WO2020000860A1 - 降雨量评估方法及装置、电子设备和计算机非易失性可读存储介质 - Google Patents

降雨量评估方法及装置、电子设备和计算机非易失性可读存储介质 Download PDF

Info

Publication number
WO2020000860A1
WO2020000860A1 PCT/CN2018/114486 CN2018114486W WO2020000860A1 WO 2020000860 A1 WO2020000860 A1 WO 2020000860A1 CN 2018114486 W CN2018114486 W CN 2018114486W WO 2020000860 A1 WO2020000860 A1 WO 2020000860A1
Authority
WO
WIPO (PCT)
Prior art keywords
rainfall
historical
information
environmental factors
prediction model
Prior art date
Application number
PCT/CN2018/114486
Other languages
English (en)
French (fr)
Inventor
顾宝宝
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2020000860A1 publication Critical patent/WO2020000860A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01W—METEOROLOGY
    • G01W1/00—Meteorology
    • G01W1/10—Devices for predicting weather conditions
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Definitions

  • the present application relates to the field of computer technology, and in particular, to a rainfall assessment method and device, an electronic device, and a computer non-volatile readable storage medium.
  • weather forecast is often performed.
  • the weather forecast can predict the rainfall and other information in the next few days, so that people can arrange the plan according to the weather forecast.
  • the farm can arrange the rainfall information based on the weather forecast Whether to delay sowing or collect crops in advance.
  • the embodiments of the present application provide a rainfall assessment method and device, an electronic device, and a computer non-volatile readable storage medium, which aim to solve the technical problem of low accuracy of rainfall forecast information and can improve the effectiveness of rainfall assessment. Sex.
  • an embodiment of the present application provides a rainfall assessment method, including: obtaining historical rainfall information of a target area and corresponding historical environmental factors; and performing the historical rainfall information and the corresponding historical environmental factors. Deep learning to obtain a rainfall prediction model; applying the rainfall prediction model to evaluate future rainfall information of the target area according to the real-time environmental factors of the target area.
  • the historical environmental factors include humidity information; or the historical environmental factors include humidity information, and further include: climate type and / or temperature information.
  • the step of performing deep learning on the historical rainfall information and the corresponding historical environmental factors to obtain a rainfall prediction model specifically includes: combining the historical environmental factors As an input, the corresponding historical rainfall information is used as an output, and a long-term and short-term memory network is used for deep learning to obtain the rainfall prediction model.
  • the step of performing deep learning on the historical rainfall information and the corresponding historical environmental factors to obtain a rainfall prediction model specifically includes: The sequence of historical environmental factors corresponding to multiple rainfalls is taken as an input, and the multiple historical rainfall information sequences corresponding to the multiple rainfalls are taken as an output, and a long-term and short-term memory network is used for deep learning to obtain the rainfall prediction model.
  • the rainfall prediction model is used to predict rainfall information in the first time period in the future.
  • the step of performing deep learning on the historical rainfall information and the corresponding historical environmental factors to obtain a rainfall prediction model specifically includes: Historical rainfall information corresponding to multiple rainfalls to determine historical rainfall change trend information; taking the sequence of historical environmental factors corresponding to multiple rainfalls within the second duration as input, and using the historical rainfall change trend information as At the output, a long-term and short-term memory network is used to perform deep learning to obtain the rainfall prediction model, wherein the rainfall prediction model is used to predict the change trend information of rainfall in the second time period in the future.
  • an embodiment of the present application provides a rainfall assessment device, including: an obtaining unit that obtains historical rainfall information of a target area and corresponding historical environmental factors; and a deep learning unit that compares the historical rainfall information and Perform deep learning on the corresponding historical environmental factors to obtain a rainfall prediction model; a rainfall evaluation unit applies the rainfall prediction model to evaluate future rainfall information of the target area according to the real-time environmental factors of the target area.
  • the historical environmental factors include humidity information; or the historical environmental factors include humidity information, and further include: climate type and / or temperature information.
  • the deep learning unit is configured to: use the historical environmental factors as input, take the corresponding historical rainfall information as output, and use long-short-term memory networks for deep learning, The rainfall prediction model is obtained.
  • the deep learning unit is configured to: use a sequence of historical environmental factors corresponding to multiple rainfalls within the first duration as input, and take multiple historical rainfalls corresponding to the multiple rainfalls.
  • the amount information sequence is used as an output, and a long-term and short-term memory network is used for deep learning to obtain the rainfall prediction model, wherein the rainfall prediction model is used to predict rainfall information within the first time period in the future.
  • the deep learning unit is configured to: determine historical rainfall change trend information according to historical rainfall information corresponding to multiple rainfalls in a second duration, and change the first rainfall information
  • the sequence of historical environmental factors corresponding to multiple rainfalls in a two-time period is used as an input, and the trend information of the historical rainfall is used as an output.
  • the long-term and short-term memory network is used for deep learning to obtain the rainfall prediction model.
  • the rainfall prediction model is used to predict the change trend information of rainfall in the second period of time in the future.
  • an embodiment of the present application provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a memory that can be processed by the at least one processor Instructions executed by the processor, the instructions are configured to perform the following steps: obtaining historical rainfall information of the target area and corresponding historical environmental factors; performing deep learning on the historical rainfall information and the corresponding historical environmental factors To obtain a rainfall prediction model; and applying the rainfall prediction model to evaluate future rainfall information of the target area based on real-time environmental factors of the target area.
  • the historical environmental factors include humidity information; or the historical environmental factors include humidity information, and further include: climate type and / or temperature information.
  • the instruction is specifically configured to perform the following steps: the historical environmental factors are used as an input, the corresponding historical rainfall information is used as an output, and long-term and short-term memory are used.
  • the network performs deep learning to obtain the rainfall prediction model.
  • the instruction is configured to specifically perform the following steps: a sequence of historical environmental factors corresponding to multiple rainfalls in the first duration is used as an input, and the multiple rainfalls are corresponding Multiple historical rainfall information sequences as output, long-short-term memory network is used for deep learning to obtain the rainfall prediction model, wherein the rainfall prediction model is used to predict the rainfall information in the first time period in the future .
  • the instruction is specifically configured to perform the following steps: determining historical rainfall change trend information according to historical rainfall information corresponding to multiple rainfalls in the second duration; Taking the sequence of historical environmental factors corresponding to multiple rainfalls within the second duration as input, taking the change trend information of the historical rainfall as output, and performing long-term short-term memory network deep learning to obtain the rainfall prediction model,
  • the rainfall prediction model is used to predict the change trend information of rainfall in the second time period in the future.
  • the present application also provides a computer non-volatile readable storage medium that stores computer instructions, and the computer instructions are used to cause a computer to perform the following steps: obtaining a target Regional historical rainfall information and corresponding historical environmental factors; performing deep learning on the historical rainfall information and the corresponding historical environmental factors to obtain a rainfall prediction model; and applying the The rainfall prediction model evaluates future rainfall information for the target area.
  • the historical environmental factors include humidity information; or the historical environmental factors include humidity information, and further include: climate type and / or temperature information.
  • the computer instructions are used to cause the computer to specifically perform the following steps: take the historical environmental factors as input, take the corresponding historical rainfall information as output, and use long
  • the short-term memory network performs deep learning to obtain the rainfall prediction model.
  • the computer instructions are used to cause the computer to specifically perform the following steps: using the sequence of historical environmental factors corresponding to multiple rainfalls in the first duration as an input, A plurality of historical rainfall information sequences corresponding to rainfall are used as an output, and a long-term and short-term memory network is used for deep learning to obtain the rainfall prediction model, wherein the rainfall prediction model is used to predict future rainfall in the first time period ⁇ ⁇ Quantity information.
  • the computer instructions are used to cause the computer to specifically perform the following steps: determine a change trend of historical rainfall according to historical rainfall information corresponding to multiple rainfalls in a second period of time Information; taking the sequence of historical environmental factors corresponding to multiple rainfalls within the second duration as input, taking the change information of the historical rainfall as output, using long-term and short-term memory networks for deep learning to obtain the rainfall prediction The model, wherein the rainfall prediction model is used to predict the change trend information of rainfall in the second time period in the future.
  • the above technical solution addresses the technical problem of inaccurate rainfall prediction in related technologies, and proposes to establish a rainfall prediction model through deep learning, and applies real-time environmental factors to the rainfall prediction model.
  • the rainfall prediction model It is based on deep learning of historical rainfall information and corresponding historical environmental factors.
  • real-time environmental factors are substituted into the rainfall prediction model to evaluate all possible rainfall under real-time environmental factors. information.
  • rainfall assessment is conducted in a deep learning manner, which greatly improves the effectiveness of rainfall assessment, facilitates people to arrange travel and work according to effective rainfall information, and facilitates people's daily lives.
  • FIG. 1 shows a flowchart of a rainfall assessment method according to an embodiment of the present application
  • FIG. 2 shows a flowchart of a rainfall assessment method according to another embodiment of the present application
  • FIG. 3 shows a flowchart of a rainfall assessment method according to still another embodiment of the present application.
  • FIG. 4 shows a block diagram of a rainfall assessment device according to an embodiment of the present application
  • FIG. 5 is a schematic diagram of a hardware structure of an electronic device that executes a rainfall assessment method according to an embodiment of the present application.
  • FIG. 1 shows a flowchart of a rainfall assessment method according to an embodiment of the present application.
  • an embodiment of the present application provides a rainfall assessment method, including:
  • Step 102 Obtain historical rainfall information of the target area and corresponding historical environmental factors.
  • Step 104 Perform deep learning on the historical rainfall information and the corresponding historical environmental factors to obtain a rainfall prediction model.
  • the historical environment factor is used as an input
  • the corresponding historical rainfall information is used as an output
  • long-term and short-term memory networks are used for deep learning to obtain the rainfall prediction model.
  • the historical environmental factor is an item
  • the corresponding historical rainfall information is also an item. It is mostly used to train a model that can predict a single rainfall through multiple single rainfalls.
  • Deep learning includes a variety of branches, and here is the long short-term memory network (LSTM, Long Short-Term Memory), which is a kind of time recurrent neural network, suitable for processing and predicting the interval and Important events with relatively long delays have historical environmental factors as conditions and historical rainfall information as results. Therefore, these two items can be used as input and output respectively, and a model for calculating rainfall information based on environmental factors can be obtained through training.
  • LSTM Long Short-Term Memory
  • Step 106 Apply the rainfall prediction model to evaluate future rainfall information of the target area according to the real-time environmental factors of the target area.
  • a rainfall prediction model can be established by deep learning, and real-time environmental factors are applied to the rainfall prediction model.
  • the rainfall prediction model is obtained by deep learning of historical rainfall information and corresponding historical environmental factors. Therefore, according to the efficient prediction function of deep learning, real-time environmental factors can be substituted into the rainfall prediction model to evaluate all possible rainfall information under real-time environmental factors.
  • rainfall assessment is conducted in a deep learning manner, which greatly improves the effectiveness of rainfall assessment, facilitates people to arrange travel and work according to effective rainfall information, and facilitates people's daily lives.
  • the historical environmental factors may include only humidity information.
  • Humidity information is closely related to rainfall and is the most important factor affecting rainfall. Therefore, rainfall information can be evaluated by using humidity information as the only historical environmental factor.
  • the historical environmental factors include humidity information, and further include: climate type and / or temperature information.
  • factors such as temperature and climate will also affect the regional humidity, or the environmental factors are the result of the interaction of various factors such as humidity, temperature, and climate.
  • climate information climatic type and / or temperature information is also taken into consideration, which is conducive to establishing a rainfall prediction model that is more in line with actual environmental conditions, thereby improving the prediction accuracy of the rainfall prediction model.
  • FIG. 2 shows a flowchart of a rainfall assessment method according to another embodiment of the present application.
  • a rainfall assessment method includes:
  • Step 202 Obtain historical rainfall information of the target area and corresponding historical environmental factors.
  • step 204 a sequence of historical environmental factors corresponding to multiple rainfalls in the first time period is used as an input, and a plurality of historical rainfall information sequences corresponding to the multiple rainfalls are used as an output.
  • the rainfall prediction model wherein the rainfall prediction model is used to predict rainfall information in the first time period in the future.
  • Step 206 Apply the rainfall prediction model to evaluate future rainfall information of the target area according to the real-time environmental factors of the target area.
  • the multiple rainfalls in the first duration as a whole that is, the multiple rainfalls in multiple groups are trained to obtain a model capable of predicting the multiple rainfalls in the first duration.
  • the historical environmental factors are ordered multiples, that is, a sequence, and the corresponding historical rainfall information is also ordered multiples. For example, based on historical environmental factors and rainfall information in the past three days, the rainfall information in the next three days is predicted. In this way, the time range of rainfall forecast is extended, it is convenient for people to arrange plans in advance, and it helps to improve the orderliness of people's lives and work.
  • FIG. 3 shows a flowchart of a rainfall assessment method according to another embodiment of the present application.
  • a rainfall assessment method includes:
  • Step 302 Obtain historical rainfall information of the target area and corresponding historical environmental factors.
  • Step 304 Determine change trend information of historical rainfall according to historical rainfall information corresponding to multiple rainfalls in the second duration.
  • the rainfall change trend information includes, but is not limited to, the average increase in the number of rainfalls in the second period, the average increase percentage, and the like.
  • Step 306 Take the sequence of historical environmental factors corresponding to multiple rainfalls in the second duration as input, take the change trend information of the historical rainfall as output, and perform long-term short-term memory network for deep learning to obtain the rainfall.
  • a prediction model wherein the rainfall prediction model is used to predict the change trend information of rainfall in the future for the second period of time.
  • the multiple rainfalls in the second duration as a whole are trained through multiple groups of multiple rainfalls to obtain a model capable of predicting multiple rainfall change trend information in the second duration.
  • the historical environmental factors are an ordered multiple, that is, a sequence
  • the corresponding historical rainfall change trend information is also an ordered multiple. For example, based on historical environmental factors and historical rainfall change trend information for three days in the history, predictions of rainfall change trend information for the next three days are predicted. In this way, the time range of the rainfall forecast is expanded than the single rainfall forecast, which makes it easier for people to arrange plans in advance and helps to improve the orderliness of people's lives and work.
  • Step 308 Apply the rainfall prediction model to evaluate future rainfall information of the target area according to the real-time environmental factors of the target area.
  • the prediction result is the change trend information of rainfall, that is, the change of rainfall is presented to people, compared with simply predicting the Multiple rainfalls can enable people to more clearly and comprehensively control future rainfall conditions, thereby saving the time cost of artificially assessing rainfall trends and facilitating faster preparation and response to future rainfall.
  • This change trend information is useful for agricultural production and Geographical research is of great significance.
  • FIG. 4 shows a block diagram of a rainfall assessment device according to an embodiment of the present application.
  • an embodiment of the present application provides a rainfall assessment device 400, including: an obtaining unit 402, which obtains historical rainfall information of a target area and corresponding historical environmental factors; and a deep learning unit 404, which analyzes the history The rainfall information and the corresponding historical environmental factors are subjected to deep learning to obtain a rainfall prediction model.
  • the rainfall evaluation unit 406 applies the rainfall prediction model to evaluate the target area based on the real-time environmental factors of the target area. Future rainfall information.
  • the rainfall assessment device 400 uses the solution described in any one of the embodiments in FIG. 1 to FIG. 3, and therefore has all the technical effects described above, which will not be repeated here.
  • the rainfall assessment device 400 also has the following technical features:
  • the historical environmental factors include humidity information; or the historical environmental factors include humidity information, and further include: climate type and / or temperature information.
  • the deep learning unit 404 is configured to: use the historical environmental factors as input, and use the corresponding historical rainfall information as output, and use long-term and short-term memory networks for deep learning To obtain the rainfall prediction model.
  • the deep learning unit 404 is configured to: use a sequence of historical environmental factors corresponding to multiple rainfalls in the first duration as input, and use multiple historical records corresponding to the multiple rainfalls.
  • the rainfall information sequence is used as an output, and a long-term and short-term memory network is used for deep learning to obtain the rainfall prediction model, wherein the rainfall prediction model is used to predict the rainfall information within the first time period in the future.
  • the deep learning unit 404 is configured to determine historical rainfall change trend information according to historical rainfall information corresponding to multiple rainfalls within a second duration, and The sequence of historical environmental factors corresponding to multiple rainfalls in the second time period is used as input, the change trend information of the historical rainfall is used as an output, and the short-term memory network is used to perform deep learning to obtain the rainfall prediction model.
  • the rainfall prediction model is used to predict the change trend information of rainfall in the second period in the future.
  • FIG. 5 is a schematic diagram of a hardware structure of an electronic device that performs a rainfall assessment method according to an embodiment of the present application. As shown in FIG. 5, the electronic device includes:
  • One or more processors 510 and a memory 520 are taken as an example in FIG. 5.
  • the electronic device may further include an input device 530 and an output device 540.
  • the processor 510, the memory 520, the input device 530, and the output device 540 may be connected through a bus or other methods.
  • the connection through the bus is taken as an example.
  • the memory 520 is a computer non-volatile readable storage medium, and can be used to store non-volatile software programs, non-volatile computer executable programs, and modules, such as programs corresponding to the rainfall assessment method in the embodiments of the present application. Instruction / module.
  • the processor 510 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions, and modules stored in the memory 520, that is, implementing the rainfall assessment method in the foregoing method embodiment.
  • the memory 520 may include a storage program area and a storage data area, where the storage program area may store an operating system and application programs required for at least one function; the storage data area may store data created according to the use of the rainfall assessment device, and the like.
  • the memory 520 may include a high-speed random access memory, and may further include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device.
  • the memory 520 may optionally include a memory remotely disposed with respect to the processor 510, and these remote memories may be connected to the rainfall assessment device through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
  • the input device 530 may receive inputted numeric or character information, and generate key signal inputs related to user settings and function control of the rainfall evaluation device.
  • the output device 540 may include a display device such as a display screen.
  • the one or more modules are stored in the memory 520, and when executed by the one or more processors 510, execute the rainfall amount evaluation method in any of the method embodiments described above.
  • the above product can execute the method provided in the embodiment of the present application, and has corresponding function modules and beneficial effects of executing the method.
  • the above product can execute the method provided in the embodiment of the present application, and has corresponding function modules and beneficial effects of executing the method.
  • the electronic devices in the embodiments of the present application exist in various forms, including but not limited to:
  • Mobile communication equipment This type of equipment is characterized by mobile communication functions, and its main goal is to provide voice and data communication.
  • Such terminals include: smart phones (such as iPhone), multimedia phones, feature phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has mobile Internet access characteristics.
  • Such terminals include: PDA, MID and UMPC devices, such as iPad.
  • Portable entertainment equipment This type of equipment can display and play multimedia content. These devices include audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.
  • the composition of the server includes a processor, hard disk, memory, and system bus.
  • the server is similar to a general-purpose computer architecture. , Reliability, security, scalability, manageability and other aspects of higher requirements.
  • this application also provides a computer non-volatile readable storage medium that stores computer instructions, and the computer instructions are used to cause a computer to perform the following steps: Historical rainfall information and corresponding historical environmental factors; deep learning of the historical rainfall information and corresponding historical environmental factors to obtain a rainfall prediction model; and applying the rainfall according to real-time environmental factors of the target area A quantitative prediction model evaluates future rainfall information for the target area.
  • the historical environmental factors include humidity information; or the historical environmental factors include humidity information, and further include: climate type and / or temperature information.
  • the computer instructions are used to cause the computer to specifically perform the following steps: take the historical environmental factors as input, take the corresponding historical rainfall information as output, and use long
  • the short-term memory network performs deep learning to obtain the rainfall prediction model.
  • the computer instructions are used to cause the computer to specifically perform the following steps: using the sequence of historical environmental factors corresponding to multiple rainfalls in the first duration as an input, A plurality of historical rainfall information sequences corresponding to rainfall are used as an output, and a long-term and short-term memory network is used for deep learning to obtain the rainfall prediction model, wherein the rainfall prediction model is used to predict future rainfall in the first time period ⁇ ⁇ Quantity information.
  • the computer instructions are used to cause the computer to specifically perform the following steps: determine a change trend of historical rainfall according to historical rainfall information corresponding to multiple rainfalls in a second period of time Information; taking the sequence of historical environmental factors corresponding to multiple rainfalls within the second duration as input, taking the change information of the historical rainfall as output, using long-term and short-term memory networks for deep learning to obtain the rainfall prediction The model, wherein the rainfall prediction model is used to predict the change trend information of rainfall in the second time period in the future.
  • the word “if” as used herein can be interpreted as “at” or “when” or “responding to determination” or “responding to detection”.
  • the phrases “if determined” or “if detected (the stated condition or event)” can be interpreted as “when determined” or “responded to the determination” or “when detected (the stated condition or event) ) “Or” in response to a test (statement or event stated) ".
  • the disclosed systems, devices, and methods may be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, which may be electrical, mechanical or other forms.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each of the units may exist separately physically, or two or more units may be integrated into one unit.
  • the above integrated unit may be implemented in the form of hardware, or in the form of hardware plus software functional units.

Landscapes

  • Environmental & Geological Engineering (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Atmospheric Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Ecology (AREA)
  • Environmental Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请提出了一种降雨量评估方法及系统和终端，其中，该方法包括：获取目标区域的历史降雨量信息和对应的历史环境因素；对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型；根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。本申请中，以深度学习的方式进行降雨量评估，提升了降雨量评估的有效性，方便了人们的日常生活。

Description

降雨量评估方法及装置、电子设备和计算机非易失性可读存储介质
本申请要求于2018年6月29日提交中国专利局、申请号为201810699290.1、发明名称为“降雨量评估方法及系统和终端”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及计算机技术领域，尤其涉及一种降雨量评估方法及装置、电子设备和计算机非易失性可读存储介质。
背景技术
目前，为满足人们实际生活需求，往往会进行天气预报，天气预报可预测未来几日的降雨量等信息，以便人们根据天气预报合理安排计划，如，农场可根据天气预报预测的降雨量信息安排是否延迟播种或提前收取农作物等。
然而，目前的降雨量预测信息准确度不高，对降雨量变化趋势定位不准，这就造成了人们根据不准确的降雨量信息安排的计划无效，极大地影响了人们的日常生活和工作。
因此，如何提升降雨量预测的准确性，成为目前亟待解决的技术问题。
申请内容
本申请实施例提供了一种降雨量评估方法及装置、电子设备和计算机非易失性可读存储介质，旨在解决降雨量预测信息准确度不高的技术问题，能够提升降雨量评估的有效性。
第一方面，本申请实施例提供了一种降雨量评估方法，包括：获取目标区域的历史降雨量信息和对应的历史环境因素；对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型；根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
在本申请上述实施例中，可选地，所述历史环境因素包括湿度 信息；或者所述历史环境因素包括湿度信息，以及还包括：气候类型和/或温度信息。
在本申请上述实施例中，可选地，所述对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型的步骤，具体包括：将所述历史环境因素作为输入，将对应的所述历史降雨量信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型。
在本申请上述实施例中，可选地，所述对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型的步骤，具体包括：将第一时长内的多次降雨对应的历史环境因素序列作为输入，将所述多次降雨对应的多项历史降雨量信息序列作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第一时长内的降雨量信息。
在本申请上述实施例中，可选地，所述对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型的步骤，具体包括：根据第二时长内的多次降雨对应的历史降雨量信息，确定历史降雨量的变化趋势信息；将所述第二时长内的多次降雨对应的历史环境因素序列作为输入，将所述历史降雨量的变化趋势信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第二时长内降雨量的变化趋势信息。
第二方面，本申请实施例提供了一种降雨量评估装置，包括：获取单元，获取目标区域的历史降雨量信息和对应的历史环境因素；深度学习单元，对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型；降雨量评估单元，根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
在本申请上述实施例中，可选地，所述历史环境因素包括湿度 信息；或者所述历史环境因素包括湿度信息，以及还包括：气候类型和/或温度信息。
在本申请上述实施例中，可选地，所述深度学习单元用于：将所述历史环境因素作为输入，将对应的所述历史降雨量信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型。
在本申请上述实施例中，可选地，所述深度学习单元用于：将第一时长内的多次降雨对应的历史环境因素序列作为输入，将所述多次降雨对应的多项历史降雨量信息序列作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第一时长内的降雨量信息。
在本申请上述实施例中，可选地，所述深度学习单元用于：根据第二时长内的多次降雨对应的历史降雨量信息，确定历史降雨量的变化趋势信息，以及将所述第二时长内的多次降雨对应的历史环境因素序列作为输入，将所述历史降雨量的变化趋势信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第二时长内降雨量的变化趋势信息。
第三方面，本申请实施例提供了一种电子设备，包括：至少一个处理器；以及，与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被设置为用于执行以下步骤：获取目标区域的历史降雨量信息和对应的历史环境因素；对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型；根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
在本申请上述实施例中，可选地，所述历史环境因素包括湿度信息；或者所述历史环境因素包括湿度信息，以及还包括：气候类型和/或温度信息。
在本申请上述实施例中，可选地，所述指令被设置为具体用于 执行以下步骤：将所述历史环境因素作为输入，将对应的所述历史降雨量信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型。
在本申请上述实施例中，可选地，所述指令被设置为用于具体执行以下步骤：将第一时长内的多次降雨对应的历史环境因素序列作为输入，将所述多次降雨对应的多项历史降雨量信息序列作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第一时长内的降雨量信息。
在本申请上述实施例中，可选地，所述指令被设置为具体用于执行以下步骤：根据第二时长内的多次降雨对应的历史降雨量信息，确定历史降雨量的变化趋势信息；将所述第二时长内的多次降雨对应的历史环境因素序列作为输入，将所述历史降雨量的变化趋势信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第二时长内降雨量的变化趋势信息。
第四方面，本申请还提供了一种计算机非易失性可读存储介质，所述计算机非易失性可读存储介质存储计算机指令，所述计算机指令用于使计算机执行以下步骤：获取目标区域的历史降雨量信息和对应的历史环境因素；对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型；根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
在本申请上述实施例中，可选地，所述历史环境因素包括湿度信息；或者所述历史环境因素包括湿度信息，以及还包括：气候类型和/或温度信息。
在本申请上述实施例中，可选地，所述计算机指令用于使所述计算机具体执行以下步骤：将所述历史环境因素作为输入，将对应的所述历史降雨量信息作为输出，利用长短期记忆网络进行深度学 习，得到所述降雨量预测模型。
在本申请上述实施例中，可选地，所述计算机指令用于使所述计算机具体执行以下步骤：将第一时长内的多次降雨对应的历史环境因素序列作为输入，将所述多次降雨对应的多项历史降雨量信息序列作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第一时长内的降雨量信息。
在本申请上述实施例中，可选地，所述计算机指令用于使所述计算机具体执行以下步骤：根据第二时长内的多次降雨对应的历史降雨量信息，确定历史降雨量的变化趋势信息；将所述第二时长内的多次降雨对应的历史环境因素序列作为输入，将所述历史降雨量的变化趋势信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第二时长内降雨量的变化趋势信息。
以上技术方案，针对相关技术中的降雨量预测不准确的技术问题，提出通过深度学习的方式建立降雨量预测模型，并将实时环境因素应用于该降雨量预测模型，其中，该降雨量预测模型是由历史降雨量信息和对应的历史环境因素深度学习而成，根据深度学习的高效预测功能，将实时环境因素代入该降雨量预测模型即可评估出实时环境因素下所有可能带来的降雨量信息。
通过以上技术方案，以深度学习的方式进行降雨量评估，大大提升了降雨量评估的有效性，便于人们根据有效的降雨量信息安排出行和工作等事务，方便了人们的日常生活。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其它的附图。
图1示出了本申请的一个实施例的降雨量评估方法的流程图；
图2示出了本申请的另一个实施例的降雨量评估方法的流程图；
图3示出了本申请的再一个实施例的降雨量评估方法的流程图；
图4示出了本申请的一个实施例的降雨量评估装置的框图；
图5示出了本申请的一个实施例的执行降雨量评估方法的电子设备的硬件结构示意图。
具体实施方式
图1示出了本申请的一个实施例的降雨量评估方法的流程图。
如图1所示，本申请实施例提供了一种降雨量评估方法，包括：
步骤102，获取目标区域的历史降雨量信息和对应的历史环境因素。
步骤104，对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型。
其中，在深度学习过程中，将所述历史环境因素作为输入，将对应的所述历史降雨量信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型。此方法中，历史环境因素为一项，对应的历史降雨量信息也为一项，多用于通过多种单次降雨，训练得到能预测单次降雨量的模型。
深度学习包括多种分支，而在此采用的则是长短期记忆网络(LSTM，Long Short-Term Memory)这一种，其为一种时间递归神经网络，适合于处理和预测时间序列中间隔和延迟相对较长的重要事件，历史环境因素为条件，历史降雨量信息为结果，故将这两项分别作为输入和输出，能够通过训练得到以环境因素计算出降雨量信息的模型。
步骤106，根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
由此，可通过深度学习的方式建立降雨量预测模型，并将实时环境因素应用于该降雨量预测模型，其中，该降雨量预测模型是由历史降雨量信息和对应的历史环境因素深度学习而成，根据深度学习的高效预测功能，将实时环境因素代入该降雨量预测模型即可评 估出实时环境因素下所有可能带来的降雨量信息。
通过以上技术方案，以深度学习的方式进行降雨量评估，大大提升了降雨量评估的有效性，便于人们根据有效的降雨量信息安排出行和工作等事务，方便了人们的日常生活。
在本申请的一种实现方式中，所述历史环境因素可仅包括湿度信息。湿度信息与降雨量息息相关，是影响降雨量的最重要的因素，因此，可通过湿度信息作为唯一的历史环境因素对降雨量进行评估。
在本申请的另一种实现方式中，所述历史环境因素包括湿度信息，以及还包括：气候类型和/或温度信息。在一定程度上，温度和气候等因素也会对地域的湿度有影响，或者说，环境因素是湿度、温度、气候等各种因素相互作用的结果。在湿度信息之外，还考虑气候类型和/或温度信息，有利于建立更加符合实际环境情况的降雨量预测模型，从而提升该降雨量预测模型的预测准确性。
图2示出了本申请的另一个实施例的降雨量评估方法的流程图。
如图2所示，本申请的另一个实施例的降雨量评估方法，包括：
步骤202，获取目标区域的历史降雨量信息和对应的历史环境因素。
步骤204，将第一时长内的多次降雨对应的历史环境因素序列作为输入，将所述多次降雨对应的多项历史降雨量信息序列作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第一时长内的降雨量信息。
步骤206，根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
具体来说，将第一时长内的多次降雨作为一个整体，即通过多组的多次降雨，训练得到能够预测第一时长内的多次降雨的模型。其中，历史环境因素为有序的多项，即一个序列，对应的历史降雨量信息也为有序的多项。比如，通过历史上多次的三天内历史环境因素及降雨量信息，预测未来三天内的降雨量信息。这样一来，扩 大了降雨量预测的时间范围，便于人们尽可能提前安排计划，有助于提升人们生活和工作的有序性。
图3示出了本申请的再一个实施例的降雨量评估方法的流程图。
如图3所示，本申请的再一个实施例的降雨量评估方法，包括：
步骤302，获取目标区域的历史降雨量信息和对应的历史环境因素。
步骤304，根据第二时长内的多次降雨对应的历史降雨量信息，确定历史降雨量的变化趋势信息。
其中，降雨量的变化趋势信息包括但不限于在第二时长内的多次降雨的平均增长量、平均增长百分比等。
步骤306，将所述第二时长内的多次降雨对应的历史环境因素序列作为输入，将所述历史降雨量的变化趋势信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第二时长内降雨量的变化趋势信息。
具体来说，将第二时长内的多次降雨作为一个整体，通过多组的多次降雨，训练得到能够预测第二时长内的多次降雨变化趋势信息的模型。其中，历史环境因素为有序的多项，即一个序列，对应的历史降雨量的变化趋势信息也为有序的多项。比如，通过历史上多次的三天内历史环境因素及历史降雨量的变化趋势信息，预测未来三天内的降雨量的变化趋势信息。这样一来，比预测单次的降雨量扩大了降雨量预测的时间范围，便于人们尽可能提前安排计划，有助于提升人们生活和工作的有序性。
步骤308，根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
此实施例与图1和图2示出的实施例的区别在于，其预测的结果为降雨量的变化趋势信息，即将降雨量的变化情况呈现在人们面前，相比于单纯预测一定时间内的多次降雨，能够使人们更清晰全面地掌控未来的降雨情况，从而节省人为评估降雨量趋势的时间成 本，便于更快速地对未来降雨做出准备和反应，这种变化趋势信息对于农业生产和地理研究等具有重大意义。
图4示出了本申请的一个实施例的降雨量评估装置的框图。
如图4所示，本申请实施例提供了一种降雨量评估装置400，包括：获取单元402，获取目标区域的历史降雨量信息和对应的历史环境因素；深度学习单元404，对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型；降雨量评估单元406，根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
该降雨量评估装置400使用图1至图3中任一实施例中任一项所述的方案，因此，具有上述所有技术效果，在此不再赘述。降雨量评估装置400还具有以下技术特征：
在本申请上述实施例中，可选地，所述历史环境因素包括湿度信息；或者所述历史环境因素包括湿度信息，以及还包括：气候类型和/或温度信息。
在本申请上述实施例中，可选地，所述深度学习单元404用于：将所述历史环境因素作为输入，将对应的所述历史降雨量信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型。
在本申请上述实施例中，可选地，所述深度学习单元404用于：将第一时长内的多次降雨对应的历史环境因素序列作为输入，将所述多次降雨对应的多项历史降雨量信息序列作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第一时长内的降雨量信息。
在本申请上述实施例中，可选地，所述深度学习单元404用于：根据第二时长内的多次降雨对应的历史降雨量信息，确定历史降雨量的变化趋势信息，以及将所述第二时长内的多次降雨对应的历史环境因素序列作为输入，将所述历史降雨量的变化趋势信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型， 其中，所述降雨量预测模型用于预测未来所述第二时长内降雨量的变化趋势信息。
图5示出了本申请的一个实施例的执行降雨量评估方法的电子设备的硬件结构示意图，如图5所示，该电子设备包括：
一个或多个处理器510以及存储器520，图5中以一个处理器510为例。
该电子设备还可以包括：输入装置530和输出装置540。
处理器510、存储器520、输入装置530和输出装置540可以通过总线或者其他方式连接，图5中以通过总线连接为例。
存储器520作为一种计算机非易失性可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本申请实施例中的降雨量评估方法对应的程序指令/模块。处理器510通过运行存储在存储器520中的非易失性软件程序、指令以及模块，从而执行服务器的各种功能应用以及数据处理，即实现上述方法实施例中的降雨量评估方法。
存储器520可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据降雨量评估装置的使用所创建的数据等。此外，存储器520可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，存储器520可选包括相对于处理器510远程设置的存储器，这些远程存储器可以通过网络连接至降雨量评估装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置530可接收输入的数字或字符信息，以及产生与降雨量评估装置的用户设置以及功能控制有关的键信号输入。输出装置540可包括显示屏等显示设备。
所述一个或者多个模块存储在所述存储器520中，当被所述一个或者多个处理器510执行时，执行上述任意方法实施例中的降雨 量评估方法。
上述产品可执行本申请实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本申请实施例所提供的方法。
本申请实施例的电子设备以多种形式存在，包括但不限于:
(1)移动通信设备:这类设备的特点是具备移动通信功能，并且以提供话音、数据通信为主要目标。这类终端包括:智能手机(例如iPhone)、多媒体手机、功能性手机，以及低端手机等。
(2)超移动个人计算机设备:这类设备属于个人计算机的范畴，有计算和处理功能，一般也具备移动上网特性。这类终端包括:PDA、MID和UMPC设备等，例如iPad。
(3)便携式娱乐设备:这类设备可以显示和播放多媒体内容。该类设备包括:音频、视频播放器(例如iPod)，掌上游戏机，电子书，以及智能玩具和便携式车载导航设备。
(4)服务器:提供计算服务的设备，服务器的构成包括处理器、硬盘、内存、系统总线等，服务器和通用的计算机架构类似，但是由于需要提供高可靠的服务，因此在处理能力、稳定性、可靠性、安全性、可扩展性、可管理性等方面要求较高。
(5)其他具有数据交互功能的电子装置。
另外，本申请还提供了一种计算机非易失性可读存储介质，所述计算机非易失性可读存储介质存储计算机指令，所述计算机指令用于使计算机执行以下步骤：获取目标区域的历史降雨量信息和对应的历史环境因素；对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型；根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
在本申请上述实施例中，可选地，所述历史环境因素包括湿度信息；或者所述历史环境因素包括湿度信息，以及还包括：气候类型和/或温度信息。
在本申请上述实施例中，可选地，所述计算机指令用于使所述计算机具体执行以下步骤：将所述历史环境因素作为输入，将对应的所述历史降雨量信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型。
在本申请上述实施例中，可选地，所述计算机指令用于使所述计算机具体执行以下步骤：将第一时长内的多次降雨对应的历史环境因素序列作为输入，将所述多次降雨对应的多项历史降雨量信息序列作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第一时长内的降雨量信息。
在本申请上述实施例中，可选地，所述计算机指令用于使所述计算机具体执行以下步骤：根据第二时长内的多次降雨对应的历史降雨量信息，确定历史降雨量的变化趋势信息；将所述第二时长内的多次降雨对应的历史环境因素序列作为输入，将所述历史降雨量的变化趋势信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第二时长内降雨量的变化趋势信息。
以上结合附图详细说明了本申请的技术方案，通过本申请的技术方案，以深度学习的方式进行降雨量评估，大大提升了降雨量评估的有效性，便于人们根据有效的降雨量信息安排出行和工作等事务，方便了人们的日常生活。
应当理解，本文中使用的术语“和/或”仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。
取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”或“响应于检测”。类似地，取决于语境，短语“如果确定”或“如果检测(陈述的条件或事件)”可以被解释成为“当确定时”或“响应于确定”或“当检测(陈述的条件 或事件)时”或“响应于检测(陈述的条件或事件)”。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
以上所述仅为本申请的较佳实施例而已，并不用以限制本申请，凡在本申请的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本申请保护的范围之内。

Claims (20)

  1. 一种降雨量评估方法，其特征在于，包括：
    获取目标区域的历史降雨量信息和对应的历史环境因素；
    对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型；
    根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
  2. 根据权利要求1所述的降雨量评估方法，其特征在于，
    所述历史环境因素包括湿度信息；或者
    所述历史环境因素包括湿度信息，以及还包括：气候类型和/或温度信息。
  3. 根据权利要求1所述的降雨量评估方法，其特征在于，所述对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型的步骤，具体包括：
    将所述历史环境因素作为输入，将对应的所述历史降雨量信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型。
  4. 根据权利要求3所述的降雨量评估方法，其特征在于，所述对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型的步骤，具体包括：
    将第一时长内的多次降雨对应的历史环境因素序列作为输入，将所述多次降雨对应的多项历史降雨量信息序列作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第一时长内的降雨量信息。
  5. 根据权利要求3所述的降雨量评估方法，其特征在于，所述对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型的步骤，具体包括：
    根据第二时长内的多次降雨对应的历史降雨量信息，确定历史降雨量的变化趋势信息；
    将所述第二时长内的多次降雨对应的历史环境因素序列作为输入，将所述历史降雨量的变化趋势信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第二时长内降雨量的变化趋势信息。
  6. 一种降雨量评估装置，其特征在于，包括：
    获取单元，获取目标区域的历史降雨量信息和对应的历史环境因素；
    深度学习单元，对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型；
    降雨量评估单元，根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
  7. 根据权利要求6所述的降雨量评估装置，其特征在于，
    所述历史环境因素包括湿度信息；或者
    所述历史环境因素包括湿度信息，以及还包括：气候类型和/或温度信息。
  8. 根据权利要求6所述的降雨量评估装置，其特征在于，所述深度学习单元用于：
    将所述历史环境因素作为输入，将对应的所述历史降雨量信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型。
  9. 根据权利要求8所述的降雨量评估装置，其特征在于，所述深度学习单元用于：
    将第一时长内的多次降雨对应的历史环境因素序列作为输入，将所述多次降雨对应的多项历史降雨量信息序列作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第一时长内的降雨量信息。
  10. 根据权利要求8所述的降雨量评估装置，其特征在于，所述深度学习单元用于：根据第二时长内的多次降雨对应的历史降雨量信息，确定历史降雨量的变化趋势信息，以及将所述第二时长内 的多次降雨对应的历史环境因素序列作为输入，将所述历史降雨量的变化趋势信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第二时长内降雨量的变化趋势信息。
  11. 一种电子设备，其特征在于，包括：至少一个处理器；以及，与所述至少一个处理器通信连接的存储器；
    其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被设置为用于执行以下步骤：
    获取目标区域的历史降雨量信息和对应的历史环境因素；
    对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型；
    根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
  12. 根据权利要求11所述的电子设备，其特征在于，
    所述历史环境因素包括湿度信息；或者
    所述历史环境因素包括湿度信息，以及还包括：气候类型和/或温度信息。
  13. 根据权利要求11所述的电子设备，其特征在于，所述指令被设置为具体用于执行以下步骤：
    将所述历史环境因素作为输入，将对应的所述历史降雨量信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型。
  14. 根据权利要求13所述的电子设备，其特征在于，所述指令被设置为用于具体执行以下步骤：
    将第一时长内的多次降雨对应的历史环境因素序列作为输入，将所述多次降雨对应的多项历史降雨量信息序列作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第一时长内的降雨量信息。
  15. 根据权利要求13所述的电子设备，其特征在于，所述指令 被设置为具体用于执行以下步骤：
    根据第二时长内的多次降雨对应的历史降雨量信息，确定历史降雨量的变化趋势信息；
    将所述第二时长内的多次降雨对应的历史环境因素序列作为输入，将所述历史降雨量的变化趋势信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第二时长内降雨量的变化趋势信息。
  16. 一种计算机非易失性可读存储介质，其特征在于，所述计算机非易失性可读存储介质存储计算机指令，所述计算机指令用于使计算机执行以下步骤：
    获取目标区域的历史降雨量信息和对应的历史环境因素；
    对所述历史降雨量信息和所述对应的历史环境因素进行深度学习，得到降雨量预测模型；
    根据所述目标区域的实时环境因素，应用所述降雨量预测模型评估所述目标区域的未来降雨量信息。
  17. 根据权利要求16所述的计算机非易失性可读存储介质，其特征在于，
    所述历史环境因素包括湿度信息；或者
    所述历史环境因素包括湿度信息，以及还包括：气候类型和/或温度信息。
  18. 根据权利要求16所述的计算机非易失性可读存储介质，其特征在于，所述计算机指令用于使所述计算机具体执行以下步骤：
    将所述历史环境因素作为输入，将对应的所述历史降雨量信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型。
  19. 根据权利要求18所述的计算机非易失性可读存储介质，其特征在于，所述计算机指令用于使所述计算机具体执行以下步骤：
    将第一时长内的多次降雨对应的历史环境因素序列作为输入，将所述多次降雨对应的多项历史降雨量信息序列作为输出，利用长 短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第一时长内的降雨量信息。
  20. 根据权利要求18所述的计算机非易失性可读存储介质，其特征在于，所述计算机指令用于使所述计算机具体执行以下步骤：
    根据第二时长内的多次降雨对应的历史降雨量信息，确定历史降雨量的变化趋势信息；
    将所述第二时长内的多次降雨对应的历史环境因素序列作为输入，将所述历史降雨量的变化趋势信息作为输出，利用长短期记忆网络进行深度学习，得到所述降雨量预测模型，其中，所述降雨量预测模型用于预测未来所述第二时长内降雨量的变化趋势信息。
PCT/CN2018/114486 2018-06-29 2018-11-08 降雨量评估方法及装置、电子设备和计算机非易失性可读存储介质 WO2020000860A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810699290.1 2018-06-29
CN201810699290.1A CN109239807A (zh) 2018-06-29 2018-06-29 降雨量评估方法及系统和终端

Publications (1)

Publication Number Publication Date
WO2020000860A1 true WO2020000860A1 (zh) 2020-01-02

Family

ID=65072272

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/114486 WO2020000860A1 (zh) 2018-06-29 2018-11-08 降雨量评估方法及装置、电子设备和计算机非易失性可读存储介质

Country Status (2)

Country Link
CN (1) CN109239807A (zh)
WO (1) WO2020000860A1 (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109799550B (zh) * 2019-03-20 2022-02-18 北京百度网讯科技有限公司 用于预测降雨强度的方法和装置
CN110646867A (zh) * 2019-08-28 2020-01-03 北京无线电计量测试研究所 一种城市排水监测预警方法和系统
CN115438841A (zh) * 2019-11-13 2022-12-06 吉林农业大学 基于人工智能精准预测降雨模型的训练方法及预测方法
CN111324039A (zh) * 2020-04-13 2020-06-23 湖南文理学院 一种用于屋顶花园浇灌的雨水循环系统及其控制方法
CN112241813B (zh) * 2020-10-20 2024-01-23 山东大学 基于小波分解的降雨预测方法及系统
CN112470888A (zh) * 2020-11-02 2021-03-12 广东职业技术学院 一种智慧社区的自动浇水方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7941274B1 (en) * 2006-08-03 2011-05-10 The Weather Channel, Llc Advanced verification information for improved operational results
CN107179566A (zh) * 2017-05-12 2017-09-19 周调彪 一种区县天气预测的自学习修正方法及系统
CN107966747A (zh) * 2017-11-22 2018-04-27 成都欧远信电子科技有限公司 高精度的区域天气预测系统
CN107991722A (zh) * 2017-12-25 2018-05-04 北京墨迹风云科技股份有限公司 天气预测模型的建立方法、预测方法和预测装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10467540B2 (en) * 2016-06-02 2019-11-05 The Climate Corporation Estimating confidence bounds for rainfall adjustment values
CN106405682B (zh) * 2016-08-29 2019-04-26 深圳先进技术研究院 一种降雨预测方法及装置
CN107703564B (zh) * 2017-10-13 2020-04-14 中国科学院深圳先进技术研究院 一种降雨预测方法、系统及电子设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7941274B1 (en) * 2006-08-03 2011-05-10 The Weather Channel, Llc Advanced verification information for improved operational results
CN107179566A (zh) * 2017-05-12 2017-09-19 周调彪 一种区县天气预测的自学习修正方法及系统
CN107966747A (zh) * 2017-11-22 2018-04-27 成都欧远信电子科技有限公司 高精度的区域天气预测系统
CN107991722A (zh) * 2017-12-25 2018-05-04 北京墨迹风云科技股份有限公司 天气预测模型的建立方法、预测方法和预测装置

Also Published As

Publication number Publication date
CN109239807A (zh) 2019-01-18

Similar Documents

Publication Publication Date Title
WO2020000860A1 (zh) 降雨量评估方法及装置、电子设备和计算机非易失性可读存储介质
US20200143681A1 (en) Parking Identification and Availability Prediction
CN111210656B (zh) 停车场空闲车位预测方法、装置、电子设备及存储介质
US8954503B2 (en) Identify experts and influencers in a social network
US11195125B2 (en) Pollution prediction
WO2019062414A1 (zh) 应用程序管控方法、装置、存储介质及电子设备
WO2019000887A1 (zh) 信息推荐方法和装置
CN110830812B (zh) 相似主播分类模型训练方法、主播推荐方法及相关装置
WO2019218427A1 (zh) 基于行为特征对比的关注度检测方法以及装置
US11182447B2 (en) Customized display of emotionally filtered social media content
CN111325382B (zh) 停车场空闲车位预测方法、装置、电子设备及存储介质
WO2023005120A1 (zh) 楼宇能耗预测方法、装置、计算机设备和存储介质
US20120226521A1 (en) Utilize Experts and Influencers in a Social Network
CN112084413B (zh) 一种信息推荐的方法、装置及存储介质
US10012765B2 (en) Geographical condition prediction
WO2019085754A1 (zh) 应用清理方法、装置、存储介质及电子设备
US10762089B2 (en) Open ended question identification for investigations
CN113886721B (zh) 个性化兴趣点推荐方法、装置、计算机设备及存储介质
CN111126422A (zh) 行业模型的建立及行业的确定方法、装置、设备及介质
Alia et al. On the exploitation of GPS-based data for real-time visualisation of pedestrian dynamics in open environments
CN117391866A (zh) 一种数据处理方法、装置、设备及其存储介质
US8417811B1 (en) Predicting hardware usage in a computing system
CN116703466A (zh) 基于改进灰狼算法的系统访问量预测方法及其相关设备
CN112085566B (zh) 基于智能决策的产品推荐方法、装置及计算机设备
CN111127057B (zh) 一种多维用户画像恢复方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18924327

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 26/03/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18924327

Country of ref document: EP

Kind code of ref document: A1