Traceability tracking platform construction method and system based on multi-source heterogeneous data fusion

Abstract

The invention relates to the technical field of traceability tracking, in particular to a traceability tracking platform construction method and system based on multi-source heterogeneous data fusion, and the method comprises the steps: collecting operation state index parameters of a target traceability tracking platform in a historical period; the operation state index characterization value is analyzed; determining whether the operation efficiency of the target traceability tracking platform meets the standard; in response to the condition that the operation efficiency of the target traceability tracking platform meets the standard, collecting risk assessment parameters of the target traceability tracking platform in a historical period; analyzing the risk assessment characterization value; determining whether the target traceability tracking platform meets a risk assessment standard; and determining a processing strategy based on a difference result between the risk assessment characterization value and a predetermined risk assessment characterization threshold value in response to the fact that the target traceability tracking platform does not conform to the risk assessment standard. According to the invention, the accuracy and response efficiency of the traceability tracking platform are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traceability, and in particular to a traceability platform construction method and system based on multi-source heterogeneous data fusion. BACKGROUND

[0002] A civil material traceability platform plays a vital role in the fields of food safety, emergency material allocation, market supply guarantee, etc. Its core task is to integrate heterogeneous data sources from multiple links such as production, processing, logistics, and sales, such as sensor data, business system records, and Internet of Things device information, to form a complete and reliable digital footprint of civil materials throughout their life cycle, so as to realize rapid source tracing, accurate flow monitoring, and efficient responsibility definition, thereby safeguarding public safety and market stability. The existing technology has obvious limitations in monitoring and evaluating the traceability platform: the evaluation dimension is single, relying only on isolated indicators such as response time, lacking multi-dimensional comprehensive quantitative analysis of data coverage, cache hit rate, and response time, resulting in one-sided overall efficiency evaluation; the evaluation logic lacks stratification, and performance monitoring is separated from data quality and business risk verification, which cannot effectively guarantee the credibility of traceability results while ensuring operational efficiency; at the same time, the evaluation standard is rigid, and it is difficult to adapt to dynamic business load and data source changes, which is prone to false positives and false negatives and lacks system adaptability, together leading to problems such as inaccurate evaluation, delayed risk warning, and improper operation and decision-making in complex scenarios, ultimately affecting traceability accuracy and overall response efficiency.

[0003] Chinese patent publication CN115734158A discloses a material traceability monitoring system, which includes a sensing tag, a sub-server arranged at an auxiliary base station, and a main server arranged at an ultra-high frequency base station; the sensing tag is used to store a unique ID number, is arranged in a material package, and senses environmental information of the material; the sub-server is used to accept a main server signal, frequency-converts and forwards an identification collection command to the sensing tag covered by an antenna electromagnetic wave, and transmits sensing tag information to the main server; the main server transmits an identification collection command to the auxiliary base station, and processes collection data transmitted by the sensing tag. The present application combines the auxiliary base station and the sensing tag to position the material location and upload it to a remote main server, so that the material can be traced. Various environmental sensors are arranged on the sensing tag to monitor the material state and prevent the occurrence of dampness and fire.

[0004] Chinese patent publication No. CN113362077A discloses a product traceability system based on a blockchain, which includes a block storage platform, a running sound acquisition module, a fault traceability analysis module, a parameter evolution tracking module, a predictive data modeling module, a running environment interference evaluation module, and a traceability tracking management platform. The product traceability system based on the blockchain can accurately analyze whether the fault source of the engine is from the manufacturing process or improper use of the engine, realize accurate fault source positioning, and adjust the production and processing parameters according to the faults generated during the manufacturing process to reduce the fault interference caused by the engine processing process, greatly improve the process requirements during engine production, reduce engine faults caused by production and manufacturing, and improve the service life of the engine.

[0005] Therefore, the prior art has the following problems: The existing consumer goods traceability tracking platform mainly relies on isolated static indicators, lacks multi-dimensional indicator fusion calculation, hierarchical cascade verification mechanism, and dynamic adjustment capability, resulting in one-sided evaluation, delayed risk response, and insufficient system adaptability, thereby reducing the accuracy and response efficiency of the traceability tracking platform. SUMMARY

[0006] Therefore, the present application provides a traceability tracking platform construction method and system based on multi-source heterogeneous data fusion to overcome the problem that the existing consumer goods traceability tracking platform mainly relies on isolated static indicators, lacks multi-dimensional indicator fusion calculation, hierarchical cascade verification mechanism, and dynamic adjustment capability, resulting in one-sided evaluation, delayed risk response, and insufficient system adaptability, thereby reducing the accuracy and response efficiency of the traceability tracking platform.

[0007] To achieve the purpose, the present application provides a traceability tracking platform construction method based on multi-source heterogeneous data fusion, comprising: Collecting the running state indicator parameters of the target traceability tracking platform in the historical period; Analyzing the running state indicator representation value based on the running state indicator parameters; Determining whether the running efficiency of the target traceability tracking platform meets the standard based on the comparison result of the running state indicator representation value and the predetermined running state indicator representation threshold value; In response to the target traceability tracking platform running efficiency meeting the standard, collecting the risk assessment parameters of the target traceability tracking platform in the historical period; Analyzing the risk assessment representation value based on the risk assessment parameters; Determining whether the target traceability tracking platform meets the risk assessment standard based on the difference result of the risk assessment representation value and the predetermined risk assessment representation threshold value; determining a processing strategy based on a difference between the risk assessment characterization value and a predetermined risk assessment characterization threshold value, in response to the target traceability platform not meeting the risk assessment standard, to determine an adjustment range of the operating state characterization threshold value; The operating state indicator parameter includes data coverage, cache hit rate, and response time. The risk assessment parameter includes data deduplication accuracy and abnormal data detection rate.

[0008] Further, the process of analyzing the operating state indicator characterization value includes: Collecting data coverage, cache hit rate, and response time within a historical period of the target traceability platform; Calculating the ratio of data coverage to a predetermined data coverage threshold value as a first state limiting characterization parameter; Calculating the ratio of cache hit rate to a predetermined cache hit rate threshold value as a second state limiting characterization parameter; Calculating the ratio of a predetermined response time threshold value to the response time as a third state limiting characterization parameter; Summing the first, second, and third state limiting characterization parameters to determine the operating state indicator characterization value.

[0009] Further, the process of determining whether the target traceability platform operating efficiency meets the standard based on the comparison result of the operating state indicator characterization value and the predetermined operating state indicator characterization threshold value includes: Extracting the comparison result of the operating state indicator characterization value and the predetermined operating state indicator characterization threshold value; If the operating state indicator characterization value is greater than the predetermined operating state indicator characterization threshold value, it is determined that the target traceability platform operating efficiency meets the standard.

[0010] Further, the process of determining whether the target traceability platform operating efficiency meets the standard based on the comparison result of the operating state indicator characterization value and the predetermined operating state indicator characterization threshold value includes: Extracting the comparison result of the operating state indicator characterization value and the predetermined operating state indicator characterization threshold value; If the operating state indicator characterization value is less than or equal to the predetermined operating state indicator characterization threshold value, it is determined that the target traceability platform operating efficiency does not meet the standard.

[0011] Further, the process of analyzing the risk assessment parameter to analyze the risk assessment characterization value includes: Collecting data deduplication accuracy and abnormal data detection rate within a historical period of the target traceability platform; Calculating the ratio of data deduplication accuracy to a predetermined data deduplication accuracy threshold value as a first risk limiting characterization parameter; a ratio of the predetermined abnormal data detection rate threshold value and the abnormal data detection rate is calculated to determine a second risk limiting characterization parameter; the first risk limiting characterization parameter and the second risk limiting characterization parameter are summed to determine the risk assessment characterization value.

[0012] Further, the process of determining whether the target traceability platform meets the risk assessment standard based on the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value includes: the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is calculated; If the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is greater than a predetermined difference threshold value, it is determined that the target traceability platform meets the risk assessment standard.

[0013] Further, the process of determining whether the target traceability platform meets the risk assessment standard based on the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value includes: the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is calculated; If the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is less than or equal to a predetermined difference threshold value, it is determined that the target traceability platform does not meet the risk assessment standard.

[0014] Further, the process of determining the processing strategy based on the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value includes: the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is calculated; If the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is less than or equal to a predetermined difference threshold value, it is determined that the operating state indicator characterization threshold value is adjusted.

[0015] Further, the process of determining the adjustment range of the operating state indicator characterization threshold value based on the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value includes: the absolute value of the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is calculated; a corresponding target adjustment coefficient is determined based on the absolute value of the difference; an adjustment direction is determined based on the difference, and the operating state indicator characterization threshold value is adjusted accordingly according to the target adjustment range.

[0016] Further, the system of the traceability platform construction method based on multi-source heterogeneous data fusion includes: a data acquisition module for acquiring operating state indicator parameters and risk assessment parameters in a historical period of the target traceability platform; a data analysis module connected with the data collection module, configured to analyze the operation state index characteristic value and the risk assessment characteristic value; a state assessment module connected with the data analysis module, configured to determine whether the operation efficiency of the target traceability platform meets the standard; if the operation state index characteristic value is greater than the predetermined operation state index characteristic threshold value, it is determined that the operation efficiency of the target traceability platform meets the standard; if the operation state index characteristic value is less than or equal to the predetermined operation state index characteristic threshold value, it is determined that the operation efficiency of the target traceability platform does not meet the standard; a risk verification module connected with the state assessment module, configured to determine whether the target traceability platform meets the risk assessment standard in response to the operation efficiency of the target traceability platform meeting the standard; if the difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value is greater than the predetermined difference threshold value, it is determined that the target traceability platform meets the risk assessment standard; if the difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value is less than or equal to the predetermined difference threshold value, it is determined that the target traceability platform does not meet the risk assessment standard; an intelligent decision module connected with the risk verification module, configured to determine a processing strategy based on the difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value in response to the target traceability platform not meeting the risk assessment standard; determine the adjustment range of the operation state characteristic threshold value based on the difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value; wherein, the operation state index parameter includes data coverage, cache hit rate, response time; the risk assessment parameter includes data deduplication accuracy, abnormal data detection rate.

[0017] Compared with the prior art, the present application has the beneficial effects that the present application provides a traceability tracking platform construction method and system based on multi-source heterogeneous data fusion. By constructing a closed-loop, intelligent evaluation and optimization system, multi-dimensional heterogeneous indicators such as data coverage, cache hit rate and response time are fused and normalized calculation is performed, panoramic and quantitative evaluation of platform running efficiency is realized, and the prior standard triggering condition of running efficiency is innovatively introduced. The risk evaluation of data deduplication accuracy and abnormal data detection rate is cascaded, thereby overcoming the disadvantages of single dimension, performance and quality disconnection in traditional monitoring; based on the difference analysis of the running state and risk evaluation representation value and the threshold value, the simple judgment of whether it is abnormal is realized to the precise quantification of the deviation degree, and the automatic generation of the hierarchical processing strategy and the dynamic self-adaptive adjustment of the running threshold value are driven, so that the system has the ability to perceive business fluctuations, predict potential risks and optimize itself, realizing the paradigm shift from passive response to active regulation.

[0018] Especially, by ratio calculation of data coverage, cache hit rate and response time multi-dimensional heterogeneous indicators and preset threshold values respectively, and normalization to dimensionless state limiting representation parameters, a unified running state indicator representation value is generated by fusion, realizing global, standardized comprehensive quantitative evaluation of platform running efficiency, overcoming the problem of different dimensions in traditional multi-index monitoring, which is difficult to determine as a whole; on this basis, by comparing the comprehensive representation value with a single preset threshold value to determine whether the running efficiency meets the standard, the complex multi-dimensional decision is simplified to an efficient single judgment, which not only greatly improves the evaluation efficiency, but also ensures the comprehensiveness and reliability of the judgment conclusion, effectively avoiding the risk of misjudgment caused by the fact that a single indicator meets the standard, thereby providing a solid and reliable decision basis for subsequent risk evaluation.

[0019] Especially, by standardizing and fusing the two key risk indicators of data deduplication accuracy and abnormal data detection rate, a unified risk evaluation representation value is generated, thereby realizing fine and quantitative evaluation of platform data quality risk; further, by introducing a secondary comparison mechanism of the difference between the representation value and the preset threshold value, the risk judgment is upgraded from static eligibility check to dynamic deviation degree grading, significantly improving the sensitivity of risk identification and the accuracy of decision basis; finally, based on this quantitative difference, a closed-loop adaptive adjustment logic is driven, through dynamic coefficient mapping and target amplitude calculation, intelligent reverse adjustment of the running efficiency threshold value is realized, so that the system can achieve dynamic balance between running performance and data quality, thereby completing the complete closed loop from risk perception to automatic optimization of system parameters, fundamentally enhancing the autonomy, reliability and long-term stability of the platform.

[0020] Especially, the application realizes the process of data collection, multi-dimensional analysis, state evaluation, risk verification and intelligent decision-making through a modular architecture, realizes the key constraints of prior standard of operation efficiency by a series of work flow, ensures the effective allocation of evaluation resources and logical rigor; relies on the quantitative data driving mechanism of the whole link, automates and objectivizes the processes of heterogeneous index fusion, difference analysis and threshold comparison, significantly reduces the dependence on manual intervention; through the intelligent decision-making module, generates the treatment strategy according to the quantitative results and feeds back the system threshold, forms a complete evaluation, decision-making and adjustment closed loop, makes the system evolve into an organic whole that can dynamically balance operation efficiency and data quality and has the ability of continuous self-adaptive optimization, fundamentally improves the autonomy, reliability and long-term stability of the traceability platform. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 A step flowchart of the traceability tracking platform construction method based on multi-source heterogeneous data fusion of the embodiment of the application is shown in the figure. Figure 2 A determination logic diagram for determining whether the operation efficiency of the target traceability tracking platform meets the standard is provided for the embodiment of the application. Figure 3 A determination logic diagram for determining whether the target traceability tracking platform meets the risk evaluation standard is provided for the embodiment of the application. Figure 4 A structure block diagram of the traceability tracking platform construction system based on multi-source heterogeneous data fusion of the embodiment of the application. DETAILED DESCRIPTION

[0022] In order to make the purpose and advantages of the application clearer and more apparent, the application will be further described below with reference to the embodiments; it should be understood that the specific embodiments described herein are only used to explain the application and do not limit the application.

[0023] The preferred embodiments of the application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that the embodiments are only used to explain the technical principles of the application and do not limit the protection scope of the application.

[0024] Please refer to Figure 1 The figure is a step flowchart of the traceability tracking platform construction method based on multi-source heterogeneous data fusion of the embodiment of the application, and the application provides a traceability tracking platform construction method based on multi-source heterogeneous data fusion, which comprises: Step S1, collecting the operation state index parameters in the historical period of the target traceability tracking platform; Step S2, analyzing the operation state index representation value based on the operation state index parameters; Step S3, determining whether the target traceability tracking platform running efficiency meets the standard based on the comparison result of the running state index characterization value and the predetermined running state index characterization threshold value; Step S4, in response to the target traceability tracking platform running efficiency meeting the standard, collecting risk assessment parameters in the historical period of the target traceability tracking platform; and analyzing a risk assessment characterization value based on the risk assessment parameters; Step S5, determining whether the target traceability tracking platform meets the risk assessment standard based on the difference result of the risk assessment characterization value and the predetermined risk assessment characterization threshold value; Step S6, in response to the target traceability tracking platform not meeting the risk assessment standard, determining a processing strategy based on the difference result of the risk assessment characterization value and the predetermined risk assessment characterization threshold value to determine the adjustment range of the running state characterization threshold value; The running state index parameters include data coverage, cache hit rate, and response time. The risk assessment parameters include data deduplication accuracy and abnormal data detection rate.

[0025] In the embodiment, through the forced hierarchical progression logic from the prior evaluation of running efficiency to the risk verification of data quality, an evaluation sequence with clear target and efficient resource allocation is constructed, ensuring that the system always pursues reliable quality on the basis of performance meeting the standard; through the introduction of comparison and judgment mechanism based on quantitative characterization value and difference at each key node, the complex multidimensional state is converted into objective and measurable decision basis, making the whole process realize the objectification and automation of the whole link from data acquisition to conclusion output; finally, the process forms a dynamic feedback loop from risk perception to parameter optimization by directly feeding back the risk assessment results to drive the generation of processing strategy and threshold adjustment, making the system no longer a passive monitoring tool, but an adaptive intelligent agent with the ability of continuous self-adjustment and dynamic balance between running efficiency and data quality, thereby significantly improving the overall robustness and long-term autonomy level of the traceability platform.

[0026] Specifically, the process of analyzing the running state index characterization value by the running state index parameter includes: Collecting data coverage, cache hit rate, and response time in the historical period of the target traceability tracking platform; Calculating the ratio of the data coverage to the predetermined data coverage threshold value as a first state limited characterization parameter; Calculating the ratio of the cache hit rate to the predetermined cache hit rate threshold value as a second state limited characterization parameter; Calculating the ratio of the predetermined response time threshold value to the response time as a third state limited characterization parameter; The first state limiting characterization parameter, the second state limiting characterization parameter and the third state limiting characterization parameter are summed to determine the operation state index characterization value.

[0027] In the embodiment, the predetermined data coverage threshold, cache hit rate threshold and response duration threshold are obtained in advance, all data coverage, cache hit rate and response duration of the target traceability platform within 3 months of stable operation are collected, and the average values thereof are determined as the data coverage threshold, cache hit rate threshold and response duration threshold.

[0028] In the embodiment, the data coverage is dependent on periodic comparison of actual business data recorded in the platform with an authoritative metadata list from a production execution system or an enterprise resource planning system, and is calculated by deploying a probe to listen to data arrival events at key nodes of a data pipeline; the cache hit rate is measured by embedding monitoring code in a cache client or an API gateway layer of an application program, and the number of requests directly responded by the cache service and the number of requests requiring access to a backend data source are counted respectively; the response duration is mainly calculated by capturing high-precision timestamps of requests at the entrance and exit of the system to calculate the full-link delay by means of a distributed link tracking technology; the methods collectively constitute a quantitative monitoring basis for data integrity, internal performance efficiency and external user experience of the platform, and provide accurate and reliable raw data input for subsequent index fusion analysis and intelligent evaluation.

[0029] In the embodiment, the calculation formula of the data coverage is: Data coverage = number of entities with complete key node data records / total number of traced entities In the embodiment, the calculation formula of the cache hit rate is: Cache hit rate = cache hit times / (cache hit times + cache miss times) In the embodiment, the calculation formula of the response duration is: Response duration = timestamp of request processing completion - timestamp of request arrival at the system In the embodiment, by selecting data coverage rate, cache hit rate and response time as core parameters, the overall beneficial effect is fundamentally supported: in the evaluation level, the three from the three non-substitutable dimensions of data integrity, system internal efficiency and terminal user experience provide a comprehensive and quantifiable perception basis for platform health, so that the subsequent normalized fusion and comprehensive representation value calculation can objectively and completely describe the running state, overcoming the one-sidedness of traditional single index evaluation; in the regulation level, the continuous collection and analysis of these parameters are the source signal and scientific basis for driving the operation of the efficiency evaluation, risk assessment and threshold dynamic adjustment intelligent closed-loop feedback mechanism, so that the system can adaptively balance performance and quality targets based on quantified deviation; finally in the business level, the parameter system setting directly anchors the core value pursuit of the traceability platform, which guarantees the traceability credibility by improving the coverage rate, and guarantees the service efficiency by optimizing the hit rate and response time, thereby realizing the comprehensive performance of improving business accuracy, enhancing system resilience and optimizing user experience.

[0030] Please refer to Figure 2 As shown in the figure, the embodiment of the present application provides a determination logic diagram for determining whether the running efficiency of the target traceability platform meets the standard, and the process of determining whether the running efficiency of the target traceability platform meets the standard comprises: Extracting the comparison result of the running state index representation value and the predetermined running state index representation threshold value; If the running state index representation value is greater than the predetermined running state index representation threshold value, it is determined that the running efficiency of the target traceability platform meets the standard; If the running state index representation value is less than or equal to the predetermined running state index representation threshold value, it is determined that the running efficiency of the target traceability platform does not meet the standard.

[0031] In the embodiment, the predetermined running state index representation threshold value is obtained in advance, all running state index representation values of the target traceability platform within 3 months of stable operation are collected, and the average value is calculated as the running state index representation threshold value, the predetermined running state index representation threshold value in the embodiment is selected in the interval [3.05, 3.35], and the predetermined running state index representation threshold value in the embodiment is preferably 3.15.

[0032] In the embodiment, by condensing the multi-dimensional complex platform running state into a single comprehensive characteristic value and directly comparing it with the preset threshold, the evaluation conclusion is completely objectified and the decision-making process is extremely simplified, providing a clear and reliable instruction basis for automated operation and maintenance; the predetermined threshold serves as a clear quality benchmark, providing a precise target orientation for performance optimization; this decision-making link, as the key control gate of the entire evaluation system, ensures that subsequent risk assessment and other in-depth analysis are triggered only when the platform's basic performance is stable, thereby achieving rational allocation of system resources and rigorous stratification of the evaluation process, and ultimately building an efficient, reliable and goal-oriented intelligent evaluation closed loop.

[0033] Specifically, the process of analyzing the risk assessment characteristic value by the risk assessment parameter includes: Collecting the data deduplication accuracy and abnormal data detection rate of the target traceability platform in the historical period; Calculating the ratio of the data deduplication accuracy to the predetermined data deduplication accuracy threshold to determine the first risk limiting characteristic parameter; Calculating the ratio of the predetermined abnormal data detection rate threshold to the abnormal data detection rate to determine the second risk limiting characteristic parameter; Summing the first risk limiting characteristic parameter and the second risk limiting characteristic parameter to determine the risk assessment characteristic value.

[0034] In the embodiment, the predetermined data deduplication accuracy threshold and the abnormal data detection rate threshold are obtained in advance, the data deduplication accuracy and the abnormal data detection rate of the target traceability platform within 3 months of stable operation are collected, and their average values are calculated as the data deduplication accuracy threshold and the abnormal data detection rate threshold.

[0035] In the embodiment, the data deduplication accuracy is obtained by establishing an artificial annotation benchmark through sampling of historical data and comparing it with the system deduplication result to calculate the precision rate; the abnormal data detection rate is obtained by injecting a predetermined abnormal sample into the data stream and calculating the recall rate by counting the system recognition proportion, both of which quantize the data management and risk discovery ability of the platform from the accuracy and coverage dimensions through repeatable experiments, providing an auditable measurement basis for subsequent analysis.

[0036] In the embodiment, the calculation formula of the data deduplication accuracy is: Data deduplication accuracy = number of records correctly deduplicated by the system / total number of records confirmed as duplicates by manual verification In the embodiment, the calculation formula of the abnormal data detection rate is: Abnormal data detection rate = number of abnormal data items successfully detected by the system / total number of known abnormal items injected In the embodiment, through the establishment of a multi-dimensional quantitative and cascade verification evaluation mechanism, panoramic diagnosis of the platform health is realized; and based on the adaptive adjustment driven by the difference value, an intelligent closed loop is formed, so that the system can dynamically balance and autonomously optimize between performance and quality; finally, the data accuracy and system response efficiency are simultaneously improved at the business level, and the reliability and service capability of the traceability platform are comprehensively enhanced.

[0037] Referring to Figure 3 As shown in the figure, the embodiment of the present application provides a determination logic diagram for determining whether the target traceability platform meets the risk assessment standard, and the process of determining whether the target traceability platform meets the risk assessment standard comprises: calculating the difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value; If the difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value is greater than the predetermined difference threshold value, it is determined that the target traceability platform meets the risk assessment standard; If the difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value is less than or equal to the predetermined difference threshold value, it is determined that the target traceability platform does not meet the risk assessment standard.

[0038] In the embodiment, the predetermined risk assessment characteristic threshold value is obtained in advance, all risk assessment characteristic values of the target traceability platform within a stable running period of 3 months are collected, and the average value thereof is calculated as the predetermined risk assessment characteristic threshold value, the predetermined risk assessment characteristic threshold value in the embodiment is selected within the interval [2.05, 2.35], and the predetermined risk assessment characteristic threshold value in the embodiment is preferably 2.15.

[0039] In the embodiment, the predetermined difference threshold value is obtained in advance, the difference between all risk assessment characteristic values of the target traceability platform within a stable running period of 3 months and the predetermined risk assessment characteristic threshold value is calculated, and the average value thereof is calculated as the difference threshold value, the predetermined difference threshold value in the embodiment is selected within the interval [0.05, 0.35], and the predetermined difference threshold value in the embodiment is preferably 0.15.

[0040] In the embodiment, through quantitative difference analysis and secondary threshold determination, accurate risk grading and intelligent decision-making are realized: the difference calculation accurately measures the deviation degree, replacing the traditional binary judgment; the independent difference threshold value clearly divides the risk levels, supporting differentiated disposal strategies; finally, the quantitative result directly drives the dynamic adjustment of system parameters, so that the platform can realize adaptive balance between performance and quality targets, and the risk assessment is changed from a static check point to a core decision-making node driving the continuous optimization of the system.

[0041] Specifically, the process of determining the processing strategy based on the difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value comprises: The difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value is calculated. If the difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value is less than or equal to a predetermined difference threshold value, it is determined that the adjustment range of the operating state index characteristic threshold value is adjusted.

[0042] In the embodiment, the dynamic adjustment of the operating state threshold value driven by the risk assessment difference value realizes an intelligent closed loop from risk identification to system parameter optimization, and this mechanism enables the system to adaptively balance the operating efficiency and the data quality target, reversely adjusts the performance threshold according to the risk level, and thus converts a static evaluation system into an intelligent control system driving self-optimization of the platform.

[0043] Specifically, the process that the difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value determines the adjustment range of the operating state index characteristic threshold value includes: The absolute value of the difference between the risk assessment characteristic value and the predetermined risk assessment characteristic threshold value is calculated. A target adjustment coefficient corresponding to the absolute value of the difference is determined based on the absolute value of the difference. An adjustment direction is determined based on the difference, and the operating state index characteristic threshold value is adjusted accordingly according to the target adjustment range.

[0044] In the embodiment, by defining the corresponding relationship between different risk difference absolute values and adjustment coefficients, a nonlinear control strategy that the greater the risk deviation, the stronger the adjustment strength is coded; and the target adjustment coefficient is a real-time multiplier determined by querying the mapping table according to the risk difference calculated in real time in each evaluation, and the value of the target adjustment coefficient dynamically changes with the risk degree. The target adjustment coefficient is obtained in advance, and the predetermined target adjustment coefficient in the embodiment is selected in the interval [1.05, 2.35].

[0045] In the embodiment, the quantitative process converts the abstract risk judgment into specific parameter control instructions, so that the system can dynamically relax or tighten the compliance requirements for operating efficiency according to the risk level, thereby realizing a closed-loop adaptive balance between operating performance and data quality, and embodying the intelligent decision-making ability from risk perception to system self-optimization.

[0046] Please refer to Figure 4 The structure block diagram of the traceability tracking platform construction system based on multi-source heterogeneous data fusion in the embodiment of the application is shown in the figure, and the traceability tracking platform construction system based on multi-source heterogeneous data fusion is also provided, which includes: A data acquisition module is used to acquire operating state index parameters and risk assessment parameters in a historical period of the target traceability tracking platform. A data analysis module is connected with the data acquisition module and is used to analyze operating state index characteristic values and risk assessment characteristic values. a state evaluation module connected with the data analysis module to determine whether the target traceability platform operating efficiency meets the standard; If the operating state index representation value is greater than the predetermined operating state index representation threshold value, it is determined that the target traceability platform operating efficiency meets the standard. If the operating state index representation value is less than or equal to the predetermined operating state index representation threshold value, it is determined that the target traceability platform operating efficiency does not meet the standard. a risk verification module connected with the state evaluation module to determine whether the target traceability platform meets the risk assessment standard in response to the target traceability platform operating efficiency meeting the standard; If the difference between the risk assessment representation value and the predetermined risk assessment representation threshold value is greater than the predetermined difference threshold value, it is determined that the target traceability platform meets the risk assessment standard. If the difference between the risk assessment representation value and the predetermined risk assessment representation threshold value is less than or equal to the predetermined difference threshold value, it is determined that the target traceability platform does not meet the risk assessment standard. an intelligent decision module connected with the risk verification module to determine a processing strategy based on the difference between the risk assessment representation value and the predetermined risk assessment representation threshold value in response to the target traceability platform not meeting the risk assessment standard. determine the adjustment range of the operating state representation threshold value based on the difference between the risk assessment representation value and the predetermined risk assessment representation threshold value. The operating state index parameters include data coverage, cache hit rate, and response time. The risk assessment parameters include data deduplication accuracy and abnormal data detection rate.

[0047] In the embodiment, the modular architecture realizes the process-based collaboration of data collection, multi-dimensional analysis, state evaluation, risk verification and intelligent decision-making, and the serial work flow forces the key constraints of prior standard of operating efficiency to be met, ensuring effective allocation of evaluation resources and logical rigor. Relying on the full-link quantitative data-driven mechanism, the processes of heterogeneous index fusion, difference analysis and threshold comparison are automated and objectified, significantly reducing the dependence on manual intervention. Through the intelligent decision module, the treatment strategy is generated according to the quantitative results and the system threshold is fed back to form a complete evaluation, decision-making and adjustment closed loop, so that the system evolves into an organic whole that can dynamically balance operating efficiency and data quality and has the ability of continuous self-adaptive optimization, fundamentally improving the autonomy, reliability and long-term stability of the traceability platform.

[0048] So far, the technical solutions of the present application have been described in combination with the embodiments shown in the drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to the specific embodiments of the embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after the changes or replacements of the embodiments will fall within the protection scope of the present application.

Claims

1. A method for constructing a traceability tracking platform based on multi-source heterogeneous data fusion, characterized in that, The method comprises the following steps: collecting running state index parameters in a historical period of a target traceability platform; analyzing running state index representation values based on the running state index parameters; determining whether the running efficiency of the target traceability platform meets the standard based on the comparison result of the running state index representation values and the predetermined running state index representation threshold value; in response to the running efficiency of the target traceability platform meeting the standard, collecting risk assessment parameters in the historical period of the target traceability platform; analyzing risk assessment representation values based on the risk assessment parameters; determining whether the target traceability platform meets the risk assessment standard based on the difference result of the risk assessment representation values and the predetermined risk assessment representation threshold value; in response to the target traceability platform not meeting the risk assessment standard, determining a processing strategy based on the difference result of the risk assessment representation values and the predetermined risk assessment representation threshold value to determine the adjustment range of the running state representation threshold value; wherein the running state index parameters include data coverage, cache hit rate, and response time; the risk assessment parameters include data deduplication accuracy and abnormal data detection rate. 2.The multi-source heterogeneous data fusion based traceability tracking platform construction method according to claim 1, characterized in that, The process of analyzing running state index representation values based on the running state index parameters comprises: collecting data coverage, cache hit rate, and response time in a historical period of a target traceability platform; calculating the ratio of data coverage to the predetermined data coverage threshold value as a first state limited representation parameter; calculating the ratio of cache hit rate to the predetermined cache hit rate threshold value as a second state limited representation parameter; calculating the ratio of the predetermined response time threshold value to the response time as a third state limited representation parameter; summing the first, second, and third state limited representation parameters to determine the running state index representation value. 3.The multi-source heterogeneous data fusion based traceability tracking platform construction method of claim 2, characterized in that, The process of determining whether the running efficiency of the target traceability platform meets the standard based on the comparison result of the running state index representation values and the predetermined running state index representation threshold value comprises: extracting the comparison result of the running state index representation values and the predetermined running state index representation threshold value; if the running state index representation value is greater than the predetermined running state index representation threshold value, it is determined that the running efficiency of the target traceability platform meets the standard.

4. The method according to claim 3, wherein, The process of determining whether the running efficiency of the target traceability platform meets the standard based on the comparison result of the running state index representation values and the predetermined running state index representation threshold value comprises: extracting the comparison result of the running state index representation values and the predetermined running state index representation threshold value; if the running state index representation value is less than or equal to the predetermined running state index representation threshold value, it is determined that the running efficiency of the target traceability platform does not meet the standard.

5. The method according to claim 4, wherein, The process of analyzing risk assessment representation values based on the risk assessment parameters comprises: collecting data deduplication accuracy and abnormal data detection rate in a historical period of a target traceability platform; calculating the ratio of data deduplication accuracy to the predetermined data deduplication accuracy threshold value to determine a first risk limited representation parameter; calculating the ratio of the predetermined abnormal data detection rate threshold value to the abnormal data detection rate to determine a second risk limited representation parameter; The first risk limiting characterization parameter is summed with a second risk limiting characterization parameter to determine the risk assessment characterization value.

6. The method according to claim 5, wherein, The process of determining whether the target traceability platform meets the risk assessment standard based on the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value includes: calculating the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value; if the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is greater than a predetermined difference threshold value, it is determined that the target traceability platform meets the risk assessment standard.

7. The method according to claim 6, wherein, The process of determining whether the target traceability platform does not meet the risk assessment standard based on the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value includes: calculating the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value; if the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is less than or equal to a predetermined difference threshold value, it is determined that the target traceability platform does not meet the risk assessment standard. 8.The multi-source heterogeneous data fusion based traceability tracking platform construction method of claim 7, characterized in that, The process of determining the processing strategy based on the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value includes: calculating the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value; if the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is less than or equal to a predetermined difference threshold value, it is determined that the operating state indicator characterization threshold value is adjusted. 9.The multi-source heterogeneous data fusion based traceability tracking platform construction method of claim 8, characterized in that, The process of determining the adjustment amplitude of the operating state indicator characterization threshold value based on the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value includes: calculating the absolute value of the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value; determining the corresponding target adjustment coefficient based on the absolute value of the difference; determining the adjustment direction based on the difference, and adjusting the operating state indicator characterization threshold value by the target adjustment amplitude.

10. A system for constructing a method of tracing and tracking platform based on multi-source heterogeneous data fusion according to any one of claims 1 to 9, characterized in that, It includes: a data acquisition module for acquiring operating state indicator parameters and risk assessment parameters in a historical period of a target traceability platform; a data analysis module connected to the data acquisition module for analyzing operating state indicator characterization values and risk assessment characterization values; a state evaluation module connected to the data analysis module for determining whether the operating efficiency of the target traceability platform meets the standard; if the operating state indicator characterization value is greater than the predetermined operating state indicator characterization threshold value, it is determined that the operating efficiency of the target traceability platform meets the standard; if the operating state indicator characterization value is less than or equal to the predetermined operating state indicator characterization threshold value, it is determined that the operating efficiency of the target traceability platform does not meet the standard; a risk verification module connected to the state evaluation module for determining whether the target traceability platform meets the risk assessment standard in response to the operating efficiency of the target traceability platform meeting the standard; if the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is greater than a predetermined difference threshold value, it is determined that the target traceability platform meets the risk assessment standard. if the difference between the risk assessment characterization value and the predetermined risk assessment characterization threshold value is less than or equal to a predetermined difference threshold value, it is determined that the target traceability platform does not meet the risk assessment standard. An intelligent decision module connected with the risk verification module, configured to determine a processing strategy based on a difference between the risk assessment characteristic value and a predetermined risk assessment characteristic threshold value in response to the target traceability platform not meeting the risk assessment standard; determine an adjustment range of the operating state characteristic threshold value based on a difference between the risk assessment characteristic value and a predetermined risk assessment characteristic threshold value; The operating state index parameter includes data coverage, cache hit rate, response time length. The risk assessment parameter includes data deduplication accuracy, abnormal data detection rate.

Images