Regional water environment quality evaluation system and method based on artificial intelligence

Abstract

The invention discloses a regional water environment quality evaluation system and method based on artificial intelligence, and relates to the technical field of water environment evaluation.The regional water environment quality evaluation method comprises the steps that pollution detection is conducted on a river channel in a to-be-detected region through a sensor, and obtained pollution detection feature information is bound with the corresponding river channel position in the to-be-detected region; calculating a single-factor pollution index of each pollutant based on the pollution detection feature information; based on the corrected Nemerow index method, analyzing the comprehensive pollution index of each position in the river channel; constructing a pollution index change model of each position in the river channel through the comprehensive pollution index, and analyzing an association score between the river channel sections by using the pollution index change model in combination with the position information of the river channel; predicting the comprehensive pollution index; and analyzing the pollution index change value of the river channel section based on the prediction result. The accuracy of system analysis is improved; and automation of water environment quality assessment and early warning is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of water environment assessment, and in particular to a regional water environment quality assessment system and method based on artificial intelligence. Background Art

[0002] With the acceleration of industrialization and urbanization, water pollution is becoming increasingly serious, directly threatening the sustainable development of agricultural production and ecological environment. Water pollutants include heavy metals, pesticide residues and organic pollution, which usually come from human activities such as industrial emissions, agricultural activities, and urban construction. These pollutants will affect the physical and chemical properties of the water environment, and then affect crop growth, agricultural product safety and the health of the ecosystem. Therefore, water environment quality monitoring has become an important task in the field of environmental protection.

[0003] Traditional water pollution monitoring usually relies on manual sampling and laboratory testing, which is complicated and time-consuming. It is difficult to achieve large-scale, real-time data collection, resulting in insufficient timeliness of data and difficulty in timely reflecting the changes in water pollution and the correlation between water environment. Existing monitoring methods usually only focus on the detection of a single pollutant, lack a comprehensive monitoring mechanism for multiple pollutants, and cannot fully reflect the overall situation of water pollution.

[0004] Therefore, the present invention discloses a regional water environment quality assessment system and method based on artificial intelligence to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a regional water environment quality assessment system and method based on artificial intelligence to solve the problems raised in the prior art.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for evaluating regional water environment quality based on artificial intelligence, the method comprising the following steps: S1: Obtain the location distribution of the river lines in the area to be tested; perform pollution detection on the river in the area to be tested through sensors, generate pollution detection feature information corresponding to each position in the river in the area to be tested, and bind each obtained pollution detection feature information with the corresponding river position in the area to be tested; S2: Calculate the single factor pollution index of each pollutant based on the pollution detection characteristic information; Based on the modified Nemerow index method, combine the maximum and average values ​​of the single factor pollution index to analyze the comprehensive pollution index of each location in the river; S3: A pollution index change model for each location in the river is constructed through the comprehensive pollution index, and the correlation scores between river sections are analyzed using the pollution index change model combined with the location information of the river; S4: According to the pollution index change model of each location in the river, the comprehensive pollution index is predicted; based on the prediction results, the pollution index change value of the river section is analyzed, the river section with correlation is marked, and the river location of the marked river section is sent to the administrator.

[0007] According to the above scheme, in S1, the pollution detection characteristic information includes the detection position of the corresponding river channel, the river channel route to which it belongs, and the pollutant detection data of the corresponding detection position; the pollution detection characteristic information corresponding to the same river channel detection position at different times is different; each river channel is divided into two or more river channel sections of equal length, and each river channel section is numbered, and each river channel section is used as a detection position of the river channel.

[0008] This application divides each river into two or more river sections of equal length. Each river section is used as a detection location for a river. This can effectively divide the river and conduct water environment quality assessment on the river by region. This can effectively analyze the correlation between different regions and provide effective data support for subsequent river management. According to the above scheme, in S2, the single factor pollution index of the i-th pollutant under the j-th standard in the preset environmental element quality standard table is recorded as F ij , the specific calculation formula is: F ij =C i ÷S ij Among them, C i represents the actual measured concentration of the i-th pollutant, S ij is the environmental quality standard value of the i-th pollutant under the j-th standard in the preset environmental element quality standard table; i∈[1,I], j∈[1,J], i and j are both positive integers; I represents the total number of pollutants; J represents the total number of standards in the preset environmental element quality standard table.

[0009] The total number of standards is obtained from the preset environmental element quality standard table. There are multiple standards for water environment quality assessment, and each standard contains different classification rules for water quality levels; According to the above scheme, in S2, the comprehensive pollution index P is analyzed using the modified Nemerow index method. 综 : P 综 =[(F ’ （j，max） 2 +F （j，ave） 2 )÷2] 1 / 2 ; Among them, F （j，ave） It represents the single factor pollution index F under the jth standard ij The arithmetic mean of （j，ave） =(∑I i=1Fij )÷I;F ’ （j，max） It represents the single factor pollution index F under the jth standard ij The maximum value of the correction; F ’ （j，max） =(F （j，max） +F ’ （j，ave） )÷2; Among them, F （j，max） It represents the single factor pollution index F under the jth standard ij The maximum value, F （j，max） =max{F ij |i∈[1,I]}; max{} is the maximum value calculation function; F ’ （j，ave） It represents the single factor pollution index F under the jth standard ij The modified arithmetic mean of F ’ （j，ave） =∑I i=1(F ij ×W ij ); Among them, W ij Represents the single factor pollution index F ij The modified weight value of W ij =R ij ÷(∑I i=1R ij ); R ij Represents the ratio of environmental quality standard value; R ij =S （j，max） ÷S ij ; S （j，max） Represents the maximum value of the environmental quality standard value under the jth standard.

[0010] The analysis of the comprehensive pollution index based on the modified Nemerow index method improves the applicability of the typical Nemerow index method and the accuracy of the evaluation results; it can better fit the situation of complex water environments with multiple pollution factors and improve the accuracy of system analysis; According to the above scheme, in S3, building a pollution index change model includes the following: S301: Mark the river sections whose comprehensive pollution index is greater than a preset threshold, and extract the marked river sections to form an abnormal section set, denoted as AS={AS1, AS2, …, AS p , …, AS P}; where AS p represents the pth river channel section; P represents the total number of river channel sections in the abnormal section set; p∈[1,P], p is a positive integer; Mark the river sections with comprehensive pollution index greater than the preset threshold, extract the marked river sections, and form an abnormal section set; remove the river sections without problems; reduce the amount of data calculated by the system and improve the analysis speed of the system; S302: Combined with the pollution detection cycle, the AS of the river section p The comprehensive pollution index is extracted to form a pollution index cycle set, denoted as PIC p ={(T1,P 综-1 ), (T2, P 综-2 ),…,(T q , P 综-q ),…,(T Q , P 综-Q )}; where T q represents the qth pollution detection cycle, P 综-q represents the comprehensive pollution index corresponding to the qth pollution detection cycle; Q represents the total number of pollution detection cycles; q∈[1,Q], q is a positive integer; construct the river section AS based on the pollution index cycle set p Pollution index change model: y=α1 p ×x+α2 p ; where α1 p and α2 p represents the fitting coefficient, x represents the independent variable of the pollution detection cycle, y represents the dependent variable of the comprehensive pollution index, and the α1 in the pollution index change model is calculated by the least squares method. p and α2 p Perform calculations to solve the problem.

[0011] According to the above scheme, S3 also includes the following contents: analyzing the correlation score WPC between any two river sections in the abnormal section set; WPC=exp[-(α1 p ÷α1 p’ +β×α2 p ÷α2 p’ -1-β)]; where α1 p’ and α2 p’ Indicates the river section AS p’ The fitting coefficient of the pollution index change model, p'∈[1,P], p' is a positive integer, p'≠p; exp[] represents an exponential function with the real number e as the base; β is the correlation coefficient preset by the system; if the correlation score of two river sections is greater than or equal to the correlation score threshold, there is a correlation between the two river sections; if the correlation score of the two river sections is less than the correlation score threshold, there is no correlation between the two river sections.

[0012] Based on the pollution index change model corresponding to different river sections, the correlation between river sections can be analyzed. The river sections with correlation can be found from the comprehensive pollution index change relationship, providing data support for subsequent analysis. According to the above scheme, S4 includes the following contents: S401: predicting the comprehensive pollution index of any two associated river sections based on the pollution index change model, and analyzing the pollution index change value CVPI of the associated river sections based on the predicted comprehensive pollution index; CVPI=exp[(P （Q+1，p） ×P （Q+1，p’） )÷(P （Q，p） ×P （Q，p’） )-1]; Among them, P （Q，p） Indicates the river section AS p The comprehensive pollution index corresponding to the Qth pollution detection cycle; P （Q，p’） Indicates the river section AS p’ The comprehensive pollution index corresponding to the Qth pollution detection cycle; P （Q+1，p） Indicates the river section AS p The predicted comprehensive pollution index of the next pollution detection cycle; P （Q+1，p’） Indicates the river section AS p’ The predicted comprehensive pollution index for the next pollution detection cycle; S402: Setting a pollution index change value threshold, if the pollution index change value is greater than the set threshold, marking the corresponding two associated river sections; sending the river channel locations of all marked associated river sections to the administrator.

[0013] When the change value of the pollution index of an associated river section is greater than the threshold, it means that the water environment quality of the associated river section is rapidly declining, and management personnel are required to carry out emergency management of the water environment of the associated river section. The analysis method of this application can realize the automation of water environment quality assessment and early warning based on the dynamic prediction and analysis of the comprehensive pollution index.

[0014] Another aspect of the present application provides a regional water environment quality assessment system based on artificial intelligence, which is applied to the above-mentioned regional water environment quality assessment method based on artificial intelligence, and the system includes a pollution data acquisition module, a river pollution assessment module, a river pollution correlation analysis module and an index change abnormality analysis module; The pollution data acquisition module is used to obtain the location distribution of the river route in the area to be tested; perform pollution detection on the river in the area to be tested through sensors, generate pollution detection feature information corresponding to each position in the river in the area to be tested, and bind each pollution detection feature information obtained with the corresponding river position in the area to be tested; The river pollution assessment module is used to calculate the single factor pollution index of each pollutant based on the pollution detection feature information; based on the modified Nemerow index method, combined with the maximum and average values ​​of the single factor pollution index, analyze the comprehensive pollution index of each location in the river; The river pollution correlation analysis module is used to construct a pollution index change model for each location in the river through a comprehensive pollution index, and analyze the correlation scores between river sections using the pollution index change model combined with the location information of the river; The index change anomaly analysis module is used to predict the comprehensive pollution index according to the pollution index change model at each location in the river; analyze the pollution index change value of the river section based on the prediction result, mark the river section with correlation, and send the river location of the marked river section to the administrator.

[0015] The pollution data collection module includes a river channel splitting unit and a detection data collection unit; The river channel splitting unit is used to divide each river channel into two or more river channel sections of equal length, and number each river channel section, each river channel section being a detection position of a river channel; The detection data acquisition unit is used to perform pollution detection on the river channel in the test area through a sensor, generate pollution detection feature information corresponding to each position in the river channel in the test area, and bind each pollution detection feature information obtained with the corresponding river channel position in the test area; the pollution detection feature information includes the detection position of the corresponding river channel, the river channel route to which it belongs, and the pollutant detection data of the corresponding detection position; The river pollution assessment module includes a single factor pollution index analysis unit and a comprehensive pollution index analysis unit; The single factor pollution index analysis unit calculates the single factor pollution index of each pollutant based on the pollution detection feature information; The comprehensive pollution index analysis unit is used to calculate the comprehensive pollution index based on the modified Nemerow index method; The river pollution correlation analysis module includes a pollution index change model construction unit and a river section pollution correlation unit; The pollution index change model construction unit is used to mark the river sections whose comprehensive pollution index is greater than a preset threshold, and extract the marked river sections to form an abnormal section set; extract the comprehensive pollution index of the river sections in combination with the pollution detection cycle to form a pollution index cycle set; and construct a pollution index change model based on the pollution index cycle set; The river section pollution association unit is used to analyze the association score between any two river sections in the abnormal section set based on the pollution index change model; The index change abnormality analysis module includes a pollution index change value analysis unit and a marking reminder unit; The pollution index change value analysis unit is used to predict the comprehensive pollution index of any two associated river sections based on the pollution index change model, and analyze the pollution index change value of the associated river sections based on the predicted comprehensive pollution index; The marking reminder unit sets a pollution index change value threshold, marks the river channel section corresponding to the pollution index change value greater than the set threshold; and sends the river channel locations of all marked river channel sections with correlation to the administrator.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: the present application divides each river channel into two or more river channel sections of equal length, and each river channel section is used as a detection position of a river channel, which can effectively divide the river channel, and evaluate the water environment quality of the river channel by region, which can effectively analyze the correlation between different regions, and can provide effective data support for subsequent river channel management; the comprehensive pollution index analyzed based on the modified Nemerow index method improves the applicability of the typical Nemerow index method and the accuracy of the evaluation results; it can be more suitable for the situation with multiple pollution factors in complex water environments, and improve the accuracy of system analysis; the river channel sections with a comprehensive pollution index greater than a preset threshold are marked, and the marked river channel sections are evaluated. Extract and form a set of abnormal sections; remove river sections with no problems; reduce the amount of data calculated by the system and improve the analysis speed of the system; analyze the correlation between river sections based on the pollution index change model corresponding to different river sections, and find the associated river sections from the comprehensive pollution index change relationship, providing data support for subsequent analysis; when the pollution index change value of the associated river section is greater than the threshold, it means that the water environment quality of the associated river section is rapidly declining, and management personnel are required to carry out emergency treatment of the water environment of the associated river section. The analysis method of this application can be based on the dynamic prediction and analysis of the comprehensive pollution index, and realize the automation of water environment quality assessment and early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 A schematic diagram of a flow chart of a regional water environment quality assessment method based on artificial intelligence according to the present invention; Figure 2 The present invention is a schematic structural diagram of a regional water environment quality assessment system based on artificial intelligence. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 , the present invention provides a technical solution: a regional water environment quality assessment system and method based on artificial intelligence to solve the problems raised in the prior art.

[0020] To achieve the above object, the present invention provides the following technical solution: a method for evaluating regional water environment quality based on artificial intelligence, the method comprising the following steps: S1: Obtain the location distribution of the river lines in the area to be tested; perform pollution detection on the river in the area to be tested through sensors, generate pollution detection feature information corresponding to each position in the river in the area to be tested, and bind each obtained pollution detection feature information with the corresponding river position in the area to be tested; In S1, the pollution detection characteristic information includes the detection position of the corresponding river channel, the river channel route to which it belongs, and the pollutant detection data of the corresponding detection position; the pollution detection characteristic information corresponding to the same river channel detection position at different times is different; each river channel is divided into two or more river channel sections of equal length, and each river channel section is numbered, and each river channel section is used as a detection position of the river channel.

[0021] S2: Calculate the single factor pollution index of each pollutant based on the pollution detection characteristic information; Based on the modified Nemerow index method, combine the maximum and average values ​​of the single factor pollution index to analyze the comprehensive pollution index of each location in the river; In S2, the single factor pollution index of the i-th pollutant under the j-th standard in the preset environmental element quality standard table is recorded as F ij , the specific calculation formula is: F ij =C i ÷S ijAmong them, C i represents the actual measured concentration of the i-th pollutant, S ij is the environmental quality standard value of the i-th pollutant under the j-th standard in the preset environmental element quality standard table; i∈[1,I], j∈[1,J], i and j are both positive integers; I represents the total number of pollutants; J represents the total number of standards in the preset environmental element quality standard table.

[0022] In S2, the modified Nemerow index method was used to analyze the comprehensive pollution index P 综 : P 综 =[(F ’ （j，max） 2 +F （j，ave） 2 )÷2] 1 / 2 ; Among them, F （j，ave） It represents the single factor pollution index F under the jth standard ij The arithmetic mean of （j，ave） =(∑I i=1F ij )÷I;F ’ （j，max） It represents the single factor pollution index F under the jth standard ij The maximum value of the correction; F ’ （j，max） =(F （j，max） +F ’ （j，ave） )÷2; Among them, F （j，max） It represents the single factor pollution index F under the jth standard ij The maximum value, F （j，max） =max{F ij |i∈[1,I]}; max{} is the maximum value calculation function; F ’ （j，ave） It represents the single factor pollution index F under the jth standard ij The modified arithmetic mean of F ’ （j，ave） =∑I i=1(F ij ×W ij ); Among them, W ij Represents the single factor pollution index F ij The modified weight value of W ij =R ij ÷(∑I i=1R ij ); R ij Represents the ratio of environmental quality standard value; R ij=S （j，max） ÷S ij ; S （j，max） Represents the maximum value of the environmental quality standard value under the jth standard.

[0023] S3: A pollution index change model for each location in the river is constructed through the comprehensive pollution index, and the correlation scores between river sections are analyzed using the pollution index change model combined with the location information of the river; In S3, building a pollution index change model includes the following: S301: Mark the river sections whose comprehensive pollution index is greater than a preset threshold, and extract the marked river sections to form an abnormal section set, denoted as AS={AS1, AS2, …, AS p , …, AS P}; where AS p represents the pth river channel section; P represents the total number of river channel sections in the abnormal section set; p∈[1,P], p is a positive integer; S302: Combined with the pollution detection cycle, the AS of the river section p The comprehensive pollution index is extracted to form a pollution index cycle set, denoted as PIC p ={(T1,P 综-1 ), (T2, P 综-2 ),…,(T q , P 综-q ),…,(T Q , P 综-Q )}; where T q represents the qth pollution detection cycle, P 综-q represents the comprehensive pollution index corresponding to the qth pollution detection cycle; Q represents the total number of pollution detection cycles; q∈[1,Q], q is a positive integer; construct the river section AS based on the pollution index cycle set p Pollution index change model: y=α1 p ×x+α2 p ; where α1 p and α2 p represents the fitting coefficient, x represents the independent variable of the pollution detection cycle, y represents the dependent variable of the comprehensive pollution index, and the α1 in the pollution index change model is calculated by the least squares method. p and α2 p Perform calculations to solve the problem.

[0024] In S3, the following contents are also included: Analyze the correlation score WPC between any two river sections in the abnormal section set; WPC=exp[-(α1 p ÷α1 p’ +β×α2 p ÷α2 p’-1-β)]; where α1 p’ and α2 p’ Indicates the river section AS p’ The fitting coefficient of the pollution index change model, p'∈[1,P], p' is a positive integer, p'≠p; exp[] represents an exponential function with the real number e as the base; β is the correlation coefficient preset by the system; if the correlation score of two river sections is greater than or equal to the correlation score threshold, there is a correlation between the two river sections; if the correlation score of the two river sections is less than the correlation score threshold, there is no correlation between the two river sections.

[0025] S4: According to the pollution index change model of each location in the river, the comprehensive pollution index is predicted; based on the prediction results, the pollution index change value of the river section is analyzed, the river section with correlation is marked, and the river location of the marked river section is sent to the administrator.

[0026] In S4, the following are included: S401: predicting the comprehensive pollution index of any two associated river sections based on the pollution index change model, and analyzing the pollution index change value CVPI of the associated river sections based on the predicted comprehensive pollution index; CVPI=exp[(P （Q+1，p） ×P （Q+1，p’） )÷(P （Q，p） ×P （Q，p’） )-1]; Among them, P （Q，p） Indicates the river section AS p The comprehensive pollution index corresponding to the Qth pollution detection cycle; P （Q，p’） Indicates the river section AS p’ The comprehensive pollution index corresponding to the Qth pollution detection cycle; P （Q+1，p） Indicates the river section AS p The predicted comprehensive pollution index of the next pollution detection cycle; P （Q+1，p’） Indicates the river section AS p’ The predicted comprehensive pollution index for the next pollution detection cycle; Example 1: In this example, there is an associated river channel segment AS p The comprehensive pollution index P corresponding to the Qth pollution detection cycle （Q，p） 2, river section AS p’ The comprehensive pollution index P corresponding to the Qth pollution detection cycle （Q，p’） is 1.8; Based on river section AS p and AS p’ The respective pollution index change models predict P （Q+1，p） =3, P （Q+1，p’）is 2.5; Therefore, CVPI = exp[(3×2.5)÷(2×1.8)-1]≈exp[1.08]≈8.03; S402: Setting a pollution index change value threshold, if the pollution index change value is greater than the set threshold, marking the corresponding two associated river sections; sending the river channel locations of all marked associated river sections to the administrator.

[0027] Embodiment 2: In this embodiment, the abnormal segment set AS={AS1, AS2, AS3, AS4}; The pollution index change threshold is set to 3, where the pollution index change value of river sections AS1 and AS2 is 8, and the pollution index change value of river sections AS2 and AS3 is 5; the pollution index change value of river sections AS1 and AS3 is 2.5; the pollution index change value of river section AS4 and river sections AS1, AS2 and AS3 is 1; Therefore, the river sections AS1, AS2 and AS3 are marked; and the river positions of the river sections AS1, AS2 and AS3 are sent to the administrator.

[0028] See also Figure 2 , the present invention provides a technical solution: a regional water environment quality assessment system based on artificial intelligence, the system includes a pollution data acquisition module, a river pollution assessment module, a river pollution correlation analysis module and an index change abnormality analysis module; The pollution data acquisition module is used to obtain the location distribution of the river lines in the area to be tested; the pollution detection of the river in the area to be tested is carried out by the sensor, the pollution detection feature information corresponding to each position in the river in the area to be tested is generated, and each pollution detection feature information obtained is bound to the corresponding river position in the area to be tested; The river pollution assessment module is used to calculate the single factor pollution index of each pollutant based on the pollution detection feature information; based on the modified Nemerow index method, combined with the maximum and average values ​​of the single factor pollution index, the comprehensive pollution index of each location in the river is analyzed; The river pollution correlation analysis module is used to construct a pollution index change model for each location in the river through the comprehensive pollution index, and use the pollution index change model combined with the location information of the river to analyze the correlation scores between river sections; The index change anomaly analysis module is used to predict the comprehensive pollution index according to the pollution index change model at each location in the river; based on the prediction results, the pollution index change value of the river section is analyzed, the river section with correlation is marked, and the river location of the marked river section is sent to the administrator.

[0029] The pollution data collection module includes a river channel splitting unit and a detection data collection unit; The river channel splitting unit is used to divide each river channel into two or more river channel sections of equal length, and number each river channel section. Each river channel section is used as a detection position of a river channel. The detection data acquisition unit is used to perform pollution detection on the river channel in the test area through the sensor, generate pollution detection feature information corresponding to each position in the river channel in the test area, and bind each pollution detection feature information obtained with the corresponding river channel position in the test area; the pollution detection feature information includes the detection position of the corresponding river channel, the river channel line to which it belongs, and the pollutant detection data of the corresponding detection position; The river pollution assessment module includes a single factor pollution index analysis unit and a comprehensive pollution index analysis unit; The single factor pollution index analysis unit calculates the single factor pollution index of each pollutant based on the pollution detection characteristic information; The comprehensive pollution index analysis unit is used to calculate the comprehensive pollution index based on the modified Nemerow index method; The river pollution correlation analysis module includes a pollution index change model construction unit and a river section pollution correlation unit; The pollution index change model construction unit is used to mark the river sections whose comprehensive pollution index is greater than the preset threshold, and extract the marked river sections to form an abnormal section set; extract the comprehensive pollution index of the river sections in combination with the pollution detection cycle to form a pollution index cycle set; and construct a pollution index change model based on the pollution index cycle set; The river section pollution correlation unit is used to analyze the correlation score between any two river sections in the abnormal section set based on the pollution index change model; The index change abnormality analysis module includes a pollution index change value analysis unit and a marking reminder unit; The pollution index change value analysis unit is used to predict the comprehensive pollution index of any two associated river sections based on the pollution index change model, and analyze the pollution index change value of the associated river sections based on the predicted comprehensive pollution index; The marking reminder unit sets a threshold value for the change in the pollution index, and marks the river sections corresponding to the pollution index change values ​​greater than the set threshold value; and sends the river locations of all marked river sections with correlation to the administrator.

[0030] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0031] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A regional water environment quality assessment method based on artificial intelligence, characterized in that: The method comprises the following steps: S1: Obtain the location distribution of the river lines in the area to be tested; perform pollution detection on the river in the area to be tested through sensors, generate pollution detection feature information corresponding to each position in the river in the area to be tested, and bind each obtained pollution detection feature information with the corresponding river position in the area to be tested; S2: Calculate the single factor pollution index of each pollutant based on the pollution detection characteristic information; Based on the modified Nemerow index method, combine the maximum and average values ​​of the single factor pollution index to analyze the comprehensive pollution index of each location in the river; S3: A pollution index change model for each location in the river is constructed through the comprehensive pollution index, and the correlation scores between river sections are analyzed using the pollution index change model combined with the location information of the river; S4: According to the pollution index change model of each location in the river, the comprehensive pollution index is predicted; based on the prediction results, the pollution index change value of the river section is analyzed, the river section with correlation is marked, and the river location of the marked river section is sent to the administrator.

2. The method for assessing regional water environment quality based on artificial intelligence according to claim 1, characterized in that: In S1, the pollution detection characteristic information includes the detection position of the corresponding river channel, the river channel route to which it belongs, and the pollutant detection data of the corresponding detection position; each river channel is divided into two or more river channel sections of equal length, and each river channel section is numbered, and each river channel section is used as a detection position of the river channel.

3. The method for regional water environment quality assessment based on artificial intelligence according to claim 2 is characterized in that: In S2, the single factor pollution index of the i-th pollutant under the j-th standard in the preset environmental element quality standard table is recorded as F ij , the specific calculation formula is: F ij =C i ÷S ij ; Among them, C i represents the actual measured concentration of the i-th pollutant, S ij is the environmental quality standard value of the i-th pollutant under the j-th standard in the preset environmental element quality standard table; i∈[1,I], j∈[1,J], i and j are both positive integers; I represents the total number of pollutants; J represents the total number of standards in the preset environmental element quality standard table.

4. The method for regional water environment quality assessment based on artificial intelligence according to claim 3 is characterized by: In S2, the modified Nemerow index method was used to analyze the comprehensive pollution index P 综 : P 综 =[(F ’ （j，max） 2 +F （j，ave） 2 )÷2] 1 / 2 ; Among them, F （j，ave） It represents the single factor pollution index F under the jth standard ij The arithmetic mean of （j，ave） =(∑I i=1F ij )÷I;F ’ （j，max） It represents the single factor pollution index F under the jth standard ij The maximum value of the correction; F ’ （j，max） =(F （j，max） +F ’ （j，ave） )÷2; Among them, F （j，max） It represents the single factor pollution index F under the jth standard ij The maximum value, F （j，max） =max{F ij |i∈[1,I]}; max{} is the maximum value calculation function; F ’ （j，ave） It represents the single factor pollution index F under the jth standard ij The modified arithmetic mean of F ’ （j，ave） =∑I i=1(F ij ×W ij ); Among them, W ij Represents the single factor pollution index F ij The modified weight value of W ij =R ij ÷(∑I i=1R ij ); R ij Represents the ratio of environmental quality standard value; R ij =S （j，max） ÷S ij ; S （j，max） Represents the maximum value of the environmental quality standard value under the jth standard.

5. The method for regional water environment quality assessment based on artificial intelligence according to claim 4 is characterized in that: In S3, building a pollution index change model includes the following: S301: Mark the river sections whose comprehensive pollution index is greater than a preset threshold, and extract the marked river sections to form an abnormal section set, denoted as AS={AS1, AS2, …, AS p , …, AS P }; where AS p represents the pth river channel section; P represents the total number of river channel sections in the abnormal section set; p∈[1,P], p is a positive integer; S302: Combined with the pollution detection cycle, the AS of the river section p The comprehensive pollution index is extracted to form a pollution index cycle set, denoted as PIC p ={(T1,P 综-1 ), (T2, P 综-2 ),…,(T q , P 综-q ),…,(T Q , P 综-Q )}; where T q represents the qth pollution detection cycle, P 综-q represents the comprehensive pollution index corresponding to the qth pollution detection cycle; Q represents the total number of pollution detection cycles; q∈[1,Q], q is a positive integer; construct the river section AS based on the pollution index cycle set p Pollution index change model: y=α1 p ×x+α2 p ; where α1 p and α2 p represents the fitting coefficient, x represents the independent variable of the pollution detection cycle, y represents the dependent variable of the comprehensive pollution index, and the α1 in the pollution index change model is calculated by the least squares method. p and α2 p Perform calculations to solve the problem.

6. The method for regional water environment quality assessment based on artificial intelligence according to claim 5 is characterized in that: In S3, the following are also included: Analyze the correlation score WPC between any two river sections in the abnormal section set; WPC=exp[-(α1 p ÷α1 p’ +β×α2 p ÷α2 p’ -1-β)]; where α1 p’ and α2 p’ Indicates the river section AS p’ The fitting coefficient of the pollution index change model, p'∈[1,P], p' is a positive integer, p'≠p; β is the correlation coefficient preset by the system; if the correlation score of two river sections is greater than or equal to the correlation score threshold, there is a correlation between the two river sections; if the correlation score of the two river sections is less than the correlation score threshold, there is no correlation between the two river sections.

7. The method for regional water environment quality assessment based on artificial intelligence according to claim 5 is characterized in that: In S4, the following are included: S401: predicting the comprehensive pollution index of any two associated river sections based on the pollution index change model, and analyzing the pollution index change value CVPI of the associated river sections based on the predicted comprehensive pollution index; CVPI=exp[(P （Q+1，p） ×P （Q+1，p’） )÷(P （Q，p） ×P （Q，p’） )-1]; Among them, P （Q，p） Indicates the river section AS p The comprehensive pollution index corresponding to the Qth pollution detection cycle; P （Q，p’） Indicates the river section AS p’ The comprehensive pollution index corresponding to the Qth pollution detection cycle; P （Q+1，p） Indicates the river section AS p The predicted comprehensive pollution index of the next pollution detection cycle; P （Q+1，p’） Indicates the river section AS p’ The predicted comprehensive pollution index for the next pollution detection cycle; S402: Setting a pollution index change value threshold, marking the river sections corresponding to the pollution index change value greater than the set threshold; and sending the river locations of all marked river sections with correlation to the administrator.

8. A regional water environment quality assessment system based on artificial intelligence, the system is applied to the regional water environment quality assessment method based on artificial intelligence as described in any one of claims 1 to 7, characterized in that: The system includes a pollution data acquisition module, a river pollution assessment module, a river pollution correlation analysis module and an index change anomaly analysis module; The pollution data acquisition module is used to obtain the location distribution of the river route in the area to be tested; perform pollution detection on the river in the area to be tested through sensors, generate pollution detection feature information corresponding to each position in the river in the area to be tested, and bind each pollution detection feature information obtained with the corresponding river position in the area to be tested; The river pollution assessment module is used to calculate the single factor pollution index of each pollutant based on the pollution detection feature information; based on the modified Nemerow index method, combined with the maximum and average values ​​of the single factor pollution index, analyze the comprehensive pollution index of each location in the river; The river pollution correlation analysis module is used to construct a pollution index change model for each location in the river through a comprehensive pollution index, and analyze the correlation scores between river sections using the pollution index change model combined with the location information of the river; The index change anomaly analysis module is used to predict the comprehensive pollution index according to the pollution index change model at each location in the river; analyze the pollution index change value of the river section based on the prediction result, mark the river section with correlation, and send the river location of the marked river section to the administrator.

Images