CN116821636B - Internet of things data acquisition, analysis and management system based on big data - Google Patents
Internet of things data acquisition, analysis and management system based on big data Download PDFInfo
- Publication number
- CN116821636B CN116821636B CN202311103458.5A CN202311103458A CN116821636B CN 116821636 B CN116821636 B CN 116821636B CN 202311103458 A CN202311103458 A CN 202311103458A CN 116821636 B CN116821636 B CN 116821636B
- Authority
- CN
- China
- Prior art keywords
- data
- value
- target
- actual data
- internet
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 36
- 238000007405 data analysis Methods 0.000 claims abstract description 26
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 13
- 230000007613 environmental effect Effects 0.000 claims description 32
- 238000000034 method Methods 0.000 claims description 21
- 238000007726 management method Methods 0.000 claims description 12
- 238000013480 data collection Methods 0.000 claims description 6
- 238000013523 data management Methods 0.000 claims description 4
- 238000010191 image analysis Methods 0.000 claims description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 7
- 229910052757 nitrogen Inorganic materials 0.000 description 4
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- -1 pH value Chemical compound 0.000 description 1
- 239000013618 particulate matter Substances 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000012855 volatile organic compound Substances 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to a big data-based internet of things data acquisition, analysis and management system which comprises a historical data analysis module, an actual data acquisition module, a characteristic analysis module and an image establishment module, wherein the historical data analysis module is used for calculating an influence capacity value, the characteristic analysis module is used for calculating a characteristic value, and the image establishment module is used for establishing a characteristic image in a target area. Compared with the prior art, in the characteristic image established by the invention, different kinds of actual data are reflected through different color channels, then the gray value is obtained by combining the characteristic value reflecting the characteristics of the actual data and the influence capability value representing the kinds of the actual data through the pixel gray value environment state of the image, so that the characteristic image can keep the information contained in the actual data to the greatest extent. The subsequent analysis of the data only needs to adopt any existing trained image convolutional neural network, and a network architecture is not required to be designed independently.
Description
Technical Field
The invention relates to the technical field of data analysis of the Internet of things in the field of environmental protection, in particular to an Internet of things data acquisition, analysis and management system based on big data.
Background
In the environmental protection industry, big data analysis plays a vital role. The analysis process typically needs to be implemented by means of various intelligent algorithms. Among them, the convolutional neural network based on the image is one of the most widely used intelligent algorithms at present, and has been developed quite mature.
The image convolution neural network can be directly used for analyzing the image data, and can be applied to other types of data on the premise that the data can be expressed in the form of images. For example, when sound data needs to be analyzed, features of sound may be extracted and converted into feature images, and then the images may be deeply analyzed using an image-based convolutional neural network. The image convolutional neural network for analyzing the non-picture data is a WaveNet network, a SpecCNN network, a GAN network and the like.
However, current data analysis processes often require specialized designs for specific convolutional neural networks, which are quite cumbersome and increase the period of analysis. Therefore, a method for storing environmental data collected from the internet of things in the form of characteristic images is urgently needed to preserve information contained in the data, and meanwhile, an image convolutional neural network is not required to be specially designed in the subsequent data analysis, and an existing trained neural network model is adopted for analysis, so that a data analysis period is shortened, and the working efficiency is improved.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a data acquisition, analysis and management system of the internet of things based on big data, so as to solve the problem of how to store the environmental data collected from the internet of things in the form of characteristic images.
The invention provides an Internet of things data acquisition, analysis and management system based on big data, which comprises the following steps:
the system comprises a historical data analysis module, a data analysis module and a data analysis module, wherein the historical data analysis module is used for acquiring historical data of various Internet of things environmental data and obtaining an influence capability value of each Internet of things environmental data according to the historical data, and the Internet of things environmental data comprises a data value and a source coordinate;
the actual data acquisition module is used for acquiring actual data of various Internet of things environmental data in a target area within a target time period;
the characteristic analysis module is used for obtaining the characteristic value of each actual data on the source coordinates in the target time period according to the data value of the actual data;
the image establishing module is used for respectively corresponding each kind of actual data to one color channel, establishing pixels according to the source coordinates of the actual data and the position relation of the target area, and establishing characteristic images in the target area according to the characteristic values of each kind of actual data and the gray values of each pixel in each color channel corresponding to the characteristic values of the actual data.
Further, the method further comprises the following steps:
and the image analysis module is used for analyzing the characteristic images based on a preset image convolutional neural network to obtain analysis results.
Further, the obtaining the historical data of the plurality of internet of things environmental data and obtaining the influence capability value of each internet of things environmental data according to the historical data includes:
acquiring the environment data of the Internet of things of a target type, and at the same time, historical data in a target area;
establishing a coordinate-data value function of the historical data in the target area according to the data value and the source coordinate of the historical data;
and obtaining the influence capability value of the environment data of the Internet of things of the target type according to the average gradient of the coordinate-data value function.
Further, the establishing a coordinate-data value function of the history data in the target area according to the data value and the source coordinate of the history data includes:
obtaining source coordinates and corresponding data values of the discrete historical data in the target area according to the historical data;
and interpolating among the data values of the plurality of historical data based on the source coordinates of the historical data and the corresponding data values to obtain a continuous data value curved surface in the target area and obtain a coordinate-data value function in the target area.
Further, the influence capability value of the environment data of the internet of things of the target type is obtained by the following formula:
wherein,as the influence capability value of the environment data of the Internet of things of the target class, the method comprises the following steps of ++>Representing the coordinate-data value function in said target area A>Average gradient of>Is area element->Is the area of the target area a.
Further, the obtaining, according to the data value of the actual data, the characteristic value of each actual data on the source coordinate in the target time period includes:
acquiring the upper and lower value limits of the data value of the actual data of the target class;
acquiring a plurality of target data values of the actual data of the target type on target source coordinates in the target time period;
obtaining the characteristic value of the actual data of the target type on the target source coordinate in the target time period according to the following formula:
wherein,for the characteristic value of the actual data of the target species on the target source coordinates within the target time period, +.>For the total number of target data values within said target time period,/or->Numbering of the target data value within said target time period,/for>For the target time period, < th > on the target source coordinates>Target data value->Upper limit of the data value of the actual data of the target class,/for>And taking a lower limit for the data value of the actual data of the target class.
Further, the step of respectively corresponding each kind of actual data to one color channel, establishing a pixel according to the source coordinates of the actual data and the position relation of the target area, and establishing a characteristic image in the target area according to the characteristic value of each kind of actual data and the gray value of each pixel in each color channel corresponding to the influence capability value, includes:
dividing the target area into a plurality of grids with preset sizes, and respectively establishing a pixel for each grid;
obtaining an initial gray value of each pixel in a color channel corresponding to each actual data according to a grid where each source coordinate is located and a corresponding characteristic value in each actual data;
superposing the initial gray value of each pixel based on the influence capability value corresponding to each kind of actual data to obtain the gray value of each pixel in the color channel corresponding to each kind of actual data;
and superposing gray values of pixels at the same position in color channels corresponding to various actual data, and establishing a characteristic image in the target area.
Further, an initial gray value of the pixel corresponding to the target source coordinate is obtained by the following formula:
wherein,and in the color channel corresponding to the actual data of the target type, the initial gray value on the pixel corresponding to the target source coordinate.
Further, in the color channel corresponding to each actual data, the gray value of each pixel is obtained by the following formula:
wherein,in the color channel corresponding to the actual data of the target class, the coordinates are +.>Gray value of the pixel of +.>In the color channel corresponding to the actual data of the target class, the coordinates are +.>Is>For the set of all pixels +.>For the coordinates +.>Is +.>Euclidean distance between pixels of +.>In the color channel corresponding to the actual data of the target class, the coordinates are +.>Is used for the initial gray value of the pixel.
The beneficial effects of the invention are as follows:
the invention provides a big data-based internet of things data acquisition analysis management system, which is characterized in that historical data of various internet of things environment data are obtained through a historical data analysis module, influence capacity values of each internet of things environment data are obtained according to the historical data, the internet of things environment data comprise data values and source coordinates, then actual data of the various internet of things environment data in a target time period are obtained through an actual data acquisition module, then characteristic values of each actual data in source coordinates in the target time period are obtained through a characteristic analysis module according to the data values of the actual data, finally each actual data corresponds to a color channel through an image building module, pixels are built according to the position relation between the source coordinates of each actual data and the target area, gray values of each pixel in each color channel are obtained according to the characteristic values of each actual data and the corresponding influence capacity values, and a characteristic image in the target area is built. Compared with the prior art, in the characteristic image established by the invention, different kinds of actual data are reflected through different color channels, then the environment state represented by the actual data in each position in the target area is reflected through the pixel gray value of the image, and the gray value is obtained by combining the characteristic value reflecting the characteristic of the actual data and the influence capacity value representing the kind of the actual data, so that the established characteristic image can keep the information contained in the actual data to the greatest extent. The subsequent analysis of the data only needs to adopt any existing trained image convolutional neural network, a network architecture is not required to be designed independently, a large number of links of training and verification are saved, the period of data analysis is shortened greatly, and the working efficiency is improved.
Drawings
Fig. 1 is a system architecture diagram of an embodiment of a big data-based internet of things data acquisition analysis management system provided by the invention;
fig. 2 is a flowchart illustrating an implementation of an embodiment of a big data-based internet of things data collection analysis management system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, a specific embodiment of the present invention discloses a data collection, analysis and management system 100 of internet of things based on big data, including:
the historical data analysis module 110 is configured to obtain historical data of a plurality of types of internet of things environmental data, and obtain an influence capability value of each type of internet of things environmental data according to the historical data, where the internet of things environmental data includes a data value and a source coordinate;
the actual data obtaining module 120 is configured to obtain actual data in a target area of a plurality of types of internet of things environmental data within a target time period;
the feature analysis module 130 is configured to obtain, according to the data values of the actual data, a feature value of each actual data on the source coordinates in the target time period;
the image establishing module 140 is configured to respectively correspond each actual data to one color channel, establish pixels according to the source coordinates of the actual data and the position relationship of the target area, and establish the feature image in the target area according to the feature value of each actual data and the gray value of each pixel in each color channel corresponding to the feature value of each actual data and the corresponding influence capability value.
Compared with the prior art, in the characteristic image established by the invention, different kinds of actual data are reflected through different color channels, then the environment state represented by the actual data in each position in the target area is reflected through the pixel gray value of the image, and the gray value is obtained by combining the characteristic value reflecting the characteristic of the actual data and the influence capacity value representing the kind of the actual data, so that the established characteristic image can keep the information contained in the actual data to the greatest extent. The subsequent analysis of the data only needs to adopt any existing trained image convolutional neural network, a network architecture is not required to be designed independently, a large number of links of training and verification are saved, the period of data analysis is shortened greatly, and the working efficiency is improved.
It should be noted that, in the above process, the environmental data of the internet of things refers to data that can be collected by the device at a specific location (and the source coordinates) for the analysis environment in the environmental protection field, where the data content is the data value, for example:
air quality data: including particulate matter (PM 2.5, PM 10), harmful gases (sulfur dioxide, nitrogen oxides, ozone, etc.), volatile organic compounds, etc. These data are typically acquired by an air sensor.
Water quality data: comprises indexes such as dissolved oxygen, pH value, ammonia nitrogen, total phosphorus, total nitrogen and the like in water. Such data are typically obtained by water quality sensors or water sample collection analysis instruments.
Noise data: including ambient noise levels, spectral characteristics, etc. Such data is typically recorded by acoustic sensors or noise monitoring equipment.
In addition, the historical data in the process is the data which is acquired and stored before the method is operated, and the actual data is the data acquired at the current moment.
Obviously, the diffusion capacity of the pollution factor represented by the three data is different, and the influence capacity of the pollution factor on the surrounding environment is different, and the influence capacity value represents the influence capacity of the pollution factor represented by each data on the surrounding environment.
The characteristic value is a value of an environmental state of a corresponding pollution factor at a certain position, for example, the characteristic value of the environmental data of the internet of things, such as air quality, can be represented by the mean value, the peak value or the variance characteristic of a plurality of data values, so as to further describe the air quality state, and the characteristic value of the environmental data of the internet of things, such as noise, can be represented by the characteristics of the frequency, the phase and the like of the plurality of data values, so as to further describe the noise state.
When the image is built, the three data can be respectively corresponding to R, G, B color channels in the image, and gray values are built according to the characteristic values to represent the environment state, so that the finally superimposed characteristic image can contain the information of the three data.
Further, in a preferred embodiment, the big data based internet of things data collection, analysis and management system further includes:
and the image analysis module is used for analyzing the characteristic images based on a preset image convolutional neural network to obtain analysis results.
The process can be realized by adopting any existing preset image convolutional neural network, a plurality of characteristic images can be spliced to obtain the characteristic image of the complete area during analysis, and then partial areas in the characteristic image can be selected for analysis according to specific requirements.
In a preferred embodiment, in the historical data analysis module 110, the obtaining historical data of the plurality of environmental data of the internet of things, and obtaining the influence capability value of each environmental data of the internet of things according to the historical data specifically includes:
acquiring the environment data of the Internet of things of a target type, and at the same time, historical data in a target area;
establishing a coordinate-data value function of the historical data in the target area according to the data value and the source coordinate of the historical data;
and obtaining the influence capability value of the environment data of the Internet of things of the target type according to the average gradient of the coordinate-data value function.
In the above process, the influence capability of a factor is described by the change of the data value in the target area (and the average gradient of the coordinate-data value function), taking the internet of things environment data of the type that the content of a certain substance in the air is taken as an example, if the change gradient of the data value of the data in the target area is large, the content of the substance in the air can be considered to be large, and further the diffusion capability of the substance is considered to be poor, and the influence on the surrounding environment is small, so that the influence capability value is also small, and vice versa.
Specifically, the data needs to be preprocessed before the coordinate-data value function is obtained and the gradient calculated. In practice, the sensors for acquiring the data are all arranged in a discrete manner, so that the obtained data values and source coordinates are discrete, and therefore, in order to obtain a continuous complete coordinate-data value function, interpolation is needed according to the existing data to obtain a continuous complete coordinate-data value curve. Therefore, in a preferred embodiment, the establishing a coordinate-data value function of the history data in the target area according to the data value and the source coordinate of the history data in the above process specifically includes:
obtaining source coordinates and corresponding data values of the discrete historical data in the target area according to the historical data;
and interpolating among the data values of the plurality of historical data based on the source coordinates of the historical data and the corresponding data values to obtain a continuous data value curved surface in the target area and obtain a coordinate-data value function in the target area.
The values of discrete locations within a region can be serialized by interpolation. Interpolation is a functional approximation method based on known data points that uses the relationship between known data points to estimate the value of an unknown point. Common interpolation methods include linear interpolation, polynomial interpolation, and spline interpolation. The selection of an appropriate interpolation method depends on the particular application scenario. The linear interpolation is simple and quick, and is suitable for the condition of small data change; polynomial interpolation can more accurately approximate data, but is susceptible to the phenomenon of Runge; spline interpolation can overcome the limitation of polynomial interpolation and can generate a smooth curve.
Further, in a preferred embodiment, the influence capability value of the environmental data of the internet of things of the target class is obtained by the following formula:
wherein,an influence capability value of the environment data of the internet of things of the target type, A is the target area,representing the coordinate-data value function in said target area A>Average gradient of>Is area element->Is the area of the target area a.
The meaning of the above formula is that the average gradient of the coordinate-data value function is calculated, the average gradient is rounded and the reciprocal is taken to obtain the influence capability value, the larger the average gradient is, the larger the change of the data value is represented, the smaller the obtained influence capability value is, and further the influence capability of the factors corresponding to the data on the surrounding environment is represented to be smaller.
Further, in a preferred embodiment, in the feature analysis module 130, the obtaining, according to the data value of the actual data, the feature value of each actual data on the source coordinate in the target period specifically includes:
acquiring the upper and lower value limits of the data value of the actual data of the target class;
acquiring a plurality of target data values of the actual data of the target type on target source coordinates in the target time period;
obtaining the characteristic value of the actual data of the target type on the target source coordinate in the target time period according to the following formula:
wherein,for the characteristic value of the actual data of the target species on the target source coordinates within the target time period, +.>For the total number of target data values within said target time period,/or->Numbering of the target data value within said target time period,/for>For the target time period, < th > on the target source coordinates>Target data value->Upper limit of the data value of the actual data of the target class,/for>Data which is the actual data of the target classThe lower value limit of the value.
For example, ifRepresenting the +.o on the coordinates of the source of the object during the object time period>The data value of nitrogen content in the water collected again is>Is the maximum attainable nitrogen content in water, < >>Is the minimum achievable nitrogen content in the water.
In the above process, the characteristic value of the actual data in a period of time is represented by a characteristic value in a mean value obtaining manner, and the obtained characteristic value is a mean value of a proportionality coefficient and represents the degree that the environmental level represented by the actual data reaches a limit value. The method reserves the characteristic of the time dimension to a certain extent, can describe the environment characteristic, and is convenient for endowing gray values to each pixel. It will be appreciated that in practice, other existing methods may be selected to calculate the feature value according to specific requirements.
Further, in a preferred embodiment, in the image creating module 140, each of the actual data corresponds to a color channel, a pixel is created according to a positional relationship between a source coordinate of the actual data and the target area, a gray value of each pixel in each color channel is obtained according to a feature value of each of the actual data and a corresponding influence capability value, and a feature image in the target area is created, which specifically includes:
dividing the target area into a plurality of grids with preset sizes, and respectively establishing a pixel for each grid;
obtaining an initial gray value of each pixel in a color channel corresponding to each actual data according to a grid where each source coordinate is located and a corresponding characteristic value in each actual data;
superposing the initial gray value of each pixel based on the influence capability value corresponding to each kind of actual data to obtain the gray value of each pixel in the color channel corresponding to each kind of actual data;
and superposing gray values of pixels at the same position in color channels corresponding to various actual data, and establishing a characteristic image in the target area.
The above procedure takes into account not only the initial gray value of the pixel itself, but also the influence of surrounding pixels on it (i.e. also the influence of the surrounding environmental level on a certain location) when assigning a certain pixel gray value (representing the environmental level of a certain location). So that the established gray value can reflect the real situation most closely.
Further, in a preferred embodiment, the initial gray value of the pixel corresponding to the target source coordinate is obtained by the following formula:
wherein,and in the color channel corresponding to the actual data of the target type, the initial gray value on the pixel corresponding to the target source coordinate.
In the foregoing and in the description, E is a scaling factor, so that it can be directly multiplied by the gray level of the image at this time, so that the initial gray value can be obtained. However, the above procedure is only directed to the pixels corresponding to the source position in the actual data, and those pixels represented by the positions without data source can set the initial gray value to 0, and then perform the subsequent optimization.
Further, in a preferred embodiment, in the color channel corresponding to each actual data, the gray value of each pixel is obtained by the following formula:
wherein,in the color channel corresponding to the actual data of the target class, the coordinates are +.>Gray value of the pixel of +.>In the color channel corresponding to the actual data of the target class, the coordinates are +.>Is>For the set of all pixels +.>For the coordinates +.>Is +.>Euclidean distance between pixels of +.>In the color channel corresponding to the actual data of the target class, the coordinates are +.>Is used for the initial gray value of the pixel.
Since the gray value of one pixel in this embodiment needs to reflect the environmental characteristics within a period of time, the motion influence of each factor needs to be considered, so when the gray value of the target point is recalculated, the gray value of the target point needs to be obtained by combining the original gray value of the target point and the influence of the nearby pixels. This allows each of the resulting color channels to reflect the most realistic state. For example, although a detector at a certain position detects the smoke concentration at a certain position in a target time period, the detector cannot monitor the smoke spreading at other positions due to the limitation of the hardware level, so that the environment level of other positions nearby should be considered when calculating the gray value, and the correction is performed based on the influence capability value, so that the finally obtained characteristic image can reflect the environment level of a certain period of time, not the environment level at a moment.
The invention provides a big data-based internet of things data acquisition analysis management system, which is characterized in that historical data of various internet of things environment data are obtained through a historical data analysis module, influence capacity values of each internet of things environment data are obtained according to the historical data, the internet of things environment data comprise data values and source coordinates, then actual data of the various internet of things environment data in a target time period are obtained through an actual data acquisition module, then characteristic values of each actual data in source coordinates in the target time period are obtained through a characteristic analysis module according to the data values of the actual data, finally each actual data corresponds to a color channel through an image building module, pixels are built according to the position relation between the source coordinates of each actual data and the target area, gray values of each pixel in each color channel are obtained according to the characteristic values of each actual data and the corresponding influence capacity values, and a characteristic image in the target area is built. Compared with the prior art, in the characteristic image established by the invention, different kinds of actual data are reflected through different color channels, then the environment state represented by the actual data in each position in the target area is reflected through the pixel gray value of the image, and the gray value is obtained by combining the characteristic value reflecting the characteristic of the actual data and the influence capacity value representing the kind of the actual data, so that the established characteristic image can keep the information contained in the actual data to the greatest extent. The subsequent analysis of the data only needs to adopt any existing trained image convolutional neural network, a network architecture is not required to be designed independently, a large number of links of training and verification are saved, the period of data analysis is shortened greatly, and the working efficiency is improved.
It should be noted that, in the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described as different from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. The Internet of things data acquisition, analysis and management system based on big data is characterized by comprising:
the system comprises a historical data analysis module, a data analysis module and a data analysis module, wherein the historical data analysis module is used for acquiring historical data of various Internet of things environmental data and obtaining an influence capability value of each Internet of things environmental data according to the historical data, and the Internet of things environmental data comprises a data value and a source coordinate;
the actual data acquisition module is used for acquiring actual data of various Internet of things environmental data in a target area within a target time period;
the characteristic analysis module is used for obtaining the characteristic value of each actual data on the source coordinates in the target time period according to the data value of the actual data;
the image establishing module is used for respectively corresponding each kind of actual data to one color channel, establishing pixels according to the source coordinates of the actual data and the position relation of the target area, and establishing characteristic images in the target area according to the characteristic values of each kind of actual data and the gray values of each pixel in each color channel corresponding to the characteristic values of the actual data;
the method for obtaining the historical data of the plurality of Internet of things environmental data and obtaining the influence capability value of each Internet of things environmental data according to the historical data comprises the following steps:
acquiring the environment data of the Internet of things of a target type, and at the same time, historical data in a target area;
establishing a coordinate-data value function of the historical data in the target area according to the data value and the source coordinate of the historical data;
obtaining the influence capability value of the environment data of the Internet of things of the target type according to the average gradient of the coordinate-data value function;
the influence capability value of the environment data of the Internet of things of the target type is obtained by the following formula:
wherein,an influence capability value of the environment data of the internet of things of the target type, A is the target area,representing the coordinate-data value function in said target area A>Average gradient of>Is area element->Is the area of the target area a.
2. The big data based internet of things data collection analysis management system of claim 1, further comprising:
and the image analysis module is used for analyzing the characteristic images based on a preset image convolutional neural network to obtain analysis results.
3. The big data based internet of things data collection, analysis and management system according to claim 1, wherein the establishing a coordinate-data value function of the historical data in the target area according to the data value and the source coordinate of the historical data comprises:
obtaining source coordinates and corresponding data values of the discrete historical data in the target area according to the historical data;
and interpolating among the data values of the plurality of historical data based on the source coordinates of the historical data and the corresponding data values to obtain a continuous data value curved surface in the target area and obtain a coordinate-data value function in the target area.
4. The big data-based internet of things data acquisition, analysis and management system according to claim 1, wherein the obtaining, according to the data value of the actual data, the characteristic value of each actual data on the source coordinate in the target time period includes:
acquiring the upper and lower value limits of the data value of the actual data of the target class;
acquiring a plurality of target data values of the actual data of the target type on target source coordinates in the target time period;
obtaining the characteristic value of the actual data of the target type on the target source coordinate in the target time period according to the following formula:
wherein,for the target time period, the real object of the target categoryCharacteristic value of the inter-data on the coordinates of the target source,/->For the total number of target data values within said target time period,/or->Numbering of the target data value within said target time period,/for>For the target time period, < th > on the target source coordinates>Target data value->Upper limit of the data value of the actual data of the target class,/for>And taking a lower limit for the data value of the actual data of the target class.
5. The internet of things data collection, analysis and management system based on big data according to claim 4, wherein the step of respectively corresponding each kind of actual data to a color channel, establishing pixels according to the source coordinates of the actual data and the positional relationship of the target area, and establishing a characteristic image in the target area according to the characteristic value of each kind of actual data and the gray value of each pixel in each color channel corresponding to the influence capability value, includes:
dividing the target area into a plurality of grids with preset sizes, and respectively establishing a pixel for each grid;
obtaining an initial gray value of each pixel in a color channel corresponding to each actual data according to a grid where each source coordinate is located and a corresponding characteristic value in each actual data;
superposing the initial gray value of each pixel based on the influence capability value corresponding to each kind of actual data to obtain the gray value of each pixel in the color channel corresponding to each kind of actual data;
superposing gray values of pixels at the same positions in color channels corresponding to various actual data, and establishing a characteristic image in the target area;
in the color channel corresponding to each actual data, the gray value of each pixel is obtained by the following formula:
wherein,as the influence capability value of the environment data of the Internet of things of the target class, the method comprises the following steps of ++>In the color channel corresponding to the actual data of the target class, the coordinates are +.>Gray value of the pixel of +.>In the color channel corresponding to the actual data of the target class, the coordinates are +.>Is>For a set of all of the pixels,for the coordinates +.>Is +.>Euclidean distance between pixels of +.>In the color channel corresponding to the actual data of the target class, the coordinates are +.>Is used for the initial gray value of the pixel.
6. The big data-based internet of things data acquisition, analysis and management system according to claim 5, wherein the initial gray value of the pixel corresponding to the target source coordinate is obtained by the following formula:
wherein,and in the color channel corresponding to the actual data of the target type, the initial gray value on the pixel corresponding to the target source coordinate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311103458.5A CN116821636B (en) | 2023-08-30 | 2023-08-30 | Internet of things data acquisition, analysis and management system based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311103458.5A CN116821636B (en) | 2023-08-30 | 2023-08-30 | Internet of things data acquisition, analysis and management system based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116821636A CN116821636A (en) | 2023-09-29 |
CN116821636B true CN116821636B (en) | 2023-11-14 |
Family
ID=88120705
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311103458.5A Active CN116821636B (en) | 2023-08-30 | 2023-08-30 | Internet of things data acquisition, analysis and management system based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116821636B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006221374A (en) * | 2005-02-09 | 2006-08-24 | National Institute Of Advanced Industrial & Technology | Multi-band/multi-period multi-spectrum image data/sound conversion system |
WO2019114191A1 (en) * | 2017-12-14 | 2019-06-20 | 特斯联(北京)科技有限公司 | Internet of things-based building operation device status monitoring and visual analysis system |
CN110738360A (en) * | 2019-09-27 | 2020-01-31 | 华中科技大学 | equipment residual life prediction method and system |
CN111445110A (en) * | 2020-03-05 | 2020-07-24 | 深圳供电局有限公司 | Cable channel-based environmental risk decision method and device and computer equipment |
CN115599779A (en) * | 2022-11-28 | 2023-01-13 | 中南大学(Cn) | Urban road traffic missing data interpolation method and related equipment |
CN115661650A (en) * | 2022-10-28 | 2023-01-31 | 广东云钜网络科技有限公司 | Farm management system based on data monitoring of Internet of things |
CN115759460A (en) * | 2022-11-30 | 2023-03-07 | 重庆富民银行股份有限公司 | Method for predicting cooperation relationship between core enterprise and supplier based on convolutional neural network |
CN115829105A (en) * | 2022-11-24 | 2023-03-21 | 三峡大学 | Photovoltaic power prediction method based on historical data feature search |
CN116595121A (en) * | 2023-07-19 | 2023-08-15 | 北京国遥新天地信息技术股份有限公司 | Data display monitoring system based on remote sensing technology |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021228966A1 (en) * | 2020-05-14 | 2021-11-18 | Siemens Aktiengesellschaft | Method of converting time series data into an image |
US20220108424A1 (en) * | 2021-12-17 | 2022-04-07 | SenseBrain Technology Limited LLC | Method and device for image processing, and storage medium |
-
2023
- 2023-08-30 CN CN202311103458.5A patent/CN116821636B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006221374A (en) * | 2005-02-09 | 2006-08-24 | National Institute Of Advanced Industrial & Technology | Multi-band/multi-period multi-spectrum image data/sound conversion system |
WO2019114191A1 (en) * | 2017-12-14 | 2019-06-20 | 特斯联(北京)科技有限公司 | Internet of things-based building operation device status monitoring and visual analysis system |
CN110738360A (en) * | 2019-09-27 | 2020-01-31 | 华中科技大学 | equipment residual life prediction method and system |
CN111445110A (en) * | 2020-03-05 | 2020-07-24 | 深圳供电局有限公司 | Cable channel-based environmental risk decision method and device and computer equipment |
CN115661650A (en) * | 2022-10-28 | 2023-01-31 | 广东云钜网络科技有限公司 | Farm management system based on data monitoring of Internet of things |
CN115829105A (en) * | 2022-11-24 | 2023-03-21 | 三峡大学 | Photovoltaic power prediction method based on historical data feature search |
CN115599779A (en) * | 2022-11-28 | 2023-01-13 | 中南大学(Cn) | Urban road traffic missing data interpolation method and related equipment |
CN115759460A (en) * | 2022-11-30 | 2023-03-07 | 重庆富民银行股份有限公司 | Method for predicting cooperation relationship between core enterprise and supplier based on convolutional neural network |
CN116595121A (en) * | 2023-07-19 | 2023-08-15 | 北京国遥新天地信息技术股份有限公司 | Data display monitoring system based on remote sensing technology |
Non-Patent Citations (3)
Title |
---|
Artificial intelligence - enabled soft sensor and internet of things for sustainable agriculture using ensemble deep learning architecture;Anupong Wongchai 等;《ELSEVIER》;全文 * |
基于轻量级 CNN 的无人车转向控制研究;刘浩强 等;《控制工程》;全文 * |
都市圈资源环境承载能力监测预警方法探讨;伍磊 等;《中国会议》;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN116821636A (en) | 2023-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5764238B2 (en) | Steel pipe internal corrosion analysis apparatus and steel pipe internal corrosion analysis method | |
CN102509099B (en) | Detection method for image salient region | |
CN113344956B (en) | Ground feature contour extraction and classification method based on unmanned aerial vehicle aerial photography three-dimensional modeling | |
CN108550159B (en) | Flue gas concentration identification method based on image three-color segmentation | |
CN111815708B (en) | Service robot grabbing detection method based on dual-channel convolutional neural network | |
JP2021531571A (en) | Certificate image extraction method and terminal equipment | |
CN112101349A (en) | License plate sample generation method and device | |
CN115359431B (en) | Atmospheric environment pollution source pollution degree evaluation method and system | |
CN111597932A (en) | Road crack image identification method, device and system based on convolutional neural network | |
CN116821636B (en) | Internet of things data acquisition, analysis and management system based on big data | |
CN114519698A (en) | Equipment oil leakage detection method, device, equipment and storage medium in dark environment | |
CN114138868B (en) | Method and device for drawing air quality statistical distribution map | |
CN111476062A (en) | Lane line detection method and device, electronic equipment and driving system | |
CN116612438B (en) | Steam boiler combustion state real-time monitoring system based on thermal imaging | |
CN116343100B (en) | Target identification method and system based on self-supervision learning | |
CN111383219B (en) | Method and system for intelligently detecting cleanliness of aerial work platform equipment | |
CN110135274B (en) | Face recognition-based people flow statistics method | |
CN106462966B (en) | Method for identifying color block area in image and image processing device | |
CN116385288A (en) | Depth image restoration method and device and readable storage medium | |
CN115115891A (en) | Target detection model deployment application method based on embedded platform | |
CN111931658B (en) | Cooking fume identification method | |
CN116977190A (en) | Image processing method, apparatus, device, storage medium, and program product | |
CN110334657B (en) | Training sample generation method and system for fisheye distortion image and electronic equipment | |
CN111898525A (en) | Smoke recognition model construction method, smoke detection method and smoke detection device | |
CN111127535B (en) | Method and device for processing hand depth image |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |