Archive information mining system based on data analysis

Abstract

The invention discloses an archive information mining system based on data analysis, particularly relates to the field of archive information management, and comprises a data acquisition module, a data extraction module, a first data analysis module, a second data analysis module and a comprehensive analysis module. Through the data acquisition, extraction and analysis module, archive information can be comprehensively and accurately acquired and processed, a scientific basis is provided for repair work, and each analysis unit in the second data analysis module further quantitatively evaluates repair difficulty, optimizes a material ratio, monitors environment quality and evaluates a repair effect. And the comprehensive analysis module comprehensively and objectively reflects the porcelain repair quality by calculating a comprehensive optimization index, a scientific standard is provided for evaluation and improvement of the repair work, and on the whole, the precision and efficiency of archive information mining are improved, and innovation is brought to archive work such as ancient porcelain repair.

Description

Technical Field

[0001] The present invention relates to the technical field of archive information management, and more specifically, to an archive information mining system based on data analysis. Background Art

[0002] In the field of archival information management, the rapid development of information technology and the explosive growth of data volume have made efficient and accurate mining of archival information particularly important. This field is not only related to the modernization process of archival management, but also plays a key role in many aspects such as cultural relics protection and historical research.

[0003] In the existing technology, the management and mining of archival information usually rely on automated information systems. These systems process, classify and store archival data through preset algorithms and programs, and realize rapid query and utilization of information through efficient retrieval mechanisms. This process has improved the efficiency and accuracy of archival management to a certain extent, and provided strong support for the widespread application of archival information.

[0004] However, although the existing technology has achieved certain results, there are still some obvious shortcomings in practical applications. For example, in the face of massive and complex archival data, the depth and breadth of data mining in the existing system still needs to be improved; at the same time, there are certain challenges in the accuracy and completeness of information. Therefore, in order to further improve the efficiency and quality of archival information management, it is still necessary to continuously explore and innovate more advanced technical means. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an archive information mining system based on data analysis, which solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solution: an archive information mining system based on data analysis, comprising: Data collection module: used to collect archive data from the target archive storage source and aggregate the data into the data warehouse; Data extraction module: used to extract first archive data from source data, the first archive data including first restoration difficulty assessment data, first restoration material ratio data, first environmental monitoring data and first restoration effect data, pre-process the first archive data and transmit it to the first data analysis module; The first data analysis module is used to analyze the first file data to obtain the second file data, the second file data includes the second restoration difficulty assessment data, the second restoration material ratio data, the second environmental monitoring data and the second restoration effect data, and transmit the second file data to the second data analysis module; The second data analysis module includes a second restoration difficulty assessment data analysis unit, a second restoration material ratio data analysis unit, a second environmental monitoring data analysis unit, and a second restoration effect data analysis unit, and is used to analyze the second file data to obtain third file data, and transmit the third file data to the comprehensive analysis module; Comprehensive analysis module: used to establish a comprehensive analysis model to conduct comprehensive analysis on the third-party archive data, calculate the comprehensive optimization index of the target archive storage source, and analyze the quality of porcelain restoration based on the comprehensive optimization index.

[0007] Preferably, the data acquisition module is used to collect restoration difficulty assessment source data, restoration material ratio source data, environmental monitoring source data and restoration effect source data from the target archive storage source, and transmit the collected source data to the data extraction module.

[0008] Preferably, the restoration difficulty assessment source data include fragment area measurement values, dimensions of similar artifacts in archaeological materials, edge wear measurement data, microscopic photography data, glaze integrity scanning data, pattern image data, archaeological database references, image clarity measurement values, Mohs hardness test data, porosity test data and dating data; the restoration material ratio source data include material testing reports, formula records, firing process parameters, penetration test data, material physical property archives, spectrophotometer measurement data, standard color card data, material physical and chemical property test reports and accelerated aging test data; the environmental monitoring source data include environmental monitoring system records, meteorological data, illuminometer array measurement data, spot distribution scanning data, temperature monitoring time series data, air particulate monitoring data and airflow monitoring data; the restoration effect source data include surface scanning data, reflectivity measurement data, ultrasonic flaw detection data, stress distribution test data, 3D scanning comparison data, expert evaluation records, material aging data, environmental monitoring historical data and similar case statistical data.

[0009] Preferably, the first restoration difficulty assessment data includes the total area of ​​found fragments, the estimated original area of ​​the artifact, the wear rate of the fragment edge, the glaze peeling area, the glaze crack length, the average width, the total glaze area, the number of identifiable patterns, the number of standard patterns of similar artifacts of the same period, the pattern clarity coefficient, the body hardness standard value, the current hardness measurement value, the porosity coefficient and the age coefficient; the first restoration material ratio data includes the basic toughness coefficient, the toughening agent ratio, the firing temperature correction coefficient, the initial penetration rate, the capillary effect coefficient, the material density coefficient, the Euclidean distance between the standard color value and the measured color value, the maximum allowable color difference, the thermal expansion coefficient matching degree, the chemical stability Qualitative coefficient and aging test coefficient, the first environmental monitoring data includes real-time humidity, average humidity, number of monitoring points, seasonal correction coefficient, minimum illumination value, maximum illumination value, spot rate, temperature standard deviation, allowable temperature fluctuation range, basic cleanliness score, particle counting score and air flow coefficient, the first restoration effect data includes reflectivity difference of repaired parts, surface texture difference, standard visible threshold, foundation stability, stress concentration coefficient, structural integrity coefficient, morphological restoration degree, pattern restoration degree, glaze color restoration degree, overall coordination coefficient, foundation protection period, material life coefficient, environmental impact coefficient and use intensity correction coefficient.

[0010] Preferably, the preprocessing includes data cleaning and standardization.

[0011] Preferably, the second repair difficulty assessment data include the fragment integrity coefficient, glaze loss rate, original pattern recognition and body weathering index; the second repair material ratio data include tire repair material toughness value, adhesive permeability, colorant matching and material compatibility index; the second environmental monitoring data include repair environment humidity fluctuation value, lighting uniformity coefficient, temperature stability index and air cleanliness level; the second repair effect data include repair trace visibility, structural stability score, aesthetic restoration degree and protection period prediction value.

[0012] Preferably, the calculation method of the fragment integrity coefficient is fragment integrity coefficient = (total area of ​​found fragments / estimated original area of ​​the artifact) × (1-fragment edge wear rate), the calculation method of the glaze loss rate is glaze loss rate = (glaze peeling area + glaze crack length × average width) / total glaze area × 100%, the calculation method of the original pattern recognition is original pattern recognition = (number of identifiable patterns / number of standard patterns of similar artifacts of the same period) × pattern clarity coefficient, and the calculation method of the body weathering index is body weathering index = (body hardness standard value - current hardness measurement value) × porosity coefficient × age coefficient.

[0013] Preferably, the calculation method of the toughness value of the tire repair material is tire repair material toughness value = basic toughness coefficient × (1 + toughening agent ratio) × firing temperature correction coefficient, the calculation method of the adhesive permeability is adhesive permeability = initial penetration rate × capillary effect coefficient × exp (-material density coefficient), the calculation method of the color material matching degree is color material matching degree = 1-(Euclidean distance between standard color value and measured color value / maximum allowable color difference), and the calculation method of the material compatibility index is material compatibility index = (thermal expansion coefficient matching degree × 0.4 + chemical stability coefficient × 0.6) × aging test coefficient.

[0014] Preferably, the calculation method of the repair environment humidity fluctuation value is repair environment humidity fluctuation value = √(∑(real-time humidity-average humidity)² / number of monitoring points) × seasonal correction coefficient, the calculation method of the illumination uniformity coefficient is illumination uniformity coefficient = minimum illumination value / maximum illumination value × (1-spot rate), the calculation method of the temperature stability index is temperature stability index = 1-(temperature standard deviation / allowable temperature fluctuation range), and the calculation method of the air cleanliness level is air cleanliness level = (basic cleanliness score + particle count score) × air flow coefficient.

[0015] Preferably, the calculation method for the visibility of the repair marks is repair mark visibility = (reflectivity difference of the repaired part × 0.5 + surface texture difference × 0.5) / standard visible threshold, the calculation method for the structural stability score is structural stability score = basic stability × (1-stress concentration coefficient) × structural integrity coefficient, the calculation method for the aesthetic restoration degree is aesthetic restoration degree = (morphological restoration degree × 0.3 + pattern restoration degree × 0.4 + glaze color restoration degree × 0.3) × overall coordination coefficient, and the calculation method for the protection period prediction value is protection period prediction value = basic protection period × material life coefficient × environmental impact coefficient × usage intensity correction coefficient.

[0016] Preferably, the second restoration difficulty assessment data analysis unit is used to establish a second restoration difficulty assessment data analysis model, which is specifically expressed as: , DI represents the restoration difficulty index, IC represents the fragment integrity coefficient, DR represents the glaze loss rate, RR represents the original pattern recognition, and WI represents the body weathering index.

[0017] Preferably, the second repair material ratio data analysis unit is used to establish a second repair material ratio data analysis model, which is specifically expressed as: , MI represents the repair material index, TF represents the toughness value of the tire repair material, PR represents the adhesive penetration rate, CM represents the color matching degree, and CI represents the material compatibility index.

[0018] Preferably, the second environment monitoring data analysis unit is used to establish a second environment monitoring data analysis model, which is specifically expressed as: , EI represents the environmental stability index, HF represents the humidity fluctuation value of the repaired environment, LU represents the light uniformity coefficient, TS represents the temperature stability index, and AC represents the air cleanliness level.

[0019] Preferably, the second restoration effect data analysis unit is used to establish a second restoration effect data analysis model, which is specifically expressed as: , RI represents the restoration quality index, TV represents the visibility of restoration traces, SS represents the structural stability score, AR represents the aesthetic restoration, and PC represents the predicted value of the protection period.

[0020] Preferably, the comprehensive analysis model is specifically expressed as: , CI represents the comprehensive optimization index of the target archive storage source, DI′ represents the standard value of the restoration difficulty index, MI′ represents the standard value of the restoration material index, EI′ represents the standard value of the environmental stability index, and RI′ represents the standard value of the restoration quality index.

[0021] Preferably, when CI ≥ 0.85, it indicates that the quality of porcelain restoration is excellent; when 0.70 ≤ CI < 0.85, it indicates that the quality of porcelain restoration is good; when 0.55 ≤ CI < 0.70, it indicates that the quality of porcelain restoration is qualified; and when CI < 0.55, it indicates that the quality of porcelain restoration needs to be improved.

[0022] Technical effects and advantages of the present invention: The present invention can comprehensively and accurately collect restoration difficulty assessment source data, restoration material ratio source data, environmental monitoring source data and restoration effect source data from the target archive storage source through the data acquisition module, which provides a solid foundation for subsequent data analysis and processing, and ensures the reliability and accuracy of the entire archive information mining system; through the data extraction module, the key first archive data is extracted from the source data, and pre-processed, which can further refine and optimize the data, provide more accurate and available data input for subsequent data analysis, and help improve the efficiency and accuracy of data analysis; through the first data analysis module, the first archive data is analyzed to obtain the second archive data, which more deeply reflects the restoration difficulty, material ratio, environmental monitoring and restoration effect information of the archive, and provides more detailed and in-depth data support for the subsequent second data analysis; through the second data analysis module, a second restoration difficulty assessment data analysis model is established, which can quantitatively evaluate the restoration difficulty, material ratio, environmental monitoring and restoration effect of the archive. The difficulty of restoring the archives is estimated, which provides a scientific basis for the planning and implementation of the restoration work. The second restoration material ratio data analysis model is established, which can optimize the ratio of restoration materials and improve the performance and effect of restoration materials, thereby ensuring the quality of the restoration work. The second environmental monitoring data analysis model is established, which can monitor and evaluate the quality of the restoration environment in real time, and provide a stable and reliable environmental guarantee for the restoration work. The second restoration effect data analysis model is established, which can quantitatively evaluate the effect of the restoration work, and provide strong support for the control and improvement of the restoration quality. Through the comprehensive analysis module, a comprehensive analysis model is established to conduct a comprehensive analysis of the third archive data, and the comprehensive optimization index of the target archive storage source is calculated, which can comprehensively and objectively reflect the quality level of porcelain restoration, and provide a scientific basis for the evaluation and improvement of restoration work. At the same time, the quality of porcelain restoration can be graded and evaluated according to the comprehensive optimization index, which provides a clearer and more specific goal for the quality control of restoration work. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION

[0024] 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.

[0025] refer to Figure 1 The archival information mining system based on data analysis shown includes: Data collection module: used to collect archival data from the target archival storage source and aggregate the data into the data warehouse.

[0026] The data acquisition module is used to collect restoration difficulty assessment source data, restoration material ratio source data, environmental monitoring source data and restoration effect source data from the target archive storage source, and transmit the collected source data to the data extraction module.

[0027] The restoration difficulty assessment source data include fragment area measurement values, dimensions of similar artifacts in archaeological materials, edge wear measurement data, microscopic photography data, glaze integrity scanning data, pattern image data, archaeological database references, image clarity measurement values, Mohs hardness test data, porosity test data and dating data; the restoration material ratio source data include material inspection reports, formula records, firing process parameters, penetration test data, material physical property archives, spectrophotometer measurement data, standard color card data, material physical and chemical property inspection reports and accelerated aging test data; the environmental monitoring source data include environmental monitoring system records, meteorological data, illuminance meter array measurement data, spot distribution scanning data, temperature monitoring time series data, air particle monitoring data and airflow monitoring data; the restoration effect source data include surface scanning data, reflectivity measurement data, ultrasonic flaw detection data, stress distribution test data, 3D scanning comparison data, expert evaluation records, material aging data, environmental monitoring historical data and statistical data of similar cases.

[0028] Data extraction module: used to extract first archive data from source data, the first archive data including first restoration difficulty assessment data, first restoration material ratio data, first environmental monitoring data and first restoration effect data, pre-process the first archive data and transmit it to the first data analysis module.

[0029] The first restoration difficulty assessment data includes the total area of ​​found fragments, the estimated original area of ​​the artifact, the wear rate of the fragment edge, the glaze peeling area, the glaze crack length, the average width, the total glaze area, the number of identifiable patterns, the number of standard patterns of similar artifacts of the same period, the pattern clarity coefficient, the standard value of the body hardness, the current hardness measurement value, the porosity coefficient and the age coefficient. The first restoration material ratio data includes the basic toughness coefficient, the toughening agent ratio, the firing temperature correction coefficient, the initial penetration rate, the capillary effect coefficient, the material density coefficient, the Euclidean distance between the standard color value and the measured color value, the maximum allowable color difference, the thermal expansion coefficient matching, and the chemical stability. The first environmental monitoring data include real-time humidity, average humidity, number of monitoring points, seasonal correction coefficient, minimum illumination value, maximum illumination value, spot rate, temperature standard deviation, allowable temperature fluctuation range, basic cleanliness score, particle counting score and air flow coefficient; the first restoration effect data include reflectivity difference of repaired parts, surface texture difference, standard visible threshold, foundation stability, stress concentration coefficient, structural integrity coefficient, morphological restoration degree, decorative restoration degree, glaze color restoration degree, overall coordination coefficient, foundation protection period, material life coefficient, environmental impact coefficient and use intensity correction coefficient.

[0030] The preprocessing includes data cleaning and standardization.

[0031] The first data analysis module is used to analyze the first file data to obtain the second file data, the second file data includes the second restoration difficulty assessment data, the second restoration material ratio data, the second environmental monitoring data and the second restoration effect data, and transmit the second file data to the second data analysis module.

[0032] The second restoration difficulty assessment data includes the fragment integrity coefficient, glaze loss rate, original pattern recognition and body weathering index; the second restoration material ratio data includes the tire repair material toughness value, adhesive permeability, colorant matching and material compatibility index; the second environmental monitoring data includes the restoration environment humidity fluctuation value, lighting uniformity coefficient, temperature stability index and air cleanliness level; the second restoration effect data includes the visibility of restoration traces, structural stability score, aesthetic restoration degree and protection period prediction value.

[0033] The calculation method of the fragment integrity coefficient is fragment integrity coefficient = (total area of ​​found fragments / estimated original area of ​​the artifact) × (1-fragment edge wear rate), the calculation method of the glaze loss rate is glaze loss rate = (glaze peeling area + glaze crack length × average width) / total glaze area × 100%, the calculation method of the original pattern recognition is original pattern recognition = (number of identifiable patterns / number of standard patterns of similar artifacts of the same period) × pattern clarity coefficient, and the calculation method of the body weathering index is body weathering index = (body hardness standard value - current hardness measurement value) × porosity coefficient × age coefficient.

[0034] The calculation method of the toughness value of the tire repair material is tire repair material toughness value = basic toughness coefficient × (1 + toughening agent ratio) × firing temperature correction coefficient, the calculation method of the adhesive permeability is adhesive permeability = initial penetration speed × capillary effect coefficient × exp (-material density coefficient), the calculation method of the color matching degree is color matching degree = 1-(Euclidean distance between standard color value and measured color value / maximum allowable color difference), and the calculation method of the material compatibility index is material compatibility index = (thermal expansion coefficient matching degree × 0.4 + chemical stability coefficient × 0.6) × aging test coefficient.

[0035] The calculation method for the repair environment humidity fluctuation value is repair environment humidity fluctuation value = √(∑(real-time humidity-average humidity)² / number of monitoring points) × seasonal correction coefficient, the calculation method for the illumination uniformity coefficient is illumination uniformity coefficient = minimum illumination value / maximum illumination value × (1-spot rate), the calculation method for the temperature stability index is temperature stability index = 1-(temperature standard deviation / allowable temperature fluctuation range), and the calculation method for the air cleanliness level is air cleanliness level = (basic cleanliness score + particle count score) × air flow coefficient.

[0036] The calculation method for the visibility of the repair marks is repair mark visibility = (reflectivity difference of the repaired part × 0.5 + surface texture difference × 0.5) / standard visible threshold, the calculation method for the structural stability score is structural stability score = basic stability × (1-stress concentration coefficient) × structural integrity coefficient, the calculation method for the aesthetic restoration degree is aesthetic restoration degree = (morphological restoration degree × 0.3 + pattern restoration degree × 0.4 + glaze color restoration degree × 0.3) × overall coordination coefficient, and the calculation method for the protection period prediction value is protection period prediction value = basic protection period × material life coefficient × environmental impact coefficient × usage intensity correction coefficient.

[0037] The second data analysis module: includes a second restoration difficulty assessment data analysis unit, a second restoration material ratio data analysis unit, a second environmental monitoring data analysis unit and a second restoration effect data analysis unit, and is used to analyze the second file data to obtain third file data and transmit it to the comprehensive analysis module.

[0038] The second restoration difficulty assessment data analysis unit is used to establish a second restoration difficulty assessment data analysis model, which is specifically expressed as: , DI represents the restoration difficulty index, IC represents the fragment integrity coefficient, DR represents the glaze loss rate, RR represents the original pattern recognition, and WI represents the body weathering index.

[0039] The second repair difficulty assessment data analysis model It indicates the nonlinear relationship between completeness and loss. The greater the loss, the faster the difficulty index increases. It indicates the balance between the recognition degree of the ornamentation and the degree of weathering. The square root is used to make the value more stable. Indicates the exponential relationship between completeness and recognition, reflecting the restoration potential. The square of the weathering index is expressed as the attenuation factor. The more severe the weathering, the greater the difficulty.

[0040] The second repair material ratio data analysis unit is used to establish a second repair material ratio data analysis model, which is specifically expressed as: , MI represents the repair material index, TF represents the toughness value of the tire repair material, PR represents the adhesive penetration rate, CM represents the color matching degree, and CI represents the material compatibility index.

[0041] The second repair material ratio data analysis model represents the basic relationship between toughness and permeability, The hyperbolic sine function is used to reflect the nonlinear effects of color matching. represents the cube root of the compatibility index, smoothing extreme values, It represents the logarithmic relationship between toughness and compatibility, reflecting the overall performance of the material.

[0042] The second environment monitoring data analysis unit is used to establish a second environment monitoring data analysis model, which is specifically expressed as: , EI represents the environmental stability index, HF represents the humidity fluctuation value of the repaired environment, LU represents the light uniformity coefficient, TS represents the temperature stability index, and AC represents the air cleanliness level.

[0043] The second environmental monitoring data analysis model It indicates the inverse relationship between humidity fluctuations. The greater the fluctuation, the smaller the index. A bounded mapping representing illumination uniformity and temperature stability, Indicates the logarithmic relationship of air cleanliness, reflecting the environmental quality. It represents the square root of the ratio of temperature stability to humidity fluctuation, reflecting environmental stability.

[0044] The second restoration effect data analysis unit is used to establish a second restoration effect data analysis model, which is specifically expressed as: , RI represents the restoration quality index, TV represents the visibility of restoration traces, SS represents the structural stability score, AR represents the aesthetic restoration, and PC represents the predicted value of the protection period.

[0045] The second repair effect data analysis model Indicates the complementary value of the repair trace visibility. The lower the visibility, the better. The hyperbolic tangent function that represents the degree of aesthetic restoration ensures that the result is within a reasonable range. Indicates the logarithmic relationship of the protection period, reflecting the long-term effect. It represents the comprehensive index relationship between structural stability, aesthetic restoration and protection period.

[0046] Comprehensive analysis module: used to establish a comprehensive analysis model to conduct comprehensive analysis on the third-party archive data, calculate the comprehensive optimization index of the target archive storage source, and analyze the quality of porcelain restoration based on the comprehensive optimization index.

[0047] The comprehensive analysis model is specifically expressed as: , CI represents the comprehensive optimization index of the target archive storage source, DI′ represents the standard value of the restoration difficulty index, MI′ represents the standard value of the restoration material index, EI′ represents the standard value of the environmental stability index, and RI′ represents the standard value of the restoration quality index.

[0048] When CI≥0.85, it indicates that the quality of porcelain restoration is excellent; when 0.70≤CI<0.85, it indicates that the quality of porcelain restoration is good; when 0.55≤CI<0.70, it indicates that the quality of porcelain restoration is qualified; and when CI<0.55, it indicates that the quality of porcelain restoration needs to be improved.

[0049] The present invention can comprehensively and accurately collect restoration difficulty assessment source data, restoration material ratio source data, environmental monitoring source data and restoration effect source data from the target archive storage source through the data acquisition module, which provides a solid foundation for subsequent data analysis and processing, and ensures the reliability and accuracy of the entire archive information mining system; through the data extraction module, the key first archive data is extracted from the source data, and pre-processed, which can further refine and optimize the data, provide more accurate and available data input for subsequent data analysis, and help improve the efficiency and accuracy of data analysis; through the first data analysis module, the first archive data is analyzed to obtain the second archive data, which more deeply reflects the restoration difficulty, material ratio, environmental monitoring and restoration effect information of the archive, and provides more detailed and in-depth data support for the subsequent second data analysis; through the second data analysis module, a second restoration difficulty assessment data analysis model is established, which can quantitatively evaluate the restoration difficulty, material ratio, environmental monitoring and restoration effect of the archive. The difficulty of restoring the archives is estimated, which provides a scientific basis for the planning and implementation of the restoration work. The second restoration material ratio data analysis model is established, which can optimize the ratio of restoration materials and improve the performance and effect of restoration materials, thereby ensuring the quality of the restoration work. The second environmental monitoring data analysis model is established, which can monitor and evaluate the quality of the restoration environment in real time, and provide a stable and reliable environmental guarantee for the restoration work. The second restoration effect data analysis model is established, which can quantitatively evaluate the effect of the restoration work, and provide strong support for the control and improvement of the restoration quality. Through the comprehensive analysis module, a comprehensive analysis model is established to conduct a comprehensive analysis of the third archive data, and the comprehensive optimization index of the target archive storage source is calculated, which can comprehensively and objectively reflect the quality level of porcelain restoration, and provide a scientific basis for the evaluation and improvement of restoration work. At the same time, the quality of porcelain restoration can be graded and evaluated according to the comprehensive optimization index, which provides a clearer and more specific standard for the quality control of restoration work.

[0050] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other; Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An archive information mining system based on data analysis, characterized in that: include: Data collection module: used to collect archive data from the target archive storage source and aggregate the data into the data warehouse; The data acquisition module is used to collect restoration difficulty assessment source data, restoration material ratio source data, environmental monitoring source data and restoration effect source data from the target archive storage source, and transmit the collected source data to the data extraction module; Data extraction module: used to extract first archive data from source data, the first archive data including first restoration difficulty assessment data, first restoration material ratio data, first environmental monitoring data and first restoration effect data, pre-process the first archive data and transmit it to the first data analysis module; The first data analysis module is used to analyze the first file data to obtain the second file data, the second file data includes the second restoration difficulty assessment data, the second restoration material ratio data, the second environmental monitoring data and the second restoration effect data, and transmit the second file data to the second data analysis module; The second restoration difficulty assessment data includes the fragment integrity coefficient, glaze loss rate, original pattern recognition and body weathering index; the second restoration material ratio data includes the tire repair material toughness value, adhesive penetration rate, color matching degree and material compatibility index; the second environmental monitoring data includes the restoration environment humidity fluctuation value, illumination uniformity coefficient, temperature stability index and air cleanliness level; the second restoration effect data includes the restoration trace visibility, structural stability score, aesthetic restoration degree and protection period prediction value; The second data analysis module includes a second restoration difficulty assessment data analysis unit, a second restoration material ratio data analysis unit, a second environmental monitoring data analysis unit, and a second restoration effect data analysis unit, and is used to analyze the second file data to obtain third file data, and transmit the third file data to the comprehensive analysis module; Comprehensive analysis module: used to establish a comprehensive analysis model to conduct comprehensive analysis on the third-party archive data, calculate the comprehensive optimization index of the target archive storage source, and analyze the quality of porcelain restoration based on the comprehensive optimization index.

2. The archival information mining system based on data analysis according to claim 1 is characterized in that: The calculation method of the fragment integrity coefficient is fragment integrity coefficient = (total area of ​​found fragments / estimated original area of ​​the artifact) × (1-fragment edge wear rate), the calculation method of the glaze loss rate is glaze loss rate = (glaze peeling area + glaze crack length × average width) / total glaze area × 100%, the calculation method of the original pattern recognition is original pattern recognition = (number of identifiable patterns / number of standard patterns of similar artifacts of the same period) × pattern clarity coefficient, and the calculation method of the body weathering index is body weathering index = (body hardness standard value - current hardness measurement value) × porosity coefficient × age coefficient.

3. The archival information mining system based on data analysis according to claim 1 is characterized in that: The calculation method of the toughness value of the tire repair material is tire repair material toughness value = basic toughness coefficient × (1 + toughening agent ratio) × firing temperature correction coefficient, the calculation method of the adhesive permeability is adhesive permeability = initial penetration speed × capillary effect coefficient × exp (-material density coefficient), the calculation method of the color matching degree is color matching degree = 1-(Euclidean distance between standard color value and measured color value / maximum allowable color difference), and the calculation method of the material compatibility index is material compatibility index = (thermal expansion coefficient matching degree × 0.4 + chemical stability coefficient × 0.6) × aging test coefficient.

4. The archival information mining system based on data analysis according to claim 1 is characterized in that: The calculation method for the repair environment humidity fluctuation value is repair environment humidity fluctuation value = √(∑(real-time humidity-average humidity)² / number of monitoring points) × seasonal correction coefficient, the calculation method for the illumination uniformity coefficient is illumination uniformity coefficient = minimum illumination value / maximum illumination value × (1-spot rate), the calculation method for the temperature stability index is temperature stability index = 1-(temperature standard deviation / allowable temperature fluctuation range), and the calculation method for the air cleanliness level is air cleanliness level = (basic cleanliness score + particle count score) × air flow coefficient.

5. The archival information mining system based on data analysis according to claim 1 is characterized in that: The calculation method for the visibility of the repair marks is repair mark visibility = (reflectivity difference of the repaired part × 0.5 + surface texture difference × 0.5) / standard visible threshold, the calculation method for the structural stability score is structural stability score = basic stability × (1-stress concentration coefficient) × structural integrity coefficient, the calculation method for the aesthetic restoration degree is aesthetic restoration degree = (morphological restoration degree × 0.3 + pattern restoration degree × 0.4 + glaze color restoration degree × 0.3) × overall coordination coefficient, and the calculation method for the protection period prediction value is protection period prediction value = basic protection period × material life coefficient × environmental impact coefficient × usage intensity correction coefficient.

6. The archival information mining system based on data analysis according to claim 1 is characterized in that: The second restoration difficulty assessment data analysis unit is used to establish a second restoration difficulty assessment data analysis model, which is specifically expressed as: , DI represents the restoration difficulty index, IC represents the fragment integrity coefficient, DR represents the glaze loss rate, RR represents the original pattern recognition, and WI represents the body weathering index.

7. The archival information mining system based on data analysis according to claim 1 is characterized in that: The second repair material ratio data analysis unit is used to establish a second repair material ratio data analysis model, which is specifically expressed as: , MI represents the repair material index, TF represents the toughness value of the tire repair material, PR represents the adhesive penetration rate, CM represents the color matching degree, and CI represents the material compatibility index.

8. The archival information mining system based on data analysis according to claim 1 is characterized in that: The second environment monitoring data analysis unit is used to establish a second environment monitoring data analysis model, which is specifically expressed as: , EI represents the environmental stability index, HF represents the humidity fluctuation value of the repaired environment, LU represents the light uniformity coefficient, TS represents the temperature stability index, and AC represents the air cleanliness level.

9. The archival information mining system based on data analysis according to claim 1 is characterized in that: The second restoration effect data analysis unit is used to establish a second restoration effect data analysis model, which is specifically expressed as: , RI represents the restoration quality index, TV represents the visibility of restoration traces, SS represents the structural stability score, AR represents the aesthetic restoration, and PC represents the predicted value of the protection period.

Images