River water ecosystem health evaluation method and system, medium and product

Abstract

The invention relates to the technical field of data analysis, in particular to a river water ecosystem health evaluation method and system, a medium and a product, and the method comprises the steps: obtaining a plurality of criterion indexes and criterion index data corresponding to each criterion layer of a to-be-evaluated river; obtaining an index assignment value corresponding to each criterion index based on a preset index assignment neural network model and each criterion index data; obtaining a preset index weight and a preset criterion layer weight corresponding to the to-be-evaluated river, and determining a river health comprehensive score corresponding to the to-be-evaluated river based on the preset index weight corresponding to the to-be-evaluated river, the preset criterion layer weight and each index score; and determining the health condition grade of the to-be-evaluated river based on the river health comprehensive score. The method is convenient for improving the accuracy of health evaluation of the river water ecosystem.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to a method, system, medium, and product for assessing the health of a river aquatic ecosystem. Background Technology

[0002] With the rapid advancement of industrialization and urbanization in my country, river aquatic ecosystems are facing increasingly severe challenges. Problems such as water shortages, water quality deterioration, and disrupted hydrological rhythms are frequent. Excessive water extraction and imbalanced water resource allocation in some small and medium-sized rivers have led to a sharp reduction in upstream water flow, resulting in riverbed siltation, shrinkage, and even flow interruption. This not only disrupts the continuity of river aquatic ecosystems but also poses a serious threat to biodiversity. As the core carrier of the water resource cycle, the health of river aquatic ecosystems directly relates to regional ecological security, sustainable water resource utilization, and the quality of the human living environment. Therefore, conducting scientific and accurate health assessments of river aquatic ecosystems is a crucial prerequisite for identifying ecological problems, formulating restoration strategies, and ensuring the ecological functions of rivers. It has significant practical importance and application value for promoting ecological civilization and achieving sustainable development.

[0003] Existing technologies rely excessively on human experience in the selection and weighting of indicators in multi-indicator comprehensive evaluation, which is easily influenced by subjective preferences and may lead to evaluation results that deviate from the actual health status of rivers. In addition, existing methods generally use general standards or regional experience thresholds for health evaluation, without fully considering the differences in hydrological characteristics and ecological needs of different rivers. Therefore, they have the drawback of low accuracy in health evaluation. Summary of the Invention

[0004] To improve the accuracy of health assessments of river aquatic ecosystems, this application provides a method, system, medium, and product for assessing the health of river aquatic ecosystems.

[0005] Firstly, this application provides a method for assessing the health of a river aquatic ecosystem, employing the following technical solution: A method for assessing the health of a river aquatic ecosystem includes: Obtain multiple criterion indicators and criterion indicator data for the river to be evaluated at each criterion level; Based on the preset indicator scoring neural network model and the data of each criterion indicator, the indicator score value corresponding to each criterion indicator is obtained. Obtain the preset indicator weights and preset criterion layer weights corresponding to the river to be evaluated. Based on the preset indicator weights, preset criterion layer weights, and scores of each indicator corresponding to the river to be evaluated, determine the comprehensive river health score corresponding to the river to be evaluated. The health status level of the river to be evaluated is determined based on the comprehensive river health score.

[0006] By adopting the above technical solution, and comprehensively considering the criterion indicator data of the river under evaluation at each criterion level, a health assessment of the river is conducted. This avoids the one-sidedness of health assessment caused by relying on a single factor, thereby reducing the interference of a single factor on the health assessment results and ensuring the integrity of the assessment perspective. In addition, by using a preset indicator scoring neural network to assign scores to each criterion indicator, the neural network model's ability to learn and fit complex data patterns facilitates the in-depth exploration of the potential nonlinear mapping relationship between each criterion indicator data and its corresponding score value. This overcomes the limitations of traditional manual scoring that relies on experience, thus improving the accuracy of the scoring results. On this basis, by integrating all highly accurate indicator scores and combining them with scientifically preset indicator weights and criterion level weights for comprehensive calculation, the true contribution of each criterion indicator is effectively integrated into the comprehensive river health score. This avoids the impact of local criterion indicator data errors or unreasonable weights on the overall health assessment results, thereby improving the accuracy of health assessments of river aquatic ecosystems.

[0007] In one possible implementation, obtaining the index score value corresponding to each criterion index based on a preset index scoring neural network model and various criterion index data includes: Identify the criterion indicator features corresponding to each criterion indicator data, and determine the indicator scoring strategy corresponding to each criterion indicator feature from the preset indicator scoring neural network model based on each criterion indicator feature. Based on the data of each criterion indicator and the corresponding indicator scoring strategy, the indicator score value corresponding to each criterion indicator is determined.

[0008] By adopting the above technical solution, the characteristics of the criteria indicators contained in different criteria indicator data are identified, and a corresponding exclusive scoring strategy is assigned to each criterion indicator characteristic. This helps to avoid scoring deviations caused by mismatched scoring strategies, thereby improving the accuracy of determining the corresponding indicator score for each criterion indicator.

[0009] In one possible implementation, determining the comprehensive river health score for the river to be evaluated based on the preset index weights, the preset criterion layer weights, and the scores of each index includes: Based on the preset indicator weights, the preset criterion layer weights, the indicator scores corresponding to each criterion indicator, and the first comprehensive river health scoring formula, the comprehensive river health score is determined, wherein the first comprehensive river health scoring formula is: ,in: RHI i The comprehensive river health score represents the i-th river to be evaluated. ZB nw The preset indicator weight of the nth indicator in the characterization criterion layer; ZB nr The score assigned to the nth indicator in the characterization criteria layer; YMB mw The preset criterion layer weights represent the m-th criterion layer.

[0010] By adopting the above technical solution, a specific implementation method is provided for determining the comprehensive river health score of the river to be evaluated.

[0011] In one possible implementation, when the river to be evaluated contains segmented sections, the following is also included: Identify the number of river segments corresponding to the river segment to be evaluated, the segment length of each river segment, and the comprehensive health score of each segment; Based on the number of segments, the segment length of each segment, the comprehensive health score of each segment, and the comprehensive health score formula for the second river, the comprehensive health score of the river to be evaluated, which includes segmented rivers, is determined. The comprehensive health score formula for the second river is as follows: ,in: RHI characterizes the overall river health score of the river to be evaluated, which includes segmented river sections. RHI i The overall health score of the i-th segment of the river is assigned. W i Represents the i-th segment of the river and the segment length; R s This characterizes the number of segments in a segmented river.

[0012] By adopting the above technical solution, when the river to be evaluated includes segmented rivers, the data of each segmented river can be independently verified and scored through segmented integration processing. Then, the impact of local data errors on the overall result can be weakened through weighted integration, thereby facilitating the improvement of the accuracy of the comprehensive river health score of the river to be evaluated.

[0013] In one possible implementation, the process of determining the preset index weights includes: Subjective weights are calculated based on the scores assigned to each criterion indicator to obtain the weights of multiple subjective indicators corresponding to each criterion indicator. Objective weights are calculated based on the scores assigned to each criterion indicator to obtain the weights of multiple objective indicators corresponding to each criterion indicator. Weight fitting is performed on the weights of multiple subjective indicators and multiple objective indicators corresponding to each criterion indicator to obtain the preset indicator weights corresponding to each criterion indicator.

[0014] By adopting the above technical solutions, subjective weight calculation is usually based on the evaluator's experience in judging the importance of the criteria indicators, which is convenient to reflect the inherent attributes of the river water ecosystem and the actual governance needs. On the other hand, objective weight calculation is convenient to reflect the distinction of the criteria indicators in the actual health assessment of the river health status. By combining the two, it is easy to avoid the limitations of relying on experience due to a single subjective weight, which may be detached from the actual data, or ignoring ecological logic due to a single objective weight, which may be interfered with by abnormal data. It is easy to make the preset indicator weights conform to ecological cognition while also conforming to the essence of the data.

[0015] In one possible implementation, weight fitting is performed on the weights of multiple subjective indicators and multiple objective indicators corresponding to the criterion indicator to obtain the preset indicator weights corresponding to the criterion indicator, including: The weights of multiple subjective indicators and multiple objective indicators corresponding to the criterion indicators are used as input data and respectively input into a preset first neural network model and a preset second neural network model for weight fitting to obtain a first fitting weight and a second fitting weight. The preset first neural network model outputs the first fitting weight and the preset second neural network model outputs the second fitting weight. Based on the performance metrics of the preset first neural network model and the preset second neural network model, determine the first weight contribution ratio corresponding to the preset first neural network model and the second weight contribution ratio corresponding to the preset second neural network model; Based on the first fitting weight, the second fitting weight, the contribution ratio of the first weight, and the contribution ratio of the second weight, the preset index weight corresponding to the criterion index is determined.

[0016] By adopting the above technical solution, the parallel processing of the two models facilitates the analysis of the intrinsic relationship between subjective and objective weights from different perspectives, thereby improving the fitting effect. In addition, by identifying and analyzing the performance indicators of the two neural network models and dynamically determining their respective weight contribution ratios, the accuracy of the weight fitting results can be further improved.

[0017] Secondly, this application provides an evaluation system, which adopts the following technical solution: An evaluation system comprising: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: perform the above-described river aquatic ecosystem health assessment method.

[0018] Thirdly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium includes: a computer program stored thereon that can be loaded by a processor and execute the above-described river aquatic ecosystem health assessment method.

[0019] Fourthly, this application provides a computer program product, which adopts the following technical solution: A computer program product includes a computer program that, when executed by a processor, implements the aforementioned method for assessing the health of a river aquatic ecosystem.

[0020] In summary, this application includes at least one of the following beneficial technical effects: By comprehensively considering the criterion indicator data of the river under evaluation at various criterion levels, a health assessment of the river is conducted. This avoids the one-sidedness of health assessments caused by relying on a single factor, thereby reducing the interference of a single factor on the health assessment results and ensuring the integrity of the assessment perspective. In addition, by using a pre-set indicator scoring neural network to assign scores to each criterion indicator, the neural network model's ability to learn and fit complex data patterns facilitates the in-depth exploration of the potential nonlinear mapping relationship between each criterion indicator data and its corresponding score value. This overcomes the limitations of traditional manual scoring that relies on experience, thus improving the accuracy of the scoring results. On this basis, by integrating all highly accurate indicator scores and combining them with scientifically preset indicator weights and criterion level weights for comprehensive calculation, the true contribution of each criterion indicator is effectively integrated into the comprehensive river health score. This avoids the impact of local criterion indicator data errors or unreasonable weights on the overall health assessment results, thereby improving the accuracy of health assessments of river aquatic ecosystems.

[0021] Subjective weight calculation is usually based on the evaluator's experience in judging the importance of the criteria indicators, which is convenient to reflect the inherent attributes of the river water ecosystem and the actual governance needs. Objective weight calculation, on the other hand, is convenient to reflect the distinction of the criteria indicators in the actual health assessment of the river health status. Combining the two can avoid the limitations of relying on experience due to a single subjective weight, which may be detached from the actual data, or ignoring ecological logic due to a single objective weight, which may be affected by abnormal data. It can make the preset indicator weights conform to ecological cognition while also being consistent with the essence of the data. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating a method for assessing the health of a river aquatic ecosystem according to an embodiment of this application. Figure 2 This is a flowchart illustrating a method for determining the weight of a preset indicator in an embodiment of this application. Figure 3 This is a schematic diagram of the structure of an evaluation system according to an embodiment of this application. Detailed Implementation

[0023] The following is in conjunction with the appendix Figures 1 to 3 This application will be described in further detail.

[0024] After reading this specification, those skilled in the art may make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0025] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] It should be noted that, in the optional embodiments of this application, the data related to object information, when applied to specific products or technologies, requires the permission or consent of the object. Furthermore, the collection, use, and processing of this data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. In other words, if the embodiments of this application involve data related to an object, it must be obtained with the object's authorization and consent, the authorization and consent of relevant departments, and in accordance with the relevant laws, regulations, and standards of the country and region. If the embodiments involve personal information, the acquisition of all personal information requires the individual's consent. If sensitive information is involved, the separate consent of the information subject is required. The embodiments also need to be implemented with the object's authorization and consent.

[0027] Specifically, this application provides a method for assessing the health of a river aquatic ecosystem, executed by an assessment system. This system can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and this application does not impose any limitations on this.

[0028] refer to Figure 1 , Figure 1 This is a flowchart illustrating a method for assessing the health of a river aquatic ecosystem according to an embodiment of this application. The method includes steps S110-S140, wherein: Step S110: Obtain multiple criterion indicators and criterion indicator data corresponding to each criterion layer of the river to be evaluated.

[0029] Specifically, the rivers to be evaluated are those requiring health assessments, and relevant staff can upload their data to the evaluation system according to actual health assessment needs. In the comprehensive evaluation system of multiple indicators, including river aquatic ecosystem health assessment, the criteria layer is one of the core layers for constructing the evaluation framework. Because rivers in different regions vary significantly in terms of natural environment and social impact, the health of river aquatic ecosystems is easily affected by hydrology, water quality, biology, geomorphology, human activities, and other factors. Directly using a large number of scattered indicators for health assessment may lead to confusion in the evaluation logic. Therefore, a large number of indicators can be assigned to different criteria layers, making the evaluation framework clearer and more hierarchical. In this embodiment, the criteria layer includes a "basin" criteria layer, a "water" criteria layer, a biological criteria layer, and a social service function criteria layer. The "basin" criteria layer includes six criteria indicators: river longitudinal connectivity index, riverbank stability, shoreline vegetation coverage, standardized construction rate of sewage outfalls, rationality of sewage outfall layout, and the status of "four irregularities" in the river channel. The "water" criteria layer includes three criteria indicators: ecological flow satisfaction, water quality, and water body self-purification capacity. The biological criteria layer includes two criteria indicators: fish population index and waterbird status. The social service criteria layer includes four criteria indicators: flood control compliance of dikes, flood control compliance of cross-river structures, shoreline management index, and public satisfaction. In addition, criteria indicators can also include navigation guarantee rate, macrobenthic invertebrate biodiversity integrity, etc. Specific criteria indicators can be set by relevant technical personnel according to the actual health assessment needs of the river to be evaluated.

[0030] The criterion indicator data describes or summarizes the content of the corresponding criterion indicator and directly reflects the actual state, characteristics, or performance of each criterion indicator. It can be collected or tested by relevant personnel through methods such as on-site monitoring, laboratory analysis, historical data compilation, and questionnaires, and then uploaded to the evaluation system. For example, the criterion indicator data corresponding to the shoreline vegetation coverage rate in the "basin" criterion layer could be remote sensing images containing the shoreline vegetation of the river to be evaluated, or on-site measurement data of the shoreline vegetation of the river to be evaluated. The criterion indicator data corresponding to the shoreline management index in the social service criterion layer could be: "Currently, the total planned riverbank length is 18.90 km. After the delineation of the guiding line, the area between the guiding lines on both banks is the flood discharge area designed for flood control standards. The water area, sandbars, beaches, flood discharge area, and embankment protection areas, as well as the area extending horizontally outward 5-10 m from the guiding line, are designated as the river management area." The specific form of the criterion indicator data is not specifically limited in this application embodiment.

[0031] Step S120: Based on the preset indicator scoring neural network model and the data of each criterion indicator, obtain the indicator score value corresponding to each criterion indicator.

[0032] Specifically, the preset indicator scoring neural network model includes scoring strategies for multiple criterion indicator data. Different criterion indicators correspond to different scoring methods, and adopting personalized scoring methods helps improve the fit between the scoring results and the actual situation. Furthermore, to avoid scoring deviations caused by mismatched scoring strategies, based on the preset indicator scoring neural network model and the data of each criterion indicator, the indicator score value corresponding to each criterion indicator is obtained, which may specifically include: Identify the criterion indicator features corresponding to each criterion indicator data, and determine the indicator scoring strategy corresponding to each criterion indicator feature from the preset indicator scoring neural network model based on each criterion indicator feature; determine the indicator score value corresponding to each criterion indicator based on each criterion indicator data and the corresponding indicator scoring strategy.

[0033] Specifically, the scoring strategy for the "basin" criterion layer in the preset index scoring neural network model can include: a1. River Longitudinal Connectivity Index Scoring: A preset feature recognition algorithm identifies the corresponding types and numbers of river-blocking structures from the criterion index data. Based on this, the number of longitudinal connectivity structures is determined. Longitudinal connectivity structures are those equipped with fish passage facilities, capable of normal passage, and able to meet the biological and ecological flow requirements of the river being evaluated. Scoring is then assigned according to the number of longitudinal connectivity structures and the river longitudinal connectivity index scoring standard threshold table. This table includes scoring values ​​corresponding to different numbers of longitudinal connectivity structures per 100 km. For example, if the river being evaluated contains one longitudinal connectivity structure per 100 km, the corresponding river longitudinal connectivity index score is 20 points. The river longitudinal connectivity index scoring standard threshold table can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0034] a2. Riverbank Stability Scoring: A preset feature recognition algorithm identifies the corresponding bank slope angle, vegetation cover, slope height, bank matrix, and riverbank erosion status from the criterion index data corresponding to riverbank stability. Then, based on a riverbank stability scoring standard threshold table, the corresponding riverbank stability score is determined. This table includes riverbank stability scores corresponding to different combinations of bank slope angle, vegetation cover, slope height, bank matrix, and riverbank erosion status. For example, when the bank slope angle is less than or equal to 15°, the vegetation cover is greater than or equal to 75%, the slope height is less than or equal to 1m, the bank matrix is ​​bedrock, and there are no signs of riverbank erosion, the corresponding riverbank stability score is 100 points. The riverbank stability scoring standard threshold table can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0035] a3. Shoreline Vegetation Coverage Scoring: A preset feature recognition algorithm can be used to identify the proportion of the vertical projection area of ​​natural and artificial vegetation on the riverbank to the total riverbank area (i.e., the shoreline vegetation coverage rate) from the criterion index data corresponding to the shoreline vegetation coverage rate. Then, the corresponding shoreline vegetation coverage rate score is determined according to the shoreline vegetation coverage rate scoring standard threshold table. This table includes shoreline vegetation coverage rate scores corresponding to different riverbank vegetation coverage rates. For example, when the shoreline vegetation coverage rate is 50%-75%, the corresponding shoreline vegetation coverage rate score can be determined to be 75 points. The shoreline vegetation coverage rate scoring standard threshold table can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0036] a4. Scoring for Standardized Construction of River Discharge Outlets: A preset feature recognition algorithm can be used to identify the number and total number of river discharge outlets undergoing standardized construction from the corresponding criteria and indicators. The standardized construction rate of river discharge outlets is then calculated based on the formula, and the corresponding level is determined. Finally, the corresponding standardized construction rate is determined according to the level and the scoring standard threshold table. The formula for the standardized construction rate of river discharge outlets is R... G =N i / N*100, where R G To increase the standardization rate of sewage outfalls into rivers, N i The number of sewage outfalls discharging into rivers for standardized construction is defined by N, representing the total number of such outfalls. The threshold table for the scoring standard of the standardized construction rate of sewage outfalls includes different levels of standardized construction rate corresponding to different scores. For example, if the standardized construction rate of a sewage outfall is rated as "Excellent," its corresponding score is 100 points. The threshold table for the scoring standard of the standardized construction rate of sewage outfalls can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0037] a5. Scoring on the Reasonableness of River Discharge Outlet Layout: A preset feature recognition algorithm can identify the location, number, and corresponding water quality of river discharge outlets from the criterion index data corresponding to the reasonableness of their layout. Then, based on the threshold table for the scoring standard of river discharge outlet layout, the corresponding score is determined. This threshold table includes multiple parameter combinations for the reasonableness of river discharge outlet layout, such as the location, number, and corresponding water quality of the outlets. For example, if there are no river discharge outlets in either the primary or secondary protection zones of the drinking water source, no outlets within 1 km upstream of the water intake, and the length of the sewage belt formed by the discharge is less than 1 km, or the width is less than 1 / 4 of the river width, the corresponding score for the reasonableness of the river discharge outlet layout is 50 points. The threshold table for the scoring standard of river discharge outlet layout can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0038] a6. Scoring of "Four Disorders" in River Channels: A preset feature recognition algorithm can identify the degree of illegal mining, illegal occupation, illegal dumping, and illegal construction from the corresponding criterion indicator data. Then, based on the river channel "Four Disorders" scoring standard threshold table, the corresponding river channel "Four Disorders" score is determined. River sections without "Four Disorders" receive 100 points. Deductions for "Four Disorders" should consider their severity, and deductions are made until all points are reached. For example, if illegal mining is a general problem, 5 points are deducted; illegal occupation is a relatively serious problem, 25 points are deducted; illegal dumping is a major problem, 50 points are deducted; and illegal construction is a general problem, 5 points are deducted, for a total deduction of 85 points. The corresponding river channel "Four Disorders" score is 15 points. The river channel "Four Disorders" scoring standard threshold table can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0039] The scoring strategy for the "water" criterion layer in the preset index scoring neural network model can include: b1. Assignment of ecological flow satisfaction level: The river type to be evaluated can be identified from the criterion index data corresponding to the ecological flow satisfaction level based on the preset feature recognition algorithm. The river types include rivers with perennial flow and seasonal rivers. For rivers with perennial flow, the minimum daily average flow ratio during the dry season and the minimum daily average flow ratio during the wet season can be determined using the ratio of minimum daily average flow to ecological flow. Then, the corresponding ecological flow satisfaction score is determined based on the ecological flow satisfaction score threshold table. This table includes different ecological flow satisfaction scores corresponding to different minimum daily average flow ratios during the dry or wet seasons. For example, when the minimum daily average flow ratio during the wet season is 40%, the corresponding ecological flow satisfaction score is 80 points. For seasonal rivers, the runoff length / water surface area retention rate can be determined using the runoff length / water surface area retention rate method. Then, the corresponding ecological flow satisfaction score is determined based on the runoff length retention rate threshold table. This table includes different ecological flow satisfaction scores corresponding to different runoff length retention rates. For example, when the runoff length retention rate is 85%, the corresponding ecological flow satisfaction score is 75 points. The threshold tables for scoring the degree of ecological flow satisfaction and the threshold tables for scoring the runoff length retention rate can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0040] b2. Water Quality Score: A preset feature recognition algorithm identifies the corresponding water quality category from the criterion index data corresponding to different water quality levels. Then, based on a water quality score threshold table, the corresponding water quality score is determined. This threshold table contains scores for different water quality levels; for example, when the water quality level is Level 2, the corresponding score is 90 points. The water quality score threshold table can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0041] b3. Water Body Self-Purification Capacity Scoring: A preset feature recognition algorithm can be used to identify the corresponding dissolved oxygen concentration from the criterion index data related to water body self-purification capacity. Then, based on a water body self-purification capacity scoring standard threshold table, the corresponding water body self-purification capacity score is determined. This table includes scores corresponding to different dissolved oxygen concentrations; for example, when the dissolved oxygen concentration is greater than or equal to 90%, the corresponding water body self-purification capacity score is 100 points. The water body self-purification capacity scoring standard threshold table can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0042] The scoring strategy for the biological criteria layer in the preset index scoring neural network model may include: c1. Fish Retention Index Scoring: A preset feature recognition algorithm identifies the number of fish species (excluding invasive species) surveyed in the river under evaluation and the historical number of fish species in the river under evaluation from the criterion index data corresponding to the fish retention index. Then, the corresponding fish retention index is determined according to the fish retention index calculation formula. Finally, the fish retention index score is determined based on the fish retention index scoring standard threshold table. The fish retention index calculation formula is FOEI = FO / FE * 100, where FOEI is the fish retention index, FO is the number of fish species surveyed in the river under evaluation, and FE is the historical number of fish species in the river under evaluation. The fish retention index scoring standard threshold table contains fish retention index scores corresponding to different fish retention indices. For example, when the fish retention index is 75%, the corresponding fish retention index score is 60 points. The fish retention index scoring standard threshold table can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0043] c2. Waterbird Status Scoring: A preset feature recognition algorithm can identify the species, quantity, and presence of rare bird species from the corresponding criterion index data for waterbird status. Then, based on a bird habitat status scoring standard threshold table, the corresponding waterbird status score is determined. This table includes waterbird status scores corresponding to different combinations of bird species, quantity, and the presence of rare bird species. For example, when there are many species and quantities, and rare bird species are present, the corresponding waterbird status score is 95 points. The bird habitat status scoring standard threshold table can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0044] The scoring strategy for the social service function criterion layer in the pre-defined indicator scoring neural network model may include: d1. Dike Flood Control Compliance Scoring: A preset feature recognition algorithm identifies the proportion of dike length meeting flood control standards out of the total dike length from the corresponding criterion index data, i.e., the flood control compliance rate. Then, based on the dike flood control compliance score threshold table, the corresponding score is determined. This table includes scores corresponding to different flood control compliance rates; for example, when the compliance rate is greater than or equal to 95%, the corresponding score is 100 points. The dike flood control compliance score threshold table can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0045] d2. Scoring of Flood Control Compliance of Cross-River Structures: A preset feature recognition algorithm can be used to identify the flood control compliance level of cross-river structures from the corresponding criterion index data. Then, based on a threshold table for scoring the flood control compliance level of cross-river structures, the corresponding score is determined. This threshold table includes different scores for different levels of flood control compliance of cross-river structures. For example, when the flood control compliance level of a cross-river structure is greater than or equal to 95%, the corresponding score is 100 points. The threshold table for scoring the flood control compliance level of cross-river structures can be determined by relevant technical personnel based on historical experimental data and uploaded to the evaluation system in advance.

[0046] d3. Shoreline Management Index Scoring: Based on a preset feature recognition algorithm, the total shoreline length, the length of developed and utilized shoreline, and the length of utilized shoreline that has been well protected can be identified from the corresponding criterion indicator data of the shoreline management index. Then, the corresponding shoreline utilization management index is calculated based on the calculation formula of the shoreline management and utilization index. The calculation formula for the shoreline management and utilization index is as follows: , R u For shoreline utilization management index, L n The total length of the shoreline. L u The length of the shoreline that has been developed and utilized. L 0 The shoreline utilization and management index score is calculated as follows: shoreline utilization and management index = shoreline management and utilization index × 100.

[0047] d4. Public Satisfaction Score: The average satisfaction level of the public with the river environment, water quality and quantity, and water-related landscape can be identified from the criterion index data corresponding to public satisfaction based on the preset feature recognition algorithm. Then, the score is determined based on the average satisfaction and the public satisfaction index scoring standard threshold table. Different average satisfaction intervals in the public satisfaction index scoring standard threshold table correspond to different public satisfaction scores. For example, the average satisfaction of 85 falls into the average satisfaction interval and corresponds to a public satisfaction score of 80.

[0048] The above method can be used to obtain the score for each criterion indicator.

[0049] Step S130: Obtain the preset indicator weights and preset criterion layer weights corresponding to the river to be evaluated. Based on the preset indicator weights, preset criterion layer weights, and the scores of each indicator, determine the comprehensive river health score corresponding to the river to be evaluated.

[0050] Specifically, different rivers to be evaluated have different preset index weights and preset criterion layer weights, which can be obtained from the evaluation system based on the river identifier corresponding to the river to be evaluated. The preset criterion layer weights are used to characterize the importance of different criterion layers in the health evaluation process, and the preset index weights are used to characterize the importance of each criterion indicator within the criterion layer. This application provides a specific implementation method for determining the comprehensive river health score of a river to be evaluated, namely, determining the comprehensive river health score based on the preset index weights, preset criterion layer weights, the index score value corresponding to each criterion indicator, and a first comprehensive river health scoring formula. The first comprehensive river health scoring formula is as follows: ,in: RHI i The comprehensive river health score is assigned to the i rivers to be evaluated. ZB nw The preset indicator weight of the nth indicator in the characterization criterion layer; ZB nr The score assigned to the nth indicator in the characterization criteria layer; YMB mw The preset criterion layer weights represent the m-th criterion layer.

[0051] The calculation principle is as follows: based on the preset indicator weights and scores of each indicator corresponding to each criterion layer, the score of each criterion layer is determined; then, based on the preset criterion layer weights and scores of each criterion layer, the score of each criterion layer is determined; finally, the sum of the scores of each criterion layer is calculated to obtain the comprehensive river health score of the river to be evaluated.

[0052] Step S140: Determine the health status level of the river to be evaluated based on the comprehensive river health score.

[0053] Specifically, different comprehensive health scores for rivers correspond to different health status levels. When a river's comprehensive health score falls within the range of [90, 100), its corresponding health status level is determined to be very healthy; when it falls within the range of [75, 90), its corresponding health status level is determined to be healthy; when it falls within the range of [60, 75), its corresponding health status level is determined to be sub-healthy; when it falls within the range of [40, 60), its corresponding health status level is determined to be unhealthy; and when it falls within the range of [0, 40), its corresponding health status level is determined to be poor. To facilitate intuitive viewing of the health status level of the river being evaluated, different colors can be used to represent it. For example, blue, green, yellow, orange, and red can be used to represent very healthy, healthy, sub-healthy, unhealthy, and poor, respectively. The specific colors corresponding to different health status levels are not specifically limited in this embodiment of the application and can be set by relevant personnel according to actual needs.

[0054] In this embodiment, by comprehensively considering the criterion index data of the river to be evaluated at each criterion layer, a health assessment of the river is conducted. This avoids the one-sidedness of health assessment caused by relying on only a single factor, thereby reducing the interference of a single factor on the health assessment results and ensuring the integrity of the assessment perspective. In addition, by using a preset index scoring neural network to assign scores to each criterion index, the neural network model's ability to learn and fit complex data patterns facilitates the in-depth mining of the potential nonlinear mapping relationship between each criterion index data and the corresponding index score value. This overcomes the limitations of traditional manual scoring that relies on experience, thereby improving the accuracy of the scoring results. On this basis, by integrating all highly accurate index scores and combining them with scientific preset index weights and criterion layer weights for comprehensive calculation, the true contribution of each criterion index is effectively integrated into the comprehensive river health score. This avoids the impact of local criterion index data errors or unreasonable weights on the overall health assessment results, thereby improving the accuracy of health assessments of river aquatic ecosystems.

[0055] Furthermore, when the river to be evaluated comprises segmented sections, the above method can be used to conduct health assessments on each segment. Additionally, the following can also be applied: Identify the number of river segments corresponding to the river to be evaluated, the segment length of each river segment, and the comprehensive health score of each segment; based on the number of segments, the segment length of each river segment, the comprehensive health score of each segment, and the second comprehensive health score formula, determine the comprehensive health score of the river to be evaluated that includes the river segments, where the second comprehensive health score formula is: ,in: RHI characterizes the overall river health score of the river to be evaluated, which includes segmented river sections. RHI i The overall health score of the i-th segment of the river is assigned. W i Represents the i-th segment of the river and the segment length; R s This characterizes the number of segments in a segmented river.

[0056] Specifically, the method provided in the above embodiments can be used to calculate the comprehensive health score of each segment of the river, and to identify the number and length of each segment of the river. The comprehensive health score of each segment, the number of segments, and the length of each segment are then imported into the second comprehensive health score formula to obtain the final comprehensive health score of the river to be evaluated, which includes the segmented river. Through segmented integration processing, the data of each segment of the river can be independently verified and scored first, and then the impact of local data errors on the overall result can be weakened by weighted integration, thereby facilitating the improvement of the accuracy when determining the comprehensive health score of the river to be evaluated.

[0057] Furthermore, this application provides a method for determining the weights of preset indicators corresponding to each criterion indicator, which may specifically include steps S210-S230, such as... Figure 2 As shown, where: Step S210: Calculate subjective weights based on the scores of each criterion indicator to obtain the weights of multiple subjective indicators corresponding to each criterion indicator.

[0058] Specifically, this application provides three subjective weight calculation methods: expert scoring, analytic hierarchy process (AHP), and pecking order graph method.

[0059] Regarding the expert scoring method: Questionnaire surveys can be used to obtain the evaluation results of the importance of each criterion level and the importance of each criterion indicator within each criterion level. Specifically, all criterion levels and each criterion indicator can be listed, and multiple experts in relevant fields can be asked to score the relative importance of each criterion level and each criterion indicator. Finally, the scores of each criterion level and each criterion indicator are normalized to obtain the first subjective weight determined by the expert scoring method. The first subjective weight includes the first subjective weight of each criterion level and the first subjective weight of each criterion indicator.

[0060] Regarding the Analytic Hierarchy Process (AHP): The AHP treats a complex multi-objective decision-making problem as a system, decomposing the objective into multiple criteria and indicators. It calculates the hierarchical single ranking (weights) and overall ranking using qualitative indicator fuzzy quantification methods, thereby optimizing the decision results. Specifically, it can utilize expert scoring, employing a 1-9 scale for pairwise comparisons to determine the relative importance of each criterion level and indicator, thus constructing a judgment matrix. The eigenvalues ​​and eigenvectors of the judgment matrix are then calculated, and the eigenvectors are normalized to obtain the second subjective weights determined by the AHP. These second subjective weights include the second subjective weights of each criterion level and each indicator. Since the judgment matrix is ​​determined using expert scoring, it may contain some subjectivity, potentially leading to logical errors in subsequent calculations. Therefore, a consistency check can be performed on the judgment matrix. If the data in the judgment matrix passes the consistency check, it indicates that logical errors will not occur in subsequent calculations. The CR value can be used to perform a consistency check on the judgment matrix, where the CR value can be used first... Consistency indicators were identified, among which, CI As a consistency indicator, λ max To determine the largest eigenvalue of a matrix, where n is the order of the matrix to be determined, and then based on... The consistency ratio was determined, among which, CR The consistency ratio, RI As the average random consistency index, when CR If the value is less than 0.1, the judgment matrix can be considered to have passed the consistency test; otherwise, it means that the consistency test has not been passed. The method of performing the consistency test is not specifically limited in this embodiment of the application.

[0061] Regarding the pecking order graph method: The pecking order graph method analyzes the importance of each indicator by constructing a matrix diagram. The input is the indicator scores for four rivers. The specific steps are as follows: First, calculate the average value of each indicator. A relatively larger value is assigned 1 point, a relatively smaller value is assigned 0 points, and completely equal values ​​are assigned 0.5 points. Then, construct a matrix based on the calculated average values. The elements in the matrix represent the relative importance of each indicator. Finally, normalize the data in the matrix to obtain the third subjective weight determined by the pecking order graph method. The third subjective weight includes the third subjective weights of each criterion layer and the third subjective weights of each criterion indicator.

[0062] Step S220: Calculate the objective weights based on the scores of each criterion indicator to obtain the weights of multiple objective indicators corresponding to each criterion indicator.

[0063] Specifically, this application also provides four objective weight calculation methods, namely, information content weight method, CRITIC weight method, principal component analysis method, and entropy weight method.

[0064] Regarding the information content weighting method: Also known as the coefficient of variation method, this method calculates weights based on the coefficient of variation of the data. A larger coefficient of variation indicates a greater amount of information carried, thus increasing the weight accordingly. The specific steps may include: first, standardizing the criterion indicator data to ensure that criterion indicators of different magnitudes can be compared; then, calculating the coefficient of variation (the ratio of standard deviation to mean) for the standardized criterion indicators; finally, based on the coefficient of variation of each criterion indicator, calculating the first objective weight determined by the information content weighting method. This first objective weight includes the first objective weights for each criterion layer and the first objective weights for each criterion indicator.

[0065] Regarding the CRITIC weighting method: The CRITIC weighting method is an objective weighting method based on data volatility and the conflict between criterion indicators. Its core idea is to determine the weight of each criterion layer and each criterion indicator by calculating the comparative strength and conflict of the criterion indicator data. The specific steps are as follows: Calculate the standard deviation to measure the volatility of the criterion indicator data. The larger the standard deviation, the greater the volatility of the criterion indicator data, and the higher the weight should be assigned. Then calculate the correlation coefficient to measure the conflict between criterion indicators. The larger the correlation coefficient, the smaller the conflict between criterion indicators, and the weight should be reduced accordingly. Finally, normalize the calculation results of comparative strength and conflict to obtain the second objective weight determined by the CRITIC weighting method. The second objective weight includes the second objective weight of each criterion layer and the second objective weight of each criterion indicator.

[0066] Principal Component Analysis (PCA): PCA reduces the dimensionality of criterion index data through mathematical transformations, extracting new variables that can explain most of the variation. These new variables are called principal components. The weights of these principal components are calculated mathematically, without relying on human subjective judgment, thus possessing high objectivity. Specific steps may include: first, standardizing the criterion index data so that the mean of each feature is 0 and the variance is 1; then, calculating the covariance matrix based on the standardized data; and finally, calculating eigenvalues ​​and eigenvectors through the covariance matrix. The eigenvectors represent principal components, and the eigenvalues ​​represent the variance contribution rate of each principal component; finally, multiplying the variance contribution rate of each principal component by the loading coefficient of that principal component on the original variables, and performing normalization processing, we obtain the third objective weights determined by PCA. The third objective weights include the third objective weights of each criterion layer and the third objective weights of each criterion index.

[0067] Regarding the entropy weight method: The entropy weight method is a method for determining the weights of criteria and indicators based on the concept of information entropy. The fourth objective weight is determined based on the entropy weight method. The third objective weight includes the fourth objective weight of each criterion layer and the fourth objective weight of each criterion indicator.

[0068] Step S230: Perform weight fitting on the weights of multiple subjective indicators and multiple objective indicators corresponding to each criterion indicator to obtain the preset indicator weights corresponding to each criterion indicator.

[0069] Specifically, expert scoring, analytic hierarchy process (AHP), and ordinal ranking methods rely on human judgment. While these methods can reflect professional experience and practical needs, they may be influenced by expert subjective preferences, knowledge limitations, or regional biases, leading to excessive subjectivity and insufficient result stability. Information weighting, CRITIC weighting, principal component analysis, and entropy weighting are entirely based on the analysis of data characteristics. While these methods avoid human bias, they may overlook actual business logic or professional experience. Therefore, by fitting these two types of weights, the influence of subjective experience and objective data can be balanced, preserving the rationality of professional judgment while incorporating the objective laws reflected by the data, thus avoiding weight bias caused by a single method. A backpropagation (BP) neural network can be used to fit the weights of multiple subjective and objective indicators corresponding to each criterion indicator. Alternatively, an MLP model can be used to fit the weights of multiple subjective and objective indicators corresponding to each criterion indicator. The specific fitting process is not specifically limited in this embodiment.

[0070] However, historical fitting data reveals that BP neural networks perform too well during training, relying excessively on details and noise in the training data. This makes the model highly sensitive to changes in the training data; performance can significantly degrade with alterations. MLPs, being parametric models, require sufficient data to learn the mapping between input and output. Insufficient sample size can lead to underfitting, meaning the model may fail to capture core patterns, resulting in poor fitting. Therefore, to further improve the accuracy of weight fitting results, when performing weight fitting on multiple subjective and objective indicator weights corresponding to the criterion indicator to obtain the preset indicator weights, the following can be included: The weights of multiple subjective and objective indicators corresponding to the criterion indicators are used as input data and fed into a first and a second preset neural network model for weight fitting, respectively, to obtain a first fitting weight and a second fitting weight. The first preset neural network model outputs the first fitting weight, and the second preset neural network model outputs the second fitting weight. Based on the performance indicators of the first and second preset neural network models, the contribution ratio of the first weight corresponding to the first preset neural network model and the contribution ratio of the second weight corresponding to the second preset neural network model are determined. Based on the first fitting weight, the second fitting weight, the contribution ratio of the first weight, and the contribution ratio of the second weight, the preset indicator weights corresponding to the criterion indicators are determined.

[0071] Specifically, for any given criterion, the first preset neural network model can be a BP neural network model, and the second preset neural network model can be an MLP model. The performance indicators corresponding to the preset neural network models are used to quantitatively evaluate the model's fitting effect, stability, and reliability. Different performance indicators correspond to different weight contribution ratios. Performance indicators can be error-related indicators or correlation indicators. The specific performance indicators can be determined by relevant personnel according to actual needs. When the performance indicator is a correlation indicator, the first difference between the correlation index of the first preset neural network model and 1, and the second difference between the correlation index of the second preset neural network model and 1 can be determined first. The first weight contribution ratio and the second weight contribution ratio are determined based on the first and second differences. The smaller the first or second difference, the closer the corresponding correlation index is to 1. This also indicates a stronger linear correlation between the fitting weights output by the corresponding neural network model and the input subjective and objective indicator weights. The neural network model has a stronger interpretive ability for the weight data. In other words, the smaller the difference, the larger the corresponding weight contribution ratio.

[0072] Based on the performance metrics of the first and second preset neural network models, the contribution ratios of the first and second weights can be determined. Finally, the preset index weights of the criterion are calculated by summing the first fitting weight, the second fitting weight, the contribution ratio of the first weight, and the contribution ratio of the second weight. The performance metrics of the first and second preset neural network models can be uploaded to the evaluation system in advance by relevant personnel. A weight ratio correspondence exists between the performance metrics and the contribution ratios, which can be determined by relevant personnel based on historical experimental data and then uploaded to the evaluation system. For example, when the first fitting weight of criterion A obtained under the fitting simulation of the first preset neural network model is 0.06, the second fitting weight obtained under the fitting simulation of the second preset neural network model is 0.07, the contribution ratio of the first weight corresponding to the performance metrics of the first preset neural network model is 0.4, and the contribution ratio of the second weight corresponding to the performance metrics of the second preset neural network model is 0.6, the preset index weight of criterion A can be calculated as 0.06*0.4 + 0.07*0.6 = 0.066. The preset index weights for all criterion indicators can be obtained using the above method.

[0073] This application provides an evaluation system, such as... Figure 3 As shown, Figure 3The evaluation system 300 shown includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the evaluation system 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this evaluation system 300 does not constitute a limitation on the embodiments of this application.

[0074] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0075] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by only one line, but this does not mean that there is only one bus or one type of bus.

[0076] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0077] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0078] The evaluation system includes, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Tablet PCs), PMPs (Portable Multimedia Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. It can also include servers. Figure 3 The evaluation system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0079] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments.

[0080] This application provides a computer program product including a computer program that, when executed by a processor, implements the methods described in any of the above embodiments.

[0081] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0082] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for assessing the health of a river aquatic ecosystem, characterized in that, include: Obtain multiple criterion indicators and criterion indicator data for the river to be evaluated at each criterion level; Based on the preset indicator scoring neural network model and the data of each criterion indicator, the indicator score value corresponding to each criterion indicator is obtained. Obtain the preset indicator weights and preset criterion layer weights corresponding to the river to be evaluated. Based on the preset indicator weights, preset criterion layer weights, and scores of each indicator corresponding to the river to be evaluated, determine the comprehensive river health score corresponding to the river to be evaluated. The health status level of the river to be evaluated is determined based on the comprehensive river health score.

2. The method for assessing the health of a river aquatic ecosystem according to claim 1, characterized in that, The process of obtaining the score for each criterion indicator based on a preset indicator scoring neural network model and various criterion indicator data includes: Identify the criterion indicator features corresponding to each criterion indicator data, and determine the indicator scoring strategy corresponding to each criterion indicator feature from the preset indicator scoring neural network model based on each criterion indicator feature. Based on the data of each criterion indicator and the corresponding indicator scoring strategy, the indicator score value corresponding to each criterion indicator is determined.

3. The method for assessing the health of a river aquatic ecosystem according to claim 1, characterized in that, The determination of the comprehensive river health score for the river under evaluation based on the preset index weights, the preset criterion layer weights, and the scores of each index for the river under evaluation includes: Based on the preset indicator weights, the preset criterion layer weights, the indicator scores corresponding to each criterion indicator, and the first comprehensive river health scoring formula, the comprehensive river health score is determined, wherein the first comprehensive river health scoring formula is: ,in: RHI i The comprehensive river health score represents the i-th river to be evaluated. ZB nw The preset indicator weight of the nth indicator in the characterization criterion layer; ZB nr The score assigned to the nth indicator in the characterization criteria layer; YMB mw The preset criterion layer weights represent the m-th criterion layer.

4. The method for assessing the health of a river aquatic ecosystem according to claim 3, characterized in that, When the river to be evaluated includes segmented sections, it also includes: Identify the number of river segments corresponding to the river segment to be evaluated, the segment length of each river segment, and the comprehensive health score of each segment; Based on the number of segments, the segment length of each segment, the comprehensive health score of each segment, and the comprehensive health score formula for the second river, the comprehensive health score of the river to be evaluated, which includes segmented rivers, is determined. The comprehensive health score formula for the second river is as follows: ,in: RHI characterizes the overall river health score of the river to be evaluated, which includes segmented river sections. RHI i The overall health score of the i-th segment of the river is assigned. W i Represents the i-th segment of the river and the segment length; R s This characterizes the number of segments in a segmented river.

5. The method for assessing the health of a river aquatic ecosystem according to claim 1, characterized in that, The process of determining the preset index weights includes: Subjective weights are calculated based on the scores assigned to each criterion indicator to obtain the weights of multiple subjective indicators corresponding to each criterion indicator. Objective weights are calculated based on the scores assigned to each criterion indicator to obtain the weights of multiple objective indicators corresponding to each criterion indicator. Weight fitting is performed on the weights of multiple subjective indicators and multiple objective indicators corresponding to each criterion indicator to obtain the preset indicator weights corresponding to each criterion indicator.

6. The method for assessing the health of a river aquatic ecosystem according to claim 5, characterized in that, Weight fitting is performed on the weights of multiple subjective indicators and multiple objective indicators corresponding to the criterion indicators to obtain the preset indicator weights corresponding to the criterion indicators, including: The weights of multiple subjective indicators and multiple objective indicators corresponding to the criterion indicators are used as input data and respectively input into a preset first neural network model and a preset second neural network model for weight fitting to obtain a first fitting weight and a second fitting weight. The preset first neural network model outputs the first fitting weight and the preset second neural network model outputs the second fitting weight. Based on the performance metrics of the preset first neural network model and the preset second neural network model, determine the first weight contribution ratio corresponding to the preset first neural network model and the second weight contribution ratio corresponding to the preset second neural network model; Based on the first fitting weight, the second fitting weight, the contribution ratio of the first weight, and the contribution ratio of the second weight, the preset index weight corresponding to the criterion index is determined.

7. An evaluation system, characterized in that, The evaluation system includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: perform a method for assessing the health of a river aquatic ecosystem according to any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, include: The system contains a computer program that can be loaded by a processor and executed as described in any one of claims 1-6 for assessing the health of a river aquatic ecosystem.

9. A computer program product, characterized in that, The system includes a computer program that, when executed by a processor, implements the steps of a method for assessing the health of a river aquatic ecosystem according to any one of claims 1-6.

Images