CN112685492A - Multi-source data fusion method and device - Google Patents
Multi-source data fusion method and device Download PDFInfo
- Publication number
- CN112685492A CN112685492A CN202011615040.9A CN202011615040A CN112685492A CN 112685492 A CN112685492 A CN 112685492A CN 202011615040 A CN202011615040 A CN 202011615040A CN 112685492 A CN112685492 A CN 112685492A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- level
- accuracy
- weight mask
- precipitation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 11
- 238000012544 monitoring process Methods 0.000 claims abstract description 269
- 238000012806 monitoring device Methods 0.000 claims abstract description 79
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000001556 precipitation Methods 0.000 claims description 148
- 238000013507 mapping Methods 0.000 claims description 37
- 238000004364 calculation method Methods 0.000 claims description 31
- 238000010586 diagram Methods 0.000 claims description 30
- 230000015654 memory Effects 0.000 claims description 19
- 230000004927 fusion Effects 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 14
- 206010020751 Hypersensitivity Diseases 0.000 description 5
- 208000026935 allergic disease Diseases 0.000 description 4
- 230000007815 allergy Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 206010027146 Melanoderma Diseases 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000172 allergic effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 208000010668 atopic eczema Diseases 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007340 echolocation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The application discloses a multi-source data fusion method and a device, wherein the method comprises the following steps: calculating monitoring accuracy according to monitoring data output by a plurality of monitoring devices; generating a weight mask according to monitoring data and monitoring accuracy output by a plurality of monitoring devices; and fusing the monitoring data output by the plurality of monitoring devices by using the weight masks to obtain fused data. The accuracy of monitoring indexes of each monitoring device in the dimensions of time, space, monitoring numerical intensity and the like is calculated, a weight mask of each monitoring device is dynamically generated, and then the monitoring value of each grid point and the mask are weighted and summed to form a fused monitoring value at the position of each grid point in the coverage area of the monitoring device. The accuracy of the fused regional global data is improved.
Description
Technical Field
The application relates to the field of deep learning, in particular to the field of data fusion.
Background
The monitoring device can detect a monitoring target object in a certain space range to form a group of grid point level monitoring data, the monitoring data is usually primary data, and grid point level monitoring indexes which are most concerned by people are generated through a series of calculation and transformation. When a large area is monitored, multiple monitoring devices (i.e., multiple data generation sources) are generally required to be uniformly deployed in space, different monitoring data are output respectively, and then the multiple data source data are fused to generate a monitoring overall view on the whole area.
At present, under the condition that monitoring equipment covers an overlapping area, a method for fusing multi-source data mainly comprises the following steps: maximum value method, nearest neighbor method, inverse distance exponential weight method, static radar weight method, etc. The maximum value method and the nearest neighbor method cause certain errors to the monitoring numerical values in the monitoring overlapping area, and particularly, under the condition that the monitoring numerical value of a certain monitoring device in the monitoring area is large, the errors are large. The nearest neighbor method is used for completely hooking each grid point position with one corresponding observation device, when the observation device fails and generates false reports of missing reports, data of the corresponding grid point position can generate errors, and experiments show that the nearest neighbor method often has a large proportion of false reports. The inverse distance index weighting method and the static weighting method only consider the weighting processing of the whole monitoring data from the distance or a certain single characteristic of the monitoring equipment, and the accuracy of the finally generated overall monitoring data is also poor.
Therefore, the monitoring data obtained by the current multi-source data fusion method has larger error and lower accuracy.
Disclosure of Invention
The embodiment of the application provides a multi-source data fusion method and device, which are used for solving the problems in the related technology and have the following technical scheme:
in a first aspect, an embodiment of the present application provides a multi-source data fusion method, including:
calculating monitoring accuracy according to monitoring data output by a plurality of monitoring devices;
generating a weight mask according to monitoring data and monitoring accuracy output by a plurality of monitoring devices;
and fusing the monitoring data output by the plurality of monitoring devices by using the weight masks to obtain fused data.
In one embodiment, calculating the monitoring accuracy from the monitoring data output by the plurality of monitoring devices comprises:
and under the condition that the monitoring data comprises a historical monitoring data set, a contemporaneous monitoring data set and a recent monitoring data set, calculating the historical monitoring accuracy, the contemporaneous monitoring accuracy and the recent monitoring accuracy.
In one embodiment, generating a weight mask based on monitoring data and monitoring accuracy output by a plurality of monitoring devices comprises:
generating a historical weight mask according to the historical monitoring data set and the historical monitoring accuracy;
generating a contemporaneous weight mask according to the contemporaneous monitoring data set and the contemporaneous monitoring accuracy;
and generating a recent weight mask according to the recent monitoring data set and the recent monitoring accuracy.
In one embodiment, calculating a monitoring accuracy from monitoring data output by a plurality of monitoring devices includes:
acquiring monitoring data in a monitoring coverage area, wherein the monitoring data comprises an echo diagram and a rain gauge station data set;
performing regional classification on the monitoring coverage area, and calculating the ratio of the number of samples with precipitation and the number of samples with the echo value r of the rain gauge station on each regional block obtained by the classification to the number of samples with the echo value r of the rain gauge station on the regional block under the condition that the echo value r of the rain gauge station is greater than or equal to a threshold value, so as to obtain the precipitation accuracy of the echo value r in the regional block, and recording the precipitation accuracy as the regional precipitation accuracy;
regional precipitation accuracy rates include: historical precipitation accuracy at the zone level, contemporaneous precipitation accuracy at the zone level, and recent precipitation accuracy at the zone level.
In one embodiment, generating a weight mask based on monitoring data and monitoring accuracy output by a plurality of monitoring devices comprises:
generating a region level mapping table according to the echo value of the region block in the echo diagram, the distance between the echo value and the radar center, and the corresponding relation between the azimuth angle and the region level precipitation accuracy rate;
and generating a weight mask corresponding to the echo diagram by using the region level mapping table, wherein the weight mask comprises a historical weight mask of the region level, a contemporaneous weight mask of the region level and a recent weight mask of the region level.
In one embodiment, calculating a monitoring accuracy from monitoring data output by a plurality of monitoring devices includes:
acquiring monitoring data output by a plurality of monitoring devices, wherein the monitoring data comprises an echo chart and a precipitation chart;
carrying out lattice-level division on the monitoring coverage area, calculating the ratio of the number of samples with precipitation and the number of samples with the echo value r 'on the central point to the number of samples with the echo value r' on the central point in each lattice-level block obtained by division when the echo value r 'of the central point is greater than or equal to a threshold value, obtaining the precipitation accuracy rate of the echo value r' in each lattice-level block, and recording the precipitation accuracy rate as the lattice-level precipitation accuracy rate, wherein each lattice-level block is smaller than the region block;
lattice-level precipitation accuracy includes: historical precipitation accuracy at a grid point level, contemporaneous precipitation accuracy at a grid point level, and recent precipitation accuracy at a grid point level.
In one embodiment, generating a weight mask based on monitoring data and monitoring accuracy output by a plurality of monitoring devices comprises:
generating a grid point level mapping table according to the echo value of a grid level block in an echo diagram, the distance between the echo value and the radar center, and the corresponding relation between the azimuth angle and the grid point level precipitation accuracy rate;
and generating a weight mask corresponding to the echo diagram by using the grid point level mapping table, wherein the weight mask comprises a historical weight mask of a grid point level, a contemporaneous weight mask of the grid point level and a recent weight mask of the grid point level.
In one embodiment, the method further comprises:
generating a basic weight mask corresponding to each monitoring device by using an inverse distance index function;
obtaining a comprehensive weight mask according to the historical weight mask of the region level, the contemporaneous weight mask of the region level, the recent weight mask of the region level, the historical weight mask of the lattice level, the contemporaneous weight mask of the lattice level, the recent weight mask of the lattice level and the basic weight mask corresponding to each monitoring device, and fusing the monitoring data output by the monitoring devices by using the weight masks to obtain fused data.
In a second aspect, a multi-source data fusion apparatus is provided, including:
the monitoring accuracy calculation module is used for calculating monitoring accuracy according to the monitoring data output by the plurality of monitoring devices;
the weight mask generating module is used for generating weight masks according to the monitoring data and the monitoring accuracy output by the monitoring equipment;
and the data fusion module is used for fusing the monitoring data output by the plurality of monitoring devices by using the weight masks to obtain fused data.
In one embodiment, the monitoring accuracy calculation module includes:
and the time level monitoring accuracy calculation submodule is used for calculating the historical monitoring accuracy, the contemporaneous monitoring accuracy and the recent monitoring accuracy under the condition that the monitoring data comprise a historical monitoring data set, a recent monitoring data set and the like.
In one embodiment, the weight mask generation module includes:
the time-level weight mask generation submodule is used for generating a historical weight mask according to the historical monitoring data set and the historical monitoring accuracy; generating a contemporaneous weight mask according to the contemporaneous monitoring data set and the contemporaneous monitoring accuracy; and generating a recent weight mask according to the recent monitoring data set and the recent monitoring accuracy.
In one embodiment, the monitoring accuracy calculation module includes:
the first data acquisition submodule is used for acquiring monitoring data in a monitoring coverage area, and the monitoring data comprises an echo diagram and a rain gauge station data set;
the area level precipitation accuracy rate calculation submodule is used for carrying out area level division on the monitoring coverage area, and under the condition that the echo value r of a rain gauge station is larger than or equal to a threshold value in each divided area block, calculating the ratio of the number of samples with precipitation and the echo value r on the rain gauge station to the number of samples with the echo value r on the rain gauge station, so as to obtain the precipitation accuracy rate of the echo value r in the area block, and recording the precipitation accuracy rate as the area level precipitation accuracy rate; regional precipitation accuracy rates include: historical precipitation accuracy at the zone level, contemporaneous precipitation accuracy at the zone level, and recent precipitation accuracy at the zone level.
In one embodiment, the weight mask generation module includes:
the area level mapping table generation submodule is used for generating an area level mapping table according to the echo value of an area block in the echo diagram, the distance between the echo value and the radar center and the corresponding relation between the azimuth angle and the area level precipitation accuracy rate;
and the region-level weight mask generation submodule generates a weight mask corresponding to the echo map by using the region-level mapping table, wherein the weight mask comprises a history weight mask of a region level, a contemporaneous weight mask of the region level and a recent weight mask of the region level.
In one embodiment, the monitoring accuracy calculation module includes:
the second data acquisition submodule is used for acquiring monitoring data output by the plurality of monitoring devices, and the monitoring data comprises an echo map and a precipitation map;
the lattice-level precipitation accuracy rate calculation submodule is used for carrying out lattice-level division on the monitoring coverage area, calculating the ratio of the number of samples with precipitation and the number of samples with the echo value r 'on the central point to the number of samples with the echo value r' on the central point in each lattice-level block obtained by division under the condition that the echo value r 'of the central point is greater than or equal to a threshold value, obtaining the precipitation accuracy rate of the echo value r' in each lattice-level block, and recording the precipitation accuracy rate as the lattice-level precipitation accuracy rate, wherein each lattice-level block is smaller than the region block; lattice-level precipitation accuracy includes: historical precipitation accuracy at a grid point level, contemporaneous precipitation accuracy at a grid point level, and recent precipitation accuracy at a grid point level.
In one embodiment, the weight mask generation module includes:
the grid point level mapping table generation submodule is used for generating a grid point level mapping table according to the echo value of a grid level block in the echo diagram, the distance between the echo value and the radar center, and the corresponding relation between the azimuth angle and the grid point level precipitation accuracy rate;
and the grid point level weight mask generation submodule generates a weight mask corresponding to the echo graph by utilizing the grid point level mapping table, wherein the weight mask comprises a historical weight mask of a grid point level, a contemporaneous weight mask of the grid point level and a recent weight mask of the grid point level.
In one embodiment, the weight mask generating module further comprises:
the basic weight mask generation submodule is used for generating a basic weight mask corresponding to each monitoring device by utilizing an inverse distance index function;
and the comprehensive weight mask calculation submodule is used for obtaining a comprehensive weight mask according to the historical weight mask of the area level, the contemporary weight mask of the area level and the recent weight mask of the area level, the historical weight mask of the lattice level, the contemporary weight mask of the lattice level and the recent weight mask of the lattice level, and the basic weight masks corresponding to the monitoring devices, so that the monitoring data output by the monitoring devices are fused by using the weight masks to obtain fused data.
In a third aspect, an electronic device is provided, including:
at least one processor; and a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any of the methods described above.
In a fourth aspect, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any of the above.
One embodiment in the above application has the following advantages or benefits: the accuracy of monitoring indexes of each monitoring device in the dimensions of time, space, monitoring numerical intensity and the like is calculated, a weight mask of each monitoring device is dynamically generated, and then the monitoring value of each grid point and the mask are weighted and summed to form a fused monitoring value at the position of each grid point in the coverage area of the monitoring device. By dividing the training data set into the historical data set, the contemporaneous data set and the recent data set, the updating of the weight mask is more timely, effective and intelligent, and the accuracy of the fused regional full-face data is further improved.
Other effects of the above-described alternative will be described below with reference to specific embodiments.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is a schematic diagram of a multi-source data fusion method according to an embodiment of the present application;
FIG. 2 is a flow chart of a multi-source data fusion method according to another embodiment of the present application;
FIG. 3 is a schematic illustration of a radar partition according to another embodiment of the present application;
FIG. 4 is a schematic diagram of a multi-source data fusion apparatus according to an embodiment of the present application;
FIG. 5 is a block diagram of an electronic device for implementing a multi-source data fusion method according to an embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In a specific embodiment, as shown in fig. 1, a multi-source data fusion method is provided, which includes the following steps:
step S110: calculating monitoring accuracy according to monitoring data output by a plurality of monitoring devices;
step S120: generating a weight mask according to monitoring data and monitoring accuracy output by a plurality of monitoring devices;
step S130: and fusing the monitoring data output by the plurality of monitoring devices by using the weight masks to obtain fused data.
In one example, when a monitoring device monitors a certain area, a set of monitoring data is generated regularly, so that multi-source data fusion is a periodic task. The method described in this embodiment is not only suitable for multi-source data fusion of meteorological radar, but also suitable for multi-source data fusion of other monitoring devices, and for convenience and accuracy in description, a radar jigsaw is taken as an example for introduction in the following. FIG. 2 shows a complete process flow for performing single cycle multi-source data fusion.
(1) When data of a plurality of data sources are fused, the latest current monitoring data of each monitoring device needs to be acquired.
(2) The monitoring index value calculated from the monitoring data is more abundant (spatial range, spatial granularity, temporal range, temporal granularity, etc.) than the observation index value obtained by direct observation, and it is desired to obtain a rich monitoring index value. The site-level monitoring indexes are obtained through site-level monitoring data, the grid-point-level monitoring indexes are obtained through grid-point-level monitoring data, monitoring indexes fed back by a user can be obtained, and the monitoring index values are precipitation in the embodiment and do not need to be calculated.
(3) And calculating the monitoring accuracy of the monitoring equipment on the historical data set, the contemporaneous data set and the recent data set. The historical data set, the contemporaneous data set and the recent data set respectively represent site level monitoring indexes, user feedback monitoring indexes and grid point level monitoring indexes obtained by historical time, contemporaneous time and recent time. The accuracy on the historical data set and the contemporaneous data set is calculated on line, only regular updating is needed, and the accuracy on the recent data set needs to be calculated on line in real time. And calculating the accuracy of each monitoring device on different monitoring data size grades, orientations and distances in the historical data set, the contemporaneous data set and the recent data set, and generating historical weight masks, contemporaneous weight masks and recent weight masks on different monitoring data size grades, orientations and distances.
(4) And fusing the historical weight mask, the contemporaneous weight mask, the recent weight mask and the monitoring equipment basic mask to generate a comprehensive weight mask.
(5) The integrated weight mask is applied to any one grid location for each monitoring device coverage area. And selecting proper monitoring data for fusion from different monitoring data size grades and different areas according to the comprehensive weight mask.
Among the above steps, step 4 and step 5 are mainly used for dynamically generating a weight mask, and a method of fusing a plurality of data source data based on weight of the weight mask is used, and essentially, a monitoring index value is used as guidance information for fusion. Experiments show that for different monitoring index purposes, radar echo is taken as an example, radar echo monitoring is taken as a purpose, whether rainfall exists or not is also taken as a purpose, and a certain difference exists in fusion results of monitoring data of a plurality of data sources.
The embodiment provides a method for fusing data of a plurality of data sources based on a dynamic update mask. The accuracy of monitoring indexes of each monitoring device in the dimensions of time, space, monitoring numerical intensity and the like is calculated, a weight mask of each monitoring device is dynamically generated, and then the monitoring value of each grid point and the mask are weighted and summed to form a fused monitoring value at the position of each grid point in the coverage area of the monitoring device. By dividing the training data set into the historical data set, the contemporaneous data set and the recent data set, the updating of the weight mask is more timely, effective and intelligent, and the accuracy of the fused regional full-face data is further improved.
In one embodiment, calculating the monitoring accuracy from the monitoring data output by the plurality of monitoring devices comprises:
and under the condition that the monitoring data comprises a historical monitoring data set, a contemporaneous monitoring data set and a recent monitoring data set, calculating the historical monitoring accuracy, the contemporaneous monitoring accuracy and the recent monitoring accuracy.
In one example, in order to fully and reasonably utilize existing monitoring data, when the radar precipitation accuracy rate of a region level is calculated, the monitoring data is divided into a historical monitoring data set, a contemporaneous monitoring data set and a recent monitoring data set. The historical monitoring data set may be all monitoring data that has been available for the last 10 years, and the radar performance has been reflected for a long time by calculating the radar precipitation accuracy using all data. The synchronous observation data refers to observation data of the current month in the previous year, and the performance of the radar influenced by seasons and months is reflected by calculating the precipitation accuracy of the radar by using the synchronous data. Recent observation data refers to observation data of recent days, and the performance change of the radar influenced by recent specific factors (special climate, manual maintenance, mechanical failure and the like) is reflected by calculating the precipitation accuracy of the radar by using the recent observation data. When the accuracy is calculated by using recent observation data, due to the small amount of data, when the coverage area of the radar is divided, the area range needs to be divided into a larger number (for example, the area range can be divided only in the range dimension without considering the azimuth angle), and the division of the echo strength also needs to be more coarse-grained (for example, only the echo value is divided by being greater than or equal to the threshold R _ rain and less than the threshold R _ rain).
In one embodiment, generating a weight mask based on monitoring data and monitoring accuracy output by a plurality of monitoring devices comprises:
generating a historical weight mask according to the historical monitoring data set and the historical monitoring accuracy;
generating a contemporaneous weight mask according to the contemporaneous monitoring data set and the contemporaneous monitoring accuracy;
and generating a recent weight mask according to the recent monitoring data set and the recent monitoring accuracy.
In one embodiment, calculating a monitoring accuracy from monitoring data output by a plurality of monitoring devices includes:
acquiring monitoring data in a monitoring coverage area, wherein the monitoring data comprises an echo diagram and a rain gauge station data set;
performing regional classification on the monitoring coverage area, and calculating the ratio of the number of samples with precipitation and the number of samples with the echo value r of the rain gauge station on each regional block obtained by the classification to the number of samples with the echo value r of the rain gauge station on the regional block under the condition that the echo value r of the rain gauge station is greater than or equal to a threshold value, so as to obtain the precipitation accuracy of the echo value r in the regional block, and recording the precipitation accuracy as the regional precipitation accuracy;
regional precipitation accuracy rates include: historical precipitation accuracy at the zone level, contemporaneous precipitation accuracy at the zone level, and recent precipitation accuracy at the zone level.
In one embodiment, generating a weight mask based on monitoring data and monitoring accuracy output by a plurality of monitoring devices comprises:
generating a region level mapping table according to the echo value of the region block in the echo diagram, the distance between the echo value and the radar center, and the corresponding relation between the azimuth angle and the region level precipitation accuracy rate;
and generating a weight mask corresponding to the echo diagram by using the region level mapping table, wherein the weight mask comprises a historical weight mask of the region level, a contemporaneous weight mask of the region level and a recent weight mask of the region level.
In one example, a region level radar precipitation accuracy rate is calculated and a weight mask is generated. On an observation region, precipitation observation information at a site level is generally sparse, and although the site data can be converted into lattice data in an interpolation mode, errors are introduced. In combination with the fact that the radar has similar accuracy in a certain local area, the accuracy of the area can be considered to replace the accuracy of the grid point. The radar area is divided according to two dimensions of distance and direction, as shown in fig. 3. In actual use, the radar echo value is usually processed into a discrete value, and when the accuracy of an area is calculated, the accuracy of a certain echo intensity can be calculated after an echo data set and a precipitation station data set are selected. On the echo data set, num _ all (r) represents the number of samples with echo value r at the black spot position in fig. 3, and num _ rain (r) represents the number of samples with echo value r at the black spot position in fig. 3 and with precipitation at that position (whether precipitation at that position is required according to the precipitation site data set). Assuming that precipitation is generated when the echo value R is greater than or equal to the threshold value R _ rain, the precipitation accuracy rate of the echo value R in the region is calculated according to the following formula when the echo value R is greater than or equal to R _ rain:
wherein num _ all (r) represents the number of samples with echo value r at the precipitation observation site in the area, num _ rain (r) represents the number of samples with echo value r and precipitation is observed at the precipitation observation site in the area, and the ratio of the two is the accuracy of the echo value r in the area. When the echo value R is smaller than the threshold value R _ rain, the precipitation accuracy rate of the echo value R in the region is calculated by the following formula:
wherein, in the radar coverage range, but no echo is detected, the echo value r is considered to be 0.
And obtaining a mapping table of each echo value r and the precipitation accuracy rate thereof in the region through the calculation, and generating a weight mask M corresponding to the echo map in a table look-up mode after giving the latest echo map RAD in the region. Through the steps, the historical weight mask Mhis, the contemporaneous weight mask Mmon and the recent weight mask Mrcn are generated by the echo of each radar.
In one embodiment, calculating a monitoring accuracy from monitoring data output by a plurality of monitoring devices includes:
acquiring monitoring data output by a plurality of monitoring devices, wherein the monitoring data comprises an echo chart and a precipitation chart;
carrying out lattice-level division on the monitoring coverage area, calculating the ratio of the number of samples with precipitation and the number of samples with the echo value r 'on the central point to the number of samples with the echo value r' on the central point in each lattice-level block obtained by division when the echo value r 'of the central point is greater than or equal to a threshold value, obtaining the precipitation accuracy rate of the echo value r' in each lattice-level block, and recording the precipitation accuracy rate as the lattice-level precipitation accuracy rate, wherein each lattice-level block is smaller than the region block;
lattice-level precipitation accuracy includes: historical precipitation accuracy at a grid point level, contemporaneous precipitation accuracy at a grid point level, and recent precipitation accuracy at a grid point level.
In one embodiment, generating a weight mask based on monitoring data and monitoring accuracy output by a plurality of monitoring devices comprises:
generating a grid point level mapping table according to the echo value of a grid level block in an echo diagram, the distance between the echo value and the radar center, and the corresponding relation between the azimuth angle and the grid point level precipitation accuracy rate;
and generating a weight mask corresponding to the echo diagram by using the grid point level mapping table, wherein the weight mask comprises a historical weight mask of a grid point level, a contemporaneous weight mask of the grid point level and a recent weight mask of the grid point level.
In one example, the live precipitation map provides a grid-level precipitation record with a high rate of accuracy. Similar to the calculation of the area-level radar precipitation accuracy rate, historical observation data are divided into a historical observation data set, a contemporaneous observation data set and a recent observation data set, and an accuracy rate mapping table is calculated on each data set independently. The accuracy rate mapping comprises the mapping of azimuth angle, distance from the center point of the radar and echo value r to the accuracy rate of the radar. When calculating the accuracy of the grid point level, actually, the calculation grid points are not required to be completely divided according to the grid points of the radar echo diagram, a plurality of radar grid points can be contained in one calculation grid point, and the radar grid points in the same calculation grid point have the same precipitation accuracy. After the accuracy mapping table of the lattice point level is obtained in the above manner, for the input radar echo map, a historical weight mask Nhis, a contemporaneous weight mask Nmon, and a recent weight mask Nrcn based on the lattice point accuracy can be generated. The precipitation accuracy rate is short for the radar echo forecast precipitation accuracy rate, the lattice point level accuracy rate is the precipitation accuracy rate of the radar on a lattice point level, and the area accuracy rate is the precipitation accuracy rate of the radar on an area level; "accuracy of the detection device in each dimension, accuracy on the data set, echo intensity accuracy" is associated with contextual analysis.
The method for dynamically updating the weight masks of the radars during picture splicing comprises the steps of directly updating the weight masks based on the accuracy rate of the radar on precipitation, calculating a long-term performance weight mask, a contemporaneous performance weight mask and a recent performance weight mask of the radar by adopting two precipitation data of site-level precipitation and lattice-level precipitation, and finally weighting to generate a comprehensive weight mask.
In one embodiment, the method further comprises:
generating a basic weight mask corresponding to each monitoring device by using an inverse distance index function;
obtaining a comprehensive weight mask according to the historical weight mask of the region level, the contemporaneous weight mask of the region level, the recent weight mask of the region level, the historical weight mask of the lattice level, the contemporaneous weight mask of the lattice level, the recent weight mask of the lattice level and the basic weight mask corresponding to each monitoring device, and fusing the monitoring data output by the monitoring devices by using the weight masks to obtain fused data.
In one example, the meteorological radar detects clouds with larger errors as the clouds are farther from the radar, and such errors appear on the echo value and on the echo location. This radar characteristic can be described using an inverse distance exponential function, using which a base weight mask Wdis is generated for each radar.
And generating a comprehensive weight Mask by combining the region-level accuracy weight Mask, the lattice-level accuracy weight Mask and the basic weight Mask, wherein the formula is as follows:
in the above formula, the coefficients wmh, wmm, wmr, wnh, wnm, wnr, wd before each weight mask are the weighting coefficients of the corresponding mask in the integrated weight mask. Post-puzzle echo computation, the post-puzzle echo being a mapping of the current echo values and weight masks for each radar, which may be a function considered as a construct, or a simple neural network, as follows:
rs ═ F (r (n), mask (n)) (formula 4)
In the above formula, rs represents an echo value after puzzle-assembling on a certain lattice point, r (n) represents an echo value of radar n on the lattice point, mask (n) represents a comprehensive weight value of radar n on the lattice point, and F represents a mapping relation, which may be a function or a neural network.
For convenience of calculation, in practical use, the weighted average of the echo at the lattice point with respect to the integrated weight can be calculated as the echo after the mosaicing, and the formula is as follows:
in another embodiment, as shown in fig. 4, there is provided a multi-source data fusion apparatus, including:
a monitoring accuracy calculation module 110, configured to calculate a monitoring accuracy according to monitoring data output by the multiple monitoring devices;
a weight mask generating module 120, configured to generate a weight mask according to the monitoring data and the monitoring accuracy output by the multiple monitoring devices;
and the data fusion module 130 is configured to fuse the monitoring data output by the multiple monitoring devices by using the weight masks to obtain fused data.
In one embodiment, the monitoring accuracy calculation module includes:
and the time level monitoring accuracy calculation submodule is used for calculating the historical monitoring accuracy, the contemporaneous monitoring accuracy and the recent monitoring accuracy under the condition that the monitoring data comprise a historical monitoring data set, a recent monitoring data set and the like.
In one embodiment, the weight mask generation module includes:
the time-level weight mask generation submodule is used for generating a historical weight mask according to the historical monitoring data set and the historical monitoring accuracy; generating a contemporaneous weight mask according to the contemporaneous monitoring data set and the contemporaneous monitoring accuracy; and generating a recent weight mask according to the recent monitoring data set and the recent monitoring accuracy.
In one embodiment, the monitoring accuracy calculation module includes:
the first data acquisition submodule is used for acquiring monitoring data in a monitoring coverage area, and the monitoring data comprises an echo diagram and a rain gauge station data set;
the area level precipitation accuracy rate calculation submodule is used for carrying out area level division on the monitoring coverage area, and under the condition that the echo value r of a rain gauge station is larger than or equal to a threshold value in each divided area block, calculating the ratio of the number of samples with precipitation and the echo value r on the rain gauge station to the number of samples with the echo value r on the rain gauge station, so as to obtain the precipitation accuracy rate of the echo value r in the area block, and recording the precipitation accuracy rate as the area level precipitation accuracy rate; regional precipitation accuracy rates include: historical precipitation accuracy at the zone level, contemporaneous precipitation accuracy at the zone level, and recent precipitation accuracy at the zone level.
In one embodiment, the weight mask generation module includes:
the area level mapping table generation submodule is used for generating an area level mapping table according to the echo value of an area block in the echo diagram, the distance between the echo value and the radar center and the corresponding relation between the azimuth angle and the area level precipitation accuracy rate;
and the region-level weight mask generation submodule generates a weight mask corresponding to the echo map by using the region-level mapping table, wherein the weight mask comprises a history weight mask of a region level, a contemporaneous weight mask of the region level and a recent weight mask of the region level.
In one embodiment, the monitoring accuracy calculation module includes:
the second data acquisition submodule is used for acquiring monitoring data output by the plurality of monitoring devices, and the monitoring data comprises an echo map and a precipitation map;
the lattice-level precipitation accuracy rate calculation submodule is used for carrying out lattice-level division on the monitoring coverage area, calculating the ratio of the number of samples with precipitation and the number of samples with the echo value r 'on the central point to the number of samples with the echo value r' on the central point in each lattice-level block obtained by division under the condition that the echo value r 'of the central point is greater than or equal to a threshold value, obtaining the precipitation accuracy rate of the echo value r' in each lattice-level block, and recording the precipitation accuracy rate as the lattice-level precipitation accuracy rate, wherein each lattice-level block is smaller than the region block; lattice-level precipitation accuracy includes: historical precipitation accuracy at a grid point level, contemporaneous precipitation accuracy at a grid point level, and recent precipitation accuracy at a grid point level.
In one embodiment, the weight mask generation module includes:
the grid point level mapping table generation submodule is used for generating a grid point level mapping table according to the echo value of a grid level block in the echo diagram, the distance between the echo value and the radar center, and the corresponding relation between the azimuth angle and the grid point level precipitation accuracy rate;
and the grid point level weight mask generation submodule generates a weight mask corresponding to the echo graph by utilizing the grid point level mapping table, wherein the weight mask comprises a historical weight mask of a grid point level, a contemporaneous weight mask of the grid point level and a recent weight mask of the grid point level.
In one embodiment, the weight mask generating module further comprises:
the basic weight mask generation submodule is used for generating a basic weight mask corresponding to each monitoring device by utilizing an inverse distance index function;
and the comprehensive weight mask calculation submodule is used for obtaining a comprehensive weight mask according to the historical weight mask of the region level, the contemporaneous weight mask of the region level, the recent weight mask of the region level, the historical weight mask of the lattice point level, the contemporaneous weight mask of the lattice point level, the recent weight mask of the lattice point level and the basic weight masks corresponding to all the monitoring devices, so that the monitoring data output by the monitoring devices are fused by using the weight masks to obtain fused data.
The functions of each module in each apparatus in the embodiment of the present application may refer to corresponding descriptions in the above method, and are not described herein again.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
Fig. 5 is a block diagram of an electronic device for an allergy plant distribution statistical method according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 5, the electronic apparatus includes: one or more processors 501, memory 502, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display Graphical information for a Graphical User Interface (GUI) on an external input/output device, such as a display device coupled to the Interface. In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 5, one processor 501 is taken as an example.
The memory 502, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to a method for allergy plant distribution statistics in the embodiments of the present application. The processor 501 executes various functional applications and data processing of the server by running non-transitory software programs, instructions and modules stored in the memory 502, so as to implement a method for counting the distribution of the allergic plants in the above method embodiment.
The memory 502 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of an electronic device of a allergy plant distribution statistical method, and the like. Further, the memory 502 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 502 optionally includes memory located remotely from processor 501, which may be connected to the electronic devices via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device may further include: an input device 503 and an output device 504. The processor 501, the memory 502, the input device 503 and the output device 504 may be connected by a bus or other means, and fig. 5 illustrates the connection by a bus as an example.
The input device 503 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or other input devices. The output devices 504 may include a display device, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD) such as a Cr5sta display 5, a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, Integrated circuitry, Application Specific Integrated Circuits (ASICs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (Cathode Ray Tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present application can be achieved, and the present invention is not limited herein.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (18)
1. A multi-source data fusion method, comprising:
calculating monitoring accuracy according to monitoring data output by a plurality of monitoring devices;
generating a weight mask according to the monitoring data output by the plurality of monitoring devices and the monitoring accuracy;
and fusing the monitoring data output by the plurality of monitoring devices by using the weight masks to obtain fused data.
2. The method of claim 1, wherein calculating a monitoring accuracy from the monitoring data output by the plurality of monitoring devices comprises:
and under the condition that the monitoring data comprises a historical monitoring data set, a contemporaneous monitoring data set and a recent monitoring data set, calculating the historical monitoring accuracy, the contemporaneous monitoring accuracy and the recent monitoring accuracy.
3. The method of claim 2, wherein generating a weight mask based on the monitoring data and the monitoring accuracy output by the plurality of monitoring devices comprises:
generating a historical weight mask according to the historical monitoring data set and the historical monitoring accuracy;
generating a contemporaneous weight mask according to the contemporaneous monitoring data set and the contemporaneous monitoring accuracy;
and generating a recent weight mask according to the recent monitoring data set and the recent monitoring accuracy.
4. The method of claim 3, wherein calculating a monitoring accuracy from the monitoring data output by the plurality of monitoring devices comprises:
acquiring monitoring data in a monitoring coverage area, wherein the monitoring data comprises an echo diagram and a rain gauge station data set;
performing regional classification on the monitoring coverage area, and calculating the ratio of the number of samples with rainfall and the number of samples with the echo value r on the rain gauge station to the number of samples with the echo value r on the rain gauge station in each regional block obtained by the classification under the condition that the echo value r of the rain gauge station is greater than or equal to a threshold value, so as to obtain the rainfall accuracy of the echo value r in the regional block, and recording the rainfall accuracy as the regional precipitation accuracy;
the region level precipitation accuracy rate comprises: historical precipitation accuracy at the zone level, contemporaneous precipitation accuracy at the zone level, and recent precipitation accuracy at the zone level.
5. The method of claim 4, wherein generating a weight mask based on the monitoring data and the monitoring accuracy output by the plurality of monitoring devices comprises:
generating a region level mapping table according to the echo value of the region block in the echo diagram, the distance between the echo value and the radar center, and the corresponding relation between the azimuth angle and the region level precipitation accuracy rate;
and generating a weight mask corresponding to the echo diagram by using the region level mapping table, wherein the weight mask comprises a history weight mask of a region level, a contemporaneous weight mask of the region level and a recent weight mask of the region level.
6. The method of claim 5, wherein calculating a monitoring accuracy from the monitoring data output by the plurality of monitoring devices comprises:
acquiring monitoring data output by the plurality of monitoring devices, wherein the monitoring data comprises an echo chart and a precipitation chart;
carrying out lattice point level division on the monitoring coverage area, calculating the ratio of the number of samples with precipitation and the number of samples with the echo value r 'on the central point to the number of samples with the echo value r' on the central point in each divided lattice level block under the condition that the echo value r 'of the central point is greater than or equal to the threshold value, obtaining the precipitation accuracy rate of the echo value r' in the lattice level block, and recording the precipitation accuracy rate as the lattice point level precipitation accuracy rate, wherein the lattice level block is smaller than the region block;
the lattice-level precipitation accuracy includes: historical precipitation accuracy at a grid point level, contemporaneous precipitation accuracy at a grid point level, and recent precipitation accuracy at a grid point level.
7. The method of claim 6, wherein generating a weight mask based on the monitoring data and the monitoring accuracy output by the plurality of monitoring devices comprises:
generating a grid point level mapping table according to the echo value of a grid level block in the echo diagram, the distance between the echo value and a radar center and the corresponding relation between the azimuth angle and the grid point level precipitation accuracy rate;
and generating a weight mask corresponding to the echo graph by using the grid point level mapping table, wherein the weight mask comprises a historical weight mask of a grid point level, a contemporaneous weight mask of the grid point level and a recent weight mask of the grid point level.
8. The method of claim 7, further comprising:
generating a basic weight mask corresponding to each monitoring device by using an inverse distance index function;
obtaining a comprehensive weight mask according to the historical weight mask of the region level, the contemporary weight mask of the region level and the recent weight mask of the region level, the historical weight mask of the lattice point level, the contemporary weight mask of the lattice point level and the recent weight mask of the lattice point level, and the basic weight masks corresponding to the monitoring devices, so as to fuse the monitoring data output by the monitoring devices by using the weight masks to obtain fused data.
9. A multi-source data fusion apparatus, comprising:
the monitoring accuracy calculation module is used for calculating monitoring accuracy according to the monitoring data output by the plurality of monitoring devices;
the weight mask generating module is used for generating weight masks according to the monitoring data output by the plurality of monitoring devices and the monitoring accuracy;
and the data fusion module is used for fusing the monitoring data output by the plurality of monitoring devices by using the weight masks to obtain fused data.
10. The apparatus of claim 9, wherein the monitoring accuracy calculation module comprises:
and the time level monitoring accuracy calculation submodule is used for calculating the historical monitoring accuracy, the contemporaneous monitoring accuracy and the recent monitoring accuracy under the condition that the monitoring data comprise a historical monitoring data set, a recent monitoring data set.
11. The apparatus of claim 10, wherein the weight mask generation module comprises:
the time-level weight mask generation submodule is used for generating a historical weight mask according to the historical monitoring data set and the historical monitoring accuracy; generating a contemporaneous weight mask according to the contemporaneous monitoring data set and the contemporaneous monitoring accuracy; and generating a recent weight mask according to the recent monitoring data set and the recent monitoring accuracy.
12. The apparatus of claim 11, wherein the monitoring accuracy calculation module comprises:
the first data acquisition submodule is used for acquiring monitoring data in a monitoring coverage area, and the monitoring data comprises an echo diagram and a rain gauge station data set;
the area level precipitation accuracy calculation submodule is used for carrying out area level division on the monitoring coverage area, and under the condition that the echo value r of a rain gauge station is larger than or equal to a threshold value in each divided area block, calculating the ratio of the number of samples with precipitation and the echo value r on the rain gauge station to the number of samples with precipitation, so as to obtain the precipitation accuracy of the echo value r in the area block, and recording the precipitation accuracy as the area level precipitation accuracy; the region level precipitation accuracy rate comprises: historical precipitation accuracy at the zone level, contemporaneous precipitation accuracy at the zone level, and recent precipitation accuracy at the zone level.
13. The apparatus of claim 12, wherein the weight mask generation module comprises:
the area level mapping table generation submodule is used for generating an area level mapping table according to the echo value of an area block in the echo diagram, the distance between the echo value and a radar center, and the corresponding relation between an azimuth angle and the area level precipitation accuracy rate;
and the region-level weight mask generation submodule generates a weight mask corresponding to the echo map by using the region-level mapping table, wherein the weight mask comprises a region-level historical weight mask, a region-level contemporaneous weight mask and a region-level recent weight mask.
14. The apparatus of claim 13, wherein the monitoring accuracy calculation module comprises:
the second data acquisition submodule is used for acquiring monitoring data output by the plurality of monitoring devices, and the monitoring data comprises an echo diagram and a precipitation diagram;
a lattice-level precipitation accuracy rate calculation submodule, configured to perform lattice-level division on the monitoring coverage area, and calculate, in each divided lattice-level block, a ratio of the number of samples with precipitation and an echo value r 'at a central point, where the echo value r' at the central point is greater than or equal to the threshold, to the number of samples with precipitation and the echo value at the central point is r ', so as to obtain a precipitation accuracy rate of the echo value r' in the lattice-level block, which is recorded as a lattice-level precipitation accuracy rate, and the lattice-level block is smaller than the region block; the lattice-level precipitation accuracy includes: historical precipitation accuracy at a grid point level, contemporaneous precipitation accuracy at a grid point level, and recent precipitation accuracy at a grid point level.
15. The apparatus of claim 14, wherein the weight mask generation module comprises:
a grid point level mapping table generation submodule, configured to generate a grid point level mapping table according to an echo value of a grid level block in the echo diagram, the distance from the radar center, and a corresponding relationship between the azimuth angle and the grid point level precipitation accuracy rate;
and the grid point level weight mask generation submodule generates the weight masks corresponding to the echo graph by utilizing the grid point level mapping table, wherein the weight masks comprise historical weight masks of grid point levels, contemporaneous weight masks of the grid point levels and recent weight masks of the grid point levels.
16. The apparatus of claim 15, wherein the weight mask generation module further comprises:
the basic weight mask generation submodule is used for generating a basic weight mask corresponding to each monitoring device by utilizing an inverse distance index function;
and the comprehensive weight mask calculation submodule is used for obtaining a comprehensive weight mask according to the historical weight mask of the area level, the contemporary weight mask of the area level and the recent weight mask of the area level, the historical weight mask of the lattice level, the contemporary weight mask of the lattice level and the recent weight mask of the lattice level, and the basic weight masks corresponding to the monitoring devices, so that the monitoring data output by the monitoring devices are fused by using the weight masks to obtain fused data.
17. An electronic device, comprising:
at least one processor; and a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011615040.9A CN112685492B (en) | 2020-12-30 | 2020-12-30 | Multi-source data fusion method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011615040.9A CN112685492B (en) | 2020-12-30 | 2020-12-30 | Multi-source data fusion method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112685492A true CN112685492A (en) | 2021-04-20 |
| CN112685492B CN112685492B (en) | 2024-04-16 |
Family
ID=75455416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011615040.9A Active CN112685492B (en) | 2020-12-30 | 2020-12-30 | Multi-source data fusion method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112685492B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114565330A (en) * | 2022-04-30 | 2022-05-31 | 江西省气象信息中心(江西省气象培训中心、江西省农村经济信息中心) | Health degree evaluation method, system, equipment and storage medium of precipitation observation equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150164389A1 (en) * | 2013-12-16 | 2015-06-18 | Medtronic Minimed, Inc. | Methods and systems for improving the reliability of orthogonally redundant sensors |
| CN108761574A (en) * | 2018-05-07 | 2018-11-06 | 中国电建集团北京勘测设计研究院有限公司 | Rainfall evaluation method based on Multi-source Information Fusion |
| CN108761576A (en) * | 2018-05-28 | 2018-11-06 | 国网山西省电力公司电力科学研究院 | A kind of X-band weather radar and precipitation station data fusion method and system |
| CN111123410A (en) * | 2019-12-26 | 2020-05-08 | 国网北京市电力公司 | Precipitation monitoring system and method, storage medium and processor |
| CN111259366A (en) * | 2020-01-22 | 2020-06-09 | 支付宝(杭州)信息技术有限公司 | Verification code recognizer training method and device based on self-supervision learning |
-
2020
- 2020-12-30 CN CN202011615040.9A patent/CN112685492B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150164389A1 (en) * | 2013-12-16 | 2015-06-18 | Medtronic Minimed, Inc. | Methods and systems for improving the reliability of orthogonally redundant sensors |
| CN108761574A (en) * | 2018-05-07 | 2018-11-06 | 中国电建集团北京勘测设计研究院有限公司 | Rainfall evaluation method based on Multi-source Information Fusion |
| CN108761576A (en) * | 2018-05-28 | 2018-11-06 | 国网山西省电力公司电力科学研究院 | A kind of X-band weather radar and precipitation station data fusion method and system |
| CN111123410A (en) * | 2019-12-26 | 2020-05-08 | 国网北京市电力公司 | Precipitation monitoring system and method, storage medium and processor |
| CN111259366A (en) * | 2020-01-22 | 2020-06-09 | 支付宝(杭州)信息技术有限公司 | Verification code recognizer training method and device based on self-supervision learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114565330A (en) * | 2022-04-30 | 2022-05-31 | 江西省气象信息中心(江西省气象培训中心、江西省农村经济信息中心) | Health degree evaluation method, system, equipment and storage medium of precipitation observation equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112685492B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pinson et al. | From probabilistic forecasts to statistical scenarios of short‐term wind power production | |
| CN110471979B (en) | Power grid information display simulation system based on multi-source simulation data aggregation and mining | |
| CN111858820B (en) | Land property identification method and device, electronic equipment and storage medium | |
| CN110555061B (en) | Method and device for determining track similarity | |
| JP2018054626A (en) | Method and system for nowcasting precipitation on the basis of probability distributions | |
| CN111757098B (en) | Debugging method and device after installation of intelligent face monitoring camera, camera and medium | |
| CN112256526A (en) | Data real-time monitoring method and device based on machine learning | |
| US11689154B2 (en) | Systems and methods for distributed-solar power forecasting using parameter regularization | |
| CN111553844B (en) | Method and device for updating point cloud | |
| CN111578951B (en) | Method and device for generating information in automatic driving | |
| CN111738072A (en) | Training method and device of target detection model and electronic equipment | |
| CN110675635A (en) | Method and device for acquiring external parameters of camera, electronic equipment and storage medium | |
| CN111506803A (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN112987064A (en) | Building positioning method, device, equipment, storage medium and terminal equipment | |
| CN112685492A (en) | Multi-source data fusion method and device | |
| CN112100302A (en) | Map information point display method, device, equipment and readable storage medium | |
| CN116028730A (en) | Search resource abnormality identification method and device and electronic equipment | |
| CN115203340A (en) | Method, device, equipment and storage medium for determining companion relationship | |
| WO2022063029A1 (en) | Detecting and managing anomalies in underground sensors for agricultural applications | |
| James et al. | Forecasters’ cognitive task analysis and mental workload analysis of issuing probabilistic hazard information (PHI) during FACETs PHI prototype experiment | |
| US20210192554A1 (en) | Method, apparatus, device and storage medium for judging permanent area change | |
| CN111694914A (en) | User resident area determining method and device | |
| WO2023178328A2 (en) | Systems and methods for ramp predictions for forecasting power using neighboring sites | |
| CN114418243B (en) | Distributed new energy cloud grid prediction method and system | |
| CN115687587A (en) | Internet of things equipment and space object association matching method, device, equipment and medium based on position information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |