Meteorological detection forecast information issuing system based on intelligent early warning
Through an intelligent early warning system based on the LSTM model, combined with user needs and early warning needs, a meteorological early warning model is built, which solves the problems of redundancy and inefficiency in the traditional meteorological early warning information release system, and realizes the accurate release and efficient transmission of meteorological early warning information.
Patent Information
- Application Number
- CN202510648923.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-20
- Publication Date
- 2025-08-15
AI Technical Summary
The traditional meteorological warning information release system lacks consideration for users' meteorological attention needs, resulting in redundant and inefficient information release, which makes it difficult to meet the efficient and accurate needs of modern society for meteorological warning information.
Using an intelligent early warning system based on the LSTM model, through the information release comprehensive need analysis module and the early warning information release execution module, a meteorological early warning model for different meteorological early warning types is constructed, and in-depth analysis is carried out based on user needs and early warning needs, priority is given to the release requirements, and publishing strategies are selected through information matching groups.
It realizes the accurate release of meteorological warning information, improves the efficiency and accuracy of information release, and meets the personalized needs of users.
Smart Images
Figure CN120494752A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of meteorological early warning, and more particularly to a meteorological detection and forecast information release system based on intelligent early warning. Background Art
[0002] In the field of meteorological warning technology, accurate and timely weather warning information release is crucial for protecting public life and property and reducing losses from natural disasters. However, traditional weather warning information release systems often suffer from issues such as lack of targeted information release and low efficiency, making them unable to meet modern society's demand for efficient and accurate weather warning information.
[0003] The rapid development of technologies like big data and artificial intelligence has provided new technical means for the accurate and efficient dissemination of meteorological warning information. The LSTM (Long Short-Term Memory) model, a specialized recurrent neural network (RNN), boasts strong capabilities for processing time series data and capturing long-term dependencies, and has been widely used in fields such as meteorological forecasting and early warning.
[0004] Although the existing meteorological warning system based on the LSTM model can meet the requirements of accurate warning of comprehensive meteorological information, the warning information release strategy is simple. After the warning information appears, all warning information needs to be integrated first, and then the integrated warning information is sent indiscriminately to system users. The lack of consideration for users' meteorological attention needs leads to information redundancy and inefficient release, which reduces the effectiveness of information release and user experience.
[0005] In order to solve the above problems, the present invention proposes a meteorological detection and forecast information release system based on intelligent early warning.
[0006] Invention Type In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a meteorological detection and forecast information release system based on intelligent early warning.
[0007] To achieve the above object, the present invention provides the following technical solutions: The meteorological detection and forecast information release system based on intelligent early warning includes an information warning release determination module, an information release comprehensive needs analysis module, an early warning information release execution module, and a release information browsing and collection module; The information warning release determination module is used to determine the weather warning users the system is targeting, collect weather data of the weather warning location in real time, set the weather forecast cycle, and determine all information release types after each weather forecast cycle; The information release comprehensive demand analysis module obtains the information release comprehensive demand value of each information release type when an information release type appears; The warning information release execution module sorts all information release types in descending order according to the values of the information release comprehensive requirement values, matches the first two adjacent information release types after sorting into an information collocation group, obtains the information collocation release value of the information collocation group, and executes the warning information release strategy based on the comparison result of the information collocation release value and the information collocation release threshold value; The published information browsing collection module collects browsing data of the weather warning user in real time when the weather warning user browses the weather warning content of the information publishing type.
[0008] Furthermore, after each weather forecast cycle, all information release types are determined, specifically: the weather warning value of each weather warning type in the weather warning location is obtained, and the weather warning threshold is set. When the weather warning value of a weather warning type is greater than or equal to the weather warning threshold, the weather warning type is marked as an information release type.
[0009] Furthermore, the meteorological warning value of the meteorological warning type is obtained in the following manner: obtain the meteorological characteristics of the meteorological warning location in the previous j consecutive meteorological forecast periods, combine the j meteorological characteristics into a meteorological period feature set, obtain a meteorological warning model of the meteorological warning type, use the meteorological period feature set as input data of the meteorological warning model, and the meteorological warning model outputs the meteorological warning value of the meteorological warning type.
[0010] Furthermore, the meteorological characteristics of the weather forecast period are obtained by collecting all meteorological data of the weather warning locations within the weather forecast period, preprocessing and feature extraction of the meteorological data, and obtaining meteorological characteristics.
[0011] Furthermore, the comprehensive information release demand value of the information release type is obtained by the following method: determine an information release type, obtain the information demand value of each meteorological warning user for the information release type, match all meteorological warning users into a demand comparison group, obtain the demand difference value of the demand comparison group, sum up the demand difference values of all demand comparison groups and take the average to obtain the demand difference mean Bzg, set the information demand threshold, when the information demand value of the meteorological warning user for the information release type is greater than the information demand threshold, mark the meteorological warning user as a release target user, when the information demand value of the meteorological warning user for the information release type is less than or equal to the information demand threshold, mark the meteorological warning user as a release exclusion user, mark the total number of release target users as Mey, mark the total number of release exclusion users as Hap, and use the formula Get the information release comprehensive demand value Ves of this information release type, and obtain the weather warning value Tep of this information release type, where da is the demand difference coefficient, db is the release target user coefficient, dc is the release exclusion user coefficient, and dd is the weather warning coefficient.
[0012] Furthermore, the demand difference value of the demand comparison group is obtained by calculating the difference between the information demand values of two weather warning users in the demand comparison group for the information release type and taking the absolute value to obtain the demand difference value of the demand comparison group.
[0013] Furthermore, the information demand value of the meteorological warning user for the information release type is obtained in the following way: obtain the information attention value of a meteorological warning user in the previous h consecutive meteorological forecast periods, sort all the information attention values in order according to the order of the meteorological forecast periods, sum the information attention values of the two adjacent meteorological forecast periods after sorting to obtain the attention duration value, set the attention duration threshold value, when the attention duration value is greater than the attention duration threshold value, increase the attention duration times by one, mark the attention duration times as Rtys, calculate the difference between the information attention values of the two adjacent meteorological forecast periods after sorting and take the absolute value, obtain the attention fluctuation value, set the attention fluctuation threshold value, when the attention fluctuation value is less than or equal to the attention fluctuation threshold value, increase the attention stability times by one, mark the attention stability times as Dskt, and use the formula The information demand value Hvmx of the weather warning user for the information release type is obtained, where wa is the attention persistence coefficient and wb is the attention stability coefficient.
[0014] Furthermore, the information attention value of a weather forecast period is obtained in the following manner: all browsing data of weather warning users for information release types within a weather forecast period are obtained, the browsing data are preprocessed and feature extracted to obtain browsing features, a browsing attention analysis model is obtained, the browsing features are used as input data of the browsing attention analysis model, and the browsing demand analysis model outputs the information attention value of the weather forecast period.
[0015] Furthermore, based on the comparison result of the information matching release value and the information matching release boundary value, the warning information release strategy is executed, specifically: the information matching release boundary value is set, when the information matching release value of the information matching group is greater than the information matching release boundary value, the meteorological warning contents of the two information release types in the information matching group are integrated and processed, and the integrated meteorological warning contents are sent to all meteorological warning users; when the information matching release value of the information matching group is less than or equal to the information matching release boundary value, the meteorological warning contents of the two information release types in the information matching group are sent separately to the corresponding release target users.
[0016] Furthermore, the information collocation release value of the information collocation group is obtained by the following method: summing the information release comprehensive demand values of two information release types in the information collocation group to obtain the information collocation release value of the information collocation group.
[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. Through the information release comprehensive demand analysis module and the warning information release execution module, the LSTM model is used to build a meteorological warning model for different meteorological warning types to meet the requirements of accurate warnings for different meteorological warning types. When the information release type that requires warning appears, the information release type is deeply analyzed from the two aspects of warning demand and user demand, and the release demand of different information release types is comprehensively analyzed; 2. Through the warning information release execution module, the information release types are sorted according to the priority of the release needs, and the necessity of combining the information release types is further considered through the information matching group. Different release strategies are selected for the release of meteorological warning information based on actual analysis, which comprehensively guarantees the release efficiency and accuracy of meteorological warning information. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 This is a system module diagram of a meteorological detection and forecast information release system based on intelligent early warning; Figure 2 This is the system operation flow chart of the meteorological detection and forecast information release system based on intelligent early warning; Figure 3 This is the execution flow chart for the early warning information release strategy. DETAILED DESCRIPTION
[0019] Reference Figures 1 to 3 The meteorological detection and forecast information release system based on intelligent early warning includes an information early warning release determination module, an information release comprehensive need analysis module, an early warning information release execution module, and a release information browsing and collection module.
[0020] Information warning release determination module: Determine the meteorological warning users the system is targeting (meteorological warning users are users who register for this system), collect meteorological data of meteorological warning locations in real time, set the meteorological forecast cycle, and obtain the meteorological warning value of each meteorological warning type in the meteorological warning location after each meteorological forecast cycle (meteorological warning types include typhoon warning type, rainstorm warning type, strong wind warning type, high temperature warning type, etc.), set the meteorological warning threshold (the meteorological warning threshold is the system preset threshold), when the meteorological warning value of the meteorological warning type is greater than or equal to the meteorological warning threshold, the meteorological warning type is marked as an information release type, and when the meteorological warning value of the meteorological warning type is less than the meteorological warning threshold, no further processing is performed.
[0021] The meteorological warning value of a meteorological warning type is obtained in the following way: obtain the meteorological characteristics of the meteorological warning location in the previous j consecutive meteorological forecast periods, combine the j meteorological characteristics into a meteorological period feature set, obtain a meteorological warning model of the meteorological warning type, use the meteorological period feature set as input data of the meteorological warning model, and the meteorological warning model outputs the meteorological warning value of the meteorological warning type.
[0022] The meteorological characteristics of the weather forecast period are obtained in the following way: all meteorological data of the weather warning locations within the weather forecast period are collected, and the meteorological data are preprocessed and feature extracted (preprocessing includes data cleaning, denoising, normalization and other steps, and feature extraction includes statistical feature extraction, frequency domain feature extraction and other steps) to obtain meteorological characteristics.
[0023] Different meteorological warning types correspond to different meteorological warning models. All meteorological warning models are built based on the LSTM model. In the specific implementation method, the construction process of the meteorological warning model of the typhoon warning type will be disclosed in detail, and the construction process of the meteorological warning model of the rainstorm warning type will be briefly disclosed.
[0024] The process of constructing a meteorological warning model for typhoon warning type is as follows: multiple meteorological cycle feature sets are collected, an LSTM model is constructed, and the meteorological cycle feature sets are used as training data for the LSTM model. A meteorological warning value is assigned to each training data. The meteorological warning value ranges from 1.0 to 5.0. The larger the meteorological warning value, the higher the typhoon severity predicted for the next meteorological forecast period (the higher the severity, the greater the intensity, and the disaster risk will also increase accordingly). The smaller the meteorological warning value, the lower the typhoon severity predicted for the next meteorological forecast period. The training data is divided into a training set, a validation set, and a test set according to a set ratio of 5:2:1. The training set, validation set, and test set are trained. After the training is completed, the meteorological warning model is constructed.
[0025] The construction process of the meteorological warning model of the rainstorm warning type is as follows: the larger the meteorological warning value, the higher the predicted rainstorm severity in the next meteorological forecast cycle (the higher the severity, the greater the intensity, and the disaster risk will also increase accordingly); the smaller the meteorological warning value, the lower the predicted rainstorm severity in the next meteorological forecast cycle. The rest of the construction process is consistent with the construction process of the meteorological warning model of the typhoon warning type.
[0026] Information release comprehensive demand analysis module: when the information release type appears, obtain the information release comprehensive demand value of each information release type.
[0027] The comprehensive information release demand value of the information release type is obtained in the following way: determine an information release type, obtain the information demand value of each meteorological warning user for the information release type, match all meteorological warning users into a demand comparison group, obtain the demand difference value of the demand comparison group, sum up the demand difference values of all demand comparison groups and take the average to obtain the demand difference mean Bzg, set the information demand threshold (the information demand threshold is the system preset threshold), when the information demand value of the meteorological warning user for the information release type is greater than the information demand threshold, mark the meteorological warning user as the release target user, when the information demand value of the meteorological warning user for the information release type is less than or equal to the information demand threshold, mark the meteorological warning user as the release exclusion user, mark the total number of release target users as Mey, mark the total number of release exclusion users as Hap, and use the formula Get the comprehensive information release demand value Ves of this information release type, and get the meteorological warning value Tep of this information release type, where da is the demand difference coefficient, db is the release target user coefficient, dc is the release exclusion user coefficient, and dd is the meteorological warning coefficient. The value of da is 0.62, the value of db is 0.83, the value of dc is 0.81, and the value of dd is 0.71.
[0028] The demand difference value of the demand comparison group is obtained by calculating the difference between the information demand values of two weather warning users in the demand comparison group for the information release type and taking the absolute value to obtain the demand difference value of the demand comparison group.
[0029] The information demand value of the meteorological warning user for the information release type is obtained in the following way: obtain the information attention value of a meteorological warning user in the previous h consecutive meteorological forecast periods, sort all the information attention values in order according to the order of the meteorological forecast periods, sum the information attention values of the two adjacent meteorological forecast periods after sorting to obtain the attention duration value, set the attention duration threshold (the attention duration threshold is the system preset threshold), when the attention duration value is greater than the attention duration threshold, increase the attention duration times by one, when the attention duration value is less than or equal to the attention duration threshold, no further processing is performed, and the attention duration times are marked as Rtys, calculate the difference between the information attention values of the two adjacent meteorological forecast periods after sorting and take the absolute value to obtain the attention fluctuation value, set the attention fluctuation threshold (the attention fluctuation threshold is the system preset threshold), when the attention fluctuation value is greater than the attention fluctuation threshold, no further processing is performed, when the attention fluctuation value is less than or equal to the attention fluctuation threshold, increase the attention stability times by one, and mark the attention stability times as Dskt, and use the formula The information demand value Hvmx of the weather warning user for the information release type is obtained, where wa is the attention persistence coefficient and wb is the attention stability coefficient. The value of wa is 1.28 and the value of wb is 1.39.
[0030] The information attention value of a weather forecast period is obtained in the following way: obtaining all browsing data of weather warning users for information release types within a weather forecast period (such as all browsing data for typhoon warning types), preprocessing and feature extraction of the browsing data to obtain browsing features, obtaining a browsing attention analysis model, using the browsing features as input data of the browsing attention analysis model, and outputting the browsing demand analysis model to obtain the information attention value of the weather forecast period.
[0031] The browsing attention analysis model is constructed as follows: multiple browsing features are collected to build a deep learning model. The browsing features are used as training data for the deep learning model. An information attention value is assigned to each training data. The index range of the information attention value is (0.1~3.0). The larger the information attention value, the more attention the meteorological warning users pay to the information release type. The smaller the information attention value, the less attention the meteorological warning users pay to the information release type. The training data is divided into a 70% training set and a 30% validation set. The training set and the validation set are trained. After the training is completed, the browsing attention analysis model is constructed.
[0032] Through the information release comprehensive demand analysis module and the warning information release execution module, the LSTM model is used to build a meteorological warning model for different meteorological warning types to meet the precise warning requirements of different meteorological warning types. When the information release type that requires a warning appears, the information release type is deeply analyzed from the two aspects of warning needs and user needs, and the release needs of different information release types are comprehensively analyzed.
[0033] Warning information release execution module: sort all information release types in descending order according to the value of the comprehensive information release requirement value, match the first two adjacent information release types after sorting into an information matching group (for example, all information release types are sorted in descending order according to the value of the comprehensive information release requirement value as 1, typhoon warning type; 2, rainstorm warning type; 3, high wind warning type; 4, high temperature warning type, then the typhoon warning type and the rainstorm warning type are matched into an information matching group), obtain the information matching release value of the information matching group, set the information matching release boundary value (the information matching release boundary value is the system preset threshold value), when the information matching release value of the information matching group is greater than the information matching release boundary value, integrate the meteorological warning contents of the two information release types in the information matching group, and send the integrated meteorological warning contents to all meteorological warning users, when the information matching release value of the information matching group is less than or equal to the information matching release boundary value When the release threshold is matched, the meteorological warning contents of the two information release types in the information matching group are sent separately to the corresponding target users (taking the sorting order 1, typhoon warning type; 2, rainstorm warning type; 3, gale warning type; 4, high temperature warning type as an example, the typhoon warning type and the rainstorm warning type are matched into one information matching group, and the gale warning type and the high temperature warning type are matched into one information matching group. When the information matching release value of the information matching group containing the typhoon warning type and the rainstorm warning type is greater than the information matching release threshold, the meteorological warning contents of the typhoon warning type and the rainstorm warning type are integrated and processed, and the integrated meteorological warning contents are sent to all meteorological warning users. When the information matching release value of the information matching group containing the gale warning type and the high temperature warning type is less than or equal to the information matching release threshold, the meteorological warning contents of the gale warning type and the high temperature warning type are sent separately to the corresponding target users).
[0034] The information collocation release value of the information collocation group is obtained by the following method: summing the information release comprehensive demand values of two information release types in the information collocation group to obtain the information collocation release value of the information collocation group.
[0035] Release information browsing collection module: When a weather warning user browses the weather warning content of the information release type, the browsing data of the weather warning user is collected in real time.
[0036] Through the warning information release execution module, the information release types are sorted according to the priority of the release needs, and the necessity of combining the release types of information is further considered through the information matching group. Different release strategies are selected for the release of meteorological warning information based on actual analysis, which comprehensively ensures the release efficiency and accuracy of meteorological warning information.
[0037] The above formulas are all dimensionless and numerically calculated, and the preset parameters in the formulas are set by technicians in this field according to actual conditions.
[0038] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.
[0039] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0040] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0041] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0042] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0043] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0044] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.
Claims
1. The weather detection and forecast information release system based on intelligent early warning is characterized by: It includes information warning release determination module, information release comprehensive needs analysis module, warning information release execution module, and release information browsing and collection module; The information warning release determination module is used to determine the weather warning users the system is targeting, collect weather data of the weather warning location in real time, set the weather forecast cycle, and determine all information release types after each weather forecast cycle; The information release comprehensive demand analysis module obtains the information release comprehensive demand value of each information release type when an information release type appears; The warning information release execution module sorts all information release types in descending order according to the values of the information release comprehensive requirement values, matches the first two adjacent information release types after sorting into an information collocation group, obtains the information collocation release value of the information collocation group, and executes the warning information release strategy based on the comparison result of the information collocation release value and the information collocation release threshold value; The published information browsing collection module collects browsing data of the weather warning user in real time when the weather warning user browses the weather warning content of the information publishing type.
2. The weather detection and forecast information release system based on intelligent early warning according to claim 1 is characterized in that: After each weather forecast cycle, all information release types are determined, specifically: the weather warning value of each weather warning type in the weather warning location is obtained, the weather warning threshold is set, and when the weather warning value of a weather warning type is greater than or equal to the weather warning threshold, the weather warning type is marked as an information release type.
3. The weather detection and forecast information release system based on intelligent early warning according to claim 1 is characterized in that: The meteorological warning value of a meteorological warning type is obtained in the following way: obtain the meteorological characteristics of the meteorological warning location in the previous j consecutive meteorological forecast periods, combine the j meteorological characteristics into a meteorological period feature set, obtain a meteorological warning model of the meteorological warning type, use the meteorological period feature set as input data of the meteorological warning model, and the meteorological warning model outputs the meteorological warning value of the meteorological warning type.
4. The weather detection and forecast information release system based on intelligent early warning according to claim 3 is characterized in that: The meteorological characteristics of the weather forecast period are obtained by collecting all meteorological data of the weather warning locations within the weather forecast period, preprocessing and feature extraction of the meteorological data, and obtaining meteorological characteristics.
5. The weather detection and forecast information release system based on intelligent early warning according to claim 1 is characterized in that: The comprehensive information release demand value of the information release type is obtained by the following method: determine an information release type, obtain the information demand value of each meteorological warning user for the information release type, match all meteorological warning users into a demand comparison group, obtain the demand difference value of the demand comparison group, sum up the demand difference values of all demand comparison groups and take the average to obtain the demand difference mean Bzg, set the information demand threshold, when the information demand value of the meteorological warning user for the information release type is greater than the information demand threshold, mark the meteorological warning user as the release target user, when the information demand value of the meteorological warning user for the information release type is less than or equal to the information demand threshold, mark the meteorological warning user as the release exclusion user, mark the total number of release target users as Mey, mark the total number of release exclusion users as Hap, and use the formula Get the information release comprehensive demand value Ves of this information release type, and obtain the weather warning value Tep of this information release type, where da is the demand difference coefficient, db is the release target user coefficient, dc is the release exclusion user coefficient, and dd is the weather warning coefficient.
6. The weather detection and forecast information release system based on intelligent early warning according to claim 5 is characterized in that: The demand difference value of the demand comparison group is obtained by calculating the difference between the information demand values of two weather warning users in the demand comparison group for the information release type and taking the absolute value to obtain the demand difference value of the demand comparison group.
7. The weather detection and forecast information release system based on intelligent early warning according to claim 5 is characterized in that: The information demand value of the meteorological warning user for the information release type is obtained in the following way: obtain the information attention value of a meteorological warning user in the previous h consecutive meteorological forecast periods, sort all the information attention values in order of the meteorological forecast periods, sum the information attention values of the two adjacent meteorological forecast periods after sorting to obtain the attention duration value, set the attention duration threshold value, when the attention duration value is greater than the attention duration threshold value, increase the attention duration times by one, mark the attention duration times as Rtys, calculate the difference between the information attention values of the two adjacent meteorological forecast periods after sorting and take the absolute value, obtain the attention fluctuation value, set the attention fluctuation threshold value, when the attention fluctuation value is less than or equal to the attention fluctuation threshold value, increase the attention stability times by one, mark the attention stability times as Dskt, and use the formula The information demand value Hvmx of the weather warning user for the information release type is obtained, where wa is the attention persistence coefficient and wb is the attention stability coefficient.
8. The weather detection and forecast information release system based on intelligent early warning according to claim 7 is characterized in that: The information attention value of a weather forecast period is obtained in the following way: all browsing data of weather warning users for information release types within a weather forecast period are obtained, the browsing data are preprocessed and feature extracted to obtain browsing features, a browsing attention analysis model is obtained, the browsing features are used as input data of the browsing attention analysis model, and the browsing demand analysis model outputs the information attention value of the weather forecast period.
9. The weather detection and forecast information release system based on intelligent early warning according to claim 1 is characterized in that: Based on the comparison results of the information matching release value and the information matching release boundary value, the warning information release strategy is executed, specifically: the information matching release boundary value is set. When the information matching release value of the information matching group is greater than the information matching release boundary value, the meteorological warning contents of the two information release types in the information matching group are integrated and processed, and the integrated meteorological warning contents are sent to all meteorological warning users. When the information matching release value of the information matching group is less than or equal to the information matching release boundary value, the meteorological warning contents of the two information release types in the information matching group are sent separately to the corresponding release target users.
10. The weather detection and forecast information release system based on intelligent early warning according to claim 1 is characterized in that: The information collocation release value of the information collocation group is obtained by the following method: summing the information release comprehensive demand values of two information release types in the information collocation group to obtain the information collocation release value of the information collocation group.