CN114997310A - Environment-friendly monitoring data processing method and system - Google Patents
Environment-friendly monitoring data processing method and system Download PDFInfo
- Publication number
- CN114997310A CN114997310A CN202210622474.4A CN202210622474A CN114997310A CN 114997310 A CN114997310 A CN 114997310A CN 202210622474 A CN202210622474 A CN 202210622474A CN 114997310 A CN114997310 A CN 114997310A
- Authority
- CN
- China
- Prior art keywords
- data
- environmental protection
- environmental
- environment
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses an environmental protection monitoring data processing method and system. A plurality of environmental monitoring data is obtained. And processing data based on the environmental protection monitoring data to obtain environmental protection enhancement data. And obtaining an environmental protection judgment value through an environmental data judgment model based on the environmental protection enhancement data. The discrete environmental monitoring data is constructed into continuous curves, so that the data can be better distinguished. A new environmental protection monitoring constant value and a new environmental protection range value in the curve are obtained based on the continuous environmental protection monitoring curve, and the new environmental protection monitoring constant value and the new environmental protection range value are used for calculation to limit judgment and can better judge. Meanwhile, after the environmental protection monitoring curve information is obtained, the burden of a computer is reduced. And (3) inputting the data into an LSTM neural network structure through fixed time division, and judging the environmental protection monitoring data of a plurality of time periods under the influence of the range and the constant value obtained by the environmental protection monitoring curve. The time information, namely the overall information, is considered by using the LSTM neural network structure, so that the judgment is more accurate.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an environment-friendly monitoring data processing method and system.
Background
The environmental air monitoring is an important support means for environmental quality management, and plays an important role in improving the environmental quality management. In the existing environmental monitoring method, the data of the components in the environment are monitored, and the content of the monitored data is changed. However, in the monitoring process, a lot of data are generally obtained, and then the data are judged, which results in a lot of calculation, and meanwhile, since the data are obtained by monitoring each time point, if only the discrete data are used for judging, the judgment cannot be made for other data which are not monitored at the time point.
Disclosure of Invention
The invention aims to provide an environment-friendly monitoring data processing method and system, which are used for solving the problems in the prior art.
In a first aspect, an embodiment of the present invention provides an environmental monitoring data processing method, including:
obtaining a plurality of environmental monitoring data; the environmental protection monitoring data is detected environmental protection information;
based on the environmental protection monitoring data, carrying out data processing to obtain environmental protection enhancement data; the environmental protection enhancement data comprises new environmental protection data and an environmental average data set;
obtaining an environmental protection judgment value through an environmental data judgment model based on the environmental protection enhancement data;
the environment-friendly judgment model comprises an environment-friendly neural network structure and an LSTM neural network structure.
Optionally, the method for training the environmental data judgment model includes:
obtaining a training set; the training set comprises training environment-friendly enhanced data and marking data; the training environment-friendly enhancement data comprises training new environment-friendly data and a training environment average data set; the marking data is a marking judgment value; the marking judgment value indicates whether monitoring limitation is met;
obtaining a training environment-friendly judgment value through the environment data judgment model based on the training environment-friendly enhancement data; the environmental protection judgment value is 1, which represents a coincidence condition; the environmental protection judgment value is 0, which indicates that the condition is not met;
obtaining an environmental protection judgment loss value based on the training environmental protection judgment value and the labeled data;
obtaining the current training iteration times of an environment data judgment model and the preset maximum iteration times of the environment data judgment model training;
and stopping training when the environmental protection judgment loss value is less than or equal to a threshold value or the training iteration number reaches the maximum iteration number, so as to obtain a trained environmental data judgment model.
Optionally, the obtaining a training environment-friendly judgment value based on the training environment-friendly enhancement data through the environment data judgment model includes:
inputting new training environment-friendly data and new training environment-friendly monitoring data in the training environment-friendly enhanced data into an environment-friendly neural network to obtain an output value of the environment-friendly neural network;
and inputting the output value of the environment-friendly neural network and the training environment-friendly monitoring data in the training environment-friendly enhanced data into an environment-friendly judgment model to obtain an environment-friendly judgment value.
Optionally, the method includes the steps of inputting the environmental protection monitoring data in the environmental protection enhancement data and the environmental protection neural network output value into an environmental protection judgment model to obtain an environmental protection judgment value, where the environmental protection judgment value includes:
obtaining first training environmental protection monitoring data; the first training environmental protection monitoring data is a first value in the training environmental protection monitoring data;
inputting the first training environment-friendly monitoring data and the environment-friendly neural network output value into a first LSTM neural network to obtain a first LSTM output value;
obtaining second training environment-friendly monitoring data; the second training environmental protection monitoring data is a second value in the training environmental protection monitoring data;
inputting the second training environment-friendly monitoring data, the environment-friendly neural network output value and the first LSTM output value into a second LSTM neural network to obtain a second LSTM output value;
and inputting training environment-friendly monitoring data and the environment-friendly neural network output value into a corresponding LSTM neural network for multiple times to obtain an environment-friendly judgment value.
Optionally, the processing the data based on the environmental protection monitoring data to obtain environmental protection enhancement data includes:
obtaining an environment-friendly monitoring curve based on the environment-friendly monitoring data;
obtaining new environmental protection data based on the environmental protection monitoring curve; the new environmental protection data comprises a new environmental protection monitoring constant value and a new environmental protection range value;
and obtaining environmental protection enhancement data based on the environmental protection monitoring data and the new environmental protection data.
Optionally, obtaining new environmental protection data based on the environmental protection monitoring curve includes:
obtaining a new environmental monitoring constant value based on the environmental monitoring curve; the new environmental monitoring constant value is environmental monitoring data with the most occurrence times in the environmental monitoring curve;
obtaining a plurality of environment protection extreme values based on the environment protection monitoring curve; the environmental protection extreme value represents environmental protection monitoring data of an extreme point in an environmental protection monitoring curve;
obtaining a new environmental protection range value based on the plurality of environmental protection extreme values; the new environmental protection range value comprises a new environmental protection minimum value and a new environmental protection maximum value; the new environmental protection maximum value is an environmental protection extreme value larger than other environmental protection extreme values; the new environmental minimum value is an environmental extreme value smaller than other environmental extreme values.
Optionally, obtaining environmental protection enhancement data based on the environmental protection monitoring data and the new environmental protection data includes:
obtaining a plurality of environmental monitoring data subsets; the environment-friendly monitoring data subset is environment-friendly monitoring data obtained by dividing the environment-friendly monitoring data according to a fixed time interval;
obtaining an environmental protection data average value based on the environmental protection monitoring data subset; a plurality of environment-friendly monitoring data subsets correspondingly obtain a plurality of environment-friendly data average values;
and forming an environment average data set by the plurality of environment-friendly data average values.
In a second aspect, an embodiment of the present invention provides an environmental monitoring data processing system, including:
an acquisition module: obtaining a plurality of environmental monitoring data; the environmental protection monitoring data is detected environmental protection information;
a reinforcing module: based on the environmental protection monitoring data, carrying out data processing to obtain environmental protection enhancement data; the environmental protection enhancement data comprises new environmental protection data and an environmental average data set;
a judging module: obtaining an environmental protection judgment value through an environmental data judgment model based on the environmental protection enhancement data;
the environment-friendly judgment model comprises an environment-friendly neural network structure and an LSTM neural network structure.
Optionally, the processing the data based on the environmental protection monitoring data to obtain environmental protection enhancement data includes:
obtaining a plurality of environmental monitoring data; the environment-friendly monitoring data is classified according to data categories;
obtaining a plurality of corresponding environment-friendly monitoring curves based on the plurality of environment-friendly monitoring data;
obtaining a plurality of corresponding new environmental protection data based on the plurality of environmental protection monitoring curves; the new environmental protection data comprises a new environmental protection monitoring constant value and a new environmental protection range value;
and obtaining a plurality of environmental protection enhancement data based on the plurality of environmental protection monitoring data and the plurality of new environmental protection data.
Optionally, obtaining new environmental protection data based on the environmental protection monitoring curve includes:
obtaining a new environmental monitoring constant value based on the environmental monitoring curve; the new environmental monitoring constant value is environmental monitoring data with the most occurrence times in the environmental monitoring curve;
obtaining a plurality of environment protection extreme values based on the environment protection monitoring curve; the environmental protection extreme value represents environmental protection monitoring data of an extreme point in an environmental protection monitoring curve;
obtaining a new environmental protection range value based on the plurality of environmental protection extreme values; the new environmental protection range value comprises a new environmental protection minimum value and a new environmental protection maximum value; the new environmental protection maximum value is an environmental protection extreme value larger than other environmental protection extreme values; the new environmental minimum value is an environmental extreme value smaller than other environmental extreme values.
Compared with the prior art, the embodiment of the invention achieves the following beneficial effects:
the embodiment of the invention also provides an environmental monitoring data processing method and a system, wherein the method comprises the following steps: a plurality of environmental monitoring data is obtained. The environmental protection monitoring data is detected environmental protection information. And processing data based on the environmental protection monitoring data to obtain environmental protection enhancement data. The environmental enhancement data includes new environmental data and an environmental mean data set. And obtaining an environmental protection judgment value through an environmental data judgment model based on the environmental protection enhancement data. The environment-friendly judgment model comprises an environment-friendly neural network structure and an LSTM neural network structure.
The discrete environmental monitoring data is constructed into continuous curves, so that the data can be better distinguished. A new environmental protection monitoring constant value and a new environmental protection range value in the curve are obtained based on the continuous environmental protection monitoring curve, and the new environmental protection monitoring constant value and the new environmental protection range value are used for calculation to limit judgment and can better judge. Meanwhile, after the environmental protection monitoring curve information is obtained, in order to reduce the load of a computer, the data are judged at fixed time intervals. And inputting the data into an LSTM neural network structure, and judging the environmental monitoring data of a plurality of time periods under the influence of the range and the constant value obtained by the environmental monitoring curve. The time information, namely the overall information, is considered by using the LSTM neural network structure, so that the judgment is more accurate.
In conclusion, the environmental protection monitoring data is controlled layer by layer, so that the environmental protection data is safer and more reliable.
Drawings
Fig. 1 is a flowchart of an environmental monitoring data processing method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of an environmental data determination model in the environmental monitoring data processing method system according to the embodiment of the present invention.
Fig. 3 is a schematic block structure diagram of an electronic device according to an embodiment of the present invention.
The labels in the figure are: a bus 500; a receiver 501; a processor 502; a transmitter 503; a memory 504; a bus interface 505.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present invention provides an environmental monitoring data processing method, where the method includes:
s101: obtaining a plurality of environmental monitoring data; the environmental protection monitoring data is detected environmental protection information;
the environmental monitoring data is one of a plurality of categories of monitoring data at a plurality of time points, and the categories of the monitoring data comprise sulfur dioxide, nitrogen oxides, smoke dust, sewage components and the like.
The environmental monitoring data are obtained by detecting according to each time point. If the sewage discharge condition is detected, the discharged sewage is detected at fixed time intervals, and the detection time and the corresponding sewage component condition are recorded.
S102: and processing data based on the environmental protection monitoring data to obtain environmental protection enhancement data. The environmental enhancement data includes new environmental data and an environmental average data set.
S103: and obtaining an environmental protection judgment value through an environmental data judgment model based on the environmental protection enhancement data.
Wherein, the environment data judgment model is a trained model. The method for obtaining the environmental protection judgment value through the environmental data judgment model based on the environmental protection enhancement data is similar to the training process.
And inputting the protection enhancement data into an environment-friendly neural network to obtain monitoring environment-friendly neural network output. Obtaining first environmental monitoring data; the first environmental protection monitoring data is a first value in the environmental protection monitoring data. And inputting the first environment-friendly monitoring data and the environment-friendly neural network output value into a first LSTM neural network. Second warranty monitoring data is obtained. The second environmental protection monitoring data is a second value in the training environmental protection monitoring data. And inputting the second environment-friendly monitoring data, the environment-friendly neural network output value and the first LSTM output value into a second LSTM neural network to obtain a second LSTM output value. And sequentially inputting the training environment-friendly monitoring data and the output of the monitoring environment-friendly neural network into the corresponding LSTM neural network for multiple times to obtain an environment-friendly judgment value.
The environment-friendly judgment model comprises an environment-friendly neural network structure and an LSTM neural network structure.
The monitoring mode and the model construction mode of other monitored types of data are the same as the above method.
Optionally, the method for training the environmental data judgment model includes:
obtaining a training set; the training set comprises training environment-friendly enhanced data and marking data; the training environment-friendly enhancement data comprises training new environment-friendly data and a training environment average data set; the marking data is a marking judgment value; the annotation judgment value indicates whether the monitoring limit is satisfied.
And obtaining a training environment-friendly judgment value through the environment data judgment model based on the training environment-friendly enhancement data. The environmental judgment value of 1 indicates a coincidence condition. The environmental judgment value of 0 indicates that the situation is not met.
And obtaining an environmental protection judgment loss value based on the training environmental protection judgment value and the labeled data.
And calculating to obtain an environment-friendly judgment loss value by using a quadratic cross entropy loss function.
If the marking data is yes, a component specified range is set, whether the marking data is in the range is judged, and if the marking data is not in the specified range, the marking data is set as 0, and the marking data is set as 1 in the specified range. The component specification range in this example is a condition for restricting the pollution condition in the country. The discrimination of the labeled data is manual discrimination.
And acquiring the current training iteration times of the environment data judgment model and the preset maximum iteration times of the environment data judgment model training.
In this embodiment, the maximum number of iterations of the environmental data determination model training that is preset in this embodiment is 1200.
And stopping training when the environmental protection judgment loss value is less than or equal to a threshold value or the training iteration number reaches the maximum iteration number, so as to obtain a trained environmental data judgment model.
By the method, the environmental protection enhancement data is input into an environmental data judgment model, whether the environment meets the environmental protection condition is judged, and information among data can be better obtained through a neural network so as to judge.
Optionally, obtaining a training environmental protection judgment value based on the training environmental protection enhancement data through the environmental data judgment model includes:
and inputting the new training environment-friendly data and the new training environment-friendly monitoring data in the training environment-friendly enhanced data into an environment-friendly neural network to obtain an output value of the environment-friendly neural network.
And inputting the output value of the environment-friendly neural network and the training environment-friendly monitoring data in the training environment-friendly enhanced data into an environment-friendly judgment model to obtain an environment-friendly judgment value.
By the method, the characteristics of the new environmental monitoring constant value and the new environmental range value in the new environmental data are extracted by using the environmental neural network and then input into the LSTM neural network structure, so that the judgment of the LSTM neural network structure on the environmental monitoring data is more accurate.
Optionally, the training environmental protection monitoring data and the fuzzy data are input into an environmental protection judgment neural network to obtain an environmental protection judgment value, including:
obtaining first training environment-friendly monitoring data; the first training environmental protection monitoring data is a first value in the training environmental protection monitoring data.
And inputting the first training environment-friendly monitoring data into a first LSTM neural network to obtain a first LSTM output value.
And obtaining second training environment-friendly monitoring data. The second training environmental protection monitoring data is a second value in the training environmental protection monitoring data.
And inputting the second training environment-friendly monitoring data and the first LSTM output value into a second LSTM neural network to obtain a second LSTM output value.
And inputting the training environment-friendly monitoring data into the corresponding LSTM neural network for multiple times to obtain an environment-friendly judgment value.
Put into the neural network according to different orders, or input the neural setting judgment switch according to the value of time quantum.
In the method, the environmental protection monitoring data is obtained by monitoring the environmental protection monitoring data at a plurality of time points, and in order to prevent the numerical value at one moment from being too large, the judgment is carried out by adopting an LSTM neural network method in consideration of the situation of a period of time.
Optionally, the processing the data based on the environmental protection monitoring data to obtain environmental protection enhancement data includes:
and obtaining an environment-friendly monitoring curve based on the environment-friendly monitoring data.
The environment-friendly monitoring curve is obtained by fitting the environment-friendly monitoring data classified according to the data types.
Wherein, fitting the environmental monitoring curve by using a fitting method. The fitting method used in this example is a least squares fitting method.
The environment-friendly monitoring curves represent a plurality of curves formed by taking different detection data as abscissa according to time points and taking obtained detection values as ordinate.
And obtaining new environmental protection data based on the environmental protection monitoring curve. The new environmental data includes a new environmental monitoring constant value and a new environmental range value.
Wherein the new environmental monitoring constant value represents the most number of values in the environmental monitoring curve.
And obtaining environmental protection enhancement data based on the environmental protection monitoring data and the new environmental protection data.
By the method, the discrete data are converted into the continuous curve, so that more than the current detection situation can be considered, and other situations can be considered. And in the process of changing into continuous, some mutation values are removed.
Optionally, obtaining new environmental protection data based on the environmental protection monitoring curve includes:
and obtaining a plurality of corresponding new environmental protection monitoring constant values based on the plurality of environmental protection monitoring curves. The new environmental monitoring constant value is an environmental monitoring data value with the most occurrence times in the environmental monitoring curve.
And obtaining a plurality of environment protection extreme values based on the environment protection monitoring curve. The environmental protection extreme value represents environmental protection monitoring data of an extreme point in an environmental protection monitoring curve.
And obtaining a new environmental protection range value based on the plurality of environmental protection extreme values. The new environmental protection range value includes a new environmental protection minimum value and a new environmental protection maximum value. The new environmental protection maximum value is an environmental protection extreme value larger than other environmental protection extreme values. The new environmental minimum value is an environmental extreme value smaller than other environmental extreme values.
By the method, the most frequently-occurring data value in the environment-friendly monitoring curve and the maximum value and the minimum value of the environment detection curve can be obtained, so that the data range of the environment detection curve can be obtained from the maximum value and the minimum value, and the data can be accurately distinguished in the subsequent detection.
Optionally, obtaining environmental protection enhancement data based on the environmental protection monitoring data and the new environmental protection data includes:
a plurality of environmental monitoring data subsets are obtained. The environment-friendly monitoring data subset is environment-friendly monitoring data obtained by dividing the environment-friendly monitoring data according to a fixed time interval.
And detecting the environment-friendly monitoring data at a fixed time interval in sequence and putting the environment-friendly monitoring data into an environment-friendly monitoring data subset. If the environmental protection data is obtained within three days, the obtained data is detected every minute, and the set fixed time interval is 2 hours. The number of the environment-friendly monitoring data subsets is 3x 24/2-36 subsets. The number of the data subsets in the environment-friendly monitoring data subset is 2x 60-120. As part of the environmental monitoring data is {10, 25, 18, 30}, the unit of the environmental monitoring data is (mg/m) to represent the emission concentration of sulfur dioxide. The environmental monitoring data subsets are 10, 25 and 18, 30. The {10, 25} represents a first environmental monitoring subset, the data monitored at a first point in time of the first environmental monitoring subset represented by 10, the data monitored at a second point in time of the first environmental monitoring subset represented by 25. The {18, 30} representation represents a second subset of the environmental protection monitoring, the data monitored at a first point in time of the second subset of the environmental protection monitoring of 18, the data monitored at a second point in time of the second subset of the environmental protection monitoring of 18. Array calculations are used in the calculation process.
Obtaining an environmental protection data average value based on the environmental protection monitoring data subset; and correspondingly obtaining a plurality of environment-friendly data average values by the plurality of environment-friendly monitoring data subsets.
And forming an environment average data set by the plurality of environment-friendly data average values.
By the method, the environmental monitoring data are grouped, and if excessive data is input at one time, a load is caused to the computer. Therefore, the judgment is not accurate, so that the method of grouping and averaging each group is adopted, not only the data characteristics are kept, but also the data input is reduced, and the load of a computer is reduced.
By the method, the environmental protection monitoring data are obtained, and the discrete data of the environmental protection monitoring data are constructed into continuous curves according to different categories, so that the data can be better distinguished. A new environmental protection monitoring constant value and a new environmental protection range value in the curve are obtained based on the continuous environmental protection monitoring curve, and the new environmental protection monitoring constant value and the new environmental protection range value are used for calculation to limit judgment and can better judge. Meanwhile, after the environmental protection monitoring curve information is obtained, in order to reduce the load of a computer, the data is judged at fixed time intervals. The data are input into the LSTM neural network structure, under the influence of the range and the constant value obtained by the environment-friendly monitoring curve, the environment-friendly monitoring data in a plurality of time periods are judged, time information is considered by using the LSTM neural network structure, namely, integral information is considered, and the judgment is more accurate.
Example 2
Based on the above method for processing environmental monitoring data, the embodiment of the invention also provides a system for processing environmental monitoring data, wherein the system comprises an acquisition module, an enhancement module and a judgment module.
The acquisition module is used for acquiring a plurality of environmental protection monitoring data; the environmental protection monitoring data is detected environmental protection information.
The enhancement module is used for carrying out data processing based on the environmental protection monitoring data to obtain environmental protection enhancement data. The environmental enhancement data includes new environmental data and an environmental mean data set.
The judgment module is used for obtaining an environment-friendly judgment value through an environment data judgment model based on the environment-friendly enhanced data.
The environment-friendly judgment model comprises an environment-friendly neural network structure and an LSTM neural network structure.
Optionally, the processing the data based on the environmental protection monitoring data to obtain environmental protection enhancement data includes:
obtaining a plurality of environmental monitoring data; the environmental protection monitoring data is classified according to data types.
And obtaining a plurality of corresponding environment-friendly monitoring curves based on the plurality of environment-friendly monitoring data.
And obtaining a plurality of corresponding new environmental protection data based on the plurality of environmental protection monitoring curves. The new environmental data includes a new environmental monitoring constant value and a new environmental range value.
And obtaining a plurality of environmental protection enhancement data based on the plurality of environmental protection monitoring data and the plurality of new environmental protection data.
Optionally, obtaining new environmental protection data based on the environmental protection monitoring curve includes:
and obtaining a new environmental monitoring constant value based on the environmental monitoring curve. The new environmental monitoring constant value is the environmental monitoring data with the most occurrence times in the environmental monitoring curve.
And obtaining a plurality of environment protection extreme values based on the environment protection monitoring curve. The environmental protection extreme value represents environmental protection monitoring data of an extreme point in an environmental protection monitoring curve.
And obtaining a new environmental protection range value based on the plurality of environmental protection extreme values. The new environmental protection range value includes a new environmental protection minimum value and a new environmental protection maximum value. The new environmental protection maximum value is an environmental protection extreme value larger than other environmental protection extreme values. The new environmental minimum value is an environmental extreme value smaller than other environmental extreme values.
The specific manner in which the respective modules perform operations has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
An embodiment of the present invention further provides an electronic device, as shown in fig. 3, which includes a memory 504, a processor 502, and a computer program stored on the memory 504 and executable on the processor 502, where the processor 502 implements the steps of any one of the environmental protection monitoring data processing methods described above when executing the program.
Where in fig. 3 a bus architecture (represented by bus 500) is shown, bus 500 may include any number of interconnected buses and bridges, and bus 500 links together various circuits including one or more processors, represented by processor 502, and memory, represented by memory 504. The bus 500 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 505 provides an interface between the bus 500 and the receiver 501 and transmitter 503. The receiver 501 and the transmitter 503 may be the same element, i.e. a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 502 is responsible for managing the bus 500 and general processing, and the memory 504 may be used for storing data used by the processor 502 in performing operations.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of any one of the foregoing methods for processing environmental monitoring data, and the above mentioned data.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system is apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in an apparatus according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (10)
1. An environmental monitoring data processing method is characterized by comprising the following steps:
obtaining a plurality of environmental monitoring data; the environmental protection monitoring data is detected environmental protection information;
based on the environmental protection monitoring data, carrying out data processing to obtain environmental protection enhancement data; the environmental protection enhancement data comprises new environmental protection data and an environmental average data set;
obtaining an environmental protection judgment value through an environmental data judgment model based on the environmental protection enhancement data;
the environment-friendly judgment model comprises an environment-friendly neural network structure and an LSTM neural network structure.
2. The environmental monitoring data processing method of claim 1, wherein the training method of the environmental data judgment model comprises:
obtaining a training set; the training set comprises training environment-friendly enhanced data and marking data; the training environment-friendly enhancement data comprises training new environment-friendly data and a training environment average data set; the marking data is a marking judgment value; the marking judgment value indicates whether monitoring limitation is met;
obtaining a training environment-friendly judgment value through the environment data judgment model based on the training environment-friendly enhancement data; the environmental protection judgment value is 1, which represents a coincidence condition; the environmental protection judgment value is 0, which indicates that the condition is not met;
obtaining an environmental protection judgment loss value based on the training environmental protection judgment value and the labeled data;
obtaining the current training iteration times of an environment data judgment model and the preset maximum iteration times of the environment data judgment model training;
and stopping training when the environmental protection judgment loss value is less than or equal to a threshold value or the training iteration number reaches the maximum iteration number, so as to obtain a trained environmental data judgment model.
3. The environmental monitoring data processing method of claim 2, wherein the obtaining of the training environmental judgment value through the environmental data judgment model based on the training environmental enhancement data comprises:
inputting new training environment-friendly data and new training environment-friendly monitoring data in the training environment-friendly enhanced data into an environment-friendly neural network to obtain an output value of the environment-friendly neural network;
and inputting the output value of the environment-friendly neural network and the training environment-friendly monitoring data in the training environment-friendly enhanced data into an environment-friendly judgment model to obtain an environment-friendly judgment value.
4. The method for processing environmental protection monitoring data according to claim 3, wherein the step of inputting the environmental protection neural network output value and the training environmental protection monitoring data in the training environmental protection enhancement data into an environmental protection judgment model to obtain an environmental protection judgment value comprises:
obtaining first training environment-friendly monitoring data; the first training environmental protection monitoring data is a first value in the training environmental protection monitoring data;
inputting the first training environment-friendly monitoring data and the environment-friendly neural network output value into a first LSTM neural network to obtain a first LSTM output value;
obtaining second training environment-friendly monitoring data; the second training environmental protection monitoring data is a second value in the training environmental protection monitoring data;
inputting the second training environment-friendly monitoring data, the environment-friendly neural network output value and the first LSTM output value into a second LSTM neural network to obtain a second LSTM output value;
and inputting the training environment-friendly monitoring data and the output value of the environment-friendly neural network into the corresponding LSTM neural network for multiple times to obtain an environment-friendly judgment value.
5. The environmental monitoring data processing method of claim 1, wherein the processing the data based on the environmental monitoring data to obtain environmental enhancement data comprises:
obtaining an environment-friendly monitoring curve based on the environment-friendly monitoring data;
obtaining new environmental protection data based on the environmental protection monitoring curve; the new environmental protection data comprises a new environmental protection monitoring constant value and a new environmental protection range value;
and obtaining environmental protection enhancement data based on the environmental protection monitoring data and the new environmental protection data.
6. The environmental monitoring data processing method of claim 5, wherein obtaining new environmental data based on the environmental monitoring curve comprises:
obtaining a new environmental monitoring constant value based on the environmental monitoring curve; the new environmental monitoring constant value is environmental monitoring data with the most occurrence times in an environmental monitoring curve;
obtaining a plurality of environmental protection extreme values based on the environmental protection monitoring curve; the environmental protection extreme value represents environmental protection monitoring data of an extreme point in an environmental protection monitoring curve;
obtaining a new environmental protection range value based on the plurality of environmental protection extreme values; the new environmental protection range value comprises a new environmental protection minimum value and a new environmental protection maximum value; the new environmental protection maximum value is an environmental protection extreme value larger than other environmental protection extreme values; the new environmental minimum value is an environmental extreme value smaller than other environmental extreme values.
7. The environmental monitoring data processing method of claim 6, wherein the obtaining environmental enhancement data based on the environmental monitoring data and the new environmental data comprises:
obtaining a plurality of environmental monitoring data subsets; the environment-friendly monitoring data subset is environment-friendly monitoring data obtained by dividing the environment-friendly monitoring data according to a fixed time interval;
obtaining an environmental protection data average value based on the environmental protection monitoring data subset; a plurality of environment-friendly monitoring data subsets correspondingly obtain a plurality of environment-friendly data average values;
and forming an environment average data set by the plurality of environment-friendly data average values.
8. An environmental monitoring data processing system, comprising:
an acquisition module: obtaining a plurality of environmental monitoring data; the environmental protection monitoring data is detected environmental protection information;
a reinforcing module: based on the environmental protection monitoring data, carrying out data processing to obtain environmental protection enhancement data; the environmental enhancement data comprises new environmental data and an environmental average data set;
a judging module: obtaining an environmental protection judgment value through an environmental data judgment model based on the environmental protection enhancement data;
the environment-friendly judgment model comprises an environment-friendly neural network structure and an LSTM neural network structure.
9. The environmental monitoring data processing system of claim 8, wherein the processing of the data based on the environmental monitoring data to obtain environmental enhancement data comprises:
obtaining a plurality of environmental monitoring data; the environment-friendly monitoring data is classified according to data categories;
obtaining a plurality of corresponding environment-friendly monitoring curves based on the plurality of environment-friendly monitoring data;
obtaining a plurality of corresponding new environmental protection data based on the plurality of environmental protection monitoring curves; the new environmental protection data comprises a new environmental protection monitoring constant value and a new environmental protection range value;
and obtaining a plurality of environmental protection enhancement data based on the plurality of environmental protection monitoring data and the plurality of new environmental protection data.
10. The environmental monitoring data processing system of claim 9, wherein obtaining new environmental data based on the environmental monitoring curve comprises: with emphasis instead on the claims
Obtaining a new environmental monitoring constant value based on the environmental monitoring curve; the new environmental monitoring constant value is environmental monitoring data with the most occurrence times in an environmental monitoring curve;
obtaining a plurality of environment protection extreme values based on the environment protection monitoring curve; the environmental protection extreme value represents environmental protection monitoring data of an extreme point in an environmental protection monitoring curve;
obtaining a new environmental protection range value based on the plurality of environmental protection extreme values; the new environmental protection range value comprises a new environmental protection minimum value and a new environmental protection maximum value; the new environmental protection maximum value is an environmental protection extreme value larger than other environmental protection extreme values; the new environmental minimum value is an environmental extreme value smaller than other environmental extreme values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210622474.4A CN114997310A (en) | 2022-06-02 | 2022-06-02 | Environment-friendly monitoring data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210622474.4A CN114997310A (en) | 2022-06-02 | 2022-06-02 | Environment-friendly monitoring data processing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114997310A true CN114997310A (en) | 2022-09-02 |
Family
ID=83031069
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210622474.4A Pending CN114997310A (en) | 2022-06-02 | 2022-06-02 | Environment-friendly monitoring data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114997310A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115638831A (en) * | 2022-12-21 | 2023-01-24 | 四川九通智路科技有限公司 | Highway facility risk monitoring method and system based on MEMS sensor |
-
2022
- 2022-06-02 CN CN202210622474.4A patent/CN114997310A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115638831A (en) * | 2022-12-21 | 2023-01-24 | 四川九通智路科技有限公司 | Highway facility risk monitoring method and system based on MEMS sensor |
| CN115638831B (en) * | 2022-12-21 | 2023-04-25 | 四川九通智路科技有限公司 | Highway facility risk monitoring method and system based on MEMS sensor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114997310A (en) | Environment-friendly monitoring data processing method and system | |
| CN111775159A (en) | Ethical risk prevention method based on dynamic artificial intelligence ethical rules and robot | |
| CN111881243A (en) | Taxi track hotspot area analysis method and system | |
| CN114333317B (en) | Traffic event processing method and device, electronic equipment and storage medium | |
| CN112632179A (en) | Model construction method and device, storage medium and equipment | |
| CN113282000A (en) | Fault diagnosis method and device of data center and dynamic loop monitoring system | |
| CN116483623A (en) | Data storage system and storage equipment based on cloud computing | |
| CN110794308A (en) | Method and device for predicting train battery capacity | |
| CN111222968A (en) | Enterprise tax risk management and control method and system | |
| CN113032239A (en) | Risk prompting method and device, electronic equipment and storage medium | |
| CN111507269B (en) | Parking space state identification method and device, storage medium and electronic device | |
| CN115114124A (en) | Host risk assessment method and device | |
| CN116558574B (en) | Big data-based gas station safety monitoring method and device | |
| CN106682516A (en) | Detection method, detection device and server of application programs | |
| CN114493317A (en) | Intelligent acquisition and evaluation method and system based on enterprise environment | |
| CN115660451A (en) | Supplier risk early warning method, device, equipment and medium based on RPA | |
| CN111625720B (en) | Method, device, equipment and medium for determining execution strategy of data decision item | |
| CN114443738A (en) | Abnormal data mining method, device, equipment and medium | |
| CN110991659B (en) | Abnormal node identification method, device, electronic equipment and storage medium | |
| CN112949951A (en) | Data prediction method, data prediction device, electronic equipment and storage medium | |
| CN113552444A (en) | Online setting method and device for leakage current characteristic threshold | |
| CN111353553A (en) | Method and device for cleaning error labeling data, computer equipment and storage medium | |
| CN110955286A (en) | Poultry egg monitoring method and device | |
| CN112785075B (en) | Pedestrian behavior prediction method and system based on RFID positioning | |
| CN117349734B (en) | Water meter equipment identification method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |