CN115966061B - Disaster early warning processing method, system and device based on 5G message - Google Patents
Disaster early warning processing method, system and device based on 5G message Download PDFInfo
- Publication number
- CN115966061B CN115966061B CN202211699898.7A CN202211699898A CN115966061B CN 115966061 B CN115966061 B CN 115966061B CN 202211699898 A CN202211699898 A CN 202211699898A CN 115966061 B CN115966061 B CN 115966061B
- Authority
- CN
- China
- Prior art keywords
- disaster
- data
- information
- early warning
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 50
- 238000004891 communication Methods 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000012550 audit Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 12
- 238000000605 extraction Methods 0.000 description 7
- 230000002265 prevention Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000009467 reduction Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
Landscapes
- Alarm Systems (AREA)
Abstract
The application discloses a disaster early warning processing method, a disaster early warning processing system and a disaster early warning processing device based on 5G information, wherein after receiving multi-mode disaster data, the disaster early warning processing method respectively carries out recognition processing on first-mode type data and second-mode type data in the disaster data to obtain disaster description information in the first-mode type data and object characteristic information in the second-mode type data; judging whether the disaster description information is matched with the object characteristic information or not based on a preset matching rule, and if so, generating disaster early warning information according to the disaster description information; and determining a target communication base station, acquiring a target information receiving terminal according to the target communication base station, and sending the disaster early warning information to the target information receiving terminal through a 5G message. The disaster early warning method solves the technical problems that the existing disaster early warning method in the related technology is not accurate and efficient, realizes automatic disaster recognition, and enables disaster early warning to be more accurate and efficient.
Description
Technical Field
The application belongs to the technical field of computers, and particularly relates to a disaster early warning processing method, system and device based on 5G messages.
Background
In our real life, various natural disasters are encountered, which sometimes cause life threatening and property loss to us. Although the central and local weather departments can foretell disasters in advance, firefighting and armed officers and soldiers in each place can rescue at the first time when the disasters occur, so as to protect the safety of disaster-stricken personnel and reduce property loss. The system is a powerful means for preventing disasters, and is a mature disaster forecasting and early warning system facing natural disasters.
In the related art, the existing disaster early warning system can only simply release disaster grade and early warning reminding information before disasters, and cannot locate and early warn target people in real time conditions and disaster ranges, so that disaster early warning is not accurate and efficient.
Aiming at the technical problems that the existing disaster early warning method in the related technology is not accurate and efficient enough, no effective solution is proposed at present.
Disclosure of Invention
Therefore, an embodiment of the present application is to provide a disaster early warning processing method, apparatus, electronic device and storage medium based on 5G messages, which aims to solve at least one problem existing in the prior art.
In order to achieve the above object, in a first aspect, the present application provides a disaster early warning processing method based on 5G messages, including:
After multi-mode disaster data are received, respectively identifying and processing first-mode type data and second-mode type data in the disaster data to obtain disaster description information in the first-mode type data and object characteristic information in the second-mode type data;
judging whether the disaster description information is matched with the object characteristic information or not based on a preset matching rule, and if so, generating disaster early warning information according to the disaster description information;
and determining a target communication base station, acquiring a target information receiving terminal according to the target communication base station, and sending the disaster early warning information to the target information receiving terminal through a 5G message.
In one embodiment, the first modality type data includes text data and/or voice data, and the identifying process for the first modality type data in disaster data includes: converting the voice data into language text data, inputting the text data or the language text data into a pre-trained natural language model, and outputting the disaster description information;
the second mode type data comprises picture data and/or video data, and the identifying processing of the second mode type data in disaster data comprises the following steps: and acquiring a picture frame in the video data, identifying and processing the picture data or the picture frame through a picture neural network identification algorithm to obtain a corresponding characteristic picture, inputting the characteristic picture into a pre-trained deep neural network identification model, and outputting the object characteristic information.
In one embodiment, inputting the text data or language text data into a pre-trained natural language model to output the disaster description information includes: and identifying the text data or language text data by utilizing a BM25 algorithm to obtain corresponding disaster type and disaster brief description text, inputting the disaster type and the disaster brief description text into a BERT model, and outputting the disaster description information, wherein the disaster description information comprises the disaster type, the occurrence time and the occurrence place of the disaster.
In one embodiment, inputting the feature picture into a pre-trained deep neural network recognition model to output the object feature information includes: and inputting the characteristic picture into a pre-trained UNet model to output the object characteristic information, wherein the object characteristic information comprises an object type, shooting time and shooting places.
In one embodiment, the disaster description information includes a disaster type, an occurrence time and an occurrence place of a disaster, and the object characteristic information includes an object type, a photographing time and a photographing place; the judging whether the disaster situation description information is matched with the object characteristic information based on a preset matching rule comprises the following steps:
And calculating the similarity between the text features of the disaster description information and the text features of the object feature information, and matching the disaster description information with the object feature information when the similarity is greater than or equal to a threshold value.
In one embodiment, if not, the disaster data is determined to be non-disaster information, and an audit result that the disaster data is not audited is returned.
In one embodiment, the determining the target communication base station, acquiring the target information receiving terminal according to the target communication base station, and sending the disaster early warning information to the target information receiving terminal through a 5G message, includes:
according to GPS positioning information of the reporting position of the disaster data, determining a communication base station within a preset range from the reporting position as the target communication base station;
acquiring an international mobile subscriber identification code/international mobile equipment identification code and a mobile phone number of a mobile phone accessed to a target communication base station, and determining the target information receiving terminal according to the international mobile subscriber identification code/international mobile equipment identification code and the mobile phone number;
and sending the disaster early warning information to the target information receiving terminal through the mobile phone number by a 5G message.
In one embodiment, the disaster early warning information includes a time of occurrence, a place of occurrence, a type of disaster, and a prompt message, and the method further includes: and responding to clicking of the 5G message body of the disaster early warning information, and returning the electronic map marked with the disaster early warning information through a front-end interface.
In a second aspect, the present application also provides a disaster early warning processing system based on 5G messages, including:
the disaster data processing unit is used for respectively identifying and processing the first mode type data and the second mode type data in the disaster data after receiving the multi-mode disaster data to obtain disaster description information in the first mode type data and object characteristic information in the second mode type data;
the disaster information judging unit is used for judging whether the disaster description information is matched with the object characteristic information or not based on a preset matching rule, and if yes, disaster early warning information is generated according to the disaster description information;
the disaster information sending unit is used for determining a target communication base station, acquiring a target information receiving terminal according to the target communication base station, and sending the disaster early warning information to the target information receiving terminal through a 5G message.
In a third aspect, the present application also provides an electronic device, including a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to execute the steps of the disaster early warning processing method based on the 5G message.
In a fourth aspect, the present application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, causes the processor to execute the steps of the disaster early warning processing method based on 5G messages.
According to the disaster early warning processing method, the disaster early warning processing system, the electronic equipment and the storage medium based on the 5G message, after multi-mode disaster data are received, the first-mode type data and the second-mode type data in the disaster data are respectively identified, so that disaster description information in the first-mode type data and object characteristic information in the second-mode type data are obtained; judging whether the disaster description information is matched with the object characteristic information or not based on a preset matching rule, and if so, generating disaster early warning information according to the disaster description information; and determining a target communication base station, acquiring a target information receiving terminal according to the target communication base station, and sending the disaster early warning information to the target information receiving terminal through a 5G message. The method solves the technical problems of insufficient precision and high efficiency of the existing disaster early warning method in the related technology, realizes automatic disaster identification, and enables people affected by the disaster with accurate disaster information to know disaster sending time, place, degree and the like more clearly, so that disaster prevention and disaster reduction can be better achieved, secondary disasters are avoided, and disaster early warning is more accurate and efficient.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, are incorporated in and constitute a part of this specification. The drawings and their description are illustrative of the application and are not to be construed as unduly limiting the application. In the drawings:
FIG. 1 is a flow chart of a disaster early warning processing method based on 5G messages according to an embodiment of the present application;
fig. 2 is a schematic diagram of a communication base station of a disaster early warning processing method based on a 5G message according to an embodiment of the present application;
FIG. 3 is a schematic diagram of main modules of a disaster early warning processing system based on 5G messages according to an embodiment of the present application;
FIG. 4 is a diagram of an exemplary system architecture to which embodiments of the present application may be applied;
fig. 5 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the present application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate an azimuth or a positional relationship based on that shown in the drawings. These terms are only used to better describe the present application and its embodiments and are not intended to limit the scope of the indicated devices, elements or components to the particular orientations or to configure and operate in the particular orientations.
Also, some of the terms described above may be used to indicate other meanings in addition to orientation or positional relationships, for example, the term "upper" may also be used to indicate some sort of attachment or connection in some cases. The specific meaning of these terms in the present application will be understood by those of ordinary skill in the art according to the specific circumstances.
In addition, the term "plurality" shall mean two as well as more than two.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
Fig. 1 shows a realization flow of a disaster early warning processing method based on a 5G message according to an embodiment of the present application, and for convenience of explanation, only the relevant parts of the embodiment of the present application are shown, which is described in detail as follows:
a disaster early warning processing method based on 5G information comprises the following steps:
s101: after multi-mode disaster data are received, respectively identifying and processing first-mode type data and second-mode type data in the disaster data to obtain disaster description information in the first-mode type data and object characteristic information in the second-mode type data;
S102: judging whether the disaster description information is matched with the object characteristic information or not based on a preset matching rule, and if so, generating disaster early warning information according to the disaster description information;
s103: and determining a target communication base station, acquiring a target information receiving terminal according to the target communication base station, and sending the disaster early warning information to the target information receiving terminal through a 5G message.
In step S101: after multi-mode disaster data are received, respectively identifying and processing first-mode type data and second-mode type data in the disaster data to obtain disaster description information in the first-mode type data and object characteristic information in the second-mode type data. Here, the multi-modal disaster data may include text, voice, image, video, and the like; the first mode type data can be text data and voice data, and is related description of the occurred disaster; the second modality type data may be image data, video data, or the like, which are recorded on the relevant fact images of the disaster. Therefore, after multi-mode disaster data are received, specific identification processing is carried out on the data with different mode types, and description information of the disaster and object characteristic information in the fact image are obtained, so that subsequent disaster and fact analysis is facilitated.
It should be noted that, the identifying processing is performed on the first modality type data and the second modality type data in the disaster situation data respectively, which can be understood that different identifying processing can be performed on the first modality type data and the second modality type data, where corresponding technical means can be adopted for identifying processing of data according to characteristics of different types of data to obtain relevant information, for example, important description information in text data can be obtained by adopting a natural language technology on text data, and the text data can be converted into text first and then identified by using the same technical means as the text data; the image data can be subjected to image recognition technology to obtain object features in the image, the video data can be subjected to video processing technology to capture key image frames in the video, and then the image frames are subjected to recognition means of the image data to obtain the object features in the video, wherein the similar prior art can be used for carrying out different or same recognition processing on data in different modes, so long as disaster description information and object feature information in disaster facts can be obtained.
Here, the disaster description information may include a disaster type, an occurrence time, and an occurrence place of the disaster, and the object characteristic information includes an object type, a photographing time, and a photographing place. Specifically, the disaster description information may be an outline of a disaster type, an occurrence time, and an occurrence place in a text, a voice, etc. describing an occurrence of a disaster obtained by recognition processing of text data and voice data, for example, the disaster description information may be: at day 14, 2022, 1 and 13, a certain area (concretely, longitude and latitude) is in fire; the object feature information may be description of information such as a shooting time and a shooting location (position) of an image or a video by describing description information of a main object feature appearing in the image or the video after the image and the video data are subjected to identification processing, and the shooting time and the location of the image or the video may be synthesized into a corresponding watermark to the image or the video when the image or the video is uploaded or acquired so as to match the shooting time and the location. For example, the object characteristic information may be: fire, in a certain area (concretely, longitude and latitude), 2022, 1, 13 and 14 days.
It should be noted that, the disaster situation data may be reported through a related system for reporting the disaster situation, for example, a user interface for reporting the disaster situation may be provided, then, when the user interface reports the disaster situation, the data such as the image and the video of the disaster situation are uploaded, and when the image or the video is uploaded, the capturing time and the place of the image or the video are synthesized to be corresponding to the watermark to the image or the video so as to match the capturing time and the place, and meanwhile, the description may be text or voice description, and then all the data are reported, thereby realizing the collection of the disaster situation data. Of course, disaster data can be collected through various collecting devices, for example, data collection is performed through a camera, a sensor and other devices, automatic text editing is realized through a text editor with disaster conditions, and then multi-mode disaster data collection is realized. In this embodiment, the user interface is preferably used to report and collect the multi-modal disaster data.
Therefore, after the disaster occurs, the disaster occurrence information can be rapidly acquired, and the disaster occurrence information can be timely released. The faster the disaster information is released, the more abundant the media content, the clearer the target crowd, and the more obvious the disaster prevention and reduction effect. And then the disaster early warning is more efficient and accurate.
In one embodiment, the first modality type data includes text data and/or voice data, and the identifying process for the first modality type data in disaster data includes: converting the voice data into language text data, inputting the text data or the language text data into a pre-trained natural language model, and outputting the disaster description information; the second mode type data comprises picture data and/or video data, and the identifying processing of the second mode type data in disaster data comprises the following steps: and acquiring a picture frame in the video data, identifying and processing the picture data or the picture frame through a picture neural network identification algorithm to obtain a corresponding characteristic picture, inputting the characteristic picture into a pre-trained deep neural network identification model, and outputting the object characteristic information. Namely, if the first modality type data is text data, outputting the disaster description information directly by inputting the text data into a pre-trained natural language model; if the first mode type data is voice data, converting the voice data into text data by utilizing a voice-to-text technology, and inputting the corresponding text data into a pre-trained natural language model to output the disaster description information; if the first mode type data comprises text data and voice data, converting the voice data into language text data, inputting the text data and the language text data into a pre-trained natural language model, and outputting the disaster description information.
Further, inputting the text data or language text data into a pre-trained natural language model to output the disaster situation description information includes: and identifying the text data or language text data by utilizing a BM25 algorithm to obtain corresponding disaster type and disaster brief description text, inputting the disaster type and the disaster brief description text into a BERT model, and outputting the disaster description information, wherein the disaster description information comprises the disaster type, the occurrence time and the occurrence place of the disaster.
In the present embodiment, it is possible to create a standard text library of disaster description information in advance and then makeAnd training a model in advance by using the bert, and finally realizing entity extraction (disaster description information extraction). Related keywords (disaster type and disaster brief description text) in disaster data (text data and language text data) can be extracted by using a classical text matching algorithm, for example, the BM25 is used for solving the similarity of short texts, identifying the disaster text data and obtaining the disaster type and the disaster brief content. The BM25 main calculation formula is as followsWherein Q is the description of disaster text, d is a standard description of standard library, n is the number of user description words, Q i For the ith word in the user disaster description, W i Is the weight of the word, R (q i D) describing a relevance score for the word and the criterion; and the named entity identification locates and classifies named entities in the disaster text data into predefined (standard library) related words (such as time expression, occurrence position, disaster type and the like), then inputs the related words into a pre-trained BERT model to output the disaster description information, and finally realizes entity extraction to obtain the disaster type, occurrence time and occurrence place of the disaster.
For example, for voice data, voice processing may be performed first to obtain corresponding text data. For example, speech recognition is to find the speech to maximize the text sequence (expressed as a Bayesian formula Take the output maximum sequence). Thereby obtaining voice text data corresponding to the voice data, and facilitating subsequent recognition processing of the voice data.
Further, inputting the feature picture into a pre-trained deep neural network recognition model to output the object feature information includes: and inputting the characteristic picture into a pre-trained UNet model to output the object characteristic information, wherein the object characteristic information comprises an object type, shooting time and shooting places.
In this embodiment, the depth neural network recognition model for recognizing the object features in the image is trained in advance to recognize the object feature information in the feature image, so as to obtain description information of the object features in the image data and the video data, for example, the object in the image is fire, the position and time of the object in the image, and the like. It should be noted that, training of the deep neural network recognition model only needs to prepare pictures of related scenes (for example, pictures of related disaster type objects) for marking, and then input the pictures into the model for training, and specifically, a UNet model can be selected. Therefore, the description information of the object features in the image or the video can be obtained after the feature pictures are input into the UNet model, for example, a picture with big fire is input into the UNet model and then the description text is output: fire, location (GPS latitude and longitude of picture taking), time (time of picture taking).
In this embodiment, the feature image may be obtained by performing texture segmentation (segmentation into a plurality of regions based on the similarity of pixel points) on the image data or the image frame, then processing the image with different convolution check using a convolution neural network, extracting edge information, and obtaining edge data. For example, the convolution kernel may use a gaussian convolution kernel verification step: 1. determining the size of a convolution kernel; 2. the standard deviation of the gaussian function is set, σ＝ 1 ， such as σ=1,3. and calculating the weight value 4 of each position of the convolution kernel, and normalizing the weight value. Edge extraction can use the gradient of the image +.>Referring to the fastest direction of gray scale transformation, the modulus of the gradient is used: />The value reflects edge information.
It should be noted that, for video data, video may be subjected to processing such as video reading, inter-frame feature extraction, intra-frame feature extraction, feature encoding, feature classification, and the like, and then the obtained data is input into a convolutional neural network model to obtain a picture frame in the video data.
Therefore, after disaster data such as text, voice, images and videos are received, natural language identification processing is carried out on the text data and the voice data to obtain disaster description information, and after identification processing is carried out on the image data and the video data in the disaster data, object characteristic information in shooting images related to the disaster is obtained, and whether the disaster actually occurs can be judged by comparing the disaster description information with the object characteristics in the images.
In step S102: judging whether the disaster description information is matched with the object characteristic information or not based on a preset matching rule, and if so, generating disaster early warning information according to the disaster description information. Therefore, whether the disaster description information is matched with the object characteristic information or not can be judged, whether the disaster data is a real disaster or not is further judged, and if the disaster is the real disaster, disaster early warning information is generated for information release. Here, the preset matching rule can be realized based on a word searching technology, and the words of the disaster description information and the description words of the object feature information are searched and matched to see whether the words are the same; the preset matching rule can also be a mode of calculating text similarity, so that word similarity between disaster description information and object characteristic information is calculated, and judgment is carried out according to the similarity. If not, determining the disaster data as non-disaster information, and returning an audit result that the disaster data is not audited. Namely, disaster data is reported in a non-real disaster, and the reported disaster data is rejected.
In one embodiment, the determining whether the disaster situation description information matches the object feature information based on a preset matching rule includes: and calculating the similarity between the text features of the disaster description information and the text features of the object feature information, and matching the disaster description information with the object feature information when the similarity is greater than or equal to a threshold value. For example, the threshold value may be set to 90%, and when the text similarity between the disaster description information (e.g., fire, position 1, time 1) and the object feature information (e.g., fire, position 1, time 1) is 95%, the disaster description information is matched with the object feature information, so that the disaster data can be determined to be a real disaster.
In step S103: and determining a target communication base station, acquiring a target information receiving terminal according to the target communication base station, and sending the disaster early warning information to the target information receiving terminal through a 5G message. Thus, disaster information can be notified to the nearby possible disaster-stricken population through the communication base station.
Specifically, the determining the target communication base station, acquiring a target information receiving terminal according to the target communication base station, and sending the disaster early warning information to the target information receiving terminal through a 5G message, includes: according to GPS positioning information of the reporting position of the disaster data, determining a communication base station within a preset range from the reporting position as the target communication base station; acquiring an international mobile subscriber identification code/international mobile equipment identification code and a mobile phone number of a mobile phone accessed to a target communication base station, and determining the target information receiving terminal according to the international mobile subscriber identification code/international mobile equipment identification code and the mobile phone number; and sending the disaster early warning information to the target information receiving terminal through the mobile phone number by a 5G message.
For example, fig. 3 is a schematic diagram of a communication base station of a disaster early warning processing method based on 5G messages according to an embodiment of the present application, which is a relationship diagram after a mobile communication system user accesses a mobile communication network. The VLR is a database of information required for MSC calls in jurisdiction, provides user numbers, and can acquire the mobile phone numbers of the access users of the associated base stations after disaster through the base station information as a condition. Therefore, after the position information (GPS positioning information longitude and latitude data) reported by the disaster is determined, the I MSI/I MEI and the mobile phone number of the accessed mobile phone can be obtained through the base station of the position by the operator, and then the target information receiving terminal is determined.
In one embodiment, the disaster early warning information includes a time of occurrence, a place of occurrence, a type of disaster, and a prompt message, and the method further includes: and responding to clicking of the 5G message body of the disaster early warning information, and returning the electronic map marked with the disaster early warning information through a front-end interface. The disaster early warning information can be marked in the electronic map, for example, a certain natural disaster can occur at a certain time, therefore, longitude and latitude and disaster pictures reported by disaster data are used, the map is marked by disaster small pictures, the disaster is clicked and displayed at a certain time, a disaster receiving user receives 5G information and can check when and where the natural disaster which possibly affects himself can occur on the electronic map by checking the 5G information (the 5G information body is jumped to web map display with an operation button). Therefore, disaster prevention and mass disaster relief are better realized by checking disaster information and degree, so that the influence of disasters is reduced, meanwhile, the safety threat of personnel can be reduced by reducing secondary disasters, and the property loss is reduced.
The disaster early warning processing method based on the 5G message can reduce personnel security threat and property loss. The artificial intelligent system performs intelligent disaster situation recognition reporting through the 5G message or as an information reporting entrance (or the app thereof is taken as an entrance), so that the recognition efficiency is improved; and (3) determining disaster influence groups (simultaneously, sending information to related personnel of government departments) by reporting the geographic position information of the disaster information by using the information base station. The method has the advantages that the reporting efficiency is high, the auditing is quick, the base station acquires accurate crowds and uses 5G messages as carriers, compared with the traditional message sending method such as short messages and multimedia messages, the 5G messages can be used as inlets, and electronic maps can be linked and utilized, so that disaster information can be used as bearing media, the affected crowds can know disaster occurrence time, place, degree and the like more clearly, disaster prevention and reduction can be better achieved, and secondary disasters are avoided.
According to the disaster early warning processing method based on the 5G message, after multi-mode disaster data are received, the first mode type data and the second mode type data in the disaster data are respectively identified, so that disaster description information in the first mode type data and object characteristic information in the second mode type data are obtained; judging whether the disaster description information is matched with the object characteristic information or not based on a preset matching rule, and if so, generating disaster early warning information according to the disaster description information; and determining a target communication base station, acquiring a target information receiving terminal according to the target communication base station, and sending the disaster early warning information to the target information receiving terminal through a 5G message. The method solves the technical problems of insufficient precision and high efficiency of the existing disaster early warning method in the related technology, realizes automatic disaster identification, and enables people affected by the disaster with accurate disaster information to know disaster sending time, place, degree and the like more clearly, so that disaster prevention and disaster reduction can be better achieved, secondary disasters are avoided, and disaster early warning is more accurate and efficient.
Fig. 3 is a schematic diagram of main modules of a disaster early warning processing system based on 5G messages according to an embodiment of the present application, and for convenience of explanation, only the relevant parts of the embodiment of the present application are shown, which is described in detail below:
a disaster early warning processing system 200 based on 5G messages, comprising:
the disaster data processing unit 201 is configured to, after receiving multi-mode disaster data, respectively identify first-mode type data and second-mode type data in the disaster data, so as to obtain disaster description information in the first-mode type data and object feature information in the second-mode type data;
the disaster information judging unit 202 is configured to judge whether the disaster description information is matched with the object feature information based on a preset matching rule, and if yes, generate disaster early warning information according to the disaster description information;
and the disaster information sending unit 203 is configured to determine a target communication base station, obtain a target information receiving terminal according to the target communication base station, and send the disaster early warning information to the target information receiving terminal through a 5G message.
It should be noted that, the disaster early warning processing system based on the 5G message in the embodiment of the present application configures the disaster early warning processing method based on the 5G message corresponding to the embodiment of the present application, and other embodiments of the disaster early warning processing system based on the 5G message correspond to all embodiments of the disaster early warning processing method based on the 5G message, which are not described herein again.
Therefore, the disaster early warning processing system based on the 5G message solves the technical problems that an existing disaster early warning method in the related technology is not accurate and efficient, achieves automatic disaster recognition, and enables people affected by the disaster with accurate disaster information to know disaster sending time, place, degree and the like more clearly, disaster prevention and disaster reduction are achieved better, secondary disaster is avoided, and disaster early warning is more accurate and efficient.
The embodiment of the application also provides electronic equipment, which comprises: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by one or more processors, the one or more processors realize the disaster early warning processing method based on the 5G message.
The embodiment of the application also provides a computer readable medium, on which a computer program is stored, which when executed by a processor, implements the disaster early warning processing method based on the 5G message of the embodiment of the application.
Fig. 4 illustrates an exemplary system architecture 300 to which the 5G message-based disaster warning processing method or apparatus of the present application may be applied.
As shown in fig. 4, the system architecture 300 may include terminal devices 301, 302, 303, a network 304, and a server 305. The network 304 is used as a medium to provide communication links between the terminal devices 301, 302, 303 and the server 305. The network 304 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 305 via the network 304 using the terminal devices 301, 302, 303 to receive or send messages or the like. Various communication client applications, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc., may be installed on the terminal devices 301, 302, 303.
The terminal devices 301, 302, 303 may be a variety of electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 305 may be a server providing various services, such as a background management server providing support for user messages sent to and from the terminal devices 301, 302, 303. The background management server can perform analysis and other processes after receiving the terminal equipment request, and feed back the processing result to the terminal equipment.
It should be noted that, the disaster early warning processing method based on the 5G message provided in the embodiment of the present application is generally executed by the terminal device 301, 302, 303 or the server 305, and accordingly, the disaster early warning processing system based on the 5G message is generally set in the terminal device 301, 302, 303 or the server 305.
It should be understood that the number of terminal devices, networks and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 5, there is illustrated a schematic diagram of a computer system 400 suitable for use in implementing a terminal device or server in accordance with an embodiment of the present application. The computer system illustrated in fig. 5 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present application.
As shown in fig. 5, the computer system 400 includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In RAM403, various programs and data required for the operation of system 400 are also stored. The CPU 401, ROM 402, and RAM403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output portion 407 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage section 408 including a hard disk or the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. The drive 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 409 and/or installed from the removable medium 411. The above-described functions defined in the system of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 401.
The computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present application may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor includes a determination module, an extraction module, a training module, and a screening module. Where the names of the modules do not constitute a limitation on the module itself in some cases, the determination module may also be described as "module for determining a candidate set of users", for example.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (7)
1. The disaster early warning processing method based on the 5G message is characterized by comprising the following steps of:
after multi-mode disaster data are received, respectively identifying and processing first-mode type data and second-mode type data in the disaster data to obtain disaster description information in the first-mode type data and object characteristic information in the second-mode type data;
Judging whether the disaster description information is matched with the object characteristic information or not based on a preset matching rule, and if so, generating disaster early warning information according to the disaster description information;
determining a target communication base station, acquiring a target information receiving terminal according to the target communication base station, and sending the disaster early warning information to the target information receiving terminal through a 5G message;
the first mode type data comprises text data and/or voice data, and the identification processing of the first mode type data in disaster data comprises the following steps: converting the voice data into language text data, inputting the text data or the language text data into a pre-trained natural language model, and outputting the disaster description information;
the second mode type data comprises picture data and/or video data, and the identifying processing of the second mode type data in disaster data comprises the following steps: acquiring a picture frame in video data, identifying and processing the picture data or the picture frame through a picture neural network identification algorithm to obtain a corresponding characteristic picture, inputting the characteristic picture into a pre-trained deep neural network identification model, and outputting the object characteristic information;
Inputting the text data or language text data into a pre-trained natural language model to output the disaster situation description information, wherein the method comprises the following steps of: identifying the text data or language text data by utilizing a BM25 algorithm to obtain a corresponding disaster type and a disaster brief description text, inputting the disaster type and the disaster brief description text into a BERT model, and outputting disaster description information, wherein the disaster description information comprises the disaster type, the occurrence time and the occurrence place of the disaster;
identifying the text data or language text data by using a BM25 algorithm to obtain corresponding disaster type and disaster brief description text, wherein the method comprises the following steps:
wherein Q is the description of disaster text, d is a standard description of standard library, n is the number of user description words, Q i For the ith word in the user disaster description, W i Is the weight of the word, R (q i D) describing a relevance score for the word and the criterion;
inputting the characteristic picture into a pre-trained deep neural network recognition model to output the object characteristic information, wherein the method comprises the following steps of: inputting the characteristic picture into a pre-trained UNet model to output the object characteristic information, wherein the object characteristic information comprises an object type, shooting time and shooting places;
Inputting the characteristic picture into a pre-trained UNet model to output the object characteristic information, wherein the method comprises the following steps of:
the image data or the picture frame is subjected to texture segmentation to obtain a plurality of area images, the convolutional neural network is utilized to process the images by using different convolutional checks, edge information is extracted to obtain edge data, and then the characteristic picture is obtained.
2. The disaster early warning processing method based on 5G messages according to claim 1, wherein the disaster description information includes a disaster type, an occurrence time and an occurrence place of a disaster, and the object characteristic information includes an object type, a photographing time and a photographing place; the judging whether the disaster situation description information is matched with the object characteristic information based on a preset matching rule comprises the following steps:
and calculating the similarity between the text features of the disaster description information and the text features of the object feature information, and matching the disaster description information with the object feature information when the similarity is greater than or equal to a threshold value.
3. The disaster early warning processing method based on 5G messages according to claim 1, wherein if not, the disaster data is determined to be non-disaster information, and an audit result that the disaster data is not audited is returned.
4. The disaster early warning processing method based on 5G message as set forth in claim 1, wherein the determining a target communication base station, acquiring a target information receiving terminal according to the target communication base station, and transmitting the disaster early warning information to the target information receiving terminal through the 5G message, comprises:
according to GPS positioning information of the reporting position of the disaster data, determining a communication base station within a preset range from the reporting position as the target communication base station;
acquiring an international mobile subscriber identification code/international mobile equipment identification code and a mobile phone number of a mobile phone accessed to a target communication base station, and determining the target information receiving terminal according to the international mobile subscriber identification code/international mobile equipment identification code and the mobile phone number;
and sending the disaster early warning information to the target information receiving terminal through the mobile phone number by a 5G message.
5. The disaster early warning processing method based on 5G messages as set forth in claim 4, wherein the disaster early warning information includes occurrence time, occurrence location, disaster type and hint message of the disaster, the method further comprising: and responding to clicking of the 5G message body of the disaster early warning information, and returning the electronic map marked with the disaster early warning information through a front-end interface.
6. Disaster early warning processing system based on 5G message, characterized by comprising:
the disaster data processing unit is used for respectively identifying and processing the first mode type data and the second mode type data in the disaster data after receiving the multi-mode disaster data to obtain disaster description information in the first mode type data and object characteristic information in the second mode type data;
the disaster information judging unit is used for judging whether the disaster description information is matched with the object characteristic information or not based on a preset matching rule, and if yes, disaster early warning information is generated according to the disaster description information;
the disaster information sending unit is used for determining a target communication base station, acquiring a target information receiving terminal according to the target communication base station, and sending the disaster early warning information to the target information receiving terminal through a 5G message;
the first mode type data comprises text data and/or voice data, and the identification processing of the first mode type data in disaster data comprises the following steps: converting the voice data into language text data, inputting the text data or the language text data into a pre-trained natural language model, and outputting the disaster description information;
The second mode type data comprises picture data and/or video data, and the identifying processing of the second mode type data in disaster data comprises the following steps: acquiring a picture frame in video data, identifying and processing the picture data or the picture frame through a picture neural network identification algorithm to obtain a corresponding characteristic picture, inputting the characteristic picture into a pre-trained deep neural network identification model, and outputting the object characteristic information;
inputting the text data or language text data into a pre-trained natural language model to output the disaster situation description information, wherein the method comprises the following steps of: identifying the text data or language text data by utilizing a BM25 algorithm to obtain a corresponding disaster type and a disaster brief description text, inputting the disaster type and the disaster brief description text into a BERT model, and outputting disaster description information, wherein the disaster description information comprises the disaster type, the occurrence time and the occurrence place of the disaster;
identifying the text data or language text data by using a BM25 algorithm to obtain corresponding disaster type and disaster brief description text, wherein the method comprises the following steps:
wherein Q is the description of disaster text, d is a standard description of standard library, n is the number of user description words, Q i For the ith word in the user disaster description, W i Is the weight of the word, R (q i D) describing a relevance score for the word and the criterion;
inputting the characteristic picture into a pre-trained deep neural network recognition model to output the object characteristic information, wherein the method comprises the following steps of: inputting the characteristic picture into a pre-trained UNet model to output the object characteristic information, wherein the object characteristic information comprises an object type, shooting time and shooting places;
inputting the characteristic picture into a pre-trained UNet model to output the object characteristic information, wherein the method comprises the following steps of:
the image data or the picture frame is subjected to texture segmentation to obtain a plurality of area images, the convolutional neural network is utilized to process the images by using different convolutional checks, edge information is extracted to obtain edge data, and then the characteristic picture is obtained.
7. An electronic device comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, causes the processor to perform the steps of the 5G message-based disaster warning processing method as set forth in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211699898.7A CN115966061B (en) | 2022-12-28 | 2022-12-28 | Disaster early warning processing method, system and device based on 5G message |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211699898.7A CN115966061B (en) | 2022-12-28 | 2022-12-28 | Disaster early warning processing method, system and device based on 5G message |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115966061A CN115966061A (en) | 2023-04-14 |
| CN115966061B true CN115966061B (en) | 2023-10-24 |
Family
ID=87352370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211699898.7A Active CN115966061B (en) | 2022-12-28 | 2022-12-28 | Disaster early warning processing method, system and device based on 5G message |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115966061B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116932731B (en) * | 2023-09-18 | 2024-01-30 | 上海帜讯信息技术股份有限公司 | Multi-mode knowledge question-answering method and system for 5G message |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930619A (en) * | 2010-08-25 | 2010-12-29 | 中国科学院自动化研究所 | Collaborative filtering-based real-time voice-driven human face and lip synchronous animation system |
| CN103218924A (en) * | 2013-03-29 | 2013-07-24 | 上海众实科技发展有限公司 | Audio and video dual mode-based spoken language learning monitoring method |
| CN103995804A (en) * | 2013-05-20 | 2014-08-20 | 中国科学院计算技术研究所 | Cross-media topic detection method and device based on multimodal information fusion and graph clustering |
| CN105376856A (en) * | 2015-10-23 | 2016-03-02 | 浙江大学 | Detection system and cooperative communication positioning method for disaster assistance |
| CN110365946A (en) * | 2019-07-26 | 2019-10-22 | 浙江大华技术股份有限公司 | Generation method, device, storage medium and the electronic device of the condition of a disaster counte-rplan |
| CN112148997A (en) * | 2020-08-07 | 2020-12-29 | 江汉大学 | Multi-modal confrontation model training method and device for disaster event detection |
| CN212344062U (en) * | 2020-07-01 | 2021-01-12 | 四川艾欧特智能科技有限公司 | Forest zone data monitoring system based on 5G communication |
| CN114356084A (en) * | 2021-12-24 | 2022-04-15 | 阿里巴巴（中国）有限公司 | Image processing method and system and electronic equipment |
| WO2022134701A1 (en) * | 2020-12-22 | 2022-06-30 | 上海幻电信息科技有限公司 | Video processing method and apparatus |
| CN114723986A (en) * | 2022-03-16 | 2022-07-08 | 平安科技（深圳）有限公司 | Text image matching method, device, equipment and storage medium |
| CN115062112A (en) * | 2022-06-24 | 2022-09-16 | 杭州海康威视数字技术股份有限公司 | Monitoring and defense deploying method, device and system based on text description |
| WO2022198854A1 (en) * | 2021-03-24 | 2022-09-29 | 北京百度网讯科技有限公司 | Method and apparatus for extracting multi-modal poi feature |
| CN115348247A (en) * | 2022-08-09 | 2022-11-15 | 四川科瑞源信息科技有限公司 | Forest fire detection early warning and decision-making system based on sky-ground integration technology |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220392637A1 (en) * | 2021-06-02 | 2022-12-08 | Neumora Therapeutics, Inc. | Multimodal dynamic attention fusion |
-
2022
- 2022-12-28 CN CN202211699898.7A patent/CN115966061B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930619A (en) * | 2010-08-25 | 2010-12-29 | 中国科学院自动化研究所 | Collaborative filtering-based real-time voice-driven human face and lip synchronous animation system |
| CN103218924A (en) * | 2013-03-29 | 2013-07-24 | 上海众实科技发展有限公司 | Audio and video dual mode-based spoken language learning monitoring method |
| CN103995804A (en) * | 2013-05-20 | 2014-08-20 | 中国科学院计算技术研究所 | Cross-media topic detection method and device based on multimodal information fusion and graph clustering |
| CN105376856A (en) * | 2015-10-23 | 2016-03-02 | 浙江大学 | Detection system and cooperative communication positioning method for disaster assistance |
| CN110365946A (en) * | 2019-07-26 | 2019-10-22 | 浙江大华技术股份有限公司 | Generation method, device, storage medium and the electronic device of the condition of a disaster counte-rplan |
| CN212344062U (en) * | 2020-07-01 | 2021-01-12 | 四川艾欧特智能科技有限公司 | Forest zone data monitoring system based on 5G communication |
| CN112148997A (en) * | 2020-08-07 | 2020-12-29 | 江汉大学 | Multi-modal confrontation model training method and device for disaster event detection |
| WO2022134701A1 (en) * | 2020-12-22 | 2022-06-30 | 上海幻电信息科技有限公司 | Video processing method and apparatus |
| WO2022198854A1 (en) * | 2021-03-24 | 2022-09-29 | 北京百度网讯科技有限公司 | Method and apparatus for extracting multi-modal poi feature |
| CN114356084A (en) * | 2021-12-24 | 2022-04-15 | 阿里巴巴（中国）有限公司 | Image processing method and system and electronic equipment |
| CN114723986A (en) * | 2022-03-16 | 2022-07-08 | 平安科技（深圳）有限公司 | Text image matching method, device, equipment and storage medium |
| CN115062112A (en) * | 2022-06-24 | 2022-09-16 | 杭州海康威视数字技术股份有限公司 | Monitoring and defense deploying method, device and system based on text description |
| CN115348247A (en) * | 2022-08-09 | 2022-11-15 | 四川科瑞源信息科技有限公司 | Forest fire detection early warning and decision-making system based on sky-ground integration technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115966061A (en) | 2023-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11122100B2 (en) | Detecting events from ingested data | |
| KR101897923B1 (en) | System for providing identify target object based on neural network learning model, method thereof, and computer readable storage having the same | |
| US20180150928A1 (en) | Cognitive recommendations for first responders | |
| US20150294233A1 (en) | Systems and methods for automatic metadata tagging and cataloging of optimal actionable intelligence | |
| US20200162534A1 (en) | Detecting an event from signal data | |
| CN111062389A (en) | Character recognition method and device, computer readable medium and electronic equipment | |
| CN112258254B (en) | Internet advertisement risk monitoring method and system based on big data architecture | |
| US10880672B2 (en) | Evidence management system and method | |
| CN112765485A (en) | Network social event prediction method, system, terminal, computer device and medium | |
| US11601391B2 (en) | Automated image processing and insight presentation | |
| CN109902681B (en) | User group relation determining method, device, equipment and storage medium | |
| CN115966061B (en) | Disaster early warning processing method, system and device based on 5G message | |
| KR20160001994A (en) | Server and method for managing crime using big data | |
| CN114708426A (en) | Target detection method, model training method, device, equipment and storage medium | |
| CN107766498A (en) | Method and apparatus for generating information | |
| CN116628507B (en) | Data processing method, device, equipment and readable storage medium | |
| CN109740510B (en) | Method and apparatus for outputting information | |
| Chair et al. | Towards a social media-based framework for disaster communication | |
| Sathianarayanan et al. | Extracting disaster location identification from social media images using deep learning | |
| CN113342978A (en) | City event processing method and device | |
| CN114579876A (en) | False information detection method, device, equipment and medium | |
| KR102367110B1 (en) | System for providing watch registration service | |
| CN107451180B (en) | Method, device, equipment and computer storage medium for identifying site homologous relation | |
| CN116468907B (en) | Method and device for image processing, image classification and image detection | |
| BAROZZI | Visual social media and crowdsourcing: analysis of tools for disaster management applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |