Data falsification suspicion identification method and device applied to water sample dilution scene

By using an isolated forest algorithm to identify water quality parameter data in diluted water sample scenarios, the monitoring parameter set and characteristic indicators are constructed, and the problem of low efficiency and accuracy of fraud identification of diluted water sample data in the existing technology is solved, and high Accurate judgment on suspected fraud and the authenticity of environmental monitoring.

CN118964949APending Publication Date: 2024-11-15FOSHAN KENEITE ENVIRONMENT TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411184215.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

In the diluted water sample scenario, it is difficult for the existing technology to effectively identify data fraud, and rely on manual experience, resulting in low identification efficiency and accuracy, and the inability to effectively ensure the authenticity and effectiveness of environmental monitoring.

Method used

The isolated forest algorithm is used to identify abnormalities of water quality parameter data. By constructing a monitoring parameter set and characteristic indicators, historical data and data to be detected for multiple periods are collected, and the sample set to be detected is formed to identify abnormalities and warnings are performed to reduce human intervention.

Benefits of technology

It improves the accuracy of the judgment of suspected data fraud, and can fully feedback the water quality fraud of the water sample scene without human-set parameters, reduces the degree of human intervention, and improves the recognition efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118964949A_ABST
    Figure CN118964949A_ABST
Patent Text Reader

Abstract

The invention discloses a data falsification suspicion identification method and device applied to a dilution water sample scene, under the condition of an isolated forest algorithm, water quality parameter historical data before the current moment are collected to construct a monitoring parameter set and characteristic indexes, conditional data are determined according to the current day moment of water sample extraction, and the data are determined according to the current day moment of water sample extraction. The method comprises the following steps of: acquiring to-be-detected water quality parameter data of a plurality of time periods, and forming a to-be-detected sample set by the to-be-detected water quality parameter data of the plurality of time periods and characteristic indexes corresponding to a monitoring parameter set; abnormality identification and warning are carried out on to-be-detected water quality parameter data of each time period in a to-be-detected sample set based on an isolated forest algorithm, and for an overall identification task, the water quality parameter data are all extracted from a water sample scene; and the water quality counterfeiting condition of the current water sample scene can be fully fed back.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of environmental monitoring and protection technology, and in particular to a method and device for identifying suspected data falsification in a water sample dilution scenario. Background Art

[0002] At present, as society pays more attention to environmental protection and the demand for water quality monitoring increases, some unscrupulous companies may use various means to falsify water sample monitoring data in order to evade supervision, reduce costs or pursue improper interests. In the diluted water sample scenario, since the composition of the water sample is relatively complex, falsification is easier to hide and more challenging.

[0003] At present, although there are some technologies for identifying data fraud, with the advancement of technology, especially the development of adversarial technology, this field is still full of challenges. The current identification methods mainly rely on manual experience, among which data consistency checks and on-site verification are common means.

[0004] During the field inspection, the means of data falsification include but are not limited to blocking the sampling head, placing the monitoring instrument in a mineral water bottle, tampering with the monitoring data, pretending to operate the treatment facilities, manually setting the program, remotely controlling the parameters of the monitoring equipment, installing filtering and absorption devices, etc. The emergence of these means has brought greater challenges to environmental monitoring, because they may cause the actual monitoring data to be inconsistent with the actual situation.

[0005] Therefore, solutions are urgently needed to address the above-mentioned issues, which can reduce the degree of human intervention in the identification of water sample testing data fraud, so as to improve the efficiency and accuracy of identifying water sample monitoring data fraud and ensure the authenticity and effectiveness of environmental monitoring. Summary of the invention

[0006] The purpose of the present invention is to provide a method and device for identifying suspected data falsification in a dilution water sample scenario, aiming to solve the technical problems mentioned in the background technology and to provide a means of identifying whether the data in a dilution water sample scenario in an enterprise is suspected of falsification.

[0007] In order to achieve the above object, the technical solutions of the present invention are:

[0008] As one aspect of the present application, a method for identifying suspected data falsification in a dilution water sample scenario includes:

[0009] Collect historical data of water quality parameters before the current moment, and construct a monitoring parameter set and characteristic indicators corresponding to the monitoring parameter set based on the historical data of water quality parameters;

[0010] Based on the constructed monitoring parameter set, water quality parameter data to be tested in multiple time periods are collected, and the water quality parameter data to be tested in multiple time periods and the characteristic indicators corresponding to the monitoring parameter set are combined to form a sample set to be tested;

[0011] The isolation forest algorithm is used to identify and warn abnormalities in the water quality parameter data to be tested in each multiple time period in the sample set to be tested.

[0012] In the present application, the water quality parameter historical data before the current moment is collected, and a monitoring parameter set and characteristic indicators corresponding to the monitoring parameter set are constructed according to the water quality parameter historical data, including:

[0013] Collect all water quality parameter data at the current moment and the moment before the current moment;

[0014] The difference between the water quality parameter data at the current moment and the water quality parameter data at the moment before the current moment is taken as the characteristic index, and the number of data items in the water quality parameter data is taken as the monitoring parameter set.

[0015] Furthermore, the monitoring parameter set includes one or more of effluent flow, ammonia nitrogen content, total phosphorus content, chemical oxygen demand and pH value.

[0016] Furthermore, the characteristic indicators include one or more of the difference in water flow rate per unit time, the difference in ammonia nitrogen content per unit time, the difference in total phosphorus content per unit time, the difference in chemical oxygen demand per unit time, and the difference in pH value per unit time.

[0017] In the present application, the monitoring parameter set constructed based on the above method collects water quality parameter data to be detected in multiple time periods, and the water quality parameter data to be detected in multiple time periods and the characteristic indicators corresponding to the monitoring parameter set together constitute a sample set to be detected, including:

[0018] Collect water quality parameter data for multiple time periods after the current moment, and use the difference between the water quality parameter data at the start moment and the water quality parameter data at the end moment of each time period as the sample parameter to be tested;

[0019] The characteristic indicators corresponding to the multiple sample parameters to be detected and the monitoring parameter set together constitute the sample set to be detected.

[0020] Furthermore, the sample parameters to be detected include one or more of the difference in water flow rate per unit time, the difference in ammonia nitrogen content per unit time, the difference in total phosphorus content per unit time, the difference in chemical oxygen demand per unit time, and the difference in pH value per unit time.

[0021] Furthermore, the isolation forest algorithm is used to identify and warn abnormalities in the water quality parameter data to be tested in each of the multiple time periods in the sample set to be tested, including:

[0022] Construct an isolation forest algorithm model;

[0023] According to the collected samples to be tested, the characteristic indicators corresponding to the monitoring parameter set are used as identification references to determine whether there are more than a set number of samples to be tested with abnormal parameters in the collected samples to be tested;

[0024] If yes, a warning indication is given to the currently collected sample set to be tested.

[0025] As a second aspect of the present application, an identification device includes:

[0026] The historical data collection and processing module is used to collect historical data of water quality parameters, and to construct a monitoring parameter set and characteristic indicators corresponding to the monitoring parameter set based on the historical data of water quality parameters;

[0027] The current data collection and processing module is used to collect water quality parameter data to be tested in multiple time periods based on the constructed monitoring parameter set, and the water quality parameter data to be tested in multiple time periods and the characteristic indicators corresponding to the monitoring parameter set together form a sample set to be tested;

[0028] The data processing and warning module uses the isolation forest algorithm to identify and warn abnormalities in the water quality parameter data to be tested in each of the multiple time periods in the sample set to be tested.

[0029] Compared with the prior art, the present invention provides a method and device for identifying suspected data falsification in a diluted water sample scenario. Based on the isolation forest algorithm, the historical data of water quality parameters before the current moment are collected to construct a monitoring parameter set and characteristic indicators. The conditional data is determined according to the time of the day when the water sample is extracted to improve the accuracy of the judgment of suspected data falsification, and then the water quality parameter data to be tested in multiple time periods are collected, and the water quality parameter data to be tested in multiple time periods and the characteristic indicators corresponding to the monitoring parameter set are used together to form a sample set to be tested. Based on the isolation forest algorithm, the water quality parameter data to be tested in each of the multiple time periods in the sample set to be tested are identified and warned of abnormalities. For the overall identification task, the heavy water quality parameter data are extracted from the water sample scene. In the absence of intervention in manually set parameters, the water quality falsification situation of the current water sample scene can be fully fed back.

[0030] For better understanding and implementation, the present invention is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a flow chart of a method for identifying suspected data fraud in a dilution water sample scenario in this embodiment;

[0032] Figure 2is a flowchart indicating a specific method of step S1 in a method for identifying suspected data fraud in a dilution water sample scenario in this embodiment;

[0033] Figure 3 is a flowchart indicating a specific method of step S2 in a method for identifying suspected data fraud in a dilution water sample scenario in this embodiment;

[0034] Figure 4 is a flowchart indicating a specific method of step S3 in a method for identifying suspected data fraud in a dilution water sample scenario in this embodiment;

[0035] Figure 5 It is a structural diagram of a device for identifying suspected data falsification in a dilution water sample scenario in this embodiment. DETAILED DESCRIPTION

[0036] In order to better illustrate the present invention, the present invention is further described in detail below with reference to the accompanying drawings.

[0037] It should be clear that the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the embodiments of the present application.

[0038] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present application. The singular forms of "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0039] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0040] In addition, in the description of this application, unless otherwise specified, "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0041] At present, the means of data falsification include but are not limited to blocking sampling heads, placing monitoring instruments in mineral water bottles, tampering with and falsifying monitoring data, pretending to operate treatment facilities, manually setting programs, remotely controlling monitoring equipment parameters, and installing filtering and absorption devices.

[0042] Some of the above operations, such as blocking the sampling head, placing the monitoring instrument in a mineral water bottle, and installing a filter absorption device, are still difficult to detect. Although regulatory requirements have promoted the monitoring of the operation of treatment facilities, there is currently no effective solution to the problem of interference with the enterprise's terminal monitoring data, which mainly relies on manual experience and judgment.

[0043] Moreover, for the enterprise's end-point detection data, the falsified content is not limited to non-compliant / substandard data, and there is also suspicion of falsification of compliant / standard data, which is even more difficult to judge based on manual experience.

[0044] Based on the above, the technical problem actually solved by the present invention is to provide a new identification method and device for suspected data falsification applied in the dilution water sample scenario, so as to replace the manual identification of whether the data in the dilution water sample scenario is suspected of falsification.

[0045] The following is an illustrative example as an aspect of this embodiment. Figure 1 As shown, a method for identifying suspected data falsification in a dilution water sample scenario is provided, comprising the following steps:

[0046] Step S1, collecting historical data of water quality parameters before the current moment, and constructing a monitoring parameter set and characteristic indicators corresponding to the monitoring parameter set according to the historical data of water quality parameters;

[0047] Specifically, in this embodiment, if Figure 2 As shown, the step S1 specifically includes:

[0048] Step S11, collecting all water quality parameter data at the current moment and the moment before the current moment;

[0049] Step S12: taking the difference between the water quality parameter data at the current moment and the water quality parameter data at the moment before the current moment as the characteristic index, and taking the number of data items in the water quality parameter data as the monitoring parameter set.

[0050] According to the type of wastewater discharge of each enterprise, a monitoring parameter set is generally agreed upon manually, and the monitoring parameter set corresponds to one or more of effluent flow, ammonia nitrogen content, total phosphorus content, chemical oxygen demand and pH value.

[0051] Moreover, when the enterprise is discharging sewage, process fraud is prevented. For example, when the inspection personnel and the enterprise conduct on-site inspection at an agreed time point, the enterprise may perform data fraud actions such as blocking the sampling head, placing the monitoring instrument in a mineral water bottle, and installing a filtering absorption device within a period of time at that time point, resulting in the acquired data being fraudulent data. Therefore, the inspection personnel collect water quality parameter data before the current moment through inspection tools (such as sensors and processor tools for various data indicators). In this embodiment, the current moment is set to time t, and the water quality parameter data less than or equal to time t is the water quality parameter historical data. The water quality parameter historical data type is obtained by the inspection personnel in real time to ensure the authenticity of the data, which can influence the benchmark for subsequent judgment of suspected data fraud;

[0052] Furthermore, it should be noted that the difference between the water quality parameter data collected at different times generally maintains a constant value. When the water quality parameter data is falsified, there is a mutation in the difference between at least one adjacent water quality parameter data. The characteristic indicator is constructed based on the above principle.

[0053] In this embodiment, characteristic indicators corresponding to the monitoring parameter set are constructed, and the characteristic indicators include one or more of the difference in water flow rate per unit time, the difference in ammonia nitrogen content per unit time, the difference in total phosphorus content per unit time, the difference in chemical oxygen demand per unit time, and the difference in pH value per unit time;

[0054] For example, take the historical water quality parameter data for the period of 1 hour before time t;

[0055] Record the water flow rate as A n , ammonia nitrogen content is B n , the total phosphorus content is C n , chemical oxygen demand is D n , pH value is E n , where n indicates a certain moment, then the characteristic index parameter is obtained as (A t -A t-1 , B t -B t-1 , C t -C t-1 , D t -D t-1 , E t -E t-1 ), where (A t -A t-1 , B t -Bt-1 , C t -C t-1 , D t -D t-1 , E t -E t-1 ) are indicated in turn as the difference in water outlet flow between the current moment t and one hour before moment t, the difference in water outlet flow between the current moment t and one hour before moment t, the difference in ammonia nitrogen content between the current moment t and one hour before moment t, the difference in total phosphorus content between the current moment t and one hour before moment t, the difference in chemical oxygen demand between the current moment t and one hour before moment t, and the difference in pH value between the current moment t and one hour before moment t.

[0056] Step S2, based on the constructed monitoring parameter set, collecting water quality parameter data to be detected in multiple time periods, and combining the water quality parameter data to be detected in multiple time periods with the characteristic indicators corresponding to the monitoring parameter set to form a sample set to be detected;

[0057] like Figure 3 As shown, the step S2 specifically includes:

[0058] Step S21, collecting water quality parameter data of multiple time periods after the current moment, and taking the difference between the water quality parameter data at the start moment and the water quality parameter data at the end moment of each time period as the sample parameter to be detected;

[0059] According to the above, under normal circumstances, the water quality parameter data of sewage will not fluctuate greatly, but in the diluted water sample scenario, the data will have a significant increase or decrease, so it can be reflected in the indicators constructed above, that is, the situation where the difference is abnormally large actually has a certain suspicion of dilution, so it is necessary to sample the water quality parameter data for multiple time periods;

[0060] For example, in this embodiment, the current time is set as time t, and water quality parameter data is collected in multiple time periods with a set time interval of 1 hour. Each water quality parameter data includes the water flow rate A n , ammonia nitrogen content B n , total phosphorus content C n , chemical oxygen demand D n , pH value E n , thereby obtaining the following parameters of the sample to be tested, wherein the parameters of the sample to be tested include one or more of the difference in water flow rate per unit time, the difference in ammonia nitrogen content per unit time, the difference in total phosphorus content per unit time, the difference in chemical oxygen demand per unit time, and the difference in pH value per unit time;

[0061] The parameters of the sample to be tested between time t and time t+1 are recorded as: U 1 :(A t -At+ 1 , B t -B t+ 1 , C t -C t+ 1 , D t -D t+ 1 , E t -E t+ 1 );

[0062] The parameters of the samples to be tested between time t+1 and time t+2 are recorded as: U 2 :(A t+ 1 -A t+ 2 , B t+ 1 -B t+ 2 , C t+ 1 -C t+ 2 , D t+ 1 -D t+ 2 , E t+ 1 -E t+ 2 );

[0063] …

[0064] The parameters of the samples to be tested between time t+m and time t+m+1 are recorded as: U m+ 1 :(A t+m -A t+m+ 1 , B t+m -B t+m+ 1 , C t+m -C t+m+ 1 , D t+m -D t+m+ 1 , E t+m -E t+m+ 1 );

[0065] Step S22: a plurality of parameters of samples to be detected and characteristic indicators corresponding to the monitoring parameter set together constitute a sample set to be detected.

[0066] In this embodiment, in order to facilitate the subsequent use of the isolation forest algorithm to call data and form a sample set to be detected, based on the above example, it is formed as follows ((U1, U2, ..., Um+1): (A t -A t-1 , B t -B t-1 , C t -C t-1 , D t -D t-1 , E t -E t-1 )) of the sample set to be tested.

[0067] Step S3: Use the isolation forest algorithm to identify and warn of abnormalities in the water quality parameter data to be tested in each of the multiple time periods in the sample set to be tested.

[0068] Specifically, in this embodiment, if Figure 4 As shown, the step S3 specifically includes:

[0069] Step S31, constructing an isolation forest algorithm model;

[0070] In this embodiment, a mathematical model constructed by applying the existing isolation forest algorithm is used. According to the existing description of the isolation forest algorithm, in a data set with common characteristics, the data set is gradually screened in order with multiple set conditions to obtain the final differential data results.

[0071] In this embodiment, the following is constructed: (A t -A t-1 , B t -B t-1 , C t -C t-1 , D t -D t-1 , E t -E t-1 ))'s sample set to be tested is applied in the isolation forest algorithm model, with the difference in water flow rate per unit time, the difference in ammonia nitrogen content per unit time, the difference in total phosphorus content per unit time, the difference in chemical oxygen demand per unit time and the difference in pH value per unit time as judgment criteria, i.e., characteristic indicators, and the differences in the parameters of multiple samples to be tested are judged according to the sorting.

[0072] Step S32: according to the collected sample set to be detected, using the characteristic indicators corresponding to the monitoring parameter set as identification references, determining whether there are more than a set number of sample set to be detected with abnormal parameters in the collected sample set to be detected;

[0073] Based on the application of the isolation forest algorithm in step S31, the difference judgment is performed on the parameters of multiple samples to be detected. For example, for the structure ((U1, U2, ..., Um+1): (A t -A t-1 , B t -B t-1 , C t -C t-1 , D t -D t-1 , E t -E t-1 )) of the sample set to be detected, compare the difference in water flow rate per unit time with all the sample parameters to be detected between time t and time t+m+1, if the difference between the sample parameters to be detected corresponding to each time period between time t to time t+1 and time t+m to time t+m+1 and the difference in water flow rate per unit time is large, it is judged that the sample parameters to be detected in this time period are abnormal, and the sample parameters to be detected in this time period are extracted and classified according to the isolation forest algorithm, and the sample set to be detected after screening and classification is obtained, and the characteristic index of the difference in water flow rate per unit time and the abnormal sample parameters to be detected are isolated in the sample set to be detected after screening; after completing the screening and classification with the difference in water flow rate per unit time as the characteristic index, the same method is used to distinguish whether the sample parameters to be detected corresponding to each time period are abnormal, so as to obtain the final abnormality judgment result, that is, the abnormal classification set of sample parameters to be detected and the normal classification set of sample parameters to be detected are obtained.

[0074] It should be noted that the difference in the water flow rate per unit time is relatively large. For example, the numerical difference between the water flow rate difference per unit time and the water flow rate difference in the sample parameters to be tested is relatively large. The specific judgment criterion can be set artificially.

[0075] Step S33: If yes, a warning indication is given to the currently collected sample set to be tested;

[0076] Based on the judgment method of step S32, in order to ensure the accuracy of the judgment, in this embodiment, when there are at least two abnormal sample parameters to be detected in the obtained abnormal sample parameter classification set, step S33 is executed, and warning indications such as buzzing and indicator lights are used to indicate that the water quality parameter data of the enterprise is falsified.

[0077] As two aspects of this application, Figure 5 As shown, an identification device 100 is provided, comprising:

[0078] The historical data collection and processing module 101 is used to collect historical data of water quality parameters, and to construct a monitoring parameter set and characteristic indicators corresponding to the monitoring parameter set according to the historical data of water quality parameters;

[0079] The current data collection and processing module 102 is used to collect water quality parameter data to be detected in multiple time periods based on the constructed monitoring parameter set, and to form a sample set to be detected by combining the water quality parameter data to be detected in multiple time periods with the characteristic indicators corresponding to the monitoring parameter set;

[0080] The data processing and warning module 103 uses the isolation forest algorithm to perform abnormal identification and warning on the water quality parameter data to be detected in each of the multiple time periods in the sample set to be detected.

[0081] In the present embodiment, a method and device for identifying suspected data falsification in a diluted water sample scenario is used. Based on the isolation forest algorithm, historical data of water quality parameters before the current moment are collected to construct a monitoring parameter set and characteristic indicators. The conditional data is determined based on the time of the day when the water sample is extracted to improve the accuracy of the judgment of suspected data falsification, and then water quality parameter data to be tested in multiple time periods are collected, and the water quality parameter data to be tested in multiple time periods and the characteristic indicators corresponding to the monitoring parameter set are used together to form a sample set to be tested. Based on the isolation forest algorithm, abnormal identification and warning are performed on the water quality parameter data to be tested in each of the multiple time periods in the sample set to be tested. For the overall identification task, the heavy water quality parameter data are all extracted from the water sample scene. In the absence of intervention in manually set parameters, the water quality falsification situation of the current water sample scene can be fully fed back.

[0082] According to the disclosure and teaching of the above description, those skilled in the art to which the present invention belongs may also make changes and modifications to the above embodiments. Therefore, the present invention is not limited to the specific embodiments disclosed and described above, and some modifications and changes to the present invention should also fall within the scope of protection of the claims of the present invention. In addition, although some specific terms are used in this specification, these terms are only for the convenience of description and do not constitute any limitation to the present invention.

Claims

1. A method for identifying suspected data fraud in a dilution water sample scenario, characterized in that: include: Collect historical data of water quality parameters before the current moment, and construct a monitoring parameter set and characteristic indicators corresponding to the monitoring parameter set based on the historical data of water quality parameters; Based on the constructed monitoring parameter set, water quality parameter data to be tested in multiple time periods are collected, and the water quality parameter data to be tested in multiple time periods and the characteristic indicators corresponding to the monitoring parameter set are combined to form a sample set to be tested; The isolation forest algorithm is used to identify anomalies in the water quality parameter data to be tested in each time period in the sample set to be tested, and the water quality parameter falsification judgment result is obtained according to the difference between the water quality parameter data to be tested in each time period and the monitoring parameter set and the characteristic indicators corresponding to the monitoring parameter set.

2. The identification method according to claim 1, characterized in that: The collecting of historical data of water quality parameters before the current moment, and constructing a monitoring parameter set and characteristic indicators corresponding to the monitoring parameter set according to the historical data of water quality parameters, include: Collect all water quality parameter data at the current moment and the moment before the current moment; The difference between the water quality parameter data at the current moment and the water quality parameter data at the moment before the current moment is used as the characteristic index, and the number of data items in the water quality parameter data is used as the monitoring parameter set.

3. The identification method according to claim 2, characterized in that: The monitoring parameter set includes one or more of effluent flow, ammonia nitrogen content, total phosphorus content, chemical oxygen demand and pH value.

4. The identification method according to claim 2, characterized in that: The characteristic indicators include one or more of the difference in water flow rate per unit time, the difference in ammonia nitrogen content per unit time, the difference in total phosphorus content per unit time, the difference in chemical oxygen demand per unit time, and the difference in pH value per unit time.

5. The identification method according to claim 1, characterized in that: The monitoring parameter set constructed based on the above method collects water quality parameter data to be detected in multiple time periods, and the water quality parameter data to be detected in multiple time periods and the characteristic indicators corresponding to the monitoring parameter set together form a sample set to be detected, including: Collect water quality parameter data for multiple time periods after the current moment, and use the difference between the water quality parameter data at the start moment and the water quality parameter data at the end moment of each time period as the sample parameter to be tested; The characteristic indicators corresponding to the multiple sample parameters to be detected and the monitoring parameter set together constitute the sample set to be detected.

6. The identification method according to claim 5, characterized in that: The sample parameters to be detected include one or more of the difference in water flow rate per unit time, the difference in ammonia nitrogen content per unit time, the difference in total phosphorus content per unit time, the difference in chemical oxygen demand per unit time, and the difference in pH value per unit time.

7. The identification method according to claim 5, characterized in that: The isolation forest algorithm is used to identify anomalies in the water quality parameter data to be tested in each period of the sample set to be tested, and the water quality parameter fraud judgment results are obtained based on the differences between the water quality parameter data to be tested in each period and the monitoring parameter set and the characteristic indicators corresponding to the monitoring parameter set, including: Construct an isolation forest algorithm model; According to the collected samples to be tested, the characteristic indicators corresponding to the monitoring parameter set are used as identification references to determine whether there are more than a set number of samples to be tested with abnormal parameters in the collected samples to be tested; If so, a warning indication is given to the currently collected sample set to be tested, and the water quality parameter fraud judgment result is output.

8. An identification device, characterized in that: include: The historical data collection and processing module is used to collect historical data of water quality parameters, and to construct a monitoring parameter set and characteristic indicators corresponding to the monitoring parameter set based on the historical data of water quality parameters; The current data collection and processing module is used to collect water quality parameter data to be tested in multiple time periods based on the constructed monitoring parameter set, and the water quality parameter data to be tested in multiple time periods and the characteristic indicators corresponding to the monitoring parameter set together form a sample set to be tested; The data processing and warning module uses the isolation forest algorithm to identify anomalies in the water quality parameter data to be tested in each time period in the sample set to be tested, and obtains the water quality parameter falsification judgment result based on the difference between the water quality parameter data to be tested in each time period and the monitoring parameter set and the characteristic indicators corresponding to the monitoring parameter set.