Method and device for identifying precipitation particle type, storage medium and electronic equipment

Abstract

The embodiment of the invention provides a precipitation particle type identification method and device, a storage medium and electronic equipment, and the method is applied to a server, and comprises the steps: obtaining a reflection signal value of a measured precipitation particle through a base station; acquiring the field intensity attenuation of the wireless signal transmitted by the base station through the base station and the receiver; and determining the type of the measured rainfall particles based on the reflected signal value and the field intensity attenuation amount. Through the method and the device, the problem of low accuracy of identifying the type of the rainfall particles is solved, and the effect of improving the accuracy of identifying the rainfall particles is further achieved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of communications, and in particular, to a method, device, storage medium and electronic device for identifying precipitation particle types. Background Art

[0002] The study of precipitation is of great significance to the prevention of natural disasters such as floods, landslides, and mud-rock flows. When measuring and studying precipitation, the first thing to do is to distinguish the types of precipitation particles - rain, snow, hail, etc.

[0003] At present, the identification of rain, snow and hail is mainly based on the method of weather radar volume scanning data and dual polarization Doppler radar polarization parameters. Among them, the method of weather radar volume scanning is relatively simple, but the resolution is low and the microphysical characteristics of precipitation particles are ignored; while the resolution of dual polarization Doppler radar is higher than that of ordinary weather radar, but it is easily interfered and has large errors.

[0004] In addition, the microwave attenuation characteristics of microwave links are used to invert the droplet spectrum and particle shape distribution of rain, snow, and hail, but a large amount of labeled microwave attenuation data is required. In actual scenarios, the amount of microwave attenuation data with precipitation type labels is often not sufficient, so the classification monitoring scheme for rain, snow, and hail often has the problem of low accuracy. Summary of the invention

[0005] Embodiments of the present invention provide a method, device, storage medium and electronic device for identifying the type of precipitation particles, so as to at least solve the problem of low accuracy in identifying the type of precipitation particles in the related art.

[0006] According to an embodiment of the present invention, a method for identifying precipitation particle types is provided, and the method is applied to a server, comprising:

[0007] Acquire the reflection signal value of the measured precipitation particles through the base station;

[0008] Acquire, through the base station and the receiver, a field strength attenuation of a wireless signal transmitted by the base station;

[0009] The type of the detected precipitation particle is determined based on the reflection signal value and the field intensity attenuation.

[0010] According to yet another embodiment of the present invention, a method for identifying precipitation particle types is also provided. The method is applied to a base station and includes:

[0011] Analyze the reflection signal value of the measured precipitation particles;

[0012] Transmitting a wireless signal and recording a wireless signal value, so that a receiver obtains an attenuated signal value and sends the attenuated signal value to a server;

[0013] The reflected signal value and the wireless signal value are sent to a server, so that the server obtains a field intensity attenuation based on the wireless signal value and the attenuated signal value, and determines the type of the measured precipitation particles according to the reflected signal value and the field intensity attenuation.

[0014] According to yet another embodiment of the present invention, a method for identifying precipitation particle types is also provided. The method is applied to a receiver and includes:

[0015] Acquire a wireless signal sent by a base station, obtain an attenuated signal value, and send the attenuated signal value to a server;

[0016] The server obtains the field intensity attenuation based on the attenuated signal value and the wireless signal value sent by the base station, and determines the type of the measured precipitation particles based on the field intensity attenuation and the reflected signal value sent by the base station.

[0017] According to another embodiment of the present invention, there is provided a device for identifying precipitation particle types, comprising:

[0018] An acquisition module is used to acquire the reflection signal value of the measured precipitation particles and the field intensity attenuation of the wireless signal transmitted by the base station;

[0019] A processing module is used to determine the type of the detected precipitation particles based on the reflection signal value and the field intensity attenuation.

[0020] According to yet another embodiment of the present invention, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, wherein the computer program implements the steps in any of the above method embodiments when executed by a processor.

[0021] According to another embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0022] Through the present invention, since the method of using a base station to identify the type of precipitation particles is used, the problem of low accuracy in identifying the type of precipitation particles can be solved by obtaining multi-dimensional information, multi-parameter analysis and real-time feedback optimization, thereby improving the accuracy of identifying precipitation particles. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a schematic diagram of a network architecture for running a method for identifying precipitation particle types according to an embodiment of the present invention;

[0024] Figure 2is a flow chart of a method for identifying precipitation particle types according to an embodiment of the present invention;

[0025] Figure 3 is a flow chart for determining the type of precipitation particles to be measured based on the reflection signal value and the field intensity attenuation according to an embodiment of the present invention;

[0026] Figure 4 is a flowchart of a method for obtaining a classification model according to an embodiment of the present invention;

[0027] Figure 5 is a flow chart of constructing a training data set and a verification data set according to the reflection signal value and the field intensity attenuation in the historical data according to an embodiment of the present invention;

[0028] Figure 6 is a flowchart of a method for obtaining a first data set and a second data set according to an embodiment of the present invention;

[0029] Figure 7 is a flow chart of obtaining a combined data set based on differential reflectivity and differential attenuation rate according to an embodiment of the present invention;

[0030] Figure 8 is a flowchart of obtaining a fifth data set and a sixth data set according to an embodiment of the present invention;

[0031] Fig. 9 is a precipitation particle distribution map obtained by using differential reflectivity and differential attenuation rate according to an embodiment of the present invention;

[0032] Fig.10 is a variation trend diagram of K value-error rate according to an embodiment of the present invention;

[0033] Fig.11 4 is a schematic diagram of the structure of a device for identifying precipitation particle types according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings and in combination with the embodiments.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0036] The present application embodiment can be run on Figure 1 In the network architecture shown in Figure 1As shown, the network architecture includes: a server, a communication base station and a receiver. The communication base station is connected to the server and the receiver, and the receiver is connected to the server. The communication base station is used to transmit wireless signals and receive echoes; the receiver is used to receive wireless signals transmitted by the communication base station, which can be a terminal or another communication base station. The server is used to collect, analyze, process and output data. Specifically, the communication base station can transmit detection signals to the sky and receive reflected signals fed back by precipitation particles and send wireless signals to the receiver.

[0037] In this embodiment, a method for identifying precipitation particle types running on the above network architecture is provided. Figure 2 is a flow chart of a method for identifying precipitation particle types according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0038] Step S201, obtaining the reflection signal value of the measured precipitation particles through the base station;

[0039] In an exemplary embodiment, the specific implementation method is as follows:

[0040] The base station transmits a detection signal: The base station will transmit a beam of electromagnetic waves (usually a signal in the microwave band). This detection signal will be transmitted at a certain power and specific frequency.

[0041] Interaction between detection signal and precipitation particles: The emitted detection signal will interact with precipitation particles. When the detection signal meets precipitation particles, the detection signal will be scattered, reflected or absorbed.

[0042] Receiving and processing reflected signals: The base station receives the signals reflected from the precipitation particles. These reflected signals are received by the receiving antenna and transmitted to the signal processing system for processing.

[0043] Analyze the reflected signal: The signal processing system will analyze and process the received reflected signal. By analyzing the intensity, frequency, phase and other parameters of the reflected signal, the reflected signal value of the precipitation particles can be obtained, and the intensity, type, distribution and other information of the precipitation can be further inferred.

[0044] Step S202, obtaining the field intensity attenuation of the wireless signal transmitted by the base station through the base station and the receiver;

[0045] In an exemplary embodiment, the specific implementation method is as follows:

[0046] Base stations transmit wireless signals: Base stations transmit wireless signals, which are transmitted at a certain power and specific frequency.

[0047] Wireless signal propagation process: The transmitted wireless signal will be affected by precipitation particles during the propagation process, and these factors will cause the wireless signal to attenuate.

[0048] Receiving wireless signals: At a location near the receiver, the wireless signal is received during the propagation process using a receiving antenna. The receiving antenna converts the wireless signal into an electrical signal and passes it to the receiver.

[0049] Wireless signal strength measurement: The receiver measures the strength of the received wireless signal. By measuring the power or voltage of the received wireless signal, the field strength of the wireless signal can be obtained.

[0050] Field strength attenuation calculation: By comparing the field strength of the received wireless signal with the field strength of the wireless signal when the base station transmits, the attenuation experienced by the wireless signal during propagation can be calculated.

[0051] Step S203: determining the type of the precipitation particle to be detected based on the reflection signal value and the field intensity attenuation.

[0052] Through the above steps, the method of using the base station to identify the type of precipitation particles solves the problem of low accuracy in identifying the type of precipitation particles by obtaining multi-dimensional information, multi-parameter analysis and real-time feedback optimization, thereby improving the accuracy of identifying precipitation particles.

[0053] Figure 3 is a flow chart of determining the type of precipitation particles to be measured based on the reflection signal value and the field intensity attenuation according to an embodiment of the present invention. Figure 3 As shown,

[0054] The type of precipitation particles being measured is determined based on the reflection signal value and field strength attenuation, including:

[0055] Step S301, obtaining a differential reflectivity based on a reflection signal value;

[0056] In an exemplary embodiment, the reference signal value is set, and the reflection signal value of a known reference object or position can be selected as the reference value, or a background noise signal can be used as a reference. The reflection signal value and the reference signal value are calculated to obtain a differential signal. This differential signal represents the reflection ability of the target object relative to the reference signal. According to the specific application requirements, calibration and calibration steps may be required. This may include calibrating the response of the sensor and calibrating the relationship between the reflection signal value and the reference signal value to obtain a more accurate and comparable differential reflectivity. According to the definition and unit of the differential signal, the differential signal can be converted into a differential reflectivity. The differential reflectivity is an indicator of the reflection ability of the target object relative to the reference object. The specific conversion method may involve a calibration curve, a calibration coefficient, etc. to ensure the accuracy and comparability of the differential reflectivity.

[0057] Step S302, obtaining a differential attenuation rate based on the field intensity attenuation;

[0058] In an exemplary embodiment, a reference field strength attenuation is set. A known field strength attenuation of a reference object or position can be selected as a reference value, or a background noise field strength attenuation can be used as a benchmark. The field strength attenuation is calculated by difference with the reference field strength attenuation to obtain a differential field strength attenuation. This differential field strength attenuation represents the attenuation capability of the target object relative to the reference signal. According to specific application requirements, calibration and calibration steps can be performed. This can include calibration of the sensor response and calibration of the relationship between the field strength attenuation and the reference field strength attenuation to obtain a more accurate and comparable differential attenuation rate. According to the definition and unit of the differential field strength attenuation, the differential field strength attenuation can be converted into a differential attenuation rate. The differential attenuation rate is an indicator of the attenuation capability of the target object relative to the reference object. The specific conversion method may involve a calibration curve, a calibration coefficient, etc. to ensure the accuracy and comparability of the differential attenuation rate.

[0059] Step S303, obtaining a combined data set based on the differential reflectivity and the differential attenuation rate;

[0060] In an exemplary embodiment, the differential reflectivity dataset and the differential attenuation rate dataset are aligned and matched. This can be done by means of timestamps or spatial coordinates to ensure that the data in the two datasets correspond to the same target object or position. The aligned and matched differential reflectivity dataset and differential attenuation rate dataset are combined to form a new combined dataset. The differential reflectivity and differential attenuation rate can be used as two dimensions, or they can be combined into one dimension. The specific combination method depends on the characteristics of the data and the application requirements, which are not limited here.

[0061] Step S304: input the combined data set into a classification model to determine the type of the detected precipitation particles.

[0062] In an exemplary embodiment, the combined data set is input into a well-trained classification model so that the classification model processes the combined data to determine the type of the detected precipitation particles.

[0063] Figure 4 is a flow chart of a method for obtaining a classification model according to an embodiment of the present invention. Figure 4 As shown,

[0064] The way to obtain the classification model is as follows:

[0065] Step S401, constructing a training data set and a verification data set according to the reflection signal value and the field intensity attenuation in the historical data;

[0066] In an exemplary embodiment, the specific implementation method is as follows:

[0067] Data collection: Collect historical data on reflected signal values ​​and field strength attenuation. These data can be measured by sensors or devices, or extracted from existing data sets.

[0068] Data preprocessing: Preprocess the collected data, including data cleaning, removing outliers, filling missing values, etc., to ensure the quality and integrity of the data.

[0069] Data partitioning: Divide the preprocessed data into training data set and validation data set. Generally speaking, random partitioning or chronological partitioning can be used.

[0070] Random partitioning: randomly divide the data set into a training data set and a validation data set. You can use a cross-validation method, such as K-fold cross-validation, to divide the data set into K subsets, using K-1 subsets as the training data set each time and the remaining subset as the validation data set. Time-order partitioning: in chronological order, use the first part of the data set as the training data set and the second part as the validation data set. This partitioning method is suitable for time series data and can better simulate actual application scenarios.

[0071] Feature engineering: According to specific application requirements, feature engineering is performed on the data to extract features related to the reflected signal value and field intensity attenuation. Feature extraction can be performed using statistical features, frequency domain features, time domain features, and other methods.

[0072] Data normalization: Normalize the extracted features to ensure that different features have the same scale. Common normalization methods include Z-score normalization and Min-Max normalization.

[0073] Construct training and validation datasets: Divide the feature-engineered and standardized data into training and validation datasets. Generally speaking, the training dataset is used to train the model, and the validation dataset is used to evaluate the performance and generalization ability of the model.

[0074] Step S402, constructing an initial classification model using a training data set and a preset algorithm;

[0075] In an exemplary implementation, the preset algorithm may be a KNN algorithm, an ANN algorithm, or the like.

[0076] Step S403, using the verification data set to train the initial classification model until the initial classification model converges to obtain a classification model.

[0077] Figure 5FIG. 4 is a flowchart of constructing a training data set and a verification data set according to the reflection signal value and the field intensity attenuation in the historical data according to an embodiment of the present invention. Figure 5 As shown,

[0078] The training data set and validation data set are constructed based on the reflection signal values ​​and field strength attenuation in the historical data, including:

[0079] Step S501, calculating the differential reflectivity according to the first data set, and constructing a third data set based on the differential reflectivity, wherein the first data set is a historical data set of reflection signal values;

[0080] Step S502, calculating the differential attenuation rate according to the second data set, and constructing a fourth data set based on the differential attenuation rate, wherein the second data set is a historical data set of field intensity attenuation;

[0081] Step S503: Combine the third data set and the fourth data set and split them into a training data set and a verification data set.

[0082] Figure 6 is a flowchart of a method for obtaining a first data set and a second data set according to an embodiment of the present invention. Figure 6 As shown,

[0083] The method of obtaining the first and second data sets is as follows:

[0084] Step S601, obtaining the vertical polarization transmission field strength, horizontal polarization transmission field strength transmitted by the base station and the vertical polarization echo field strength, horizontal polarization echo field strength reflected by the precipitation particles, and marking the time and the type of precipitation particles, recording the vertical polarization transmission field strength, horizontal polarization transmission field strength, vertical polarization echo field strength, horizontal polarization echo field strength, precipitation particle type, and time at the same time as a group of first data, obtaining multiple groups of first data, and recording the multiple groups of first data as a first data set;

[0085] Step S602, obtaining the vertical polarization transmission field strength and the horizontal polarization transmission field strength transmitted by the base station and the vertical polarization reception field strength and the horizontal polarization reception field strength transmitted by the receiver, and marking the time and the type of precipitation particles, recording the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization reception field strength, the horizontal polarization reception field strength, the type of precipitation particles, and the time at the same time as a set of second data, obtaining multiple sets of second data, and recording the multiple sets of second data as a second data set;

[0086] The first data and the second data are two sets of data at the same time.

[0087] Figure 7 FIG. 4 is a flow chart of obtaining a combined data set based on differential reflectivity and differential attenuation rate according to an embodiment of the present invention. Figure 7 As shown,

[0088] Based on the differential reflectivity and differential attenuation, a combined data set is obtained, including:

[0089] Step S701, calculating multiple sets of differential reflectivity according to the fifth data set, the differential reflectivity is marked with a timestamp, and constructing the multiple sets of differential reflectivity into a seventh data set based on the timestamp, the fifth data set is a real-time collection data set of reflection signal values;

[0090] Step S702, calculating multiple sets of differential attenuation rates according to the sixth data set, the differential attenuation rates are marked with timestamps, and constructing the multiple sets of differential attenuation rates into an eighth data set based on the timestamps, the sixth data set being a real-time collection data set of field intensity attenuation;

[0091] Step S703: merge the first data and the second data with the same timestamp into a set of data in a combined data set.

[0092] Figure 8 is a flowchart of obtaining the fifth data set and the sixth data set according to an embodiment of the present invention, such as Figure 8 As shown,

[0093] The method for obtaining the fifth and sixth data sets is as follows:

[0094] Step S801, obtaining the vertical polarization transmission field strength, horizontal polarization transmission field strength, and vertical polarization echo field strength and horizontal polarization echo field strength reflected by precipitation particles of the base station, and marking the time, recording the vertical polarization transmission field strength, horizontal polarization transmission field strength, vertical polarization echo field strength, horizontal polarization echo field strength, and time at the same time as a set of fifth data, obtaining multiple sets of fifth data, and recording the multiple sets of fifth data as a fifth data set;

[0095] Step S802, obtaining the vertical polarization transmission field strength and the horizontal polarization transmission field strength transmitted by the base station and the vertical polarization reception field strength and the horizontal polarization reception field strength sent by the receiver, and marking the time, recording the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization reception field strength, the horizontal polarization reception field strength, and the time at the same time as a set of sixth data, obtaining multiple sets of sixth data, and recording the multiple sets of sixth data as a sixth data set;

[0096] Among them, the fifth data and the sixth data are two sets of data at the same time.

[0097] In an exemplary embodiment, the process of the above method is explained by taking an example:

[0098] 1. Data accumulation and processing part

[0099] This part analyzes and processes the data under known precipitation particle conditions to build a classification model.

[0100] 1: Original data collection.

[0101] The base station detects the reflected field intensity of precipitation particles through echoes, including vertical polarization and horizontal polarization, and marks the particle type. This is recorded as the first data set.

[0102] Specifically, let the vertical polarization transmission field strength of the base station be Pv, and the horizontal polarization transmission field strength be Ph. Let the received vertical polarization echo field strength be Sv, and the horizontal polarization echo field strength be Sh. The first data set can be expressed as: D1 = {(Pv1, Ph1, Sv1, Sh1, T1), (Pv2, Ph2, Sv2, Sh2, T2)...(Pvn, Phn, Svn, Shn, Tn)}, where 1 to n represent different moments, and Tn represents the type of precipitation particles at moment n.

[0103] The base station detects the sending and receiving field strength, including vertical polarization and horizontal polarization, and marks the particle type, which is recorded as the second data set.

[0104] Specifically, let the vertical polarization transmission field strength of the base station be Tv, and the horizontal polarization transmission field strength be Th. The received vertical polarization field strength is Hv, and the horizontal polarization reception field strength is Hh. The second data set can be expressed as: D2 = {(Tv1, Th1, Hv1, Hh1, T1), (Tv2, Th2, Hv2, Hh2, T2)...(Tvn, Thn, Hvn, Hhn, Tn)}, where 1 to n represent different moments, and Tn represents the type of precipitation particles at moment n.

[0105] 2: Data preprocessing.

[0106] Obvious outliers in the first data set and the second data set are removed respectively.

[0107] Specifically, the data in the first data set and the second data set that are obviously deviated from the normal value are removed. The commonly used method is to remove the data that deviates from the mean by more than 3 times the variance.

[0108] The differential reflectance of the first data set is calculated to construct the third data set.

[0109] Specifically, according to the first data set, the vertical polarization reflectivity at the nth moment can be calculated as Rvn=Svn / Pvn, the horizontal polarization reflectivity is Rhn=Shn / Phn, and the differential reflectivity is The differential reflectivity of all data in the first data set is calculated to construct a third data set. The third data set can be expressed as: D3 = {(R1, T1), (R2, T2).....(Rn, Tn)}.

[0110] The differential attenuation rate is calculated for the second data set to construct a fourth data set.

[0111] Specifically, according to the second data set, the vertical polarization attenuation field strength at the nth moment can be calculated as Avn=Tvn-Hvn; the vertical polarization attenuation rate per kilometer is Fvn=Avn / (Tvn*L), where L is the distance (in kilometers); the horizontal polarization attenuation field strength is Ahn=Thn-Hhn; the horizontal polarization attenuation rate per kilometer is Fhn=Ahn / (Thn*L), where L is the distance (in kilometers); the differential attenuation rate is The differential reflectivity of all data in the second data set is calculated to construct a fourth data set. The fourth data set can be expressed as: D4 = {(F1, T1), (F2, T2).....(Fn, Tn)}.

[0112] The third data set and the fourth data set are used to obtain a training data set and a verification data set.

[0113] Specifically, the third data set and the fourth data set are combined into a mixed data set, and the mixed data set is split into a training data set and a verification data set in a ratio of 6:4. The training data set can be expressed as: DT = {(R1, F1, T1), (R2, F2, T2) ... (Rn1, Fn1, Tn1)}; the verification data set can be expressed as: DV = {(R1, F1, T1), (R2, F2, T2) ... (Rn2, Fn2, Tn2)}.

[0114] 3: Algorithm part.

[0115] This section takes the KNN algorithm as an example, including but not limited to the KNN algorithm.

[0116] A classification model is constructed for the training data set (DT) using the KNN algorithm.

[0117] Fig. 9 is a precipitation particle distribution diagram obtained by using differential reflectivity and differential attenuation rate according to an embodiment of the present invention, such as Fig. 9 As shown, the horizontal axis is the differential reflectivity R, the vertical axis is the differential attenuation rate F, and points of different shapes represent different particle types T.

[0118] Validate based on the validation data set and select the optimal K value.

[0119] Fig.10 is a variation trend diagram of K value-error rate according to an embodiment of the present invention. The relationship between the variation of K value and the variation of error rate is as follows: Fig.10 shown.

[0120] Specifically, set K to x, substitute multiple sets of data in the validation data set into the classification model, and set the substituted data to (Rm, Fm, Tm), where Rm is the differential reflectivity of the precipitation particles at the mth moment in the validation data set, Fm is the differential attenuation rate of the precipitation particles at the mth moment in the validation data set, Tm is the mth moment, and (Rm, Fm, Tm) is a set of data at the mth moment in the validation data set. The calculation steps are:

[0121] Calculate the distance value between all the data in the training data set. There are many distance value algorithms. Taking Euclidean distance as an example, the Euclidean distance between (Rm, Fm, Tm) and the data in the training data set (Ri, Fi, Ti) is Among them, Ri is the differential reflectivity of the precipitation particles at the i-th moment in the training data set, Fi is the differential attenuation rate of the precipitation particles at the i-th moment in the training data set, Ti is the i-th moment, and (Ri, Fi, Ti) is a set of data at the i-th moment in the training data set;

[0122] Select the smallest x distance values ​​from all the distance values ​​calculated in the previous step. If the category in the training data set corresponding to these x distance values ​​is mostly Tk, then the category of the validation data set data is determined to be Tk;

[0123] The calculated category value Tk is then compared with the actual category value Tm in the validation data set to draw a conclusion, correct or wrong.

[0124] Perform the above calculations on the data of all validation data sets in turn, and calculate the category error rate Wx;

[0125] Change the K value and calculate the error rate of different K values. The corresponding set of K values ​​and error rates is {(W1, K1), (W2, K2)...(Wn, Kn)}. Select the K value corresponding to the lowest error rate as the optimal K value. For example, Fig.10 As shown, when the K value is 10, the error rate is the smallest, about 3%, so the optimal K value is 10.

[0126] 2. Real-time data collection and judgment part

[0127] This part collects data in real time under unknown weather conditions, and analyzes and processes the data according to the above-mentioned classification algorithm to distinguish different precipitation particles.

[0128] 1: Real-time data collection.

[0129] The communication base station detects the reflected field strength of precipitation particles through echoes, including vertical polarization and horizontal polarization. This is recorded as the fifth data set.

[0130] Assume that the vertical polarization transmission field strength of the base station is Pv, and the horizontal polarization transmission field strength is Ph. The received vertical polarization echo field strength is Sv, and the horizontal polarization echo field strength is Sh. The fifth data set can be expressed as: D1 = {(Pv1, Ph1, Sv1, Sh1), (Pv2, Ph2, Sv2, Sh2) ... (Pvn, Phn, Svn, Shn)}, 1 to n represent different moments respectively.

[0131] The communication base station calculates the attenuation field strength of precipitation particles by sending and receiving field strength, including vertical polarization and horizontal polarization. This is recorded as the sixth data set.

[0132] Assume that the vertical polarization transmission field strength of the base station is Tv, and the horizontal polarization transmission field strength is Th. The received vertical polarization field strength is Hv, and the horizontal polarization reception field strength is Hh. The sixth data set can be expressed as: D2 = {(Tv1, Th1, Hv1, Hh1), (Tv2, Th2, Hv2, Hh2) ... (Tvn, Thn, Hvn, Hhn)}, 1 to n represent different moments respectively.

[0133] 2: Data preprocessing.

[0134] The obvious outliers in the fifth and sixth data sets were removed respectively.

[0135] The specific steps are the same as the data preprocessing part in the data accumulation and processing part.

[0136] The differential reflectance of the fifth data set is calculated to construct the seventh data set.

[0137] The specific steps are the same as the data preprocessing part in the data accumulation and processing part.

[0138] The differential attenuation rate is calculated for the sixth data set, and the eighth data set is constructed.

[0139] The specific steps are the same as the data preprocessing part in the data accumulation and processing part.

[0140] The seventh data set and the eighth data set are combined into a ninth data set.

[0141] Specifically, the ninth data set after synthesis is: D9 = {(R1, F1), (R2, F2) ... (Rn, Fn)}, where 1 ... n represents n different moments.

[0142] 3: Data classification.

[0143] The ninth data set is calculated according to the classification algorithm in the third part to obtain the precipitation particle category.

[0144] Specifically, suppose the input data is (Rm, Fm), where Rm is the differential reflectivity of the precipitation particles at the mth moment, Fm is the differential attenuation rate of the precipitation particles at the mth moment, (Rm, Fm) is a set of real-time data collected at the mth moment, and the calculation steps are:

[0145] a) Calculate the distance between all data in the training data set. There are many distance value algorithms. Take the Euler distance as an example: the Euclidean distance between (Rm, Fm) and the data in the training data set (Ri, Fi, Ti) is Calculate all distance values. Among them, Ri is the differential reflectivity of the precipitation particles at the i-th moment in the training data set, Fi is the differential attenuation rate of the precipitation particles at the i-th moment in the training data set, Ti is the i-th moment, and (Ri, Fi, Ti) is a set of data at the i-th moment in the training data set.

[0146] b) Select the smallest K distance values ​​from all the distance values ​​calculated in the previous step. If the category in the training data set corresponding to these K distance values ​​is Tk, the precipitation particle category of the data is determined to be Tk.

[0147] This embodiment also provides a method for identifying precipitation particle types, which is applied to a base station and includes:

[0148] Analyze the reflection signal value of the measured precipitation particles;

[0149] Transmitting a wireless signal and recording a wireless signal value, so that the receiver obtains an attenuated signal value and sends the attenuated signal value to a server;

[0150] The reflected signal value and the wireless signal value are sent to the server, so that the server obtains the field intensity attenuation based on the wireless signal value and the attenuated signal value, and determines the type of the measured precipitation particles according to the reflected signal value and the field intensity attenuation.

[0151] In one embodiment, determining the type of precipitation particles to be detected based on the reflection signal value and the field intensity attenuation includes:

[0152] A differential reflectivity is obtained based on the reflection signal value;

[0153] The differential attenuation rate is obtained based on the field intensity attenuation;

[0154] A combined data set is obtained based on the differential reflectivity and the differential attenuation rate;

[0155] The combined dataset is input into a classification model to determine the type of precipitation particles being measured.

[0156] In one implementation, the classification model is obtained as follows:

[0157] Construct training data set and validation data set according to the reflection signal value and field strength attenuation in the historical data;

[0158] Build an initial classification model using the training dataset and preset algorithms;

[0159] The initial classification model is trained using the validation data set until the initial classification model converges to obtain a classification model.

[0160] In one embodiment, constructing a training data set and a verification data set according to the reflection signal value and the field intensity attenuation in the historical data includes:

[0161] Calculating a differential reflectivity according to a first data set, and constructing a third data set based on the differential reflectivity, wherein the first data set is a historical data set of reflection signal values;

[0162] Calculating the differential attenuation rate according to the second data set, and constructing a fourth data set based on the differential attenuation rate, wherein the second data set is a historical data set of field intensity attenuation;

[0163] The third data set and the fourth data set are combined and split into a training data set and a validation data set.

[0164] In one embodiment, a method for obtaining the first data set and the second data set is as follows:

[0165] Obtaining the vertical polarization transmission field strength, horizontal polarization transmission field strength, and vertical polarization echo field strength and horizontal polarization echo field strength transmitted by the base station and reflected by precipitation particles, and marking the time and the type of precipitation particles, recording the vertical polarization transmission field strength, horizontal polarization transmission field strength, vertical polarization echo field strength, horizontal polarization echo field strength, precipitation particle type, and time at the same time as a group of first data, obtaining multiple groups of first data, and recording the multiple groups of first data as a first data set;

[0166] Obtaining the vertical polarization transmission field strength and the horizontal polarization transmission field strength transmitted by the base station and the vertical polarization reception field strength and the horizontal polarization reception field strength sent by the receiver, and marking the time and the type of precipitation particles, recording the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization reception field strength, the horizontal polarization reception field strength, the type of precipitation particles, and the time at the same time as a set of second data, obtaining multiple sets of second data, and recording the multiple sets of second data as a second data set;

[0167] The first data and the second data are two sets of data at the same time.

[0168] In one embodiment, a combined data set is obtained based on the differential reflectivity and the differential attenuation rate, including:

[0169] Calculating multiple sets of differential reflectances according to the fifth data set, the differential reflectances are marked with timestamps, and constructing the multiple sets of differential reflectances into a seventh data set based on the timestamps, the fifth data set being a real-time collection data set of reflection signal values;

[0170] Calculating multiple sets of differential attenuation rates according to the sixth data set, the differential attenuation rates are marked with timestamps, and constructing the multiple sets of differential attenuation rates into an eighth data set based on the timestamps, the sixth data set being a real-time collection data set of field intensity attenuation;

[0171] The first data and the second data having the same time stamp are combined into a set of data in the combined data set.

[0172] In one implementation, a method for obtaining the fifth data set and the sixth data set is as follows:

[0173] Obtaining the vertical polarization transmission field strength, horizontal polarization transmission field strength, and vertical polarization echo field strength and horizontal polarization echo field strength reflected by precipitation particles of the base station, and marking the time, recording the vertical polarization transmission field strength, horizontal polarization transmission field strength, vertical polarization echo field strength, horizontal polarization echo field strength, and time at the same time as a set of fifth data, obtaining multiple sets of fifth data, and recording the multiple sets of fifth data as a fifth data set;

[0174] Obtain the vertical polarization transmission field strength and the horizontal polarization transmission field strength transmitted by the base station and the vertical polarization reception field strength and the horizontal polarization reception field strength sent by the receiver, and mark the time, record the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization reception field strength, the horizontal polarization reception field strength, and the time at the same time as a set of sixth data, obtain multiple sets of sixth data, and record the multiple sets of sixth data as a sixth data set;

[0175] Among them, the fifth data and the sixth data are two sets of data at the same time.

[0176] This embodiment also provides a method for identifying precipitation particle types, which is applied to a receiver and includes:

[0177] Acquire the wireless signal sent by the base station, obtain the attenuated signal value, and send the attenuated signal value to the server;

[0178] The server obtains the field intensity attenuation based on the attenuated signal value and the wireless signal value sent by the base station, and determines the type of the measured precipitation particles based on the field intensity attenuation and the reflected signal value sent by the base station.

[0179] In one embodiment, determining the type of precipitation particles to be detected based on the reflection signal value and the field intensity attenuation includes:

[0180] A differential reflectivity is obtained based on the reflection signal value;

[0181] The differential attenuation rate is obtained based on the field intensity attenuation;

[0182] A combined data set is obtained based on the differential reflectivity and the differential attenuation rate;

[0183] The combined dataset is input into a classification model to determine the type of precipitation particles being measured.

[0184] In one implementation, the classification model is obtained as follows:

[0185] Construct training data set and validation data set according to the reflection signal value and field strength attenuation in the historical data;

[0186] Build an initial classification model using the training dataset and preset algorithms;

[0187] The initial classification model is trained using the validation data set until the initial classification model converges to obtain a classification model.

[0188] In one embodiment, constructing a training data set and a verification data set according to the reflection signal value and the field intensity attenuation in the historical data includes:

[0189] Calculating a differential reflectivity according to a first data set, and constructing a third data set based on the differential reflectivity, wherein the first data set is a historical data set of reflection signal values;

[0190] Calculating the differential attenuation rate according to the second data set, and constructing a fourth data set based on the differential attenuation rate, wherein the second data set is a historical data set of field intensity attenuation;

[0191] The third data set and the fourth data set are combined and split into a training data set and a validation data set.

[0192] In one embodiment, a method for obtaining the first data set and the second data set is as follows:

[0193] Obtaining the vertical polarization transmission field strength, horizontal polarization transmission field strength, and vertical polarization echo field strength and horizontal polarization echo field strength transmitted by the base station and reflected by precipitation particles, and marking the time and the type of precipitation particles, recording the vertical polarization transmission field strength, horizontal polarization transmission field strength, vertical polarization echo field strength, horizontal polarization echo field strength, precipitation particle type, and time at the same time as a group of first data, obtaining multiple groups of first data, and recording the multiple groups of first data as a first data set;

[0194] Obtaining the vertical polarization transmission field strength and the horizontal polarization transmission field strength transmitted by the base station and the vertical polarization reception field strength and the horizontal polarization reception field strength sent by the receiver, and marking the time and the type of precipitation particles, recording the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization reception field strength, the horizontal polarization reception field strength, the type of precipitation particles, and the time at the same time as a set of second data, obtaining multiple sets of second data, and recording the multiple sets of second data as a second data set;

[0195] The first data and the second data are two sets of data at the same time.

[0196] In one embodiment, a combined data set is obtained based on the differential reflectivity and the differential attenuation rate, including:

[0197] Calculating multiple sets of differential reflectances according to the fifth data set, the differential reflectances are marked with timestamps, and constructing the multiple sets of differential reflectances into a seventh data set based on the timestamps, the fifth data set being a real-time collection data set of reflection signal values;

[0198] Calculating multiple sets of differential attenuation rates according to the sixth data set, the differential attenuation rates are marked with timestamps, and constructing the multiple sets of differential attenuation rates into an eighth data set based on the timestamps, the sixth data set being a real-time collection data set of field intensity attenuation;

[0199] The first data and the second data having the same time stamp are combined into a set of data in the combined data set.

[0200] In one implementation, a method for obtaining the fifth data set and the sixth data set is as follows:

[0201] Obtaining the vertical polarization transmission field strength, horizontal polarization transmission field strength, and vertical polarization echo field strength and horizontal polarization echo field strength reflected by precipitation particles of the base station, and marking the time, recording the vertical polarization transmission field strength, horizontal polarization transmission field strength, vertical polarization echo field strength, horizontal polarization echo field strength, and time at the same time as a set of fifth data, obtaining multiple sets of fifth data, and recording the multiple sets of fifth data as a fifth data set;

[0202] Obtain the vertical polarization transmission field strength and the horizontal polarization transmission field strength transmitted by the base station and the vertical polarization reception field strength and the horizontal polarization reception field strength sent by the receiver, and mark the time, record the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization reception field strength, the horizontal polarization reception field strength, and the time at the same time as a set of sixth data, obtain multiple sets of sixth data, and record the multiple sets of sixth data as a sixth data set;

[0203] Among them, the fifth data and the sixth data are two sets of data at the same time.

[0204] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by adding the necessary general hardware platform with the help of software, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0205] In this embodiment, a device for identifying precipitation particle types is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made are not repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0206] Fig.11 is a schematic diagram of a structure of a device for identifying precipitation particle types according to an embodiment of the present invention. Fig.11 As shown, the device comprises:

[0207] The acquisition module 111 is used to obtain the reflection signal value of the measured precipitation particles and the field intensity attenuation of the wireless signal transmitted by the base station;

[0208] The processing module 112 is used to determine the type of the detected precipitation particles based on the reflection signal value and the field intensity attenuation.

[0209] In one embodiment, the device further includes: an output module 113, configured to output the type of the detected precipitation particles.

[0210] In one embodiment, the device is further used to determine the type of precipitation particles to be measured based on the reflection signal value and the field intensity attenuation, including:

[0211] A differential reflectivity is obtained based on the reflection signal value;

[0212] The differential attenuation rate is obtained based on the field intensity attenuation;

[0213] A combined data set is obtained based on the differential reflectivity and the differential attenuation rate;

[0214] The combined dataset is input into a classification model to determine the type of precipitation particles being measured.

[0215] In one embodiment, the device is further used to obtain the classification model in the following manner:

[0216] Construct training data set and validation data set according to the reflection signal value and field strength attenuation in the historical data;

[0217] Build an initial classification model using the training dataset and preset algorithms;

[0218] The initial classification model is trained using the validation data set until the initial classification model converges to obtain a classification model.

[0219] In one embodiment, the device is further used to construct a training data set and a verification data set according to the reflection signal value and the field intensity attenuation in the historical data, including:

[0220] Calculating a differential reflectivity according to a first data set, and constructing a third data set based on the differential reflectivity, wherein the first data set is a historical data set of reflection signal values;

[0221] Calculating the differential attenuation rate according to the second data set, and constructing a fourth data set based on the differential attenuation rate, wherein the second data set is a historical data set of field intensity attenuation;

[0222] The third data set and the fourth data set are combined and split into a training data set and a validation data set.

[0223] In one embodiment, the device is further used to: obtain the first data set and the second data set in the following method:

[0224] Obtaining the vertical polarization transmission field strength, horizontal polarization transmission field strength, and vertical polarization echo field strength and horizontal polarization echo field strength transmitted by the base station and reflected by precipitation particles, and marking the time and the type of precipitation particles, recording the vertical polarization transmission field strength, horizontal polarization transmission field strength, vertical polarization echo field strength, horizontal polarization echo field strength, precipitation particle type, and time at the same time as a group of first data, obtaining multiple groups of first data, and recording the multiple groups of first data as a first data set;

[0225] Obtaining the vertical polarization transmission field strength and the horizontal polarization transmission field strength transmitted by the base station and the vertical polarization reception field strength and the horizontal polarization reception field strength sent by the receiver, and marking the time and the type of precipitation particles, recording the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization reception field strength, the horizontal polarization reception field strength, the type of precipitation particles, and the time at the same time as a set of second data, obtaining multiple sets of second data, and recording the multiple sets of second data as a second data set;

[0226] The first data and the second data are two sets of data at the same time.

[0227] In one embodiment, the apparatus is further used to obtain a combined data set based on the differential reflectivity and the differential attenuation rate, comprising:

[0228] Calculating multiple sets of differential reflectances according to the fifth data set, the differential reflectances are marked with timestamps, and constructing the multiple sets of differential reflectances into a seventh data set based on the timestamps, the fifth data set being a real-time collection data set of reflection signal values;

[0229] Calculating multiple sets of differential attenuation rates according to the sixth data set, the differential attenuation rates are marked with timestamps, and constructing the multiple sets of differential attenuation rates into an eighth data set based on the timestamps, the sixth data set being a real-time collection data set of field intensity attenuation;

[0230] The first data and the second data having the same time stamp are combined into a set of data in the combined data set.

[0231] In one embodiment, the device is further used to: obtain the fifth data set and the sixth data set in the following method:

[0232] Obtaining the vertical polarization transmission field strength, horizontal polarization transmission field strength, and vertical polarization echo field strength and horizontal polarization echo field strength reflected by precipitation particles of the base station, and marking the time, recording the vertical polarization transmission field strength, horizontal polarization transmission field strength, vertical polarization echo field strength, horizontal polarization echo field strength, and time at the same time as a set of fifth data, obtaining multiple sets of fifth data, and recording the multiple sets of fifth data as a fifth data set;

[0233] Obtain the vertical polarization transmission field strength and the horizontal polarization transmission field strength transmitted by the base station and the vertical polarization reception field strength and the horizontal polarization reception field strength sent by the receiver, and mark the time, record the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization reception field strength, the horizontal polarization reception field strength, and the time at the same time as a set of sixth data, obtain multiple sets of sixth data, and record the multiple sets of sixth data as a sixth data set;

[0234] Among them, the fifth data and the sixth data are two sets of data at the same time.

[0235] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0236] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0237] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0238] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0239] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0240] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0241] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0242] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying precipitation particle types, characterized in that: The method is applied to a server and includes: Acquire the reflection signal value of the measured precipitation particles through the base station; Acquire, through the base station and the receiver, a field strength attenuation of a wireless signal transmitted by the base station; The type of the detected precipitation particle is determined based on the reflection signal value and the field intensity attenuation.

2. The method according to claim 1, characterized in that Determining the type of the detected precipitation particle based on the reflection signal value and the field intensity attenuation includes: Obtaining a differential reflectivity based on the reflection signal value; Obtaining a differential attenuation rate based on the field intensity attenuation; obtaining a combined data set based on the differential reflectivity and the differential attenuation rate; The combined data set is input into a classification model to determine the type of the detected precipitation particles.

3. The method according to claim 2, characterized in that The classification model is obtained as follows: Construct training data set and validation data set according to the reflection signal value and field strength attenuation in the historical data; Using the training data set and the preset algorithm to build an initial classification model; The initial classification model is trained using the validation data set until the initial classification model converges to obtain the classification model.

4. The method according to claim 3, characterized in that The training data set and validation data set are constructed based on the reflection signal values ​​and field strength attenuation in the historical data, including: Calculating a differential reflectivity according to a first data set, and constructing a third data set based on the differential reflectivity, wherein the first data set is a historical data set of reflection signal values; Calculating a differential attenuation rate according to a second data set, and constructing a fourth data set based on the differential attenuation rate, wherein the second data set is a historical data set of field intensity attenuation; The third data set and the fourth data set are combined and then split into the training data set and the verification data set.

5. The method according to claim 4, characterized in that The method for obtaining the first data set and the second data set is as follows: Obtaining the vertical polarization transmission field strength and the horizontal polarization transmission field strength transmitted by the base station and the vertical polarization echo field strength and the horizontal polarization echo field strength reflected by the precipitation particles, and marking the time and the type of the precipitation particles, recording the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization echo field strength, the horizontal polarization echo field strength, the precipitation particle type, and the time at the same time as a group of first data, obtaining multiple groups of first data, and recording the multiple groups of first data as a first data set; Obtaining the vertical polarization transmission field strength and the horizontal polarization transmission field strength transmitted by the base station and the vertical polarization reception field strength and the horizontal polarization reception field strength sent by the receiver, and marking the time and the type of the precipitation particles, recording the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization reception field strength, the horizontal polarization reception field strength, the type of precipitation particles, and the time at the same time as a set of second data, obtaining multiple sets of second data, and recording the multiple sets of second data as a second data set; The first data and the second data are two sets of data at the same time.

6. The method according to claim 2, characterized in that Obtaining a combined data set based on the differential reflectivity and the differential attenuation rate, comprising: Calculating multiple sets of differential reflectivity according to the fifth data set, wherein the differential reflectivity is marked with a timestamp, and constructing the multiple sets of differential reflectivity into a seventh data set based on the timestamp, wherein the fifth data set is a real-time collection data set of the reflection signal value; Calculating multiple groups of differential attenuation rates according to the sixth data set, wherein the differential attenuation rates are marked with timestamps, and constructing the multiple groups of differential attenuation rates into an eighth data set based on the timestamps, wherein the sixth data set is a real-time collection data set of the field intensity attenuation amount; The first data and the second data with the same time stamp are combined into a set of data in a combined data set.

7. The method according to claim 6, characterized in that The method for obtaining the fifth data set and the sixth data set is as follows: Obtaining the vertical polarization transmission field strength, the horizontal polarization transmission field strength, and the vertical polarization echo field strength and the horizontal polarization echo field strength reflected by the precipitation particles of the base station, and marking the time, recording the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization echo field strength, the horizontal polarization echo field strength, and the time at the same time as a set of fifth data, obtaining multiple sets of fifth data, and recording the multiple sets of fifth data as a fifth data set; Obtaining the vertical polarization transmission field strength and the horizontal polarization transmission field strength transmitted by the base station and the vertical polarization reception field strength and the horizontal polarization reception field strength sent by the receiver, and marking the time, recording the vertical polarization transmission field strength, the horizontal polarization transmission field strength, the vertical polarization reception field strength, the horizontal polarization reception field strength, and the time at the same time as a set of sixth data, obtaining multiple sets of sixth data, and recording the multiple sets of sixth data as a sixth data set; The fifth data and the sixth data are two sets of data at the same time.

8. A method for identifying precipitation particle types, characterized in that: The method is applied to a base station, comprising: Analyze the reflection signal value of the measured precipitation particles; Transmitting a wireless signal and recording a wireless signal value, so that a receiver obtains an attenuated signal value and sends the attenuated signal value to a server; The reflected signal value and the wireless signal value are sent to a server, so that the server obtains a field intensity attenuation based on the wireless signal value and the attenuated signal value, and determines the type of the measured precipitation particles according to the reflected signal value and the field intensity attenuation.

9. A method for identifying precipitation particle types, characterized in that: The method is applied to a receiver, comprising: Acquire a wireless signal sent by a base station, obtain an attenuated signal value, and send the attenuated signal value to a server; The server obtains the field intensity attenuation based on the attenuated signal value and the wireless signal value sent by the base station, and determines the type of the measured precipitation particles based on the field intensity attenuation and the reflected signal value sent by the base station.

10. A device for identifying precipitation particle types, characterized in that: include: An acquisition module is used to acquire the reflection signal value of the measured precipitation particles and the field intensity attenuation of the wireless signal transmitted by the base station; A processing module is used to determine the type of the detected precipitation particles based on the reflection signal value and the field intensity attenuation.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of the method described in any one of claims 1 to 7, or implements the steps of the method described in claim 8, or implements the steps of the method described in claim 9.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the processor implements the steps of the method described in any one of claims 1 to 7, or implements the steps of the method described in claim 8, or implements the steps of the method described in claim 9.

Images