Method, device and equipment for identifying abnormal water source of sewer network and storage medium

Abstract

The present application relates to the field of municipal environmental protection, and discloses a method, device and equipment for identifying the source of abnormal water quantity in a drainage pipe network and a storage medium. The method filters a plurality of preselected characteristic factors by using first index sequence data of each characteristic factor corresponding to different types of pipe-in water quantity sources and second index sequence data of each characteristic factor corresponding to a target abnormal water quantity source, filters out characteristic factors that can effectively distinguish between abnormal water quantity sources and normal pipe-in water quantity sources, obtains a target characteristic factor combination, and uses the target characteristic factor combination obtained through the filtering to identify the source of abnormal water quantity in a drainage pipe network area, thereby effectively reducing the detection complexity and high detection cost caused by too many characteristic factors, and providing technical support for low-cost and high-efficiency identification of the source of abnormal water quantity in a drainage pipe network and risk assessment.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of municipal environmental protection, and in particular to a drainage pipe network abnormal water source identification method, device, equipment and storage medium. BACKGROUND

[0002] The drainage pipe network has problems such as mixed connection, inflow and infiltration, industrial wastewater illegal discharge and leakage, which can seriously affect the efficiency of urban sewage collection and treatment. Normalization of abnormal water source identification and risk assessment can help to develop scientific improvement measures.

[0003] In related technologies, the feature factor analysis method can be used to identify different water sources and analyze the contribution rate, so as to identify the abnormal water source in the drainage pipe network. The basic principle is: based on the physical and chemical characteristics of the water body, the source of the water body is identified, and further combined with the mass balance, the contribution proportion of different source water bodies is analyzed. Each source type water body contains at least one corresponding characteristic factor, that is, the number of characteristic factors is related to the number of water body sources. When the number of water body sources is large, the number of characteristic factors will also increase. When using characteristic factors to detect water body sources, the detection cost and diagnosis complexity will be high, which is difficult to meet the needs of efficient, fast and normal application in engineering practice. SUMMARY

[0004] Therefore, the present application provides a drainage pipe network abnormal water source identification method, device, equipment and storage medium to solve the problem that in related technologies, when the number of water body sources is large, the number of characteristic factors will also increase, and using more characteristic factors to detect water body sources will result in high detection cost and diagnosis complexity.

[0005] In a first aspect, the present application provides a drainage pipe network abnormal water source identification method, which comprises: obtaining a plurality of characteristic factors of a drainage pipe network area, a first index sequence data of each characteristic factor corresponding to different types of pipe-in water sources, and a second index sequence data of each characteristic factor corresponding to a target abnormal water source. The characteristic factor is used to represent the characteristic index that can distinguish the pipe-in water source from the target abnormal water source in the drainage pipe network area; using the first index sequence data of each characteristic factor corresponding to different types of pipe-in water sources and the second index sequence data of each characteristic factor corresponding to the target abnormal water source to screen the plurality of characteristic factors, to obtain a target characteristic factor combination; and using the target characteristic factor combination to identify the abnormal water source of the drainage pipe network area.

[0006] The drainage pipe network abnormal water source identification method provided by the application can effectively distinguish the abnormal water source and the normal pipe water source by screening the characteristic factors that can effectively distinguish the abnormal water source and the normal pipe water source, and obtains the target characteristic factor combination, thereby effectively reducing the detection complexity and the high detection cost caused by too many characteristic factors, and providing technical support for low-cost and high-efficiency realization of drainage pipe network abnormal water source identification and risk assessment.

[0007] In an optional implementation, the step of screening a plurality of characteristic factors by using the first index sequence data of each characteristic factor corresponding to different types of pipe water sources and the second index sequence data of each characteristic factor corresponding to the target abnormal water source to obtain a target characteristic factor combination includes: determining at least one target set based on the plurality of characteristic factors, the target set including a preset number of preset characteristic factors, and the preset number being an integer greater than 1; determining a plurality of first data points according to the first index sequence data of each preset characteristic factor corresponding to each type of pipe water source, marking the plurality of first data points in the coordinate system of the corresponding type of pipe water source, screening the plurality of first data points in the coordinate system according to a preset rule, determining a first fingerprint area of the corresponding type of pipe water source according to the screened first data points, and the coordinate system being constructed with the preset characteristic factors in the target set as coordinate axes; determining a plurality of second data points according to the second index sequence data of each preset characteristic factor corresponding to the target abnormal water source, marking the plurality of second data points in the coordinate system of the target abnormal water source, screening the plurality of second data points in the coordinate system according to the preset rule, determining a second fingerprint area of the target abnormal water source according to the screened second data points, and the second fingerprint area including a target center point, the target center point being determined according to the mean value of different data in the second index sequence data of each preset characteristic factor corresponding to the target abnormal water source; determining a plurality of mixed points based on the first fingerprint area of each type of pipe water source and the second fingerprint area of the target abnormal water source; one mixed point is obtained by extracting one first target data point in each first fingerprint area according to a preset rule and processing a plurality of first target data points; marking the plurality of mixed points in a target coordinate system to obtain a first mixed area, mixing the plurality of mixed points with the target center point according to a first preset proportion to obtain a plurality of third data points, and marking the plurality of third data points in the target coordinate system to obtain a second mixed area; if the first mixed area and the second mixed area do not overlap, regarding the plurality of preset characteristic factors in the target set as the target characteristic factor combination.

[0008] The method provided by the optional embodiment realizes dimension reduction of the identification system of the multi-source water body, and reduces the difficulty of subsequent identification of the abnormal water source.

[0009] In an optional embodiment, the step of identifying the abnormal water source of the drainage pipe network area by using the target characteristic factor combination includes: obtaining first sampling data in the drainage pipe network partition; determining index data of each target characteristic factor in the target characteristic factor combination based on the first sampling data; determining a target point according to the index data of each target characteristic factor, and labeling the target point into a target coordinate system of a target set corresponding to the target characteristic factor combination; and determining that the drainage pipe network area has the abnormal water source if the target point in the target coordinate system is located outside the first mixed area.

[0010] The method provided by the optional embodiment significantly distinguishes the abnormal type water volume and other type water volumes through the low-dimensional characteristic factor combination system composed of the target characteristic factor combination based on the "clustering" and "isolation" ideas, proposes a new identification idea, optimizes the accuracy and logic of the characteristic factor method, reduces the identification difficulty, significantly reduces the diagnosis cost, and improves the work efficiency.

[0011] In an optional embodiment, the step of screening a plurality of characteristic factors by using the first index sequence data of each characteristic factor corresponding to different types of pipe-connected water sources and the second index sequence data of each characteristic factor corresponding to the target abnormal water source to obtain the target characteristic factor combination further includes: mixing a plurality of mixed points and a target center point of each target set according to different second preset proportions to obtain a plurality of fourth data points respectively corresponding to different second preset proportions, labeling the plurality of fourth data points under each second preset proportion into the target coordinate system, and determining a third mixed area corresponding to each second preset proportion under different second preset proportions according to the plurality of fourth data points of each second preset proportion in the target coordinate system.

[0012] In an optional embodiment, the step of identifying the abnormal water source of the drainage pipe network area by using the target characteristic factor combination further includes: when the drainage pipe network area has the abnormal water source, determining relative position information of the target point and each mixed area in the target coordinate system; and evaluating the severity of the abnormal water infiltration in the drainage pipe network area based on the relative position information of the target point and each mixed area.

[0013] In an optional embodiment, the plurality of characteristic factors of the drainage pipe network area are obtained by the following steps: obtaining a plurality of initial characteristic factors corresponding to different types of water sources and detection data of each initial characteristic factor; calculating a variation coefficient of the corresponding initial characteristic factor by using the detection data of each initial characteristic factor; and removing an initial characteristic factor with a variation coefficient greater than a preset threshold from the plurality of initial characteristic factors of each type of water source to obtain at least one characteristic factor corresponding to the type of water source.

[0014] In a second aspect, the present application provides a device for identifying an abnormal water source in a sewer network, comprising: an acquisition module configured to acquire a plurality of characteristic factors of a sewer network area, a first index sequence data of each characteristic factor corresponding to different types of water sources, and a second index sequence data of each characteristic factor corresponding to a target abnormal water source, wherein the characteristic factors are used to represent characteristic indexes capable of distinguishing the water sources and the target abnormal water source in the sewer network area; a screening module configured to screen the plurality of characteristic factors by using the first index sequence data of each characteristic factor corresponding to different types of water sources and the second index sequence data of each characteristic factor corresponding to the target abnormal water source, to obtain a target characteristic factor combination; and an identification module configured to identify the abnormal water source in the sewer network area by using the target characteristic factor combination.

[0015] In a third aspect, the present application provides a computer device, comprising: a memory and a processor, which are communicatively connected to each other, and the memory stores computer instructions, and the processor executes the computer instructions to perform the method for identifying an abnormal water source in a sewer network according to the first aspect or any one of the corresponding embodiments thereof.

[0016] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the method for identifying an abnormal water source in a sewer network according to the first aspect or any one of the corresponding embodiments thereof.

[0017] In a fifth aspect, the present application provides a computer program product, which comprises computer instructions, and the computer instructions are used to make a computer execute the method for identifying an abnormal water source in a sewer network according to the first aspect or any one of the corresponding embodiments thereof. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the drawings needed in the description of the specific embodiments or the prior art will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0019] Figure 1 is a flowchart of a method for identifying an abnormal water source in a sewer network according to an embodiment of the present application;

[0020] Figure 2 is a flowchart of another method for identifying an abnormal water source in a sewer network according to an embodiment of the present application;

[0021] Figure 3is a schematic diagram of different mixing areas when different preset characteristic indexes of the target set are hardness and ammonia nitrogen in the embodiment of the application;

[0022] Figure 4 is a schematic diagram of different mixing areas when different preset characteristic indexes of the target set are hardness and potassium ions in the embodiment of the application;

[0023] Figure 5 is a flowchart of another method for identifying an abnormal water source of a drainage pipe network according to an embodiment of the application;

[0024] Figure 6 is a schematic diagram of the relative positions of the identification point and the convex hulls of the corresponding areas of the mixing areas in the target coordinate system in the embodiment of the application;

[0025] Figure 7 is a structural block diagram of a device for identifying an abnormal water source of a drainage pipe network according to an embodiment of the application;

[0026] Figure 8 is a schematic diagram of the hardware structure of a computer device according to an embodiment of the application. DETAILED DESCRIPTION

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the application clearer, the technical solutions in the embodiments of the application will be described below in connection with the drawings in the embodiments of the application. Obviously, the described embodiments are some but not all of the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the application.

[0028] In related technologies, the identification of different water sources and the analysis of contribution rates can be realized by a characteristic factor analysis method, so as to identify an abnormal water source of a drainage pipe network. The basic principle is as follows: the sources of water bodies are identified based on the physical and chemical characteristic factors of the water bodies, and further combined with mass balance, the contribution proportions of different source water bodies are analyzed. Each source type water body contains at least one corresponding characteristic factor, that is, the number of characteristic factors is related to the number of water body sources. When the number of water body sources is large, the number of characteristic factors will also increase. When the characteristic factors are used for water body source detection, the detection cost and diagnosis complexity are high, and it is difficult to meet the needs of efficient, fast, and normalized application in engineering practice.

[0029] Therefore, the drainage pipe network abnormal water source identification method provided by the embodiments of the present application can be applied to a server to realize identification of the drainage pipe network abnormal water source. The method provided by the embodiments of the present application can filter a plurality of characteristic factors by using the first index sequence data of each characteristic factor corresponding to different types of pipe-accepted water sources and the second index sequence data of each characteristic factor corresponding to a target abnormal water source, filter out the characteristic factors that can effectively distinguish the abnormal water source and the normal pipe-accepted water source, obtain a target characteristic factor combination, and use the target characteristic factor combination obtained by filtering to identify the abnormal water source of the drainage pipe network area, thereby effectively reducing the problems of high detection complexity and high detection cost caused by too many characteristic factors, and providing technical support for low-cost and high-efficiency realization of identification and risk assessment of the drainage pipe network abnormal water source.

[0030] According to the embodiments of the present application, a drainage pipe network abnormal water source identification method is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] In the present embodiment, a drainage pipe network abnormal water source identification method is provided, which can be used in the server described above, Figure 1 The flowchart of the drainage pipe network abnormal water source identification method according to the embodiments of the present application is shown in FIG. 1, which includes the following steps: Figure 1

[0032] In step S101, a plurality of characteristic factors of a drainage pipe network area, first index sequence data of each characteristic factor corresponding to different types of pipe-accepted water sources, and second index sequence data of each characteristic factor corresponding to a target abnormal water source are obtained. The characteristic factors are used to represent characteristic indexes that can distinguish pipe-accepted water sources from the target abnormal water source in the drainage pipe network area.

[0033] ​Exemplarily, the drainage pipe network is an important part of urban infrastructure, mainly used for collecting, transporting and discharging domestic sewage, industrial wastewater and rainwater, and is crucial for urban flood control, environmental protection and residents' quality of life. The drainage pipe network area refers to any area in the drainage pipe network that needs to identify abnormal water sources. Different types of water sources in the drainage pipe network area refer to normal pipe-accepted water source types and target abnormal inflow in the drainage pipe network area. The former can include but is not limited to various types of domestic sewage, treated industrial wastewater, and the latter can include but is not limited to inflow and infiltration of groundwater, rainwater, river (lake) water, and untreated industrial wastewater. In the embodiments of the present application, by carrying out drainage household data collection, pipe network survey data analysis, field investigation and other work, according to the known drainage pipe network data (CAD pipeline map, planning map, etc.), the topological structure is analyzed, and the normal pipe-accepted water source types (various types of domestic sewage, treated industrial wastewater) and potential abnormal input water source types (including inflow and infiltration of groundwater, rainwater, river (lake) water, and untreated industrial wastewater) in the drainage pipe network area are sorted out. Combined with literature reports, research basis and monitoring data in the past area and similar areas, 1-3 characteristic indexes that can represent the characteristics of each water source are preliminarily screened, such as TN, Cl - , LAS can be selected as the characteristic index of domestic sewage (subdivided according to specific domestic sewage), hardness, Mn + can be selected as the characteristic index of groundwater, chlorophyll a as the characteristic index of river water, and Na + , K + , F - , Cl - , SO4 - and other related process-related metal ions and salt ions can be selected as the characteristic index of industrial wastewater. In addition, the hydrogen and oxygen stable isotope combination system (δ 2 H-δ 18O) There are significant differences between sewage, groundwater, mountain water and river water, so it is also an important characteristic index for identifying different types of water sources. In the preliminary screening of characteristic indexes, combined with the preliminary judgment of the potential target abnormal water source to be identified and the main pipe network water body, for example, when identifying groundwater intrusion, the target abnormal water source is groundwater, and the main pipe network water body is the water produced by the life and industrial drainage households that meets the pipe network requirements; when identifying industrial wastewater discharge, the target abnormal water source is specific industrial wastewater, and the pipe network water body is domestic wastewater and other types of non-key industrial wastewater, then select the typical characteristic index of each type of water source as the characteristic index of the corresponding water source. According to the characteristic indexes of each type of pipe network water source and the characteristic indexes of the target abnormal water source, analyze the characteristic indexes that can distinguish between normal pipe network water sources and target abnormal water sources, and select the characteristic indexes that can distinguish between pipe network water sources and target abnormal water sources as characteristic factors. The characteristic factors can be selected according to the actual situation, for example, when identifying groundwater intrusion, the A and B indexes of groundwater are both high, or the A index of groundwater is high and the B index of the other three types of pipe network water bodies is high, which can be used as characteristic factors.

[0034] Step S102, the first index sequence data of each characteristic factor corresponding to different types of pipe network water sources and the second index sequence data of each characteristic factor corresponding to the target abnormal water source are screened for multiple characteristic factors to obtain a target characteristic factor combination.

[0035] Exemplarily, the first index sequence data of each characteristic factor corresponding to different types of pipe network water sources and the second index sequence data of each characteristic factor corresponding to the target abnormal water source are screened for multiple characteristic factors to screen out the characteristic factors that can effectively distinguish between abnormal water sources and main pipe network water bodies, and obtain a target characteristic factor combination.

[0036] Step S103, using the target characteristic factor combination to identify the abnormal water source of the drainage pipe network area.

[0037] Exemplarily, in the embodiments of the present application, the abnormal water source of the drainage pipe network area is identified according to the target characteristic factor combination, and the specific identification method is not limited in the embodiments of the present application, which can be determined by the person skilled in the art according to the needs.

[0038] The drainage pipe network abnormal water source identification method provided in the embodiment can effectively reduce the detection complexity and detection cost caused by too many characteristic factors, and provides technical support for low-cost and high-efficiency realization of drainage pipe network abnormal water source identification and risk assessment.

[0039] In the embodiment, a drainage pipe network abnormal water source identification method is provided, which can be used for the server described above, Figure 2 is a flowchart of the drainage pipe network abnormal water source identification method according to the embodiment of the present application, as shown in the figure, the flowchart comprises the following steps: Figure 2

[0040] In step S201, a plurality of characteristic factors of a drainage pipe network area, first index sequence data of each characteristic factor corresponding to different types of pipe-integrated water sources, and second index sequence data of each characteristic factor corresponding to a target abnormal water source are obtained. The characteristic factors are used to represent characteristic indexes that can distinguish between pipe-integrated water sources and target abnormal water sources in the drainage pipe network area. For details, refer to step S101 of the embodiment shown in Figure 1

[0041] In some optional embodiments, the plurality of characteristic factors of the drainage pipe network area are obtained by the following steps:

[0042] In step a1, a plurality of initial characteristic factors corresponding to different types of water sources and detection data of each initial characteristic factor are obtained.

[0043] For example, in the embodiment of the present application, the initial characteristic factors refer to a plurality of characteristic factors determined by human experience.

[0044] In step a2, the detection data of each initial characteristic factor is used to calculate the coefficient of variation of the corresponding initial characteristic factor.

[0045] ​​Exemplarily, in the embodiments of the present application, the collection of various types of water sources and the detection of corresponding characteristic factors in the service area, and the calculation of the average value and standard deviation of the detection values of the characteristic factors are carried out. In the process of collecting samples of various types of water sources, when the water source is a drainage user, the collection time of the water source sample is required to be not less than the complete production and life cycle of the drainage user, and the sampling frequency is not less than 4 hours / time, wherein the industrial drainage user should detect the water quality before and after treatment respectively; when the water source is groundwater, river (lake) water, and tap water, the collection time of the water body sample is required to be not less than 24 hours, and the sampling frequency is not less than 4 hours / time; when the water source is rainwater, the sampling activity is required to cover the early, middle and late stages of rainfall. After detection, the data should be preprocessed and corrected, including abnormal data rejection, stability evaluation of each index by using the coefficient of variation (CV), when it is a drainage user type water body, the one with larger coefficient of variation (more than 100%) in the production cycle should be subdivided according to the working time and idle time. The coefficient of variation is calculated by the following formula:

[0046] 00%

[0047] wherein, represents the coefficient of variation, is the standard deviation of the detection data sample, is the average value of the detection data sample.

[0048] Specifically, in the embodiments of the present application, when the target abnormal water source is groundwater, hardness can be selected as a representative index of groundwater, as a representative recommended factor of water body, TN and NH3-N can be selected as characteristic indexes of domestic wastewater and agricultural market wastewater, and Na + and Cl - can be selected as characteristic indexes of hospital medical wastewater, in combination with literature reports, research basis and monitoring data in the past area and similar regions.

[0049] The detection of characteristic factors of domestic wastewater, agricultural market wastewater, hospital medical wastewater and groundwater in the service area is carried out, and the sampling period, frequency and quantity are shown in Table 1.

[0050] Table 1

[0051]

[0052] After detection, the data should be preprocessed and corrected, including calculation of the average value and standard deviation of the extracted characteristic factor detection values, abnormal data rejection, and stability evaluation of each index by using the coefficient of variation (CV), and the data results are shown in Table 2.

[0053] Table 2

[0054]

[0055] Step a3, removing the initial characteristic factor with a coefficient of variation greater than a preset threshold from the plurality of initial characteristic factors of the water source of each type, to obtain at least one characteristic factor corresponding to the water source of each type.

[0056] Exemplarily, the initial characteristic factor with a coefficient of variation greater than a preset threshold is removed. The greater the coefficient of variation, the poorer the stability of the initial characteristic factor. The specific content of the preset threshold is not limited in the embodiment of the application, and can be determined by the person skilled in the art according to the needs.

[0057] Step S202, filtering a plurality of characteristic factors by using the first index sequence data of each characteristic factor corresponding to the different types of water source respectively, and the second index sequence data of each characteristic factor corresponding to the target abnormal water source, to obtain a target characteristic factor combination.

[0058] Specifically, the above step S202 includes:

[0059] Step S2021, determining at least one target set based on the plurality of characteristic factors, the target set including a preset number of preset characteristic factors, and the preset number being an integer greater than 1.

[0060] Exemplarily, the preset number can include but is not limited to 2, and the target set includes the preset number of characteristic factors. In the embodiment of the application, the target abnormal water source to be identified is groundwater, and the main water bodies to be managed are domestic community wastewater, agricultural market wastewater and hospital medical wastewater. The typical index of groundwater is hardness, and the common characteristic indexes of the other three main water bodies to be managed include Cl - , NH3-N, TN, K + , and Na + . The coefficient of variation of Cl - and Na + in the agricultural market water body is too large, indicating poor stability. Therefore, NH3-N, TN and K + are selected as the characteristic factors, and the three characteristic factors are combined two by two, a total of three combinations, and two characteristic factors in each combination are used as elements to obtain the corresponding target set.

[0061] Step S2022, determining a plurality of first data points according to the first index sequence data of each preset characteristic factor corresponding to each type of water source to be managed, labeling the plurality of first data points to the coordinate system corresponding to the type of water source to be managed, filtering the plurality of first data points in the coordinate system according to a preset rule, determining a first fingerprint area of the type of water source to be managed according to the filtered first data points, and the coordinate system is constructed by taking each preset characteristic factor in the target set as a coordinate axis.

[0062] Exemplarily, a plurality of first data points are determined according to the first index sequence data of each preset characteristic factor in the target set corresponding to each type of water source under control, for example, the target set includes preset characteristic factor 1 and preset characteristic factor 2, the sequence data of the preset characteristic factor 1 is x, y, and z, and the sequence data of the preset characteristic factor 2 is 1, 2, and 3, then the coordinates of the plurality of first data points determined are (x, 1), (y, 2), and (z, 3), and the plurality of first data points in the coordinate system are screened according to a preset rule, the preset rule can include but is not limited to determining the coordinates of the center point as the mean value of different data in the first index sequence data, and the 2 standard deviations of different data in the first index sequence data as the boundary, and the first data points located between the center point and the boundary are screened out to obtain the first fingerprint region of the type of water source under control. The characteristic fingerprint region of each type of water source takes the mean value of each type of water body characteristic as the center point coordinate, and the 2 standard deviations as the distance from the center point to the boundary. The fingerprint region represents the fluctuation range of the characteristic index of the type of water source in the statistical sense. This means that most (about 95%) of the sample characteristic values will fall within this range, reflecting the concentration trend and dispersion degree of the characteristic index of the type of water source.

[0063] In step S2023, a plurality of second data points are determined according to the second index sequence data of each preset characteristic factor corresponding to the target abnormal water source, the plurality of second data points are labeled into the coordinate system of the target abnormal water source, the plurality of second data points in the coordinate system are screened according to a preset rule, and a second fingerprint region of the target abnormal water source is determined according to the screened second data points. The second fingerprint region includes a target center point, and the target center point is determined according to the mean value of different data in the second index sequence data of each preset characteristic factor corresponding to the target abnormal water source.

[0064] Exemplarily, the construction process of the second fingerprint region is similar to that of the first fingerprint region, which will not be described here. In the embodiment of the application, the target abnormal water source can include a plurality of types of abnormal water sources, a plurality of second data points are determined according to the proportion and index sequence data of each type of abnormal water source, and a second fingerprint region is constructed according to the plurality of second data points.

[0065] In step S2024, a plurality of mixed points are determined based on the first fingerprint region of each type of water source under control and the second fingerprint region of the target abnormal water source. One mixed point is obtained by extracting one first target data point in each first fingerprint region according to a preset rule, and the plurality of first target data points are processed.

[0066] Exemplarily, the preset rule can include but is not limited to randomly extracting data points from the fingerprint area in a uniform sampling manner. In the embodiment of the present application, one point is randomly taken from the fingerprint area of each type of metered water source (metered water body) by using the uniform sampling method, and a metered water body mixing point representing the metered water body is generated according to a random ratio. The mixing point can be determined by the following formula:

[0067]

[0068]

[0069]

[0070] wherein, , respectively represent the horizontal and vertical coordinates of the metered water body mixing point, i.e., the concentration of the corresponding characteristic factor; , respectively represent the horizontal and vertical coordinates of the randomly extracted i-th type of metered water body point, i.e., the concentration of the corresponding characteristic factor; represents the proportion of the i-th metered water body when the metered water body mixing point is composed, and the proportion is generated by a random function.

[0071] In step S2025, the plurality of mixing points are labeled into the target coordinate system to obtain a first mixing area. The plurality of mixing points and the target center point are mixed according to a first preset ratio to obtain a plurality of third data points. The plurality of third data points are labeled into the target coordinate system to obtain a second mixing area.

[0072] Exemplarily, the target coordinate system is also constructed with each preset characteristic factor in the target set as a coordinate axis. The plurality of mixing points are labeled into the target coordinate system to obtain a first mixing area, which forms a clustering convex hull of the metered water body when there is no external water intrusion in the target coordinate system. The first mixing area is used for the fluctuation range of the index value corresponding to the preset characteristic factor when the drainage pipe network is partitioned without external water intrusion. The first preset ratio can be determined based on the identification accuracy of the target abnormal water source. In the embodiment of the present application, the first preset ratio can include but is not limited to 10%. The mixing points are weighted by 10%, and the metered water body mixing points and the fingerprint area center point of the target abnormal water source are mixed according to the ratio to generate all possible mixing points. The sampling and mixing point generation process is repeated 10000 times. The target center point is weighted by 90%, and the coordinate values of each mixing point and the target center point are linearly weighted to obtain the corresponding third data points. The plurality of third data points are labeled into the target coordinate system to obtain a second mixing area, which forms a region convex hull corresponding to the first preset ratio (external water ratio 10%) in the target coordinate system.

[0073] Step S2026, if the first mixing area and the second mixing area do not coincide, a plurality of preset characteristic factors in the target set are taken as the target characteristic factor combination.

[0074] Exemplarily, if the first mixing area and the second mixing area coincide, it indicates that the combination of different preset factors in the target set can realize the identification of the abnormal water source when the first preset proportion of the target abnormal water source is invaded by external water, the index system has a higher sensitivity to the mixing of the abnormal water and other pipe-in water bodies, and can cluster the other pipe-in water bodies and the non-key attention water source into a whole through the two indexes, isolate the abnormal water as another type, simplify the actual multi-water source problem into a two-source problem, and effectively distinguish the abnormal water source; otherwise, it indicates that the index system cannot effectively cluster the pipe-in water bodies and distinguish the abnormal water, and needs to replace the indexes and repeat the above screening steps.

[0075] Step S2027, mixing the plurality of mixing points and the target center point of each target set according to different second preset proportions to obtain a plurality of fourth data points respectively corresponding to different second preset proportions, marking the plurality of fourth data points under each second preset proportion to the target coordinate system, and determining the third mixing area respectively corresponding to different second preset proportions according to the plurality of fourth data points under each second preset proportion in the target coordinate system.

[0076] Exemplarily, in the embodiment of the present application, the different second preset proportions can be 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, etc., and the proportions can be adjusted according to actual needs. Marking the plurality of fourth data points obtained under each preset proportion to the target coordinate system to obtain the third mixing area under the corresponding preset proportion. When the different preset characteristic indexes in the target set are hardness and ammonia nitrogen, the schematic diagram of different mixing areas is as shown in FIG. 6, wherein the purple square represents groundwater, the green square represents a residential area, the red square represents a farmers' market, the blue square represents a hospital, the polygon of the yellow and purple mixed area represents a pipe-in water body clustering convex hull, and the remaining polygons represent a pipe-in water body and external water mixing convex hull. Figure 3 When the different preset characteristic indexes in the target set are hardness and potassium ion, the schematic diagram of different mixing areas is as shown in FIG. 7, wherein the purple square represents groundwater, the green square represents a residential area, the red square represents a farmers' market, the blue square represents a hospital, the polygon of the yellow and purple mixed area represents a pipe-in water body clustering convex hull, and the remaining polygons represent a pipe-in water body and external water mixing convex hull. Figure 4

[0077] Step S203, identifying the abnormal water source of the drainage pipe network area by using the target characteristic factor combination. For details, please refer to step S103 of the embodiment shown in FIG. 5, which will not be repeated here. Figure 1

[0078] ​​The embodiment provides a sewer network abnormal water source identification method, which can be used for the server, Figure 5 is a flowchart of the sewer network abnormal water source identification method according to the embodiment of the application, as shown in the figure, the flowchart comprises the following steps: Figure 5

[0079] In step S501, at least one characteristic factor corresponding to different types of water sources in a sewer network area, first index sequence data of each characteristic factor and second index sequence data are obtained, the first index sequence data is used to represent index sequence values of the corresponding characteristic factor in the sewer network area when there is no target abnormal water intrusion, and the second index sequence data is used to represent index sequence values of the corresponding characteristic factor in the sewer network area when there is target abnormal water intrusion.

[0080] In step S502, the first index sequence data and the second index sequence data of each characteristic factor are used to screen at least one characteristic factor corresponding to different types of water sources, to obtain a target characteristic factor combination. For details, refer to step S202 of the embodiment shown in Figure 2 , which will not be repeated here.

[0081] In step S503, the target characteristic factor combination is used to identify the abnormal water source in the sewer network area.

[0082] Specifically, the above step S503 comprises:

[0083] In step S5031, first sampling data in the sewer network partition is obtained.

[0084] Exemplarily, the first sampling data can be analysis data obtained by analyzing water samples collected from any node in the sewer network partition.

[0085] In step S5032, index data of each target characteristic factor in the target characteristic factor combination is determined based on the first sampling data.

[0086] Exemplarily, the first sampling data contains index values of each target characteristic factor, and the index values are taken as the index data.

[0087] In step S5033, a target point is determined according to the index data of each target characteristic factor, and the target point is marked in a target coordinate system of a target set corresponding to the target characteristic factor combination.

[0088] In step S5034, if the target point in the target coordinate system is located outside the first mixed area, it is determined that the sewer network area has an abnormal water source. Exemplarily, when the target point in the target coordinate system is located in the first mixed area, it indicates that the partition has no target abnormal water source intrusion, otherwise, the sewer network area has an abnormal water source. ​

[0089] In some optional embodiments, the step S503 further comprises:

[0090] Step S5035, when the drainage pipe network area has an abnormal water source, determining the relative position information of the target point and each mixed area in the target coordinate system.

[0091] Step S5036, evaluating the severity of the abnormal water infiltration in the drainage pipe network area based on the relative position information of the target point and each mixed area.

[0092] Exemplarily, the screened feature factor combination system and the external water source to be identified in the actual subdivided area are sampled and detected with respect to the feature factor, the sampling duration and frequency of the sample of the key node of the drainage pipe network are determined according to actual needs, the total sampling of a single node should be not less than 5 times, the mean value and standard deviation are calculated by data processing. The water quality data of the node and each mixed area of the target coordinate system are identified and compared, the abnormal water source and the water volume proportion range can be judged according to the spatial position of the identification point. And the risk of external water invasion in different pipe sections is evaluated. In the embodiment of the application, the screened hardness, ammonia nitrogen and K + can be used as feature indicators of water source fingerprint identification of underground water, therefore, hardness, K + are selected as detection indicators, detection is carried out on important pipe network nodes in each area, the total sampling of a single node should be not less than 5 times, the mean value and standard deviation are calculated by data processing, and the sampling point data are shown in Table 3.

[0093] Table 3

[0094]

[0095] The obtained data are respectively used as the horizontal and vertical coordinates of the target point to draw the identification point in the graph of the target coordinate system for identification and comparison, wherein the schematic diagram of the relative position of the identification point in the target coordinate system and the corresponding area convex hull of each mixed area is shown in Figure 6 , wherein the purple square represents underground water, the green square represents a residential area, the red square represents a farmers market, the blue square represents a hospital, and the polygon of the mixed area of yellow and purple represents the pipe-in water body clustering convex hull, and the remaining polygons represent the pipe-in water body and external water mixed convex hull. According to the spatial position of the identification point in the coordinate system, it can be judged that the underground water proportion of identification point 1 is about 10% to 20%, the underground water proportion of identification point 2 is about 60%, and the underground water proportion of identification point 3 is about 40%, which indicates that there is damage and infiltration along the pipe section and the underground water infiltration in this area is serious.

[0096] The method provided in the embodiment distinguishes the abnormal type water quantity from other type water quantities through a two-dimensional characteristic factor combination system based on the "clustering" and "isolation" ideas, thereby simplifying the multi-source type water quantity identification problem into a two-source identification problem, proposing a new identification idea, optimizing the accuracy and logicality of the characteristic factor method, reducing the identification difficulty, significantly reducing the diagnosis cost, and improving the work efficiency; since the method has high identification sensitivity for the abnormal water quantity source, and only binary indexes are used in the process, a localization characteristic database can be established, and it is expected that the abnormal problems can be normalized and real-time warned through online monitoring.

[0097] In the embodiment, a drainage pipe network abnormal water quantity source identification device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and is conceived.

[0098] The embodiment provides a drainage pipe network abnormal water quantity source identification device, as shown in Figure 7 , comprising:

[0099] The acquisition module 701 is configured to acquire a plurality of characteristic factors of a drainage pipe network area, first index sequence data of each characteristic factor corresponding to different types of pipe-in water quantity sources, and second index sequence data of each characteristic factor corresponding to a target abnormal water quantity source. The characteristic factors are used to represent characteristic indexes capable of distinguishing the pipe-in water quantity sources from the target abnormal water quantity source in the drainage pipe network area.

[0100] The screening module 702 is configured to screen the plurality of characteristic factors by using the first index sequence data of each characteristic factor corresponding to different types of pipe-in water quantity sources and the second index sequence data of each characteristic factor corresponding to the target abnormal water quantity source, to obtain a target characteristic factor combination.

[0101] The identification module 703 is configured to identify the abnormal water quantity source of the drainage pipe network area by using the target characteristic factor combination.

[0102] In some optional embodiments, the screening module 702 comprises:

[0103] The first determination sub-module is configured to determine at least one target set based on the plurality of characteristic factors, wherein the target set comprises a preset number of preset characteristic factors, and the preset number is an integer greater than 1.

[0104] The second determining sub-module is configured to determine a plurality of first data points according to the first index sequence data of each type of managed water source corresponding to each preset characteristic factor, mark the plurality of first data points in a coordinate system corresponding to the type of managed water source, filter the plurality of first data points in the coordinate system according to a preset rule, and determine a first fingerprint area of the type of managed water source according to the filtered first data points, wherein the coordinate system is constructed by taking each preset characteristic factor in the target set as a coordinate axis;

[0105] The third determining sub-module is configured to determine a plurality of second data points according to the second index sequence data of the target abnormal water source corresponding to each preset characteristic factor, mark the plurality of second data points in a coordinate system of the target abnormal water source, filter the plurality of second data points in the coordinate system according to a preset rule, and determine a second fingerprint area of the target abnormal water source according to the filtered second data points, wherein the second fingerprint area contains a target center point, and the target center point is determined according to the mean value of different data in the second index sequence data of the target abnormal water source corresponding to each preset characteristic factor;

[0106] The fourth determining sub-module is configured to determine a plurality of mixed points based on the first fingerprint areas of each type of managed water source and the second fingerprint area of the target abnormal water source; one mixed point is obtained by extracting one first target data point in each first fingerprint area according to a preset rule and processing the plurality of first target data points;

[0107] The fifth determining sub-module is configured to mark the plurality of mixed points in a target coordinate system to obtain a first mixed area, and mix the plurality of mixed points and the target center point according to a first preset proportion to obtain a plurality of third data points, mark the plurality of third data points in the target coordinate system to obtain a second mixed area.

[0108] The sixth determining sub-module is configured to combine the plurality of preset characteristic factors in the target set as a target characteristic factor combination if the first mixed area and the second mixed area do not coincide.

[0109] In some optional embodiments, the identification module 703 includes:

[0110] The acquisition sub-module is configured to acquire first sampling data in a drainage pipe network partition;

[0111] The seventh determining sub-module is configured to determine index data of each target characteristic factor in the target characteristic factor combination based on the first sampling data.

[0112] The eighth determining sub-module is configured to determine a target point according to the index data of each target characteristic factor, and mark the target point in a target coordinate system of a target set corresponding to the target characteristic factor combination.

[0113] The ninth determining sub-module is configured to determine that the water pipe network area has abnormal water infiltration if the target point in the target coordinate system is located outside the first mixed area.

[0114] In some optional embodiments, the screening module 702 further includes:

[0115] The mixing sub-module is configured to mix the multiple mixed points and the target center point of each target set according to different second preset proportions to obtain multiple fourth data points respectively corresponding to different second preset proportions, mark the multiple fourth data points under each second preset proportion to the target coordinate system, and determine third mixed areas respectively corresponding to different second preset proportions according to the multiple fourth data points under each second preset proportion in the target coordinate system.

[0116] In some optional embodiments, the identifying module 703 further includes:

[0117] The eighth determining sub-module is configured to determine relative position information of the target point and each mixed area in the target coordinate system when the water pipe network area has an abnormal water source.

[0118] The evaluating sub-module is configured to evaluate the severity of abnormal water infiltration in the water pipe network area based on the relative position information of the target point and each mixed area.

[0119] In some optional embodiments, the multiple characteristic factors of the water pipe network area are obtained through the following steps:

[0120] Obtain multiple initial characteristic factors respectively corresponding to different types of water sources and detection data of each initial characteristic factor;

[0121] Calculate the variation coefficient of each initial characteristic factor using the detection data of the initial characteristic factor;

[0122] Remove the initial characteristic factors with a variation coefficient greater than a preset threshold from the multiple initial characteristic factors of each type of water source to obtain at least one characteristic factor corresponding to the type of water source.

[0123] Further function descriptions of each module and unit are the same as those of the above-mentioned embodiments, and will not be described here.

[0124] The water pipe network abnormal water source identification device in the embodiment is presented in the form of a functional unit. The unit herein refers to an ASIC (Application Specific Integrated Circuit, Application Specific Integrated Circuit) circuit, a processor and a memory executing one or more software or fixed programs, and / or other devices that can provide the above functions.

[0125] The embodiment of the present application also provides a computer device having the aboveFigure 7 The illustrated drainage network abnormal water amount source identification device.

[0126] See Figure 8 , Figure 8 is a structural schematic diagram of a computer device provided by an optional embodiment of the present application, as Figure 8 indicated, the computer device includes one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are communicatively connected to each other by using different buses, and can be installed on a common motherboard or in other manners as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or graphics information of a GUI stored in the memory for displaying on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used together with multiple memories, if needed. Similarly, multiple computer devices can be connected, each providing part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 In the above description, the processor 10 is taken as an example.

[0127] The processor 10 can be a central processor, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic gate array, a generic array logic, or any combination thereof.

[0128] The memory 20 stores instructions executable by the at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.

[0129] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system and application programs required by at least one function; the data storage area can store data created according to the use of the computer device, etc. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some optional embodiments, the memory 20 can optionally include a memory remotely arranged with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0130] The memory 20 can include a volatile memory, such as a random access memory, and / or a non-volatile memory, such as a flash memory, a hard disk, or a solid state disk. The memory 20 can also include a combination of the above-mentioned types of memories.

[0131] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0132] The embodiments of the present application also provide a computer readable storage medium, and the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or be implemented as computer code stored in a remote storage medium or a non-transitory machine readable storage medium and stored in a local storage medium to be downloaded through a network, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that the computer, the processor, the microprocessor controller, or the programmable hardware includes a storage component that can store or receive software or computer code, which, when accessed and executed by the computer, the processor, or the hardware, implements the method shown in the above embodiments.

[0133] Part of the present application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide a method and / or technical solution according to the present application through the operation of the computer. Those skilled in the art should understand that the form of the computer program instructions in the computer readable medium includes but is not limited to source files, executable files, installation package files, etc. Correspondingly, the way of executing the computer program instructions by the computer includes but is not limited to: the computer directly executes the instructions, or the computer executes the corresponding compiled program after compiling the instructions, or the computer reads and executes the instructions, or the computer executes the corresponding installed program after reading and installing the instructions. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0134] Although the embodiments of the present application are described in conjunction with the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A method of sewer network abnormal water quantity source identification, characterized in that, The method comprises: obtaining a plurality of characteristic factors of a drainage pipe network area, a first index sequence data of each characteristic factor corresponding to different types of pipe-in water sources respectively, and a second index sequence data of each characteristic factor corresponding to a target abnormal water source, wherein the characteristic factors are used to represent characteristic indexes capable of distinguishing between pipe-in water sources and the target abnormal water source in the drainage pipe network area; screening the plurality of characteristic factors by using the first index sequence data of each characteristic factor corresponding to different types of pipe-in water sources respectively and the second index sequence data of each characteristic factor corresponding to the target abnormal water source, to obtain a target characteristic factor combination; identifying the abnormal water source of the drainage pipe network area by using the target characteristic factor combination; the step of screening the plurality of characteristic factors by using the first index sequence data of each characteristic factor corresponding to different types of pipe-in water sources respectively and the second index sequence data of each characteristic factor corresponding to the target abnormal water source, to obtain a target characteristic factor combination, comprises: determining at least one target set based on the plurality of characteristic factors, wherein the target set comprises a preset number of preset characteristic factors, and the preset number is an integer greater than 1; determining a plurality of first data points according to the first index sequence data of each preset characteristic factor corresponding to each type of pipe-in water source, marking the plurality of first data points into a coordinate system corresponding to the type of pipe-in water source, screening the plurality of first data points in the coordinate system according to a preset rule, and determining a first fingerprint area of the type of pipe-in water source according to the screened first data points, wherein the coordinate system is constructed by taking each preset characteristic factor in the target set as a coordinate axis; determining a plurality of second data points according to the second index sequence data of each preset characteristic factor corresponding to the target abnormal water source, marking the plurality of second data points into a coordinate system of the target abnormal water source, screening the plurality of second data points in the coordinate system according to a preset rule, and determining a second fingerprint area of the target abnormal water source according to the screened second data points, wherein the second fingerprint area contains a target center point, and the target center point is determined according to the mean value of different data in the second index sequence data of each preset characteristic factor corresponding to the target abnormal water source; determining a plurality of mixed points based on the first fingerprint area of each type of pipe-in water source and the second fingerprint area of the target abnormal water source, wherein one mixed point is obtained by extracting one first target data point in each first fingerprint area according to a preset rule, and the plurality of first target data points are processed to obtain the mixed point; marking the plurality of mixed points into a target coordinate system to obtain a first mixed area, and mixing the plurality of mixed points with the target center point according to a first preset proportion to obtain a plurality of third data points, wherein the plurality of third data points are marked into the target coordinate system to obtain a second mixed area; if the first mixed area does not coincide with the second mixed area, regarding the plurality of preset characteristic factors in the target set as a target characteristic factor combination.

2. The method of claim 1, wherein, the step of identifying the abnormal water source of the drainage pipe network area by using the target characteristic factor combination, comprises: Obtaining first sampling data in a drainage pipe network partition; Determining index data of each target characteristic factor in the target characteristic factor combination based on the first sampling data; Determining a target point according to the index data of each target characteristic factor, and labeling the target point into the target coordinate system; If the target point in the target coordinate system is located outside the first mixed area, determining that the water pipe network partition has an abnormal water source.

3. The method of claim 2, wherein, The step of screening the plurality of characteristic factors by using the first index sequence data of each characteristic factor corresponding to different types of pipe-in water sources and the second index sequence data of each characteristic factor corresponding to the target abnormal water source to obtain the target characteristic factor combination further comprises: Mixing the plurality of mixed points and the target center point of each target set according to different second preset proportions to obtain a plurality of fourth data points respectively corresponding to different second preset proportions, labeling the plurality of fourth data points under each second preset proportion into the target coordinate system, and determining a third mixed area corresponding to each second preset proportion in the target coordinate system.

4. The method of claim 3, wherein, The step of identifying the abnormal water source of the drainage pipe network partition by using the target characteristic factor combination further comprises: When the drainage pipe network partition has an abnormal water source, determining the relative position information of the target point and each mixed area in the target coordinate system; Based on the relative position information of the target point and each mixed area, evaluating the severity of the abnormal water infiltration in the drainage pipe network partition.

5. The method according to any one of claims 1 to 4, characterized in that, The plurality of characteristic factors of the drainage pipe network partition are obtained by the following steps: Obtaining a plurality of initial characteristic factors corresponding to different types of water sources and detection data of each initial characteristic factor; Calculating the coefficient of variation of each initial characteristic factor by using the detection data of each initial characteristic factor; Removing the initial characteristic factors with a coefficient of variation greater than a preset threshold from the plurality of initial characteristic factors of each type of water source to obtain at least one characteristic factor corresponding to each type of water source.

6. A sewer network abnormal water quantity source identification device characterized by, The device comprises: An acquisition module is configured to acquire a plurality of characteristic factors of a drainage pipe network partition, first index sequence data of each characteristic factor corresponding to different types of pipe-in water sources, and second index sequence data of each characteristic factor corresponding to a target abnormal water source, wherein the characteristic factors are used to represent characteristic indexes capable of distinguishing between pipe-in water sources and the target abnormal water source in the drainage pipe network partition; A screening module is configured to screen the plurality of characteristic factors by using the first index sequence data of each characteristic factor corresponding to different types of pipe-in water sources and the second index sequence data of each characteristic factor corresponding to the target abnormal water source to obtain a target characteristic factor combination; An identification module is configured to identify an abnormal water source of the drainage pipe network partition by using the target characteristic factor combination. The step of screening the plurality of characteristic factors by using the first index sequence data of each characteristic factor corresponding to different types of pipe-in water sources and the second index sequence data of each characteristic factor corresponding to the target abnormal water source to obtain the target characteristic factor combination comprises: determine at least one target set based on the plurality of characteristic factors, the target set including a preset number of preset characteristic factors, the preset number being an integer greater than 1; determine a plurality of first data points according to the first index sequence data of each type of pipe-in water source corresponding to each preset characteristic factor, mark the plurality of first data points into a coordinate system corresponding to the type of pipe-in water source, filter the plurality of first data points in the coordinate system according to a preset rule, and determine a first fingerprint area of the type of pipe-in water source according to the filtered first data points, the coordinate system being constructed with each preset characteristic factor in the target set as a coordinate axis; determine a plurality of second data points according to the second index sequence data of the target abnormal water source corresponding to each preset characteristic factor, mark the plurality of second data points into a coordinate system of the target abnormal water source, filter the plurality of second data points in the coordinate system according to a preset rule, and determine a second fingerprint area of the target abnormal water source according to the filtered second data points, the second fingerprint area including a target center point determined according to the mean value of different data in the second index sequence data of the target abnormal water source corresponding to each preset characteristic factor; determine a plurality of mixed points based on the first fingerprint area of each type of pipe-in water source and the second fingerprint area of the target abnormal water source, one mixed point being obtained by extracting a first target data point in each first fingerprint area according to a preset rule and processing a plurality of first target data points; mark the plurality of mixed points into a target coordinate system to obtain a first mixed area, and mix the plurality of mixed points with the target center point according to a first preset proportion to obtain a plurality of third data points, the plurality of third data points being marked into the target coordinate system to obtain a second mixed area; if the first mixed area and the second mixed area do not overlap, combine the plurality of preset characteristic factors in the target set as target characteristic factors.

7. A computer device, comprising: comprise: a memory and a processor, which are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the method of any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing a computer to perform the method of any one of claims 1 to 5.

9. A computer program product, characterised in that, comprise computer instructions for causing a computer to perform the method of any one of claims 1 to 5.

Images