Water accumulation point intelligent identification method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a water accumulation point intelligent identification method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring text information related to rainstorm waterlogging from social media by adopting a crawler technology, and carrying out text clause and keyword inverse screening preprocessing operation to obtain target text information; classifying the target text information, and performing category labeling on the classified text information; constructing a fine-grained geographic position automatic extraction algorithm, and obtaining target fine-grained ponding point position information from the ponding information and the loss information according to the fine-grained geographic position automatic extraction algorithm; and longitude and latitude information corresponding to the target fine-grained ponding point position information is determined, and the target fine-grained ponding point position is coded and visualized according to the longitude and latitude information. By adopting the scheme, the fine-grained ponding point position information is efficiently mined from the social media text information at low cost, and the utilization value of the social media big data is greatly improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of disaster prevention and mitigation, and in particular to a method, device, electronic device and storage medium for intelligently identifying waterlogging points. Background Art

[0002] In recent years, extreme rainstorms have occurred frequently around the world, causing significant casualties and economic losses. Compared with rural areas, floods cause more serious damage to densely built and densely populated cities. Urban waterlogging points are characterized by spatial dispersion and dynamic changes, and it is extremely difficult to collect complete waterlogging location information in a timely manner.

[0003] Among the traditional technologies for obtaining waterlogging points in real time, although manual detection and ground sensors can ensure measurement accuracy, the measurement range is limited; remote sensing, radar satellite and other technologies can collect real-time information, but the data quality is easily affected by cloud cover or revisit cycle; drone low-altitude photography technology can obtain high-resolution data, but large-scale collection of real-time data on urban waterlogging points is still limited by multiple factors such as airspace control, rainy day operations and electricity. The emergence of social media has made it easier to quickly obtain information related to waterlogging. However, the proportion of geotags provided by social media is limited, and the location in the user profile in most cases reflects the registered location, which is usually inaccurate or outdated. Users of social media platforms pay more attention to personal privacy, and most users are unwilling to share their location, resulting in very limited geotag data that can be directly obtained. The relatively rich geographical descriptions in social media texts provide new ideas for the mining of geographical locations, but the mining and application of such information is still in its infancy.

[0004] Therefore, how to obtain the location information of waterlogging points from social media data is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, electronic device and storage medium for intelligently identifying waterlogging points, so as to efficiently and low-cost mine fine-grained waterlogging point location information from social media text information, greatly improve the utilization value of social media big data, and help promote the construction of smart cities.

[0006] In a first aspect, an embodiment of the present invention provides a method for intelligently identifying water accumulation points, comprising:

[0007] Using crawler technology to obtain text information related to rainstorm waterlogging from social media, and preprocessing the text information to obtain target text information; the preprocessing includes text sentence segmentation and keyword reverse screening;

[0008] Classify the target text information and label the classified text information by category; wherein the classified text information includes water accumulation information and loss information;

[0009] Constructing a fine-grained geographic location automatic extraction algorithm, and obtaining target fine-grained waterlogging point location information from waterlogging information and loss information based on the fine-grained geographic location automatic extraction algorithm;

[0010] Determine the longitude and latitude information corresponding to the target fine-grained water accumulation point location information, and encode and visualize the target fine-grained water accumulation point location based on the longitude and latitude information.

[0011] In a second aspect, an embodiment of the present invention further provides a device for intelligently identifying water accumulation points, comprising:

[0012] A text information acquisition and preprocessing module is used to acquire text information related to rainstorm waterlogging from social media using crawler technology, and preprocess the text information to obtain target text information; the preprocessing includes text sentence segmentation and keyword reverse screening;

[0013] The text information classification and labeling module is used to classify the target text information and label the classified text information by category; wherein the classified text information includes water accumulation information and loss information;

[0014] A fine-grained waterlogging point location information extraction module is used to construct a fine-grained geographic location automatic extraction algorithm, and obtain the target fine-grained waterlogging point location information from the waterlogging information and the loss information according to the fine-grained geographic location automatic extraction algorithm;

[0015] The fine-grained water accumulation point location information visualization module is used to determine the longitude and latitude information corresponding to the target fine-grained water accumulation point location information, and encode and visualize the target fine-grained water accumulation point location based on the longitude and latitude information.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0017] one or more processors;

[0018] A storage device for storing one or more programs;

[0019] When the one or more programs are executed by the one or more processors, the one or more processors implement the intelligent identification method for water accumulation points described in any embodiment of the present invention.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for intelligently identifying water accumulation points described in any embodiment of the present invention.

[0021] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for intelligently identifying water accumulation points as described in any embodiment of the present invention.

[0022] The embodiment of the present invention provides a method, device, electronic device and storage medium for intelligent identification of waterlogging points. The crawler technology is used to obtain text information related to rainstorm waterlogging from social media and preprocess it to obtain target text information; the target text information is classified into waterlogging information and loss information and annotated; a fine-grained geographic location automatic extraction algorithm is constructed, and the target fine-grained waterlogging point location information is obtained from the waterlogging information and loss information according to the fine-grained geographic location automatic extraction algorithm; the longitude and latitude information corresponding to the target fine-grained waterlogging point location information is determined, and the target fine-grained waterlogging point location is encoded and visualized according to the longitude and latitude information. The technical solution of the embodiment of the present invention integrates rapid data collection, processing and classification, fine-grained waterlogging point location mining, location encoding and visualization, and mines fine-grained waterlogging point location information from social media text information efficiently and at low cost, greatly improving the utilization value of social media big data and helping to promote the construction of smart cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts. In the drawings:

[0024] Figure 1 This is a flow chart of a method for intelligently identifying water accumulation points provided in the first embodiment of the present invention;

[0025] Figure 2 A flow chart of a method for intelligently identifying water accumulation points provided in Embodiment 2 of the present invention;

[0026] Figure 3 This is a flowchart of a method for acquiring keywords based on crawler technology provided in Embodiment 2 of the present invention;

[0027] Figure 4 A schematic diagram of a text binary classification model architecture provided in Embodiment 2 of the present invention;

[0028] Figure 5A schematic diagram of a multi-label text classification model architecture provided in Embodiment 2 of the present invention;

[0029] Figure 6 A schematic diagram of a fine-grained water accumulation point visualization provided in the second embodiment of the present invention;

[0030] Figure 7 A flow chart of a method for intelligently identifying water accumulation points provided in Embodiment 3 of the present invention;

[0031] Figure 8 A schematic diagram of a named entity recognition model architecture provided in Embodiment 3 of the present invention;

[0032] Fig. 9 A schematic diagram of the architecture of a method for extracting fine-grained water accumulation points provided in the third embodiment of the present invention;

[0033] Fig.10 A schematic diagram of a fine-grained water accumulation point output logic provided in Embodiment 3 of the present invention;

[0034] Fig.11 It is a structural schematic diagram of a water accumulation point intelligent identification device provided by the fourth embodiment of the present invention;

[0035] Fig.12 It is a structural schematic diagram of an electronic device provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0036] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0037] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0038] Among them, the acquisition, storage, use and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. It should be noted that in the embodiments of this application, some existing solutions in the industry such as certain software, components or models may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0039] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0040] Embodiment 1

[0041] Figure 1 This is a flow chart of a method for intelligently identifying waterlogging points provided by the first embodiment of the present invention. This embodiment is applicable to the case of intelligently identifying waterlogging points from social media. The method of this embodiment can be executed by a device for intelligently identifying waterlogging points, which can be implemented in hardware and / or software. The device can be configured in a server for intelligently identifying waterlogging points. The method specifically includes the following steps:

[0042] S110, using crawler technology to obtain text information related to rainstorm waterlogging from social media, and preprocessing the text information to obtain target text information.

[0043] Crawler technology refers to a technology for automatically acquiring Internet information, also known as web crawlers, web spiders or web robots. Crawler technology automatically accesses network resources through programs, captures useful data, and stores it in local or remote servers. Crawler technology can automatically acquire a large amount of data, greatly improving the efficiency and accuracy of data acquisition, and also providing more possibilities for data analysis and mining.

[0044] Social media can refer to virtual communities and online platforms used to create, share, exchange opinions, and exchange views and experiences. Social media can allow users to enjoy more choices and editing capabilities, and to assemble into a certain kind of reading and listening community. Social media can be presented in a variety of different forms, including text, images, music, and video. Preprocessing can refer to data cleaning and useless information filtering of text information; the useless information filtering can refer to the elimination of information that does not contain rainstorm waterlogging water points.

[0045] The embodiment of the present invention adopts crawler technology to obtain text information related to rainstorm waterlogging from texts in social media, and performs data cleaning and useless information filtering on the text information to obtain target text information containing rainstorm waterlogging waterlogging points.

[0046] S120: classify the target text information, and label the classified text information by category.

[0047] The geographical location mentioned in the target text information does not always refer to the location of the water accumulation point, but may also include the geographical location information of the secondary disasters caused by the rainstorm and the geographical location information of the opinions on the occurrence of the rainstorm disaster.

[0048] In the embodiment of the present invention, the target text information is classified and the classified text information is annotated. The classified text information includes water accumulation information, loss information and other information; the water accumulation information may refer to information describing the location of the water accumulation point, the loss information may refer to information describing the loss of secondary disasters caused by heavy rain and waterlogging, and other information is used to describe the views on the disasters caused by heavy rain and waterlogging. The water accumulation information, loss information and other information may all contain location information related to heavy rain and waterlogging.

[0049] S130, constructing a fine-grained geographic location automatic extraction algorithm, and acquiring target fine-grained waterlogging point location information from waterlogging information and loss information based on the fine-grained geographic location automatic extraction algorithm.

[0050] The fine-grained automatic geographic location extraction algorithm may refer to a technology for automatically identifying and extracting geographic location information from text data. The fine-grained automatic geographic location extraction algorithm can identify specific place names, such as streets, communities, roads, and buildings, rather than just rough location information at the country or continent, city, or district level. In the embodiment of the present invention, the fine-grained automatic geographic location extraction algorithm is used to obtain more fine-grained geographic location information of rainstorm waterlogging waterlogging points from waterlogging information and loss information, so that the acquired geographic location information of rainstorm waterlogging waterlogging points is more accurate and detailed.

[0051] S140, determining the longitude and latitude information corresponding to the target fine-grained water accumulation point location information, and encoding and visualizing the target fine-grained water accumulation point location according to the longitude and latitude information.

[0052] Among them, encoding the target fine-grained water accumulation point position may refer to the process of coordinate conversion of the longitude and latitude information corresponding to the target fine-grained water accumulation point position information. In the embodiment of the present invention, after determining the target fine-grained water accumulation point position information, the corresponding longitude and latitude information is determined, and the longitude and latitude information is converted into the world geodetic system coordinates through a coordinate conversion tool to complete the encoding of the target fine-grained water accumulation point position information. After determining the world geodetic system coordinates of the target fine-grained water accumulation point position information, the target fine-grained water accumulation point position is marked on the map and visualized.

[0053] The embodiment of the present invention provides an intelligent identification method for waterlogging points, which uses crawler technology to obtain text information related to rainstorm waterlogging from social media, and pre-processes the text information to obtain target text information; classifies the target text information, and labels the classified text information; wherein the classified text information includes waterlogging information and loss information; constructs a fine-grained geographic location automatic extraction algorithm, and obtains target fine-grained waterlogging point location information from the waterlogging information and loss information according to the fine-grained geographic location automatic extraction algorithm; determines the longitude and latitude information corresponding to the target fine-grained waterlogging point location information, and encodes and visualizes the target fine-grained waterlogging point location according to the longitude and latitude information. The technical solution of the embodiment of the present invention integrates rapid data collection, processing and classification, fine-grained waterlogging point location mining, location encoding and visualization, and mines fine-grained waterlogging point location information from social media text information efficiently and at low cost, greatly improving the utilization value of social media big data and helping to promote the construction of smart cities.

[0054] Embodiment 2

[0055] Figure 2 The flowchart of a method for intelligently identifying water accumulation points provided in the second embodiment of the present invention. The embodiment of the present invention further optimizes the above embodiment on the basis of the above embodiment, and the embodiment of the present invention can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the intelligent water accumulation point identification method provided in the embodiment of the present invention may include the following steps:

[0056] S210: Using crawler technology to obtain text information related to rainstorm waterlogging from social media, and preprocessing the text information to obtain target text information.

[0057] Among them, crawler technology is used to collect text information under the theme of heavy rain from social media and perform data preprocessing. Crawler technology is used to collect text information under the theme of heavy rain and urban waterlogging on social media platforms. In social media, personal accounts and official accounts usually post information related to urban waterlogging on the platform. Using web crawler technology based on simulated login, text information is quickly collected according to the specified social media type, time range and keywords; at the same time, user address, posting time and related information will be automatically stored in the database.

[0058] As an optional but non-limiting implementation, the crawler technology is used to obtain text information related to rainstorm waterlogging from social media, and the text information is preprocessed to obtain target text information, including but not limited to steps A1-A2:

[0059] Step A1: Using web crawler technology based on simulated login, obtain text information related to rainstorm waterlogging waterlogging points according to preset social media types, time ranges and keywords.

[0060] Among them, the Octopus collector is used to automatically collect text information related to flooding points caused by heavy rain. The collection ideas can be found in Figure 3 . By simulating the user's browsing path, the internal collection logic is extracted to complete data collection. For page-turning loops and single-page microblog loops, the corresponding path language needs to be set to ensure the accuracy of the crawling results. In the step of editing and optimizing the crawling fields, delete the fields that do not need to be crawled; in the main crawling fields, the text information needs to set the path language separately, because the text information contains long texts and needs to be accurately located. The number of likes, comments, and reposts also needs to be formatted, and regular expressions are used to obtain the corresponding numbers. By modifying the keywords and time separately, you can obtain batches of URLs and realize the rapid collection of text information.

[0061] Taking the rainstorm in city A as an example, the time range is set from January 1, 2018 to December 31, 2022, the keywords are 'waterlogging in city A', 'flooding in city A', 'inundation in city A', 'waterlogging in city A', 'flood in city A', and 'original' is selected as the social media type. The target text information is obtained according to the above crawler mechanism, and a total of 7243 original text information is obtained.

[0062] Step A2: Clean the text information and filter out useless information, and remove information irrelevant to the rainstorm waterlogging points to obtain the target text information.

[0063] Among them, preprocessing includes data cleaning and useless information filtering, data cleaning includes sentence-level cleaning and symbol-level cleaning, and sentence-level cleaning includes keyword reverse screening, text segmentation, waterlogging-related keyword screening, and text similarity deduplication processing.

[0064] Among them, keyword inverse screening may refer to removing geographical locations that have the same name as the geographical location of the waterlogging point but do not belong to the corresponding geographical location of the waterlogging point. For example, to obtain the geographical location of point B1 in area A, the text information includes the location information of point B2, but point B2 belongs to a street in area C, so point B2 is removed; among them, the names of B1 and B2 are the same.

[0065] Text clause splitting may refer to splitting the text information according to the punctuation marks in the text information. Through text clause splitting, first, a large number of sentences that do not contain information related to rainstorm waterlogging can be excluded, improving data quality. Second, it helps to determine the category to which a sentence belongs in the text classification task, improving the classification accuracy. Third, it can exclude the interference of place names in non-flooded areas.

[0066] Among them, in the embodiment of the present invention, the MinHash-LSH algorithm is selected for text similarity deduplication processing, and text information with a similarity higher than 70% can be removed. Symbol-level cleaning may refer to removing special symbols such as @person names, uniform resource locators (URLs), '收起d', '全文', '网页链接', etc. through regular expressions (the're' module).

[0067] The purpose of useless information filtering is to remove useless information, and useless information filtering can be transformed into a text binary classification task. In the embodiment of the present invention, the TextCNN model is used for text binary classification to screen out useful information; "useful information" refers to text information that truly reports rainstorm waterlogging accumulation points, and vice versa is "useless information". The TextCNN model consists of an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The network architecture of TextCNN is shown in Figure 4 . Before entering the input layer, first use Word2Vec to convert the collected text information into a language word vector that can be understood by a computer; among them, Word2Vec is a model for learning word vectors, which can convert words into real number vectors, and these vectors can capture the semantic and syntactic relationships between words. Due to the small sample data, the skip-gram model with negative sampling (word2vec / skip-gram with negative sampling) is selected. The convolutional layer uses three sizes of convolutional kernels (3, 4, and 5) to perform convolution on the input vector to achieve feature mapping. In the pooling layer, the maximum pooling function is used to capture the most prominent features. The fully connected layer is responsible for connecting the word vectors. Finally, the Softmax activation function is used to generate the corresponding class output. Among them, the skip-gram model is a language model widely used in the field of natural language processing, especially widely used in the Word2Vec algorithm, and the model is trained by predicting the occurrence of a word in the context to capture the semantic information of the word.

[0068] In the embodiment of the present invention, the preprocessing of 7243 original text information is taken as an example. The 7243 original microblogs are reversely screened, and a total of 4222 original microblogs are obtained; the text is segmented according to '. ', and a total of 17939 sentences are obtained after the segmentation; 4486 sentences are obtained after the waterlogging-related keywords are screened; a total of 3453 target text information is obtained after deduplication; and a total of 3452 target text information is obtained after symbol level cleaning. Before filtering useless information, it is necessary to annotate the training data set, adjust the hyperparameters and train the TextCNN model. 600 useful information and useless information are annotated at a ratio of 1:1. Due to the small number of training sets, a five-fold cross validation is used to evaluate the model training effect. The average accuracy of the test set is 89.67%, the average precision is 86.69%, the average recall is 93.88%, and the average F1 score is 90.03%. The model with a recall rate of 100% is selected to predict the type of text information, and a total of 1782 useful information is obtained, and 1670 useless information is filtered out.

[0069] In the embodiment of the present invention, crawler technology is used to obtain a large amount of text information related to waterlogging points caused by heavy rain from social media, thereby improving the efficiency of obtaining text information and reducing the cost of manual acquisition; data cleaning is performed on the text information and the TextCNN model is used to filter useless information, which can quickly filter out useless information and help improve the efficiency of system recognition.

[0070] S220: classify the target text information, and label the classified text information by category.

[0071] Among them, after data collection and preprocessing, text information reporting on waterlogging points can be obtained, but the geographical locations mentioned in this type of text information do not all refer to waterlogging points. This mainly depends on the specific subject of the text information, such as waterlogging caused by heavy rain, secondary disaster loss information caused by heavy rain, and opinions on disasters. In order to accurately locate waterlogging points, multi-label text classification is needed to divide useful information into waterlogging information, loss information, and other information. Manual annotation is performed according to the category definition, and the results are used to train the model.

[0072] As an optional but non-limiting implementation, the target text information is classified and the classified text information is labeled by category, including but not limited to steps B1-B2:

[0073] Step B1: Analyze the target text information to determine the subject content described by the target text information.

[0074] Step B2: Classify the target text information into waterlogging information, loss information and other information according to the subject content, and mark the classified text information.

[0075] The loss information is used to describe the secondary disaster loss information caused by heavy rain and waterlogging, and the other information is used to describe the views on the disasters caused by heavy rain and waterlogging.

[0076] The target text information is classified into water accumulation information, loss information and other information, and the classified text information is annotated. The annotated text information is used to train a text classification model, and the model uses an ALBERT+BiGRU+Attention+FC model.

[0077] Among them, see Figure 5 , ALBERT is responsible for converting text into vectors in the model, and BiGRU (BidirectionalGRU) + Attention is a feature extraction layer, which is used to extract the global semantic features of the vector matrix output by the text vector representation layer. The two layers of forward and backward GRU are superimposed as BiGRU, and the output is determined by the collaboration of the two layers of GRU units. Therefore, the bidirectional gated recurrent unit (BiGRU) can extract deep features containing contextual information. The attention mechanism (Attention) can focus on details according to the target, perceive important semantic features in the text context content, and distinguish the importance by assigning different weights to each hidden layer node, so that the model can focus on the key words and sentence information of the text. The fully connected layer (Fully Connected, FC) can map the results to the corresponding label category. The output of the FC layer is compressed by the sigmoid function to obtain the probability of the target text information belonging to each type.

[0078] Optionally, for the 600 manually annotated data, they are divided into training set, validation set and test set in a ratio of 8:1:1. The annotated samples are input into the model for training. The word vector dimension of the ALBERT layer is 312, the hidden layer dimension of the BiGRU is 128, and the dimension of the attention mechanism Attention layer is 32. The operating system is Windows 10, the Python version is 3.6, and the Keras deep learning framework is used to build the experimental model. The Adam optimizer is used to minimize the final objective function during the training process. When Epoch = 30, the test set Acc is 70.00% and the HL is 0.14. That is, the target text information in the test set that completely predicts the correct category accounts for 70%, and the difference between the predicted label and the true label is 0.14. The model is used to perform multi-label text classification on 1782 useful information, and the target text information is given a suitable label category. Among them, 'water accumulation information|loss information' is the largest, with 527 pieces, and 'loss information|other information' is the least, with 14 pieces. There are 32 pieces of information belonging to the 'blank' class. This shows that the probability that the target text information belongs to the three categories is less than 0.5. Based on the principle of multi-label text classification, the two types of target text information, 'water accumulation information|other information' and 'loss information|other information', are merged into the 'water accumulation information' and 'loss information' categories respectively. After processing, there are 954 target text information with the label of 'water accumulation information' and 802 target text information with the label of 'loss information'. A total of 1,229 water accumulation information and loss information were obtained, but only 5.04% of the target text information contained its own fine-grained geographic labels, and the fine-grained geographic locations of the remaining 1,167 water accumulation information and loss information are still to be mined.

[0079] S230: construct a fine-grained geographic location automatic extraction algorithm, and obtain target fine-grained waterlogging point location information from waterlogging information and loss information based on the fine-grained geographic location automatic extraction algorithm.

[0080] S240: Determine the longitude and latitude information corresponding to the target fine-grained water accumulation point location information, and encode and visualize the target fine-grained water accumulation point location based on the longitude and latitude information.

[0081] Among them, after determining the target fine-grained water accumulation point location information, the standardized name and longitude and latitude information corresponding to each target fine-grained water accumulation point location information are automatically retrieved, the longitude and latitude information obtained is encrypted once based on the Mars coordinate system, and the coordinate conversion toolkit is used to convert all coordinate systems into the coordinates of the world geodetic system to complete the geocoding. The encoded water accumulation point poles are visualized, such as Figure 6 shown.

[0082] The embodiment of the present invention provides a method for intelligently identifying waterlogging points, which uses crawler technology to obtain a large amount of text information related to waterlogging points caused by heavy rain from social media, improves the efficiency of obtaining text information, and reduces the cost of manual acquisition; the text information is cleaned and the TextCNN model is used to filter useless information, which can quickly filter useless information and help improve the efficiency of system recognition. The model is used to classify and annotate the target text information, which greatly reduces the labor and time costs of model training. The target fine-grained waterlogging point location is encoded and visualized, which facilitates the timely processing of the waterlogging point, and helps promote the construction of smart cities.

[0083] Embodiment 3

[0084] Figure 7 This is a flow chart of a method for intelligently identifying water accumulation points provided in the third embodiment of the present invention. The embodiment of the present invention further optimizes the above embodiment on the basis of the above embodiment, and the embodiment of the present invention can be combined with various optional solutions in one or more of the above embodiments. Figure 7 As shown, the intelligent water accumulation point identification method provided in the embodiment of the present invention may include the following steps:

[0085] S710: Acquire text information related to rainstorm waterlogging from social media using crawler technology, and pre-process the text information to obtain target text information.

[0086] S720: Classify the target text information, and label the classified text information.

[0087] S730: construct a language rule-based geographic location extraction algorithm, and use the language rule-based geographic location extraction algorithm to process the waterlogging information, loss information, and geographic location identification results to obtain first fine-grained waterlogging point location information.

[0088] Among them, the geographic location extraction algorithm based on language rules can refer to establishing a corresponding semantic location concept hierarchical model by analyzing the geographic description features in natural language, and defining location extraction rules accordingly, including place name extraction rules and spatial relationship extraction rules. The extraction of location information is achieved by identifying place names and spatial relationships. In the embodiment of the present invention, a geographic location extraction algorithm based on language rules is used to process waterlogging information, loss information and geographic location identification results to obtain the first fine-grained waterlogging point location information. Among them, the geographic location identification result is obtained by using a general named entity recognition model to perform named entity recognition of the geographic location of the waterlogging point on the target text information.

[0089] In the prior art, a Universal Chinese Named Entity Recognition (UCNER) model is usually trained using a Chinese general corpus to extract waterlogging locations from waterlogging information and loss information. However, the place names recognized by the UCNER model are incomplete, imprecise, noisy, and cannot be directly visualized as waterlogging points. In order to solve these problems, an embodiment of the present invention proposes a waterlogging location refinement (GLR) algorithm to improve the recognition results of UCNER to obtain fine-grained waterlogging points.

[0090] Among them, see Figure 8 The network architecture of the UCNER model is BERT+BiLSTM+CRF. The model input is a sentence and the output is the label corresponding to each word in the sentence. BERT represents a pre-trained language representation model. In the BERT layer, the input text is converted into a semantically rich vector. Each vector contains three kinds of information, namely, word embedding (E T ), the sentence embedding (E S ) and position embedding (E P ). Subsequently, the embedding layer is input into the Transformer encoder model. During the training process, the model's attention mechanism adjusts the attention to individual words in the context by changing the weights; therefore, the word vectors are generated through deep bidirectional encoding. BiLSTM is a bidirectional long short-term memory network. The BiLSTM layer extracts context and semantic features from these vectors to achieve semantic encoding. This layer consists of a forward LSTM and a backward LSTM, which can obtain context information by capturing the forward and backward information in the sentence sequence. Conditional Random Field (CRF) is a commonly used sequence labeling model. The CRF layer assigns the label with the highest probability to each character in the sentence and determines the best category after obtaining the hidden vector output by the BiLSTM layer.

[0091] The embodiment of the present invention selects the People's Daily Corpus (PFR) to train the NER model. PFR is a unique named entity recognition dataset, which is annotated using the BIO system. In PFR, there are three different types of named entities, namely, people (PER), places (LOC), and organizations (ORG). However, for location tags, PFR only provides the "LOC" tag, and does not provide more fine-grained location tags, such as "street", "region" or "building". In addition, most of the locations in PFR are broad areas, such as continents, countries, cities, and regions. The training effect of PFR on the named entity recognition model is shown in Table 1. The PFR-NER model predicts the largest number of LOC tags, and the recall rate can reach 96.05%, indicating that the model can recognize the vast majority of place names in the text, and the recognition effect meets the requirements of the present invention.

[0092] Table 1 PFR training effect on named entity recognition model

[0093]

[0094] The evaluation criteria for geographic named entity recognition methods are based on precision P, recall R, and F1 value as evaluation indicators for recognition model methods. They are also basic indicators for evaluating models in fields such as information search, knowledge classification, and entity recognition. The precision Р represents the accuracy of the prediction of the results of geographic named entity recognition. The recall R represents the probability that the original data contains geographic entity names and is accurately recognized as geographic entity names.

[0095] Optionally, 1,167 pieces of waterlogging and loss information were input into the trained PFR-NER model to extract the place names contained in each target text message. Among them, 999 target text messages were identified with place names, accounting for 85.60% of the target text messages containing place names. However, among the identified place names, most of them did not reach the fine-grained level.

[0096] To solve the problems that UCNER cannot recognize special positioning words and complete complex fine-grained water accumulation points, and outputs descriptions of the same place with different degrees of accuracy in a sentence as multiple addresses at the same time, see Fig. 9 ,The present paper proposes a geographic location refinement (GLR) algorithm, GLR includes two sub-algorithms, namely a rule-based geographic location extraction algorithm (RGLE) and a category label based geographic location filtering algorithm (CGLF).

[0097] As an optional but non-limiting implementation, the language rule-based geographic location extraction algorithm is used to process the waterlogging information, loss information, and geographic location identification results to obtain first fine-grained waterlogging point location information, including but not limited to steps C1-C6:

[0098] Step C1: Segment the waterlogging information and loss information, and divide different geographical locations into different segments.

[0099] Step C2: De-noising the geographic location recognition result to obtain a de-noised geographic location recognition result.

[0100] Step C3: Detect the segment to determine whether the segment contains a target recognition result; the target recognition result is a denoised geographic location recognition result.

[0101] Step C4: If the segment contains a target recognition result, the target recognition result is used as the third fine-grained water accumulation point location information.

[0102] Step C5: If the segment contains at least two target recognition results, determine whether the at least two target recognition results belong to the same geographical location based on the distance between the two adjacent target recognition results, and combine the at least two target recognition results belonging to the same geographical location to obtain fourth fine-grained water accumulation point location information.

[0103] Step C6: Determine whether the waterlogging information and the loss information contain special locating words, and determine whether the special locating words are connected to the third fine-grained waterlogging point location information or the fourth fine-grained waterlogging point location information; if they are connected, combine the special locating words with the third fine-grained waterlogging point location information or the fourth fine-grained waterlogging point location information to obtain the first fine-grained waterlogging point location information.

[0104] The input of the rule-based geographic location extraction algorithm is the waterlogging information and loss information and their corresponding UCNER geographic location recognition results, and the output is the first fine-grained waterlogging point location information. The specific steps include the following three steps:

[0105] In the first step, the input data is preprocessed, including the segmentation of waterlogging information and loss information and the denoising of geographic location recognition results. Segmentation of waterlogging information and loss information can simplify the difficulty of distinguishing complex geographic locations. In Chinese expressions, different geographic locations are usually separated by punctuation marks such as ',';'','. Therefore, each target text information is divided into different segments according to the above punctuation marks. In this way, for sentences that mention multiple places at the same time, different geographic locations can be correctly divided into different segments. Next, in order to eliminate the interference of repeated place names in the geographic location recognition results, the geographic location recognition results corresponding to each waterlogging information and loss information are cleaned of noise vocabulary, that is, the geographic location recognition results are denoised. Through the operations in the initialization stage, each segment of waterlogging information and loss information corresponds to the denoised geographic location recognition result, that is, the target recognition result.

[0106] The second step is to include the target recognition result (ner s ) to extract the geographic location from the fragments. Check each fragment in turn to see if it contains a target recognition result. If so, process it in two different cases. If there is only one target recognition result corresponding to the fragment, output the corresponding target recognition result as the third fine-grained water point location information. If the target recognition result contains m ner i , that is, ner s =[ner1,ner2,…,ner m ], the program will further determine whether multiple target recognition results belong to the same geographical location. The judgment standard is adjacent ner i The character distance between adjacent ner i The character distance between them determines whether multiple target recognition results belong to the same geographical location. And the adjacent target recognition results belonging to the same geographical location are combined to obtain the fourth fine-grained water accumulation point location information.

[0107] In the third step, the algorithm will check whether special positioning words are missing in the waterlogging information and loss information. The special positioning words not recognized by UCNER are stored in a list, which include but are not limited to intersections, sections, interchanges, intersections, junctions, directions, ramps, bridge tunnels, bridge bottoms and entrances and exits. Chinese expression habits usually put special positioning words at the end of the geographic location. Using regular expressions, check whether the third fine-grained waterlogging point location information or the fourth fine-grained waterlogging point location information is connected to the special positioning words. If connected, they are combined to obtain the first fine-grained waterlogging point location information.

[0108] As an optional but non-limiting implementation, if the segment contains at least two target recognition results, whether the at least two target recognition results belong to the same geographical location is determined based on the distance between the two adjacent target recognition results, and at least two target recognition results belonging to the same geographical location are combined to obtain fourth fine-grained water accumulation point location information, including but not limited to steps D1-D2:

[0109] Step D1: Determine whether the first distance between the first target recognition result and the second target recognition result is less than or equal to a preset distance threshold, and combine the first target recognition result and the second target recognition result when the first distance is less than or equal to the preset distance threshold, and output the combined fine-grained geographic location.

[0110] Step D2: Determine whether the second distance between the combined fine-grained geographic location and the third target recognition result is less than or equal to a preset distance threshold. If the second distance is greater than the preset distance threshold, the combined fine-grained geographic location and the third target recognition result are used as the fourth fine-grained water accumulation point location information.

[0111] Among them, the character distance between the target recognition results is used to determine whether multiple target recognition results belong to the same geographical location. When the first distance between the first target recognition result and the second target recognition result is less than or equal to the preset distance threshold, the two adjacent target recognition results in the same segment and the characters between them will be merged into a fine-grained geographical location and enter the next round of judgment cycle as a new target recognition result; determine whether the second distance between the new target recognition result and the third target recognition result is less than or equal to the preset distance threshold. If the character distance between the new target recognition result and the third target recognition result is greater than the preset distance threshold, the content of the target recognition result remains unchanged. When ner m Enter the loop and judge the end, and the process ends. In order to distinguish the target recognition result before processing from the target recognition result before processing, the target recognition result after processing can be assigned a value.

[0112] The embodiment of the present invention can combine place names belonging to the same geographical location into a complex fine-grained geographical location through a geographical location extraction algorithm based on language rules, thereby ensuring the accuracy of the complex fine-grained geographical location output result.

[0113] S740. Construct a geographic location filtering algorithm based on category labels, and use the geographic location filtering algorithm based on category labels to prioritize the first fine-grained waterlogging point location information to obtain the second fine-grained waterlogging point location information, and use the second fine-grained waterlogging point location information as the target fine-grained waterlogging point location information.

[0114] The geolocation filtering algorithm based on category labels is a processing method for optimizing geolocation data. It filters and optimizes data by combining geolocation information and category labels. The geolocation extraction algorithm based on language rules can complete the locations extracted by UCNER into waterlogging points, and the geolocation filtering algorithm based on category labels is used to determine which waterlogging points should be output in the end.

[0115] Optionally, for target text information without category labels, it is necessary to extract fine-grained geographic locations in the target text information; for target text information with category labels, the corresponding category labels can be directly matched.

[0116] As an optional but non-limiting implementation, the use of a category label-based geographic location filtering algorithm to prioritize the first fine-grained waterlogging point location information to obtain the second fine-grained waterlogging point location information includes but is not limited to steps E1-E3:

[0117] Step E1: Construct a priority list representing the fine-grained level of water accumulation point locations.

[0118] Step E2: Use geographic location category labels to label the first fine-grained waterlogging point location information, and assign the labeled first fine-grained waterlogging point location information to a corresponding priority list.

[0119] Step E3: Retrieve the first fine-grained waterlogging point location information in the priority list according to priority, and select the first fine-grained waterlogging point location information that exists and is at the highest priority position from the first priority, the second priority, and the third priority as the second fine-grained waterlogging point location information.

[0120] Among them, the geographic location category labels include roads, intersections, points of interest, communities, streets, districts and cities; roads, intersections and points of interest are the first priority, communities are the second priority, streets are the third priority, districts are the third priority, and cities are the fifth priority.

[0121] Among them, see Fig.10 , the embodiment of the present invention uses 7 geographic location category labels to indicate the accuracy level of waterlogging points, and the geographic place name database and Baidu map location search API are used to provide category labels. Among them, the geographic place name database can only provide location category labels for communities, streets, districts and cities, and the Baidu map location search API can provide category labels at the road, intersection and point of interest (POI) levels. In the present invention, district-level or city-level locations have a lower priority because they are too rough and cannot make effective contributions to risk warning or emergency management. Therefore, these low-priority waterlogging locations will be ignored. Although communities and subdistricts represent regions, they can still provide valuable information to citizens in a small range. Category labels such as roads, intersections and POIs can provide more refined geographic locations for waterlogging points, so they have the highest priority.

[0122] The input of the category label-based geolocation filtering algorithm is the first fine-grained waterlogging location information of each target text information, and the output is the second fine-grained waterlogging location information and its corresponding geolocation category label after the first fine-grained waterlogging location information is standardized. It is mainly divided into three tasks, namely data preparation, priority matching and sequential output, which can be specifically expressed as:

[0123] In the data preparation task, you need to create a new list to save the results and the specific category labels of the geographic locations. First, create five lists, namely the first priority list, the second priority list, the third priority list, the fourth priority list, and the fifth priority list, to store the output results of different priorities. Secondly, search the geographic location where the waterlogging point appears in the geographic place name database and PlaceAPI in turn, and obtain its corresponding geographic information (second fine-grained waterlogging point location information, geographic location category label and longitude and latitude), save the results matched by the geographic place name database in the priority list, and save the results matched by PlaceAPI in a folder, where each geographic location corresponds to a Json format file named after the geographic location.

[0124] In the priority matching task, the program will first search in the priority list, and store the second fine-grained water accumulation point location information and its geographic location category label corresponding to the priority level of the category label of level 2, 3, 4, and 5 in the corresponding priority list. For the geographic location that is not matched in the priority list, the program will automatically search in the Json file under the folder. In the case of information retrieved, if the category label corresponding to the geographic location is 'road' or 'intersection', the second fine-grained water accumulation point location information and the geographic location category label corresponding to the first fine-grained water accumulation point location information are saved; if it is not the above two, the category corresponding to the second fine-grained water accumulation point location information is saved as 'POI'. This is because in the folder, a certain geographic location will not be specified as belonging to 'POI', but a more specific type will be specified, such as toll booths, city parks, etc. Finally, the information saved by the above three geographic location category labels is stored in the first priority list. So far, the geographic locations with corresponding category labels have been put into the five priority lists.

[0125] In the sequential output task, each target text information is used as a judgment unit, and the content in the priority list is searched in descending order of priority to see if it is empty. If the current priority list is not empty, all the information under the current priority list is output; if it is empty, continue to judge the content of the next priority list. If the third priority list is judged and it is empty, the output result corresponding to the target text information is empty, indicating that there is no fine-grained geographic location in the target text information.

[0126] Optionally, through the GLR algorithm, among the 999 target text information of place names, a total of 425 target text information were identified with fine-grained geographic locations, accounting for 42.54% of all target text information containing place names. The 100 randomly selected target text information contained a total of 156 fine-grained geographic locations. The PFR-NER model identified a total of 108 correct fine-grained geographic locations, with an accuracy rate of 69.23%; after adding the GLR algorithm, 30 more correct fine-grained geographic locations were identified, increasing the accuracy rate to 88.46%, an increase of 27.78%.

[0127] S750: Determine the longitude and latitude information corresponding to the target fine-grained water accumulation point location information, and encode and visualize the target fine-grained water accumulation point location based on the longitude and latitude information.

[0128] The embodiment of the present invention provides an intelligent identification method for waterlogging points, which constructs a geographic location extraction algorithm based on language rules, and uses the geographic location extraction algorithm based on language rules to process waterlogging information, loss information and geographic location identification results to obtain first fine-grained waterlogging point location information; wherein the geographic location identification result is obtained by using a general named entity recognition model to perform named entity recognition of the geographic location of the waterlogging point on the target text information; constructs a geographic location filtering algorithm based on category labels, and uses the geographic location filtering algorithm based on category labels to prioritize the first fine-grained waterlogging point location information to obtain second fine-grained waterlogging point location information, and uses the second fine-grained waterlogging point location information as the target fine-grained waterlogging point location information. By adopting the technical solution of the embodiment of the present invention, the identified geographic location of the waterlogging point can be accurately determined to the road, intersection or POI, and fine-grained waterlogging points can be mined from social media texts efficiently and at low cost, greatly improving the value of social media big data utilization; the full process technology from data collection to fine-grained waterlogging point visualization is low-cost and fast, which helps promote the construction of smart cities.

[0129] Embodiment 4

[0130] Fig.11 This is a schematic diagram of the structure of a water point intelligent identification device provided by the fourth embodiment of the present invention. The technical solution of this embodiment can be applied to the case of water point intelligent identification. The device can be implemented by software and / or hardware and is generally integrated on any electronic device with network communication function, including but not limited to: servers, computers, personal digital assistants and other devices. Fig.11As shown, the intelligent water accumulation point identification device provided in this embodiment may include: a text information acquisition and preprocessing module 1110, a text information classification and labeling module 1120, a fine-grained water accumulation point location information extraction module 1130 and a fine-grained water accumulation point location information visualization module 1140; wherein,

[0131] The text information acquisition and preprocessing module 1110 is used to acquire text information related to rainstorm waterlogging from social media using crawler technology, and preprocess the text information to obtain target text information; the preprocessing includes text sentence segmentation and keyword reverse screening;

[0132] The text information classification and labeling module 1120 is used to classify the target text information and label the classified text information by category; wherein the classified text information includes water accumulation information and loss information;

[0133] The fine-grained waterlogging point location information extraction module 1130 is used to construct a fine-grained geographic location automatic extraction algorithm, and obtain the target fine-grained waterlogging point location information from the waterlogging information and the loss information according to the fine-grained geographic location automatic extraction algorithm;

[0134] The fine-grained water accumulation point location information visualization module 1140 is used to determine the longitude and latitude information corresponding to the target fine-grained water accumulation point location information, and encode and visualize the target fine-grained water accumulation point location according to the longitude and latitude information.

[0135] Based on the above embodiment, optionally, the text information acquisition and preprocessing module is specifically used to:

[0136] Using web crawler technology based on simulated login, text information related to flooding points caused by heavy rain is obtained according to preset social media types, time ranges, and keywords;

[0137] The text information is cleaned and useless information is filtered to remove information irrelevant to the rainstorm waterlogging point to obtain the target text information;

[0138] Among them, data cleaning includes sentence-level cleaning and symbol-level cleaning. Sentence-level cleaning includes keyword reverse screening, text segmentation, waterlogging-related keyword screening, and text similarity deduplication processing.

[0139] On the basis of the above embodiment, optionally, the text information classification and annotation module is specifically used for:

[0140] Analyze the target text information to determine the subject content described by the target text information;

[0141] Classifying the target text information into waterlogging information, loss information, and other information according to the subject content, and marking the classified text information by category;

[0142] The loss information is used to describe the secondary disaster loss information caused by heavy rain and waterlogging, and the other information is used to describe the views on the disasters caused by heavy rain and waterlogging.

[0143] Based on the above embodiment, optionally, the fine-grained water accumulation point location information extraction module is specifically used to:

[0144] A geographic location extraction algorithm construction unit is used to construct a geographic location extraction algorithm based on language rules, and use the geographic location extraction algorithm based on language rules to process the waterlogging information, loss information and geographic location recognition results to obtain first fine-grained waterlogging point location information; wherein the geographic location recognition results are obtained by using a general named entity recognition model to perform named entity recognition of the geographic location of the waterlogging point on the target text information;

[0145] A geographic location filtering algorithm construction unit is used to construct a geographic location filtering algorithm based on category labels, and use the geographic location filtering algorithm based on category labels to prioritize the first fine-grained waterlogging point location information to obtain the second fine-grained waterlogging point location information, and use the second fine-grained waterlogging point location information as the target fine-grained waterlogging point location information.

[0146] Based on the above embodiment, optionally, the geographic location extraction algorithm construction unit is specifically used to:

[0147] Segment the waterlogging and loss information and divide different geographical locations into different segments;

[0148] De-noising the geographic location recognition result to obtain a denoised geographic location recognition result;

[0149] Detecting the segment to determine whether the segment contains a target recognition result; the target recognition result is a denoised geographic location recognition result;

[0150] If the segment contains a target recognition result, the target recognition result is used as the third fine-grained water accumulation point location information;

[0151] If the segment contains at least two target recognition results, determine whether the at least two target recognition results belong to the same geographical location according to the distance between the two adjacent target recognition results, and combine the at least two target recognition results belonging to the same geographical location to obtain fourth fine-grained water accumulation point location information;

[0152] Determine whether the waterlogging information and the loss information contain special locating words, and determine whether the special locating words are connected to the third fine-grained waterlogging point location information or the fourth fine-grained waterlogging point location information; if they are connected, combine the special locating words with the third fine-grained waterlogging point location information or the fourth fine-grained waterlogging point location information to obtain the first fine-grained waterlogging point location information.

[0153] Based on the above embodiment, optionally, the geographic location extraction algorithm construction unit is further specifically used for:

[0154] Determine whether a first distance between the first target recognition result and the second target recognition result is less than or equal to a preset distance threshold, and combine the first target recognition result and the second target recognition result when the first distance is less than or equal to the preset distance threshold, and output a combined fine-grained geographic location;

[0155] Determine whether the second distance between the combined fine-grained geographic location and the third target recognition result is less than or equal to a preset distance threshold. If the second distance is greater than the preset distance threshold, the combined fine-grained geographic location and the third target recognition result are used as the fourth fine-grained water accumulation point location information.

[0156] Based on the above embodiment, optionally, the geographic location filtering algorithm construction unit is specifically used to:

[0157] Construct a priority list representing a fine-grained level of water accumulation location;

[0158] Using geographic location category labels to mark the first fine-grained waterlogging point location information, and assigning the marked first fine-grained waterlogging point location information to a corresponding priority list;

[0159] Retrieve the first fine-grained waterlogging point location information in the priority list according to the priority, and select the first fine-grained waterlogging point location information that exists and is at the highest priority position from the first priority, the second priority, and the third priority as the second fine-grained waterlogging point location information;

[0160] Among them, the geographic location category labels include roads, intersections, points of interest, communities, streets, districts and cities; roads, intersections and points of interest are the first priority, communities are the second priority, streets are the third priority, districts are the third priority, and cities are the fifth priority.

[0161] The intelligent water accumulation point identification device provided in the embodiment of the present invention can execute the intelligent water accumulation point identification method provided in any of the above-mentioned embodiments of the present invention, and has the corresponding functions and beneficial effects of executing the intelligent water accumulation point identification method. For detailed process, please refer to the relevant operations of the intelligent water accumulation point identification method in the above-mentioned embodiments.

[0162] Embodiment 5

[0163] Fig.12 1 is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0164] like Fig.12 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0165] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0166] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the intelligent identification method of water accumulation points.

[0167] In some embodiments, the method for intelligently identifying water accumulation points may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for intelligently identifying water accumulation points described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for intelligently identifying water accumulation points in any other appropriate manner (e.g., by means of firmware).

[0168] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0169] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0170] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0171] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0172] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0173] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0174] Embodiment 6

[0175] An embodiment of the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the intelligent water accumulation point identification method provided in any embodiment of the present application.

[0176] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0177] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0178] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for intelligently identifying water accumulation points, characterized in that: The method comprises: Using crawler technology to obtain text information related to rainstorm waterlogging from social media, and preprocessing the text information to obtain target text information; the preprocessing includes text sentence segmentation and keyword reverse screening; Classify the target text information and label the classified text information by category; wherein the classified text information includes water accumulation information and loss information; Constructing a fine-grained geographic location automatic extraction algorithm, and obtaining target fine-grained waterlogging point location information from waterlogging information and loss information based on the fine-grained geographic location automatic extraction algorithm; Determine the longitude and latitude information corresponding to the target fine-grained water accumulation point location information, and encode and visualize the target fine-grained water accumulation point location based on the longitude and latitude information.

2. The method according to claim 1, characterized in that The crawler technology is used to obtain text information related to rainstorm waterlogging from social media, and the text information is preprocessed to obtain target text information, including: Using web crawler technology based on simulated login, text information related to rainstorm waterlogging is obtained according to preset social media types, time ranges, and keywords; Performing data cleaning and useless information filtering on the text information, and removing information irrelevant to the rainstorm waterlogging waterlogging point, so as to obtain the target text information; Among them, data cleaning includes sentence-level cleaning and symbol-level cleaning. Sentence-level cleaning includes keyword reverse screening, text segmentation, waterlogging-related keyword screening, and text similarity deduplication processing.

3. The method according to claim 1, characterized in that The step of classifying the target text information and labeling the classified text information by category includes: Analyze the target text information to determine the subject content described by the target text information; Classifying the target text information into waterlogging information, loss information, and other information according to the subject content, and marking the classified text information by category; The loss information is used to describe the secondary disaster loss information caused by heavy rain and waterlogging, and the other information is used to describe the views on the disasters caused by heavy rain and waterlogging.

4. The method according to claim 1, characterized in that: The method of constructing a fine-grained geographic location automatic extraction algorithm and obtaining target fine-grained waterlogging point location information from waterlogging information and loss information according to the fine-grained geographic location automatic extraction algorithm includes: Constructing a geographic location extraction algorithm based on language rules, and using the geographic location extraction algorithm based on language rules to process waterlogging information, loss information and geographic location recognition results to obtain first fine-grained waterlogging point location information; wherein the geographic location recognition results are obtained by using a general named entity recognition model to perform named entity recognition of the geographic location of the waterlogging point on the target text information; A geographic location filtering algorithm based on category labels is constructed, and the geographic location filtering algorithm based on category labels is used to prioritize the first fine-grained waterlogging point location information to obtain the second fine-grained waterlogging point location information, and the second fine-grained waterlogging point location information is used as the target fine-grained waterlogging point location information.

5. The method according to claim 4, characterized in that The method of using the language rule-based geographic location extraction algorithm to process the waterlogging information, loss information, and geographic location identification results to obtain first fine-grained waterlogging point location information includes: Segment the waterlogging and loss information and divide different geographical locations into different segments; De-noising the geographic location recognition result to obtain a denoised geographic location recognition result; Detecting the segment to determine whether the segment contains a target recognition result; the target recognition result is a denoised geographic location recognition result; If the segment contains a target recognition result, the target recognition result is used as the third fine-grained water accumulation point location information; If the segment contains at least two target recognition results, determine whether the at least two target recognition results belong to the same geographical location according to the distance between the two adjacent target recognition results, and combine the at least two target recognition results belonging to the same geographical location to obtain fourth fine-grained water accumulation point location information; Determine whether the waterlogging information and the loss information contain special locating words, and determine whether the special locating words are connected to the third fine-grained waterlogging point location information or the fourth fine-grained waterlogging point location information; if they are connected, combine the special locating words with the third fine-grained waterlogging point location information or the fourth fine-grained waterlogging point location information to obtain the first fine-grained waterlogging point location information.

6. The method according to claim 5, characterized in that If the segment contains at least two target recognition results, whether the at least two target recognition results belong to the same geographical location is determined according to the distance between the two adjacent target recognition results, and the at least two target recognition results belonging to the same geographical location are combined to obtain fourth fine-grained water accumulation point location information, including: Determine whether a first distance between the first target recognition result and the second target recognition result is less than or equal to a preset distance threshold, and combine the first target recognition result and the second target recognition result when the first distance is less than or equal to the preset distance threshold, and output a combined fine-grained geographic location; Determine whether the second distance between the combined fine-grained geographic location and the third target recognition result is less than or equal to a preset distance threshold. If the second distance is greater than the preset distance threshold, the combined fine-grained geographic location and the third target recognition result are used as the fourth fine-grained water accumulation point location information.

7. The method according to claim 4, characterized in that The method of using a geographic location filtering algorithm based on a category label to prioritize the first fine-grained waterlogging point location information to obtain the second fine-grained waterlogging point location information includes: Construct a priority list representing a fine-grained level of water accumulation location; Using geographic location category labels to mark the first fine-grained waterlogging point location information, and assigning the marked first fine-grained waterlogging point location information to a corresponding priority list; Retrieve the first fine-grained waterlogging point location information in the priority list according to the priority, and select the first fine-grained waterlogging point location information that exists and is at the highest priority position from the first priority, the second priority, and the third priority as the second fine-grained waterlogging point location information; Among them, the geographic location category labels include roads, intersections, points of interest, communities, streets, districts and cities; roads, intersections and points of interest are the first priority, communities are the second priority, streets are the third priority, districts are the third priority, and cities are the fifth priority.

8. An intelligent water point identification device, characterized in that: The device comprises: A text information acquisition and preprocessing module is used to acquire text information related to rainstorm waterlogging from social media using crawler technology, and preprocess the text information to obtain target text information; the preprocessing includes text sentence segmentation and keyword reverse screening; The text information classification and labeling module is used to classify the target text information and label the classified text information by category; wherein the classified text information includes water accumulation information and loss information; A fine-grained waterlogging point location information extraction module is used to construct a fine-grained geographic location automatic extraction algorithm, and obtain the target fine-grained waterlogging point location information from the waterlogging information and the loss information according to the fine-grained geographic location automatic extraction algorithm; The fine-grained water accumulation point location information visualization module is used to determine the longitude and latitude information corresponding to the target fine-grained water accumulation point location information, and encode and visualize the target fine-grained water accumulation point location based on the longitude and latitude information.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the intelligent water accumulation point identification method described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the intelligent water accumulation point identification method as described in any one of claims 1-7 when executed by a computer processor.

Images