Method for judging specific event and associating group

Abstract

The invention discloses a method for judging a specific event and associating a group. The method comprises the following steps: S1, a control module transmits at least one piece of user position data and at least one piece of user information corresponding to the user position data one by one to a cloud; s3, the server is connected with weather bureau websites of all countries and obtains multiple pieces of weather information data; s4, sending the predicted disaster occurrence time and the disaster type of the corresponding place to all users in the user group corresponding to the user position data; by adopting the method, the early warning information issued by a plurality of weather bureau can be automatically monitored, and the reminding is actively sent to the user when the early warning level reaches the preset threshold value.

Description

Technical Field

[0001] The present invention relates to the technical field of control and regulation systems, and in particular to a method for determining and associating specific events with groups. Background Art

[0002] As the impact of global climate change becomes increasingly significant, the frequency and intensity of extreme weather events have increased. In this context, timely and accurate meteorological information is crucial to protecting people's lives and property. Traditional meteorological warning methods include television broadcasts, mobile phone text message notifications, etc., but these methods often have certain limitations. For example, users need to actively visit the meteorological bureau website or application to obtain the latest meteorological information; or when users have travel plans and are in different countries or regions, they need to check the meteorological information of various places separately; the existing system cannot provide specific warning services based on the user's geographic location and personal preferences.

[0003] Therefore, there is a need for a method that can automatically monitor the warning information issued by multiple meteorological bureaus and actively send reminders to users when the warning level reaches a preset threshold. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method for determining and associating specific events with groups; the method can automatically monitor the warning information issued by multiple meteorological bureaus, and actively send reminders to users when the warning level reaches a preset threshold.

[0005] The technical solution adopted by the present invention to solve its technical problem is to provide a method for determining a specific event and associating a group, including a cloud end and a user end, wherein the user end includes a plurality of positioning modules corresponding to the user one by one, a plurality of control modules corresponding to the user one by one, and a plurality of display modules corresponding to the user one by one, and the cloud end includes a server;

[0006] The method comprises the following steps:

[0007] S1. The positioning module detects the user's position according to the standard positioning detection frequency preset in the control module to form user position data, and the control module transmits at least one user position data and at least one user information corresponding to the user position data to the cloud;

[0008] S2. The server presets a standard location range value. If the distance between different user location data is smaller than the standard location range value, the user information corresponding to the user location data is integrated into one user group, and the remaining user information is a separate user group, thereby obtaining multiple user groups associated with the user location data one by one;

[0009] S3. The server connects to the websites of meteorological bureaus of various countries and obtains multiple meteorological information data. The server is preset with multiple warning level databases corresponding to different countries. The meteorological information data includes meteorological warning level data. The server converts the meteorological warning level data in the meteorological information data into Chinese warning level data according to China's warning level standards through the warning level database corresponding to the country. When there is Chinese warning level data greater than or equal to the warning reminder level preset in the server, the meteorological information data corresponding to the Chinese warning level data is translated and preprocessed to obtain the unified warning translation data;

[0010] S4. The server extracts the location, disaster type and expected time of disaster occurrence from the unified translation data of the warning through natural language processing technology. When the distance between a location and a user's location data is less than the standard location range value, the expected time of disaster occurrence and disaster type of the corresponding location are sent to all users in the user group corresponding to the user's location data, and displayed through the display module corresponding to the user.

[0011] As a further improvement of the present invention, the user terminal further includes a plurality of input modules corresponding to the users one by one;

[0012] After the positioning module detects the user's position according to the standard positioning detection frequency preset in the control module in step S1 to form the user position data, the method further includes: the user can input the desired destination through the input module, and the control module generates the user position data according to the desired destination.

[0013] As a further improvement of the present invention, the user location data includes positioning data and detection time data, and the control module is preset with a time-limited value;

[0014] In step S1, the specific steps of the positioning module detecting the user's position according to the standard positioning detection frequency preset in the control module to form the user's position data are as follows: the positioning module detects the user's position according to the standard positioning detection frequency preset in the control module to obtain positioning data, and the positioning module detects the user's position and records the current detection time to obtain detection time data; the positioning data and the detection time data are combined to form the user's position data;

[0015] The specific steps of the control module generating the user location data according to the desired destination are as follows: the control module obtains the positioning data according to the desired destination, obtains the detection time data according to the time when the user inputs the desired destination, and combines the positioning data and the detection time data to form the user location data;

[0016] Before the control module transmits at least one user location data and at least one user information corresponding to the user location data to the cloud, the method also includes: deleting the user location data when the difference between the current time and the detection time data is less than the timeliness value.

[0017] As a further improvement of the present invention, the control module obtains the detection time data according to the time of the destination that the user wants to go to, and sets the detection time data to a deletion-free state;

[0018] When deleting user location data, if the detection time data is in the deletion-free state, the deletion of the user location data is cancelled.

[0019] As a further improvement of the present invention, the specific steps of translating and preprocessing the meteorological information data corresponding to the Chinese warning level data to obtain the unified warning translation data in step S3 include: submitting the meteorological information data corresponding to the Chinese warning level data to the Google Translate API to obtain the unified warning translation data.

[0020] As a further improvement of the present invention, the specific steps of extracting the location, disaster type and expected time of disaster occurrence from the unified translation data of the warning by the server through natural language processing technology in step S4 include:

[0021] S41, performing translation error correction processing on the warning unified translation data by natural language processing technology to obtain warning error correction translation data;

[0022] S42. Perform text preprocessing, word segmentation, part-of-speech tagging, entity recognition and entity extraction on the warning error correction translation data in sequence, so as to obtain the location, disaster type and estimated time of occurrence of the disaster.

[0023] As a further improvement of the present invention, the specific steps of performing translation error correction processing on the warning unified translation data by natural language processing technology in step S41 to obtain the warning error correction translation data include:

[0024] S411. Detect and mark grammatical errors in the warning unified translation data through the LanguageTool grammar checker, detect and mark spelling errors in the warning unified translation data through the PySpellChecker spell checker, and detect and mark unreasonable sentence structures through the Spacy dependency syntax analysis tool;

[0025] S412. Automatically correct the marked locations through a Seq2Seq sequence-to-sequence model.

[0026] As a further improvement of the present invention, after extracting entities from the news translation correction data set in step S42, the method further includes: correcting the extracted entity locations through the Wikipedia knowledge base.

[0027] As a further improvement of the present invention, in step S42, the warning error correction translation data is sequentially subjected to text preprocessing, word segmentation, part-of-speech tagging, entity recognition and entity extraction, so as to obtain the location, disaster type and expected time of disaster occurrence. The specific steps are: unifying the digital format in the warning error correction translation data and removing special symbols, dividing the text into multiple words through a word segmenter, and tagging each word with a part-of-speech, identifying entities through the Spacy named entity recognition tool, and extracting the entity location, entity disaster type and entity disaster expected time of occurrence, so as to obtain the location, disaster type and expected time of disaster occurrence.

[0028] As a further improvement of the present invention, the warning level database includes a plurality of warning level data of other countries corresponding to the warning level standards of the corresponding countries and a plurality of Chinese warning level data corresponding one-to-one to the warning level data of other countries.

[0029] The beneficial effect of the present invention is at least that it can automatically monitor the warning information issued by multiple meteorological bureaus and actively send reminders to users when the warning level reaches a preset threshold. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0031] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings.

[0032] Reference Figure 1 , the present invention proposes a method for determining and associating a specific event with a group, including a cloud end and a user end, the user end including a plurality of positioning modules corresponding to the user one by one, a plurality of control modules corresponding to the user one by one, and a plurality of display modules corresponding to the user one by one, the cloud end including a server;

[0033] The method comprises the following steps:

[0034] S1. The positioning module detects the user's position according to the standard positioning detection frequency preset in the control module to form user position data, and the control module transmits at least one user position data and at least one user information corresponding to the user position data to the cloud;

[0035] S2. The server presets a standard location range value. If the distance between different user location data is smaller than the standard location range value, the user information corresponding to the user location data is integrated into one user group, and the remaining user information is a separate user group, thereby obtaining multiple user groups associated with the user location data one by one;

[0036] S3. The server connects to the websites of meteorological bureaus of various countries and obtains multiple meteorological information data. The server is preset with multiple warning level databases corresponding to different countries. The meteorological information data includes meteorological warning level data. The server converts the meteorological warning level data in the meteorological information data into Chinese warning level data according to China's warning level standards through the warning level database corresponding to the country. When there is Chinese warning level data greater than or equal to the warning reminder level preset in the server, the meteorological information data corresponding to the Chinese warning level data is translated and preprocessed to obtain the unified warning translation data;

[0037] S4. The server extracts the location, disaster type and expected time of disaster occurrence from the unified translation data of the warning through natural language processing technology. When the distance between a location and a user's location data is less than the standard location range value, the expected time of disaster occurrence and disaster type of the corresponding location are sent to all users in the user group corresponding to the user's location data, and displayed through the display module corresponding to the user.

[0038] It can automatically monitor the warning information issued by multiple meteorological bureaus and proactively send reminders to users when the warning level reaches the preset threshold.

[0039] As a further improvement of the present invention, the user terminal further includes a plurality of input modules corresponding to the users one by one;

[0040] After the positioning module detects the user's position according to the standard positioning detection frequency preset in the control module in step S1 to form the user position data, the method further includes: the user can input the desired destination through the input module, and the control module generates the user position data according to the desired destination.

[0041] As a further improvement of the present invention, the user location data includes positioning data and detection time data, and the control module is preset with a time-limited value;

[0042] In step S1, the specific steps of the positioning module detecting the user's position according to the standard positioning detection frequency preset in the control module to form the user's position data are as follows: the positioning module detects the user's position according to the standard positioning detection frequency preset in the control module to obtain positioning data, and the positioning module detects the user's position and records the current detection time to obtain detection time data; the positioning data and the detection time data are combined to form the user's position data;

[0043] The specific steps of the control module generating the user location data according to the desired destination are as follows: the control module obtains the positioning data according to the desired destination, obtains the detection time data according to the time when the user inputs the desired destination, and combines the positioning data and the detection time data to form the user location data;

[0044] Before the control module transmits at least one user location data and at least one user information corresponding to the user location data to the cloud, the method also includes: deleting the user location data when the difference between the current time and the detection time data is less than the timeliness value.

[0045] Since users may be on long business trips or travel frequently, the positioning data will often change. Therefore, setting the detection time data can automatically delete invalid data and avoid redundant information reminders.

[0046] As a further improvement of the present invention, the control module obtains the detection time data according to the time of the destination that the user wants to go to, and sets the detection time data to a deletion-free state;

[0047] When deleting user location data, if the detection time data is in the deletion-free state, the deletion of the user location data is cancelled.

[0048] Since it may take a long time for users to set off after setting the place they want to go, setting up a no-deletion status allows users to always stay aware of the information.

[0049] As a further improvement of the present invention, the specific steps of translating and preprocessing the meteorological information data corresponding to the Chinese warning level data to obtain the unified warning translation data in step S3 include: submitting the meteorological information data corresponding to the Chinese warning level data to the Google Translate API to obtain the unified warning translation data.

[0050] As a further improvement of the present invention, the specific steps of extracting the location, disaster type and expected time of disaster occurrence from the unified translation data of the warning by the server through natural language processing technology in step S4 include:

[0051] S41, performing translation error correction processing on the warning unified translation data by natural language processing technology to obtain warning error correction translation data;

[0052] S42. Perform text preprocessing, word segmentation, part-of-speech tagging, entity recognition and entity extraction on the warning error correction translation data in sequence, so as to obtain the location, disaster type and estimated time of occurrence of the disaster.

[0053] First, the texts or videos of various countries are recognized and translated through the Google Translate framework. Since a large number of translation errors will occur after translation, translation error correction is required to prevent obvious deviations in the subsequent extracted physical locations.

[0054] As a further improvement of the present invention, the specific steps of performing translation error correction processing on the warning unified translation data by natural language processing technology in step S41 to obtain the warning error correction translation data include:

[0055] S411. Detect and mark grammatical errors in the warning unified translation data through the LanguageTool grammar checker, detect and mark spelling errors in the warning unified translation data through the PySpellChecker spell checker, and detect and mark unreasonable sentence structures through the Spacy dependency syntax analysis tool;

[0056] S412. Automatically correct the marked locations through a Seq2Seq sequence-to-sequence model.

[0057] By using the LanguageTool grammar checker, PySpellChecker spell checker, and Spacy dependency syntax analyzer, we can quickly find errors in the text, and then automatically correct them through the Seq2Seq sequence-to-sequence model. If we do not first use the tool to detect and mark the text, the Seq2Seq sequence-to-sequence model will have to automatically correct the entire content, which is a huge workload.

[0058] As a further improvement of the present invention, after extracting entities from the news translation correction data set in step S42, the method further includes: correcting the extracted entity locations through the Wikipedia knowledge base.

[0059] The Wikipedia knowledge base contains standard nouns, such as academic proper nouns and places. If after extracting a physical place, it is found that the place does not exist in the Wikipedia knowledge base, a similar place will be selected for correction based on the similarity of pronunciation. This is because, in weather warning reports, places are usually described in order from large to small or vice versa, such as 'landing in the south of City B, Province A'. Even if the report focuses on a smaller place, such as the south of City B, it will inevitably mention a larger place that contains it, such as Province A. This rule is more obvious, especially when the subject of the report is associated with a specific geographical location; therefore, the Wikipedia knowledge base should be able to find physical places that match or are related to the places mentioned in the report.

[0060] As a further improvement of the present invention, in step S42, the warning error correction translation data is sequentially subjected to text preprocessing, word segmentation, part-of-speech tagging, entity recognition and entity extraction, so as to obtain the location, disaster type and expected time of disaster occurrence. The specific steps are: unifying the digital format in the warning error correction translation data and removing special symbols, dividing the text into multiple words through a word segmenter, and tagging each word with a part-of-speech, identifying entities through the Spacy named entity recognition tool, and extracting the entity location, entity disaster type and entity disaster expected time of occurrence, so as to obtain the location, disaster type and expected time of disaster occurrence.

[0061] As a further improvement of the present invention, the warning level database includes a plurality of warning level data of other countries corresponding to the warning level standards of the corresponding countries and a plurality of Chinese warning level data corresponding one-to-one to the warning level data of other countries.

Claims

1. A method for determining and associating a specific event with a group, characterized in that: It includes a cloud and a user end, wherein the user end includes a plurality of positioning modules corresponding to the users one by one, a plurality of control modules corresponding to the users one by one, and a plurality of display modules corresponding to the users one by one, and the cloud includes a server; The method comprises the following steps: S1. The positioning module detects the user's position according to the standard positioning detection frequency preset in the control module to form user position data, and the control module transmits at least one user position data and at least one user information corresponding to the user position data to the cloud; S2. The server presets a standard location range value. If the distance between different user location data is smaller than the standard location range value, the user information corresponding to the user location data is integrated into one user group, and the remaining user information is a separate user group, thereby obtaining multiple user groups associated with the user location data one by one; S3. The server connects to the websites of meteorological bureaus of various countries and obtains multiple meteorological information data. The server is preset with multiple warning level databases corresponding to different countries. The meteorological information data includes meteorological warning level data. The server converts the meteorological warning level data in the meteorological information data into Chinese warning level data according to China's warning level standards through the warning level database corresponding to the country. When there is Chinese warning level data greater than or equal to the warning reminder level preset in the server, the meteorological information data corresponding to the Chinese warning level data is translated and preprocessed to obtain the unified warning translation data; S4. The server extracts the location, disaster type and expected time of disaster occurrence from the unified translation data of the warning through natural language processing technology. When the distance between a location and a user's location data is less than the standard location range value, the expected time of disaster occurrence and disaster type of the corresponding location are sent to all users in the user group corresponding to the user's location data, and displayed through the display module corresponding to the user.

2. The method for determining and associating specific events with groups according to claim 1, characterized in that: The user end also includes a plurality of input modules corresponding to the users one by one; After the positioning module detects the user's position according to the standard positioning detection frequency preset in the control module in step S1 to form the user position data, the method further includes: the user can input the desired destination through the input module, and the control module generates the user position data according to the desired destination.

3. The method for determining and associating specific events with groups according to claim 2, characterized in that: User location data includes positioning data and detection time data, and the control module presets a time-limited value; In step S1, the specific steps of the positioning module detecting the user's position according to the standard positioning detection frequency preset in the control module to form the user's position data are as follows: the positioning module detects the user's position according to the standard positioning detection frequency preset in the control module to obtain positioning data, and the positioning module detects the user's position and records the current detection time to obtain detection time data; the positioning data and the detection time data are combined to form the user's position data; The specific steps of the control module generating the user location data according to the desired destination are as follows: the control module obtains the positioning data according to the desired destination, obtains the detection time data according to the time when the user inputs the desired destination, and combines the positioning data and the detection time data to form the user location data; Before the control module transmits at least one user location data and at least one user information corresponding to the user location data to the cloud, the method also includes: deleting the user location data when the difference between the current time and the detection time data is less than the timeliness value.

4. The method for determining and associating specific events with groups according to claim 3, characterized in that: The control module obtains the detection time data according to the time of the destination that the user wants to go to, and sets the detection time data to a deletion-free state; When deleting user location data, if the detection time data is in the deletion-free state, the deletion of the user location data is cancelled.

5. The method for determining and associating specific events with groups according to claim 1, characterized in that: The specific steps of translating and preprocessing the meteorological information data corresponding to the Chinese warning level data to obtain the unified warning translation data in step S3 include: submitting the meteorological information data corresponding to the Chinese warning level data to Google Translate API to obtain the unified warning translation data.

6. The method for determining and associating specific events with groups according to claim 1, characterized in that: In step S4, the server extracts the location, disaster type, and estimated time of disaster occurrence from the unified translation data of the warning using natural language processing technology. The specific steps include: S41, performing translation error correction processing on the warning unified translation data by natural language processing technology to obtain warning error correction translation data; S42. Perform text preprocessing, word segmentation, part-of-speech tagging, entity recognition and entity extraction on the warning error correction translation data in sequence, so as to obtain the location, disaster type and estimated time of occurrence of the disaster.

7. The method for determining and associating specific events with groups according to claim 6, characterized in that: In step S41, the specific steps of performing translation error correction processing on the warning unified translation data by using natural language processing technology to obtain the warning error-corrected translation data include: S411. Detect and mark grammatical errors in the warning unified translation data through the LanguageTool grammar checker, detect and mark spelling errors in the warning unified translation data through the PySpellChecker spell checker, and detect and mark unreasonable sentence structures through the Spacy dependency syntax analysis tool; S412. Automatically correct the marked locations through a Seq2Seq sequence-to-sequence model.

8. The method for determining and associating specific events with groups according to claim 6, characterized in that: After extracting entities from the news translation correction data set in step S42, the method further includes: correcting the extracted entity locations through the Wikipedia knowledge base.

9. The method for determining and associating specific events with groups according to claim 7, characterized in that: In step S42, the warning error correction translation data is sequentially subjected to text preprocessing, word segmentation, part-of-speech tagging, entity recognition and entity extraction, so as to obtain the location, disaster type and expected time of disaster occurrence. The specific steps are as follows: unify the digital format in the warning error correction translation data and remove special symbols, divide the text into multiple words through a word segmenter, and perform part-of-speech tagging on each word, identify entities through the Spacy named entity recognition tool, and extract entity location, entity disaster type and entity disaster expected time of occurrence, so as to obtain the location, disaster type and expected time of disaster occurrence.

10. The method for determining and associating specific events with groups according to claim 1, characterized in that: The warning level database includes a plurality of warning level data of other countries corresponding to the warning level standards of the corresponding countries and a plurality of Chinese warning level data corresponding one-to-one to the warning level data of other countries.

Images