Geographic science information intelligent management method and system based on big data analysis

Abstract

The invention discloses a geographic science information intelligent management method and system based on big data analysis, and particularly relates to the technical field of geographic science information intelligent management. According to the method, an image compression distortion coefficient, a format conversion abnormal coefficient and an external attack pressure coefficient are respectively generated, potential hidden danger sources of high-resolution image data in an access link can be comprehensively covered, an image data access hidden danger assessment model is constructed, and an image data access hidden danger assessment index is generated; the overall risk level of potential hidden dangers in the image data access process is quantitatively represented, real-time assessment of the hidden dangers in a complex data access environment is achieved, and after the potential hidden dangers are recognized, whether high-risk hidden dangers exist in the high-resolution image data access process or not is intelligently judged in combination with the real-time data access scale, so that the safety of the high-resolution image data access process is improved. Therefore, early warning and accurate response are realized, and fault upgrading is avoided.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology of geographic science information, and more specifically, to a method and system for intelligent management of geographic science information based on big data analysis. Background Art

[0002] In recent years, with the development of remote sensing technology, satellite images and geographic information systems (GIS), high-resolution image data has been increasingly used in the field of geographical science. In particular, in key areas such as urban planning, disaster warning, precision agricultural management, and ecological protection, high-resolution image data provides rich spatial information and important support for decision makers. However, with the surge in data volume, the storage and management of high-resolution image data face huge technical challenges. First, such data usually have high resolution and long time span, and their storage requirements far exceed the processing capacity of traditional data management systems, resulting in a significant increase in storage costs. Second, due to the dynamic characteristics of data and high-frequency access requirements, traditional storage architectures often cannot provide sufficient flexibility and efficiency, especially when large-scale image data need to be queried and processed in real time, performance bottlenecks are prone to occur.

[0003] With the development of big data technology, the intelligent management system of geographic science information based on big data analysis has gradually become an important way to solve the problem of high-resolution image data management. However, in the process of storing and accessing high-resolution image data, potential hidden dangers and failure risks are often ignored, resulting in the system's inability to respond in time when problems occur, which in turn affects the availability of data and the accuracy of decision-making. For example, if data access failures or delays are not discovered in time, key data may not be obtained in real time, thus missing the best decision-making opportunity, and even causing serious waste of resources and decision-making errors. In order to solve these problems, an intelligent, big data-driven geographic science information management method is urgently needed, which can monitor anomalies in the data access process in real time, automatically identify potential failure hazards, and respond before failures occur to ensure data stability and availability. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a method and system for intelligent management of geographic science information based on big data analysis to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The intelligent management method of geographic science information based on big data analysis includes the following steps:

[0007] Step S1, obtaining image compression distortion information during the high-resolution image data access process, obtaining an image compression distortion coefficient according to the image compression distortion information, and evaluating the influence of the abnormal degree of image compression distortion on the high-resolution image data access;

[0008] Step S2, obtaining format conversion information of the high-resolution image data access process, obtaining a format conversion abnormality coefficient according to the format conversion information, and evaluating the influence of abnormality degrees of different high-resolution image data format conversions on the high-resolution image data access;

[0009] Step S3, obtaining external attack pressure information of the high-resolution image data access process, obtaining an external attack pressure coefficient according to the external attack pressure information, and evaluating the influence of the external attack pressure of the data access process on the high-resolution image data access;

[0010] Step S4, constructing an image data access hidden danger assessment model according to the image compression distortion coefficient, the format conversion abnormality coefficient, and the external attack pressure coefficient, generating an image data access hidden danger assessment index, and responding to and identifying potential hidden dangers in the high-resolution image data access process;

[0011] Step S5: when there are potential risks in the high-resolution image data access process, determine the early warning time of the high-risk risks in the high-resolution image data access process in combination with the current data access scale.

[0012] In a preferred embodiment, by acquiring image compression distortion information during the high-resolution image data access process, analyzing the image compression distortion during the high-resolution image data access process, and acquiring the image compression distortion coefficient, the influence of the abnormal degree of image compression distortion on the high-resolution image data access is measured;

[0013] The logic for obtaining the image compression distortion coefficient is as follows:

[0014] Get the width, height, and color depth of the high-resolution image before compression, and calculate the size of the high-resolution image before compression. The expression is as follows Where DA1 represents the size of the high-resolution image before compression, Kd represents the width of the high-resolution image, Gd represents the height of the high-resolution image, and Ys represents the color depth of the high-resolution image;

[0015] Calculate the image compression ratio YSB, the expression is as follows Where DA2 represents the compressed size of the high-resolution image;

[0016] Calculate the image peak signal-to-noise ratio YFZ, the expression is as follows Where MSE represents the mean square error of the high-resolution image before and after compression, and the calculation expression is as follows Where Yq(x i ) represents the pixel x of the high-resolution image before compression i The value of Yh(x i ) represents the pixel x after high-resolution image compression i , i={1,2,...,I}, I is a positive integer;

[0017] Calculate the image structure similarity index SSI, the expression is as follows where μ x Represents the pixel mean value of high-resolution image before compression, μ y represents the pixel mean value after high-resolution image compression, σ x represents the pixel standard deviation of the high-resolution image before compression, σ y represents the pixel standard deviation of the high-resolution image after compression, xf represents the covariance of the high-resolution image before and after compression, C1 and C2 are constants used to stabilize the calculation and avoid the denominator being zero;

[0018] Calculate the image compression distortion coefficient Yxys, the expression is as follows Among them YSB j Indicates the image compression ratio of the jth image compression behavior, YFZ j The image peak signal-to-noise ratio (SSI) of the jth image compression behavior j The image structure similarity index representing the j-th image compression behavior.

[0019] In a preferred embodiment, by acquiring format conversion information of the high-resolution image data access process, analyzing the format conversion situation of the high-resolution image data access process, and acquiring a format conversion abnormality coefficient, the influence of the abnormality of the image format conversion on the high-resolution image data access is measured;

[0020] The logic for obtaining the format conversion anomaly coefficient is as follows:

[0021] Get the storage byte size G1 before high-resolution image format conversion and the storage byte size G2 after format conversion, and calculate the format conversion size difference GS. The expression is as follows Get the start time T1 and end time T2 of the high-resolution image format conversion, and calculate the format conversion time delay GY, which is expressed as follows Where TY represents the expected format conversion time; obtain the pixel value distribution before and after the high-resolution image format conversion, and calculate the entropy value SZ1 before the high-resolution image format conversion. The expression is as follows Where P nIt represents the probability of the nth pixel value appearing before the high-resolution image format conversion, which is calculated by dividing the frequency of the pixel value by the total number of pixels, n = {1, 2, ..., N}, N is a positive integer; the entropy value difference SZC of the high-resolution image format conversion is calculated, and the expression is as follows SZC = |SZ1-SZ2|, where SZ2 represents the entropy value after the high-resolution image format conversion; the format conversion anomaly coefficient Gszy is calculated, and the expression is as follows Gszy = e GS+GY+SZC .

[0022] In a preferred embodiment, by acquiring external attack pressure information during the high-resolution image data access process, analyzing the external attack situation during the high-resolution image data access process, and acquiring the external attack pressure coefficient, the degree of external attack pressure during the high-resolution image data access process is measured;

[0023] The logic for obtaining the external attack pressure coefficient is as follows:

[0024] Obtain the network attack traffic WG during the access process of high-resolution image data and calculate the attack intensity GJ. The expression is as follows Where NT represents the normal network traffic level; obtain the number of failed data accesses SC and the total number of accesses ZF, and calculate the access intensity FW, the expression is as follows According to the hash algorithm, the data is verified and the amount of tampered data CG is counted, and the data tampering ratio SL is calculated. The expression is as follows Where ZS represents the total data volume; calculate the external attack pressure coefficient Wbgj, the expression is as follows Wbgj=GJ*FW*SL.

[0025] In a preferred embodiment, an image data access hidden danger assessment model is constructed based on the image compression distortion coefficient, the format conversion abnormality coefficient, and the external attack pressure coefficient to generate an image data access hidden danger assessment index HDI. The model is based on the following formula: Wherein a1, a2, and a3 represent preset proportional coefficients of image compression distortion coefficient, format conversion abnormality coefficient, and external attack pressure coefficient, respectively, and a1, a2, and a3 are all greater than 0.

[0026] In a preferred embodiment, the image data access hidden danger assessment index is compared with a preset image data access hidden danger assessment index threshold, and the potential hidden dangers in the high-resolution image data access process are responded and identified, as follows:

[0027] If the image data access hidden danger assessment index is greater than the image data access hidden danger assessment index threshold, an access hidden danger initial appearance signal is generated;

[0028] If the image data access risk assessment index is less than or equal to the image data access risk assessment index threshold, there is no need to generate an access risk initial occurrence signal.

[0029] In a preferred embodiment, when an initial access risk signal is generated, the output values ​​of the image data access risk assessment model at different subsequent times and the data access scale are obtained, a warning timing prediction model is constructed, and a warning timing prediction value YJS is generated. The model is based on the following formula: Among them HDI t represents the image data access hazard assessment index generated by the image data access hazard assessment model at time t, It represents the average value of the image data access risk assessment index. The calculation expression is as follows SJG t represents the data access volume of the system at time t, Represents the average value of data access volume, and the calculation expression is as follows T is a positive integer.

[0030] In a preferred implementation, the warning timing prediction value is compared with a preset warning timing prediction value threshold to determine the warning timing of high-risk hidden dangers in the high-resolution image data access process, as follows:

[0031] If the warning opportunity prediction value is greater than the warning opportunity prediction value threshold, a warning signal is generated;

[0032] If the warning opportunity prediction value is less than or equal to the warning opportunity prediction value threshold, there is no need to generate a warning signal.

[0033] In a preferred embodiment, the intelligent management system for geographic science information based on big data analysis includes an image compression distortion module, an image format conversion module, an external attack pressure module, a comprehensive evaluation module, and an early warning module;

[0034] An image compression distortion module is used to obtain image compression distortion information during the high-resolution image data access process, obtain image compression distortion coefficients based on the image compression distortion information, and evaluate the impact of the abnormal degree of image compression distortion on the high-resolution image data access;

[0035] An image format conversion module is used to obtain format conversion information of the high-resolution image data access process, obtain a format conversion anomaly coefficient based on the format conversion information, and evaluate the impact of different high-resolution image data format conversion anomalies on high-resolution image data access;

[0036] An external attack pressure module is used to obtain external attack pressure information of the high-resolution image data access process, obtain an external attack pressure coefficient based on the external attack pressure information, and evaluate the impact of the external attack pressure of the data access process on the high-resolution image data access;

[0037] Comprehensive assessment module, used to build an image data access hidden danger assessment model based on image compression distortion coefficient, format conversion anomaly coefficient, and external attack pressure coefficient, generate an image data access hidden danger assessment index, and respond to and identify potential hidden dangers in the process of high-resolution image data access;

[0038] The early warning module is used to determine the early warning time of high-risk hidden dangers in the high-resolution image data access process in combination with the current data access scale when there are potential hidden dangers in the high-resolution image data access process.

[0039] Technical effects and advantages of the present invention:

[0040] 1. The present invention generates image compression distortion coefficients, format conversion anomaly coefficients and external attack pressure coefficients respectively by acquiring and quantifying image compression distortion information, format conversion information and external attack pressure information, accurately assesses the influence of different abnormal factors in the access process of high-resolution image data, and can comprehensively cover the potential sources of hidden dangers in the access link of high-resolution image data. By integrating image compression distortion coefficients, format conversion anomaly coefficients and external attack pressure coefficients, an image data access hidden danger assessment model is constructed to generate an image data access hidden danger assessment index, quantitatively characterize the overall risk level of potential hidden dangers in the image data access process, and achieve real-time assessment of hidden dangers in a complex data access environment. After the potential hidden dangers are identified, a warning opportunity prediction model is constructed in combination with the real-time data access scale. The warning opportunity prediction value is calculated according to the dynamic change of the hidden danger assessment index and the scale of data access. By comparing with the set threshold, it is intelligently judged whether there are high-risk hidden dangers in the access process of high-resolution image data, thereby achieving early warning and accurate response, avoiding fault escalation, greatly improving the real-time performance and response capability of the image data management system, effectively reducing the waste of resources and the risk of decision-making errors caused by access delays or faults, and ensuring the stability of the image data management process. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0042] Figure 1 This is a flow chart of the method of embodiment 1 of the present invention;

[0043] Figure 2 This is a flow chart of the system of Example 2 of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Embodiment 1: Figure 1 The present invention provides a method for intelligent management of geographic science information based on big data analysis, which includes the following steps:

[0046] Step S1, obtaining image compression distortion information during the high-resolution image data access process, obtaining an image compression distortion coefficient according to the image compression distortion information, and evaluating the influence of the abnormal degree of image compression distortion on the high-resolution image data access;

[0047] Step S2, obtaining format conversion information of the high-resolution image data access process, obtaining a format conversion abnormality coefficient according to the format conversion information, and evaluating the influence of abnormality degrees of different high-resolution image data format conversions on the high-resolution image data access;

[0048] Step S3, obtaining external attack pressure information of the high-resolution image data access process, obtaining an external attack pressure coefficient according to the external attack pressure information, and evaluating the influence of the external attack pressure of the data access process on the high-resolution image data access;

[0049] Step S4, constructing an image data access hidden danger assessment model according to the image compression distortion coefficient, the format conversion abnormality coefficient, and the external attack pressure coefficient, generating an image data access hidden danger assessment index, and responding to and identifying potential hidden dangers in the high-resolution image data access process;

[0050] Step S5, when there are potential risks in the high-resolution image data access process, determine the early warning time of the high-risk risks in the high-resolution image data access process in combination with the current data access scale;

[0051] Step S1, obtaining image compression distortion information during the high-resolution image data access process, obtaining an image compression distortion coefficient according to the image compression distortion information, and evaluating the influence of the abnormal degree of image compression distortion on the high-resolution image data access;

[0052] High-resolution image data usually needs to be compressed and aggregated to save storage space. In the process of accessing high-resolution image data, repeated compression and release of data will inevitably introduce compression distortion and affect the access quality of image data. The image compression distortion coefficient is used to measure the degree of quality loss caused by data compression during the compression and decompression process of high-resolution image data, as well as the degree of impact of this quality loss on the image data access process. During the data access process, image compression distortion may cause incomplete image information, blurred details or loss of key features, thereby affecting the accuracy and reliability of accessed data. By calculating the image compression distortion coefficient, problems such as image blurring and detail loss caused by compression during the access process of high-resolution image data can be perceived in a timely manner to ensure the reliability of accessed data. Potential data access problems, such as loss of details caused by excessively high compression ratios, can be detected through the image compression distortion coefficient to avoid decision delays due to data defects.

[0053] A larger image compression distortion coefficient indicates that the data quality has been greatly affected due to frequent compression and decompression operations during data access, which may cause key information to be weakened during transmission or storage, thereby increasing data access delays, instability, and potential risks, affecting the efficiency and accuracy of real-time query and processing, and thus having a significant impact on the actual application value of high-resolution image data, such as reducing analysis accuracy, decision reliability, and data availability; on the contrary, it indicates that high-resolution image data has maintained a high quality during the compression and decompression process, key information has not been significantly lost, and the data access process is more stable and efficient, which can ensure fast and accurate real-time query and processing. This means that the transmission and storage of image data is more reliable, which can better support the needs of high-resolution image data in various applications, and improve analysis accuracy, decision reliability, and data availability;

[0054] Therefore, by obtaining the image compression distortion information of the high-resolution image data access process, analyzing the image compression distortion of the high-resolution image data access process, and obtaining the image compression distortion coefficient, the influence of the abnormal degree of image compression distortion on the high-resolution image data access is measured;

[0055] The logic for obtaining the image compression distortion coefficient is as follows:

[0056] Get the width, height, and color depth of the high-resolution image before compression, and calculate the size of the high-resolution image before compression. The expression is as follows Where DA1 represents the size of the high-resolution image before compression, Kd represents the width of the high-resolution image, Gd represents the height of the high-resolution image, and Ys represents the color depth of the high-resolution image;

[0057] It should be noted that color depth refers to the number of bits per pixel in a high-resolution image;

[0058] Calculate the image compression ratio YSB, the expression is as follows Where DA2 represents the compressed size of the high-resolution image;

[0059] Calculate the image peak signal-to-noise ratio YFZ, the expression is as follows Where MSE represents the mean square error of the high-resolution image before and after compression, and the calculation expression is as follows Where Yq(x i ) represents the pixel x of the high-resolution image before compression i The value of Yh(x i ) represents the pixel x after high-resolution image compression i , i={1,2,...,I}, I is a positive integer;

[0060] Calculate the image structure similarity index SSI, the expression is as follows where μ x Represents the pixel mean value of high-resolution image before compression, μ y represents the pixel mean value after high-resolution image compression, σ x represents the pixel standard deviation of the high-resolution image before compression, σ y represents the pixel standard deviation of the high-resolution image after compression, xf represents the covariance of the high-resolution image before and after compression, C1 and C2 are constants used to stabilize the calculation and avoid the denominator being zero;

[0061] Calculate the image compression distortion coefficient Yxys, the expression is as follows Among them YSB j Indicates the image compression ratio of the jth image compression behavior, YFZ j The image peak signal-to-noise ratio (SSI) of the jth image compression behavior j The image structure similarity index representing the j-th image compression behavior;

[0062] It should be noted that before calculating the image compression distortion coefficient, it is necessary to ensure that the image compression ratio, image peak signal-to-noise ratio, and image structure similarity index are all normalized. Commonly used normalization methods include Min-Max normalization and Z-Score normalization.

[0063] Step S2, obtaining format conversion information of the high-resolution image data access process, obtaining a format conversion abnormality coefficient according to the format conversion information, and evaluating the influence of abnormality degrees of different high-resolution image data format conversions on the high-resolution image data access;

[0064] The format conversion anomaly coefficient is a key indicator used to measure the degree of anomalies caused by format conversion during the data access process of high-resolution images, as well as the impact on image access efficiency and data integrity. By calculating the format conversion anomaly coefficient, the degree of anomalies in the format conversion process of high-resolution image data can be accurately evaluated, and the impact of data size changes, increased latency, and image quality degradation caused by the conversion can be quantified, providing support for identifying performance bottlenecks. At the same time, the format conversion anomaly coefficient comprehensively reflects the all-round impact of the conversion on storage efficiency, access speed, and image quality, which helps to optimize the storage and access strategy of high-resolution image data, improve the stability, accuracy, and practical application value of data processing, and thus ensure efficient access and reliable use of image data in multiple scenarios.

[0065] A larger format conversion anomaly coefficient may reduce access efficiency, weaken data stability, and damage image quality. Specifically, abnormal format conversion may increase processing time, reduce data access speed, affect real-time requirements, and cause data loss or damage, making it difficult to ensure data consistency and integrity during the access process. It may also cause image quality degradation, such as reduced resolution or loss of details, further affecting the accurate interpretation and subsequent analysis of the image, and ultimately weakening the practical application value of high-resolution image data. On the contrary, a smaller format conversion anomaly coefficient indicates that the format conversion process is more efficient and stable, data access speed is faster, consistency and integrity are guaranteed, image quality can be better preserved, ensuring accurate interpretation and analysis of image data, thereby improving the practical application value of high-resolution image data.

[0066] Therefore, by obtaining the format conversion information of the high-resolution image data access process, analyzing the format conversion situation of the high-resolution image data access process, and obtaining the format conversion abnormality coefficient, the influence of the abnormal degree of image format conversion on the high-resolution image data access is measured;

[0067] The logic for obtaining the format conversion anomaly coefficient is as follows:

[0068] Get the storage byte size G1 before high-resolution image format conversion and the storage byte size G2 after format conversion, and calculate the format conversion size difference GS. The expression is as follows Get the start time T1 and end time T2 of the high-resolution image format conversion, and calculate the format conversion time delay GY, which is expressed as follows Where TY represents the expected format conversion time; obtain the pixel value distribution before and after the high-resolution image format conversion, and calculate the entropy value SZ1 before the high-resolution image format conversion. The expression is as follows Where P nIt represents the probability of the nth pixel value appearing before the high-resolution image format conversion, which is calculated by dividing the frequency of the pixel value by the total number of pixels, n = {1, 2, ..., N}, N is a positive integer; the entropy value difference SZC of the high-resolution image format conversion is calculated, and the expression is as follows SZC = |SZ1-SZ2|, where SZ2 represents the entropy value after the high-resolution image format conversion; the format conversion anomaly coefficient Gszy is calculated, and the expression is as follows Gszy = e GS+GY+SZC ;

[0069] It should be noted that before calculating the format conversion anomaly coefficient, it is necessary to ensure that the format conversion size difference, format conversion time delay, and entropy value difference of high-resolution image format conversion are all normalized;

[0070] Step S3, obtaining external attack pressure information of the high-resolution image data access process, obtaining an external attack pressure coefficient according to the external attack pressure information, and evaluating the influence of the external attack pressure of the data access process on the high-resolution image data access;

[0071] During the access process of high-resolution image data, external attack pressure may affect the access speed, integrity and security of the data. The external attack pressure coefficient is used to measure the severity of external attacks in the data access process of high-resolution images, as well as the degree of impact on the access of high-resolution image data, taking into account various attack methods (such as denial of service attacks, malware infection, data theft, tampering, etc.); by calculating the external attack pressure coefficient, the impact of external attacks on the access process of high-resolution image data can be comprehensively evaluated, especially in terms of the speed, stability, security and integrity of data access. The external attack pressure coefficient can quantify the intensity of external attacks, the impact on data availability and integrity, and the potential threat to security, thereby providing a strong basis for data protection and emergency response;

[0072] Specifically, when the external attack pressure coefficient is large, it indicates that there is strong attack pressure, which may lead to many problems in the data access process, including reduced access speed, data loss, tampering or leakage risks. At this time, the availability and integrity of the data will be threatened, and may even cause the system to be unable to provide efficient and stable services, affecting the practical application of high-resolution images. In addition, the severity of external attacks may also undermine the security of data, leading to the leakage of sensitive information or malicious tampering, which will cause long-term damage to the credibility and reliability of the entire image data, reducing the actual application value of the data;

[0073] On the contrary, a smaller external attack pressure coefficient indicates a lower attack pressure, a smaller impact on the data access process, and the ability to ensure fast and stable access to high-resolution image data, and the effective protection of data security and integrity. Therefore, by calculating the external attack pressure coefficient, not only can potential attack risks be identified, but appropriate protective measures can also be taken when the attack pressure is high, such as optimizing the data transmission process, strengthening security protection, and improving the system's fault tolerance, thereby enhancing the security and reliability of high-resolution image data and ensuring its normal use in complex environments;

[0074] Therefore, by obtaining the external attack pressure information of the high-resolution image data access process, the external attack situation in the high-resolution image data access process is analyzed, and the external attack pressure coefficient is obtained to measure the degree of external attack pressure in the high-resolution image data access process;

[0075] The logic for obtaining the external attack pressure coefficient is as follows:

[0076] Obtain the network attack traffic WG during the access process of high-resolution image data and calculate the attack intensity GJ. The expression is as follows Where NT represents the normal network traffic level; obtain the number of failed data accesses SC and the total number of accesses ZF, and calculate the access intensity FW, the expression is as follows According to the hash algorithm, the data is verified and the amount of tampered data CG is counted, and the data tampering ratio SL is calculated. The expression is as follows Where ZS represents the total data volume; calculate the external attack pressure coefficient Wbgj, the expression is as follows Wbgj=GJ*FW*SL;

[0077] Step S4, constructing an image data access hidden danger assessment model according to the image compression distortion coefficient, the format conversion abnormality coefficient, and the external attack pressure coefficient, generating an image data access hidden danger assessment index, and responding to and identifying potential hidden dangers in the high-resolution image data access process;

[0078] According to the image compression distortion coefficient, format conversion anomaly coefficient, and external attack pressure coefficient, an image data access hidden danger assessment model is constructed to generate the image data access hidden danger assessment index HDI. The formula based on the model is as follows: Where a1, a2, and a3 represent the preset proportional coefficients of the image compression distortion coefficient, the format conversion abnormality coefficient, and the external attack pressure coefficient, respectively, and a1, a2, and a3 are all greater than 0;

[0079] It should be noted that before constructing the image data access risk assessment model, it is necessary to ensure that the image compression distortion coefficient, format conversion anomaly coefficient, and external attack pressure coefficient are all normalized; a1, a2, and a3 are set according to actual conditions. For example, the expert empowerment method is adopted, that is, experts in related fields are invited to determine the preset proportional coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0080] It can be seen from the above calculation expression that the larger the image compression distortion coefficient, the larger the format conversion abnormality coefficient, and the larger the external attack pressure coefficient, the larger the image data access hidden danger assessment index is, indicating that the abnormal degree of image compression distortion, the abnormal degree of different high-resolution image data format conversion, and the external attack pressure of the data access process have a deeper impact on the high-resolution image data access. On the contrary, the smaller the image compression distortion coefficient, the smaller the format conversion abnormality coefficient, and the smaller the external attack pressure coefficient, the smaller the image data access hidden danger assessment index is, indicating that the abnormal degree of image compression distortion, the abnormal degree of different high-resolution image data format conversion, and the external attack pressure of the data access process have a shallower impact on the high-resolution image data access.

[0081] The image data access hidden danger assessment index is compared with the preset image data access hidden danger assessment index threshold, and the potential hidden dangers in the high-resolution image data access process are responded and identified, as follows:

[0082] If the image data access hidden danger assessment index is greater than the image data access hidden danger assessment index threshold, it indicates that the potential hidden danger situation in the high-resolution image data access process is more serious, and an initial access hidden danger signal is generated;

[0083] If the image data access hidden danger assessment index is less than or equal to the image data access hidden danger assessment index threshold, it indicates that there is no potential hidden danger in the high-resolution image data access process, and there is no need to generate an access hidden danger initial appearance signal;

[0084] Step S5, when there are potential risks in the high-resolution image data access process, determine the early warning time of the high-risk risks in the high-resolution image data access process in combination with the current data access scale;

[0085] When the initial access hazard signal is generated, the output values ​​of the image data access hazard assessment model at different subsequent times and the data access scale are obtained, and the warning timing prediction model is constructed to generate the warning timing prediction value YJS. The model is based on the following formula: Among them HDI t represents the image data access hazard assessment index generated by the image data access hazard assessment model at time t, It represents the average value of the image data access risk assessment index. The calculation expression is as follows SJG t represents the data access volume of the system at time t, Represents the average value of data access volume, and the calculation expression is as follows T is a positive integer;

[0086] The warning timing prediction value is compared with the preset warning timing prediction value threshold to determine the warning timing of high-risk hidden dangers in the high-resolution image data access process, as follows:

[0087] If the warning opportunity prediction value is greater than the warning opportunity prediction value threshold, it indicates that there is a high-risk hidden danger in the high-resolution image data access process, and a warning signal is generated;

[0088] If the warning opportunity prediction value is less than or equal to the warning opportunity prediction value threshold, it indicates that the hidden dangers in the high-resolution image data access process and the current access scale are still within the controllable range, and there is no need to generate a warning signal;

[0089] The present invention acquires and quantifies image compression distortion information, format conversion information and external attack pressure information, respectively generates image compression distortion coefficient, format conversion abnormality coefficient and external attack pressure coefficient, accurately evaluates the influence of different abnormal factors in the access process of high-resolution image data, and can comprehensively cover the potential sources of hidden dangers in the access link of high-resolution image data. By integrating image compression distortion coefficient, format conversion abnormality coefficient and external attack pressure coefficient, an image data access hidden danger assessment model is constructed to generate an image data access hidden danger assessment index, quantitatively characterize the overall risk level of potential hidden dangers in the image data access process, and realize real-time assessment of hidden dangers in a complex data access environment. After the potential hidden dangers are identified, a warning opportunity prediction model is constructed in combination with the real-time data access scale, and the warning opportunity prediction value is calculated according to the dynamic change of the hidden danger assessment index and the scale of data access. By comparing with the set threshold, it is intelligently judged whether there are high-risk hidden dangers in the access process of high-resolution image data, thereby realizing early warning and accurate response, avoiding fault escalation, greatly improving the real-time performance and response capability of the image data management system, effectively reducing the waste of resources and the risk of decision-making errors caused by access delays or faults, and ensuring the stability of the image data management process.

[0090] Example 2: This example is an introduction to the intelligent management system of geographic science information based on big data analysis. Figure 2 As shown, it includes an image compression distortion module, an image format conversion module, an external attack pressure module, a comprehensive evaluation module, and an early warning module;

[0091] An image compression distortion module is used to obtain image compression distortion information during the high-resolution image data access process, obtain image compression distortion coefficients based on the image compression distortion information, and evaluate the impact of the abnormal degree of image compression distortion on the high-resolution image data access;

[0092] An image format conversion module is used to obtain format conversion information of the high-resolution image data access process, obtain a format conversion anomaly coefficient based on the format conversion information, and evaluate the impact of different high-resolution image data format conversion anomalies on high-resolution image data access;

[0093] An external attack pressure module is used to obtain external attack pressure information of the high-resolution image data access process, obtain an external attack pressure coefficient based on the external attack pressure information, and evaluate the impact of the external attack pressure of the data access process on the high-resolution image data access;

[0094] Comprehensive assessment module, used to build an image data access hidden danger assessment model based on image compression distortion coefficient, format conversion anomaly coefficient, and external attack pressure coefficient, generate an image data access hidden danger assessment index, and respond to and identify potential hidden dangers in the process of high-resolution image data access;

[0095] The early warning module is used to determine the early warning time of high-risk hidden dangers in the high-resolution image data access process in combination with the current data access scale when there are potential hidden dangers in the high-resolution image data access process.

[0096] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0097] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0098] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0099] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and method described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0100] In several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways.

[0101] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent management method for geographic science information based on big data analysis, characterized by: The steps include: Step S1, obtaining image compression distortion information during the high-resolution image data access process, obtaining an image compression distortion coefficient according to the image compression distortion information, and evaluating the influence of the abnormal degree of image compression distortion on the high-resolution image data access; Step S2, obtaining format conversion information of the high-resolution image data access process, obtaining a format conversion abnormality coefficient according to the format conversion information, and evaluating the influence of abnormality degrees of different high-resolution image data format conversions on the high-resolution image data access; Step S3, obtaining external attack pressure information of the high-resolution image data access process, obtaining an external attack pressure coefficient according to the external attack pressure information, and evaluating the influence of the external attack pressure of the data access process on the high-resolution image data access; Step S4, constructing an image data access hidden danger assessment model according to the image compression distortion coefficient, the format conversion abnormality coefficient, and the external attack pressure coefficient, generating an image data access hidden danger assessment index, and responding to and identifying potential hidden dangers in the high-resolution image data access process; Step S5: when there are potential risks in the high-resolution image data access process, determine the early warning time of the high-risk risks in the high-resolution image data access process in combination with the current data access scale.

2. The method for intelligent management of geographic science information based on big data analysis according to claim 1 is characterized by: By acquiring image compression distortion information during the access process of high-resolution image data, analyzing the image compression distortion during the access process of high-resolution image data, and obtaining the image compression distortion coefficient, the influence of the abnormal degree of image compression distortion on the access of high-resolution image data is measured; The logic for obtaining the image compression distortion coefficient is as follows: Get the width, height, and color depth of the high-resolution image before compression, and calculate the size of the high-resolution image before compression. The expression is as follows Where DA1 represents the size of the high-resolution image before compression, Kd represents the width of the high-resolution image, Gd represents the height of the high-resolution image, and Ys represents the color depth of the high-resolution image; Calculate the image compression ratio YSB, the expression is as follows Where DA2 represents the compressed size of the high-resolution image; Calculate the image peak signal-to-noise ratio YFZ, the expression is as follows Where MSE represents the mean square error of the high-resolution image before and after compression, and the calculation expression is as follows Where Yq(x i ) represents the pixel x of the high-resolution image before compression i The value of Yh(x i ) represents the pixel x after high-resolution image compression i , i={1,2,...,I}, I is a positive integer; Calculate the image structure similarity index SSI, the expression is as follows where μ x Represents the pixel mean value of high-resolution image before compression, μ y represents the pixel mean value after high-resolution image compression, σ x represents the pixel standard deviation of the high-resolution image before compression, σ y represents the pixel standard deviation of the high-resolution image after compression, xf represents the covariance of the high-resolution image before and after compression, C1 and C2 are constants used to stabilize the calculation and avoid the denominator being zero; Calculate the image compression distortion coefficient Yxys, the expression is as follows Among them YSB j Indicates the image compression ratio of the jth image compression behavior, YFZ j The image peak signal-to-noise ratio (SSI) of the jth image compression behavior j The image structure similarity index representing the j-th image compression behavior.

3. The method for intelligent management of geographic science information based on big data analysis according to claim 1 is characterized in that: By acquiring the format conversion information of the high-resolution image data access process, analyzing the format conversion situation of the high-resolution image data access process, and obtaining the format conversion abnormality coefficient, the influence of the abnormal degree of image format conversion on the high-resolution image data access is measured; The logic for obtaining the format conversion anomaly coefficient is as follows: Get the storage byte size G1 before high-resolution image format conversion and the storage byte size G2 after format conversion, and calculate the format conversion size difference GS. The expression is as follows Get the start time T1 and end time T2 of the high-resolution image format conversion, and calculate the format conversion time delay GY, which is expressed as follows Where TY represents the expected format conversion time; obtain the pixel value distribution before and after the high-resolution image format conversion, and calculate the entropy value SZ1 before the high-resolution image format conversion. The expression is as follows Where P n It represents the probability of the nth pixel value appearing before the high-resolution image format conversion, which is calculated by dividing the frequency of the pixel value by the total number of pixels, n = {1, 2, ..., N}, N is a positive integer; the entropy value difference SZC of the high-resolution image format conversion is calculated, and the expression is as follows SZC = |SZ1-SZ2|, where SZ2 represents the entropy value after the high-resolution image format conversion; the format conversion anomaly coefficient Gszy is calculated, and the expression is as follows Gszy = e GS+GY+SZC .

4. The method for intelligent management of geographic science information based on big data analysis according to claim 1 is characterized in that: By obtaining the external attack pressure information of the high-resolution image data access process, analyzing the external attack situation in the high-resolution image data access process, and obtaining the external attack pressure coefficient, the degree of external attack pressure in the high-resolution image data access process is measured; The logic for obtaining the external attack pressure coefficient is as follows: Obtain the network attack traffic WG during the access process of high-resolution image data and calculate the attack intensity GJ. The expression is as follows Where NT represents the normal network traffic level; obtain the number of failed data accesses SC and the total number of accesses ZF, and calculate the access intensity FW, the expression is as follows According to the hash algorithm, the data is verified and the amount of tampered data CG is counted, and the data tampering ratio SL is calculated. The expression is as follows Where ZS represents the total data volume; calculate the external attack pressure coefficient Wbgj, the expression is as follows Wbgj=GJ*FW*SL.

5. The method for intelligent management of geographic science information based on big data analysis according to claim 1 is characterized in that: According to the image compression distortion coefficient, format conversion anomaly coefficient, and external attack pressure coefficient, an image data access hidden danger assessment model is constructed to generate the image data access hidden danger assessment index HDI. The formula based on the model is as follows: Wherein a1, a2, and a3 represent preset proportional coefficients of image compression distortion coefficient, format conversion abnormality coefficient, and external attack pressure coefficient, respectively, and a1, a2, and a3 are all greater than 0.

6. The method for intelligent management of geographic science information based on big data analysis according to claim 5 is characterized by: The image data access hidden danger assessment index is compared with the preset image data access hidden danger assessment index threshold, and the potential hidden dangers in the high-resolution image data access process are responded and identified, as follows: If the image data access hidden danger assessment index is greater than the image data access hidden danger assessment index threshold, an access hidden danger initial appearance signal is generated; If the image data access risk assessment index is less than or equal to the image data access risk assessment index threshold, there is no need to generate an access risk initial occurrence signal.

7. The method for intelligent management of geographic science information based on big data analysis according to claim 6 is characterized by: When the initial access hazard signal is generated, the output values ​​of the image data access hazard assessment model at different subsequent times and the data access scale are obtained, and the warning timing prediction model is constructed to generate the warning timing prediction value YJS. The model is based on the following formula: Among them HDI t represents the image data access hazard assessment index generated by the image data access hazard assessment model at time t, It represents the average value of the image data access risk assessment index. The calculation expression is as follows SJG t represents the data access volume of the system at time t, Represents the average value of data access volume, and the calculation expression is as follows t={1,2,...,T}, T is a positive integer.

8. The method for intelligent management of geographic science information based on big data analysis according to claim 7 is characterized in that: The warning timing prediction value is compared with the preset warning timing prediction value threshold to determine the warning timing of high-risk hidden dangers in the high-resolution image data access process, as follows: If the warning opportunity prediction value is greater than the warning opportunity prediction value threshold, a warning signal is generated; If the warning opportunity prediction value is less than or equal to the warning opportunity prediction value threshold, there is no need to generate a warning signal.

9. An intelligent management system for geographic science information based on big data analysis, used to implement the intelligent management method for geographic science information based on big data analysis as described in any one of claims 1 to 8, characterized in that: It includes image compression distortion module, image format conversion module, external attack pressure module, comprehensive evaluation module and early warning module; An image compression distortion module is used to obtain image compression distortion information during the high-resolution image data access process, obtain image compression distortion coefficients based on the image compression distortion information, and evaluate the impact of the abnormal degree of image compression distortion on the high-resolution image data access; An image format conversion module is used to obtain format conversion information of the high-resolution image data access process, obtain a format conversion anomaly coefficient based on the format conversion information, and evaluate the impact of different high-resolution image data format conversion anomalies on high-resolution image data access; An external attack pressure module is used to obtain external attack pressure information of the high-resolution image data access process, obtain an external attack pressure coefficient based on the external attack pressure information, and evaluate the impact of the external attack pressure of the data access process on the high-resolution image data access; Comprehensive assessment module, used to build an image data access hidden danger assessment model based on image compression distortion coefficient, format conversion anomaly coefficient, and external attack pressure coefficient, generate an image data access hidden danger assessment index, and respond to and identify potential hidden dangers in the process of high-resolution image data access; The early warning module is used to determine the early warning time of high-risk hidden dangers in the high-resolution image data access process in combination with the current data access scale when there are potential hidden dangers in the high-resolution image data access process.

Images