Sample mapping relation determination method and device

By acquiring and processing the SST data sets, the sample mapping relationship of SST data is established, which solves the problem of neglecting the sea space connection in the existing technology and improves the accuracy of ocean temperature prediction.

CN118916633APending Publication Date: 2024-11-08HUANENG GUANGDONG SHANTOU OFFSHORE WIND POWER CO LTD +3
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410964250.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing deep learning-based ocean temperature prediction methods mainly use timing prediction, which ignores the spatial connections inside the ocean, resulting in insufficient feature extraction and inability to fully utilize the spatial information in ocean temperature data, limiting the improvement of prediction accuracy.

Method used

By obtaining the SST data set in the target period of the target area, determining the SST data set based on the depth characteristics of the SST data, and determining the feature set data and label data based on the time characteristics, establishing a sample mapping relationship to train the SST prediction model. Fully consider the spatial and temporal characteristics of the SST data.

Benefits of technology

It realizes a more accurate capture of dynamic changes in sea temperature data, improves the accuracy of ocean temperature prediction, and enhances the accuracy of prediction models.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118916633A_ABST
    Figure CN118916633A_ABST
Patent Text Reader

Abstract

The invention provides a sample mapping relation determination method and device, and the method comprises the steps: obtaining a sea temperature data set in a target time period of a target region; determining at least one sea temperature data set from the sea temperature data set according to the depth features of the sea temperature data in the sea temperature data set; for any sea temperature data group, determining feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group according to the time features of the sea temperature data in the sea temperature data group; for any target sea temperature data in the sea temperature data set, determining a sample mapping relationship between feature set data corresponding to the target sea temperature data and tag data corresponding to the target sea temperature data; wherein the sample mapping relation is used for training the sea temperature prediction model. Therefore, in the process of determining the sample mapping relation, the spatial features and the time features of the sea temperature data are fully considered, the dynamic change process of the sea temperature data can be more accurately captured, and thus accurate prediction of future sea temperature data is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of ocean observation technology, and in particular to a method and device for determining a sample mapping relationship. Background Art

[0002] Sea temperature (ocean temperature) is one of the key factors of the marine environment. It characterizes the absorption and release of heat by seawater, reflects the energy exchange in the global atmosphere and marine ecosystem, and has a great impact on many environmental and climate issues. Ocean temperature prediction is a key meteorological and oceanographic task, which is of great significance for marine resource management, shipping safety, fishery decision-making, and climate change research. In recent years, with the intensification of climate change, accurate prediction of ocean temperature has become particularly critical.

[0003] In the related technologies, the ocean temperature prediction methods based on deep learning are mainly based on time series prediction, ignoring the spatial connection within the ocean. Moreover, the point-by-point prediction method will lead to insufficient feature extraction and fail to fully utilize the spatial information in the ocean temperature data, thus limiting the improvement of prediction accuracy. Summary of the invention

[0004] The present invention provides a method and device for determining a sample mapping relationship, so as to solve one of the technical problems in the related art at least to a certain extent. The technical solution of the present invention is as follows:

[0005] According to a first aspect of an embodiment of the present invention, a method for determining a sample mapping relationship is provided, comprising: obtaining a sea temperature data set within a target area and a target time period; wherein the sea temperature data set includes a plurality of sea temperature data, each of the sea temperature data carries a longitude feature, a latitude feature, a time feature and a depth feature; determining at least one sea temperature data group from the sea temperature data set according to the depth feature of each of the sea temperature data in the sea temperature data set; wherein any of the sea temperature data groups includes a plurality of the sea temperature data; for any of the sea temperature data groups, determining feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group according to the time feature of each of the sea temperature data in the sea temperature data group; for any of the target sea temperature data in the sea temperature data group, determining a sample mapping relationship between the feature set data corresponding to the target sea temperature data and the label data corresponding to the target sea temperature data; wherein the sample mapping relationship is used to train a sea temperature prediction model.

[0006] According to a second aspect of an embodiment of the present invention, a sample mapping relationship determination device is provided, comprising: an acquisition module, used to acquire a sea temperature data set within a target area and a target time period; wherein the sea temperature data set includes a plurality of sea temperature data, each of which carries a longitude feature, a latitude feature, a time feature and a depth feature; a first determination module, used to determine at least one sea temperature data group from the sea temperature data set according to the depth feature of each of the sea temperature data in the sea temperature data set; wherein any of the sea temperature data groups includes a plurality of the sea temperature data; a second determination module, used to determine, for any of the sea temperature data groups, feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group according to the time feature of each of the sea temperature data in the sea temperature data group; a third determination module, used to determine, for any of the target sea temperature data in the sea temperature data group, a sample mapping relationship between the feature set data corresponding to the target sea temperature data and the label data corresponding to the target sea temperature data; wherein the sample mapping relationship is used to train a sea temperature prediction model.

[0007] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the sample mapping relationship determination method as described in the embodiment of the first aspect of the present invention.

[0008] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the sample mapping relationship determination method as described in the embodiment of the first aspect of the present invention.

[0009] According to a fifth aspect of an embodiment of the present invention, a computer program product is provided, including: a computer program, which, when executed by a processor, implements the sample mapping relationship determination method as described in the embodiment of the first aspect of the present invention.

[0010] The technical solution provided by the embodiments of the present invention brings at least the following beneficial effects:

[0011] In this technical solution, a sea temperature data set within a target period of time in a target area is obtained; wherein the sea temperature data set includes multiple sea temperature data, each of which carries longitude characteristics, latitude characteristics, time characteristics and depth characteristics; according to the depth characteristics of each sea temperature data in the sea temperature data set, at least one sea temperature data group is determined from the sea temperature data set; wherein any sea temperature data group includes multiple sea temperature data; for any sea temperature data group, according to the time characteristics of each sea temperature data in the sea temperature data group, feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group are determined; for any target sea temperature data in the sea temperature data group, a sample mapping relationship between feature set data corresponding to the target sea temperature data and label data corresponding to the target sea temperature data is determined; wherein the sample mapping relationship is used to train a sea temperature prediction model. Therefore, in the process of determining the sample mapping relationship, the spatial characteristics and time characteristics of the sea temperature data are fully considered, which is conducive to more accurately capturing the dynamic change process of the sea temperature data, thereby realizing accurate prediction of future sea temperature data. In addition, in addition to determining multiple groups of sample mapping relationships in the sea temperature data set, the present invention can also use a sample generator to dynamically generate sea temperature data to increase the number of sample mapping relationships and improve the prediction accuracy of the sea temperature prediction model.

[0012] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0014] Figure 1 A schematic diagram of a flow chart of a method for determining a sample mapping relationship provided by an embodiment of the present invention;

[0015] Figure 2 A schematic flow chart of another sample mapping relationship determination method provided by an embodiment of the present invention;

[0016] Figure 3 A schematic diagram of the structure of a sample mapping relationship determination device provided by an embodiment of the present invention;

[0017] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0019] The following describes a method and apparatus for determining a sample mapping relationship according to an embodiment of the present invention with reference to the accompanying drawings.

[0020] Figure 1 A schematic flow chart of a method for determining a sample mapping relationship provided by an embodiment of the present invention.

[0021] like Figure 1 As shown, the sample mapping relationship determination method includes the following steps:

[0022] Step 101, obtaining a sea temperature dataset in a target area and a target period.

[0023] The sea temperature data set includes multiple sea temperature data, each of which carries longitude features, latitude features, time features and depth features.

[0024] Among them, the longitude feature is used to indicate the longitude of the sea temperature data, the latitude feature is used to indicate the latitude of the sea temperature data, the time feature is used to indicate the acquisition time of the sea temperature data, and the depth feature is used to indicate the depth level of the sea temperature data.

[0025] As a possible implementation method, for any sea temperature data, it is possible to determine whether the sea temperature data is in the target area based on the longitude indicated by the longitude feature of the sea temperature data and the latitude indicated by the latitude feature of the sea temperature data, and to determine whether the sea temperature data is within the target time period based on the acquisition time indicated by the time feature of the sea temperature data.

[0026] As an example, the depth levels may be 0m, 50m, 100m, 200m and 300m respectively, so that the depth feature of each sea temperature data in the sea temperature dataset may be any value among 0m, 50m, 100m, 200m and 300m.

[0027] In a possible implementation, when executing step 101 to obtain the sea temperature dataset in the target area and the target period, the following steps may be specifically performed:

[0028] Step 1011, obtaining multi-layer sea temperature data.

[0029] Among them, the time range of the multi-layer SST data includes the target period.

[0030] The multi-layer sea temperature data refers to the sea temperature data measured at different depth levels (such as 0m, 10m, 50m, 100m, 200m, etc.). Optionally, these data can be obtained through buoys, submerged buoys, shipboard instruments, satellite remote sensing, etc.

[0031] It should be noted that each layer of sea temperature data in the multi-layer sea temperature data corresponds to a depth level.

[0032] As a possible implementation method, the global ocean Argo grid dataset with a time range including the target period can be obtained from the Argo (Array for Real-time Geostrophic Oceanography) data center. Optional datasets include but are not limited to BOA_Argo, GDCSM_Argo, etc.

[0033] Among them, the global ocean Argo grid dataset contains the seawater temperature and salinity from the sea surface to a depth of 1975 meters in the global ocean, as well as physical ocean environmental elements such as sound velocity, mixed layer depth, lower boundary depth of the thermocline and thermocline intensity. Its horizontal resolution is usually 1°×1°, covering the global range (0°-360° longitude, 80°S-80°N latitude). Vertically, it is divided into 58 layers with unequal intervals within the water depth range of 0-1975 meters to capture the ocean environment information at different depth layers. The temporal resolution is usually monthly.

[0034] In summary, the global ocean Argo grid dataset whose time range includes the target period is obtained, that is, the multi-layer sea temperature data whose time range includes the target period is obtained.

[0035] Step 1012, splicing the multiple layers of sea temperature data in the time dimension, selecting multiple layers of sea temperature data within a target period from the spliced ​​multiple layers of sea temperature data, and constructing a first sea temperature data set.

[0036] It should be noted that before splicing, it may be necessary to preprocess the multi-layer sea temperature data. As a possible implementation method, preprocess the multi-layer sea temperature data; wherein the data preprocessing includes at least one of the following:

[0037] Data cleaning;

[0038] Data formatting.

[0039] That is, before splicing, the multi-layer SST data can be cleaned (removing outliers, missing values, etc.) and formatted (ensuring that the data format is unified).

[0040] Each layer of sea temperature data includes at least one sea temperature data, and each sea temperature data in each layer of sea temperature data also carries longitude characteristics, latitude characteristics, time characteristics and depth characteristics. It can be understood that since each layer of sea temperature data corresponds to a depth level, that is, the depth level indicated by the depth characteristics of each sea temperature data in each layer of sea temperature data is the same, the depth characteristics of each sea temperature data in each layer of sea temperature data have the same value.

[0041] As a possible implementation method, when splicing multiple layers of sea temperature data in time latitude, each layer of sea temperature data can be spliced ​​in time dimension to obtain the spliced ​​multiple layers of sea temperature data. It should be noted that the time dimension of each sea temperature data in each layer of spliced ​​sea temperature data is consistent, that is, the dimension of the acquisition time indicated by the time characteristics of each sea temperature data in each layer of spliced ​​sea temperature data is the same.

[0042] Among them, the splicing of each layer of sea temperature data in the time dimension is to splice each sea temperature data together in time order according to the acquisition time indicated by the time characteristics of each sea temperature data in each layer of sea temperature data.

[0043] As a possible implementation method, when splicing each layer of sea temperature data in the time dimension, the splicing strategy can be determined first, and then the splicing is performed. Among them, the splicing strategy is used to indicate the time dimension according to which each layer of sea temperature data in the time range is spliced. For example, if the splicing strategy is to splice each layer of sea temperature data in the time range according to the month, then when the time resolution of the multi-layer sea temperature data is monthly, since the acquisition time indicated by the time feature of each sea temperature data is the corresponding month, it is only necessary to splice each layer of sea temperature data in the time range in the order of months. When the time resolution of the multi-layer sea temperature data is daily or higher frequency, since the acquisition time indicated by the time feature of each sea temperature data is no longer a month, it is necessary to first determine the sea temperature data corresponding to each month, and then splice. Optionally, the monthly average sea temperature can be used as the sea temperature data corresponding to each month, so that the sea temperature data corresponding to each month in the time range are spliced ​​in the order of months.

[0044] In summary, by splicing each layer of sea temperature data in the time dimension, each layer of sea temperature data after splicing within the time range can be obtained. Since the time range includes the target period, each layer of sea temperature data within the target period can be selected from each layer of sea temperature data after splicing within the time range, and then the first sea temperature data set can be constructed based on the multi-layer sea temperature data within the selected target period.

[0045] Step 1013, performing regional selection on the sea temperature data in the first sea temperature data set to obtain a sea temperature data set within a target area and a target period.

[0046] The first sea temperature data set includes a plurality of sea temperature data, and each sea temperature data also carries longitude features, latitude features, time features and depth features.

[0047] As a possible implementation method, the sea temperature data in the first sea temperature data set can be regionally selected according to the longitude indicated by the longitude feature and the latitude indicated by the latitude feature of each sea temperature data in the first sea temperature data set to obtain the sea temperature data set within the target area and target period.

[0048] Among them, the sea temperature data in the first sea temperature data set are regionally selected according to the longitude indicated by the longitude characteristics of each sea temperature data in the first sea temperature data set and the latitude indicated by the latitude characteristics, that is, the sea temperature data in the first sea temperature data set that are not in the target area are eliminated according to the longitude indicated by the longitude characteristics of each sea temperature data in the first sea temperature data set and the latitude indicated by the latitude characteristics.

[0049] In summary, as an example, the process of obtaining the sea temperature dataset in the target area and target period is as follows:

[0050] First, the global ocean Argo grid data with a time range including the target period is obtained from the Argo data center, and the multi-layer sea temperature data with a time range including the target period is obtained. Then, the multi-layer sea temperature data is spliced ​​in the time dimension to select the multi-layer sea temperature data within the target period from the spliced ​​multi-layer sea temperature data to construct a sea temperature four-dimensional data set (longitude, latitude, time and depth). The water depths corresponding to each data layer in the data set are 0m, 50m, 100m, 200m and 300m respectively. Finally, the three-dimensional data of 5 different depths created are regionally selected to obtain the sea temperature data set within the target period of the target area.

[0051] It should be noted that when obtaining the sea temperature dataset in the target area and target period, in addition to first constructing a sea temperature dataset based on the multi-layer sea temperature data in the target period and then performing region selection, you can also first perform region selection and then construct the sea temperature dataset. The specific steps are as follows:

[0052] First, multiple layers of sea temperature data are obtained, wherein the time range of the multiple layers of sea temperature data includes the target period. Then, the multiple layers of sea temperature data are spliced ​​in the time dimension to obtain the multiple layers of sea temperature data within the target period based on the spliced ​​multiple layers of sea temperature data. Then, the multiple layers of sea temperature data within the target period are selected in an area to obtain the sea temperature data within the target area within the target period. Finally, based on the sea temperature data within the target area within the target period, a sea temperature dataset within the target area within the target period is constructed.

[0053] Step 102: determining at least one sea temperature data group from the sea temperature data set according to the depth characteristics of each sea temperature data in the sea temperature data set.

[0054] Among them, any sea temperature data group includes multiple sea temperature data (in the sea temperature data set).

[0055] As a possible implementation method, multiple sea temperature data with the same depth feature value in the sea temperature data set can be determined as a sea temperature data group according to the depth feature of each sea temperature data in the sea temperature data set. Thus, if there are several values ​​of the depth feature of each sea temperature data in the sea temperature data set, several groups of sea temperature data groups can be determined, and the depth feature values ​​of each sea temperature data in each sea temperature data group are the same.

[0056] Step 103, for any sea temperature data group, determine the feature set data and label data corresponding to the target sea temperature data in the sea temperature data group according to the time characteristics of each sea temperature data in the sea temperature data group.

[0057] In some embodiments, for any sea temperature data group, feature set data and label data corresponding to target sea temperature data can be determined from each sea temperature data according to the acquisition time indicated by the time characteristics of each sea temperature data in the sea temperature data group.

[0058] In a possible implementation, when executing step 103 for any sea temperature data group, determining the feature set data and label data corresponding to the target sea temperature data in the sea temperature data group according to the time characteristics of each sea temperature data in the sea temperature data group, the following steps may be specifically performed:

[0059] Step 1031 , for any sea temperature data group, normalize each sea temperature data in the sea temperature data group to obtain a normalized value corresponding to each sea temperature data in the sea temperature data group.

[0060] As a possible implementation method, the following formula can be used to determine the normalized value corresponding to each sea temperature data in each sea temperature data group:

[0061]

[0062] Among them, x normal represents the normalized value corresponding to any sea temperature data x in any sea temperature data set, x max represents the maximum value of the sea temperature data in any sea temperature data group, x min Indicates the minimum value of the sea temperature data in any sea temperature data group.

[0063] Step 1032, according to the time characteristics of each sea temperature data in the sea temperature data group, determine the feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group from the normalized values ​​corresponding to each sea temperature data in the sea temperature data group.

[0064] As a possible implementation method, for any target sea temperature data in the sea temperature data group, according to the time characteristics of each sea temperature data in the sea temperature data group, the first sea temperature data whose time characteristics are before the time characteristics of the target sea temperature data and the second sea temperature data whose time characteristics are after the time characteristics of the target sea temperature data can be determined, wherein the target sea temperature data is the sea temperature data in the sea temperature data group that has at least a first set number of first sea temperature data and at least a second set number of second sea temperature data. Furthermore, the normalized value corresponding to the target sea temperature data and the normalized value corresponding to the first set number of first sea temperature data adjacent to the target sea temperature data can be determined as the feature set data corresponding to the target sea temperature data, and the normalized value corresponding to the second set number of second sea temperature data adjacent to the target sea temperature data can be determined as the label data corresponding to the target sea temperature data.

[0065] Among them, the first sea temperature data refers to the sea temperature data whose acquisition time indicated by the time characteristics is before the acquisition time indicated by the time characteristics of the target sea temperature data, and the second sea temperature data refers to the sea temperature data whose acquisition time indicated by the time characteristics is after the acquisition time indicated by the time characteristics of the target sea temperature data.

[0066] The first set number and the second set number can be any set value, which is not limited in the present invention. For example, assuming that the first set number is 12 and the second set number is 1, the target sea temperature data is the sea temperature data having at least 12 first sea temperature data and at least 1 second sea temperature data in the sea temperature data group, so that for any target sea temperature data, the normalized value corresponding to the target sea temperature data and the normalized values ​​corresponding to the 12 first sea temperature data adjacent to the target sea temperature data can be determined as the feature set data corresponding to the target sea temperature data, and the normalized value corresponding to the 1 second sea temperature data adjacent to the target sea temperature data can be determined as the label data corresponding to the target sea temperature data. Assuming that the target sea temperature data is the sea temperature data with an acquisition time of t indicated by the time feature, the 12 first sea temperature data adjacent to the target sea temperature data are the sea temperature data with an acquisition time of t-1 to t-12 indicated by the time feature, and the 1 second sea temperature data adjacent to the target sea temperature data is the sea temperature data with an acquisition time of t+1 indicated by the time feature.

[0067] Step 104 , for any target sea temperature data in the sea temperature data group, determine a sample mapping relationship between feature set data corresponding to the target sea temperature data and label data corresponding to the target sea temperature data.

[0068] Among them, the sample mapping relationship is used to train the sea temperature prediction model.

[0069] In the present invention, at least one sea temperature data group is determined based on spatial characteristics, and for each sea temperature data group, feature set data and label data are determined based on temporal characteristics, thereby determining a sample mapping relationship between the feature set data and the label data. Therefore, in the process of determining the sample mapping relationship, the spatial characteristics and temporal characteristics of the sea temperature data are fully considered, which is conducive to more accurately capturing the dynamic change process of the sea temperature data.

[0070] In summary, by obtaining a sea temperature data set within a target period of time in a target area; wherein the sea temperature data set includes multiple sea temperature data, each of which carries longitude characteristics, latitude characteristics, time characteristics and depth characteristics; according to the depth characteristics of each sea temperature data in the sea temperature data set, at least one sea temperature data group is determined from the sea temperature data set; wherein any sea temperature data group includes multiple sea temperature data; for any sea temperature data group, according to the time characteristics of each sea temperature data in the sea temperature data group, the feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group are determined; for any target sea temperature data in the sea temperature data group, the sample mapping relationship between the feature set data corresponding to the target sea temperature data and the label data corresponding to the target sea temperature data is determined; wherein the sample mapping relationship is used to train the sea temperature prediction model. Therefore, in the process of determining the sample mapping relationship, the spatial characteristics and temporal characteristics of the sea temperature data are fully considered, which is conducive to more accurately capturing the dynamic change process of the sea temperature data, thereby realizing accurate prediction of future sea temperature data.

[0071] In the present invention, a sample generator can also be used to dynamically generate sea temperature data to increase the number of sample mapping relationships and improve the prediction accuracy of the sea temperature prediction model. Figure 2 , which explains this process.

[0072] Figure 2 A schematic flow chart of another sample mapping relationship determination method provided by an embodiment of the present invention.

[0073] like Figure 2 As shown, the sample mapping relationship determination method may include the following steps:

[0074] Step 201, obtaining a sea temperature dataset in a target area and a target period.

[0075] Step 202: determining at least one sea temperature data group from the sea temperature data set according to the depth characteristics of each sea temperature data in the sea temperature data set.

[0076] Step 203, for any sea temperature data group, determine the feature set data and label data corresponding to the target sea temperature data in the sea temperature data group according to the time characteristics of each sea temperature data in the sea temperature data group.

[0077] Step 204 , for any target sea temperature data in the sea temperature data group, determine a sample mapping relationship between feature set data corresponding to the target sea temperature data and label data corresponding to the target sea temperature data.

[0078] It should be noted that the execution process of steps 201 to 204 can be implemented in any manner in the embodiments of the present invention, and the embodiments of the present invention do not limit this and will not be described in detail.

[0079] Step 205, training a sample generator corresponding to the sea temperature data group according to the feature set data and label data corresponding to the target sea temperature data in the sea temperature data group, so that the sample generator corresponding to the trained sea temperature data group learns the correspondence between the feature set data and the label data.

[0080] As a possible implementation method, for any target sea temperature data in the sea temperature data group, the feature set data corresponding to the target sea temperature data can be used as the input of the sample generator corresponding to the sea temperature data group, and the label data corresponding to the target sea temperature data can be used as the output of the sample generator corresponding to the sea temperature data group. The sample generator corresponding to the sea temperature data group can be trained so that the trained sample generator corresponding to the sea temperature data group can learn the correspondence between the feature set data and the label data.

[0081] Step 206 , determining a sample mapping relationship between at least one set of feature set data and label data based on each sea temperature data in the sea temperature data group and the sea temperature data generated by a sample generator corresponding to the trained sea temperature data group.

[0082] In a possible implementation, when executing step 206, based on each sea temperature data in the sea temperature data group and the sea temperature data generated by the sample generator corresponding to the trained sea temperature data group, determining the sample mapping relationship between at least one set of feature set data and the label data, the following steps may be specifically performed:

[0083] Step 2061, using the normalized value corresponding to each sea temperature data in the sea temperature data group and / or the sea temperature data generated by the sample generator corresponding to the trained sea temperature data group as the input of the sample generator corresponding to the trained sea temperature data group, so as to obtain the sea temperature data output by the sample generator corresponding to the trained sea temperature data group.

[0084] In some embodiments, when the sample generator is used to generate sea temperature data, the last sea temperature data in the sea temperature data group can be used as the target sea temperature data, the feature set data corresponding to the target sea temperature data is determined, and the feature set data corresponding to the target sea temperature data is input into the sample generator corresponding to the trained sea temperature data group to obtain the sea temperature data output by the sample generator corresponding to the trained sea temperature data group. Optionally, the feature set data corresponding to the target sea temperature data can be the normalized value corresponding to the target sea temperature data and the normalized values ​​corresponding to the first set number of first sea temperature data adjacent to the target sea temperature data, wherein the first sea temperature data is the sea temperature data whose time feature is before the time feature of the target sea temperature data, so that the sea temperature data output by the sample generator corresponding to the trained sea temperature data group is the second set number of second sea temperature data adjacent to the target sea temperature data, wherein the second sea temperature data is the sea temperature data whose time feature is after the time feature of the target sea temperature data.

[0085] After that, any sea temperature data output by the sample generator corresponding to the trained sea temperature data group can be used as the target sea temperature data, the feature set data corresponding to the target sea temperature data can be determined, and the feature set data corresponding to the target sea temperature data can be input into the sample generator corresponding to the trained sea temperature data group to obtain the sea temperature data output by the sample generator corresponding to the trained sea temperature data group. Thus, by using the sample generator to dynamically generate sea temperature data in batches, the amount of sea temperature data can be increased, and then the number of sample mapping relationships can be increased, thereby improving the prediction accuracy of the sea temperature prediction model.

[0086] Step 2062, using the input of the sample generator corresponding to the trained sea temperature data group as feature set data, and the output of the sample generator corresponding to the trained sea temperature data group as label data, to determine a sample mapping relationship between at least one set of feature set data and label data.

[0087] In some embodiments, any set of inputs and outputs of the sample generator corresponding to the trained sea temperature data set can be determined as a set of sample mapping relationships. Therefore, in the present invention, in addition to determining multiple sets of sample mapping relationships in the sea temperature data set, the number of sample mapping relationships can be increased based on the sample generator to improve the prediction accuracy of the sea temperature prediction model.

[0088] In summary, by training the sample generator corresponding to the sea temperature data group according to the feature set data and label data corresponding to the target sea temperature data in the sea temperature data group, the sample generator corresponding to the trained sea temperature data group learns the corresponding relationship between the feature set data and the label data; according to each sea temperature data in the sea temperature data group, and the sea temperature data generated by the sample generator corresponding to the trained sea temperature data group, at least one set of sample mapping relationships between the feature set data and the label data is determined. Therefore, by dynamically generating sea temperature data in batches using a sample generator, the amount of sea temperature data can be increased, and then the number of sample mapping relationships can be increased, thereby improving the prediction accuracy of the sea temperature prediction model.

[0089] In order to implement the above embodiment, the present invention also proposes a sample mapping relationship determination device.

[0090] Figure 3 A schematic diagram of the structure of a device for determining a sample mapping relationship provided by an embodiment of the present invention.

[0091] like Figure 3 As shown, the sample mapping relationship determination device includes: an acquisition module 31 , a first determination module 32 , a second determination module 33 and a third determination module 34 .

[0092] The acquisition module 31 is used to acquire a sea temperature data set in a target area and a target period; wherein the sea temperature data set includes a plurality of sea temperature data, each of which carries a longitude feature, a latitude feature, a time feature and a depth feature;

[0093] A first determination module 32 is used to determine at least one sea temperature data group from the sea temperature data set according to the depth characteristics of each sea temperature data in the sea temperature data set; wherein any sea temperature data group includes multiple sea temperature data;

[0094] The second determination module 33 is used to determine, for any sea temperature data group, feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group according to the time characteristics of each sea temperature data in the sea temperature data group;

[0095] The third determination module 34 is used to determine, for any target sea temperature data in the sea temperature data group, a sample mapping relationship between feature set data corresponding to the target sea temperature data and label data corresponding to the target sea temperature data; wherein the sample mapping relationship is used to train the sea temperature prediction model.

[0096] Furthermore, in a possible implementation of the embodiment of the present invention, the first determining module 32 is further configured to:

[0097] According to the depth characteristics of each sea temperature data in the sea temperature data set, multiple sea temperature data with the same depth characteristic value in the sea temperature data set are determined as a sea temperature data group.

[0098] Further, in a possible implementation of the embodiment of the present invention, the second determining module 33 includes:

[0099] A processing unit, for performing normalization processing on each sea temperature data in any sea temperature data group to obtain a normalized value corresponding to each sea temperature data in the sea temperature data group;

[0100] The determination unit is used to determine the feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group from the normalized values ​​corresponding to each sea temperature data in the sea temperature data group according to the time characteristics of each sea temperature data in the sea temperature data group.

[0101] Furthermore, in a possible implementation manner of the embodiment of the present invention, the determining unit is further configured to:

[0102] For any target sea temperature data in the sea temperature data group, determine, according to the time characteristics of each sea temperature data in the sea temperature data group, first sea temperature data whose time characteristics are before the time characteristics of the target sea temperature data, and second sea temperature data whose time characteristics are after the time characteristics of the target sea temperature data; wherein the target sea temperature data is sea temperature data in which there are at least a first set number of first sea temperature data and at least a second set number of second sea temperature data in the sea temperature data group;

[0103] Determine the normalized value corresponding to the target sea temperature data and the normalized values ​​corresponding to a first set number of first sea temperature data adjacent to the target sea temperature data as feature set data corresponding to the target sea temperature data;

[0104] The normalized values ​​corresponding to a second set number of second sea temperature data adjacent to the target sea temperature data are determined as label data corresponding to the target sea temperature data.

[0105] Furthermore, in a possible implementation of the embodiment of the present invention, the above-mentioned device further includes:

[0106] A training module is used to train a sample generator corresponding to the sea temperature data group according to the feature set data and label data corresponding to the target sea temperature data in the sea temperature data group, so that the sample generator corresponding to the trained sea temperature data group learns the corresponding relationship between the feature set data and the label data;

[0107] The fourth determination module is used to determine the sample mapping relationship between at least one set of feature set data and label data based on each sea temperature data in the sea temperature data group and the sea temperature data generated by the sample generator corresponding to the trained sea temperature data group.

[0108] Furthermore, in a possible implementation of the embodiment of the present invention, the training module is further used to:

[0109] For any target sea temperature data in the sea temperature data group, the feature set data corresponding to the target sea temperature data is used as the input of the sample generator corresponding to the sea temperature data group, and the label data corresponding to the target sea temperature data is used as the output of the sample generator corresponding to the sea temperature data group. The sample generator corresponding to the sea temperature data group is trained so that the trained sample generator corresponding to the sea temperature data group can learn the correspondence between the feature set data and the label data.

[0110] Further, in a possible implementation manner of the embodiment of the present invention, the fourth determining module is further configured to:

[0111] Using the normalized value corresponding to each sea temperature data in the sea temperature data group and / or the sea temperature data generated by the sample generator corresponding to the trained sea temperature data group as the input of the sample generator corresponding to the trained sea temperature data group, so as to obtain the sea temperature data output by the sample generator corresponding to the trained sea temperature data group;

[0112] The input of the sample generator corresponding to the trained sea temperature data group is used as the feature set data, and the output of the sample generator corresponding to the trained sea temperature data group is used as the label data to determine the sample mapping relationship between at least one set of feature set data and label data.

[0113] Further, in a possible implementation of the embodiment of the present invention, the longitude feature is used to indicate the longitude of the sea temperature data, the latitude feature is used to indicate the latitude of the sea temperature data, the time feature is used to indicate the acquisition time of the sea temperature data, and the depth feature is used to indicate the depth level of the sea temperature data;

[0114] The acquisition module 31 is further used for:

[0115] Acquire multi-layer sea temperature data; wherein the time range of the multi-layer sea temperature data includes the target period;

[0116] Splicing the multi-layer sea temperature data in the time dimension, so as to select the multi-layer sea temperature data within the target period from the spliced ​​multi-layer sea temperature data to construct a first sea temperature data set;

[0117] The sea temperature data in the first sea temperature data set are regionally selected to obtain a sea temperature data set within a target area and a target period.

[0118] Furthermore, in a possible implementation of the embodiment of the present invention, the above-mentioned device further includes:

[0119] A processing module is used to perform data preprocessing on the multi-layer sea temperature data; wherein the data preprocessing includes at least one of the following:

[0120] Data cleaning;

[0121] Data formatting.

[0122] It should be noted that the aforementioned explanation of the sample mapping relationship determination method embodiment is also applicable to the sample mapping relationship determination device of this embodiment, and will not be repeated here.

[0123] The sample mapping relationship determination device of the embodiment of the present invention obtains a sea temperature data set within a target period of a target area; wherein the sea temperature data set includes multiple sea temperature data, each of which carries longitude characteristics, latitude characteristics, time characteristics and depth characteristics; according to the depth characteristics of each sea temperature data in the sea temperature data set, at least one sea temperature data group is determined from the sea temperature data set; wherein any sea temperature data group includes multiple sea temperature data; for any sea temperature data group, according to the time characteristics of each sea temperature data in the sea temperature data group, the feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group are determined; for any target sea temperature data in the sea temperature data group, the sample mapping relationship between the feature set data corresponding to the target sea temperature data and the label data corresponding to the target sea temperature data is determined; wherein the sample mapping relationship is used to train the sea temperature prediction model. Therefore, in the process of determining the sample mapping relationship, the spatial characteristics and time characteristics of the sea temperature data are fully considered, which is conducive to more accurately capturing the dynamic change process of the sea temperature data, thereby realizing accurate prediction of future sea temperature data.

[0124] In order to implement the above embodiments, the present invention also proposes an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the sample mapping relationship determination method proposed in any of the above embodiments of the present invention.

[0125] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0126] It should be noted that Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0127] like Figure 4 As shown, the electronic device includes:

[0128] A memory 41 , a processor 42 , and a computer program stored in the memory 41 and executable on the processor 42 .

[0129] When the processor 42 executes the program, the sample mapping relationship determination method provided in any of the above embodiments is implemented.

[0130] Furthermore, the electronic device further comprises:

[0131] The communication interface 43 is used for communication between the memory 41 and the processor 42 .

[0132] The memory 41 is used to store computer programs that can be run on the processor 42 .

[0133] The memory 41 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0134] The processor 42 is configured to implement the sample mapping relationship determination method described in any one of the above embodiments when executing the program.

[0135] If the memory 41, the processor 42 and the communication interface 43 are implemented independently, the communication interface 43, the memory 41 and the processor 42 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0136] Optionally, in a specific implementation, if the memory 41, the processor 42 and the communication interface 43 are integrated on a chip, the memory 41, the processor 42 and the communication interface 43 can communicate with each other through an internal interface.

[0137] The processor 42 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0138] In order to implement the above embodiments, the present invention further proposes a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the sample mapping relationship determination method proposed in any of the above embodiments of the present invention.

[0139] In order to implement the above embodiments, the present invention further proposes a computer program product, including a computer program, which, when executed by a processor, implements the sample mapping relationship determination method proposed in any of the above embodiments of the present invention.

[0140] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means 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 invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0141] 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, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0142] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0143] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0144] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0145] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0146] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0147] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for determining a sample mapping relationship, characterized in that: include: Acquire a sea temperature data set within a target area and a target period; wherein the sea temperature data set includes a plurality of sea temperature data, each of which carries a longitude feature, a latitude feature, a time feature, and a depth feature; Determine at least one sea temperature data group from the sea temperature data set according to the depth characteristics of each of the sea temperature data in the sea temperature data set; wherein any of the sea temperature data groups includes a plurality of the sea temperature data; For any of the sea temperature data groups, determining feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group according to the time characteristics of each of the sea temperature data in the sea temperature data group; For any of the target sea temperature data in the sea temperature data group, determine a sample mapping relationship between feature set data corresponding to the target sea temperature data and label data corresponding to the target sea temperature data; wherein the sample mapping relationship is used to train a sea temperature prediction model.

2. The method according to claim 1, characterized in that Determining at least one sea temperature data group from the sea temperature data set according to the depth characteristics of each of the sea temperature data in the sea temperature data set comprises: According to the depth characteristics of each of the sea temperature data in the sea temperature data set, a plurality of the sea temperature data in the sea temperature data set with the same depth characteristic value are determined as one of the sea temperature data sets.

3. The method according to claim 1, characterized in that The step of determining, for any of the sea temperature data groups, feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group according to the time characteristics of each of the sea temperature data in the sea temperature data group, comprises: For any of the sea temperature data groups, normalizing each of the sea temperature data in the sea temperature data group to obtain a normalized value corresponding to each of the sea temperature data in the sea temperature data group; According to the time characteristics of each of the sea temperature data in the sea temperature data group, feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group are determined from normalized values ​​corresponding to each of the sea temperature data in the sea temperature data group.

4. The method according to claim 3, characterized in that The determining, according to the time characteristics of each of the sea temperature data in the sea temperature data group, feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group from the normalized values ​​corresponding to each of the sea temperature data in the sea temperature data group, comprises: For any of the target sea temperature data in the sea temperature data group, determine, according to the time characteristics of each of the sea temperature data in the sea temperature data group, first sea temperature data whose time characteristics are before the time characteristics of the target sea temperature data, and second sea temperature data whose time characteristics are after the time characteristics of the target sea temperature data; wherein the target sea temperature data is sea temperature data in which there are at least a first set number of the first sea temperature data and at least a second set number of the second sea temperature data in the sea temperature data group; Determine the normalized value corresponding to the target sea temperature data and the normalized values ​​corresponding to the first set number of the first sea temperature data adjacent to the target sea temperature data as feature set data corresponding to the target sea temperature data; The normalized values ​​corresponding to the second set number of the second sea temperature data adjacent to the target sea temperature data are determined as label data corresponding to the target sea temperature data.

5. The method according to claim 1, characterized in that The method further comprises: According to the feature set data and label data corresponding to the target sea temperature data in the sea temperature data group, training the sample generator corresponding to the sea temperature data group, so that the trained sample generator corresponding to the sea temperature data group learns the corresponding relationship between the feature set data and the label data; According to each of the sea temperature data in the sea temperature data group and the sea temperature data generated by the sample generator corresponding to the trained sea temperature data group, a sample mapping relationship between at least one set of feature set data and label data is determined.

6. The method according to claim 5, characterized in that The step of training a sample generator corresponding to the sea temperature data group according to the feature set data and label data corresponding to the target sea temperature data in the sea temperature data group, so that the trained sample generator corresponding to the sea temperature data group learns the corresponding relationship between the feature set data and the label data, comprises: For any of the target sea temperature data in the sea temperature data group, the feature set data corresponding to the target sea temperature data is used as the input of the sample generator corresponding to the sea temperature data group, and the label data corresponding to the target sea temperature data is used as the output of the sample generator corresponding to the sea temperature data group, and the sample generator corresponding to the sea temperature data group is trained so that the trained sample generator corresponding to the sea temperature data group learns the correspondence between the feature set data and the label data.

7. The method according to claim 5, characterized in that Determining a sample mapping relationship between at least one set of feature set data and label data according to each of the sea temperature data in the sea temperature data group and the sea temperature data generated by a sample generator corresponding to the trained sea temperature data group includes: Using the normalized value corresponding to each of the sea temperature data in the sea temperature data group and / or the sea temperature data generated by the sample generator corresponding to the trained sea temperature data group as the input of the sample generator corresponding to the trained sea temperature data group, so as to obtain the sea temperature data output by the sample generator corresponding to the trained sea temperature data group; The input of the sample generator corresponding to the trained sea temperature data group is used as feature set data, and the output of the sample generator corresponding to the trained sea temperature data group is used as label data to determine a sample mapping relationship between at least one set of feature set data and label data.

8. The method according to any one of claims 1 to 7, characterized in that The longitude feature is used to indicate the longitude of the sea temperature data, the latitude feature is used to indicate the latitude of the sea temperature data, the time feature is used to indicate the acquisition time of the sea temperature data, and the depth feature is used to indicate the depth level of the sea temperature data; The step of obtaining a sea temperature dataset in a target area and a target period includes: Acquire multi-layer sea temperature data; wherein the time range of the multi-layer sea temperature data includes the target time period; Splicing the multi-layer sea temperature data in a time dimension, so as to select multi-layer sea temperature data within a target period from the spliced ​​multi-layer sea temperature data to construct a first sea temperature data set; The sea temperature data in the first sea temperature data set is subjected to regional selection to obtain a sea temperature data set within a target area and a target period.

9. The method according to claim 8, characterized in that Before splicing the multi-layer sea temperature data in the time dimension, the method further includes: Performing data preprocessing on the multi-layer sea temperature data; wherein the data preprocessing includes at least one of the following: Data cleaning; Data formatting.

10. A sample mapping relationship determination device, characterized in that: include: An acquisition module is used to acquire a sea temperature data set within a target area and a target period; wherein the sea temperature data set includes a plurality of sea temperature data, each of which carries a longitude feature, a latitude feature, a time feature and a depth feature; A first determination module is used to determine at least one sea temperature data group from the sea temperature data set according to the depth characteristics of each of the sea temperature data in the sea temperature data set; wherein any of the sea temperature data groups includes a plurality of the sea temperature data; A second determination module is used to determine, for any of the sea temperature data groups, feature set data and label data corresponding to at least one target sea temperature data in the sea temperature data group according to the time characteristics of each of the sea temperature data in the sea temperature data group; The third determination module is used to determine, for any of the target sea temperature data in the sea temperature data group, a sample mapping relationship between the feature set data corresponding to the target sea temperature data and the label data corresponding to the target sea temperature data; wherein the sample mapping relationship is used to train a sea temperature prediction model.