CN113590880A

CN113590880A - Fire rescue positioning method and device, computer equipment and storage medium

Info

Publication number: CN113590880A
Application number: CN202110896562.9A
Authority: CN
Inventors: 谭海强; 钟伟波; 李伟; 李杰灏
Original assignee: Guangdong Power Grid Co Ltd; Dongguan Power Supply Bureau of Guangdong Power Grid Co Ltd
Current assignee: Guangdong Power Grid Co Ltd; Dongguan Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority date: 2021-08-05
Filing date: 2021-08-05
Publication date: 2021-11-02

Abstract

The embodiment of the invention provides a positioning method and device for fire rescue, computer equipment and a storage medium. The method comprises the following steps: receiving an alarm request sent by an applet running in an instant messaging tool, wherein the alarm request comprises video data collected by the applet and a first position where the applet is positioned; identifying an object in which an accident occurs in the video data as a target object; calculating a second location in the video data where the target object is located based on the first location; converging a plurality of the second locations on an electronic map to a building matching the incident to determine that the incident occurred in the building. The fire rescue positioning method provided by the embodiment of the invention realizes accurate positioning of disaster situations and information sharing of disaster situations, and further can carry out more targeted rescue.

Description

Fire rescue positioning method and device, computer equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of instant positioning, in particular to a positioning method and device for fire rescue, computer equipment and a storage medium.

Background

With the development of society, the quality of life of people is continuously improved, but with the adoption of highly dense houses, crowded traffic, highly dangerous fire, wastefully polluted nature and the like, various safety accidents occur every day around the country, and fire rescue teams face different rescue tasks every day.

At present, the main approach of crowd fire alarm is mainly telephone alarm, inform the command center who is responsible for fire rescue the position of occurence of an accident, the condition of accident scene etc. to the mode of voice conversation, this mode is limited to the cognitive and expression ability restriction of warning person, the information that the warning person described the accident under emergency is comparatively fuzzy, especially to accidents such as conflagration, it is comparatively dangerous near the place of accident, the general position far away from the accident of crowd just reports to the police, position description to occurence of an accident is mostly vague, lead to the fire rescue personnel to spend more time on the position of location accident emergence, know vaguely to the detailed condition of disaster, influence the development of rescue action.

Disclosure of Invention

Therefore, the embodiment of the invention provides a positioning method and device for fire rescue, computer equipment and a storage medium, which solve the defect of fuzzy positioning of disaster places in the existing fire operation.

In a first aspect, an embodiment of the present invention provides a method for positioning fire rescue, including:

receiving an alarm request sent by an applet running in an instant messaging tool, wherein the alarm request comprises video data collected by the applet and a first position where the applet is positioned;

identifying an object in which an accident occurs in the video data as a target object;

calculating a second location in the video data where the target object is located based on the first location;

converging a plurality of the second locations on an electronic map to a building matching the incident to determine that the incident occurred in the building.

Further, the converging the plurality of second locations on the electronic map to a building matching the incident to determine that the incident occurred in the building includes:

querying a building matched with the accident on an electronic map;

determining a building area in which the building is located on the electronic map;

calculating matching degrees between a plurality of second positions and the building area;

and selecting the building corresponding to the building area with the highest matching degree to determine that the accident occurs in the building.

Further, the calculating a matching degree between the plurality of second positions and the building area includes:

counting the number of the second positions contained in the building area;

and calculating the ratio of the number of the second positions to the area of the building area as the matching degree between the plurality of second positions and the building area.

Further, the calculating a matching degree between the plurality of second positions and the building area further includes:

fitting a plurality of said second locations to an accident area;

counting the accident areas contained in the building areas as target areas;

calculating a ratio between an area of the target area and an area of the building area as a degree of matching between the plurality of second positions and the building area.

Further, the identifying, in the video data, an object in which an accident occurs, as a target object, includes:

reading audio data in the video data;

performing voice recognition on the audio data to obtain text information;

searching preset keywords in the text information to represent accidents;

searching a target detection model trained for the accident;

and inputting the video data into the target detection model by taking the accident as a target so as to detect an object of the accident in the video data as a target object.

Further, the alert request also has a location identified by the applet to capture the video data in which the second location of the target object is calculated based on the first location, including:

calculating a distance of separation between the target object and the first location in the video data;

and adding the distance along the direction on the basis of the first position to obtain a second position of the target object.

Further, accident information is generated according to the accident and the second position, and the accident information has a time period;

and pushing the accident information to other instant communication tools through a public number or a service number matched with the small program, wherein the instant communication tools are used for loading the small program when the accident information is triggered in the time period.

In a second aspect, an embodiment of the present invention provides a positioning device for fire rescue, including:

the system comprises an alarm request receiving module, a processing module and a display module, wherein the alarm request receiving module is used for receiving an alarm request sent by an applet running in an instant messaging tool, and the alarm request comprises video data acquired by the applet and a first position where the applet is positioned;

the target object identification module is used for identifying an object with an accident in the video data as a target object;

a position determination module to calculate a second position in the video data where the target object is located based on the first position;

a building location module to converge the plurality of second locations on an electronic map to a building matching the incident to determine that the incident occurred in the building.

Further, the target object identification module includes:

the audio data reading module is used for reading audio data in the video data;

the voice recognition module is used for carrying out voice recognition on the audio data to obtain text information;

the keyword searching module is used for searching preset keywords in the text information so as to represent accidents;

a target detection model search module for searching a target detection model trained for the accident;

and the target detection module is used for inputting the video data into the target detection model by taking the accident as a target so as to detect an object of the accident in the video data as a target object.

Further, the location determination module comprises:

a distance calculation module to calculate a distance of a separation between the target object and the first location in the video data;

and the second position acquisition module is used for adding the distance along the direction on the basis of the first position to acquire a second position of the target object.

Further, the building location module includes:

the building query module is used for querying a building matched with the accident on an electronic map;

a building area determining module for determining a building area where the building is located on the electronic map;

a matching degree calculating module, configured to calculate matching degrees between the plurality of second positions and the building area;

and the selection module is used for selecting the building corresponding to the building area with the highest matching degree so as to determine that the accident occurs in the building.

Further, the module for calculating matching degree is configured to include:

the counting module is used for counting the number of the second positions contained in the building area;

and the number ratio module is used for calculating the ratio of the number of the second positions to the area of the building area as the matching degree between the plurality of second positions and the building area.

Further, the module for calculating the matching degree is further configured to:

a fit accident region module for fitting a plurality of said second locations to an accident region;

the target area module is used for counting the accident areas contained in the building areas and taking the accident areas as target areas;

and the area ratio module is used for calculating the ratio of the area of the target area to the area of the building area as the matching degree between the plurality of second positions and the building area.

Optionally, on the basis of the above apparatus, the apparatus further includes:

the time period module is used for generating accident information according to the accident and the second position, and the accident information has a time period;

and the information pushing module is used for pushing the accident information to other instant messaging tools through a public number or a service number matched with the small program, and the instant messaging tools are used for loading the small program when the accident information is triggered in the time period.

In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:

one or more processors;

a memory for storing one or more programs,

when the one or more programs are executed by the one or more processors, the one or more processors implement the method for locating a fire rescue according to the first aspect.

In a fourth aspect, the present invention further provides a storage medium containing computer executable instructions, where the computer program is executed by a processor to implement the method for locating a fire rescue according to the first aspect.

In the embodiment, a user can use the applet in the instant messaging tool for alarming, because the frequency of using the instant messaging tool by the user is high, the applet is embedded in the instant messaging tool, the applet is directly started when an alarm demand exists, the installation is not needed, the alarming efficiency is high, and the first position for positioning the video data collected by the applet and the applet is arranged in the alarm request; the object with the accident is identified in the video data and is used as the target object, so that the target object is automatically identified, the dependence on the user to describe the accident is eliminated, the alarm measure is simplified, and the influence of disordered information on rescue is avoided; calculating a second position where the target object is located based on the first position in the video data, wherein the second position can be ensured to have higher accuracy by positioning the second position based on the first position because the current hardware-based positioning accuracy is high, namely the positioning accuracy of the first position is high; and converging the plurality of second positions to a building matched with the accident on the electronic map to determine that the accident occurs in the building, wherein on one hand, the accident has correlation with the building, the range of the true position of the accident can be narrowed through matching the building with the accident, and the positioning accuracy of the true position of the accident is improved, and on the other hand, the true position of the accident is identified through converging the plurality of second positions, so that the fluctuation influence of the parameters of the collected video data on the second positions is reduced, and the positioning accuracy of the true position of the accident is improved.

Drawings

Fig. 1 is a flowchart of a positioning method for firefighting rescue according to an embodiment of the present invention;

fig. 2 is a flowchart of a positioning method for firefighting rescue according to a second embodiment of the present invention;

fig. 3 is a schematic view of a positioning device for fire rescue according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Example one

Fig. 1 is a flowchart of a fire rescue positioning method according to an embodiment of the present invention, where the embodiment is applicable to a situation where a user uses an applet of an instant messenger to perform a video alarm and automatically identify a location where an accident occurs from a video, so as to converge the location to improve positioning accuracy, the method may be executed by a fire rescue apparatus, the method may be implemented by software and/or hardware, and may be configured in a computer device, such as a server, a workstation, a personal computer, and the like, and specifically includes the following steps:

s101, receiving an alarm request sent by an applet running in the instant messaging tool.

When a disaster accident occurs, a user calls to give an alarm to inform that a disaster address has a large possibility of generating deviation, and meanwhile, the familiarity of the alarm personnel with the disaster address influences the accuracy of the arrival of rescue personnel, so that the rescue personnel needs to communicate with the alarm personnel for a plurality of times during the process of arriving at the scene, and the accurate position is continuously corrected. In addition, due to factors such as road condition change and road accident, the user cannot go to the scene at the first time, and precious time is wasted. Based on the rapid development of a Beidou and GPS (Global Positioning System) satellite Positioning System, an alarm receiving dispatcher can accurately collect corresponding fire rescue force by receiving an alarm request sent by a small program running in an instant communication tool, and avoids delaying warplanes by collecting too little force or avoiding wasting resources by collecting too much force.

The small program running in the instant messaging tool is an application which can be used without downloading or installing, a user can open the application by scanning or searching once, the idea of walking after use is also realized, the user does not need to install too many applications, and the application can be used anywhere without installation or uninstallation.

The alarm request refers to that an alarm person takes pictures or videos near a disaster place through a mobile terminal, records the disaster and uploads the recorded disaster to an applet running in an instant messaging tool, and the alarm request can refer to a plurality of requests or one request, can be sent by a party in the disaster or other requests.

Specifically, the alarm request has video data collected by the small program and a first position located by the small program. The method comprises the steps that a shooting function carried in an applet is applied or a video shot in a mobile terminal is uploaded to the applet, the applet collects data of the video, the video sending place is recorded as a first position by using technologies such as GPS positioning, Beidou satellite positioning, base station positioning, wifi (Wireless-Fidelity) positioning or Bluetooth positioning, and the video data and information of the first position are recorded as main information of an alarm request.

S102, identifying the object with the accident in the video data as a target object.

It is understood that after identifying the video data in the applet, the object in the video is labeled by using pattern recognition technology to model the object in the video where the accident occurred. For the determination of the target object, a judgment may be made according to the content provided by the video, for example, the target object may be a person, an object, an automobile, a river, a building, and the like, which is not limited in this embodiment.

In one embodiment of the present invention, S102 includes the steps of:

step 1021, reading the audio data from the video data.

When a user gives an alarm, the user records the scene situation through shooting, and at the same time, the user can give a certain explanation to the scene situation when shooting a video, for example, the scene where a disaster occurs is described, the severity of the situation is explained, and the like. Therefore, the video data includes a large amount of audio data, and after the video data is identified, the audio data in the video data needs to be read, so as to obtain the audio data therein. Note that, the audio format of the video is stripped, and may be CDA format, WAV waveform audio format, MP3/MP3 Pro format, and so on.

And step 1022, performing voice recognition on the audio data to obtain text information.

The voice recognition technology is utilized to recognize the audio data, text information of the audio data is obtained, the audio data is input, the input audio is preprocessed, and then characteristics of the audio are extracted to obtain the text information of the voice data. Speech Recognition technology, also known as Automatic Speech Recognition (ASR), aims at converting the vocabulary content in human Speech into computer-readable input, such as keystrokes, binary codes or character sequences. Applications of the voice recognition technology include voice dialing, voice navigation, indoor equipment control, voice document retrieval, simple dictation data entry and the like, and the voice recognition technology is combined with other natural language processing technologies such as machine translation and voice synthesis technology, so that more complicated applications can be constructed.

And step 1023, searching preset keywords in the text message to represent the accident.

When a user gives an alarm, the scene is disordered, the contents recorded in the text information are relatively disordered, and some information irrelevant to the disaster situation exists, so that the contents recorded in the text information need to be screened to obtain the key information. Therefore, a large amount of keyword information is preset in the small program running in the instant communication tool in advance, the fast R-CNN, the SSD and the YOLO model are used for modeling the keyword information, the keyword database in the small program is used for screening the acquired text information, and for example, when the keywords of fire, explosion, building jump, car collision, drowning and the like appear in the text, the screened keywords of the fire, explosion, building jump, car collision, drowning and the like are used for representing the occurred accidents.

Step 1024, find the target detection model trained for the accident.

The target detection model is a model obtained by processing an accident object occurring in video data as a target object through a target detection algorithm (such as one-stage algorithm, classic two-stage algorithm, Multi-stage algorithm). Further, in the invention, one target detection model can be trained for one accident, and the same target detection model can be trained for a plurality of accidents. For example, when there is only one alarm request for "fire," a target detection model may be trained for one "fire" incident in the alarm request; when there are multiple alarm requests for "fire", the same target detection model may be trained for the multiple "fire" incidents, and there is no need to train multiple target detection models for the "fire" incidents of multiple alarm requests.

In step 1025, the video data is input into the target detection model with the accident as the target, and the object of the accident is detected in the video data as the target object.

By the method, the screened keywords are used for representing the accident shot by the video, the video data are input into the target detection model for searching, and the object with the accident is detected in the video data and serves as the target object.

And S103, calculating a second position of the target object in the video data based on the first position.

It can be understood that the applet has an automatic positioning function, and provides some map API (Application Programming Interface) for obtaining information such as the geographic location of the current user, where the map API is an API for embedding a map into a web page through JavaScript (or other language), and the API provides a large number of utilities for processing the map and adding contents to the map through various services, so that a map Application with comprehensive functions can be created on a website. Therefore, when shooting or uploading a video to an accident site, the applet automatically positions the first position by calling a map API, after a camera of the mobile terminal shoots, the SLAM (simultaneous localization and mapping) technology can be called, namely, the SLAM obtains relevant information by a motion main body through observation of the environment, and then posture calculation, track estimation and environment mapping are carried out in a multi-sensor fusion and global information fusion mode, and all algorithms of the SLAM are developed around the environment information collected by the sensors. The SLAM can calculate the distance between the video shooting location and the distance between the accident occurrence locations, thereby determining the position of the target object. Further, the distance between the target object and the first position is calculated in the video data, the distance is added along the azimuth on the basis of the first position, after the second position where the target object is located is obtained, the longitude and the latitude of the first position can be determined through the automatic positioning function of the small program, when the target object is very close to the first position, the distance can be calculated by utilizing the Pythagorean theorem, and when the target object is far from the first position, the distance between the target object and the first position can be calculated by utilizing the length of the minor arc of the major circle of the standard spherical surface. And determining a possible area of the target object by taking the first position as a starting point and the calculated distance as a radius, and gradually reducing the range of the second position by taking the area with the calculated distance as the radius as a range on the basis of the first position.

And S104, converging the plurality of second positions to the buildings matched with the accident on the electronic map so as to determine that the accident occurs in the buildings.

For example, in practical operation, if a fire breaks out in a building in a cell, the distance between the target object and the first location is calculated according to the video data, and the distance is added along the azimuth on the basis of the first location to obtain the second location where the target object is located. Illustratively, a building may include a building, a park, a street, a river, etc., where a jump corresponds to a building, a crash corresponds to a street, a drowning corresponds to a river, etc. After the building with the accident and the type of the accident are determined, the fire rescue personnel can designate a rescue route on the electronic map, simultaneously can inquire usable fixed fire fighting facilities in the peripheral range of the disaster according to the accident place, and designate the optimal rescue scheme and prepare the most required equipment in the shortest time.

In one embodiment of the present invention, S104 includes the steps of:

and 1041, inquiring a building matched with the accident on the electronic map.

The electronic map is a system for map making and application, is a map generated by the control of an electronic computer, is a screen map based on a digital cartographic technology, and is a visual real map. The electronic map uses satellite remote sensing technology, namely, the satellite is used for detecting the reflection of the earth surface objects to the electromagnetic waves and the electromagnetic waves emitted by the objects in the space, thereby extracting the information of the objects and completing the remote identification of the objects. When matching an electronic map, a common matching method is a cross-correlation method, which requires correlation operation on each position in a searched image, and may also adopt a sequential detection method, a hierarchical search method, and an edge feature matching method. Scenes with accidents are recorded in the video data, target features can be determined according to the specific scenes, and building groups are matched according to the target features. The accident type corresponding to different buildings is different, namely the buildings have different attributes, so that objects equipped on the buildings and objects in the same row on the buildings are limited, and the accident occurring on the buildings is limited. If a fire disaster occurs in the residential area, the fire disaster is an accident recorded in the video data, and the building is a building matched with the fire disaster; if a drowning event occurs in the pond, the drowning is an accident recorded in the video data, and the pond is a building matched with the drowning event.

And 1042, determining the building area of the building on the electronic map.

According to the matched building of the accident, the area where the building exists can be searched on the electronic map. There will be multiple ROIs (regions of Interest) in the electronic map, so the ROI mapping technique is used to determine the building Region, that is, according to the input image, the ROIs are mapped to the corresponding positions of feature maps (feature maps), the mapped Region is divided into sections (parts) with the same size (the number of sections is the same as the output dimension), and max-pooling operation is performed on each section (part), so that corresponding feature maps (feature maps) with fixed size can be obtained from the frames with different sizes.

And 1043, calculating matching degrees between the plurality of second positions and the building area.

The plurality of building areas provided by the electronic map are obviously not enough to meet the rescue requirement, so that the plurality of building areas are screened, the second position is matched with the plurality of determined building areas one by one, and when the matching is carried out, the matching degree can be calculated by using algorithms such as correlation analysis and classification clustering (K-Means and the like).

When the second position is determined, one way is to count the number of the second positions contained in the building area; and calculating the ratio of the number of the second positions to the area of the building area as the matching degree of the plurality of second positions and the building area.

Specifically, the number of the second positions is counted, the ratio of the number of the second positions to the area of the building area is used as the matching degree, a plurality of matching degrees can be obtained through calculation, the calculated ratio is sorted from large to small by using a quick sorting algorithm, a matching degree table is generated, and the second positions are determined according to the matching degree table.

Alternatively, a plurality of second locations are fitted to the accident region; counting accident areas contained in the building area as target areas; and calculating the ratio of the area of the target area to the area of the building area as the matching degree between the plurality of second positions and the building area.

And fitting the second position into an accident area through a geometric fitting algorithm, counting the number of accident areas contained in the building area on the electronic map, and setting the accident area as a target area. And calculating the area sizes of the target area and the building area by using a mathematical formula, and taking the ratio of the area of the target area to the area of the building area as the matching degree of the second position and the building area. And sorting the calculated ratio from large to small by using a quick sorting algorithm, generating a matching table, and determining a second position according to the matching table.

The method has the advantages that the second position is converged by calculating the matching degree of the second position and the building area, the highest matching degree is finally used as an accident occurrence place, the corresponding relation between the building and the accident is utilized, the accident place can be determined more accurately by accurate calculation, an accurate position is further provided for the development of fire rescue, and targeted rescue actions are implemented.

And step 1044, selecting the building corresponding to the building area with the highest matching degree to determine that the accident occurs in the building. And selecting the buildings with accidents in the building areas with the highest matching values in the matching table, and determining the accidents occurring in the buildings.

Example two

Fig. 2 is a flowchart of a cycle of a fire fighting rescue positioning method according to a second embodiment of the present invention, which is based on the foregoing embodiment and further adds an operation of processing accident information, and the method specifically includes the following steps:

s201, receiving an alarm request sent by an applet running in an instant messaging tool, wherein the alarm request comprises video data acquired by the applet and a first position where the applet is positioned;

s202, identifying an accident object in video data as a target object;

s203, calculating a second position of the target object in the video data based on the first position;

and S204, converging the plurality of second positions to the buildings matched with the accident on the electronic map so as to determine that the accident occurs in the buildings.

S205, generating accident information according to the accident and the second position, wherein the accident information has a time period;

in the embodiment of the invention, the accident information has a time period, namely the accident information needs to be processed in a short time. When the accident has not been processed, the accident is always in a pending state, and when the accident processing is completed, the time period is over. Optionally, the accidents may be classified into an emergency, a relatively urgent state, an urgent state, and the like, the corresponding time periods in different classes are different, and when the accidents in different classes conflict, the accidents in a higher class are prioritized, but the corresponding time periods are not exceeded.

And S206, pushing the accident information to other instant communication tools through the public numbers or service numbers matched with the small programs, wherein the instant communication tools are used for loading the small programs in a time period when the accident information is triggered.

The accident information is sent to other instant communication tools through the public numbers or service numbers matched with the small programs, and the users can log in the emergency information only by authorization on the small programs, so that the users can not conveniently and quickly check the information, and the public numbers or service numbers in the aspect of public security are selected for pushing the accident information, so that the authority and convenience of the information are guaranteed. Further, since the wechat applet has a positioning function, when pushing accident information, it is emphasized that information is pushed to a person who is close to the place where the accident occurs. When the pushed accident information is in the processing time range and the accident information is received by a holder of the instant messaging tool, when the information is clicked or slid, the public number or the service number can be automatically loaded into the WeChat applet, and detailed information such as video information, a target object, a second position, the accident information and the like is displayed to the holder of the instant messaging tool receiving the accident information, so that a user can quickly know the accident information, the information sharing effect is achieved, further, the user provides more detailed accident conditions and accident places, a fire fighter can make correct judgment, and a rescue plan is made in the shortest time.

After the execution of S206, the process returns to the execution of S201.

In a specific example, when a fire breaks out in a certain building in a community, a person who finds the fire first can record the fire situation in a video mode through a WeChat applet, and in the video, a shooting person can explain the fire situation so that a fire brigade can make a correct rescue scheme. In case of emergency, only one section of fuzzy video information may exist, and the site information cannot be accurately obtained at the moment, so that the fire condition can be sent to the instant messaging tool of nearby people by using the public number or service number of the public security system, and when the nearby people receive accident information, the information condition of the accident information can be checked, namely after the information pushed by the public number or service number is clicked, the instant messaging tool can automatically transfer to the WeChat applet to know detailed information. The person in the accessory can shoot to further supplement the fire place and the scene.

According to the technical scheme of the embodiment, accident information is generated according to an accident and a second position, the accident information has a time period, and the emergency degree of the accidents occurring at the same time can be judged so as to determine a fire rescue policy; the accident information is pushed to other instant communication tools through the public number or the service number matched with the small program, the instant communication tools are used for loading the small program when the accident information is triggered in a time period, and the condition of the accident information is shared to users near an accident place, so that more accident detailed information is obtained, a fire fighter can conveniently make an optimal rescue scheme, and the technical effect of reliable commanding and scheduling is achieved.

It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.

EXAMPLE III

Fig. 3 is a structural block diagram of a positioning device for fire rescue provided in the third embodiment of the present invention, which may specifically include the following modules:

the alarm request receiving module 301 is configured to receive an alarm request sent by an applet running in an instant messaging tool, where the alarm request includes video data collected by the applet and a first location where the applet is located.

A target object identification module 302, configured to identify an object in which an accident occurs in the video data as a target object.

A position determination module 303, configured to calculate, in the video data, a second position where the target object is located based on the first position.

A building location module 304 for converging the plurality of second locations on an electronic map to a building matching the incident to determine that the incident occurred in the building.

Further, the target object identification module 302 includes:

the audio data reading module is used for reading audio data in the video data;

Further, the position determination module 303 includes:

Further, the building location module 304 includes:

Further, the module for calculating matching degree is configured to include:

Further, the module 3043 for calculating matching degree is further configured to:

The positioning device for fire rescue provided by the embodiment of the invention can execute the positioning method for fire rescue provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.

It should be noted that, in the embodiment of the function adjusting apparatus for application programs, the included units and modules are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.

Example four

Fig. four is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. four illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in FIG. four is only an example and should not bring any limitations to the functionality or scope of use of embodiments of the present invention.

As shown in FIG. four, computer device 12 is embodied in a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Computer device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown, but commonly referred to as a "hard drive"). Although not shown in FIG. four, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.

Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with computer device 12, and/or with any devices (e.g., network card, modem, etc.) that enable computer device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, computer device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with the other modules of computer device 12 via bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 16 executes programs stored in the system memory 28 to execute various functional applications and data processing, such as implementing a method for locating a fire rescue provided by an embodiment of the present invention.

EXAMPLE five

An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the positioning method for fire rescue, and can achieve the same technical effect, and in order to avoid repetition, the detailed description is omitted here.

A computer readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: 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.

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A fire rescue positioning method is characterized by comprising the following steps:

2. The method of claim 1, wherein said converging the plurality of second locations on the electronic map to a building matching the incident to determine that the incident occurred in the building comprises:

querying a building matched with the accident on an electronic map;

3. The method of claim 2, wherein said calculating a degree of match between a plurality of said second locations and said building area comprises:

counting the number of the second positions contained in the building area;

4. The method of claim 2, wherein said calculating a degree of match between a plurality of said second locations and said building area comprises:

fitting a plurality of said second locations to an accident area;

counting the accident areas contained in the building areas as target areas;

5. The method according to any one of claims 1 to 4, wherein the identifying an object in the video data where an accident occurs as a target object comprises:

reading audio data in the video data;

performing voice recognition on the audio data to obtain text information;

searching preset keywords in the text information to represent accidents;

searching a target detection model trained for the accident;

6. The method of any of claims 1-4, wherein the alert request further includes a location identified by the applet from which the video data was collected, and wherein calculating a second location in the video data at which the target object is located based on the first location comprises:

7. The method according to any one of claims 1-4, further comprising:

generating accident information according to the accident and the second position, wherein the accident information has a time period;

8. A fire rescue positioning device, comprising:

9. A computer device, characterized in that the computer device comprises:

one or more processors;

a memory for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement a method of locating a fire rescue as recited in any one of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method of locating a fire rescue according to any one of claims 1-7.