Cloud map prediction method and apparatus

Abstract

Disclosed in the embodiments of the present application are a cloud map prediction method and apparatus. The method comprises: collecting, at a plurality of first time points, cloud maps to be predicted and meteorological data to be predicted, wherein the plurality of first time points are different time points which are separated by a preset time; on the basis of said cloud map and said meteorological data at a first time point, determining mixed feature data at the first time point; and on the basis of the mixed feature data at the plurality of first time points, performing prediction to obtain predicted cloud maps at a preset predicted number of second time points, wherein the preset predicted number of second time points are different time points which are separated by the preset time, the earliest second time point is later than the latest first time point, and the earliest second time point and the latest first time point are separated by the preset time.

Description

Cloud map prediction method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on July 26, 2023, with application number 202310932605.3, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the fields of data processing and deep learning, and in particular to a cloud image prediction method and device. Background Art

[0004] Photovoltaic systems need to be controlled based on changes in the sky to maximize power generation efficiency. Therefore, predicting future panoramic sky images is crucial for the prediction and control tasks of photovoltaic control systems. Currently, other meteorological data, such as temperature, humidity, wind speed, and radiation, are collected alongside panoramic sky images. These data are closely correlated with changes in cloud cover and sunlight obstruction. However, current methods for predicting panoramic sky images only use the captured panoramic sky images as feature data without considering the corresponding meteorological data, resulting in inaccurate predicted panoramic sky images.

[0005] Summary of the Invention

[0006] The present application provides a cloud map prediction method and device to at least solve the above-mentioned technical problems.

[0007] To this end, an embodiment of the present application provides a cloud map prediction method, the method comprising:

[0008] Collecting cloud images and meteorological data to be measured at multiple first time points, where the multiple first time points are different time points at intervals of preset time;

[0009] determining mixed characteristic data at the first time point based on the cloud image to be measured and the meteorological data to be measured at the first time point;

[0010] Based on the mixed feature data of the multiple first time points, prediction is performed to obtain a prediction cloud map of a preset number of second time points, where the preset number of second time points are different time points separated by the preset time, and the first second time point is later than the last first time point and is separated by the preset time.

[0011] The determining of the mixed characteristic data at the first time point based on the cloud image to be measured and the meteorological data to be measured at the first time point includes:

[0012] Determine image feature data based on the cloud image to be measured at the first time point, wherein the image feature data is a matrix of three channels;

[0013] Determining a matrix of at least one channel based on the matrix sizes of the meteorological data to be measured and the image feature data at the first time point;

[0014] The matrix of the at least one channel is combined with the image feature data to obtain mixed feature data at the first time point.

[0015] The performing of prediction based on the mixed feature data of the multiple first time points includes:

[0016] Traversing the multiple first time points in chronological order;

[0017] Determining the first time feature data and the second time feature data of the current first time point based on the mixed feature data of the current first time point, the first time feature data and the second time feature data of the previous first time point, when the current first time point is the first first time point, the first time feature data and the second time feature data of the corresponding previous first time point are the preset first time feature data and the preset second time feature data;

[0018] After the traversal is completed, the first time feature data and the second time feature data of the last first time point are obtained.

[0019] After obtaining the first time feature data and the second time feature data of the last first time point, performing prediction based on the mixed feature data of the multiple first time points further includes:

[0020] Traversing the preset predicted number of second time points in chronological order;

[0021] Determine the first time feature data and the second time feature data of the current second time point based on the mixed feature data of the current second time point, the first time feature data and the second time feature data of the previous second time point, when the current second time point is the first second time point, the corresponding previous second time point is the last first time point;

[0022] Perform prediction based on the first time feature data and the second time feature data at the current second time point to obtain a prediction cloud map at the current second time point;

[0023] After the traversal is completed, a prediction cloud map for each second time point is obtained.

[0024] The determining of the second time feature data at the current time point based on the mixed feature data at the current time point, the first time feature data at the previous time point, and the second time feature data at the previous time point includes:

[0025] Determine first weighted feature data and second weighted feature data at the current time point based on the mixed feature data at the current time point, the first time feature data and the second time feature data at the previous time point;

[0026] The second time feature data at the current time point is determined based on the mixed feature data at the current time point, the first weighted feature data, the second weighted feature data, and the first time feature data at the previous time point.

[0027] The determining of the first time feature data at the current time point based on the mixed feature data at the current time point, the first time feature data at the previous time point, and the second time feature data includes:

[0028] Determine third weighted feature data at the current time point based on the mixed feature data at the current time point, the second time feature data, and the first time feature data at the previous time point;

[0029] The first time feature data at the current time point is determined based on the third weighted feature data and the second time feature data at the current time point.

[0030] Another aspect of the present application provides a cloud image prediction device, comprising:

[0031] An acquisition module, configured to acquire cloud images to be measured and meteorological data to be measured at a plurality of first time points, wherein the plurality of first time points are different time points at intervals of a preset time;

[0032] A calculation module, configured to determine the mixed characteristic data at the first time point based on the cloud image to be measured and the meteorological data to be measured at the first time point;

[0033] A deep learning module is used to make predictions based on the mixed feature data of the multiple first time points to obtain a prediction cloud map of a preset number of second time points, where the preset number of second time points are different time points separated by the preset time, and the first second time point is later than the last first time point and is separated by the preset time.

[0034] Among them, also include:

[0035] The calculation module is further configured to determine image feature data based on the cloud image to be measured at the first time point, wherein the image feature data is a matrix of three channels;

[0036] The calculation module is further configured to determine a matrix of at least one channel based on the matrix size of the meteorological data to be measured and the image feature data at the first time point;

[0037] A processing module is configured to merge the matrix of the at least one channel with the image feature data to obtain mixed feature data at the first time point.

[0038] The calculation module is further configured to traverse the plurality of first time points in chronological order;

[0039] The calculation module is further used to determine the first time feature data and the second time feature data of the current first time point based on the mixed feature data of the current first time point, the first time feature data and the second time feature data of the previous first time point, when the current first time point is the first first time point, the first time feature data and the second time feature data of the corresponding previous first time point are the preset first time feature data and the preset second time feature data;

[0040] The calculation module is further configured to obtain the first time feature data and the second time feature data of the last first time point after the traversal is completed.

[0041] The calculation module is further configured to traverse the second time points of the preset predicted number in chronological order;

[0042] The calculation module is further used to determine the first time feature data and the second time feature data of the current second time point based on the mixed feature data of the current second time point, the first time feature data and the second time feature data of the previous second time point, when the current second time point is the first second time point, the corresponding previous second time point is the last first time point;

[0043] The deep learning module is further configured to perform prediction based on the first time feature data and the second time feature data at the current second time point to obtain a prediction cloud map at the current second time point;

[0044] The calculation module is further used to obtain a prediction cloud map at each second time point after the traversal is completed.

[0045] In the above scheme, the cloud image to be measured and the meteorological data to be measured are merged to generate hybrid feature data, which contains both the image features of the cloud image and the features of the corresponding meteorological data. Predictions based on the hybrid feature data at multiple first time points enable the prediction method to fully consider both the image features and the features of the meteorological data, significantly improving the accuracy of the predicted cloud image at the second time point. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] FIG1 shows a flow chart of a cloud map prediction method according to an embodiment of the present application;

[0048] FIG2 shows a flowchart of determining mixed feature data at a first time point according to an embodiment of the present application;

[0049] FIG3 shows a flowchart of performing prediction based on mixed feature data at a first time point according to an embodiment of the present application;

[0050] FIG4 shows a flowchart of performing prediction based on mixed feature data at a first time point according to another embodiment of the present application;

[0051] FIG5 shows a flowchart of determining second time characteristic data according to an embodiment of the present application;

[0052] FIG6 shows a flowchart of determining first time characteristic data according to an embodiment of the present application;

[0053] FIG7 shows a schematic structural diagram of a cloud map prediction device according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, features, and advantages of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0055] In order to improve the accuracy of predicting a panoramic sky image, an embodiment of the present application provides a cloud image prediction method, as shown in FIG1 , the method comprising:

[0056] Step 101 : collecting cloud images and meteorological data to be measured at multiple first time points, where the multiple first time points are different time points separated by a preset time interval.

[0057] The fisheye camera collects cloud images to be measured at multiple time points, and the meteorological sensor collects corresponding meteorological data to be measured at each first time point. The multiple first time points are different time points with preset time intervals.

[0058] For example, if you set the cloud map and corresponding meteorological data to be collected once every hour, you can collect data three times in total. The first collection is at 5:00 AM, and the cloud map and meteorological data for 5:00 AM are collected. The second collection is at 6:00 AM, and the cloud map and meteorological data for 6:00 AM are collected. The third collection is at 7:00 AM, and the cloud map and meteorological data for 7:00 AM are collected.

[0059] Step 102: Determine mixed characteristic data at the first time point based on the cloud image to be measured and the meteorological data to be measured at the first time point.

[0060] In this embodiment, there are three ways to obtain mixed feature data:

[0061] The first method is to increase the number of channels. Since the cloud image to be measured is a three-channel matrix, the number of channels of the matrix is ​​increased, and the meteorological data to be measured is placed in the increased channels and merged with the three-channel matrix of the cloud image to be measured to obtain mixed feature data.

[0062] For example, after the cloud image to be tested is converted into feature data, The matrix of three channels, the meteorological data to be measured contains data of four dimensions: temperature, humidity, wind speed and wind direction. Then the meteorological data to be measured is converted into a matrix The matrix converted from the meteorological data to be measured is used as an additional channel and combined with the feature data converted from the cloud image to be measured to obtain the mixed feature data:

[0063] The second method is splicing. The cloud image to be measured is a matrix of three channels. The meteorological data to be measured is divided into three parts. The meteorological data of each part is converted into a vector, and then spliced ​​with the matrices of the three channels to obtain mixed feature data.

[0064] For example, after the cloud image to be tested is converted into feature data, The matrix of three channels, the meteorological data to be measured contains data of two dimensions: temperature and humidity. Then, after converting temperature and humidity into vectors, it is [5,3]. The vector converted from the meteorological data to be measured is spliced ​​with the rows or columns of the feature data converted from the cloud image to be measured, and the mixed feature data is obtained as follows: or

[0065] The third type is weighted merging, which performs weighted merging of the cloud image to be measured and the meteorological data to be measured based on preset weights to obtain mixed feature data.

[0066] For example, after the cloud image to be tested is converted into feature data, The matrix of three channels contains the meteorological data of four dimensions: temperature, humidity, wind speed and wind direction. The preset weights are The meteorological data to be measured is converted into a matrix Based on the preset weights, the matrix converted from the meteorological data to be measured and the characteristic data converted from the cloud image to be measured are weighted and merged. The calculation method of each element in the matrix is ​​to multiply the weight by the corresponding data in the meteorological data matrix to be measured, add 1 minus the weight and then multiply it by the corresponding data in the cloud image matrix to be measured. Finally, the mixed characteristic data is obtained as

[0067] Step 103, making a prediction based on the mixed feature data of the multiple first time points to obtain a prediction cloud map of a preset number of second time points, wherein the preset number of second time points are different time points separated by the preset time, and the first second time point is later than the last first time point and is separated by the preset time.

[0068] Based on the mixed feature data of multiple first time points, a prediction is performed to obtain a prediction cloud map for at least one second time point. In this embodiment, the second time point and number of the obtained prediction cloud maps can be controlled by setting a preset time and a preset number of predictions. The preset time can be set to any time, and the preset number of predictions can be set to any positive integer.

[0069] For example, the preset time is set to 1 hour, the preset prediction number is 3, and the last first time point corresponding to the mixed feature data used for prediction is 5 o'clock in the morning. After the prediction, the prediction cloud map for 6 o'clock in the morning, the prediction cloud map for 7 o'clock in the morning and the prediction cloud map for 8 o'clock in the morning are obtained.

[0070] In the above-described scheme, the cloud image to be measured and the meteorological data to be measured are combined in various ways to generate hybrid feature data. This hybrid feature data contains both the image features of the cloud image and the features of the corresponding meteorological data. Predictions based on the hybrid feature data at multiple first time points enable the prediction method to fully consider both the image features and the features of the meteorological data, significantly improving the accuracy of the predicted cloud image at at least one second time point.

[0071] In an example of the present application, as shown in FIG2 , the process of determining the mixed feature data at the first time point includes:

[0072] Step 201 : determining image feature data based on the cloud image to be measured at the first time point, wherein the image feature data is a matrix of three channels.

[0073] For example, after the cloud image to be tested is converted into image feature data, A matrix with three channels.

[0074] Step 202: Determine a matrix of at least one channel based on the matrix sizes of the meteorological data to be measured and the image feature data at the first time point.

[0075] For example, each channel in the image feature data is a 16×16 matrix, and the meteorological data to be measured contains data of four dimensions: temperature, humidity, wind speed, and wind direction. Then, the meteorological data to be measured is converted into a matrix: A 16×16 matrix is ​​created and divided into 64 4×4 matrices. The 4×4 matrix converted from the meteorological data to be measured is then repeatedly inserted into each of the 64 4×4 matrices. Finally, the 16×16 matrix is ​​combined with the image feature data to obtain a 16×16 matrix with four channels.

[0076] For another example, each channel in the image feature data is a 16×16 matrix, and the meteorological data to be measured contains data of five dimensions: temperature, humidity, wind speed, wind direction, and precipitation. Then the meteorological data to be measured can be converted into two matrices, one for If the other matrix has only one dimension of data left, the other positions of the matrix can be filled with the data of the dimension repeatedly or with zero values, then the other can be or Create two 16×16 matrices and divide each of them into 64 4×4 matrices. Repeatedly insert the first 4×4 matrix, converted from the meteorological data to be measured, into the 64 4×4 matrices divided from the first 16×16 matrix. Repeatedly insert the second 4×4 matrix, converted from the meteorological data to be measured, into the 64 4×4 matrices divided from the second 16×16 matrix. Finally, merge the two newly added 16×16 matrices with the image feature data to obtain a 16×16 matrix with five channels.

[0077] Step 203: Merge the matrix of the at least one channel with the image feature data to obtain mixed feature data at the first time point.

[0078] In the above solution, by adding more channels, the features of the meteorological data to be measured are combined with the features of the cloud map to obtain mixed feature data. During the prediction process, since the meteorological data to be measured is tiled in the matrix of the newly added channels, the convolution kernel can capture the features of the meteorological data with each convolution, further improving the accuracy of the predicted cloud map.

[0079] In an example of the present application, as shown in FIG3 , the process of performing prediction based on mixed feature data of multiple first time points includes:

[0080] Step 301: traverse the multiple first time points in chronological order.

[0081] For example, if cloud images and corresponding meteorological data are collected at 5:00 a.m., 6:00 a.m., and 7:00 a.m., the three first time points are traversed in the order of 5:00 a.m., 6:00 a.m., and 7:00 a.m.

[0082] Step 302: determine the first time feature data and the second time feature data of the current first time point based on the mixed feature data of the current first time point, the first time feature data and the second time feature data of the previous first time point, and when the current first time point is the first first time point, the first time feature data and the second time feature data of the corresponding previous first time point are the preset first time feature data and the preset second time feature data.

[0083] The second time feature data includes all previously input feature data, while the first time feature data includes the currently input feature data, and the determination process will be explained through subsequent examples.

[0084] In this application example, it is necessary to set preset first time feature data and preset second time feature data for calculating the first time feature data and the second time feature data at the first first time point. The preset first time feature data and the preset second time feature data can be filled with random fixed numbers or zero values, or can be filled with variables, which are updated during training. This disclosure does not impose any restrictions on this.

[0085] The first time feature data and the second time feature data at the current first time point may be determined based on the mixed feature data at the current first time point, the first time feature data and the second time feature data at the previous first time point.

[0086] For example, if the first first time point traversed is 5 a.m., the first time feature data of the previous first time point is the preset first time feature data, and the second time feature data of the previous first time point is the preset second time feature data. In this way, the first time feature data and the second time feature data of the current first time point (i.e., 5 a.m.) are determined based on the mixed feature data of 5 a.m., the preset first time feature data, and the preset second time feature data. Then, traversing to 6 a.m., the first time feature data and the second time feature data of the current first time point (i.e., 6 a.m.) are determined based on the mixed feature data of 6 a.m., the first time feature data and the second time feature data of the previous first time point (i.e., 5 a.m.).

[0087] Step 303: After the traversal is completed, the first time feature data and the second time feature data of the last first time point are obtained.

[0088] In the above example, the last time traversal is at 7 a.m., based on the mixed feature data at 7 a.m., the first time feature data and the second time feature data of the previous first time point (that is, 6 a.m.), the first time feature data and the second time feature data of 7 a.m. are determined.

[0089] In an example of the present application, after obtaining the first time feature data and the second time feature data of the last first time point, as shown in FIG4 , the process of performing prediction based on the mixed feature data of multiple first time points further includes:

[0090] Step 401: traverse the preset predicted number of second time points in chronological order.

[0091] Continuing with the above example, if the last first time point is 7:00 AM, the preset time is 1 hour, and the preset number of predictions is 3, then the second time points with the preset number of predictions are 8:00 AM, 9:00 AM, and 10:00 AM. The three second time points are then traversed in the order of 8:00 AM, 9:00 AM, and 10:00 AM.

[0092] Step 402, determine the first time feature data and the second time feature data of the current second time point based on the mixed feature data of the current second time point, the first time feature data and the second time feature data of the previous second time point, when the current second time point is the first second time point, the corresponding previous second time point is the last first time point.

[0093] Continuing with the above example, if the first second time point traversed is 8 a.m., the first and second time feature data for 8 a.m. are determined based on the mixed feature data for 8 a.m., the first and second time feature data for the previous second time point (i.e., the last first time point, i.e., 7 a.m.). Then, when traversing to 9 a.m., the first and second time feature data for 9 a.m. are determined based on the mixed feature data for 9 a.m., the first and second time feature data for 8 a.m.

[0094] In one example, the first time point can be associated with the second time point, and the first time point and the second time point with the same sorting can be matched according to the sorting of the first time point in the first time point set and the sorting of the second time point in the second time point set. Then, the mixed feature data of the second time point is the mixed feature data of the corresponding first time point.

[0095] Preferably, the number of first time points is the same as the number of second time points. For example, in the above example, there are three first time points: 5:00 AM, 6:00 AM, and 7:00 AM. Then, there are also three second time points: 8:00 AM, 9:00 AM, and 10:00 AM. According to the order of their respective time point sets, 8:00 AM corresponds to 5:00 AM, so the mixed feature data for 8:00 AM is the same as the mixed feature data for 5:00 AM.

[0096] In another example, a first time point can be selected from the already determined set of first time points as the first first time point corresponding to the first second time point. The first time point following the first first time point is then selected as the second first time point, corresponding to the second second time point, and so on. This example actually removes the first time point before the first first time point from the set of first time points to obtain a new set of first time points. Based on this new set of first time points and second time points, the first time points and second time points with the same order are still matched according to the rules in the above example.

[0097] Step 403 , performing prediction based on the first time feature data and the second time feature data at the current second time point to obtain a prediction cloud map at the current second time point.

[0098] Based on the first time feature data and the second time feature data at the current second time point, a prediction cloud map is obtained. The prediction can be performed using a ConvLSTM model (convolutional long short-term memory neural network), which can more accurately capture the local features and spatiotemporal dependencies in the image data.

[0099] Step 404: After the traversal is completed, a prediction cloud map for each second time point is obtained.

[0100] In the above method, by traversing the second time points, the first time feature data and the second time feature data of each second time point are determined. The second time feature data includes all previously input feature data, while the first time feature data includes the currently input feature data. The prediction cloud map for the second time point is predicted based on the first time feature data and the second time feature data, thereby further improving the accuracy of the obtained prediction cloud map.

[0101] In an example of the present application, as shown in FIG5 , determining the second time feature data at the current time point based on the mixed feature data at the current time point, the first time feature data at the previous time point, and the second time feature data includes:

[0102] Step 501 : determining first weighted feature data and second weighted feature data at the current time point based on mixed feature data at the current time point, first time feature data and second time feature data at the previous time point.

[0103] The first weighted feature data i at the current time point is determined based on the following formula t :

[0104] Among them, X t is the mixed feature data at the current time point, H t-1 is the first time feature data of the previous time point, C t-1 is the second time feature data of the previous time point, W xi is a mixed feature data weight parameter for determining the first weighted feature data, W hi is a first time feature data weight parameter for determining the first weighted feature data, W ci is a weight parameter of the second time feature data used to determine the first weighted feature data, b i is a weight adjustment parameter used to determine the first weighted feature data. * is a convolution operation, o is a Hadamard product operation, and σ is normalization. xi 、W hi 、W ci and b i These are parameters in the model and can be optimized as the model is trained.

[0105] The second weighted feature data f at the current time point is determined based on the following formula t :

[0106] Among them, W xf is a mixed feature data weight parameter for determining the second weighted feature data, W hf is the weight parameter of the first time feature data used to determine the second weighted feature data, W cf is a second time feature data weight parameter for determining the second weighted feature data, b f is a weight adjustment parameter used to determine the second weighted feature data. xf 、W hf 、W cf and b f These are parameters in the model and can be optimized as the model is trained.

[0107] Step 502: Determine the second time feature data at the current time point based on the mixed feature data at the current time point, the first weighted feature data, the second weighted feature data, and the first time feature data at the previous time point.

[0108] The second time feature data C at the current time point is determined based on the following formula t :

[0109] Among them, f t is the second weighted feature data at the current time point, i t is the first weighted feature data at the current time point, W xc is the mixed feature data weight parameter for determining the second time feature data, W hc is the weight parameter of the first time characteristic data used to determine the second time characteristic data, b c is a weight adjustment parameter used to determine the second time feature data. xc 、W hc and b c These are parameters in the model and can be optimized as the model is trained.

[0110] In an example of the present application, as shown in FIG6 , determining the first time feature data at the current time point based on the mixed feature data at the current time point, the first time feature data at the previous time point, and the second time feature data includes:

[0111] Step 601 : determining third weighted feature data at the current time point based on the mixed feature data at the current time point, the second time feature data, and the first time feature data at the previous time point.

[0112] The third weighted feature data o at the current time point is determined based on the following formula t :

[0113] Among them, C t is the second time feature data at the current time point, W xo is a mixed feature data weight parameter for determining the third weighted feature data, W ho is the weight parameter of the first time feature data used to determine the third weighted feature data, W co is the weight parameter of the second time feature data used to determine the third weighted feature data, b o is a weight adjustment parameter used to determine the third weighted feature data. xo 、W ho 、W co and b o These are parameters in the model and can be optimized as the model is trained.

[0114] Step 602: Determine the first time feature data at the current time point based on the third weighted feature data and the second time feature data at the current time point.

[0115] Determine the first time feature data H at the current time point based on the following formulat :

[0116] Among them, t is the third weighted feature data at the current time point.

[0117] In order to implement the above-mentioned cloud map prediction method, as shown in FIG7 , the present application provides an example of a cloud map prediction device, including:

[0118] The acquisition module 10 is used to acquire cloud images and meteorological data to be measured at multiple first time points, where the multiple first time points are different time points at intervals of preset time;

[0119] A calculation module 20, configured to determine mixed characteristic data at the first time point based on the cloud image to be measured and the meteorological data to be measured at the first time point;

[0120] The deep learning module 30 is used to make predictions based on the mixed feature data of the multiple first time points to obtain a prediction cloud map of a preset number of second time points, where the preset number of second time points are different time points separated by the preset time, and the first second time point is later than the last first time point and is separated by the preset time.

[0121] Among them, also include:

[0122] The calculation module 20 is further configured to determine image feature data based on the cloud image to be measured at the first time point, wherein the image feature data is a matrix of three channels;

[0123] The calculation module 20 is further configured to determine a matrix of at least one channel based on the matrix size of the meteorological data to be measured and the image feature data at the first time point;

[0124] The processing module 40 is configured to merge the matrix of the at least one channel with the image feature data to obtain mixed feature data at the first time point.

[0125] The calculation module 20 is further configured to traverse the plurality of first time points in chronological order;

[0126] The calculation module 20 is further configured to determine the first time feature data and the second time feature data of the current first time point based on the mixed feature data of the current first time point, the first time feature data and the second time feature data of the previous first time point, and when the current first time point is the first first time point, the first time feature data and the second time feature data of the corresponding previous first time point are the preset first time feature data and the preset second time feature data;

[0127] The calculation module 20 is further configured to obtain the first time feature data and the second time feature data of the last first time point after the traversal is completed.

[0128] The calculation module 20 is further configured to traverse the preset predicted number of second time points in chronological order;

[0129] The calculation module 20 is further configured to determine the first time feature data and the second time feature data of the current second time point based on the mixed feature data of the current second time point, the first time feature data and the second time feature data of the previous second time point, where when the current second time point is the first second time point, the corresponding previous second time point is the last first time point;

[0130] The deep learning module 30 is further configured to perform prediction based on the first time feature data and the second time feature data at the current second time point to obtain a prediction cloud map at the current second time point;

[0131] The calculation module 20 is further configured to obtain a prediction cloud map at each second time point after the traversal is completed.

[0132] The calculation module 20 is further configured to determine the first weighted feature data and the second weighted feature data at the current time point based on the mixed feature data at the current time point, the first time feature data and the second time feature data at the previous time point;

[0133] The calculation module 20 is further configured to determine the second time feature data at the current time point based on the mixed feature data at the current time point, the first weighted feature data, the second weighted feature data, and the first time feature data at the previous time point.

[0134] The calculation module 20 is further configured to determine the third weighted feature data at the current time point based on the mixed feature data at the current time point, the second time feature data, and the first time feature data at the previous time point;

[0135] The calculation module 20 is further configured to determine the first time feature data at the current time point based on the third weighted feature data and the second time feature data at the current time point.

[0136] In the above-described scheme, the cloud image to be measured and the meteorological data to be measured are combined in various ways to generate hybrid feature data. This hybrid feature data contains both the image features of the cloud image and the features of the corresponding meteorological data. Predictions based on the hybrid feature data at multiple first time points enable the prediction method to fully consider both the image features and the features of the meteorological data, significantly improving the accuracy of the predicted cloud image at at least one second time point.

[0137] In one example, an embodiment of the present application also provides a mobile terminal, which includes at least one memory and a processor communicatively connected to the at least one memory; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are configured to execute the cloud map prediction method described in any one of the embodiments of Figures 1 to 6 above.

[0138] In addition, an embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the cloud map prediction method process described in any one of the embodiments of Figures 1 to 6 above.

[0139] In the description of this specification, the reference terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials, or characteristics described may be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification, as well as features of different embodiments or examples, unless they are mutually inconsistent.

[0140] 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. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. In the description of the embodiments of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0141] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0142] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0143] 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 merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interface, indirect coupling or communication connection of the device or unit, which may be electrical, mechanical or other forms.

[0144] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0145] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program code.

[0146] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A cloud map prediction method, the method comprising: Collecting cloud images to be measured and meteorological data to be measured at multiple first time points, wherein the multiple first time points are different time points at intervals of preset time; Determine the mixed characteristic data at the first time point based on the cloud image to be measured and the meteorological data to be measured at the first time point; Based on the mixed feature data of the multiple first time points, prediction is performed to obtain a prediction cloud map of a preset number of second time points, wherein the preset number of second time points are different time points separated by the preset time, and the first second time point is later than the last first time point and separated by the preset time.

2. The cloud image prediction method according to claim 1, wherein: The determining of the mixed characteristic data at the first time point based on the cloud image to be measured and the meteorological data to be measured at the first time point includes: Determine image feature data based on the cloud image to be measured at the first time point, wherein the image feature data is a matrix of three channels; Determine a matrix of at least one channel based on the matrix sizes of the meteorological data to be measured and the image feature data at the first time point; The matrix of the at least one channel is combined with the image feature data to obtain mixed feature data at the first time point.

3. The cloud image prediction method according to claim 1, wherein: The predicting based on the mixed feature data of the multiple first time points includes: Traversing the multiple first time points in chronological order; The first time feature data and the second time feature data of the current first time point are determined based on the mixed feature data of the current first time point, the first time feature data and the second time feature data of the previous first time point, and when the current first time point is the first first time point, the first time feature data and the second time feature data of the corresponding previous first time point are Preset first time characteristic data and preset second time characteristic data; After the traversal is completed, the first time feature data and the second time feature data of the last first time point are obtained.

4. The cloud image prediction method according to claim 3, wherein: After obtaining the first time feature data and the second time feature data of the last first time point, performing prediction based on the mixed feature data of the plurality of first time points further includes: Traversing the preset predicted number of second time points in chronological order; Determine the first time feature data and the second time feature data of the current second time point based on the mixed feature data of the current second time point, the first time feature data and the second time feature data of the previous second time point, when the current second time point is the first second time point, the corresponding previous second time point is the last first time point; Perform prediction based on the first time feature data and the second time feature data at the current second time point to obtain a prediction cloud map at the current second time point; After the traversal is completed, a prediction cloud map is obtained for each second time point.

5. The cloud image prediction method according to claim 3 or 4, wherein: Determining the second time feature data at the current time point based on the mixed feature data at the current time point, the first time feature data at the previous time point, and the second time feature data includes: Determine first weighted feature data and second weighted feature data at the current time point based on the mixed feature data at the current time point, the first time feature data and the second time feature data at the previous time point; The second time feature data at the current time point is determined based on the mixed feature data at the current time point, the first weighted feature data, the second weighted feature data and the first time feature data at the previous time point.

6. The cloud image prediction method according to claim 5, wherein: Determining the first time feature data at the current time point based on the mixed feature data at the current time point, the first time feature data at the previous time point, and the second time feature data includes: Determine third weighted feature data at the current time point based on the mixed feature data at the current time point, the second time feature data, and the first time feature data at the previous time point; The first time feature data at the current time point is determined based on the third weighted feature data and the second time feature data at the current time point.

7. A cloud map prediction device, comprising: A collection module, used for collecting cloud images to be measured and meteorological data to be measured at multiple first time points, wherein the multiple first time points are different time points with preset time intervals; A calculation module, used to determine the mixed characteristic data at the first time point based on the cloud image to be measured and the meteorological data to be measured at the first time point; A deep learning module is used to make predictions based on the mixed feature data of the multiple first time points to obtain a prediction cloud map of a preset number of second time points, wherein the preset number of second time points are different time points separated by the preset time, and the first second time point is later than the last first time point and separated by the preset time.

8. The cloud image prediction device according to claim 7, wherein: Also includes: The calculation module is further used to determine image feature data based on the cloud image to be measured at the first time point, wherein the image feature data is a matrix of three channels; The calculation module is further used to determine the matrix of at least one channel based on the matrix size of the meteorological data to be measured and the image feature data at the first time point; A processing module is used to merge the matrix of the at least one channel with the image feature data to obtain mixed feature data at the first time point.

9. The cloud image prediction device according to claim 7, wherein: The calculation module is further used to traverse the multiple first time points in chronological order; The calculation module is further used to determine the first time feature data and the second time feature data at the current first time point based on the mixed feature data at the current first time point, the first time feature data and the second time feature data at the previous first time point, and the first time feature data and the second time feature data at the current first time point. When it is the first first time point, the first time feature data and the second time feature data of the corresponding previous first time point are the preset first time feature data and the preset second time feature data; The calculation module is also used to obtain the first time feature data and the second time feature data of the last first time point after the traversal is completed.

10. The cloud image prediction device according to claim 9, wherein: The calculation module is further used to traverse the second time points of the preset predicted number in chronological order; The calculation module is further used to determine the first time feature data and the second time feature data of the current second time point based on the mixed feature data of the current second time point, the first time feature data and the second time feature data of the previous second time point, when the current second time point is the first second time point, the corresponding previous second time point is the last first time point; The deep learning module is further used to make a prediction based on the first time feature data and the second time feature data at the current second time point to obtain a prediction cloud map at the current second time point; The calculation module is also used to obtain the prediction cloud map at each second time point after the traversal is completed.

Images