Urban monitoring point intelligent recommendation system based on meteorological data space-time collaborative analysis

Abstract

The invention relates to the field of intelligent recommendation, and particularly discloses a city monitoring point position intelligent recommendation system based on meteorological data space-time collaborative analysis, which is characterized in that a plurality of city monitoring point positions are preset, and a data set of meteorological monitoring data is acquired; a data analysis and processing algorithm based on a deep neural network model is adopted to carry out time domain analysis on the data set of the meteorological monitoring data of each city monitoring point, and then spatial significant aggregation is carried out on the meteorological monitoring time sequence characteristics of each monitoring point; and automatically determining a recommendation result of the city monitoring point according to comparison between the point location saliency coefficient between the global city monitoring point meteorological monitoring data space-time aggregation features obtained through aggregation and each time sequence feature and a preset threshold value. In this way, microclimate characteristics in a city can be reflected more comprehensively, and the problem that fixed point locations are difficult to adjust in a traditional method is solved.

Description

Technical Field

[0001] The present application relates to the field of intelligent recommendation, and more specifically, to an intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data. Background Art

[0002] With the rapid development of urbanization, the urban heat island effect has become increasingly significant, resulting in significant differences in temperature and humidity between urban areas and surrounding rural areas. In order to better understand and respond to this change, it is necessary to add more meteorological monitoring stations within the city. Reasonable arrangement of monitoring points can not only ensure that the collected meteorological data is representative and accurate, but also provide reliable information support for weather forecasting, climate research and disaster warning, which is of great significance to improving urban management efficiency and the quality of life of residents.

[0003] Traditional methods for determining urban meteorological data monitoring points mainly rely on geostatistical methods, empirical rules, and other methods. However, due to the limited number of monitoring points, it is difficult to fully capture the complex microclimate characteristics in the city, especially under special meteorological conditions such as large terrain undulations or local heavy rainfall. The data from existing monitoring points is not representative enough, which may lead to the omission of key information. In addition, traditional fixed monitoring points appear rigid in the face of rapid urban development, and the original deployment plan may quickly become outdated. However, due to the reconstruction of infrastructure and capital investment, the cost of adjusting the monitoring network is high and the cycle is long, making it difficult to adapt to new changes and needs in the city in a timely manner, which limits the flexibility and timeliness of the monitoring system.

[0004] Therefore, an optimized urban monitoring point recommendation system is desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data, which presets multiple urban monitoring points, obtains data sets of meteorological monitoring data (wind speed value, wind direction, temperature value, humidity value, air pressure value and boundary layer height) of the multiple urban monitoring points, and adopts a data analysis and processing algorithm based on a deep neural network model to perform time domain analysis on the data sets of meteorological monitoring data of each urban monitoring point, and then spatially significantly aggregates the meteorological monitoring time series features of each monitoring point, so as to automatically determine the recommendation results of the urban monitoring points according to the spatiotemporal aggregation features of the global urban monitoring point meteorological monitoring data obtained by aggregation and the comparison between the point significant coefficients and the preset thresholds. In this way, by obtaining a comprehensive data set of multiple monitoring points, the microclimate characteristics inside the city can be more comprehensively reflected, especially under complex terrain and local extreme meteorological conditions. At the same time, the monitoring points can be dynamically adjusted according to the actual monitoring results, so that the monitoring network can flexibly respond to new situations in urban development, overcoming the problem that fixed points are difficult to adjust in traditional methods.

[0006] According to one aspect of the present application, there is provided an intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data, which includes: The city monitoring point setting module is used to preset multiple city monitoring points; A meteorological monitoring data acquisition and analysis module, used to acquire a data set of meteorological monitoring data of the plurality of urban monitoring points and perform time domain analysis to obtain a set of temporal significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points; A meteorological monitoring data aggregation module is used to perform spatiotemporal dynamic aggregation of meteorological monitoring data on the set of time-series significant aggregation representation vectors of meteorological monitoring data at the city monitoring points to obtain an aggregated representation of meteorological monitoring data at the global monitoring points, wherein the meteorological monitoring data aggregation module includes: a monitoring data static energy factor calculation unit, used to calculate the static energy factor of each time-series significant aggregation representation vector of meteorological monitoring data at the city monitoring points in the set of time-series significant aggregation representation vectors of meteorological monitoring data at the city monitoring points to obtain a set of meteorological static energy factors at the monitoring points; an energy field significant aggregation unit, used to perform spatial significant aggregation based on energy fields on the set of time-series significant aggregation representation vectors of meteorological monitoring data at the city monitoring points based on the set of meteorological static energy factors at the monitoring points to obtain an aggregated representation of meteorological monitoring data at the global monitoring points; The recommendation result generation module is used to determine the recommendation results of the urban monitoring points based on the urban monitoring point significance coefficient between the global monitoring point meteorological monitoring data aggregation representation and the set of urban monitoring point meteorological monitoring data time series significant aggregation representation vectors.

[0007] Compared with the prior art, the present application provides an intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data. It presets multiple urban monitoring points, obtains data sets of meteorological monitoring data (wind speed value, wind direction, temperature value, humidity value, air pressure value and boundary layer height) of the multiple urban monitoring points, and uses a data analysis and processing algorithm based on a deep neural network model to perform time domain analysis on the data sets of meteorological monitoring data of each urban monitoring point, and then spatially significantly aggregates the meteorological monitoring time series features of each monitoring point, so as to automatically determine the recommendation results of the urban monitoring points based on the spatiotemporal aggregation features of the global urban monitoring point meteorological monitoring data obtained by aggregation and the comparison between the point significant coefficients between the various time series features and the preset threshold. In this way, by obtaining a comprehensive data set of multiple monitoring points, the microclimate characteristics inside the city can be more comprehensively reflected, especially under complex terrain and local extreme meteorological conditions. At the same time, the monitoring points can be dynamically adjusted according to the actual monitoring results, so that the monitoring network can flexibly respond to new situations in urban development, overcoming the problem that fixed points are difficult to adjust in traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0009] Figure 1 It is a block diagram of an intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to an embodiment of the present application.

[0010] Figure 2 This is a data flow diagram of an intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to an embodiment of the present application.

[0011] Figure 3 It is a block diagram of the meteorological monitoring data acquisition and analysis module in the urban monitoring point intelligent recommendation system based on spatiotemporal collaborative analysis of meteorological data according to an embodiment of the present application.

[0012] Figure 4 It is a block diagram of a meteorological monitoring data aggregation module in an intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to an embodiment of the present application.

[0013] Figure 5 It is a block diagram of the energy field significant aggregation unit in the urban monitoring point intelligent recommendation system based on spatiotemporal collaborative analysis of meteorological data according to an embodiment of the present application. DETAILED DESCRIPTION

[0014] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, but rather these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0015] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0016] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0017] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0018] With the rapid development of urbanization, the urban heat island effect has become increasingly significant, resulting in significant differences in temperature and humidity between urban areas and surrounding rural areas. In order to better understand and respond to this change, it is necessary to add more meteorological monitoring stations within the city. Reasonable arrangement of monitoring points can not only ensure that the collected meteorological data is representative and accurate, but also provide reliable information support for weather forecasting, climate research and disaster warning, which is of great significance to improving urban management efficiency and the quality of life of residents.

[0019] Traditional methods for determining urban meteorological data monitoring points mainly rely on geostatistical methods, empirical rules, and other methods. However, due to the limited number of monitoring points, it is difficult to fully capture the complex microclimate characteristics in the city, especially under special meteorological conditions such as large terrain undulations or local heavy rainfall. The data from existing monitoring points is not representative enough, which may lead to the omission of key information. In addition, traditional fixed monitoring points appear rigid in the face of rapid urban development, and the original deployment plan may quickly become outdated. However, due to the reconstruction of infrastructure and capital investment, the cost of adjusting the monitoring network is high and the cycle is long, making it difficult to adapt to new changes and needs in the city in a timely manner, which limits the flexibility and timeliness of the monitoring system.

[0020] Therefore, in view of the above technical problems, the technical concept of the present application is to preset multiple urban monitoring points, obtain the data sets of meteorological monitoring data (wind speed value, wind direction, temperature value, humidity value, air pressure value and boundary layer height) of the multiple urban monitoring points, and use the data analysis and processing algorithm based on the deep neural network model to perform time domain analysis on the data sets of meteorological monitoring data of each urban monitoring point, and then perform spatial significant aggregation of the meteorological monitoring time series characteristics of each monitoring point, so as to automatically determine the recommendation results of the urban monitoring points according to the comparison between the temporal and spatial aggregation characteristics of the global urban monitoring point meteorological monitoring data obtained by aggregation and the point significant coefficient between each time series feature and the preset threshold. In this way, by obtaining a comprehensive data set of multiple monitoring points, the microclimate characteristics inside the city can be more comprehensively reflected, especially under complex terrain and local extreme meteorological conditions. At the same time, the monitoring points can be dynamically adjusted according to the actual monitoring results, so that the monitoring network can flexibly respond to new situations in urban development, overcoming the problem that fixed points are difficult to adjust in traditional methods.

[0021] Figure 1 It is a block diagram of an intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to an embodiment of the present application. Figure 1 and Figure 2As shown, according to the embodiment of the present application, the intelligent recommendation system 100 for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data includes: an urban monitoring point setting module 110, which is used to preset multiple urban monitoring points; a meteorological monitoring data acquisition and analysis module 120, which is used to obtain a data set of meteorological monitoring data of the multiple urban monitoring points and perform time domain analysis to obtain a set of temporal significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points; a meteorological monitoring data aggregation module 130, which is used to perform spatiotemporal dynamic aggregation of meteorological monitoring data on the set of temporal significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points to obtain a global monitoring point meteorological monitoring data aggregation representation; a recommendation result generation module 140, which is used to determine the recommendation result of the urban monitoring point based on the urban monitoring point significance coefficient between the global monitoring point meteorological monitoring data aggregation representation and the set of temporal significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points.

[0022] In the embodiment of the present application, the city monitoring point setting module 110 is used to preset multiple city monitoring points. It should be understood that different city monitoring points can capture the microclimate differences in different regions and provide more comprehensive and detailed meteorological data. Based on this, the meteorological characteristics and their changing laws of each region can be more accurately understood, which is important for subsequent accurate point recommendation. In the technical solution of the present application, multiple city monitoring points are preset.

[0023] In an embodiment of the present application, the meteorological monitoring data acquisition and analysis module 120 is used to obtain a data set of meteorological monitoring data from the multiple urban monitoring points and perform time domain analysis to obtain a set of temporal significant aggregation representation vectors of the meteorological monitoring data from the urban monitoring points. Figure 3 : is a block diagram of a meteorological monitoring data acquisition and analysis module in an urban monitoring point intelligent recommendation system based on spatiotemporal collaborative analysis of meteorological data according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 3 As shown, the meteorological monitoring data acquisition and analysis module 120 includes: a city monitoring point meteorological monitoring data acquisition unit 121, which is used to obtain a data set of meteorological monitoring data of the multiple city monitoring points, wherein the meteorological monitoring data includes wind speed value, wind direction, temperature value, humidity value, air pressure value and boundary layer height; a meteorological monitoring data time domain analysis unit 122, which is used to perform time domain analysis on the data set of meteorological monitoring data of each city monitoring point in the data set of meteorological monitoring data of the multiple city monitoring points to obtain a set of time series significant aggregation representation vectors of the meteorological monitoring data of the city monitoring points.

[0024] Specifically, in an embodiment of the present application, the urban monitoring point meteorological monitoring data acquisition unit 121 is used to obtain a data set of meteorological monitoring data of the plurality of urban monitoring points, wherein the meteorological monitoring data includes wind speed value, wind direction, temperature value, humidity value, air pressure value and boundary layer height. Accordingly, considering that different data in the meteorological data of each monitoring point have different changes, and in order to be able to understand and analyze the meteorological conditions of different regions more carefully, so as to reflect the differences and characteristics of the microclimates of different regions within the entire city, in the technical solution of the present application, a data set of meteorological monitoring data of the plurality of urban monitoring points is obtained, wherein the meteorological monitoring data includes wind speed value, wind direction, temperature value, humidity value, air pressure value and boundary layer height. In this way, the meteorological changes of each monitoring point can be fully captured, thereby providing reliable data support for subsequent point recommendations.

[0025] Specifically, in an embodiment of the present application, the meteorological monitoring data time domain analysis unit 122 is used to perform time domain analysis on the data set of meteorological monitoring data of each city monitoring point in the data set of meteorological monitoring data of the multiple city monitoring points to obtain a set of time series significant aggregation representation vectors of the meteorological monitoring data of the city monitoring points. More specifically, in an embodiment of the present application, the meteorological monitoring data time domain analysis unit is used to: input the data set of meteorological monitoring data of each city monitoring point in the data set of meteorological monitoring data of the multiple city monitoring points into the forward LSTM-based time series extractor to obtain a set of time series significant aggregation representation vectors of the meteorological monitoring data of the city monitoring points. It should be understood that considering that the data set of meteorological monitoring data of each city monitoring point in the data set of meteorological monitoring data of the multiple city monitoring points has characteristic information in time series, that is, the meteorological data has a law of change over time, such as seasonal changes, periodic fluctuations, etc. Based on this, in order to capture and mine the time series patterns and potential trends of the meteorological monitoring data of each monitoring point, in the technical solution of the present application, a time domain analysis is performed on the data set of meteorological monitoring data of each city monitoring point in the data set of meteorological monitoring data of the multiple city monitoring points to obtain a set of time series significant aggregation representation vectors of the meteorological monitoring data of the city monitoring points. In particular, in a specific embodiment of the present application, a time series extractor based on a forward LSTM is used to extract time series features from the data set of meteorological monitoring data of each city monitoring point in the data set of meteorological monitoring data of the multiple city monitoring points and capture significant time domain associations in different time periods, so as to obtain a set of time series significant aggregation representation vectors of the meteorological monitoring data of the city monitoring points.

[0026] In an embodiment of the present application, the meteorological monitoring data aggregation module 130 is used to perform spatiotemporal dynamic aggregation of meteorological monitoring data on the set of temporal significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points to obtain an aggregated representation of the meteorological monitoring data of the global monitoring points. Figure 4 : is a block diagram of a meteorological monitoring data aggregation module in an urban monitoring point intelligent recommendation system based on spatiotemporal collaborative analysis of meteorological data according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 4 As shown, the meteorological monitoring data aggregation module 130 includes: a monitoring data static energy factor calculation unit 131, which is used to calculate the static energy factor of each city monitoring point meteorological monitoring data time series significant aggregation representation vector in the set of the city monitoring point meteorological monitoring data time series significant aggregation representation vector to obtain a set of monitoring point meteorological static energy factors; an energy field significant aggregation unit 132, which is used to perform energy field-based spatial significant aggregation of the set of city monitoring point meteorological monitoring data time series significant aggregation representation vectors based on the set of monitoring point meteorological static energy factors to obtain the global monitoring point meteorological monitoring data aggregation representation. Accordingly, considering that the set of city monitoring point meteorological monitoring data time series significant aggregation representation vectors expresses the significant features of each monitoring point in the time series and its aggregation representation. Meteorological phenomena usually have spatial correlation, that is, the meteorological conditions in adjacent areas are often similar. Therefore, in order to integrate the data of each monitoring point from the spatial dimension to provide a global view of the entire city and to fully understand the urban meteorological conditions, in the technical solution of the present application, the set of temporal significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points is subjected to spatiotemporal dynamic aggregation of the meteorological monitoring data to obtain the spatiotemporal collaborative significant aggregation representation vector of the global urban monitoring point meteorological monitoring data as the aggregate representation of the global monitoring point meteorological monitoring data.

[0027] Specifically, first, the static energy factor of each city monitoring point meteorological monitoring data time series significant aggregation representation vector in the set of the city monitoring point meteorological monitoring data time series significant aggregation representation vector is calculated to obtain a set of monitoring point meteorological static energy factors. That is, for a given set of feature vectors, the influence or significance of each vector in the feature space can be measured according to a specific evaluation standard, and the evaluation result is quantified into a numerical index, called the static energy factor, which reflects the position and role of each feature vector in the overall data structure, and provides help for the selection of the subsequent initial aggregation center.

[0028] Then, based on the set of meteorological static energy factors of the monitoring points, the set of time series significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points is subjected to spatial significant aggregation based on the energy field to obtain the spatiotemporal collaborative significant aggregation representation vector of the meteorological monitoring data of the global urban monitoring points. In this way, through the spatial significant aggregation based on the energy field, it is possible to identify which monitoring points have higher significance in the entire energy distribution space, and these significant points may represent important nodes or hot spots of meteorological changes. Specifically, first, the time series significant aggregation representation vector of the meteorological monitoring data of the urban monitoring points corresponding to the largest static energy factor is selected from the set of meteorological static energy factors of the monitoring points as the initial center vector of the time series clustering of the meteorological monitoring data of the urban monitoring points to determine that the data has strong representativeness and influence in the global scope, and ensure that the clustering results can better reflect the global characteristics. Then, based on the spatial span and static energy factor of the time series significant aggregation representation vector of the meteorological monitoring data of each urban monitoring point and the initial center vector of the clustering, the dynamic aggregation energy factor of the time series significant aggregation representation vector of the meteorological monitoring data of each urban monitoring point is calculated to obtain the set of dynamic aggregation energy factors of the time series of the meteorological monitoring data of the urban monitoring points. It should be understood that the dynamic aggregation energy factor can quantify the dynamic influence of each monitoring point between its time-series significant aggregation representation vector and the initial center vector of the cluster, which helps to understand the dynamic changes of each monitoring point in time and space and its impact on the overall meteorological pattern. Then, each dynamic aggregation energy factor is input into the gated mask unit for weight adaptive adjustment and screening of significant features to convert it into a weight to obtain a set of dynamic aggregation weight factors of the time series of meteorological monitoring data of the urban monitoring point. Finally, based on the set of weight factors, the set of time-series significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring point is weighted and averaged to obtain a global urban monitoring point meteorological monitoring data time-space collaborative significant aggregation representation vector that can fully reflect the time and space dimensions of each monitoring point. In this way, the time-series significant aggregation representation vectors of each monitoring point can be integrated, and the importance of each vector can be adjusted according to their weight factors (such as dynamic aggregation energy factors) to fully reflect the meteorological data of the entire city.

[0029] Specifically, in an embodiment of the present application, the monitoring data static energy factor calculation unit 131 is used to: calculate the mean and variance of the time series significant aggregation representation vector of the urban monitoring point meteorological monitoring data to obtain the time series mean and time series variance of the urban monitoring point meteorological monitoring data; subtract the time series significant aggregation representation vector of the urban monitoring point meteorological monitoring data from the time series mean of the urban monitoring point meteorological monitoring data by position, and calculate the fourth power of each position of the subtracted feature vector to obtain the time series differential modulation vector of the urban monitoring point meteorological monitoring data; calculate the expected value of the time series differential modulation vector of the urban monitoring point meteorological monitoring data to obtain the time series expected value of the urban monitoring point meteorological monitoring data; divide the time series expected value of the urban monitoring point meteorological monitoring data by the square of the time series variance of the urban monitoring point meteorological monitoring data, and input the value obtained by division into the sigmoid function to obtain the meteorological static energy factor of the monitoring point.

[0030] Figure 5 : is a block diagram of an energy field significant aggregation unit in an intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 5As shown, the energy field significant aggregation unit 132 includes: a subunit 1321 for determining the initial center vector of the clustering of meteorological monitoring data at urban monitoring points, which is used to select the time series significant aggregation representation vector of the meteorological monitoring data at urban monitoring points corresponding to the largest monitoring point meteorological static energy factor in the set of meteorological static energy factors at the monitoring points as the initial center vector of the time series clustering of meteorological monitoring data at urban monitoring points; a subunit 1322 for calculating the time series dynamic aggregation energy factor of meteorological monitoring data, which is used to calculate the time series dynamic aggregation energy factor of meteorological monitoring data based on the spatial span between the time series significant aggregation representation vector of each city monitoring point meteorological monitoring data in the set of meteorological monitoring data time series significant aggregation representation vector and the initial center vector of the time series clustering of meteorological monitoring data at urban monitoring points, as well as the static energy factor of the time series significant aggregation representation vector of each city monitoring point meteorological monitoring data and the static energy factor of the initial center vector of the time series clustering of meteorological monitoring data at urban monitoring points. , calculate the dynamic aggregation energy factor of each city monitoring point meteorological monitoring data time series significant aggregation representation vector in the set of the city monitoring point meteorological monitoring data time series significant aggregation representation vector to obtain a set of city monitoring point meteorological monitoring data time series dynamic aggregation energy factors; meteorological monitoring dynamic aggregation energy factor gating mask subunit 1323, used to input the set of city monitoring point meteorological monitoring data time series dynamic aggregation energy factors into the gating mask unit to obtain a set of city monitoring point meteorological monitoring data time series dynamic aggregation weight factors; monitoring point meteorological monitoring data global aggregation subunit 1324, used to calculate the weighted sum of the set of city monitoring point meteorological monitoring data time series significant aggregation representation vectors with the set of city monitoring point meteorological monitoring data time series dynamic aggregation weight factors to obtain the global city monitoring point meteorological monitoring data spatiotemporal collaborative significant aggregation representation vector as the global monitoring point meteorological monitoring data aggregation representation.

[0031] Specifically, the meteorological monitoring data time series dynamic aggregation energy factor calculation subunit is used to: multiply the static energy factor of the time series significant aggregation representation vector of the meteorological monitoring data at the city monitoring points and the static energy factor of the time series clustering initial center vector of the meteorological monitoring data at the city monitoring points with a first weighting parameter to obtain the first city monitoring point meteorological monitoring data time series dynamic aggregation energy factor; multiply the square of the spatial span between the time series significant aggregation representation vector of the meteorological monitoring data at the city monitoring points and the initial center vector of the time series clustering of the meteorological monitoring data at the city monitoring points with a second weighting parameter to obtain the second city monitoring point meteorological monitoring data time series dynamic aggregation energy factor; divide the first city monitoring point meteorological monitoring data time series dynamic aggregation energy factor by the second city monitoring point meteorological monitoring data time series dynamic aggregation energy factor to obtain the city monitoring point meteorological monitoring data time series dynamic aggregation energy factor.

[0032] Specifically, the meteorological monitoring dynamic aggregation energy factor gated mask subunit includes: a meteorological monitoring dynamic aggregation energy factor normalization secondary subunit, which is used to normalize the set of time series dynamic aggregation energy factors of the meteorological monitoring data of the city monitoring points to obtain a set of normalized time series dynamic aggregation energy factors of the meteorological monitoring data of the city monitoring points; a normalized meteorological monitoring dynamic aggregation energy factor mask secondary subunit, which is used to mask the set of normalized time series dynamic aggregation energy factors of the meteorological monitoring data of the city monitoring points to obtain a set of time series dynamic aggregation weight factors of the meteorological monitoring data of the city monitoring points.

[0033] More specifically, in an embodiment of the present application, the meteorological monitoring dynamic aggregation energy factor normalization secondary subunit is used to: use a sigmoid function to normalize the set of time series dynamic aggregation energy factors of the meteorological monitoring data of the urban monitoring points to obtain the set of normalized time series dynamic aggregation energy factors of the meteorological monitoring data of the urban monitoring points.

[0034] More specifically, in an embodiment of the present application, the normalized meteorological monitoring dynamic aggregation energy factor mask secondary sub-unit is used to: in response to each normalized urban monitoring point meteorological monitoring data time series dynamic aggregation energy factor in the set of normalized urban monitoring point meteorological monitoring data time series dynamic aggregation energy factors being greater than a predetermined threshold, set the normalized urban monitoring point meteorological monitoring data time series dynamic aggregation energy factor to the original value, and set the rest to zero, so as to obtain a set of urban monitoring point meteorological monitoring data time series dynamic aggregation weight factors.

[0035] In the embodiment of the present application, specifically, the meteorological monitoring data time series dynamic aggregation is performed on the set of the time series significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points, which can be expressed by the formula:

[0036] in, is a set of time series significant aggregation representation vectors of the meteorological monitoring data of the city monitoring points, are respectively the first, second, ..., and third in the set of time series significant aggregation representation vectors of the meteorological monitoring data of the city monitoring points. ,..., The time series significant aggregation representation vector of meteorological monitoring data at monitoring points in each city, It is The time series of meteorological monitoring data at monitoring points in each city are significantly aggregated to represent the eigenvalues ​​of each position in the vector. To calculate the expected value, and They are The mean and variance of yes function, yes The corresponding meteorological static energy factor of the monitoring point, To select the maximum value corresponding to value, is the maximum matching value, is the initial center vector of the time series clustering of meteorological monitoring data at urban monitoring points, yes The corresponding meteorological static energy factor of the monitoring point, express and The space span between and is the weighting parameter, for The corresponding city monitoring point meteorological monitoring data time series dynamic aggregation energy factor, yes The corresponding normalized urban monitoring point meteorological monitoring data time series dynamic aggregation energy factor, For masking, is a predetermined threshold, yes The corresponding urban monitoring point meteorological monitoring data time series dynamic aggregation weight factor, is the number of vectors in the set of time series significant aggregation representation vectors of the meteorological monitoring data of the monitoring points in the city, It is the spatiotemporal collaborative significant aggregation representation vector of the global urban monitoring point meteorological monitoring data.

[0037] In an embodiment of the present application, the recommendation result generation module 140 is used to determine the recommendation results of the urban monitoring points based on the urban monitoring point significance coefficient between the global monitoring point meteorological monitoring data aggregation representation and the set of urban monitoring point meteorological monitoring data temporal significant aggregation representation vectors. Specifically, in an embodiment of the present application, the recommendation result generation module is used to: calculate the cosine similarity between the temporal significant aggregation representation vector of the meteorological monitoring data of each urban monitoring point in the set of the meteorological monitoring data of the urban monitoring point and the spatiotemporal collaborative significant aggregation representation vector of the global urban monitoring point meteorological monitoring data as the urban monitoring point significance coefficient to obtain the set of urban monitoring point significance coefficients; determine the recommendation results of the urban monitoring points based on the comparison between the urban monitoring point significance coefficient and the preset threshold. Accordingly, in order to analyze the significance of each city monitoring point meteorological monitoring data and the entire global city in a more fine-grained and accurate manner, in the technical solution of the present application, the cosine similarity between the time series significant aggregation representation vector of each city monitoring point meteorological monitoring data in the set of the time series significant aggregation representation vector of the city monitoring point meteorological monitoring data and the spatiotemporal collaborative significant aggregation representation vector of the global city monitoring point meteorological monitoring data is calculated as the city monitoring point significant coefficient to obtain a set of city monitoring point significant coefficients. In particular, cosine similarity is used to measure the directional consistency between two vectors, rather than their size or absolute value. In meteorological monitoring data, directional consistency can reflect the similarity between the data of each monitoring point and its global representation vector in the feature space, so as to highlight those monitoring points that are closest to the global representation vector in the feature space. That is, the comparison between the set of city monitoring point significant coefficients obtained by the significant analysis between the set of the time series significant aggregation representation vector of the city monitoring point meteorological monitoring data and the spatiotemporal collaborative significant aggregation representation vector of the global city monitoring point meteorological monitoring data is used to automatically determine the recommendation results of the city monitoring points. In this way, by obtaining a comprehensive data set from multiple monitoring points, the microclimate characteristics within the city can be more comprehensively reflected, especially under complex terrain and local extreme meteorological conditions. At the same time, the monitoring points can be dynamically adjusted according to the actual monitoring results, so that the monitoring network can flexibly respond to new situations in urban development, overcoming the problem of difficult adjustment of fixed points in traditional methods.

[0038] It should be understood that in the technical solution of the present application, the time-series significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points in the set of time-series significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points respectively represent the time-series significant aggregation characteristics of the meteorological monitoring data of the urban monitoring points; the spatiotemporal collaborative significant aggregation representation vectors of the meteorological monitoring data of the global urban monitoring points represent the spatial depth correlation characteristics of the time-series characteristics of the meteorological monitoring data of each urban detection point. In this way, in the process of calculating the cosine similarity between the time series significant aggregation representation vector of the meteorological monitoring data of each city monitoring point in the set of the time series significant aggregation representation vector of the meteorological monitoring data of the city monitoring points and the spatiotemporal collaborative significant aggregation representation vector of the meteorological monitoring data of the global city monitoring points as the significant coefficient of the city monitoring points, because there are spatiotemporal differences in the characteristic distribution between the time series significant aggregation representation vector of the meteorological monitoring data of each city monitoring point in the set of the time series significant aggregation representation vector of the meteorological monitoring data of the city monitoring points and the spatiotemporal collaborative significant aggregation representation vector of the meteorological monitoring data of the global city monitoring points, this will cause the spatiotemporal sparsity of the characteristic distribution of the time series significant aggregation representation vector of the meteorological monitoring data of each city monitoring point relative to the spatiotemporal collaborative significant aggregation representation vector of the meteorological monitoring data of the global city monitoring points, thereby affecting the calculation accuracy of the significant coefficient of the city monitoring points.

[0039] Based on this, in a preferred embodiment, the time series significant aggregation representation vectors of the meteorological monitoring data of each urban monitoring point are feature enhanced to obtain an optimized time series significant aggregation representation vector of the meteorological monitoring data of the urban monitoring points, including: performing L random sampling on the time series significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points to obtain L random disturbance eigenvalues ​​of the meteorological data of the urban monitoring points; arranging the L random disturbance eigenvalues ​​of the meteorological data of the urban monitoring points in an ordered manner from large to small to obtain the random disturbance ordered vectors of the meteorological data of the urban monitoring points; calculating the self-inner product of the time series significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points to obtain the energy modulation eigenvalues ​​of the meteorological data of the urban monitoring points; based on the city The energy modulation characteristic value of the meteorological data at the city monitoring points performs semantic intensity scaling on the randomly disturbed ordered vector of the meteorological data at the city monitoring points to obtain the semantically enhanced randomly disturbed ordered vector of the meteorological data at the city monitoring points; the product of the randomly disturbed ordered vector of the meteorological data at the semantically enhanced city monitoring points and the transposed vector of the temporal significant aggregation representation vector of the meteorological monitoring data at the city monitoring points is calculated to obtain the best sample prompt orthogonal modulation matrix of the meteorological data at the city monitoring points; the matrix product of the best sample prompt orthogonal modulation matrix of the meteorological data at the city monitoring points and the temporal significant aggregation representation vector of the meteorological monitoring data at the city monitoring points is calculated to obtain the optimized temporal significant aggregation representation vector of the meteorological monitoring data at the city monitoring points.

[0040] The above optimization process is expressed as follows:

[0041] in, and Indicates the significant aggregation representation vector of the time series of meteorological monitoring data at the monitoring points in the city The random sampling The random disturbance characteristic value of meteorological data at monitoring points in each city, represents L random samplings, represents the Gaussian density probability function, represents the mean of the random disturbance characteristic values ​​of the meteorological data at the monitoring points in the city, represents the random disturbance characteristic value of the meteorological data at the monitoring point of the city, It means to calculate the mean of the vector. represents the variance of the random disturbance eigenvalue of the meteorological data at the monitoring point of the city, is the random disturbance characteristic value of the meteorological data of the monitoring point in the city The eigenvalues ​​at the positions, is the length of the random disturbance characteristic value of the meteorological data at the city monitoring point, Express Arrange them in order from large to small. represents the ordered vector of random disturbance of meteorological data at the monitoring points of the city, represents the square of the vector's two-norm, represents the energy modulation characteristic value of the meteorological data at the monitoring point of the city, It means point multiplication by position. represents matrix multiplication, The transposed vector of the transposed vector of the time series significant aggregation representation vector of the meteorological monitoring data of the monitoring points in the city, The best sample of meteorological data of the city monitoring point indicates the orthogonal modulation matrix, A significant aggregation representation vector representing the optimized time series of meteorological monitoring data at the urban monitoring points.

[0042] Accordingly, by performing L random sampling on the time series significant aggregation representation vector of the meteorological monitoring data at the urban monitoring points to obtain a set of new feature values ​​based on the original features but containing slight changes, randomness is introduced to explore different aspects of the feature space, and by simulating the noise or variation in the actual data, the model is better generalized to unseen data. Then, these random perturbation feature values ​​of the meteorological data at the urban monitoring points are arranged in order from large to small to form an ordered vector of random perturbation of the meteorological data at the urban monitoring points to identify which perturbation directions may be the most important for the current problem. Such an ordering not only helps the algorithm focus on the feature differences that can best distinguish different categories, but also helps to reveal hidden data structures or patterns. Subsequently, the inner product of the time series significant aggregation representation vector of the urban monitoring point meteorological data is calculated to obtain the energy modulation eigenvalue of the urban monitoring point meteorological data. The energy modulation eigenvalue of the urban monitoring point meteorological data reflects the overall strength or "energy" of the original feature vector, and provides a benchmark for measuring the importance of the feature. Using this energy modulation eigenvalue of the urban monitoring point meteorological data as a reference point, the previously formed random perturbation ordered vector of the urban monitoring point meteorological data is semantically scaled to construct a semantically enhanced random perturbation ordered vector of the urban monitoring point meteorological data. In this way, those disturbances that appear to be more important in the original feature space are amplified, thereby enhancing the model's sensitivity to changes in key features, while also retaining relatively small but potentially useful disturbance information.

[0043] Then, the product of the random perturbation ordered vector of semantically enhanced urban monitoring point meteorological data and the transpose of the temporal significant aggregation representation vector of urban monitoring point meteorological data is calculated to obtain the best sample prompt orthogonal modulation matrix of urban monitoring point meteorological data. The purpose is to find the interaction between features from two different perspectives. The formed matrix can be regarded as a conversion tool for capturing and representing the complex linear relationship between features. Finally, the best sample prompt orthogonal modulation matrix of urban monitoring point meteorological data constructed above is applied to the original temporal significant aggregation representation vector of urban monitoring point meteorological data to complete the final feature structure modulation, so that the features are more in line with the requirements of the objective function, reduce redundant information, and maximize the retention of useful information, so as to improve learning efficiency and prediction performance.

[0044] In summary, the feature manifold optimization process of the temporal significant aggregation representation vector of the meteorological monitoring data of the urban monitoring points is explained, which extracts the best prompt examples based on the fine-grained target retrieval of random perturbations, and then guides the adversarial robustness learning based on the best prompt examples to complete the structure of the high-dimensional manifold of the feature vector in the feature space, so as to improve the detail and structure of the feature expression. In this way, the consistency of the feature distribution between the spatiotemporal collaborative significant aggregation representation vector of the global urban monitoring point meteorological monitoring data and the temporal significant aggregation representation vector of the meteorological monitoring data of the urban monitoring point is improved to improve the calculation accuracy of the significant coefficient of the urban monitoring point between the two. In this way, by obtaining a comprehensive data set of multiple monitoring points, the microclimate characteristics of the city can be more comprehensively reflected, especially under complex terrain and local extreme meteorological conditions. At the same time, the monitoring points can be dynamically adjusted according to the actual monitoring results, so that the monitoring network can flexibly respond to new situations in urban development, overcoming the problem that fixed points are difficult to adjust in traditional methods.

[0045] In summary, the intelligent recommendation system 100 for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to the embodiment of the present application is explained, which presets multiple urban monitoring points, obtains data sets of meteorological monitoring data (wind speed value, wind direction, temperature value, humidity value, air pressure value and boundary layer height) of the multiple urban monitoring points, and adopts a data analysis and processing algorithm based on a deep neural network model to perform time domain analysis on the data sets of meteorological monitoring data of each urban monitoring point, and then spatially significantly aggregates the meteorological monitoring time series features of each monitoring point, so as to automatically determine the recommendation results of the urban monitoring points according to the spatiotemporal aggregation features of the global urban monitoring point meteorological monitoring data obtained by aggregation and the comparison between the point significant coefficients and the preset thresholds. In this way, by obtaining a comprehensive data set of multiple monitoring points, the microclimate characteristics inside the city can be more comprehensively reflected, especially under complex terrain and local extreme meteorological conditions. At the same time, the monitoring points can be dynamically adjusted according to the actual monitoring results, so that the monitoring network can flexibly respond to new situations in urban development, overcoming the problem that fixed points are difficult to adjust in traditional methods.

[0046] As described above, the intelligent recommendation system 100 for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to the embodiment of the present application can be implemented in various wireless terminals, such as a server having an intelligent recommendation algorithm for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data. In one possible implementation, the intelligent recommendation system 100 for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to the embodiment of the present application can be integrated into a wireless terminal as a software module and / or a hardware module. For example, the intelligent recommendation system 100 for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the intelligent recommendation system 100 for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data can also be one of the many hardware modules of the wireless terminal.

[0047] Alternatively, in another example, the urban monitoring point intelligent recommendation system based on spatiotemporal collaborative analysis of meteorological data 100 and the wireless terminal may also be separate devices, and the urban monitoring point intelligent recommendation system based on spatiotemporal collaborative analysis of meteorological data 100 may be connected to the wireless terminal via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0048] The above descriptions of various implementations of the present disclosure are exemplary and not exhaustive. The disclosure is not limited to the disclosed implementations, and many modifications and variations are obvious to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The terms used herein are selected to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various practical methods disclosed herein.

Claims

1. An intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data, characterized in that: include: The city monitoring point setting module is used to preset multiple city monitoring points; A meteorological monitoring data acquisition and analysis module, used to acquire a data set of meteorological monitoring data of the plurality of urban monitoring points and perform time domain analysis to obtain a set of temporal significant aggregation representation vectors of the meteorological monitoring data of the urban monitoring points; A meteorological monitoring data aggregation module is used to perform spatiotemporal dynamic aggregation of meteorological monitoring data on the set of time-series significant aggregation representation vectors of meteorological monitoring data at the city monitoring points to obtain an aggregated representation of meteorological monitoring data at the global monitoring points, wherein the meteorological monitoring data aggregation module includes: a monitoring data static energy factor calculation unit, used to calculate the static energy factor of each time-series significant aggregation representation vector of meteorological monitoring data at the city monitoring points in the set of time-series significant aggregation representation vectors of meteorological monitoring data at the city monitoring points to obtain a set of meteorological static energy factors at the monitoring points; an energy field significant aggregation unit, used to perform spatial significant aggregation based on energy fields on the set of time-series significant aggregation representation vectors of meteorological monitoring data at the city monitoring points based on the set of meteorological static energy factors at the monitoring points to obtain an aggregated representation of meteorological monitoring data at the global monitoring points; The recommendation result generation module is used to determine the recommendation results of the urban monitoring points based on the urban monitoring point significance coefficient between the global monitoring point meteorological monitoring data aggregation representation and the set of temporal significant aggregation representation vectors of the urban monitoring point meteorological monitoring data.

2. The intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to claim 1 is characterized in that: The meteorological monitoring data acquisition and analysis module includes: An urban monitoring point meteorological monitoring data acquisition unit, used to acquire a data set of meteorological monitoring data of the plurality of urban monitoring points, wherein the meteorological monitoring data includes wind speed value, wind direction, temperature value, humidity value, air pressure value and boundary layer height; The meteorological monitoring data time domain analysis unit is used to perform time domain analysis on the data sets of meteorological monitoring data of each city monitoring point in the data sets of meteorological monitoring data of the multiple city monitoring points to obtain a set of time series significant aggregation representation vectors of the meteorological monitoring data of the city monitoring points.

3. The intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to claim 2 is characterized in that: The meteorological monitoring data time domain analysis unit is used to: input the data set of meteorological monitoring data of each city monitoring point in the data set of meteorological monitoring data of the multiple city monitoring points into a forward LSTM-based time series extractor to obtain a set of time series significant aggregation representation vectors of the meteorological monitoring data of the city monitoring points.

4. The intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to claim 3 is characterized in that: The monitoring data static energy factor calculation unit is used to: Calculate the mean and variance of the significant aggregation representation vector of the time series of the meteorological monitoring data at the urban monitoring points to obtain the time series mean of the meteorological monitoring data at the urban monitoring points and the time series variance of the meteorological monitoring data at the urban monitoring points; Subtracting the significant aggregation representation vector of the time series of the meteorological monitoring data at the urban monitoring points from the time series mean of the meteorological monitoring data at the urban monitoring points by position, and calculating the fourth power of each position of the subtracted feature vector to obtain the time series differential modulation vector of the meteorological monitoring data at the urban monitoring points; Calculating the expected value of the time series differential modulation vector of the meteorological monitoring data at the urban monitoring point to obtain the expected value of the time series of the meteorological monitoring data at the urban monitoring point; The expected value of the time series of the meteorological monitoring data at the urban monitoring point is divided by the square of the time series variance of the meteorological monitoring data at the urban monitoring point, and the value obtained by the division is input into the sigmoid function to obtain the meteorological static energy factor of the monitoring point.

5. The intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to claim 4 is characterized in that: The energy field significant aggregation unit comprises: The subunit for determining the initial center vector of clustering of meteorological monitoring data at urban monitoring points is used to select the significant aggregation representation vector of the urban monitoring point meteorological monitoring data time series corresponding to the largest monitoring point meteorological static energy factor in the set of the monitoring point meteorological static energy factors as the initial center vector of the urban monitoring point meteorological monitoring data time series clustering; A meteorological monitoring data time series dynamic aggregation energy factor calculation subunit is used to calculate the dynamic aggregation energy factor of each city monitoring point meteorological monitoring data time series significant aggregation representation vector in the set of the city monitoring point meteorological monitoring data time series significant aggregation representation vector based on the spatial span between each city monitoring point meteorological monitoring data time series significant aggregation representation vector in the set of the city monitoring point meteorological monitoring data time series significant aggregation representation vector and the initial center vector of the city monitoring point meteorological monitoring data time series clustering, as well as the static energy factor of each city monitoring point meteorological monitoring data time series significant aggregation representation vector and the static energy factor of the initial center vector of the city monitoring point meteorological monitoring data time series clustering, so as to obtain a set of city monitoring point meteorological monitoring data time series dynamic aggregation energy factors; The meteorological monitoring dynamic aggregation energy factor gated mask subunit is used to input the set of the time series dynamic aggregation energy factors of the meteorological monitoring data of the urban monitoring points into the gated mask unit to obtain the set of time series dynamic aggregation weight factors of the meteorological monitoring data of the urban monitoring points; The global aggregation subunit of the meteorological monitoring data at the monitoring points is used to calculate the weighted sum of the set of time-series significant aggregation representation vectors of the meteorological monitoring data at the city monitoring points using the set of time-series dynamic aggregation weight factors of the meteorological monitoring data at the city monitoring points to obtain the spatiotemporal collaborative significant aggregation representation vector of the global meteorological monitoring data at the city monitoring points as the aggregation representation of the meteorological monitoring data at the global monitoring points.

6. The intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to claim 5 is characterized in that: The meteorological monitoring data time series dynamic aggregation energy factor calculation subunit is used to: The static energy factor of the significant aggregation representation vector of the time series of the meteorological monitoring data at the urban monitoring points and the static energy factor of the initial center vector of the time series clustering of the meteorological monitoring data at the urban monitoring points are multiplied by the first weighting parameter to obtain the first dynamic aggregation energy factor of the time series of the meteorological monitoring data at the urban monitoring points; The square of the spatial span between the significant aggregation representation vector of the urban monitoring point meteorological monitoring data time series and the initial center vector of the urban monitoring point meteorological monitoring data time series clustering is multiplied by the second weighting parameter to obtain a second urban monitoring point meteorological monitoring data time series dynamic aggregation energy factor; The time series dynamic aggregation energy factor of the meteorological monitoring data at the first city monitoring point is divided by the time series dynamic aggregation energy factor of the meteorological monitoring data at the second city monitoring point to obtain the time series dynamic aggregation energy factor of the meteorological monitoring data at the city monitoring point.

7. The intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to claim 6 is characterized in that: The meteorological monitoring dynamic aggregation energy factor gated mask subunit comprises: The meteorological monitoring dynamic aggregation energy factor normalization secondary subunit is used to normalize the set of the time series dynamic aggregation energy factors of the meteorological monitoring data of the urban monitoring points to obtain a set of normalized time series dynamic aggregation energy factors of the meteorological monitoring data of the urban monitoring points; The normalized meteorological monitoring dynamic aggregation energy factor masking secondary subunit is used to mask the set of normalized urban monitoring point meteorological monitoring data time series dynamic aggregation energy factors to obtain the set of urban monitoring point meteorological monitoring data time series dynamic aggregation weight factors.

8. The intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to claim 7 is characterized in that: The meteorological monitoring dynamic aggregation energy factor normalization secondary subunit is used to: use the sigmoid function to normalize the set of dynamic aggregation energy factors of the time series of meteorological monitoring data at the urban monitoring points to obtain the set of normalized dynamic aggregation energy factors of the time series of meteorological monitoring data at the urban monitoring points.

9. The intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to claim 8 is characterized in that: The normalized meteorological monitoring dynamic aggregation energy factor mask secondary sub-unit is used to: in response to each normalized urban monitoring point meteorological monitoring data time series dynamic aggregation energy factor in the set of normalized urban monitoring point meteorological monitoring data time series dynamic aggregation energy factors being greater than a predetermined threshold, set the normalized urban monitoring point meteorological monitoring data time series dynamic aggregation energy factor to the original value, and set the rest to zero, so as to obtain a set of urban monitoring point meteorological monitoring data time series dynamic aggregation weight factors.

10. The intelligent recommendation system for urban monitoring points based on spatiotemporal collaborative analysis of meteorological data according to claim 9 is characterized in that: The recommendation result generating module is used to: Calculate the cosine similarity between the temporal significant aggregation representation vector of the meteorological monitoring data of each urban monitoring point in the set of the temporal significant aggregation representation vector of the meteorological monitoring data of the urban monitoring points and the spatiotemporal collaborative significant aggregation representation vector of the meteorological monitoring data of the global urban monitoring points as the significant coefficient of the urban monitoring points to obtain the set of significant coefficients of the urban monitoring points; Based on the comparison between the significance coefficient of the urban monitoring point and a preset threshold, the recommendation result of the urban monitoring point is determined.

Images