Marine sample management system based on artificial intelligence

Abstract

The invention relates to the technical field of data processing, and particularly discloses an artificial intelligence-based ocean sample management system, which can monitor and deeply analyze data processing efficiency parameters of a target platform in real time, further realizes accurate optimization of a data processing flow, remarkably improves the efficiency and accuracy of data processing, and improves the accuracy of data processing. The target platform continuously collects storage environment parameters of the ocean samples, deep analysis is carried out by means of an artificial intelligence algorithm, whether the storage parameters need to be corrected or not can be judged in time, it is ensured that the ocean sample data can dynamically sense environment changes and make adaptive adjustment, and meanwhile the system analyzes efficiency parameters according to the data to achieve the real-time monitoring of the ocean samples. According to the system, whether the attribute parameter storage strategy of the ocean sample is adjusted or not is intelligently judged, so that the reasonability and high efficiency of data storage are ensured, in addition, the system can further carry out detailed analysis on the attribute parameters of the ocean sample and implement scientific classification marking management, and great convenience is provided for follow-up research.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an artificial intelligence-based marine sample management system. Background Art

[0002] In recent years, artificial intelligence technology has made rapid progress, realizing intelligent management of the entire life cycle of marine samples, including sample collection information entry, storage environment monitoring, retrieval and query, sharing and utilization, and data analysis, providing more scientific and efficient decision-making basis for the rational development and utilization of marine resources and the protection of the marine environment.

[0003] For example, the invention patent with publication number CN111127041A discloses a blockchain-based test sample management method, equipment and medium. The method includes: determining a pre-created blockchain platform; determining the sample information of the sample sent for testing by the testing party, and writing it into the blockchain platform; receiving the transportation information of the sample sent by the transportation agency, and writing it into the blockchain platform; receiving the receipt information when the testing agency signs for the sample, and writing it into the blockchain platform; when the testing agency conducts testing, determining the sample testing process, and writing it into the blockchain platform; the entire process of the sample from transportation to testing is stored in the blockchain platform.

[0004] For example, the invention patent with announcement number CN112907050B announces a full-cycle management system for laboratory samples in the field of laboratory management technology, including a data acquisition module, a data transmission module, a data storage module and a full-cycle management platform, wherein: the data acquisition module reads and updates the data information on the sample label, and the data acquisition module transmits the data information on the sample label to the full-cycle management platform through the data transmission module; the full-cycle management platform collects the test data of each process of the sample through the interface, and the full-cycle management platform conducts a comprehensive analysis of the test data.

[0005] However, in the process of implementing the embodiments of the present application, it was found that the above-mentioned technology has at least the following technical problems: the existing sample management mainly focuses on the routine collection, storage, processing and data analysis of samples. Since no abnormal warning mechanism has been established, when managing the huge amount of marine sample data, the sample performance shows a gradual decline trend or sudden abnormalities occur. The management personnel cannot quickly obtain warning information, which directly affects the response speed to abnormal situations and may cause the abnormal situation to continue to deteriorate, thereby adversely affecting the subsequent experimental analysis, data interpretation and research conclusions. Summary of the Invention

[0006] In response to the shortcomings of the existing technology, the present invention provides an artificial intelligence-based marine sample management system that can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: an artificial intelligence-based marine sample management system, including a data processing optimization and adjustment module, which is used to mark the marine sample management platform as a target platform, monitor and analyze the data processing efficiency parameters of the target platform, and thus optimize the management of the data processing process of the target platform; a data correction management module, which is used to collect the storage environment parameters of marine samples in real time through the target platform, and analyze the storage environment parameters of marine samples based on artificial intelligence, so as to determine whether to correct the quality parameters of marine samples; a sample early warning management module, which is used to store the attribute parameters of marine samples through the target platform, and based on the data analysis efficiency parameters of the target platform, determine whether to adjust the storage process of marine samples, and at the same time analyze the attribute parameters of marine samples, classify and mark the marine samples, and determine whether to perform early warning management on the marine samples.

[0008] As a further solution, the data processing process of the target platform is optimized and managed. The specific optimization management process is as follows: by analyzing the data processing efficiency parameters of the target platform, the data processing efficiency index of the target platform is obtained, and the data correction coefficient is matched from the management database, so as to optimize the data analysis process of the target platform; the data processing efficiency threshold is extracted from the management database and compared with the data processing efficiency index of the target platform. If the data processing efficiency index of the target platform is greater than or equal to the data processing efficiency threshold, the data analysis process of the target platform is not managed; if the data processing efficiency index of the target platform is less than the data processing efficiency threshold, the data analysis process of the target platform is managed. The specific management process is: based on the data processing efficiency threshold and the data processing efficiency index of the target platform, the data processing efficiency deviation value of the target platform is obtained, and the number of data processing nodes of the target platform is initially increased. If the data processing efficiency index of the target platform is still less than the data processing efficiency threshold after the management is completed, the number of data processing nodes is continuously increased until the data processing efficiency index of the target platform is greater than or equal to the data processing efficiency threshold; if the continuous increase in the number of data processing nodes is equivalent to the preset definition of continuously increasing the number of data processing nodes, and at the same time the data processing efficiency index of the target platform is still less than the data processing efficiency threshold, the increase in the number of data processing nodes is stopped, and a data processing warning is issued.

[0009] As a further solution, it is determined whether to correct and manage the quality parameters of the marine samples. The specific determination process is: by analyzing the storage environment parameters of the marine samples by artificial intelligence, the abnormal variation coefficient of the storage environment to which the marine samples belong is obtained, the abnormal variation threshold is extracted from the management database, and compared with the abnormal variation coefficient of the storage environment to which the marine samples belong; if the abnormal variation coefficient of the storage environment to which the marine samples belong is less than or equal to the abnormal variation threshold, it is determined that the quality parameters of the marine samples are not corrected and managed; if the abnormal variation coefficient of the storage environment to which the marine samples belong is greater than the abnormal variation threshold, it is determined that the quality parameters of the marine samples are corrected and managed. The specific correction management refers to: the quality parameters of the marine samples include the quality index decay rate of the marine samples, based on the abnormal variation coefficient and the abnormal change threshold of the storage environment to which the marine samples belong, the abnormal change deviation value of the storage environment to which the marine samples belong is obtained, and the rate increase coefficient is matched from the management database, so as to increase the quality index decay rate and correct management, and at the same time, early warning management is performed on the storage environment to which the marine samples belong.

[0010] As a further solution, the storage process of marine samples is adjusted and managed. The specific adjustment and management process is: obtain the data processing efficiency deviation value of the target platform at the newly added time point, and match the reserved data volume from the management database, so as to compress the data packets corresponding to the revoked marine samples until the amount of data released by compression is equal to the reserved data volume.

[0011] If the defined data volume released by compression is less than the reserved data volume, the data lifecycle management strategy is implemented, that is, invalid data is automatically identified and compressed until the data volume released by compressing the invalid data is equal to the reserved data volume; if the defined data volume released by compressing the invalid data is less than the reserved data volume, data storage early warning management is performed; at the same time, the total number of data types included in the attribute parameters of the newly added marine samples is obtained, and the number of newly added data nodes is matched from the management database, so as to hierarchically store the attribute parameters of the newly added marine samples.

[0012] As a further solution, marine samples are classified and labeled for management. The specific classification management process is: by analyzing the attribute parameters of marine samples, the quality index of marine samples is obtained, and the quality index reference interval is extracted from the management database and compared with the quality index of marine samples; if the quality index of marine samples is greater than the maximum value of the quality index reference interval, the marine sample is marked as a qualified sample; if the quality index of marine samples falls within the quality index reference interval, the marine sample is marked as a critical sample; if the quality index of marine samples is less than the minimum value of the quality index reference interval, the marine sample is marked as an unqualified sample, thereby completing the classification and labeling management of marine samples.

[0013] As a further solution, it is determined whether to subject marine samples to early warning management. The specific analysis process is as follows: obtain the label of the marine sample; if the label of the marine sample is a qualified sample, obtain the current quality index decay rate of the marine sample and compare it with the defined quality index decay rate; if the current quality index decay rate of the marine sample is greater than or equal to the defined quality index decay rate, determine to subject the marine sample to quality decay early warning management; if the current quality index decay rate of the marine sample is less than the defined quality index decay rate, determine not to subject the marine sample to quality decay early warning management; if the label of the marine sample is a critical sample, obtain and, based on the current quality index of the marine sample and the current quality index decay rate of the marine sample, derive the critical time for the marine sample to meet the quality requirements, and thus subject the marine sample to risk early warning management based on the critical time for the marine sample to meet the quality requirements; if the label of the marine sample is an unqualified sample, obtain the category label of the marine sample, match the destruction method of the marine sample from the management database, and subject the marine sample to destruction early warning management based on the category label of the marine sample and the destruction method of the marine sample; if all data corresponding to the marine sample are cleared, the label of the marine sample is marked as a revoked marine sample.

[0014] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention provides an artificial intelligence-based marine sample management system with a high level of intelligence and automation. It can monitor and deeply analyze the data processing efficiency parameters of the target platform in real time, thereby realizing the precise optimization of the data processing process and significantly improving the efficiency and accuracy of data processing. The target platform continuously collects the storage environment parameters of the marine samples and conducts in-depth analysis with the help of artificial intelligence algorithms. It can timely determine whether the storage parameters need to be corrected, ensuring that the marine sample data can dynamically perceive environmental changes and make adaptive adjustments. At the same time, the system intelligently determines whether to adjust the storage strategy of the attribute parameters of the marine samples based on the data analysis efficiency parameters, thereby ensuring the rationality and efficiency of data storage. In addition, the system can also conduct detailed analysis of the attribute parameters of the marine samples and implement scientific classification and labeling management, which provides great convenience for subsequent research. Moreover, the system has the ability to early warning and judgment, and can identify and respond to potential problems in advance, providing all-round and powerful data protection for the safe and stable storage of marine samples and marine scientific research.

[0015] (2) The present invention obtains a data processing efficiency index by analyzing data processing efficiency parameters, and compares it with the corresponding threshold to decide whether to manage. If management is required, the number of data processing nodes is dynamically adjusted until the efficiency meets the standard. If the number of nodes increases to the defined number and still does not meet the standard, the increase is stopped and an alarm is issued. This optimized management can accurately locate problems, intelligently adjust resource allocation, improve data processing efficiency, ensure stable and efficient operation of the system, provide strong support for marine sample management, and help the smooth development of marine scientific research.

[0016] (3) The present invention analyzes attribute parameters to derive a quality index, compares it with a reference interval, and accurately classifies samples into three categories: qualified, critical, and unqualified, facilitating subsequent targeted processing. In terms of early warning management, different strategies are formulated for samples with different labels: qualified samples focus on the quality decay rate, critical samples calculate the critical time for quality qualification, and unqualified samples match the destruction method to ensure sample safety and compliance. At the same time, after data is cleared, it is marked as revoked to make the management status clear. These functions can improve the efficiency and accuracy of sample management, reduce risks, and provide reliable support for marine scientific research. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of system module connections of the present invention.

[0019] Figure 2 Flowchart for optimizing and adjusting the data processing of the present invention.

[0020] Figure 3 This is a data correction management flow chart of the present invention.

[0021] Figure 4 This is a sample early warning management flow chart of the present invention. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0023] See Figure 1As shown, an embodiment of the present invention provides a technical solution: an artificial intelligence-based marine sample management system, including a data processing optimization and adjustment module, a data correction management module, a sample early warning management module and a management database.

[0024] The management database is used to store the parameters involved in the artificial intelligence-based marine sample management system.

[0025] The data processing optimization and adjustment module is connected to the data correction management module and the sample early warning management module respectively, and the data correction management module is connected to the sample early warning management module. The data processing optimization and adjustment module, the data correction management module and the sample early warning management module are all connected to the management database.

[0026] The data processing optimization and adjustment module is used to mark the marine sample management platform as a target platform, monitor and analyze the data processing performance parameters of the target platform, and thus optimize the data processing process of the target platform.

[0027] Specifically, the data processing process of the target platform is optimized and managed. The specific optimization management process is: by analyzing the data processing efficiency parameters of the target platform, the data processing efficiency index of the target platform is obtained, and the data correction coefficient is matched from the management database, so as to optimize the data analysis process of the target platform; the above-mentioned data correction coefficient refers to the proportional value of the abnormal variation coefficient of the storage environment to which the marine sample belongs and the quality index of the marine sample. The specific matching process is: the data processing efficiency index-data correction coefficient mapping table is stored in the management database, and the data processing efficiency index of the target platform is directly queried in the management database to obtain the data correction coefficient corresponding to the data processing efficiency index of the target platform.

[0028] The data correction coefficient can accurately adjust the deviations caused by these interference factors based on the actual performance of the target platform, making the analysis results closer to the actual situation and greatly improving the accuracy of data processing.

[0029] A data processing efficiency threshold is extracted from the management database and compared with the data processing efficiency index of the target platform. If the data processing efficiency index of the target platform is greater than or equal to the data processing efficiency threshold, the data analysis process of the target platform will not be managed; the above-mentioned data processing efficiency threshold represents the minimum value allowed by the data processing efficiency index.

[0030] If the data processing efficiency index of the target platform is less than the data processing efficiency threshold, the data analysis process of the target platform is managed. The specific management process is: based on the data processing efficiency threshold and the data processing efficiency index of the target platform, the data processing efficiency deviation value of the target platform is obtained, and the number of data processing nodes of the target platform is initially increased. If the data processing efficiency index of the target platform is still less than the data processing efficiency threshold after the management is completed, the number of data processing nodes is continuously increased until the data processing efficiency index of the target platform is greater than or equal to the data processing efficiency threshold; the above-mentioned data processing efficiency deviation value is used to quantify the difference between the data processing efficiency index of the target platform and the data processing efficiency threshold. The degree of deviation between the data processing efficiency thresholds is specifically obtained by subtracting the data processing efficiency index of the target platform from the data processing efficiency threshold, and the result is the data processing efficiency deviation value of the target platform; the above-mentioned initial increase management of the number of data processing nodes of the target platform refers to storing a data processing efficiency deviation value-initial increase quantity mapping table in the management database, and directly querying the data processing efficiency deviation value of the target platform in the management database to obtain the initial increase quantity corresponding to the data processing efficiency deviation value of the target platform. The initial increase quantity refers to the additional number of data processing nodes required to be increased, thereby increasing the number of data processing nodes according to the initial increase quantity.

[0031] If the continuous increase in the number of data processing nodes is equivalent to the preset definition of the continuous increase in the number of data processing nodes, and at the same time the data processing efficiency index of the target platform is still less than the data processing efficiency threshold, then the increase in the number of data processing nodes will be stopped and a data processing warning will be issued. The data processing warning refers to notifying relevant technical personnel to optimize data processing through visual methods such as system message push, email notification or SMS.

[0032] Furthermore, the data processing efficiency index of the target platform is specifically analyzed as follows: the data processing efficiency parameters of the target platform include the task processing cache queue length of the target platform, the CPU load rate of the target platform and the disk throughput of the target platform; the above-mentioned task processing cache queue length indicates the total number of tasks waiting to be processed by the CPU or other processing units in the data processing system of the target platform; the above-mentioned CPU load rate reflects the work intensity of the CPU in a specific time period; the above-mentioned disk throughput indicates the amount of data that the disk can read or write per unit time, usually in bytes / second; the task processing cache queue length, CPU load rate and disk throughput can all be monitored by performance monitoring tools (such as Newell software).

[0033] The defined task processing cache queue length, the defined CPU load rate and the defined disk throughput are extracted from the management database; the proportional relationship between the task processing cache queue length and the defined task processing cache queue length is marked as the first influencing component, the proportional relationship between the CPU load rate and the defined CPU load rate is marked as the second influencing component, and the proportional relationship between the disk throughput and the defined disk throughput is marked as the third influencing component. By introducing measurement values, the influence of the first influencing component, the second influencing component and the third influencing component on the data processing efficiency index is quantified respectively, and the influence degrees are coupled to obtain the data processing efficiency index of the target platform.

[0034] It needs to be explained that when the length of the task processing cache queue increases, it means that there is a backlog of tasks to be processed, which will cause the CPU to be continuously busy to process more tasks, thereby pushing up the CPU load rate; when the CPU load rate is too high, a large amount of CPU resources are occupied, and the read and write operations on the disk may not be responded to in time during the task processing process, thereby reducing the disk throughput. Conversely, the disk throughput decreases and the data read and write delays will slow down the task processing speed, causing the length of the task processing cache queue to further increase. These three parameters influence and restrict each other and work together to affect the data processing efficiency index of the target platform. A long cache queue will lead to a backlog of tasks, an excessively high CPU load rate will cause a resource bottleneck, and limited disk throughput will cause slow data transmission, all of which will reduce the data processing efficiency index. Conversely, a reasonable cache queue length, a moderate CPU load rate and efficient disk throughput can synergistically improve the data processing efficiency index and ensure efficient and stable operation of the system.

[0035] The data processing efficiency index of the target platform represents the data processing efficiency of the target platform. The specific expression is: ; ; ; ; Where, is the data processing performance index of the target platform, is the first impact component, is the second impact component, is the third impact component, The first impact component metric value preset in the management database, To manage the second impact component metric value preset in the database, To manage the third impact component metric value preset in the database, The task processing cache queue length for the target platform, To manage the queue length of defined tasks in the database, is the CPU load rate of the target platform, To manage the preset defined CPU load rates in the database, is the disk throughput of the target platform, To manage the preset bounded disk throughput in the database.

[0036] The above definition of task processing cache queue length indicates the maximum value allowed for the task processing cache queue length; the above definition of CPU load rate indicates the maximum value allowed for the CPU load rate; and the above definition of disk throughput indicates the minimum value allowed for the disk throughput.

[0037] The above-mentioned first influence component measurement value is used to quantify the degree of influence of the unit value of the first influence component on the data processing efficiency index; the above-mentioned second influence component measurement value is used to quantify the degree of influence of the unit value of the second influence component on the data processing efficiency index; the above-mentioned third influence component measurement value is used to quantify the degree of influence of the unit value of the third influence component on the data processing efficiency index; the management database stores the mapping relationship between the first influence component, the second influence component and the third influence component and their corresponding measurement values. For example, the first influence component, the second influence component and the third influence component are input into the management database, and the management database can retrieve the first influence component measurement value, the second influence component measurement value and the third influence component measurement value, and the value range is between 0 and 1.

[0038] In a specific embodiment, the present invention obtains a data processing efficiency index by analyzing data processing efficiency parameters, and compares it with the corresponding threshold to decide whether to manage. If management is required, the number of data processing nodes is dynamically adjusted until the efficiency meets the standard. If the number of nodes increases to a defined number and still does not meet the standard, the increase is stopped and an alert is issued. This optimized management can accurately locate problems, intelligently adjust resource allocation, improve data processing efficiency, ensure stable and efficient operation of the system, provide strong support for marine sample management, and help the smooth development of marine scientific research.

[0039] The data correction management module is used to collect the storage environment parameters of marine samples in real time through the target platform, and analyze the storage environment parameters of marine samples based on artificial intelligence to determine whether to correct and manage the quality parameters of marine samples.

[0040] Specifically, it is determined whether the quality parameters of the marine samples should be corrected and managed. The specific determination process is: by analyzing the storage environment parameters of the marine samples by artificial intelligence, the abnormal variation coefficient of the storage environment to which the marine samples belong is obtained, the abnormal variation threshold is extracted from the management database, and compared with the abnormal variation coefficient of the storage environment to which the marine samples belong; the above-mentioned abnormal variation threshold represents the maximum value allowed by the abnormal variation coefficient.

[0041] If the abnormal variation coefficient of the storage environment to which the marine sample belongs is less than or equal to the abnormal variation threshold, it is determined that no correction management will be performed on the quality parameters of the marine sample; if the abnormal variation coefficient of the storage environment to which the marine sample belongs is greater than the abnormal variation threshold, it is determined that the quality parameters of the marine sample are corrected and managed. Specifically, the correction management refers to: the quality parameters of the marine sample include the quality index decay rate of the marine sample, based on the abnormal variation coefficient and the abnormal variation threshold of the storage environment to which the marine sample belongs, the abnormal change deviation value of the storage environment to which the marine sample belongs is obtained, and the rate increase coefficient is matched from the management database, so as to increase and correct the quality index decay rate, and at the same time, perform early warning management on the storage environment to which the marine sample belongs; the above-mentioned quality index decay rate refers to the rate at which the quality index shows a downward trend over time, and the quality index will perform corresponding decreasing operations according to the decay rate; the above-mentioned abnormal change deviation value is used to quantify the storage environment to which the marine sample belongs. The deviation between the abnormal change coefficient and the abnormal change threshold is specifically obtained by subtracting the abnormal change threshold from the abnormal change coefficient of the storage environment to which the marine sample belongs, and the result is the abnormal change deviation value of the storage environment to which the marine sample belongs; the above-mentioned rate increase coefficient refers to the proportional value of the increase correction of the quality index decay rate, and the rate increase coefficient is multiplied by the rate increase coefficient, and the result is the quality index decay rate after increase correction management, wherein the rate increase coefficient, the specific matching process is: the abnormal change deviation value-rate increase coefficient mapping table is stored in the management database, and the abnormal change deviation value of the storage environment to which the marine sample belongs is directly queried in the management database to obtain the rate increase coefficient corresponding to the abnormal change deviation value of the storage environment to which the marine sample belongs; the above-mentioned early warning management of the storage environment to which the marine sample belongs refers to notifying relevant technical personnel to adjust the storage environment to which the marine sample belongs through visual methods such as system message push, email notification or SMS.

[0042] Furthermore, the abnormal variation coefficient of the storage environment of the marine samples is specifically analyzed as follows: the storage environment parameters of the marine samples include the light intensity fluctuation rate of the storage environment of the marine samples, the oxygen concentration fluctuation rate of the storage environment of the marine samples, and the temperature extreme value change frequency of the storage environment of the marine samples; the above-mentioned light intensity fluctuation rate refers to the degree of deviation between the current light intensity of the storage environment and the reference light intensity preset by the technicians. Specifically, the current light intensity and the reference light intensity are subjected to difference processing, and the absolute value of the processing result is subjected to ratio processing with the reference light intensity. The final result is the light intensity fluctuation rate. The current light intensity of the storage environment can be measured by a light sensor. The above-mentioned oxygen concentration fluctuation rate refers to the degree of deviation between the current oxygen concentration in the storage environment and the reference oxygen concentration preset by the technician. Specifically, the current oxygen concentration and the reference oxygen concentration are subjected to difference processing, and the absolute value of the processing result is ratioed with the reference oxygen concentration. The final result is the oxygen concentration fluctuation rate. The current oxygen concentration in the storage environment can be measured by an oxygen sensor. The above-mentioned temperature extreme value change frequency refers to the number of times the storage environment temperature reaches the maximum or minimum temperature preset by the technician per unit time, which can be obtained by measurement and analysis of the temperature sensor.

[0043] By introducing measurement values to quantify the degree of influence of the proportional relationship between the light intensity fluctuation rate and the defined light intensity fluctuation rate, the proportional relationship between the oxygen concentration fluctuation rate and the defined oxygen concentration fluctuation rate, and the proportional relationship between the temperature extreme change frequency and the defined temperature extreme change frequency on the anomaly variation coefficient, the various influence degrees are coupled, and the coupling results are corrected using the data correction coefficient to obtain the anomaly variation coefficient of the storage environment to which the marine samples belong.

[0044] It should be explained that when the light intensity fluctuation rate increases, it will intensify the photochemical reaction in the storage environment, affecting the activity of microorganisms and the rate of chemical reactions, and indirectly changing the balance of oxygen consumption and production in the environment, resulting in corresponding fluctuations in oxygen concentration. In other words, an increase in the light intensity fluctuation rate may cause an increase in the oxygen concentration fluctuation rate. At the same time, changes in light intensity will bring about heat changes, and the temperature in the local area will change accordingly, which will accelerate the frequency of temperature extreme changes and increase the oxygen concentration fluctuation rate. On the one hand, this will affect the biological metabolic process, generate or consume heat, interfere with the stability of the ambient temperature, and promote the increase in the frequency of temperature extreme changes. On the other hand, temperature changes will in turn affect the solubility and diffusion rate of oxygen in the storage medium, further exacerbating oxygen concentration fluctuations, forming a mutually influencing cycle. The accelerated frequency of temperature extreme changes will lead to significant thermal expansion and contraction effects in the storage environment, affecting the sealing of the equipment and gas circulation, indirectly interfering with the operation of the light adjustment device and oxygen control device, making it difficult to stabilize the light intensity fluctuation rate and oxygen concentration fluctuation rate. The abnormal changes in parameters promote and act together, resulting in an increase in the abnormal variation coefficient of the storage environment, indicating that the stability of the storage environment has been damaged and the degree of abnormality has deepened.

[0045] The abnormal variation coefficient of the storage environment of the marine sample characterizes the degree of abnormal variation of the storage environment of the marine sample. The specific expression is: ; Where, is the abnormal variation coefficient of the storage environment of the marine sample, is the light intensity fluctuation rate of the storage environment of the marine sample, To manage the preset light intensity fluctuation rate in the database, is the oxygen concentration fluctuation rate of the storage environment of the marine sample, To manage the defined oxygen concentration fluctuation rate preset in the database, is the frequency of temperature extreme value changes in the storage environment of the marine sample, To manage the frequency of temperature extreme value changes preset in the database, To manage the preset light intensity fluctuation rate measurement value in the database, To manage the oxygen concentration fluctuation rate measurement values preset in the database, To manage the temperature extreme value change frequency measurement values preset in the database, is the data correction factor.

[0046] The above definition of light intensity fluctuation rate indicates the maximum value allowed for the light intensity fluctuation rate; the above definition of oxygen concentration fluctuation rate indicates the maximum value allowed for the oxygen concentration fluctuation rate; the above definition of temperature extreme value change frequency indicates the maximum value allowed for the temperature extreme value change frequency.

[0047] The above-mentioned light intensity fluctuation rate measurement value is used to quantify the degree of influence of the light intensity fluctuation rate unit value on the abnormal variation coefficient; the above-mentioned oxygen concentration fluctuation rate measurement value is used to quantify the degree of influence of the oxygen concentration fluctuation rate unit value on the abnormal variation coefficient; the above-mentioned temperature extreme value change frequency measurement value is used to quantify the degree of influence of the temperature extreme value change frequency unit value on the abnormal variation coefficient; the management database stores the mapping relationship between the light intensity fluctuation rate, oxygen concentration fluctuation rate and temperature extreme value change frequency and their corresponding measurement values. For example, the light intensity fluctuation rate, oxygen concentration fluctuation rate and temperature extreme value change frequency are input into the management database, and the management database can retrieve the light intensity fluctuation rate measurement value, oxygen concentration fluctuation measurement value and temperature extreme value change frequency measurement value, and the value range is between 0 and 1.

[0048] The sample early warning management module is used to store the attribute parameters of marine samples through the target platform, and based on the data analysis efficiency parameters of the target platform, determine whether to adjust the storage process of marine samples. At the same time, it analyzes the attribute parameters of marine samples, classifies and labels marine samples, and determines whether to perform early warning management on marine samples.

[0049] In a specific embodiment, the present invention analyzes attribute parameters to derive a quality index, compares it with a reference interval, and accurately classifies samples into three categories: qualified, critical, and unqualified, facilitating subsequent targeted processing. In terms of early warning management, different strategies are formulated for samples with different labels: qualified samples focus on the quality decay rate, critical samples calculate the critical time for quality compliance, and unqualified samples match the destruction method to ensure sample safety and compliance. At the same time, after data is cleared, it is marked as revoked to make the management status clear. These functions can improve the efficiency and accuracy of sample management, reduce risks, and provide reliable support for marine scientific research.

[0050] Specifically, the marine samples are classified and labeled for management. The specific classification management process is: by analyzing the attribute parameters of the marine samples, the quality index of the marine samples is obtained, and the quality index reference interval is extracted from the management database and compared with the quality index of the marine samples; if the quality index of the marine sample is greater than the maximum value of the quality index reference interval, the marine sample is marked as a qualified sample; if the quality index of the marine sample belongs to the quality index reference interval, the marine sample is marked as a critical sample; if the quality index of the marine sample is less than the minimum value of the quality index reference interval, the marine sample is marked as an unqualified sample, thereby completing the classification and labeling management of the marine samples; the above-mentioned quality index reference interval is a numerical interval used to define the marine sample label.

[0051] Specifically, it is determined whether to conduct early warning management on the marine sample. The specific analysis process is: obtain the label of the marine sample; if the label of the marine sample is a qualified sample, obtain the current quality index decay rate of the marine sample, and compare it with the defined quality index decay rate; if the current quality index decay rate of the marine sample is greater than or equal to the defined quality index decay rate, it is determined that quality decay early warning management is conducted on the marine sample; if the current quality index decay rate of the marine sample is less than the defined quality index decay rate, it is determined that quality decay early warning management is not conducted on the marine sample; the above-mentioned defined quality index decay rate represents the maximum value allowed for the quality index decay rate, which is extracted from the management database; the above-mentioned quality decay early warning management of the marine sample refers to notifying relevant technical personnel through visual methods such as system message push that the quality decay rate of the marine sample is too fast and requires timely maintenance.

[0052] If the label of the marine sample is a critical sample, the critical time for the marine sample to meet the quality standards is obtained based on the current quality index of the marine sample and the current quality index decay rate of the marine sample, so as to perform risk warning management on the marine sample based on the critical time for the marine sample to meet the quality standards; the above-mentioned critical time for quality standards refers to the time when the marine sample's qualified index reaches the minimum value of the quality index reference interval, specifically, the current quality index of the marine sample is subtracted from the minimum value of the quality index reference interval, and the result is divided by the current quality index decay rate of the marine sample, and the result is the critical time for the marine sample to meet the quality standards; the above-mentioned risk warning management of the marine sample notifies relevant technical personnel of the critical time for the marine sample to meet the quality standards through visual methods such as system message push to ensure that relevant personnel respond quickly.

[0053] If the marine sample is labeled as an unqualified sample, the category label of the marine sample is obtained and the destruction method of the marine sample is matched from the management database. Based on the category label and destruction method of the marine sample, destruction warning management of the marine sample is performed. The category label of the marine sample refers to the type of marine sample, such as seawater, sediment, etc., which is directly extracted from the target platform and classified by relevant technical personnel. It can be divided into biological sample labels and chemical sample labels. The specific matching process of the destruction method of the marine sample is as follows: a category label-destruction method mapping table is stored in the management database. The category label of the marine sample is directly queried in the management database to obtain the destruction method corresponding to the category label of the marine sample. The destruction method includes the destruction steps, required equipment, precautions, safety precautions, etc. For example, for seawater samples containing high concentrations of heavy metals, the destruction method may include neutralization treatment with specific chemical reagents, followed by filtration, precipitation, and other processes to ensure that the heavy metal ions are effectively removed before discharge. The destruction warning management of marine samples refers to notifying relevant technical personnel of the marine sample category label and destruction method through visual means such as system message push to ensure a quick response from relevant personnel.

[0054] If all data corresponding to the marine sample are cleared, the label of the marine sample is marked as a revoked marine sample.

[0055] Specifically, the quality index of marine samples, the specific analysis process is: obtain the category label of the marine sample; if the category label of the marine sample is a biological sample label, the attribute parameters of the marine sample include the morphological integrity of the marine sample, the moisture content of the marine sample and the microbial density of the marine sample; the above-mentioned morphological integrity refers to the degree to which the external morphology of the marine biological sample remains intact and has not undergone obvious damage or deformation during the collection, preservation, transportation, etc., usually expressed as a percentage; the above-mentioned moisture content indicates the percentage of the weight of the water contained in the marine sample to the total weight of the sample; the above-mentioned microbial density refers to the number of microorganisms contained in the marine sample per unit weight; the morphological integrity, moisture content and microbial density are all uploaded by relevant technical personnel.

[0056] It needs to be explained that when the marine sample category is biological samples, the attribute parameters such as morphological integrity, water content and microbial density are interrelated and influence each other, and jointly affect the quality index of the biological sample. The instability of the storage environment will cause the conditions of the marine samples to fluctuate, thereby affecting these parameters. When the microbial density increases, the microorganisms will consume a large amount of nutrients in the marine samples. At the same time, the enzymes, organic acids and other substances produced by their metabolic activities will erode the cell structure and tissue of the biological samples, destroy the integrity of the cell membrane, and cause the leakage of cell contents, which will destroy the morphological integrity of the marine samples, resulting in loose tissue, structural disintegration and other phenomena. After the morphological integrity is reduced, the water distribution and retention inside the marine samples will be affected. The ability will also be affected, the originally stable cell structure will be destroyed, water will be lost more easily, resulting in a decrease in water content; and incomplete morphology will also provide more space for microorganisms to invade and reproduce, further causing the microbial density to deviate significantly from the corresponding reference value. Water content has a direct impact on microbial density. Appropriate water content is a necessary condition for the growth and reproduction of microorganisms. When the water content deviates significantly from the corresponding reference value, it is conducive to the breeding and reproduction of microorganisms, resulting in a sharp increase in microbial density. These parameters are intertwined with each other. Changes in microbial density trigger changes in morphological integrity and water content, which in turn react on microbial density. They work together to ultimately affect the quality of marine samples.

[0057] If the category label of the marine sample is a chemical sample label, the attribute parameters of the marine sample include the content of various chemical components of the marine sample, the pH value of the marine sample, and the sample density of the marine sample; the above-mentioned content of various chemical components refers to the proportion of different chemical substances in the marine sample, and various chemical components include but are not limited to inorganic components (such as sodium chloride, calcium sulfate, etc.) and organic components (such as xylene, carbohydrates); the above-mentioned pH value is an indicator used to measure the acidity and alkalinity of the solution; the above-mentioned sample density refers to the mass of the marine sample per unit volume; the content of various chemical components, pH value and sample density are all uploaded by relevant technical personnel.

[0058] It needs to be explained that when the marine sample category label is a chemical sample, the abnormal variation coefficient of the storage environment increases, which means that the conditions of the storage environment such as light, temperature, humidity, and gas composition fluctuate frequently and greatly. This unstable environment will accelerate the chemical reaction rate of various chemical components in the chemical sample. For example, light may prompt certain chemical substances to undergo photolysis reactions, and temperature changes will affect the activation energy of chemical reactions, resulting in changes in the content of various chemical components. Some volatile or easily decomposable components may decrease, while some secondary reaction products may increase; at the same time, environmental abnormalities may also introduce new impurities or interfering substances, further disrupting the composition and content of chemical components. Changes in the content of various chemical components will directly affect the acidity of marine samples. Alkalinity, such as an increase or decrease in the content of certain acidic or alkaline components, will cause the hydrogen ion or hydroxide ion concentration of the solution to change, thereby causing the pH to deviate from the normal range; and changes in pH may trigger a series of chain reactions, prompting other chemical components to undergo acid-base catalytic reactions, further changing their content. In addition, changes in chemical component content and pH will also affect the sample density of marine samples. The increase or decrease in chemical components will change the mass fraction of solutes in the solution. Changes in pH may affect the solubility and ionic state of the substance. The combined effect of these factors causes the volume or mass of the solution to change, ultimately leading to changes in sample density. These parameters are interrelated and influence each other, and jointly determine the quality status of marine samples.

[0059] If the category label of the marine sample belongs to the biological sample label, the degree of influence of the abnormal variation coefficient, the degree of deviation between the morphological integrity and the reference morphological integrity, the degree of deviation between the water content and the reference water content, and the degree of deviation between the microbial density and the reference microbial density on the quality index is quantified by introducing measurement values. The various influence degrees are aggregated, and the aggregated results are corrected using the data correction coefficient to obtain the quality index; if the category label of the marine sample belongs to the chemical sample label, the degree of influence of the abnormal variation coefficient, the degree of deviation between the chemical component content and the reference chemical component content, the degree of deviation between the pH and the reference pH, and the degree of deviation between the sample density and the reference sample density on the quality index are aggregated, and the aggregated results are corrected using the data correction coefficient to obtain the quality index.

[0060] The quality index of marine samples characterizes the quality of marine samples. The specific expression is: ; Where, is the quality index of the marine sample, Category labels for marine samples, For biological sample labeling, For chemical sample labels, is the morphological integrity of marine samples, To manage the completeness of the reference forms preset in the database, is the water content of the ocean sample, To manage the reference moisture content preset in the database, is the microbial density of the marine sample, To manage the reference microbial density preset in the database, To manage the morphological integrity metrics preset in the database, To manage the moisture content measurement values preset in the database, is the microbial density measurement value preset in the management database, s is the number of each chemical component, , r is the total number of chemical component types, is the content of the sth chemical component in the marine sample, To manage the reference content of Class S chemical components preset in the database, is the pH of the ocean sample, To manage the reference pH values preset in the database, is the sample density of the ocean sample, To manage the reference sample densities preset in the database, To manage the preset chemical composition content measurement values in the database, To manage the pH values preset in the database, To manage the sample density measurements preset in the database, is the abnormal variation coefficient of the storage environment of the marine sample, To manage the abnormal variation coefficient measurement value preset in the database, is the data correction factor.

[0061] The above-mentioned reference morphological integrity indicates the reference value of morphological integrity; the above-mentioned reference moisture content indicates the reference value of moisture content; the above-mentioned reference microbial density indicates the reference value of microbial density; the above-mentioned reference content of Class S chemical components indicates the reference value of the content of Class S chemical components; the above-mentioned reference pH indicates the reference value of pH; the above-mentioned reference sample density indicates the reference value of sample density.

[0062] The above-mentioned morphological integrity measurement value is used to quantify the degree of influence of the morphological integrity unit value on the quality index; the above-mentioned moisture content measurement value is used to quantify the degree of influence of the moisture content unit value on the quality index; the above-mentioned microbial density measurement value is used to quantify the degree of influence of the microbial density unit value on the quality index; the above-mentioned chemical component content measurement value is used to quantify the degree of influence of the chemical component content unit value on the quality index; the above-mentioned pH measurement value is used to quantify the degree of influence of the pH unit value on the quality index; the above-mentioned sample density measurement value is used to quantify the degree of influence of the sample density unit value on the quality index; the management database stores the mapping relationship between morphological integrity, moisture content, microbial density, chemical component content, pH and sample density and their corresponding measurement values. For example, the morphological integrity, moisture content, microbial density, chemical component content, pH and sample density are input into the management database, and the management database can retrieve the morphological integrity measurement value, moisture content measurement value, microbial density measurement value, chemical component content measurement value, pH measurement value and sample density measurement value, and the value range is between 0 and 1.

[0063] Furthermore, it is determined whether to adjust and manage the storage process of the marine samples. The specific determination process is: adding the attribute parameters of the marine samples and the mass index decay rate of the marine samples on the target platform, obtaining the data processing efficiency index of the target platform at the newly added time point, and comparing it with the data processing efficiency threshold. If the data processing efficiency index of the target platform at the newly added time point is less than the data processing efficiency threshold, it is determined that the storage process of the marine samples is adjusted and managed; the above-mentioned data processing efficiency threshold refers to the minimum value allowed by the data processing efficiency index, which is extracted from the management database; the above-mentioned new time point refers to the time point when the target platform receives the new instruction, which is obtained from the time log of the target platform.

[0064] If the data processing efficiency index of the target platform at the newly added time point is greater than or equal to the data processing efficiency threshold, it is determined that the storage process of the marine samples will not be adjusted and managed, and the attribute parameters of the newly added marine samples and the quality index decay rate of the marine samples on the target platform will be directly stored.

[0065] Furthermore, the storage process of the marine samples is adjusted and managed. The specific adjustment and management process is: obtaining the data processing efficiency deviation value of the target platform at the newly added time point, and matching the reserved data volume from the management database, thereby compressing the data packets corresponding to the revoked marine samples until the amount of data released by compression is equal to the reserved data volume; the above-mentioned reserved data volume refers to the amount of data that needs to be freed up in the storage space of the target platform. The specific matching process is: storing the data processing efficiency deviation value-reserved data volume mapping table in the management database, and directly querying the data processing efficiency deviation value in the management database to obtain the reserved data volume corresponding to the data processing efficiency deviation value.

[0066] If the defined amount of data released by compression is less than the reserved amount of data, the data lifecycle management strategy is implemented, that is, invalid data is automatically identified and compressed until the amount of data released by compressing the invalid data is equal to the reserved amount of data; the above-mentioned defined amount of data refers to the maximum amount of data released by compression on the target platform.

[0067] If the defined amount of data released by compressing invalid data is less than the reserved data amount, data storage early warning management will be carried out, specifically notifying relevant technical personnel of the storage anomaly of the target platform through visual methods such as system message push.

[0068] At the same time, the total number of data types included in the attribute parameters of the newly added marine samples is obtained, and the number of newly added data nodes is matched from the management database, so as to hierarchically store the attribute parameters of the newly added marine samples; data types include but are not limited to the physical properties of the samples (such as temperature, salinity, pH value), chemical composition (such as heavy metal content, organic matter concentration), biological indicators (such as microbial species, biomass) and collection information (such as collection time, location, depth), etc. Next, the number of newly added data nodes corresponding to the total number of newly added marine sample data types is matched from the management database. The management database stores the mapping between the number of different data types and the required number of data nodes. This relationship is usually set by relevant technical personnel based on factors such as data processing efficiency, storage space optimization, and query speed. According to the number of newly matched data nodes, the attribute parameters of the newly added marine samples are stored in a hierarchical manner. The hierarchical storage strategy is formulated by relevant technical personnel based on the importance of the data, frequency of use or access speed requirements. For example, core data (such as key chemical components and biological indicators) are stored in high-speed access storage devices, while auxiliary data (such as collection information) are stored in relatively low-speed but larger-capacity storage devices. Through this hierarchical storage method, the use of system resources can be optimized and the efficiency and response speed of data management can be improved.

[0069] In a specific embodiment, the present invention provides an artificial intelligence-based marine sample management system with a high level of intelligence and automation. It can monitor and deeply analyze the data processing efficiency parameters of the target platform in real time, thereby realizing precise optimization of the data processing process and significantly improving the efficiency and accuracy of data processing. The target platform continuously collects the storage environment parameters of marine samples and conducts in-depth analysis with the help of artificial intelligence algorithms. It can timely determine whether the storage parameters need to be corrected to ensure that the marine sample data can dynamically perceive environmental changes and make adaptive adjustments. At the same time, the system intelligently determines whether to adjust the storage strategy of the attribute parameters of marine samples based on the data analysis efficiency parameters, thereby ensuring the rationality and efficiency of data storage. In addition, the system can also conduct detailed analysis of the attribute parameters of marine samples and implement scientific classification and labeling management, which provides great convenience for subsequent research. Moreover, the system has early warning and judgment capabilities, which can identify and respond to potential problems in advance, and provide all-round and powerful data protection for the safe and stable storage of marine samples and marine scientific research.

[0070] Figure 2 The data processing optimization and adjustment flow chart of the present invention first monitors the performance parameters, which reflect the efficiency and effectiveness of the data processing process. By calculating the performance index, the system can quantify the current processing performance. If the performance index is lower than the preset threshold, the system will automatically increase the data processing nodes to improve the processing performance. This process will continue until the performance index reaches or exceeds the threshold, at which time the system will determine that the optimization is complete.

[0071] Figure 3 The data correction management flow chart of the present invention first collects storage environment parameters, which include environmental factors such as temperature, humidity, and light that may affect data quality. Then, the system calculates the abnormal variation coefficient to evaluate the degree of change in the environmental parameters. If the abnormal variation coefficient is higher than the threshold, the system will correct the quality parameters to compensate for the impact of environmental changes on data quality, and at the same time warn the storage environment to remind the administrator to pay attention and take corresponding measures. If the abnormal variation coefficient is within the threshold, the system will not make any corrections and maintain the current state.

[0072] Figure 4This is the sample early warning management flow chart of the present invention. By monitoring the storage status and quality of samples and issuing early warnings according to preset conditions, the system first collects storage attribute parameters to evaluate the storage efficiency of the samples. If the efficiency does not meet the standards, the system will adjust the storage process, such as changing the storage temperature, humidity and other conditions, and compressing invalid data to save storage space. During the adjustment process, the system will continuously monitor whether the data volume meets the standards. If it does not meet the standards, a warning storage notification will be issued. At the same time, the system classifies and marks the samples, and calculates the quality index, and marks the samples as qualified, critical or unqualified according to the quality index range. Finally, the system performs early warning management according to the sample labels, checks the decay rate of qualified samples, issues risk warnings for critical samples, and issues destruction warnings for unqualified samples to ensure the quality and safety of the samples.

[0073] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. The marine sample management system based on artificial intelligence is characterized by: include: The data processing optimization and adjustment module is used to mark the marine sample management platform as a target platform, monitor and analyze the data processing efficiency parameters of the target platform, and thus optimize the data processing process of the target platform; The data correction management module is used to collect the storage environment parameters of marine samples in real time through the target platform, analyze the storage environment parameters of marine samples based on artificial intelligence, and determine whether to correct and manage the quality parameters of marine samples; The sample early warning management module is used to store the attribute parameters of marine samples through the target platform, and based on the data analysis efficiency parameters of the target platform, determine whether to adjust the storage process of marine samples. At the same time, it analyzes the attribute parameters of marine samples, classifies and marks marine samples, and determines whether to perform early warning management on marine samples.

2. The artificial intelligence-based marine sample management system according to claim 1, characterized in that: The data processing process of the target platform is optimized and managed, and the specific optimization and management process is as follows: By analyzing the data processing efficiency parameters of the target platform, the data processing efficiency index of the target platform is obtained, and the data correction coefficient is matched from the management database, thereby optimizing the data analysis process of the target platform; Extracting a data processing efficiency threshold from the management database and comparing it with the data processing efficiency index of the target platform; if the data processing efficiency index of the target platform is greater than or equal to the data processing efficiency threshold, the data analysis process of the target platform will not be managed; If the data processing efficiency index of the target platform is less than the data processing efficiency threshold, the data analysis process of the target platform is managed. The specific management process is as follows: based on the data processing efficiency threshold and the data processing efficiency index of the target platform, the data processing efficiency deviation value of the target platform is obtained, and the number of data processing nodes of the target platform is initially increased. If the data processing efficiency index of the target platform is still less than the data processing efficiency threshold after the management is completed, the number of data processing nodes is continuously increased until the data processing efficiency index of the target platform is greater than or equal to the data processing efficiency threshold; If the continued increase in the number of data processing nodes is equivalent to the preset definition of continuing to increase the number of data processing nodes, and at the same time the data processing efficiency index of the target platform is still less than the data processing efficiency threshold, then stop increasing the number of data processing nodes and issue a data processing warning.

3. The artificial intelligence-based marine sample management system according to claim 2, characterized in that: The data processing efficiency index of the target platform is analyzed in the following specific steps: The data processing performance parameters of the target platform include the target platform's task processing cache queue length, the target platform's CPU load rate, and the target platform's disk throughput; Extracting defined task processing cache queue length, defined CPU load rate, and defined disk throughput from the management database; The proportional relationship between the task processing cache queue length and the defined task processing cache queue length is marked as the first influencing component, the proportional relationship between the CPU load rate and the defined CPU load rate is marked as the second influencing component, and the proportional relationship between the disk throughput and the defined disk throughput is marked as the third influencing component. By introducing measurement values, the influence of the first influencing component, the second influencing component, and the third influencing component on the data processing efficiency index are quantified respectively. The influence degrees are coupled to obtain the data processing efficiency index of the target platform. The data processing performance index of the target platform represents the data processing performance of the target platform.

4. The artificial intelligence-based marine sample management system according to claim 1, characterized in that: The specific process of determining whether to perform correction management on the quality parameters of the marine sample is as follows: By analyzing the storage environment parameters of the marine samples through artificial intelligence, the abnormal variation coefficient of the storage environment of the marine samples is obtained, the abnormal change threshold is extracted from the management database, and compared with the abnormal variation coefficient of the storage environment of the marine samples; If the abnormal variation coefficient of the storage environment of the marine sample is less than or equal to the abnormal variation threshold, it is determined that no correction management will be performed on the quality parameters of the marine sample; If the abnormal variation coefficient of the storage environment to which the marine sample belongs is greater than the abnormal variation threshold, it is determined that the quality parameters of the marine sample are to be corrected and managed. Specifically, the correction management refers to: the quality parameters of the marine sample include the quality index decay rate of the marine sample. Based on the abnormal variation coefficient and the abnormal variation threshold of the storage environment to which the marine sample belongs, the abnormal change deviation value of the storage environment to which the marine sample belongs is obtained, and the rate increase coefficient is matched from the management database, so as to increase the quality index decay rate and perform correction management, and at the same time, perform early warning management on the storage environment to which the marine sample belongs.

5. The artificial intelligence-based marine sample management system according to claim 4, characterized in that: The abnormal variation coefficient of the storage environment of the marine sample is analyzed in the following specific process: The storage environment parameters of the marine samples include the light intensity fluctuation rate of the storage environment of the marine samples, the oxygen concentration fluctuation rate of the storage environment of the marine samples, and the temperature extreme value change frequency of the storage environment of the marine samples; By introducing measurement values to quantify the degree of influence of the proportional relationship between the light intensity fluctuation rate and the defined light intensity fluctuation rate, the proportional relationship between the oxygen concentration fluctuation rate and the defined oxygen concentration fluctuation rate, and the proportional relationship between the temperature extreme change frequency and the defined temperature extreme change frequency on the anomaly variation coefficient, the various influence degrees are coupled, and the coupling results are corrected using the data correction coefficient, thereby obtaining the anomaly variation coefficient of the storage environment to which the marine samples belong; The abnormal variation coefficient of the storage environment of the marine sample represents the degree of abnormal variation of the storage environment of the marine sample.

6. The artificial intelligence-based marine sample management system according to claim 1, characterized in that: The determination of whether to adjust and manage the storage process of the marine sample is as follows: Add the attribute parameters of the marine samples and the decay rate of the quality index of the marine samples to the target platform, obtain the data processing efficiency index of the target platform at the added time point, and compare it with the data processing efficiency threshold. If the data processing efficiency index of the target platform at the added time point is less than the data processing efficiency threshold, it is determined that the storage process of the marine samples needs to be adjusted and managed; If the data processing efficiency index of the target platform at the newly added time point is greater than or equal to the data processing efficiency threshold, it is determined that the storage process of the marine samples will not be adjusted and managed, and the attribute parameters of the newly added marine samples and the quality index decay rate of the marine samples on the target platform will be directly stored.

7. The artificial intelligence-based marine sample management system according to claim 6, characterized in that: The storage process of the marine samples is adjusted and managed, and the specific adjustment and management process is as follows: Obtain the data processing efficiency deviation value of the target platform at the newly added time point, and match the reserved data volume from the management database, so as to compress the data packets corresponding to the revoked marine samples until the amount of data released by compression equals the reserved data volume; If the defined amount of data released by compression is less than the reserved amount of data, the data lifecycle management strategy is implemented, that is, invalid data is automatically identified and compressed until the amount of data released by compressing the invalid data is equal to the reserved amount of data; If the defined data volume released by compressing invalid data is less than the reserved data volume, data storage warning management is performed; At the same time, the total number of data types included in the attribute parameters of the newly added marine samples is obtained, and the number of newly added data nodes is matched from the management database, so as to hierarchically store the attribute parameters of the newly added marine samples.

8. The artificial intelligence-based marine sample management system according to claim 1, characterized in that: The classification and labeling management of marine samples is carried out as follows: By analyzing the attribute parameters of marine samples, the quality index of marine samples is obtained, and the quality index reference interval is extracted from the management database and compared with the quality index of marine samples; If the quality index of the marine sample is greater than the maximum value of the quality index reference interval, the marine sample is marked as a qualified sample; If the quality index of the marine sample falls within the quality index reference interval, the marine sample is marked as a critical sample; If the quality index of the marine sample is less than the minimum value of the quality index reference range, the marine sample will be marked as an unqualified sample, thereby completing the classification and marking management of the marine sample.

9. The artificial intelligence-based marine sample management system according to claim 1, characterized in that: The specific analysis process for determining whether to conduct early warning management on marine samples is as follows: Obtain labels for ocean samples; If the label of the marine sample is a qualified sample, the current mass index decay rate of the marine sample is obtained and compared with the defined mass index decay rate. If the current mass index decay rate of the marine sample is greater than or equal to the defined mass index decay rate, it is determined that the marine sample will be subject to mass decay warning management. If the current mass index decay rate of the marine sample is less than the defined mass index decay rate, it is determined that the marine sample will not be subject to mass decay warning management. If the label of the marine sample is a critical sample, the critical time for the marine sample to meet the quality standards is obtained based on the current quality index of the marine sample and the current quality index decay rate of the marine sample, so as to perform risk warning management on the marine sample based on the critical time for the marine sample to meet the quality standards; If the marine sample is labeled as an unqualified sample, obtain the category label of the marine sample and match the destruction method of the marine sample from the management database. Based on the category label of the marine sample and the destruction method of the marine sample, carry out destruction warning management of the marine sample; If all data corresponding to the marine sample are cleared, the label of the marine sample is marked as a revoked marine sample.

10. The artificial intelligence-based marine sample management system according to claim 1, characterized in that: The quality index of the marine sample is specifically analyzed as follows: Obtain category labels for marine samples; If the category label of the marine sample belongs to the biological sample label, the attribute parameters of the marine sample include the morphological integrity of the marine sample, the water content of the marine sample, and the microbial density of the marine sample; If the category label of the marine sample is a chemical sample label, the attribute parameters of the marine sample include the content of various chemical components of the marine sample, the pH value of the marine sample, and the sample density of the marine sample; If the category label of the marine sample is a biological sample label, the degree of influence of the abnormal variation coefficient, the degree of deviation between the morphological integrity and the reference morphological integrity, the degree of deviation between the water content and the reference water content, and the degree of deviation between the microbial density and the reference microbial density on the quality index are quantified by introducing measurement values. The various influence degrees are aggregated and the aggregated results are corrected using the data correction coefficient to obtain the quality index; If the category label of the marine sample is a chemical sample label, the influence of the abnormal variation coefficient, the deviation between the chemical component content and the reference chemical component content, the deviation between the pH and the reference pH, and the deviation between the sample density and the reference sample density on the quality index is quantified by introducing measurement values. The influence degrees are aggregated and the aggregated results are corrected using the data correction coefficient to obtain the quality index. The quality index of the marine sample characterizes the quality of the marine sample.

Images