Risk assessment method, model, readable storage medium and device
Through machine learning combined with support vector machine model, the risks of immovable cultural relics are evaluated, and the problem that traditional methods cannot accurately reflect the actual risks of cultural relics is solved, and a comprehensive and accurate assessment of cultural relics risks is achieved, providing a scientific basis for the protection of immovable cultural relics. .
Patent Information
- Application Number
- CN202411129283.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-11-29
AI Technical Summary
The prior art lacks targetedness in assessing the disaster risk of immovable cultural relics, and traditional methods cannot accurately reflect the actual risk status of cultural relics, especially because the high individual differences and intangible properties of cultural relics are not fully considered.
Using machine learning methods, combining disaster-causing weather data, cultural relics and cultural relics ontology data, risk assessment is carried out through the support vector machine model, taking into account the physical characteristics and intangible value of cultural relics, and establishing a risk assessment method and model for immovable cultural relics.
The risk assessment of immovable cultural relics has been achieved more accurate and comprehensive, subjective interference has been reduced, and the real risk status of cultural relics can be better reflected, providing a scientific basis for formulating protection measures.
Smart Images

Figure CN119047629A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of image detection technology, and in particular relates to a risk assessment method, model, readable storage medium and device for the protection of fixed cultural relics. Background Art
[0002] my country has a large number of immovable cultural relics with rich varieties. Immovable cultural relics carry rich historical and cultural information and are full of immeasurable value. The increasing number of extreme weather and precipitation have become increasingly common, leading to frequent natural disasters. These disasters will not only cause loss of life and property, but also cause immeasurable damage to immovable cultural relics. The high water level and huge impact of floods may cause the structure of cultural relics to deform, the foundation to loosen, or even collapse as a whole. Rainwater accumulation may cause mildew, corrosion and other damage. At the same time, excessive sunshine, snowfall, low temperature or high temperature difference will also affect the appearance and structure of ancient buildings or ancient cultural relics. Therefore, through risk assessment, we can identify and understand the potential risks faced by cultural relics in advance, so as to formulate targeted disaster prevention and mitigation measures to reduce the damage to cultural relics caused by disasters.
[0003] From the existing technical means, disaster risk assessment can adopt a variety of methods such as geomorphological methods, hydrodynamic methods, historical disaster assessment methods and indicator system methods. The geomorphological method mainly judges the flow direction and accumulation of floods based on topographic and geomorphological characteristics; the hydrodynamic law predicts the impact of floods on cultural relics by simulating the movement of water flow; the historical disaster assessment law evaluates the potential risks of cultural relics in future natural disasters by analyzing historical disaster data; the indicator system law comprehensively evaluates the flood risk of cultural relics by constructing a comprehensive indicator system.
[0004] When assessing the impact of disasters, existing technologies mainly focus on regions, disaster victims, economy and agriculture, but research on risk assessment of immovable cultural relics is relatively scarce. As a precious heritage with profound historical and cultural connotations, the value of immovable cultural relics is difficult to measure in monetary terms. They are of various types and shapes, and each cultural relic has its own unique characteristics and value. This high degree of individual difference makes the traditional regional large-area division evaluation method difficult to apply to the risk assessment of immovable cultural relics.
[0005] Traditional risk assessment methods are often based on a unified consideration of the entire region, and predict the possible impact of disasters by dividing risk levels. However, this method has obvious defects when applied to immovable cultural relics. First, due to the wide distribution of cultural relics and their different characteristics, the risk of regional disasters cannot accurately reflect the actual risk of each cultural relic. Secondly, factors such as the environment, structure, and materials in which the cultural relics are located may affect their disaster resistance, and these factors are often ignored in regional risk assessments. In addition, traditional methods lack consideration of non-material attributes such as the historical value and cultural significance of cultural relics, which are important components of the value of immovable cultural relics. The existing disaster risk assessment methods for immovable cultural relics have obvious limitations and cannot accurately reflect the actual risk status of cultural relics. Summary of the invention
[0006] In order to solve the problems existing in the prior art, the present invention provides a risk assessment method, model, readable storage medium and device specifically for immovable cultural relics, which comprehensively consider the physical properties, environmental factors and intangible value of the cultural relics, so as to more accurately assess the risks of cultural relics in disasters and provide a scientific basis for formulating effective protection measures.
[0007] The technical solution adopted by the present invention is:
[0008] In a first aspect, the present invention provides a risk assessment method for the protection of fixed cultural relics, which is used to collect a number of relevant influencing factors for immovable cultural relics in a sample area, and to obtain a prediction model by combining the relevant influencing factors with determined disaster-affected cultural relics samples through machine learning, and to predict the disaster risk of immovable cultural relics in the target area through the prediction model;
[0009] Relevant influencing factors include:
[0010] Disaster weather data, including rainfall, wind speed, temperature and snow accumulation in the region, are used to reflect the main variables that cause the impact on fixed cultural relics;
[0011] Cultural heritage environmental data, including elevation values, slope, vegetation cover, and river density within the area, to reflect factors that increase the probability of disasters due to disaster-causing weather data; and
[0012] The data of cultural relics include the risk values obtained through the risk value assignment table for the type of cultural relics, the level of cultural relics protection unit, the scale of cultural relics and the protection status of cultural relics.
[0013] Among them, the historical average rainfall data of the target area is obtained. Areas with high historical average rainfall are rainfall-prone areas with higher risks. The ground meteorological automatic station observation data of the target cultural relics area is obtained, that is, the average rainfall per minute during the rainstorm. The greater the intensity of the rainstorm, the more serious the damage to the cultural relics.
[0014] In the cultural relics environmental data, the elevation data and slope data observed by satellite are obtained. The elevation data reflects the undulation of the terrain. Low-lying areas are prone to waterlogging during rainfall, causing damage to cultural relics. The slope reflects the inclination of the ground. The greater the slope, the greater the impact of rainwater, and the higher the risk of damage to cultural relics. The vegetation coverage index of the target cultural relics area is obtained. Areas with rich vegetation can effectively prevent soil erosion from causing unstable foundations or mudslides. The richer the vegetation, the lower the risk. The river network density of the target cultural relics area is obtained. Areas with high river network density are prone to flood disasters during heavy rains, posing a threat to cultural relics.
[0015] In combination with the first aspect, the present invention provides a first implementation manner of the first aspect, wherein the rainfall in the disaster-causing weather data includes a weighted number of a single-day average rainfall, a maximum rainfall, and rainy days.
[0016] In combination with the first aspect, the present invention provides a second implementation of the first aspect, wherein the wind speed in the disaster weather data includes a weighted number of the maximum wind speed, the daily average wind speed, and the monthly average wind speed.
[0017] In combination with the first aspect, the present invention provides a third implementation of the first aspect, wherein the temperature in the disaster weather data includes a weighted number of sunshine intensity, total annual sunshine time, maximum temperature difference and minimum temperature.
[0018] In combination with the first aspect, the present invention provides a fourth implementation of the first aspect, and the specific steps are as follows:
[0019] Step 1: First, obtain the disaster-causing weather data and cultural relic environmental data of the sample area and calculate the corresponding weighted numbers, then set up a risk value assignment table for the cultural relic ontology data, and obtain the cultural relic ontology data of the sample area according to the risk value assignment table;
[0020] Step 2: Obtain the impact factor values of several sample areas and the disaster conditions corresponding to the sample areas, analyze the disaster conditions to determine the disaster values of the immovable cultural relics in the sample areas, thereby obtaining a matching sample group of the impact factor values and the disaster conditions, and dividing the matching sample group into a training group and a test group;
[0021] Step 3: Use the training group to establish a training model through the support vector machine, feedback the risk with the size of the disaster value, then bring the test group into the model output of the support vector machine and verify, return the model accuracy, and finally obtain the trained prediction model;
[0022] Step 4: Obtain the impact factor value of the target area, and input the impact factor value through the trained prediction model to obtain the corresponding risk assessment value.
[0023] In combination with the fourth implementation of the first aspect, the present invention provides a fifth implementation of the first aspect, wherein in step 2, the step of obtaining the disaster situation corresponding to the sample area is as follows:
[0024] First, all immovable cultural relics in the sample area are divided and classified by material, into stone, wood and metal categories, and then the cultural relics in each category are numbered and their locations are confirmed;
[0025] Then, all the classified cultural relics are evaluated for appearance damage and structure damage. The appearance damage evaluation uses the appearance integrity as the evaluation standard and obtains the appearance integrity value. The structural damage evaluation is carried out using the national standard structure detection method for the corresponding type of material and obtains the structural integrity value.
[0026] The appearance integrity values and structural integrity values of all classified cultural relics are weighted to obtain the weighted value corresponding to each classification. Finally, the weighted value of the integrity values of all classifications is used as the damage value of the independent immovable cultural relics in the sample area.
[0027] In a second aspect, the present invention provides a model, which is a prediction model established by the above-mentioned risk assessment method for the protection of fixed cultural relics.
[0028] In a third aspect, the present invention provides a readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements any of the methods described above.
[0029] In a fourth aspect, the present invention further provides a device, loaded with the above-mentioned prediction model, for obtaining the risk value of the immovable cultural relics in the target area to the environmental changes.
[0030] The beneficial effects of the present invention are:
[0031] (1) The present invention incorporates the characteristics of cultural relics into the disaster risk assessment system, taking into account different types of cultural relics, cultural relic protection levels, cultural relic scales and cultural relic status, and accurately models the actual risk of each immovable cultural relic;
[0032] (2) The present invention combines the index system method with an objective machine learning method, and uses the disaster weather data, the environmental data of the cultural relics, and the vulnerability of the cultural relics themselves as variables to apply the support vector machine (SVM) model for risk assessment and prediction, which can reduce the interference caused by subjective feelings;
[0033] (3) The present invention integrates the physical characteristics of the cultural relics, such as type and scale, the intangible values, such as protection level and preservation status, and the environmental factors such as the elevation, vegetation, and river network where the cultural relics are located into the analysis, integrating the multiple attributes of the cultural relics to achieve a comprehensive assessment of the risks of the cultural relics. This assessment method is more comprehensive and can better reflect the real risk status of the cultural relics. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] Figure 1 is a flow chart of the method of the present invention;
[0035] Figure 2 It is a flowchart of a specific method in an embodiment of the present invention. DETAILED DESCRIPTION
[0036] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.
[0037] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.
[0038] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0039] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0040] In the description of this application, it should be noted that if the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, or the orientation or position relationship in which the product of the application is usually placed when in use. It is only for the convenience of describing this application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application. In addition, if the terms "first", "second", etc. appear in the description of this application, they are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0041] Embodiment 1:
[0042] This embodiment provides a risk assessment method for the protection of fixed cultural relics, which is intended to target a single or several independent immovable cultural relics in a determined area. The so-called immovable cultural relics refer to fixed cultural relics that are in the open air or in an open state and can be affected by the external environment. They are generally structures, i.e., building complexes, stele forests, sculptures, bridges or stone masonry, etc. The cultural relics protection units that have been certified by the state are taken as the largest scope, and data are collected and analyzed for the cultural relics protection units that need to be risk analyzed, so as to obtain the risk value of the corresponding immovable cultural relics affected by disasters or natural weather conditions.
[0043] It should be noted that the immovable cultural relics targeted not only include those in remote areas, such as stone tablets, temples, ancient bridges, ancient towns, etc., but also churches, towers, iron bridges, houses, etc. in urban areas. Regardless of whether the area where they are located is a densely populated area or a natural environment, they are all affected by changes in weather and environment.
[0044] Specifically, refer to Figure 1 This method is used to collect several relevant influencing factors for the immovable cultural relics in the sample area, and train the relevant influencing factors with the determined samples of damaged cultural relics through machine learning to obtain a prediction model, and predict the disaster risk of the immovable cultural relics in the target area through the prediction model;
[0045] Relevant influencing factors include: disaster-causing weather data, including rainfall, wind speed, temperature and snow accumulation in the area where the region is located, which is used to reflect the main variables that cause the fixed cultural relics to be affected. The rainfall in the disaster-causing weather data includes the weighted number of the average daily rainfall, the maximum rainfall and the number of rainy days. The wind speed includes the weighted number of the maximum wind speed, the average daily wind speed and the average monthly wind speed. The temperature includes the weighted number of sunshine intensity, the total annual sunshine time, the maximum temperature difference and the minimum temperature.
[0046] Cultural relics environmental data, including elevation values, slopes, vegetation coverage and river network density in the area, are used to reflect factors that increase the probability of disasters due to disastrous weather data; and cultural relics data, including risk values obtained through the risk value assignment table for cultural relics type, level of cultural relics protection unit, scale of cultural relics and protection status of cultural relics.
[0047] Specifically, refer to Figure 2 First, obtain the disaster-causing weather data and cultural relics environmental data of the sample area and calculate the corresponding weighted numbers, then set up a risk value assignment table for the cultural relics ontology data, and obtain the cultural relics ontology data of the sample area according to the risk value assignment table.
[0048] Obtaining the impact factor values of several sample areas and the disaster conditions corresponding to the sample areas, analyzing the disaster conditions to determine the disaster values of the immovable cultural relics in the sample areas, thereby obtaining a matching sample group of the impact factor values and the disaster conditions, and dividing the matching sample group into a training group and a test group;
[0049] The training group uses the support vector machine to build a training model, using the disaster value to feedback the risk, and then brings the test group into the support vector machine model output results and verifies them, returns the model accuracy, and finally obtains the trained prediction model;
[0050] Obtain the impact factor value of the target area, and input the impact factor value through the trained prediction model to obtain the corresponding risk assessment value.
[0051] The steps for obtaining the disaster situation corresponding to the sample area are as follows:
[0052] First, all immovable cultural relics in the sample area are divided and classified by material, into stone, wood and metal categories, and then the cultural relics in each category are numbered and their locations are confirmed;
[0053] Then, all the classified cultural relics are evaluated for appearance damage and structure damage. The appearance damage evaluation uses the appearance integrity as the evaluation standard and obtains the appearance integrity value. The structural damage evaluation is carried out using the national standard structure detection method for the corresponding type of material and obtains the structural integrity value.
[0054] The appearance integrity values and structural integrity values of all classified cultural relics are weighted to obtain the weighted value corresponding to each classification. Finally, the weighted value of the integrity values of all classifications is used as the damage value of the independent immovable cultural relics in the sample area.
[0055] It should be noted that, for the data on the cultural relics, an indicator system needs to be established to comprehensively evaluate the vulnerability of the cultural relics through the types of cultural relics, the level of cultural relics protection units, the scale of cultural relics, and the protection status of cultural relics. Cultural relics types include ancient buildings, ancient sites, ancient tombs, grottoes and stone carvings, important modern and contemporary historical sites and representative buildings. Different categories represent different material structures and have different abilities to withstand heavy rains. The levels of cultural relics protection units include national key cultural relics protection units, provincial cultural relics protection units, municipal and county cultural relics protection units, and ungraded cultural relics protection units. The higher the level of the protection unit, the more attention it receives from the state, which can indirectly reflect its value. The scale of cultural relics refers to the area of the protection scope of the cultural relics. Cultural relics of different sizes are affected by heavy rain disasters to different extents, which also indirectly reflects the approximate value comparison of different cultural relics. The preservation status of cultural relics reflects the duration of their existence and their disaster prevention and mitigation capabilities. The worse the preservation status of cultural relics, the higher the risk during heavy rains.
[0056] The evaluation system is:
[0057]
[0058] Furthermore, the steps of constructing the model of the support vector machine in this embodiment are as follows:
[0059] The obtained disaster-causing rainfall data, the data on the environment where the cultural relics are located, and the data on the vulnerability indicators of the cultural relics themselves are divided into a training set and a test set in a ratio of 8:2. The training set is used to build a training model through a support vector machine: the target area immovable cultural relics dataset D = {(x i ,y i )|i=1,2,3,…,l}, where x i ∈R m ,y i ∈{1,…,K}. For a multi-classification problem with a sample size of l and a sample category of K. Use a support vector machine to find a classification plane that can separate different categories of data in the data set. Its hyperplane is shown in the following formula:
[0060] f(x)=w T x+b
[0061] In order to obtain the parameters w,b, we need to solve the following minimization problem:
[0062]
[0063] sty i (w T x i +b)≥1,(i=1,2,…l)
[0064] The Lagrangian function can be written as:
[0065]
[0066] Where α = (α1; α2; ...; α l ). Let the partial derivative of L(w,b,α) with respect to w and b be 0, we can get:
[0067]
[0068] Substituting into the above formula, we can get the dual problem:
[0069]
[0070] Solving for α * After that, solving for w and b gives:
[0071]
[0072] Step 5: Substitute the test set data into the support vector machine model output for verification and return the model accuracy.
[0073] Through the above method, the actual disaster risk assessment of ancient building complexes is carried out, as follows:
[0074] Target area: Meicheng Ancient Town, Jiande, Hangzhou
[0075] Assessment objects: All immovable cultural relics in the ancient town, including ancient buildings, ancient streets, ancient bridges, etc., shall be subject to the cultural relics protection units determined by the national or local cultural relics bureau.
[0076] Evaluation method: The method described in this embodiment combines geomorphological methods, hydrological dynamic methods, historical disaster assessment methods and indicator system methods, and introduces a machine learning model for comprehensive evaluation.
[0077] Evaluation steps:
[0078] 1. Get the data
[0079] Disaster-causing rainfall data:
[0080] Historical average rainfall data: directly obtain the historical average rainfall data of the ancient town and surrounding areas through the meteorological department, or summarize and analyze the rainfall distribution pattern through public meteorological data.
[0081] Ground meteorological automatic station observation data: obtain minute-by-minute rainfall data during heavy rains in the ancient town and surrounding areas, and analyze the intensity and duration of heavy rains.
[0082] The average annual precipitation in Jiande City, Zhejiang Province, where Meicheng Ancient Town is located, was 1278.7 mm in 2022. The maximum daily rainfall in 2022 was 70.8 mm. On that day, the water level of the Xin'anjiang Reservoir near Meicheng Ancient Town continued to rise and reached a historical high of 108.45 meters, causing the water level of the Xin'anjiang River downstream to reach a maximum of 25.93 meters.
[0083] Cultural relics environmental data:
[0084] Elevation data and slope: satellite remote sensing data is used to obtain elevation data and slope information of the ancient town and surrounding areas, and to analyze the impact of topography on flood disasters, especially the Xin'an River channel next to the Meicheng Ancient Town, whose river channel height is 26 meters.
[0085] Vegetation coverage index: The vegetation coverage index of the ancient town and surrounding areas is obtained through remote sensing data to analyze the impact of vegetation on soil erosion and debris flow. The vegetation coverage rate of Meicheng Ancient Town refers to the forest coverage rate of Jiande City, and the latest statistical data is 73.47%.
[0086] River network density: remote sensing data is used to obtain river network density information in the ancient town and surrounding areas, and the impact of rivers on flood disasters is analyzed, mainly the influencing factors of Xin'an River.
[0087] Vulnerability data of cultural relics:
[0088] Establish an index system to classify all immovable cultural relics in the ancient town and assess their vulnerability. The indexes include: type of cultural relics, level of cultural relics protection unit, scale of cultural relics, protection status of cultural relics, etc. Each index is graded and quantified, and a comprehensive score is calculated based on the weight to reflect the vulnerability of the cultural relics. Most of the ancient buildings in Meicheng Ancient Town, Jiande City, are stone-built, such as stone bridges, stone towers, stone walls, etc., and their stability is relatively high among cultural relics.
[0089] 2. Build a machine learning model
[0090] The acquired data is divided into training set and test set in a ratio of 8:2.
[0091] The training set is used to train the support vector machine (SVM) model to establish a risk assessment model.
[0092] The model input variables include: disaster-causing rainfall data, cultural relic environment data, and cultural relic vulnerability data.
[0093] Model output variables include: cultural relics risk level, such as low risk, medium risk, high risk, etc.
[0094] 3. Risk assessment and results analysis
[0095] Substitute the test set data into the SVM model for verification and evaluate the accuracy of the model.
[0096] Based on the model output results, the risk level distribution of immovable cultural relics in the ancient town is analyzed.
[0097] Identify high-risk cultural relics and analyze their risk factors, such as rainfall intensity, topography, and cultural relic fragility.
[0098] Formulate targeted disaster prevention and mitigation measures, such as strengthening drainage system construction, reinforcing cultural relics structures, and improving the protection level of cultural relics.
[0099] Example analysis:
[0100] Meicheng Town, Jiande City, Hangzhou City, Zhejiang Province is located in the mountainous area of western Zhejiang, at the confluence of Xin'an River and Lan River, with Wulong Mountain to the north and Sanjiangkou to the south. Meicheng Town, Jiande, is a thousand-year-old town with a history of more than 1,700 years.
[0101] Outside the ancient town of Meicheng, there are ancient city walls surrounding the Xin'an River and the Fuchun River, as well as a stone archway in the center of the ancient town. The ancient city wall is a national key cultural relic protection unit, with a large scale, but in a general state of preservation. As it was built along the river, according to the indicator system assessment, the vulnerability score of the ancient building is 0.6.
[0102] According to historical rainfall data and ground-based automatic meteorological station observation data, the ancient town has recently received heavy rainfall and is at risk of rainstorms. Combined with the topography and surrounding environment of the ancient buildings, it is analyzed that they are at high risk of flood disasters.
[0103] According to the SVM model assessment, the risk level of the ancient building is medium risk. The following measures are recommended:
[0104] Strengthen the construction of drainage systems around ancient buildings to ensure that rainwater is discharged in a timely manner.
[0105] Strengthen ancient buildings to improve their flood resistance.
[0106] Develop emergency plans to ensure that timely measures can be taken to protect ancient buildings when floods and waterlogging disasters occur.
[0107] Especially when the river water level rises above the river bank, in order to prevent flooding into the ancient city as much as possible, the ancient city wall can be used to form a second-level river bank, and the leaks or openings can be blocked to form a longer riverside enclosure, which can provide better flood prevention effects. However, in this method, the foundation of the ancient city wall needs to be evaluated, and the external wall needs to be maintained regularly to avoid damage and collapse caused by long-term rain erosion.
[0108] In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0109] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0110] This embodiment also provides a device pre-installed with the model, which is generally a computer or a cloud server. The prediction model is set in the computer and is loaded, controlled and used through a computer program.
[0111] This embodiment further provides a storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements any of the methods described above.
[0112] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0113] Those skilled in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.
[0114] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.
[0115] The present invention is not limited to the above optional implementations, and anyone can derive other various forms of products under the enlightenment of the present invention. The above specific implementations should not be understood as limiting the scope of protection of the present invention. The scope of protection of the present invention should be based on the definition in the claims, and the description can be used to interpret the claims.
Claims
1. A risk assessment method for the protection of fixed cultural relics, which is used to collect a number of relevant influencing factors for immovable cultural relics in a sample area, and to obtain a prediction model by training the relevant influencing factors and the determined samples of damaged cultural relics through machine learning, and to predict the disaster risk of immovable cultural relics in the target area through the prediction model; it is characterized by: Relevant influencing factors include: Disaster weather data, including rainfall, wind speed, temperature and snow accumulation in the region, are used to reflect the main variables that cause the impact on fixed cultural relics; Cultural heritage environmental data, including elevation values, slope, vegetation cover, and river density within the area, to reflect factors that increase the probability of disasters due to disaster-causing weather data; and The data of cultural relics include the risk values obtained through the risk value assignment table for the type of cultural relics, the level of cultural relics protection unit, the scale of cultural relics and the protection status of cultural relics.
2. A risk assessment method for the protection of fixed cultural relics according to claim 1, characterized in that: The rainfall in the disaster weather data includes the average daily rainfall, the maximum rainfall and the weighted number of rainy days.
3. A risk assessment method for the protection of fixed cultural relics according to claim 1, characterized in that: The wind speed in the disaster weather data includes the weighted number of the maximum wind speed, the daily average wind speed and the monthly average wind speed.
4. The risk assessment method for the protection of fixed cultural relics according to claim 1 is characterized by: The temperature in the disaster weather data includes the weighted number of sunshine intensity, total annual sunshine time, maximum temperature difference and minimum temperature.
5. The risk assessment method for the protection of fixed cultural relics according to claim 1 is characterized by: The specific steps are as follows: Step 1: First, obtain the disaster-causing weather data and cultural relic environmental data of the sample area and calculate the corresponding weighted numbers, then set up a risk value assignment table for the cultural relic ontology data, and obtain the cultural relic ontology data of the sample area according to the risk value assignment table; Step 2: Obtain the impact factor values of several sample areas and the disaster conditions corresponding to the sample areas, analyze the disaster conditions to determine the disaster values of the immovable cultural relics in the sample areas, thereby obtaining a matching sample group of the impact factor values and the disaster conditions, and dividing the matching sample group into a training group and a test group; Step 3: Use the training group to establish a training model through the support vector machine, feedback the risk with the size of the disaster value, then bring the test group into the model output of the support vector machine and verify, return the model accuracy, and finally obtain the trained prediction model; Step 4: Obtain the impact factor value of the target area, and input the impact factor value through the trained prediction model to obtain the corresponding risk assessment value.
6. A risk assessment method for the protection of fixed cultural relics according to claim 5, characterized in that: In step 2, the steps of obtaining the disaster situation corresponding to the sample area are as follows: First, all immovable cultural relics in the sample area are divided and classified by material, into stone, wood and metal categories, and then the cultural relics in each category are numbered and their locations are confirmed; Then, all the classified cultural relics are evaluated for appearance damage and structure damage. The appearance damage evaluation uses the appearance integrity as the evaluation standard and obtains the appearance integrity value. The structural damage evaluation is carried out using the national standard structure detection method for the corresponding type of material and obtains the structural integrity value. The appearance integrity values and structural integrity values of all classified cultural relics are weighted to obtain the weighted value corresponding to each classification. Finally, the weighted value of the integrity values of all classifications is used as the damage value of the independent immovable cultural relics in the sample area.
7. A model, characterized in that: A prediction model established by a risk assessment method for the protection of fixed cultural relics as described in any one of claims 1-7.
8. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
9. A device, characterized in that: The model of claim 8 is loaded and used to obtain the risk value of the immovable cultural relics in the target area to the environmental changes.
Citation Information
Cited By
Land space cultural relic resource risk assessment method under influence of climate change and related device
CN122572796A
