Emergency call processing method and device

Abstract

The present invention discloses an emergency call processing method and device, wherein the method comprises: obtaining real-time emergency call data; using AML technology to enable the positioning service of the caller's mobile phone according to the caller's mobile phone number, and receiving the caller's location data sent by the caller's mobile phone in the form of a text message or data packet; inputting the emergency call type data and the caller's location data into an emergency call recognition model, and outputting the emergency call recognition result; matching the emergency call recognition result with the historical emergency call level and dispatch police force information of the emergency call event stored in the emergency call database, and outputting the corresponding emergency call processing deployment information according to the matching result. The present invention can achieve accurate positioning of emergency calls, and perform emergency call processing according to the emergency call processing deployment information, thereby improving the efficiency of emergency call processing.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an emergency call processing method and device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] The existing emergency call processing method can only inform nearby police officers that a case has occurred and they need to go to the scene quickly when issuing an emergency call, but it cannot accurately locate the location of the case, nor can it obtain detailed information about the crime scene in a timely manner and formulate an emergency call processing plan. Therefore, an emergency call processing method is urgently needed to solve the above problems. Summary of the Invention

[0004] An embodiment of the present invention provides an emergency call processing method for accurately locating emergency calls, determining emergency call processing deployment information, and improving emergency call processing efficiency. The method includes:

[0005] Obtain real-time emergency call data; emergency call data includes: the caller's phone number and emergency call type data;

[0006] Based on the caller's mobile phone number, the advanced mobile location AML technology is used to enable the caller's mobile phone positioning service, and the caller's location is located through GPS satellite positioning technology to obtain the caller's location data;

[0007] If the positioning fails, the location of the alarm person is re-positioned according to the service set identifier SSID of the WiFi wireless network to obtain the location data of the alarm person;

[0008] If the positioning fails again, the location data of the mobile communication base station is sent as the location data of the alarm person;

[0009] If the positioning is successful, the alarm person's location data will be received via SMS or data packet sent by the alarm person's mobile phone;

[0010] The emergency call type data and the caller's location data are input into the emergency call recognition model, which outputs an emergency call recognition result. The emergency call recognition result includes the recognized emergency call level and the dispatched police force information for the emergency call event. The emergency call recognition model is constructed by combining the BERT model with the TextRNN model to construct a BERT-TextCNN model, and the BERT-TextCNN model is trained as follows:

[0011] Obtain historical emergency call data, caller location data, and actual emergency call results; actual emergency call results include historical emergency call levels and dispatch police force information for emergency call events;

[0012] Extract features from historical emergency call data, caller location data, and actual emergency call results to obtain feature data;

[0013] Based on the feature data, construct sample data to generate training data sets and test data sets;

[0014] Use the training dataset to train the BERT-TextCNN model, and use the test dataset to test the trained BERT-TextCNN model;

[0015] When the test passes, the trained BERT-TextCNN is determined as the emergency call recognition model;

[0016] The emergency call recognition result is matched with the historical emergency call level and dispatch police force information of the emergency call event stored in the emergency call database, and the corresponding emergency call processing deployment information is output according to the matching result.

[0017] An embodiment of the present invention further provides an emergency call processing device for accurately locating emergency calls, determining emergency call processing deployment information, and improving emergency call processing efficiency. The device includes:

[0018] Emergency call data acquisition module, used to obtain real-time emergency call data; emergency call data includes: the alarm person's mobile phone number and emergency call type data;

[0019] The first positioning module is used to enable the positioning service of the alarm person's mobile phone based on the alarm person's mobile phone number using the advanced mobile location AML technology, locate the alarm person's position through GPS satellite positioning technology, and obtain the alarm person's location data;

[0020] The second positioning module is used to re-position the alarm person's position according to the service set identifier SSID of the WiFi wireless network if the positioning fails, and obtain the alarm person's location data;

[0021] The location data sending module of the mobile communication base station is used to send the location data of the mobile communication base station as the location data of the alarm person if the positioning fails again;

[0022] The alarm person's location data acquisition module is used to receive the alarm person's location data sent by the alarm person's mobile phone in the form of text messages or data packets if the positioning is successful;

[0023] The emergency call recognition result acquisition module is used to input the emergency call type data and the caller's location data into the emergency call recognition model and output the emergency call recognition result; the emergency call recognition result includes the recognized emergency call level and the dispatch police force information of the emergency call event. The emergency call recognition model is constructed by combining the BERT model with the TextRNN model to construct a BERT-TextCNN model, and the BERT-TextCNN model is trained as follows:

[0024] Obtain historical emergency call data, caller location data, and actual emergency call results; actual emergency call results include historical emergency call levels and dispatch police force information for emergency call events;

[0025] Extract features from historical emergency call data, caller location data, and actual emergency call results to obtain feature data;

[0026] Based on the feature data, construct sample data to generate training data sets and test data sets;

[0027] Use the training dataset to train the BERT-TextCNN model, and use the test dataset to test the trained BERT-TextCNN model;

[0028] When the test passes, the trained BERT-TextCNN is determined as the emergency call recognition model;

[0029] The emergency call processing deployment information output module is used to match the emergency call recognition results with the historical emergency call levels and dispatch police force information of emergency call events stored in the emergency call database, and output the corresponding emergency call processing deployment information based on the matching results.

[0030] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned emergency call processing method when executing the computer program.

[0031] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the emergency call processing method described above is implemented.

[0032] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the emergency call processing method is implemented.

[0033] In an embodiment of the present invention, real-time emergency call data is obtained; the emergency call data includes: the mobile phone number of the caller and the emergency call type data; according to the mobile phone number of the caller, the positioning service of the caller's mobile phone is enabled by using the advanced mobile location AML technology, and the position of the caller is located by using the GPS satellite positioning technology to obtain the position data of the caller; if the positioning fails, the position of the caller is re-located according to the service set identifier SSID of the WiFi wireless network to obtain the position data of the caller; if the positioning fails again, the position data of the mobile communication base station is sent as the position data of the caller; if the positioning is successful, the position data of the caller sent by the caller's mobile phone in the form of a text message or a data packet is received; the emergency call type data and the caller's position data are input into the emergency call recognition model, and the emergency call recognition result is output; the emergency call recognition model is a BERT model combined with a TextRNN model to construct a BERT-TextCNN model; the emergency call recognition result is matched with the historical emergency call level and the dispatch police force information of the emergency call event stored in the emergency call database, and the corresponding emergency call processing deployment information is output according to the matching result. Thus, the emergency call can be accurately located through AML technology, GPS satellite positioning technology, and the service set identifier SSID of the WiFi wireless network, and the emergency call can be processed according to the emergency call processing deployment information, thereby improving the efficiency of emergency call processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0035] Figure 1 Flowchart of an emergency call processing method according to an embodiment of the present invention;

[0036] Figure 2 This is a flowchart of the BERT-TextCNN model training in an embodiment of the present invention;

[0037] Figure 3 Flowchart showing the output of emergency call processing deployment information in an embodiment of the present invention;

[0038] Figure 4 Schematic diagram of an emergency call processing device according to an embodiment of the present invention;

[0039] Figure 5 is a schematic diagram of a specific emergency call processing device in an embodiment of the present invention;

[0040] Figure 6 A schematic diagram of a positioning failure information prompt in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0042] Figure 1 Flowchart of an emergency call processing method according to an embodiment of the present invention, the method comprising:

[0043] Step 101: Acquire real-time emergency call data; the emergency call data includes: the alarm person's mobile phone number and the emergency call type data;

[0044] Step 102: Based on the mobile phone number of the caller, the advanced mobile location AML technology is used to enable the positioning service of the caller's mobile phone, and the position of the caller is located through GPS satellite positioning technology to obtain the caller's location data;

[0045] Step 1031: If the positioning fails, the location of the caller is re-positioned according to the service set identifier (SSID) of the WiFi wireless network to obtain the location data of the caller;

[0046] Step 104: If the positioning fails again, the location data of the mobile communication base station is sent as the location data of the alarm person;

[0047] Step 1032: If the positioning is successful, the location data of the alarm person sent by the alarm person's mobile phone in the form of a text message or data packet is received;

[0048] Step 105: Input the emergency call type data and the caller location data into the emergency call recognition model, and output the emergency call recognition result; the emergency call recognition result includes the recognized emergency call level and the dispatched police force information for the emergency call event; the emergency call recognition model is constructed by combining the BERT model with the TextRNN model to construct a BERT-TextCNN model, and the BERT-TextCNN model is trained as follows:

[0049] Obtain historical emergency call data, caller location data, and actual emergency call results; actual emergency call results include historical emergency call levels and dispatch police force information for emergency call events;

[0050] Extract features from historical emergency call data, caller location data, and actual emergency call results to obtain feature data;

[0051] Based on the feature data, construct sample data to generate training data sets and test data sets;

[0052] Use the training dataset to train the BERT-TextCNN model, and use the test dataset to test the trained BERT-TextCNN model;

[0053] When the test passes, the trained BERT-TextCNN is determined as the emergency call recognition model;

[0054] Step 106 : Match the emergency call recognition result with the historical emergency call levels and dispatch police force information of emergency call events stored in the emergency call database, and output corresponding emergency call processing deployment information according to the matching result.

[0055] Each step is described in detail below.

[0056] In step 101, real-time emergency call data is obtained; the emergency call data includes: the caller's mobile phone number and the emergency call type data.

[0057] In step 102, the location service of the alarming person's mobile phone is enabled using the Advanced Mobile Location (AML) technology based on the alarming person's mobile phone number, and the alarming person's location is located using the GPS satellite positioning technology to obtain the alarming person's location data.

[0058] In step 1031, if the positioning fails, the location of the person making the call is re-positioned according to the service set identifier SSID of the WiFi wireless network to obtain the location data of the person making the call.

[0059] In a specific embodiment, it also includes:

[0060] If the location data of the person making the call cannot be obtained through one of the methods or any combination of GPS satellite positioning technology, WiFi wireless network SSID identification and mobile communication base station location data, the person making the call will receive a positioning failure prompt message automatically sent by the person making the call's mobile phone.

[0061] In step 104, if the positioning fails again, the location data of the mobile communication base station is sent as the location data of the alarm person.

[0062] In a specific embodiment, when the alarm person reports an alarm through a mobile phone terminal, the mobile phone terminal connects to the nearest mobile communication base station where the alarm person is located to complete voice networking, location data and signal transmission, and transmits the location data to the emergency call processing system through the mobile communication base station.

[0063] In step 1032, if the positioning is successful, the location data of the alarm person sent by the alarm person's mobile phone in the form of a text message or a data packet is received.

[0064] like Figure 2 As shown, in step 105, the emergency call type data and the caller location data are input into the emergency call recognition model, and the emergency call recognition result is output; the emergency call recognition result includes the recognized emergency call level and the dispatch police force information of the emergency call event; the emergency call recognition model is constructed by combining the BERT model with the TextRNN model to construct a BERT-TextCNN model, and the BERT-TextCNN model is trained as follows:

[0065] Step 201: Acquire historical emergency call data, caller location data, and actual emergency call results; the actual emergency call results include historical emergency call levels and dispatch police force information for emergency call events;

[0066] Step 202: extract features from historical emergency call data, caller location data, and actual emergency call results to obtain feature data.

[0067] Step 203: construct sample data based on the feature data to generate a training data set and a test data set;

[0068] Step 204: train the BERT-TextCNN model using the training dataset, and test the trained BERT-TextCNN model using the test dataset.

[0069] Step 205: When the test passes, the trained BERT-TextCNN is determined as the emergency call recognition model.

[0070] In a specific embodiment, during the construction of BERT-TextCNN, the output of the last layer of the BERT network is used as the input of the TextCNN network. The TextCNN network fits the output feature data of the BERT network to minimize the difference in the output feature data of the BERT network and the TextCNN network.

[0071] In a specific embodiment, the severity and urgency of the matter can be judged and the police force required can be estimated based on the description of the case by the caller.

[0072] In one embodiment, before training the emergency call recognition model, the method further includes:

[0073] Perform data cleaning, data transformation and data reduction on historical emergency call data and alarm person location data.

[0074] In step 106, the emergency call recognition result is matched with the historical emergency call levels and dispatch police force information of emergency call events stored in the emergency call database, and corresponding emergency call processing deployment information is output according to the matching result.

[0075] like Figure 3 As shown, in one embodiment, the emergency call recognition result is matched with the historical emergency call level and dispatch police force information of the emergency call event stored in the emergency call database, and the corresponding emergency call processing deployment information is output according to the matching result, including:

[0076] Step 301, matching the emergency call recognition result with the historical emergency call levels and dispatch police force information of emergency call events stored in the emergency call database to determine at least one emergency call handling deployment recommendation information;

[0077] Step 302: Outputting final emergency call processing deployment information according to the selection instruction issued by the police officer terminal in response to at least one emergency call processing deployment suggestion information.

[0078] The embodiment of the present invention also provides an emergency call processing device, as described in the following embodiment. Since the principle of solving the problem of the device is similar to that of the emergency call processing method, the implementation of the device can refer to the implementation of the emergency call processing method, and the repeated parts will not be repeated. Figure 4 As shown, the device includes:

[0079] Emergency call data acquisition module 401 is used to obtain real-time emergency call data; the emergency call data includes: the alarm person's mobile phone number and the emergency call type data;

[0080] The first positioning module 402 is used to enable the positioning service of the alarming person's mobile phone based on the alarming person's mobile phone number using the advanced mobile location AML technology, locate the alarming person's position using the GPS satellite positioning technology, and obtain the alarming person's location data;

[0081] The second positioning module 403 is used to perform a second positioning of the alarm person's location according to the service set identifier SSID of the WiFi wireless network if the positioning fails, and obtain the alarm person's location data;

[0082] The location data sending module 404 of the mobile communication base station is used to send the location data of the mobile communication base station as the location data of the alarm person if the positioning fails again;

[0083] The alarm person location data acquisition module 405 is used to receive the alarm person location data sent by the alarm person's mobile phone in the form of text messages or data packets if the positioning is successful;

[0084] Emergency call recognition result acquisition module 406 is used to input the emergency call type data and the caller location data into the emergency call recognition model and output the emergency call recognition result; the emergency call recognition result includes the recognized emergency call level and the dispatch police force information of the emergency call event. The emergency call recognition model is constructed by combining the BERT model with the TextRNN model to construct a BERT-TextCNN model, and the BERT-TextCNN model is trained as follows:

[0085] Obtain historical emergency call data, caller location data, and actual emergency call results; actual emergency call results include historical emergency call levels and dispatch police force information for emergency call events;

[0086] Extract features from historical emergency call data, caller location data, and actual emergency call results to obtain feature data;

[0087] Based on the feature data, construct sample data to generate training data sets and test data sets;

[0088] Use the training dataset to train the BERT-TextCNN model, and use the test dataset to test the trained BERT-TextCNN model;

[0089] When the test passes, the trained BERT-TextCNN is determined as the emergency call recognition model;

[0090] The emergency call processing deployment information output module 407 is used to match the emergency call recognition result with the historical emergency call level and dispatch police force information of the emergency call event stored in the emergency call database, and output the corresponding emergency call processing deployment information according to the matching result.

[0091] like Figure 5 As shown, in one embodiment, a data pre-processing module 501 is further included, which is used to:

[0092] Perform data cleaning, data transformation and data reduction on historical emergency call data and alarm person location data.

[0093] like Figure 6 As shown, in one embodiment, a positioning failure information prompt module 601 is further included, which is specifically used to:

[0094] If the location data of the person making the call cannot be obtained through one of the methods or any combination of GPS satellite positioning technology, WiFi wireless network SSID identification and mobile communication base station location data, the person making the call will receive a positioning failure prompt message automatically sent by the person making the call's mobile phone.

[0095] In one embodiment, the emergency call processing deployment information output module 407 is specifically configured to:

[0096] Matching the emergency call recognition result with the historical emergency call levels and dispatch police force information of the emergency call events stored in the emergency call database to determine at least one emergency call handling deployment recommendation information;

[0097] According to the selection instruction issued by the police officer terminal for at least one emergency call processing deployment suggestion information, the final emergency call processing deployment information is output.

[0098] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned emergency call processing method when executing the computer program.

[0099] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the emergency call processing method described above is implemented.

[0100] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the emergency call processing method is implemented.

[0101] In an embodiment of the present invention, real-time emergency call data is obtained; the emergency call data includes: the mobile phone number of the caller and the emergency call type data; according to the mobile phone number of the caller, the positioning service of the caller's mobile phone is enabled by using the advanced mobile location AML technology, and the position of the caller is located by using the GPS satellite positioning technology to obtain the position data of the caller; if the positioning fails, the position of the caller is re-located according to the service set identifier SSID of the WiFi wireless network to obtain the position data of the caller; if the positioning fails again, the position data of the mobile communication base station is sent as the position data of the caller; if the positioning is successful, the position data of the caller sent by the caller's mobile phone in the form of a text message or a data packet is received; the emergency call type data and the caller's position data are input into the emergency call recognition model, and the emergency call recognition result is output; the emergency call recognition model is a BERT model combined with a TextRNN model to construct a BERT-TextCNN model; the emergency call recognition result is matched with the historical emergency call level and the dispatch police force information of the emergency call event stored in the emergency call database, and the corresponding emergency call processing deployment information is output according to the matching result. Thus, the emergency call can be accurately located through AML technology, GPS satellite positioning technology, and the service set identifier SSID of the WiFi wireless network, and the emergency call can be processed according to the emergency call processing deployment information, thereby improving the efficiency of emergency call processing.

[0102] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0103] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0106] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for handling an emergency call, characterized in that: include: Access real-time emergency call data; Emergency call data includes: the caller’s mobile phone number and emergency call type data; Based on the caller's mobile phone number, the advanced mobile location AML technology is used to enable the caller's mobile phone positioning service, and the caller's location is located through GPS satellite positioning technology to obtain the caller's location data; If the positioning fails, the location of the alarm person is re-positioned according to the service set identifier SSID of the WiFi wireless network to obtain the location data of the alarm person; If the positioning fails again, the location data of the mobile communication base station is sent as the location data of the alarm person; If the positioning is successful, the alarm person's location data will be received via SMS or data packet sent by the alarm person's mobile phone; The emergency call type data and the caller's location data are input into the emergency call recognition model, which outputs an emergency call recognition result. The emergency call recognition result includes the recognized emergency call level and the dispatched police force information for the emergency call event. The emergency call recognition model is constructed by combining the BERT model with the TextRNN model to construct a BERT-TextCNN model, and the BERT-TextCNN model is trained as follows: Obtain historical emergency call data, caller location data, and actual emergency call results; actual emergency call results include historical emergency call levels and dispatch police force information for emergency call events; Extract features from historical emergency call data, caller location data, and actual emergency call results to obtain feature data; Based on the feature data, construct sample data to generate training data sets and test data sets; Use the training dataset to train the BERT-TextCNN model, and use the test dataset to test the trained BERT-TextCNN model; When the test passes, the trained BERT-TextCNN is determined as the emergency call recognition model; The emergency call recognition result is matched with the historical emergency call level and dispatch police force information of the emergency call event stored in the emergency call database, and the corresponding emergency call processing deployment information is output according to the matching result.

2. The method according to claim 1, wherein Before training the emergency call recognition model, also include: Perform data cleaning, data transformation and data reduction on historical emergency call data and alarm person location data.

3. The method according to claim 1, wherein Also includes: If the location data of the person making the call cannot be obtained through one of the methods or any combination of GPS satellite positioning technology, WiFi wireless network SSID identification and mobile communication base station location data, the person making the call will receive a positioning failure prompt message automatically sent by the person making the call's mobile phone.

4. The method according to claim 1, wherein The emergency call recognition result is matched with the historical emergency call level and dispatch police force information of the emergency call event stored in the emergency call database, and the corresponding emergency call processing deployment information is output according to the matching result, including: Matching the emergency call recognition result with the historical emergency call levels and dispatch police force information of the emergency call events stored in the emergency call database to determine at least one emergency call handling deployment recommendation information; According to the selection instruction issued by the police officer terminal for at least one emergency call processing deployment suggestion information, the final emergency call processing deployment information is output.

5. An emergency call processing device, characterized in that: include: Emergency call data acquisition module, used to obtain real-time emergency call data; Emergency call data includes: the caller’s mobile phone number and emergency call type data; The first positioning module is used to enable the positioning service of the alarm person's mobile phone based on the alarm person's mobile phone number using the advanced mobile location AML technology, locate the alarm person's position through GPS satellite positioning technology, and obtain the alarm person's location data; The second positioning module is used to re-position the alarm person's position according to the service set identifier SSID of the WiFi wireless network if the positioning fails, and obtain the alarm person's location data; The location data sending module of the mobile communication base station is used to send the location data of the mobile communication base station as the location data of the alarm person if the positioning fails again; The alarm person's location data acquisition module is used to receive the alarm person's location data sent by the alarm person's mobile phone in the form of text messages or data packets if the positioning is successful; The emergency call recognition result acquisition module is used to input the emergency call type data and the caller's location data into the emergency call recognition model and output the emergency call recognition result; the emergency call recognition result includes the recognized emergency call level and the dispatch police force information of the emergency call event. The emergency call recognition model is constructed by combining the BERT model with the TextRNN model to construct a BERT-TextCNN model, and the BERT-TextCNN model is trained as follows: Obtain historical emergency call data, caller location data, and actual emergency call results; actual emergency call results include historical emergency call levels and dispatch police force information for emergency call events; Extract features from historical emergency call data, caller location data, and actual emergency call results to obtain feature data; Based on the feature data, construct sample data to generate training data sets and test data sets; Use the training dataset to train the BERT-TextCNN model, and use the test dataset to test the trained BERT-TextCNN model; When the test passes, the trained BERT-TextCNN is determined as the emergency call recognition model; The emergency call processing deployment information output module is used to match the emergency call recognition results with the historical emergency call levels and dispatch police force information of emergency call events stored in the emergency call database, and output the corresponding emergency call processing deployment information based on the matching results.

6. The device according to claim 5, characterized in that It also includes a data preprocessing module for: Perform data cleaning, data transformation and data reduction on historical emergency call data and alarm person location data.

7. The device according to claim 5, characterized in that It also includes a positioning failure information prompt module, which is specifically used to: If the location data of the person making the call cannot be obtained through one of the methods or any combination of GPS satellite positioning technology, WiFi wireless network SSID identification and mobile communication base station location data, the person making the call will receive a positioning failure prompt message automatically sent by the person making the call's mobile phone.

8. The device according to claim 5, wherein The emergency call processing deployment information output module is specifically used to: Matching the emergency call recognition result with the historical emergency call levels and dispatch police force information of the emergency call events stored in the emergency call database to determine at least one emergency call handling deployment recommendation information; According to the selection instruction issued by the police officer terminal for at least one emergency call processing deployment suggestion information, the final emergency call processing deployment information is output.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images