and can accurately evaluate the key indicators of the mapping process, automatically triggering an adjustment mechanism to ensure efficient operation, significantly improving the timeliness and accuracy of food safety traceability, effectively reducing the lag and error risks of traditional manual supervision. At the same time, the dynamic optimization of the mapping strategy can balance data processing efficiency and resource consumption, ensuring the integrity of the traceability chain while reducing operating costs, providing technical support for building an intelligent food safety information traceability system.

[0070] Referring to Figure 2 As shown, the second aspect of the present invention provides an intelligent supervision method for food safety information traceability, including: Step 1, marking the food safety information traceability platform as the target platform, monitoring and analyzing the instruction processing process parameters of the target platform, and initializing the mapping process of the target platform; Step 2, collecting and analyzing the data reception process parameters of the target platform, and intelligently matching the data mapping speed of the target platform; Step 3, supervising and evaluating the mapping parameters of the target platform to determine whether to adjust the mapping process of the target platform.

[0071] The above content is only an example and explanation of the structure of the present invention. Those skilled in the art of the present technology can make various modifications or supplements or use similar methods to replace the specific embodiments described, as long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should fall within the protection scope of the present invention.

Claims

1. An intelligent supervision system for food safety information traceability, characterized in that, Including: A parameter initialization module, which is used to mark the food safety information traceability platform as the target platform, monitor and analyze the instruction processing process parameters of the target platform, and initialize the mapping process of the target platform; A speed matching module, which is used to collect and analyze the data reception process parameters of the target platform, and intelligently match the data mapping speed of the target platform; A parameter adjustment module, which is used to supervise and evaluate the mapping parameters of the target platform, so as to determine whether to adjust the mapping process of the target platform.

2. The intelligent supervision system for food safety information traceability according to claim 1, wherein: The initialization of the mapping process of the target platform specifically refers to: Analyze the instruction processing process parameters of the target platform to obtain the processing efficiency index of the target platform in the first cycle; Obtain the processing efficiency index of the target platform in the historical first cycle, perform a difference process on the processing efficiency index of the target platform in the first cycle and the processing efficiency index of the target platform in the historical first cycle to obtain the processing efficiency deviation value of the target platform in the first cycle, and initialize the concurrent mapping data volume of the target platform based on the processing efficiency deviation value of the target platform in the first cycle.

3. The intelligent supervision system for food safety information traceability according to claim 2, characterized in that: The specific initialization process of initializing the concurrent mapping data volume of the target platform based on the processing efficiency deviation value of the target platform in the first cycle is as follows: Obtain the concurrent mapping data volume of the target platform in the historical first cycle; If the processing efficiency deviation value of the target platform in the first cycle is less than the reference processing efficiency deviation value, match the first reduction coefficient from the information database according to the processing efficiency deviation value of the target platform in the first cycle, adjust the concurrent mapping data volume of the target platform in the historical first cycle, and re-initialize the concurrent mapping data volume of the target platform based on the adjusted concurrent mapping data volume; If the processing efficiency deviation value of the target platform in the first cycle is equal to the reference processing efficiency deviation value, initialize the concurrent mapping data volume of the target platform based on the concurrent mapping data volume of the target platform in the historical first cycle; If the processing efficiency deviation value of the target platform in the first cycle is greater than the reference processing efficiency deviation value, match the first increase coefficient from the information database according to the processing efficiency deviation value of the target platform in the first cycle, adjust the concurrent mapping data volume of the target platform in the historical first cycle, and re-initialize the concurrent mapping data volume of the target platform based on the adjusted concurrent mapping data volume.

4. The intelligent supervision system for food safety information traceability according to claim 2, wherein: The specific analysis process of the processing efficiency index of the target platform in the first cycle is as follows: The instruction processing process parameters of the target platform include the thread pool saturation rate of the target platform in the first cycle, the average traceability response duration of the target platform in the first cycle, and the buffer hit rate of the target platform in the first cycle; The thread pool saturation rate component refers to the proportional coefficient between the thread pool saturation rate and the defined thread pool saturation rate; the average traceability response duration component refers to the proportional coefficient between the average traceability response duration and the defined average traceability response duration; the buffer hit rate component refers to the proportional coefficient between the buffer hit rate and the defined buffer hit rate. By introducing weights, the influence degrees of the thread pool saturation component, the average response duration component of tracing, and the buffer hit rate component on the processing efficiency index are quantified respectively, and the influence degrees are summarized to obtain the processing efficiency index; The processing efficiency index of the target platform in the first cycle is used to quantify the efficiency of the target platform in processing tracing instructions in the first cycle.

5. The intelligent supervision system for food safety information traceability according to claim 1, wherein: The data mapping speed of the target platform is matched. The specific matching process is as follows: By analyzing the data reception process parameters of the target platform, the data complexity factor of the target platform in the first cycle is obtained; Based on the data mapping speeds corresponding to each data complexity factor interval stored in the information database, the data complexity factor interval to which the data complexity factor of the target platform in the first cycle belongs is analyzed, and the data mapping speed corresponding to this data complexity factor interval is recorded as the data mapping speed of the target platform; The data mapping speed of the target platform in the historical first cycle is obtained, and difference and absolute value processing are performed on it and the data mapping speed of the target platform in turn. The processing result is subjected to ratio processing with the data mapping speed of the target platform in the historical first cycle, and finally the data mapping speed deviation value of the target platform is obtained and compared with the defined data mapping speed deviation value. If the data mapping speed deviation value of the target platform is greater than the defined data mapping speed deviation value, the data mapping speed of the target platform is adjusted until the data mapping speed deviation value of the target platform is equal to or less than the defined data mapping speed deviation value; At the same time, according to the data complexity factor of the target platform in the first cycle, it is compared with the data complexity threshold. If the data complexity factor of the target platform in the first cycle is less than or equal to the data complexity threshold, the first mapping method is selected for data mapping. If the data complexity factor of the target platform in the first cycle is greater than the data complexity threshold, the second mapping method is selected for data mapping.

6. The intelligent supervision system for food safety information traceability according to claim 5, characterized in that: The specific analysis process of the data complexity factor of the target platform in the first cycle is as follows: The data reception process parameters of the target platform include the protocol entropy value of the target platform in the first cycle, the graph calculation complexity of the target platform in the first cycle, and the data volume growth rate of the target platform in the first cycle; The influence degrees of the ratio between the protocol entropy value and the defined protocol entropy value on the data complexity factor, the ratio between the graph calculation complexity and the defined graph calculation complexity on the data complexity factor, and the ratio between the data volume growth rate and the defined data volume growth rate on the data complexity factor are summarized. At the same time, the influence degree of the processing efficiency index on the data complexity factor is introduced and summarized again to obtain the data complexity factor; The data complexity factor of the target platform in the first cycle represents the complexity of the data received by the target platform in the first cycle.

7. The intelligent supervision system for food safety information traceability according to claim 1, characterized in that: The determination of whether to adjust the mapping process of the target platform is as follows. The specific determination process is: By evaluating the mapping parameters of the target platform, the mapping stability coefficient of the target platform within the mapping supervision period is obtained and compared with the reference interval of the mapping stability coefficient. If the mapping stability coefficient of the target platform within the mapping supervision period belongs to the reference interval of the mapping stability coefficient, it is determined that the mapping process of the target platform will not be adjusted; If the mapping stability coefficient of the target platform within the mapping supervision period does not belong to the reference interval of the mapping stability coefficient, it is determined that the mapping process of the target platform will be adjusted.

8. The intelligent supervision system for food safety information traceability according to claim 7, characterized in that: The adjustment of the mapping process of the target platform is specifically as follows: If the mapping stability coefficient of the target platform within the mapping supervision period is greater than the maximum value of the reference interval of the mapping stability coefficient, the difference between the mapping stability coefficient of the target platform within the mapping supervision period and the maximum value of the reference interval of the mapping stability coefficient is processed, and the processing result is processed by a ratio with the maximum value of the reference interval of the mapping stability coefficient. Finally, the first mapping stability coefficient deviation value of the target platform within the mapping supervision period is obtained, and the second increase coefficient is matched from the information database to increase the concurrent mapping data volume of the target platform. At the same time, the duration corresponding to the mapping supervision period is increased according to the second increase coefficient; If the mapping stability coefficient of the target platform within the mapping supervision period is less than the minimum value of the reference interval of the mapping stability coefficient, the mapping data of the target platform within the mapping supervision period is withdrawn. At the same time, the difference between the minimum value of the reference interval of the mapping stability coefficient and the mapping stability coefficient of the target platform within the mapping supervision period is processed, and the processing result is processed by a ratio with the minimum value of the reference interval of the mapping stability coefficient. Finally, the second mapping stability coefficient deviation value of the target platform within the mapping supervision period is obtained, and the second decrease coefficient is matched from the information database to reduce the concurrent mapping data volume of the target platform, and the duration corresponding to the mapping supervision period is reduced according to the second decrease coefficient. At the same time, according to the second mapping stability coefficient deviation value of the target platform within the mapping supervision period, the data cleaning volume of the target platform is obtained for cleaning, so as to remap the mapping data of the target platform within the mapping supervision period.

9. The intelligent supervision system for food safety information traceability according to claim 8, characterized in that: The specific evaluation process of the mapping stability coefficient of the target platform within the mapping supervision period is as follows: The mapping parameters of the target platform include the parallel efficiency of the target platform within the mapping supervision period, the data mapping speed deviation value of the target platform within the mapping supervision period, and the average data mapping delay duration of the target platform within the mapping supervision period; Obtain the processing efficiency index of the target platform within the mapping supervision period and the data complexity factor of the target platform within the mapping supervision period; Summarize once the influence degree of the ratio between the parallel efficiency and the defined parallel efficiency on the mapping stability coefficient, the influence degree of the ratio between the data mapping speed deviation value and the defined data mapping speed deviation value on the mapping stability coefficient, and the influence degree of the ratio between the average data mapping delay duration and the defined average data mapping delay duration on the mapping stability coefficient. Then summarize twice the influence degree of the processing efficiency index on the mapping stability coefficient and the influence degree of the data complexity factor on the mapping stability coefficient. Finally, couple the results of the first summary and the second summary to obtain the mapping stability coefficient; The mapping stability coefficient of the target platform within the mapping supervision period characterizes the mapping stability degree of the target platform within the mapping supervision period.

10. A method for applying the intelligent supervision system for food safety information traceability as described in any one of claims 1-9, characterized in that: Including: Step 1: Mark the food safety information traceability platform as the target platform, monitor and analyze the instruction processing process parameters of the target platform, and initialize the mapping process of the target platform; Step 2: Collect and analyze the data reception process parameters of the target platform, and intelligently match the data mapping speed of the target platform; Step 3: Supervise and evaluate the mapping parameters of the target platform to determine whether to adjust the mapping process of the target platform.

Images