Environmental detection and early warning method based on artificial intelligence and related equipment

Abstract

The present application proposes an artificial intelligence-based environmental detection and early warning method, device, electronic device and storage medium. The artificial intelligence-based environmental detection and early warning method includes: detecting the ecological environment based on the Internet of Things to obtain first classification data, and storing various types of data in the first classification data in isolation; dividing the first classification data based on a clustering algorithm to obtain second classification data, and storing various types of data in the second classification data jointly; regressing the second classification data based on preset environmental factors to obtain significant reference variables; calculating significant reference variables based on preset relationship formulas to obtain significant reference weights; constructing an ecological environment early warning model based on significant reference variables and significant reference weights; and evaluating the ecological environment based on the ecological environment early warning model to determine whether to issue early warning information. This method can obtain the specific degree of influence of various ecological environment factors on the ecological environment, thereby improving the accuracy of detecting the quality of the ecological environment.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based environmental detection and early warning method, device, electronic device and storage medium. Background Art

[0002] The use of Internet of Things technology can obtain a large amount of basic data, and applying Internet of Things technology to ecological environment testing can improve the quality and efficiency of environmental testing.

[0003] However, the ecological environment is complex and changeable, involving a variety of environmental factors that often interact with each other. Currently, the detected ecological environment data are generally stored in an isolated manner. There is no effective connection between different categories of environmental data, making it impossible to effectively obtain the specific impact of various environmental factors on the ecological environment, resulting in low accuracy in detecting ecological environment quality. Summary of the invention

[0004] In view of the above content, it is necessary to provide an artificial intelligence-based environmental detection and early warning method and related equipment to solve the technical problem of how to improve the accuracy of detecting ecological environment quality. The related equipment includes an artificial intelligence-based environmental detection and early warning device, electronic equipment and storage medium.

[0005] The present application embodiment provides an artificial intelligence-based environment detection and early warning method, including:

[0006] Detecting the ecological environment according to the Internet of Things to obtain first-category data, wherein each type of data in the first-category data is stored in isolation;

[0007] Dividing the first classified data according to a clustering algorithm to obtain second classified data, and storing the various types of data in the second classified data jointly;

[0008] Regressing the second classification data according to the preset environmental factors to obtain significant reference variables;

[0009] Calculating the significant reference variable according to a preset relationship to obtain a significant reference weight;

[0010] Constructing an ecological environment early warning model based on the significant reference variables and the significant reference weights;

[0011] The ecological environment is evaluated based on the ecological environment early warning model to determine whether to issue early warning information.

[0012] In the above-mentioned environmental detection and early warning method, the impact of each classification result on the ecological environment is calculated by obtaining ecological environment data and classifying the collected ecological environment data, and then an ecological environment early warning model is established to evaluate whether the current ecological environment is normal. In this way, the specific impact of various ecological environment factors on the ecological environment can be obtained, thereby improving the accuracy of detecting the quality of the ecological environment.

[0013] In some embodiments, detecting the ecological environment to obtain first classification data includes:

[0014] Detect the ecological environment based on the Internet of Things to obtain original detection data;

[0015] converting the raw detection data to obtain a communication data packet;

[0016] Parsing the communication data packet to obtain the original data packet;

[0017] The original data packets are classified and stored according to preset environmental factors to obtain first classification data.

[0018] In this way, the acquired raw detection data can be preliminarily classified according to preset environmental factors, that is, the raw detection data of the same environmental factor are classified into one category, and the raw detection data of different environmental factors are stored separately for easy storage and management. In addition, this process can perform preliminary automatic classification of the raw detection data without manual division, thereby effectively improving the classification efficiency.

[0019] In some embodiments, dividing the first classification data according to a clustering algorithm to obtain second classification data includes:

[0020] Establish a multi-dimensional space coordinate system;

[0021] matching the multi-dimensional space coordinate system and the first classified data to generate first classified data coordinates;

[0022] dividing the first classification data coordinates according to a clustering algorithm to obtain a classification data set;

[0023] The classified data sets are jointly stored based on the multi-dimensional space coordinate system to obtain the second classified data.

[0024] In this way, by establishing a multidimensional spatial coordinate system, data of different categories can coexist in the same spatial coordinate system, and connections are established between the isolated types of data in the first classification data, which makes it possible to classify the first classification data and further obtain the specific impact of various ecological and environmental factors on the environment on this basis.

[0025] In some embodiments, regressing the second classification data according to the preset environmental factors to obtain significant reference variables includes:

[0026] Establish a regression model based on the preset environmental factors;

[0027] regressing the second categorical data based on the regression model to obtain an initial reference variable;

[0028] The initial reference variables are screened to obtain the significant reference variables.

[0029] In this way, by calculating the second classification data, we can effectively screen out the effective indicators in the second classification data that can truly affect the ecological environment and reflect changes in the ecological environment, thereby improving the accuracy of the ecological environment early warning model constructed based on these effective indicators in assessing the ecological environment.

[0030] In some embodiments, calculating the significant reference variable according to a preset relationship to obtain a significant reference weight includes:

[0031] The significant reference variable is calculated to obtain a first reference weight, wherein the first reference weight satisfies the relationship:

[0032]

[0033] Among them, F ir represents the F statistic value of the rth significant reference variable in the i-th category of the second classification data, w ir A first reference weight representing the rth significant reference variable of the i-th category in the second classification data;

[0034] The significant reference variable is calculated based on the first reference weight and the second classification data to obtain the significant reference weight, and the significant reference weight satisfies the relationship:

[0035]

[0036] Among them, W r represents the significant reference weight of the rth significant reference variable in the second classification data, N i Represents the total number of data contained in the i-th category in the second classification data.

[0037] In this way, by using the F statistic value of the significant reference variable as the basis for allocating weights, we can obtain the specific impact of each significant reference variable that can truly affect the ecological environment on the environment, thereby improving the accuracy of the ecological environment assessment results in the subsequent process. The reason is that the larger the F statistic value, the greater the impact of the corresponding significant reference variable on the environment.

[0038] In some embodiments, the ecological environment early warning model is:

[0039]

[0040] Among them, P x represents the ecological environment assessment score corresponding to the ecological environment data detected for the xth time, P xr It represents the normalized value corresponding to the rth significant reference variable in the ecological environment data detected for the xth time, and c represents the total number of significant reference variables in the ecological environment data detected for the xth time.

[0041] In this way, by establishing an ecological environment early warning model, the specific situation of the ecological environment can be comprehensively evaluated according to each significant reference variable and the corresponding significant reference weight, which is convenient for staff to understand in real time whether the ecological environment is abnormal.

[0042] In some embodiments, evaluating the ecological environment based on the ecological environment early warning model to determine whether to issue early warning information includes:

[0043] Evaluate the ecological environment based on the ecological environment early warning model to obtain an evaluation result;

[0044] Whether to issue a warning message is determined based on the evaluation result and a preset threshold.

[0045] In this way, when environmental data is abnormal, management personnel can be notified in time to handle it, so as to ensure that all ecological environment data are within the normal range and prevent further environmental damage.

[0046] The embodiment of the present application also provides an artificial intelligence-based environment detection and early warning device, including:

[0047] An acquisition unit, configured to acquire first classification data according to the detection of the ecological environment by the Internet of Things, wherein each type of data in the first classification data is stored in isolation;

[0048] a classification unit, configured to divide the first classification data according to a clustering algorithm to obtain second classification data, wherein each type of data in the second classification data is jointly stored;

[0049] A regression unit, used for regressing the second classification data according to a preset environmental factor to obtain a significant reference variable;

[0050] A calculation unit, used for calculating the significant reference variable according to a preset relationship to obtain a significant reference weight;

[0051] A construction unit, used to construct an ecological environment early warning model according to the significant reference variables and the significant reference weights;

[0052] An evaluation unit is used to evaluate the ecological environment based on the ecological environment early warning model to determine whether to issue early warning information.

[0053] The present application also provides an electronic device, including:

[0054] a memory storing computer readable instructions; and

[0055] A processor executes computer-readable instructions stored in the memory to implement the artificial intelligence-based environment detection and early warning method.

[0056] An embodiment of the present application also provides a computer-readable storage medium, in which computer-readable instructions are stored. The computer-readable instructions are executed by a processor in an electronic device to implement the artificial intelligence-based environmental detection and early warning method. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of a preferred embodiment of the artificial intelligence-based environmental detection and early warning method involved in this application.

[0058] Figure 2 It is a flowchart of a preferred embodiment of the present application for detecting the ecological environment based on the Internet of Things to obtain the first classification data.

[0059] Figure 3 It is a flowchart of a preferred embodiment of the present application for dividing the first classification data according to a clustering algorithm to obtain second classification data.

[0060] Figure 4 It is a flowchart of a preferred embodiment of the present application for regressing the second classification data according to preset environmental factors to obtain significant reference variables.

[0061] Figure 5 It is a functional module diagram of a preferred embodiment of the artificial intelligence-based environment detection and early warning device involved in this application.

[0062] Figure 6 It is a structural schematic diagram of an electronic device of a preferred embodiment of the artificial intelligence-based environment detection and early warning method involved in this application.

[0063] Figure 7 It is the Euclidean distance data table involved in the embodiments of the present application. DETAILED DESCRIPTION

[0064] In order to more clearly understand the purpose, features and advantages of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other. In the following description, many specific details are set forth to facilitate a full understanding of the present application, and the embodiments described are only a part of the embodiments of the present application, rather than all of the embodiments.

[0065] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art to which the present application belongs. The terms used herein in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0067] The embodiment of the present application provides an artificial intelligence-based environmental detection and early warning method, which can be applied to one or more electronic devices. The electronic device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a programmable gate array (Field-Programmable Gate Array, FPGA), a digital processor (Digital Signal Processor, DSP), an embedded device, etc.

[0068] An electronic device can be any electronic product that can interact with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, etc.

[0069] The electronic device may also include a network device and / or a user device, wherein the network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of hosts or network servers based on cloud computing.

[0070] The network where the electronic device is located includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, virtual private network (VPN), etc.

[0071] like Figure 1FIG. 1 is a flowchart of a preferred embodiment of the artificial intelligence-based environment detection and early warning method of the present application. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

[0072] S10, detecting the ecological environment according to the Internet of Things to obtain first classification data, and each type of data in the first classification data is stored in isolation.

[0073] See also Figure 2 In an optional embodiment, detecting the ecological environment according to the Internet of Things to obtain the first classification data includes:

[0074] S101, detect the ecological environment based on the Internet of Things to obtain original detection data.

[0075] In this optional embodiment, the ecological environment can be a pre-selected and representative place, such as a residential area, a park, a lakeside, and a construction site, and the original detection data of various environmental factors in the ecological environment include but are not limited to: temperature data, air pressure data, carbon dioxide concentration data, air quality index data, and dust concentration data.

[0076] In this optional embodiment, since various environmental factors continue to change dynamically, a large number of original detection data of various environmental factors can be continuously detected at any data detection point. For ease of understanding, a group of data containing the original detection data of various environmental factors at any moment is called a data point.

[0077] In this optional embodiment, the Long Range Radio (LoRa) technology in the Internet of Things can be used with corresponding sensors to obtain data points at multiple data detection points in the current ecological environment, and the data points include the original detection data of each environmental factor corresponding to the data detection point. Among them, LoRa is a low-power LAN wireless standard, which has a longer transmission distance than other wireless methods at the same power consumption, achieving the unity of low power consumption and long distance. The sensors used include but are not limited to: temperature sensor, air pressure sensor, carbon dioxide concentration sensor, air quality index sensor, dust concentration sensor.

[0078] In this optional embodiment, LoRa modules are embedded in various sensors to detect raw detection data of environmental factors such as temperature and air pressure. The communication between the sensor nodes and the gateway is carried out through the wireless channel of the LoRa physical layer, and the connection between the gateway and the server is carried out through TCP / IP protocol communication. The main function of the gateway is to forward the data of the sensor nodes and the data of the server to each other.

[0079] S102, converting the original detection data to obtain a communication data packet.

[0080] In this optional embodiment, after the sensor node obtains the original detection data, it converts the original detection data into a data packet that can be communicated and transmitted.

[0081] S103, parsing the communication data packet to obtain an original data packet.

[0082] In this optional embodiment, the data packet is customized and parsed through the LoRa custom protocol parsing control to obtain the parsed original data packet.

[0083] S104, classifying and storing the original data packets according to preset environmental factors to obtain first classification data.

[0084] In this optional embodiment, intelligent search can be used to retrieve and classify the data in the original data packet according to the name of the environmental factor, and each classified data can be stored in isolation in an ecological environment database, where the ecological environment database can be a common database such as MySQL, Oracle, Access, etc.

[0085] In this optional embodiment, intelligent search is a new generation of search engine that combines artificial intelligence technology. In addition to providing traditional functions such as fast retrieval and relevance sorting, it can also provide functions such as user role registration, automatic identification of user interests, semantic understanding of content, intelligent information filtering and push, etc. Intelligent search's intelligent analysis of query conditions mainly includes:

[0086] Extract the effective components of the query conditions, including vocabulary and logical relations;

[0087] Obtain synonyms, antonyms and related words of keywords through the database.

[0088] For example, when a user searches for "temperature" in the original data packet through smart search, the smart search will retrieve all data about "temperature" in the original data packet. The retrieval process for other environmental factors is the same as that for the temperature factor. Ultimately, the original data packet is divided into five categories of data: temperature, air pressure, carbon dioxide concentration, air quality index, and dust concentration, and these five categories of data are used as the first classification data.

[0089] In this way, the acquired raw detection data can be preliminarily classified according to preset environmental factors, that is, the raw detection data of the same environmental factor are classified into one category, and the raw detection data of different environmental factors are stored separately for easy storage and management. In addition, this process can perform preliminary automatic classification of the raw detection data without manual division, thereby effectively improving the classification efficiency.

[0090] S11, dividing the first classification data according to a clustering algorithm to obtain second classification data, and storing the various types of data in the second classification data jointly.

[0091] See also Figure 3 In an optional embodiment, dividing the first classification data to obtain second classification data includes:

[0092] S111, establishing a multi-dimensional space coordinate system.

[0093] In this optional embodiment, a five-dimensional space coordinate system can be established based on the five categories in the first classification data, and the names of the coordinate axes correspond to the temperature, air pressure, carbon dioxide concentration, air quality index, and dust concentration in the original detection environment.

[0094] S112, matching the multi-dimensional space coordinate system and the first classified data to generate first classified data coordinates.

[0095] In this optional embodiment, the ecological environment may be detected based on the distribution position of each data point in the first classification data in the multi-dimensional space coordinate system to obtain the first classification data coordinates.

[0096] S113: Divide the first classification data coordinates according to a clustering algorithm to obtain a classification data set.

[0097] In an optional embodiment, a K-means clustering algorithm may be used to classify the data points in the first classification data to obtain classification data. The specific process is as follows:

[0098] a. Randomly select K samples from the original detection data points distributed in the multidimensional space coordinate system as cluster centers, K = 6 in the present invention;

[0099] b. Calculate the Euclidean distance from each data point to the six cluster centers;

[0100] c. Classify each data point into the category of the cluster center that is closest to its Euclidean distance;

[0101] d. Recalculate the centroids of the six data categories obtained, and repeat steps bc until the position of the newly obtained centroids no longer changes.

[0102] For ease of understanding and calculation, this application uses two-dimensional data as an example as follows:

[0103] Suppose there are data P1(0,0), P2(1,2), P3(3,1), P4(8,8), P5(9,10), P6(10,7), select K=2, first select P1 and P2 as cluster centers, and calculate the Euclidean distances between the remaining data and P1 and P2 respectively, as follows: Figure 7 The Euclidean distance data table is shown.

[0104] Since all the data are closer to P2, after reclassification, the first category is P1, and the second category is P2, P3, P4, P5, and P6. The centroid of each category is calculated respectively, and the classification is continued according to the Euclidean distance to obtain the first category as P1, P2, and P3, and the second category is P4, P5, and P6. The centroid of each category is calculated and classified according to the Euclidean distance. The first category is P1, P2, and P3, and the second category is P4, P5, and P6. At this time, the clustering no longer changes and ends.

[0105] In this optional embodiment, the six types of data obtained after clustering by the K-means clustering algorithm are used as the classification data set.

[0106] S114: jointly store the classified data set based on the multi-dimensional space coordinate system to obtain the second classified data.

[0107] In this optional embodiment, since each category of data in the classified data set contains the original detection data of various environmental factors, and the multidimensional space coordinate system can simultaneously represent the data of each category in the same multidimensional space coordinate system and jointly store them in the ecological environment database, there is no need to store them separately according to each category in the classified data set. Therefore, the classified data set jointly stored in the ecological environment database can be used as the second classified data.

[0108] In this way, by establishing a multidimensional spatial coordinate system, data of different categories can coexist in the same spatial coordinate system, and connections are established between the isolated types of data in the first classification data, which makes it possible to classify the first classification data and further obtain the specific impact of various ecological and environmental factors on the environment on this basis.

[0109] S12, regressing the second classification data according to the preset environmental factors to obtain significant reference variables.

[0110] See also Figure 4 In an optional embodiment, regressing the second classification data according to the preset environmental factors to obtain significant reference variables includes:

[0111] S121, establishing a regression model based on preset environmental factors.

[0112] In this optional embodiment, the environmental factors include multiple ones of air temperature, air pressure, carbon dioxide concentration, air quality index, and dust concentration.

[0113] In this optional embodiment, the five environmental factors are used as five reference variables, and S i represents the i-th category in the second classification data, y j is the distance from the jth data point in this category to the origin of the coordinate axis, x jkrepresents the kth reference variable in the jth data point, then the five reference variables are used as independent variables and are respectively jk Build regression model y j =α+βx jk +ε, where α and β are constant terms and ε is a random disturbance term, which conforms to the normal distribution.

[0114] S122: regressing the second categorical data based on the regression model to obtain an initial reference variable.

[0115] In this optional embodiment, according to S i The coordinates of each data point and the regression model are used to calculate the value of the F test statistic for each variable, denoted by F ik is the F statistic value of the kth variable in the ith category. The F test is also called a joint hypothesis test or a variance homogeneity test. It is a test that the statistic follows the F distribution under the null hypothesis. The test formula is F = MSR / MSE, where MSR is the mean square of the differences between categories and MSE is the mean square of the differences within categories. ik Is it greater than the critical value corresponding to the significant level value? The significant level value in this invention adopts the empirical value of 0.05, and the critical value Q can be obtained by looking up the F distribution critical value table according to the empirical value. If F ik >Q, then the F ik The corresponding independent variable is introduced into the regression model as the initial reference variable. At the same time, the remaining independent variables are introduced again into the obtained regression model, and it is determined whether the corresponding F statistic value is greater than the critical value corresponding to the significant level value until the F test is completed for all independent variables.

[0116] For example, take temperature as the independent variable, assume that the temperature data contained in ten data points P1, P2, ..., P10 is x = (51, 54, 52, 47, 63, 59, 55, 60, 57, 54), and the distance from each data point to the origin of the multidimensional space coordinate system is y = (162, 170, 166, 158, 174, 166, 167, 170, 173, 168). Substituting multiple sets of data into the regression model, the corresponding regression The model is y=-79.39+0.804x+ε (ε=0 during the calculation process). The average values ​​of x and y can be calculated to be 55.2 and 167.4 respectively, and the corresponding mean square errors are 199.6 and 210.4. Therefore, according to the formula of the F test, F=17.12 can be calculated. At the same time, the critical value of the F distribution critical value table is 5.32 by looking up the given empirical value of the significance level of 0.05. Since F>5.32, the temperature is used as the initial reference variable.

[0117] The process of judging whether the remaining reference variables are initial reference variables is the same as the process corresponding to judging the temperature.

[0118] S123, screening the initial reference variables to obtain the significant reference variables.

[0119] In this optional embodiment, the screening process is to select the initial reference variable with the largest F statistic value among all the initial reference variables, introduce the initial reference variable into the regression model, repeat the above process, and introduce the remaining independent variables into the obtained regression model again, so that the newly added independent variable has the largest F statistic value, repeat the above process until the F statistic value cannot be made larger by introducing the newly added independent variable, then take the initial reference variable existing in the model at this time as the significant reference variable, and suppose there are a total of c significant reference variables finally obtained.

[0120] Exemplarily, the initial reference variables are assumed to be temperature, air pressure, and air quality index. Among the initial reference variables, the F statistic corresponding to the temperature is the largest. The temperature is introduced into the regression model, and then the air pressure is introduced into the regression model. After calculation, a new F statistic value of 18.53 can be obtained. Since the F statistic value obtained when the temperature is used as an independent variable in the previous example is 17.12, and 18.53>17.12, the air pressure is also introduced into the regression model as an initial reference variable. If the F statistic value calculated by introducing the air quality index as an independent variable in the obtained regression model is not greater than 18.53, the significant reference variables finally obtained are temperature and air pressure.

[0121] In this way, by calculating the second classification data, we can effectively screen out the effective indicators in the second classification data that can truly affect the ecological environment and reflect changes in the ecological environment, thereby improving the accuracy of the ecological environment early warning model constructed based on these effective indicators in assessing the ecological environment.

[0122] S13, calculating the significant reference variables according to a preset relationship to obtain the significant reference weights.

[0123] In an optional embodiment, calculating the significant reference variable according to a preset relationship to obtain the significant reference weight includes:

[0124] S131, calculating the significant reference variable according to a preset relationship to obtain a first reference weight.

[0125] In an optional embodiment, the first reference weight satisfies the relationship:

[0126]

[0127] Among them, F ir represents the F statistic value of the rth significant reference variable in the i-th category of the second classification data, w irRepresents a first reference weight of the rth significant reference variable of the ith category in the second categorical data.

[0128] For example, let category S i There are two significant reference variables in total, namely significant reference variable 1 and significant reference variable 2, and the corresponding F statistics are F i1 =0.08, F i2 =0.12, then the first reference weights corresponding to the two significant reference variables are w i1 =0.08 / 0.2=0.4,w i2 =0.12 / 0.2=0.6.

[0129] S132: Calculate the significant reference variable based on the first reference weight and the second classification data to obtain the significant reference weight.

[0130] In an optional embodiment, the significant reference weight satisfies the relationship:

[0131]

[0132] Among them, W r represents the significant reference weight of the rth significant reference variable in the second classification data, N i Represents the total number of data points contained in the i-th category in the second classification data.

[0133] Exemplarily, assuming that the total number of data points contained in each category is N1=100, N2=200, N3=300, N4=400, N5=200, N6=300, wherein categories S1 and S3 contain significant reference variable 1, and the first reference weight values ​​of significant reference variable 1 in categories S1 and S3 are 0.4 and 0.6 respectively, then the significant reference weight of significant reference variable 1 is:

[0134]

[0135] In this way, by using the F statistic value of the significant reference variable as the basis for allocating weights, we can obtain the specific impact of each significant reference variable that can truly affect the ecological environment on the environment, thereby improving the accuracy of the ecological environment assessment results in the subsequent process. The reason is that the larger the F statistic value, the greater the impact of the corresponding significant reference variable on the environment.

[0136] S14. Construct an ecological environment early warning model based on significant reference variables and significant reference weights.

[0137] In an optional embodiment, the ecological environment early warning model is:

[0138]

[0139] Among them, P x represents the ecological environment assessment score corresponding to the ecological environment data detected for the xth time, P xr It represents the normalized value corresponding to the rth significant reference variable in the ecological environment data detected for the xth time, and c represents the total number of significant reference variables in the ecological environment data detected for the xth time.

[0140] For example, suppose that there are three significant reference variables in the ecological environment data obtained from the fifth ecological environment detection, namely temperature, air pressure, and air quality index, and the corresponding normalized values ​​are P 51 =0.3, P 52 =0.5, P 53 =0.6, the significant reference weights corresponding to the three significant reference variables are W1=0.5, W2=0.3, W2=0.1, then the final ecological environment assessment score detected for the fifth time is P5=0.3·0.5+0.5·0.3+0.6·0.1=0.36.

[0141] In this optional embodiment, the normalized values ​​corresponding to each significant reference variable are obtained by a linear function normalization method, and the normalization formula is:

[0142]

[0143] where Xk norm represents the normalized data of the kth significant reference variable, Xk represents the original detection data of the kth significant reference variable, Xk max ,Xk min They represent the maximum and minimum values ​​in the original detection data of the kth significant reference variable, respectively.

[0144] For example, assume that the original temperature detection data currently detected is 20°, 30°, and 40°, where the highest temperature value is 40 and the lowest temperature value is 20. Therefore, the normalized value corresponding to the temperature of 30° is (30-20) / (40-20)=0.5.

[0145] In this way, by establishing an ecological environment early warning model, the specific situation of the ecological environment can be comprehensively evaluated according to each significant reference variable and the corresponding significant reference weight, which is convenient for staff to understand in real time whether the ecological environment is abnormal.

[0146] S15, evaluating the ecological environment based on the ecological environment early warning model to determine whether to issue early warning information.

[0147] In an optional embodiment, evaluating the ecological environment based on the ecological environment early warning model to determine whether to issue early warning information includes:

[0148] S151, evaluating the ecological environment based on the ecological environment early warning model to obtain an evaluation result.

[0149] In this optional embodiment, the normalized value of the original detection data corresponding to the acquired significant reference variable is brought into the ecological environment early warning model to calculate the corresponding evaluation result.

[0150] S152: Determine whether to issue a warning message based on the evaluation result and a preset threshold.

[0151] In this optional embodiment, the preset threshold value can be 0.1. When the evaluation result is less than 0.1, it means that the ecological environment is below the normal standard and an early warning message needs to be issued to notify the management personnel to handle it. When the evaluation result is greater than or equal to 0.1, it means that the ecological environment data is normal and no early warning message needs to be issued.

[0152] In this way, when environmental data is abnormal, management personnel can be notified in time to handle it, so as to ensure that all ecological environment data are within the normal range and prevent further environmental damage.

[0153] like Figure 5 , which is a functional module diagram of a preferred embodiment of an artificial intelligence-based environment detection and early warning device provided in an embodiment of the present application. The artificial intelligence-based environment detection and early warning device 11 includes an acquisition unit 110, a classification unit 111, a regression unit 112, a calculation unit 113, a construction unit 114, and an evaluation unit 115. The module / unit referred to in this application refers to a series of computer program segments that can be executed by the processor 13 and can complete fixed functions, which are stored in the memory 12. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0154] In an optional embodiment, the acquisition unit 110 is used to acquire the first classification data based on detecting the ecological environment of the Internet of Things.

[0155] In this optional embodiment, detecting the ecological environment according to the Internet of Things to obtain the first classification data includes:

[0156] Detect the ecological environment based on the Internet of Things to obtain original detection data;

[0157] converting the raw detection data to obtain a communication data packet;

[0158] Parsing the original detection communication data packet to obtain the original data packet;

[0159] The original data packets are classified and stored according to preset environmental factors to obtain first classification data.

[0160] In this optional embodiment, the ecological environment can be a pre-selected and representative place, such as a residential area, a park, a lakeside, and a construction site, and the original detection data of various environmental factors in the ecological environment include but are not limited to: temperature data, air pressure data, carbon dioxide concentration data, air quality index data, and dust concentration data.

[0161] In this optional embodiment, since various environmental factors continue to change dynamically, a large number of original detection data of various environmental factors can be continuously detected at any data detection point. For ease of understanding, a group of data containing the original detection data of various environmental factors at any moment is called a data point.

[0162] In this optional embodiment, the Long Range Radio (LoRa) technology in the Internet of Things can be used with corresponding sensors to obtain data points at multiple data detection points in the current ecological environment, and the data points include the original detection data of each environmental factor corresponding to the data detection point. Among them, LoRa is a low-power LAN wireless standard, which has a longer transmission distance than other wireless methods at the same power consumption, achieving the unity of low power consumption and long distance. The sensors used include but are not limited to: temperature sensor, air pressure sensor, carbon dioxide concentration sensor, air quality index sensor, dust concentration sensor.

[0163] In this optional embodiment, LoRa modules are embedded in various sensors to detect raw detection data of environmental factors such as temperature and air pressure. The communication between the sensor nodes and the gateway is carried out through the wireless channel of the LoRa physical layer, and the connection between the gateway and the server is carried out through TCP / IP protocol communication. The main function of the gateway is to forward the data of the sensor nodes and the data of the server to each other.

[0164] In this optional embodiment, after the sensor node obtains the original detection data, it converts the original detection data into a data packet that can be transmitted for communication, and then performs custom parsing on the data packet through the LoRa custom protocol parsing control to obtain the parsed original data packet.

[0165] In this optional embodiment, intelligent search can be used to retrieve and classify the data in the original data packet according to the name of the environmental factor, and each classified data can be stored in isolation in an ecological environment database, where the ecological environment database can be a common database such as MySQL, Oracle, Access, etc.

[0166] In this optional embodiment, intelligent search is a new generation of search engine that combines artificial intelligence technology. In addition to providing traditional functions such as fast retrieval and relevance sorting, it can also provide functions such as user role registration, automatic identification of user interests, semantic understanding of content, intelligent information filtering and push, etc. Intelligent search's intelligent analysis of query conditions mainly includes:

[0167] Extract the effective components of the query conditions, including vocabulary and logical relations;

[0168] Obtain synonyms, antonyms and related words of keywords through the database.

[0169] For example, when a user searches for "temperature" in the original data packet through smart search, the smart search will retrieve all data about "temperature" in the original data packet. The retrieval process for other environmental factors is the same as that for the temperature factor. Ultimately, the original data packet is divided into five categories of data: temperature, air pressure, carbon dioxide concentration, air quality index, and dust concentration, and these five categories of data are used as the first classification data.

[0170] In an optional embodiment, the classification unit 111 is configured to divide the first classification data according to a clustering algorithm to obtain second classification data.

[0171] In this optional embodiment, dividing the first classification data according to a clustering algorithm to obtain second classification data includes:

[0172] Establish a multi-dimensional space coordinate system;

[0173] matching the multi-dimensional space coordinate system and the first classified data to generate first classified data coordinates;

[0174] dividing the first classification data coordinates according to a clustering algorithm to obtain a classification data set;

[0175] The classified data sets are jointly stored based on the multi-dimensional space coordinate system to obtain the second classified data.

[0176] In this optional embodiment, a five-dimensional space coordinate system can be established based on the five categories in the first classification data, and the names of the coordinate axes correspond to the temperature, air pressure, carbon dioxide concentration, air quality index, and dust concentration in the original detection environment.

[0177] In this optional embodiment, the ecological environment may be detected based on the distribution position of each data point in the first classification data in the multi-dimensional space coordinate system to obtain the first classification data coordinates.

[0178] In an optional embodiment, a K-means clustering algorithm may be used to classify the data points in the first classification data to obtain classification data. The specific process is as follows:

[0179] a. Randomly select K samples from the original detection data points distributed in the multidimensional space coordinate system

[0180] is the cluster center, K=6 in the present invention;

[0181] b. Calculate the Euclidean distance from each data point to the six cluster centers;

[0182] c. Classify each data point into the category of the cluster center that is closest to its Euclidean distance;

[0183] d. Recalculate the centroids of the six data categories obtained, and repeat steps bc until the position of the newly obtained centroids no longer changes.

[0184] For ease of understanding and calculation, this application uses two-dimensional data as an example as follows:

[0185] Suppose there are data P1(0,0), P2(1,2), P3(3,1), P4(8,8), P5(9,10), P6(10,7), select K=2, first select P1 and P2 as cluster centers, and calculate the Euclidean distances between the remaining data and P1 and P2 respectively, as follows: Figure 7 The Euclidean distance data table is shown.

[0186] Since all the data are closer to P2, after reclassification, the first category is P1, and the second category is P2, P3, P4, P5, and P6. The centroid of each category is calculated respectively, and the classification is continued according to the Euclidean distance to obtain the first category as P1, P2, and P3, and the second category is P4, P5, and P6. The centroid of each category is calculated and classified according to the Euclidean distance. The first category is P1, P2, and P3, and the second category is P4, P5, and P6. At this time, the clustering no longer changes and ends.

[0187] In this optional embodiment, the six types of data obtained after clustering by the K-means clustering algorithm are used as the classification data set.

[0188] In this optional embodiment, since each category of data in the classified data set contains the original detection data of various environmental factors, and the multidimensional space coordinate system can simultaneously represent the data of each category in the same multidimensional space coordinate system and jointly store them in the ecological environment database, there is no need to store them separately according to each category in the classified data set. Therefore, the classified data set jointly stored in the ecological environment database can be used as the second classified data.

[0189] In an optional embodiment, the regression unit 112 is used to regress the second classification data according to preset environmental factors to obtain significant reference variables.

[0190] In this optional embodiment, regressing the second classification data according to the preset environmental factors to obtain significant reference variables includes:

[0191] Establish a regression model based on the preset environmental factors;

[0192] regressing the second categorical data based on the regression model to obtain an initial reference variable;

[0193] The initial reference variables are screened to obtain the significant reference variables.

[0194] In this optional embodiment, the environmental factors include multiple ones of air temperature, air pressure, carbon dioxide concentration, air quality index, and dust concentration.

[0195] In this optional embodiment, the five environmental factors are used as five reference variables, and S i represents the i-th category in the second classification data, y j is the distance from the jth data point in this category to the origin of the coordinate axis, x jk represents the kth reference variable in the jth data point, then the five reference variables are used as independent variables and are respectively jk Build regression model y j =α+βx jk +ε, where α and β are constant terms and ε is a random disturbance term, which conforms to the normal distribution.

[0196] In this optional embodiment, according to S i The coordinates of each data point and the regression model are used to calculate the value of the F test statistic for each variable, denoted by F ik is the F statistic value of the kth variable in the ith category. The F test is also called a joint hypothesis test or a variance homogeneity test. It is a test that the statistic follows the F distribution under the null hypothesis. The test formula is F = MSR / MSE, where MSR is the mean square of the differences between categories and MSE is the mean square of the differences within categories. ik Is it greater than the critical value corresponding to the significant level value? The significant level value in this invention adopts the empirical value of 0.05, and the critical value Q can be obtained by looking up the F distribution critical value table according to the empirical value. If F ik >Q, then the F ik The corresponding independent variable is introduced into the regression model as the initial reference variable. At the same time, the remaining independent variables are introduced again into the obtained regression model, and it is determined whether the corresponding F statistic value is greater than the critical value corresponding to the significant level value until the F test is completed for all independent variables.

[0197] For example, take temperature as the independent variable, assume that the temperature data contained in ten data points P1, P2, ..., P10 is x = (51, 54, 52, 47, 63, 59, 55, 60, 57, 54), and the distance from each data point to the origin of the multidimensional space coordinate system is y = (162, 170, 166, 158, 174, 166, 167, 170, 173, 168). Substituting multiple sets of data into the regression model, the corresponding regression The model is y=-79.39+0.804x+ε (ε=0 during the calculation process). The average values ​​of x and y can be calculated to be 55.2 and 167.4 respectively, and the corresponding mean square errors are 199.6 and 210.4. Therefore, according to the formula of the F test, F=17.12 can be calculated. At the same time, the critical value of the F distribution critical value table is 5.32 by looking up the given empirical value of the significance level of 0.05. Since F>5.32, the temperature is used as the initial reference variable.

[0198] The process of judging whether the remaining reference variables are initial reference variables is the same as the process of judging temperature.

[0199] In this optional embodiment, the screening process is to select the initial reference variable with the largest F statistic value among all the initial reference variables, introduce the initial reference variable into the regression model, repeat the above process, and introduce the remaining independent variables into the obtained regression model again, so that the newly added independent variable has the largest F statistic value, repeat the above process until the F statistic value cannot be made larger by introducing the newly added independent variable, then take the initial reference variable existing in the model at this time as the significant reference variable, and suppose there are a total of c significant reference variables finally obtained.

[0200] Exemplarily, the initial reference variables are assumed to be temperature, air pressure, and air quality index. Among the initial reference variables, the F statistic corresponding to the temperature is the largest. The temperature is introduced into the regression model, and then the air pressure is introduced into the regression model. After calculation, a new F statistic value of 18.53 can be obtained. Since the F statistic value obtained when the temperature is used as an independent variable in the previous example is 17.12, and 18.53>17.12, the air pressure is also introduced into the regression model as an initial reference variable. If the F statistic value calculated by introducing the air quality index as an independent variable in the obtained regression model is not greater than 18.53, the significant reference variables finally obtained are temperature and air pressure.

[0201] In an optional embodiment, the calculation unit 113 is used to calculate the significant reference variable according to a preset relationship to obtain a significant reference weight.

[0202] In this optional embodiment, calculating the significant reference variable according to a preset relationship to obtain the significant reference weight includes:

[0203] Calculating the significant reference variable according to a preset relationship to obtain a first reference weight;

[0204] The significant reference variable is calculated based on the first reference weight and the second classification data to obtain the significant reference weight.

[0205] In an optional embodiment, the first reference weight satisfies the relationship:

[0206]

[0207] where F ir represents the F statistic value of the rth significant reference variable in the i-th category of the second classification data, w ir Represents a first reference weight of the rth significant reference variable of the ith category in the second categorical data.

[0208] For example, let category S i There are two significant reference variables in total, namely significant reference variable 1 and significant reference variable 2, and the corresponding F statistics are F i1 =0.08, F i2 =0.12, then the first reference weights corresponding to the two significant reference variables are w i1 =0.08 / 0.2=0.4,w i2 =0.12 / 0.2=0.6.

[0209] In an optional embodiment, the significant reference weight satisfies the relationship:

[0210]

[0211] Among them, W r represents the significant reference weight of the rth significant reference variable in the second classification data, N i Represents the total number of data points contained in the i-th category in the second classification data.

[0212] Exemplarily, assuming that the total number of data points contained in each category is N1=100, N2=200, N3=300, N4=400, N5=200, N6=300, wherein categories S1 and S3 contain significant reference variable 1, and the first reference weight values ​​of significant reference variable 1 in categories S1 and S3 are 0.4 and 0.6 respectively, then the significant reference weight of significant reference variable 1 is:

[0213]

[0214] In an optional embodiment, the construction unit 114 is used to construct an ecological environment early warning model according to the significant reference variables and the significant reference weights.

[0215] In an optional embodiment, the ecological environment early warning model is:

[0216]

[0217] Among them, P x represents the ecological environment assessment score corresponding to the ecological environment data detected for the xth time, P xr It represents the normalized value corresponding to the rth significant reference variable in the ecological environment data detected for the xth time, and c represents the total number of significant reference variables in the ecological environment data detected for the xth time.

[0218] For example, suppose that there are three significant reference variables in the ecological environment data obtained from the fifth ecological environment detection, namely temperature, air pressure, and air quality index, and the corresponding normalized values ​​are P 51 =0.3, P 52 =0.5, P 53 =0.6, the significant reference weights corresponding to the three significant reference variables are W1=0.5, W2=0.3, W2=0.1, then the final ecological environment assessment score detected for the fifth time is P5=0.3·0.5+0.5·0.3+0.6·0.1=0.36.

[0219] In this optional embodiment, the normalized values ​​corresponding to each significant reference variable are obtained by a linear function normalization method, and the normalization formula is:

[0220]

[0221] where Xk norm represents the normalized data of the kth significant reference variable, Xk represents the original detection data of the kth significant reference variable, Xk max ,Xk min They represent the maximum and minimum values ​​in the original detection data of the kth significant reference variable, respectively.

[0222] For example, assume that the original temperature detection data currently detected is 20°, 30°, and 40°, where the highest temperature value is 40 and the lowest temperature value is 20. Therefore, the normalized value corresponding to the temperature of 30° is (30-20) / (40-20)=0.5.

[0223] In an optional embodiment, the evaluation unit 115 is used to evaluate the ecological environment based on the ecological environment early warning model to determine whether to issue early warning information.

[0224] In this optional embodiment, evaluating the ecological environment based on the ecological environment early warning model to determine whether to issue early warning information includes:

[0225] Evaluate the ecological environment based on the ecological environment early warning model to obtain an evaluation result;

[0226] Whether to issue a warning message is determined based on the evaluation result and a preset threshold.

[0227] In this optional embodiment, the normalized value of the original detection data corresponding to the acquired significant reference variable is brought into the ecological environment early warning model to calculate the corresponding evaluation result.

[0228] In this optional embodiment, the preset threshold value can be 0.1. When the evaluation result is less than 0.1, it means that the ecological environment is below the normal standard and an early warning message needs to be issued to notify the management personnel to handle it. When the evaluation result is greater than or equal to 0.1, it means that the ecological environment data is normal and no early warning message needs to be issued.

[0229] The above-mentioned AI-based environmental detection and early warning method detects ecological environment data through sensors, transmits and collects data based on the Internet of Things, and then classifies the collected ecological environment historical data, analyzes and calculates the impact of each classification result on the ecological environment, and then establishes an ecological environment early warning model to evaluate whether the current ecological environment is normal. In this way, the specific impact of various ecological environment factors on the ecological environment can be obtained, thereby improving the accuracy of detecting the quality of the ecological environment.

[0230] like Figure 6 , which is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 1 includes a memory 12 and a processor 13. The memory 12 is used to store computer-readable instructions, and the processor 13 executes the computer-readable instructions stored in the memory to implement the artificial intelligence-based environment detection and early warning method of any of the above embodiments.

[0231] In an optional embodiment, the electronic device 1 further includes a bus, a computer program stored in the memory 12 and executable on the processor 13, such as an artificial intelligence-based environment detection and early warning program.

[0232] Figure 6 Only the electronic device 1 having components 12-13 is shown, and those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0233] Combination Figure 1The memory 12 in the electronic device 1 stores a plurality of computer-readable instructions to implement an artificial intelligence-based environment detection and early warning method, and the processor 13 can execute the plurality of instructions to implement:

[0234] Detecting the ecological environment according to the Internet of Things to obtain first-category data, wherein each type of data in the first-category data is stored in isolation;

[0235] Dividing the first classified data according to a clustering algorithm to obtain second classified data, and storing the various types of data in the second classified data jointly;

[0236] Regressing the second classification data according to the preset environmental factors to obtain significant reference variables;

[0237] Calculating the significant reference variable according to a preset relationship to obtain a significant reference weight;

[0238] Constructing an ecological environment early warning model based on the significant reference variables and the significant reference weights;

[0239] The ecological environment is evaluated based on the ecological environment early warning model to determine whether to issue early warning information.

[0240] Specifically, the specific implementation method of the processor 13 for the above instructions can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0241] Those skilled in the art will appreciate that the schematic diagram is merely an example of the electronic device 1 and does not constitute a limitation on the electronic device 1. The electronic device 1 may have either a bus structure or a star structure. The electronic device 1 may also include more or less other hardware or software than shown in the diagram, or a different arrangement of components. For example, the electronic device 1 may also include input and output devices, network access devices, etc.

[0242] It should be noted that the electronic device 1 is only an example, and other existing or future electronic products that are suitable for the present application should also be included in the protection scope of the present application and included here by reference.

[0243] Among them, the memory 12 includes at least one type of readable storage medium, and the readable storage medium can be non-volatile or volatile. The readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 12 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. The memory 12 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the environment detection and early warning program based on artificial intelligence, but also can be used to temporarily store data that has been output or is to be output.

[0244] In some embodiments, the processor 13 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 13 is the control core (Control Unit) of the electronic device 1, and uses various interfaces and lines to connect the various components of the entire electronic device 1, and executes or executes programs or modules stored in the memory 12 (for example, executing an artificial intelligence-based environmental detection and early warning program, etc.), and calls the data stored in the memory 12 to execute various functions of the electronic device 1 and process data.

[0245] The processor 13 executes the operating system of the electronic device 1 and various installed applications. The processor 13 executes the applications to implement the steps in the above-mentioned embodiments of the environment detection and early warning method based on artificial intelligence, for example Figure 1 Steps shown.

[0246] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete the present application. The one or more modules / units may be a series of computer-readable instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the electronic device 1. For example, the computer program may be divided into an acquisition unit 110, a classification unit 111, a regression unit 112, a calculation unit 113, a construction unit 114, and an evaluation unit 115.

[0247] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to execute part of the artificial intelligence-based environmental detection and early warning method described in each embodiment of the present application.

[0248] If the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also instruct the relevant hardware devices to complete through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented.

[0249] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory and other memory, etc.

[0250] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0251] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0252] The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one arrow is used in the figure, but it does not mean that there is only one bus or one type of bus. The bus is configured to realize the connection and communication between the memory 12 and at least one processor 13, etc.

[0253] An embodiment of the present application also provides a computer-readable storage medium (not shown), in which computer-readable storage medium is stored computer-readable instructions, and the computer-readable instructions are executed by a processor in an electronic device to implement the artificial intelligence-based environmental detection and early warning method described in any of the above embodiments.

[0254] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0255] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0256] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0257] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the specification can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any specific order.

[0258] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. An artificial intelligence-based environmental detection and early warning method, characterized in that: include: Acquire original detection data according to the IoT detection ecological environment, acquire first classified data based on the original detection data, store various types of data in the first classified data in isolation, wherein a group of original detection data containing various environmental factors at any time is used as a data point; Dividing the first classified data according to a clustering algorithm to obtain second classified data includes: establishing a multidimensional space coordinate system of corresponding dimensions according to multiple types of data in the first classified data, wherein each dimension corresponds to a type of data; obtaining first classified data coordinates according to the distribution position of each data point in the first classified data in the multidimensional space coordinate system; dividing the first classified data coordinates according to a clustering algorithm according to the distance between the first classified data coordinates to obtain a classified data set, and establishing a connection between various types of data in the isolated first classified data through the classified data set; based on the connection between various types of data in the multidimensional space coordinate system, jointly storing the classified data set to obtain the second classified data, and the various types of data in the second classified data are jointly stored; Regressing the second classification data according to the preset environmental factors to obtain significant reference variables; Calculating the significant reference variable according to a preset relationship to obtain a significant reference weight; Constructing an ecological environment early warning model based on the significant reference variables and the significant reference weights; The ecological environment is evaluated based on the ecological environment early warning model to determine whether to issue early warning information.

2. The artificial intelligence-based environmental detection and early warning method according to claim 1, characterized in that: The detecting the ecological environment according to the Internet of Things to obtain the first category data includes: Detect the ecological environment based on the Internet of Things to obtain original detection data; converting the raw detection data to obtain a communication data packet; Parsing the communication data packet to obtain the original data packet; The original data packets are classified and stored according to preset environmental factors to obtain first classification data.

3. The artificial intelligence-based environmental detection and early warning method according to claim 1, characterized in that: The step of regressing the second classification data according to the preset environmental factors to obtain significant reference variables comprises: Establish a regression model based on the preset environmental factors; regressing the second categorical data based on the regression model to obtain an initial reference variable; The initial reference variables are screened to obtain the significant reference variables.

4. The artificial intelligence-based environmental detection and early warning method according to claim 1, characterized in that: The step of calculating the significant reference variable according to a preset relationship to obtain a significant reference weight includes: The significant reference variable is calculated to obtain a first reference weight, wherein the first reference weight satisfies the relationship: in, represents the F statistic value of the rth significant reference variable in the i-th category of the second classification data, A first reference weight representing the rth significant reference variable of the i-th category in the second classification data; The significant reference variable is calculated based on the first reference weight and the second classification data to obtain the significant reference weight, and the significant reference weight satisfies the relationship: in, represents the significant reference weight of the rth significant reference variable in the second classification data, Represents the total number of data contained in the i-th category in the second classification data.

5. The artificial intelligence-based environmental detection and early warning method according to claim 4, characterized in that: The ecological environment early warning model is: in, Indicates The ecological environment assessment score corresponding to the ecological environment data detected, Indicates The normalized value corresponding to the rth significant reference variable in the ecological environment data detected, c represents the The total number of significant reference variables in the ecological and environmental data detected.

6. The artificial intelligence-based environment detection and early warning method according to claim 1, characterized in that: The step of evaluating the ecological environment based on the ecological environment early warning model to determine whether to issue early warning information includes: Evaluate the ecological environment based on the ecological environment early warning model to obtain an evaluation result; Whether to issue a warning message is determined based on the evaluation result and a preset threshold.

7. An artificial intelligence-based environment detection and early warning device for implementing the artificial intelligence-based environment detection and early warning method according to claim 1, characterized in that: include: An acquisition unit, configured to acquire first classification data according to the detection of the ecological environment by the Internet of Things, wherein each type of data in the first classification data is stored in isolation; a classification unit, configured to divide the first classification data according to a clustering algorithm to obtain second classification data, wherein each type of data in the second classification data is jointly stored; A regression unit, used for regressing the second classification data according to a preset environmental factor to obtain a significant reference variable; A calculation unit, used for calculating the significant reference variable according to a preset relationship to obtain a significant reference weight; A construction unit, used to construct an ecological environment early warning model according to the significant reference variables and the significant reference weights; An evaluation unit is used to evaluate the ecological environment based on the ecological environment early warning model to determine whether to issue early warning information.

8. An electronic device, characterized in that: include: a memory storing computer readable instructions; and A processor executes computer-readable instructions stored in the memory to implement the artificial intelligence-based environment detection and early warning method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions are executed by a processor in an electronic device to implement the artificial intelligence-based environmental detection and early warning method as described in any one of claims 1 to 6.

Images