A security monitoring method, system, device and medium based on audio data

Abstract

The present invention provides a security monitoring method, system, device and medium based on audio data, which first obtains audio data collected by an audio acquisition device and the coordinate information of the audio acquisition device; then identifies whether there is a target word in the audio data; if there is a target word in the audio data, generates an alarm notification; reviews the audio data according to the alarm notification, and determines whether it is necessary to perform security monitoring on the target object associated with the audio acquisition device based on the review result; if security monitoring is required, generates motion information of the target object according to the coordinate information of the audio acquisition device; and performs security monitoring on the target object according to the motion information. The present invention uses the audio acquisition device to automatically issue an alarm, which can protect the personal and property safety of citizens to a greater extent; at the same time, the present invention can assist personnel to find the target object faster along the target object's motion route, strengthen the personal protection of the target object, and solve the problem of monitoring blind spots.

Description

Technical Field

[0001] The present invention relates to the technical field of security monitoring, and in particular to a security monitoring method, system, equipment and medium based on audio data. Background Art

[0002] At present, video security systems have been installed almost all over the country, and cameras are set up in public places such as roads to protect the safety of the streets and alleys. Setting up cameras can, on the one hand, collect evidence and leave specific targets nowhere to escape; on the other hand, it can also deter some people who are plotting ill, so that they dare not act rashly. Therefore, the significance of setting up cameras for social security is self-evident. However, there are still many places where cameras cannot cover them at all, and many things that are not visible to the public often happen in such places. In these places, on the one hand, rescuers cannot appear in the first time to protect the lives and property of citizens, and on the other hand, it is difficult for victims to obtain evidence, resulting in the perpetrators not being punished as they deserve. These places may often be some remote places or private places, where it is not convenient to install cameras. Therefore, it is necessary to upgrade the security system through the power of society and citizens to fill this gap, so that on the one hand, evidence can be collected, and on the other hand, it can also play a deterrent role and reduce the number of crimes. Summary of the invention

[0003] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a security monitoring method, system, device and medium based on audio data, which are used to solve the problems of partial monitoring blind spots and difficulty in filing cases and collecting evidence in the traditional security industry.

[0004] To achieve the above objectives and other related objectives, the present invention provides a security monitoring method based on audio data, the method comprising the following steps:

[0005] Acquire audio data collected by an audio collection device and coordinate information of the audio collection device;

[0006] Identifying whether a target word exists in the audio data;

[0007] If the target vocabulary exists in the audio data, generating an alarm notification;

[0008] Reviewing the audio data according to the alarm notification, and determining whether security monitoring of a target object associated with the audio acquisition device is required based on the review result;

[0009] If security monitoring of the target object is required, the motion information of the target object is generated according to the coordinate information of the audio acquisition device; wherein the motion information at least includes the motion time and the motion route;

[0010] Security monitoring is performed on the target object according to the motion information, wherein the security monitoring on the target object at least includes mobilizing rescue forces to rescue the target object.

[0011] Optionally, the process of performing security monitoring on the target object according to the motion information further includes:

[0012] Acquire images and / or videos captured by all monitoring devices covering the movement route;

[0013] The movement route is associated with the acquired image and / or video, and security monitoring of the target object is performed based on the association result.

[0014] Optionally, the process of performing security monitoring on the target object according to the motion information further includes:

[0015] Calculating the moving distance difference of the target object in two adjacent time periods according to the coordinate information of the audio acquisition device;

[0016] Determine the moving speed of the target object based on the moving distance difference;

[0017] If the moving speed is greater than a preset speed threshold, acquiring images and / or videos captured by all monitoring devices covering the moving route;

[0018] Filter out the top K motor vehicles with the most appearances from the images and / or videos captured by all monitoring devices covering the movement route;

[0019] The movement route of each screened motor vehicle is compared with the movement route of the target object, and security monitoring is performed on the first K motor vehicles according to the comparison result.

[0020] Optionally, after acquiring the images and / or videos captured by all monitoring devices covering the movement route, the method further includes:

[0021] A fire warning message is issued based on the acquired images and / or videos, and / or a medical emergency message is issued based on the acquired images and / or videos.

[0022] Optionally, before obtaining the audio data collected by the audio collection device and the coordinate information of the audio collection device, the method further includes:

[0023] Inputting the identity information of the target object into the audio acquisition device;

[0024] The audio acquisition device is activated using the input identity information of the target object, and the target object is associated with the audio acquisition device.

[0025] Optionally, the method further includes: storing the acquired audio data and coordinate information of the audio acquisition device in a cloud server.

[0026] Optionally, when collecting audio data, the audio collection device further includes:

[0027] Recording coordinate information, wherein the coordinate information includes at least longitude information and latitude information;

[0028] A communication connection is established with a cloud server, and the collected audio data and recorded coordinate information are transmitted to the cloud server for storage.

[0029] Optionally, the target object includes a person located in a monitoring blind spot.

[0030] The present invention also provides a security monitoring system based on audio data, the system comprising:

[0031] A collection module, used to obtain audio data collected by an audio collection device and coordinate information of the audio collection device;

[0032] An audio recognition module, used to identify whether a target word exists in the audio data;

[0033] An alarm module, used for generating an alarm notification when the target vocabulary exists in the audio data;

[0034] A review module, used for reviewing the audio data according to the alarm notification;

[0035] A security monitoring judgment module, used to determine whether it is necessary to perform security monitoring on the target object associated with the audio acquisition device according to the review result;

[0036] A security monitoring module is used to generate motion information of the target object according to the coordinate information of the audio acquisition device when security monitoring of the target object is required, and to use the motion information to perform security monitoring on the target object; wherein the motion information at least includes the motion time and the motion route, and security monitoring of the target object at least includes mobilizing rescue forces to rescue the target object.

[0037] The present invention also provides a security monitoring device based on audio data, comprising:

[0038] Processor; and

[0039] A computer-readable medium storing instructions, when the processor executes the instructions, causes the device to perform any of the methods described above.

[0040] The present invention also provides a computer-readable medium, characterized in that instructions are stored thereon, and the instructions are loaded by a processor to execute any of the methods described above.

[0041] As described above, the present invention provides a security monitoring method, system, device and medium based on audio data, which has the following beneficial effects: the present invention first obtains the audio data collected by the audio acquisition device and the coordinate information of the audio acquisition device; then identifies whether there is a target word in the audio data; if there is a target word in the audio data, an alarm notification is generated; the audio data is reviewed according to the alarm notification, and based on the review result, it is determined whether it is necessary to perform security monitoring on the target object associated with the audio acquisition device; if it is necessary to perform security monitoring on the target object, the motion information of the target object is generated according to the coordinate information of the audio acquisition device; and the target object is security monitored according to the motion information. Among them, the motion information at least includes the motion time and the motion route. The present invention automatically generates an alarm notification by identifying whether there is a target word in the audio data collected by the audio acquisition device, which is equivalent to the present invention being able to use the audio acquisition device to automatically issue an alarm in scenarios such as when citizens are in danger and have no time to call the police, when citizens are inconvenient to call the police in special occasions, and when citizens lose the ability to call the police, thereby being able to protect the personal and property safety of citizens to a greater extent. At the same time, the present invention utilizes audio acquisition equipment to collect audio data, which can solve the problems of partial monitoring blind spots and difficulty for police to file a case and collect evidence in the existing traditional security industry when the target object is in danger. At the same time, the present invention generates motion information of the target object through the coordinate information of the audio acquisition equipment, which can assist rescue personnel to find the target object along the movement route of the target object more quickly, thereby enhancing the personal protection of the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of a flow chart of a security monitoring method based on audio data provided by an embodiment;

[0043] Figure 2 A schematic diagram of a movement route provided by an embodiment;

[0044] Figure 3 A schematic diagram of the hardware structure of a security monitoring system based on audio data provided by an embodiment;

[0045] Figure 4 A schematic diagram of hardware receiving of a security monitoring system based on audio data provided by another embodiment;

[0046] Figure 5 A schematic diagram of the hardware structure of an audio acquisition device provided by an embodiment;

[0047] Figure 6A schematic diagram of the hardware structure of a security monitoring device based on audio data provided by an embodiment. DETAILED DESCRIPTION

[0048] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0049] It should be noted that the illustrations provided in this embodiment are only used to illustrate the basic concept of the present invention in a schematic manner. Therefore, the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0050] See also Figure 1 As shown, this embodiment provides a security monitoring method based on audio data, and the method includes the following steps:

[0051] S100, acquiring audio data collected by an audio collection device and coordinate information of the audio collection device;

[0052] S200, identifying whether there is a target word in the audio data;

[0053] S300, if the audio data contains the target word, generating an alarm notification;

[0054] S400, reviewing the audio data according to the alarm notification, and determining whether it is necessary to perform security monitoring on the target object associated with the audio acquisition device based on the review result;

[0055] S500, if security monitoring of the target object is required, generating movement information of the target object according to the coordinate information of the audio acquisition device; wherein the movement information at least includes movement time and movement route;

[0056] S600, security monitoring is performed on the target object according to the motion information, wherein the security monitoring of the target object at least includes mobilizing rescue forces to rescue the target object. As an example, the rescue force in this embodiment can be the police, for example, mobilizing police forces from a police station to go to the scene of the crime to rescue the target object. In this embodiment, the target object includes a person located in a monitoring blind spot.

[0057] This method automatically generates an alarm notification by identifying whether the audio data collected by the audio collection device contains the target word. This is equivalent to the method being able to use the audio collection device to automatically issue an alarm when citizens are in danger and have no time to call the police, when citizens are inconvenient to call the police in special occasions, when citizens lose the ability to call the police, etc., so as to protect the personal and property safety of citizens to a greater extent. At the same time, this method uses the audio collection device to collect audio data, which can solve the problems of partial monitoring blind spots and difficulty in filing a case and collecting evidence in the existing traditional security industry when the target object is in danger. At the same time, this method generates the motion information of the target object through the coordinate information of the audio collection device, which can assist rescue personnel to find the target object faster along the target object's motion route, thereby strengthening the personal protection of the target object. Among them, in this embodiment, the target word can be a sensitive word, such as "help", "call the police", "robbery" and other words.

[0058] In an exemplary embodiment, when the audio acquisition device acquires audio data, it further includes: recording coordinate information, wherein the coordinate information includes at least longitude information and latitude information; establishing a communication connection with a cloud server, and transmitting the acquired audio data and the recorded coordinate information to the cloud server for storage. As an example, the target vocabulary recognition of audio data in this method can be completed by the audio acquisition device or by a cloud server.

[0059] According to the above records, in an exemplary embodiment, the process of performing security monitoring on the target object according to the motion information also includes: obtaining images and / or videos captured by all monitoring devices covering the motion route; associating the motion route with the acquired images and / or videos, and performing security monitoring on the target object based on the association result. As an example, this embodiment can draw a trajectory based on the temporal and spatial information of the movement of the geographic coordinates of the audio acquisition device, combine the video and image data in the traditional security data, analyze the video and snapshot images when the coordinates pass through the camera coverage area, analyze the images generated by the camera when the trajectory passes through different positions one by one, and preliminarily determine that the same person or car identified by different cameras is a major suspect, thereby assisting the police in locking the suspect.

[0060] In an exemplary embodiment, the process of performing security monitoring on the target object according to the motion information also includes: calculating the moving distance difference of the target object in two adjacent time periods according to the coordinate information of the audio acquisition device; determining the moving speed of the target object based on the moving distance difference; if the moving speed is greater than a preset speed threshold, obtaining images and / or videos taken by all monitoring devices covering the movement route; filtering out the top K motor vehicles with the most appearances from the images and / or videos taken by all monitoring devices covering the movement route; comparing the movement route of each filtered motor vehicle with the movement route of the target object, and performing security monitoring on the top K motor vehicles according to the comparison result. Among them, the preset speed threshold in this embodiment can be set according to actual conditions, and this application does not limit its value; in addition, the value K in this embodiment can be set according to actual conditions, for example, K can be set to 5.

[0061] Since the speed of a person walking or running is limited, the method determines whether the target object is moving by a motor vehicle by determining the moving speed of the audio acquisition device. If the moving speed obtained according to the coordinate information of the audio acquisition device is greater than the preset speed threshold, it means that the target object is moving by a motor vehicle. At this time, the images and / or videos captured by all monitoring devices covering the movement route are obtained, and the first K motor vehicles with the most appearances are screened out from the images and / or videos captured by all monitoring devices covering the movement route. Then, the movement route of each screened motor vehicle is compared with the movement route of the target object, and the first K motor vehicles are monitored for security according to the comparison results.

[0062] As an example, as shown in 2, this embodiment first generates a motion trajectory route 1000 of the target object in the map, and then determines the monitoring devices that need to be linked according to the motion trajectory route 1000, that is, determines the monitoring devices IPC1, IPC2 and IPC4, and then reads the vehicle information photographed and identified by the monitoring devices IPC1, IPC2 and IPC4 in the corresponding time period according to the motion time in the target object motion information, and then selects the top K motor vehicles with the most appearances from these vehicle information. Assume that this embodiment is to select a motor vehicle with the most appearances, and the monitoring device IPC1 photographs and identifies vehicles c1, c2, c3; the monitoring device IPC2 photographs and identifies vehicles c2, c3, c4; the monitoring device IPC4 photographs and identifies vehicles c1, c2, c4; then it can be considered that vehicle c2 is a major suspect, and the target object may be on motor vehicle c2. In this embodiment, the longer the motion trajectory route of the target object, the more cameras the corresponding vehicle will pass through, and the higher the confidence level of the analysis result.

[0063] In an exemplary embodiment, after acquiring images and / or videos captured by all monitoring devices covering the movement route, the method further includes: issuing fire warning information based on the acquired images and / or videos, and / or issuing medical emergency information based on the acquired images and / or videos. After acquiring the images and / or videos, the method can also determine whether it is necessary to issue fire warning messages and medical emergency information, so that the public security can form a linkage with the fire department, medical institutions, etc.

[0064] In an exemplary embodiment, before obtaining the audio data collected by the audio acquisition device and the coordinate information of the audio acquisition device, it also includes: inputting the identity information of the target object into the audio acquisition device; activating the audio acquisition device using the input identity information of the target object, and associating the target object with the audio acquisition device. In this method, the audio acquisition device must be bound to the user's identity, and the ID card information needs to be uploaded to the alarm APP. After verification, the ID card is bound to activate the automatic alarm function of the audio acquisition device. For independent hardware devices, it is also necessary to bind the user's identity through the alarm APP before it can be activated and complete the registration with the platform. In addition, this method can also formulate certain charging strategies for objects that occupy the audio analysis resources of the security platform, and does not allow the public to arbitrarily query the audio data stored in the cloud server of the security platform, so as to avoid the behavior of deliberately placing independent acquisition devices on others for eavesdropping.

[0065] In summary, the present invention provides a security monitoring method based on audio data, which first obtains the audio data collected by the audio acquisition device and the coordinate information of the audio acquisition device; then identifies whether there is a target word in the audio data; if there is a target word in the audio data, generates an alarm notification; reviews the audio data according to the alarm notification, and determines whether it is necessary to perform security monitoring on the target object associated with the audio acquisition device based on the review result; if it is necessary to perform security monitoring on the target object, generates the motion information of the target object according to the coordinate information of the audio acquisition device; and performs security monitoring on the target object according to the motion information. The motion information at least includes the motion time and the motion route. The method automatically generates an alarm notification by identifying whether there is a target word in the audio data collected by the audio acquisition device, which is equivalent to the method being able to use the audio acquisition device to automatically issue an alarm in scenarios such as when citizens are in danger and have no time to call the police, when citizens are inconvenient to call the police in special occasions, and when citizens lose the ability to call the police, thereby being able to protect the personal and property safety of citizens to a greater extent. At the same time, this method uses audio acquisition equipment to collect audio data, which can solve the problems of partial monitoring blind spots and difficulty for police to file a case and collect evidence in the existing traditional security industry when the target object is in danger. At the same time, this method generates motion information of the target object through the coordinate information of the audio acquisition equipment, which can assist rescue personnel to find the target object along the target object's movement route more quickly, thereby strengthening the personal protection of the target object.

[0066] like Figure 3 As shown, the present invention also provides a security monitoring system based on audio data, the system comprising:

[0067] The acquisition module M10 is used to acquire the audio data acquired by the audio acquisition device and the coordinate information of the audio acquisition device;

[0068] An audio recognition module M20 is used to identify whether a target word exists in the audio data;

[0069] An alarm module M30, configured to generate an alarm notification when a target word exists in the audio data;

[0070] A review module M40, configured to review the audio data according to the alarm notification;

[0071] The security monitoring judgment module M50 is used to determine whether it is necessary to perform security monitoring on the target object associated with the audio acquisition device according to the review result;

[0072] The security monitoring module M60 is used to generate the motion information of the target object according to the coordinate information of the audio acquisition device when the target object needs to be monitored for security, and to use the motion information to perform security monitoring on the target object; wherein the motion information at least includes the movement time and the movement route, wherein the security monitoring of the target object at least includes mobilizing rescue forces to rescue the target object. As an example, the rescue force in this embodiment can be the police, for example, mobilizing the police force of the police station to go to the scene of the crime to rescue the target object.

[0073] This system automatically generates an alarm notification by identifying whether the audio data collected by the audio collection device contains the target word. This is equivalent to the system being able to use the audio collection device to automatically issue an alarm when citizens are in danger and have no time to call the police, when citizens are inconvenient to call the police in special occasions, when citizens lose the ability to call the police, etc., so as to protect the personal and property safety of citizens to a greater extent. At the same time, this system uses the audio collection device to collect audio data, which can solve the problems of some monitoring blind spots in the existing traditional security industry and the difficulty of police filing a case and collecting evidence when the target object is in danger. At the same time, this system generates the motion information of the target object through the coordinate information of the audio collection device, which can assist rescue personnel to find the target object faster along the target object's motion route, thereby strengthening the personal protection of the target object. Among them, in this embodiment, the target word can be a sensitive word, such as "help", "call the police", "robbery" and other words.

[0074] In an exemplary embodiment, the system further includes: storing the acquired audio data and the coordinate information of the audio acquisition device in a cloud server. As an example, the target vocabulary recognition of the audio data by the system can be completed by the audio acquisition device or by a cloud server.

[0075] In an exemplary embodiment, the process of the security monitoring module using the motion information to perform security monitoring on the target object includes: obtaining images and / or videos captured by all monitoring devices covering the motion route; associating the motion route with the acquired images and / or videos, and performing security monitoring on the target object based on the association result. As an example, this embodiment can draw a trajectory based on the temporal and spatial information of the movement of the geographic coordinates of the audio acquisition device, combine the video and image data in the traditional security data, analyze the video and snapshot images when the coordinates pass through the camera coverage area, analyze the images generated by the camera when the trajectory passes through different positions one by one, and preliminarily determine that the same person or car identified by different cameras is a major suspect, thereby assisting the police in locking the suspect.

[0076] In an exemplary embodiment, the process of the security monitoring module using the motion information to perform security monitoring on the target object also includes: calculating the difference in the moving distance of the target object in two adjacent time periods based on the coordinate information of the audio acquisition device; determining the moving speed of the target object based on the moving distance difference; if the moving speed is greater than a preset speed threshold, obtaining images and / or videos captured by all monitoring devices covering the movement route; filtering out the top K motor vehicles with the most appearances from the images and / or videos captured by all monitoring devices covering the movement route; comparing the movement route of each filtered motor vehicle with the movement route of the target object, and performing security monitoring on the top K motor vehicles based on the comparison result. Among them, the preset speed threshold in this embodiment can be set according to actual conditions, and this application does not limit its value; in addition, the value K in this embodiment can be set according to actual conditions, for example, K can be set to 5.

[0077] Since the speed of a person walking or running is limited, the system determines whether the target object is moving by a motor vehicle by judging the moving speed of the audio acquisition device. If the moving speed obtained according to the coordinate information of the audio acquisition device is greater than the preset speed threshold, it means that the target object is moving by a motor vehicle. At this time, the images and / or videos captured by all monitoring devices covering the movement route are obtained, and the first K motor vehicles with the most appearances are screened out from the images and / or videos captured by all monitoring devices covering the movement route. Then, the movement route of each screened motor vehicle is compared with the movement route of the target object, and the first K motor vehicles are monitored for security according to the comparison results.

[0078] As an example, as shown in 2, this embodiment first generates a motion trajectory route 1000 of the target object in the map, and then determines the monitoring devices that need to be linked according to the motion trajectory route 1000, that is, determines the monitoring devices IPC1, IPC2 and IPC4, and then reads the vehicle information photographed and identified by the monitoring devices IPC1, IPC2 and IPC4 in the corresponding time period according to the motion time in the target object motion information, and then selects the top K motor vehicles with the most appearances from these vehicle information. Assume that this embodiment is to select a motor vehicle with the most appearances, and the monitoring device IPC1 photographs and identifies vehicles c1, c2, c3; the monitoring device IPC2 photographs and identifies vehicles c2, c3, c4; the monitoring device IPC4 photographs and identifies vehicles c1, c2, c4; then it can be considered that vehicle c2 is a major suspect, and the target object may be on motor vehicle c2. In this embodiment, the longer the motion trajectory route of the target object, the more cameras the corresponding vehicle will pass through, and the higher the confidence level of the analysis result.

[0079] In an exemplary embodiment, after acquiring images and / or videos captured by all monitoring devices covering the movement route, the system further includes: issuing fire warning information based on the acquired images and / or videos, and / or issuing medical emergency information based on the acquired images and / or videos. After acquiring the images and / or videos, the system can also determine whether it is necessary to issue fire warning messages and medical emergency information, so that the public security can form a linkage with the fire department, medical institutions, etc.

[0080] In an exemplary embodiment, before obtaining the audio data collected by the audio acquisition device and the coordinate information of the audio acquisition device, it also includes: inputting the identity information of the target object into the audio acquisition device; activating the audio acquisition device using the input identity information of the target object, and associating the target object with the audio acquisition device. In this system, the audio acquisition device must be bound to the user's identity, and the ID card information needs to be uploaded to the alarm APP. After verification, the ID card is bound to activate the automatic alarm function of the audio acquisition device. For independent hardware devices, it is also necessary to bind the user's identity through the alarm APP before it can be activated and complete the registration with the platform. In addition, this system can also formulate certain charging strategies for objects that occupy the audio analysis resources of the security platform, and does not allow the public to arbitrarily query the audio data stored in the cloud server of the security platform, so as to avoid the behavior of deliberately placing independent acquisition devices on others for eavesdropping.

[0081] In summary, the present invention provides a security monitoring method based on audio data, firstly obtaining the audio data collected by the audio acquisition device and the coordinate information of the audio acquisition device; then identifying whether there is a target word in the audio data; if there is a target word in the audio data, generating an alarm notification; reviewing the audio data according to the alarm notification, and determining whether it is necessary to perform security monitoring on the target object associated with the audio acquisition device based on the review result; if it is necessary to perform security monitoring on the target object, generating the motion information of the target object according to the coordinate information of the audio acquisition device; and performing security monitoring on the target object according to the motion information. Among them, the motion information at least includes the motion time and the motion route. The system automatically generates an alarm notification by identifying whether there is a target word in the audio data collected by the audio acquisition device, which is equivalent to the system being able to use the audio acquisition device to automatically issue an alarm in scenarios such as when citizens are in danger and it is too late to call the police, when citizens are inconvenient to call the police in special occasions, when citizens lose the ability to call the police, etc., thereby being able to protect the personal and property safety of citizens to a greater extent. At the same time, this system uses audio acquisition equipment to collect audio data, which can solve the problems of partial monitoring blind spots and difficulty for police to file a case and collect evidence in the existing traditional security industry when the target object is in danger. At the same time, this system uses the coordinate information of the audio acquisition equipment to generate the motion information of the target object, which can assist rescue personnel to find the target object faster along the target object's movement route, thereby strengthening the personal protection of the target object.

[0082] The present invention also provides a security monitoring system based on audio data, the system comprising: an audio acquisition device, an audio security system and a public security system, wherein the audio acquisition device is connected to the audio security system, and the audio security system is connected to the public security system;

[0083] The audio acquisition device is used to associate the target object, collect audio data and record coordinate information, and perform target vocabulary recognition on the collected audio data to generate an alarm notification;

[0084] The intelligent security system is used to store audio data and coordinate information, and to perform target vocabulary recognition on the collected audio data, generate an alarm notification, and transmit an instruction to review the voice data to the public security system according to the notification generated by the audio collection device or the alarm notification generated by the intelligent security system body;

[0085] The public security system is used to review the audio data and perform security monitoring on the target object, wherein the security monitoring on the target object at least includes mobilizing rescue forces to rescue the target object. As an example, the rescue force in this embodiment can be the police, for example, mobilizing police forces from a police station to go to the scene of the crime to rescue the target object.

[0086] Specifically, Figure 4As shown, the security monitoring system in this embodiment may include: an audio acquisition device, an audio security system and a public security system, and the audio acquisition device is connected to the audio security system, and the audio security system is connected to the public security system;

[0087] The audio acquisition device includes: an audio acquisition module, a coordinate acquisition module, a data push module, a first audio analysis module and an alarm push module;

[0088] The audio acquisition module is used to collect audio data;

[0089] The coordinate acquisition module is used to acquire coordinate information, and the coordinate information at least includes: longitude information and latitude information;

[0090] The data push module is used to push the collected audio data and coordinate information to the audio security system;

[0091] The first audio analysis module is used to perform target vocabulary recognition on the collected audio data and generate an alarm notification;

[0092] The alarm push module is used to push the alarm notification to the audio security system.

[0093] The audio security system comprises: a data receiving module, an alarm receiving module, a public security alarm center, a second audio analysis module, a data storage module and a trajectory analysis module;

[0094] Trajectory analysis module, data storage module, second audio analysis module and public security alarm center;

[0095] The data receiving module is used to receive the audio data and coordinate information pushed by the audio acquisition device;

[0096] The alarm receiving module is used to receive the alarm notification pushed by the audio acquisition device, and transmit the received alarm notification to the public security alarm center;

[0097] The second audio analysis module is used to perform target vocabulary recognition on the collected audio data, generate an alarm notification, and transmit the generated alarm notification to the public security alarm center;

[0098] The public security alarm center is used to transmit an instruction for reviewing the voice data to the public security system according to the alarm notification;

[0099] The data storage module is used to store the audio data and coordinate information received by the data receiving module;

[0100] The trajectory analysis module is used to generate the motion information of the target object according to the coordinate information of the audio acquisition device; wherein the motion information at least includes the motion time and the motion route.

[0101] The public security system is used to review the voice data according to the review instruction, mobilize police force to perform security monitoring on the target object according to the motion information, and file a case and collect evidence according to the audio data and coordinate information stored in the data storage module. Among them, performing security monitoring on the target object at least includes mobilizing rescue forces to rescue the target object. As an example, the rescue force in this embodiment can be the police, for example, mobilizing police forces from the police station to go to the scene of the crime to rescue the target object.

[0102] The security monitoring process of the security monitoring system in this embodiment is as follows:

[0103] The audio acquisition module and the coordinate acquisition module respectively collect audio and coordinate information and report them to the data push module; the data push module pushes the data to the security platform; after the security platform receives the data, it writes the data into the cloud server for storage. Among them, the security platform in this embodiment is the audio security system in the security monitoring system.

[0104] The first audio analysis module in the audio acquisition device or the second audio analysis module in the intelligent security system analyzes the content of the audio to determine whether the target word exists in the audio data. When the first audio analysis module or the second audio analysis module identifies sensitive words such as "help" and "alarm" in the audio data, an alarm signal is generated and pushed to the public security alarm center, which pushes the alarm to the manual verification system.

[0105] After receiving the alarm notification, the manual verification system obtains the recording of the alarm time from the data storage module to verify whether rescue is needed. After verifying the distress signal, the real-time coordinate data is obtained from the data receiving module, and the police force of the nearest police station is mobilized to the scene of the crime. After receiving the police dispatch instruction, the police obtain real-time audio information and coordinate information from the audio receiving module and trigger trajectory analysis. The trajectory analysis module draws the trajectory according to the time and space information of the coordinate point movement, and combines the video and image data in the traditional security data to analyze the video and snapshot images when the coordinate passes through the camera coverage area. After analyzing the images generated by the camera when the trajectory passes through different positions one by one, it is preliminarily determined that the same person or car identified by different cameras is a major suspect, and assists the police in locking the suspect.

[0106] Among them, the trajectory analysis module is mainly used in the scene where people are in the car, because people have limited mobility, especially after being violated, the trajectory movement will not change much from the time the police dispatch to the time the police arrive at the scene, so regular trajectory analysis is not very meaningful. However, for scenes where people are in the car, such as cases where the victim is kidnapped into the car, or the driver has bad intentions towards the passengers, trajectory analysis can provide more help. Specifically, whenever the trajectory analysis module receives the reported coordinates, it finds the camera that can cover the coordinates in the video security system and pushes the monitoring screen to the police in real time. The police can decide whether to synchronize to the fire or emergency system based on the information seen in the pushed screen. When the coordinates are received, the difference is made with the last reported coordinate time and position to calculate the target movement speed. According to the preset speed threshold and the position of the coordinate point on the map, it is determined whether the target is on the motor vehicle. If you find the vehicle checkpoint camera on a motor vehicle that passes through the route, obtain the pictures taken by the camera in the corresponding time period and the vehicle information identified, combine the data from different cameras, and obtain the vehicle information that appears the most times, you can preliminarily determine that the vehicle is a major suspect, and push the information of the five most suspicious vehicles to the police.

[0107] In summary, the security monitoring system in this embodiment can solve two types of problems: one is the scenario where there is no time to call the police with a mobile phone when danger occurs; the other is the problem of difficulty in filing a case and collecting evidence after the incident. When many dangers occur, it is impossible or too late to call the police. This system is equivalent to having someone who can help you call the police and provide evidence when you are in danger. It can also be turned off at any time when you are in a safe environment, providing people with a more effective means to protect personal life and property safety.

[0108] When citizens feel that there may be a security risk, they can carry and turn on a portable audio collection device, and push the data to the intelligent audio security system in real time. When they are really in danger, a cry for help can be heard directly by the police, which is a more effective and timely means of reporting the incident. If such a first-time call to the police still fails to save lives, at least evidence of the crime can be left behind.

[0109] In addition, recordings are stored in the public security system, which makes information safer. Sharing the location with the public security is also safer than sharing it with family members. When a special incident occurs (for example, person A takes person B to a remote location to commit an offense), the police can also obtain real-time location information and quickly go to the scene of the crime to protect the lives and property of citizens.

[0110] In some cases where it is inconvenient to call the police, or the victims are unable to call the police, the victims often cannot bring the perpetrators to justice due to insufficient evidence. If the recording can be reported to the public security system in real time through the collection equipment, the police can obtain first-hand evidence and protect the rights of the victims.

[0111] According to the above records, if Figure 5 As shown, the present invention also provides an audio acquisition device using any of the above embodiments, the device comprising:

[0112] A collection unit D10, used for collecting audio data;

[0113] A location recording unit D20, used to record coordinate information, wherein the coordinate information includes at least longitude information and latitude information;

[0114] A communication unit D30, used to establish a communication connection with a cloud server;

[0115] The data transmission unit D40 is used to transmit the collected audio data and the recorded coordinate information to the cloud server for storage.

[0116] According to the above records, the collection device in this embodiment can be a mobile phone. For example, the police can open an alarm APP for citizens to download. When the alarm APP is turned on, it is responsible for collecting and uploading data. The advantage is that there is almost no cost. It can also be an independent hardware device. The advantage of an independent device is that it can be smaller in size and better concealed. It can still work in some scenes where the mobile phone may be taken away. If there is an independent collection device in the shape of a lipstick or other female belongings, it can still complete the collection and synchronization without the mobile phone. If there is a situation, the alarm can be called in time, or the truth can be restored afterwards.

[0117] In summary, the present invention provides a security monitoring method and system based on audio data, firstly obtaining the audio data collected by the audio acquisition device and the coordinate information of the audio acquisition device; then identifying whether there is a target word in the audio data; if there is a target word in the audio data, generating an alarm notification; reviewing the audio data according to the alarm notification, and determining whether it is necessary to perform security monitoring on the target object associated with the audio acquisition device based on the review result; if it is necessary to perform security monitoring on the target object, generating the motion information of the target object according to the coordinate information of the audio acquisition device; and performing security monitoring on the target object according to the motion information. Among them, the motion information at least includes the motion time and the motion route. The present invention automatically generates an alarm notification by identifying whether there is a target word in the audio data collected by the audio acquisition device, which is equivalent to the present invention being able to use the audio acquisition device to automatically issue an alarm in scenarios such as when citizens are in danger and it is too late to call the police, when citizens are inconvenient to call the police in special occasions, when citizens lose the ability to call the police, etc., thereby being able to protect the personal and property safety of citizens to a greater extent. At the same time, the present invention uses audio acquisition equipment to collect audio data, which can solve the problems of partial monitoring blind spots and difficulty for police to file a case and collect evidence in the existing traditional security industry when the target object is in danger. At the same time, the present invention generates the motion information of the target object through the coordinate information of the audio acquisition equipment, which can assist rescue personnel to find the target object along the target object's motion route more quickly, thereby strengthening the personal protection of the target object. Therefore, the present invention effectively overcomes various shortcomings in the prior art and has a high industrial utilization value.

[0118] The embodiment of the present application also provides a security monitoring device based on audio data, which may include: one or more processors; and one or more machine-readable media having instructions stored thereon, which, when executed by the one or more processors, enable the device to execute Figure 1 The method described. Figure 6 FIG. 1 shows a schematic diagram of a security monitoring device 1000 based on audio data. Figure 6 As shown, the audio data-based security monitoring device 1000 includes: a processor 1010 , a memory 1020 , a power supply 1030 , a display unit 1040 , and an input unit 1060 .

[0119] The processor 1010 is the control center of the security monitoring device 1000 based on audio data. It uses various interfaces and lines to connect various components, and executes various functions of the security monitoring device 1000 based on audio data by running or executing software programs and / or data stored in the memory 1020, thereby monitoring the security monitoring device 1000 based on audio data as a whole. In the embodiment of the present application, when the processor 1010 calls the computer program stored in the memory 1020, the following is executed: Figure 1The method described. Optionally, the processor 1010 may include one or more processing units; preferably, the processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and applications, etc., and the modem processor mainly processes wireless communications. In some embodiments, the processor and the memory may be implemented on a single chip, and in some embodiments, they may also be implemented separately on separate chips.

[0120] The memory 1020 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, various applications, etc.; the data storage area may store data created according to the use of the security monitoring device 1000 based on audio data, etc. In addition, the memory 1020 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices, etc.

[0121] The audio data-based security monitoring device 1000 also includes a power supply 1030 (such as a battery) for supplying power to each component. The power supply can be logically connected to the processor 1010 through a power management system, thereby managing functions such as charging, discharging, and power consumption through the power management system.

[0122] The display unit 1040 can be used to display information input by the user or information provided to the user and various menus of the security monitoring device 1000 based on audio data, etc. In the embodiment of the present invention, it is mainly used to display the display interface of each application in the security monitoring device 1000 based on audio data and objects such as text and pictures displayed in the display interface. The display unit 1040 may include a display panel 1050. The display panel 1050 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc.

[0123] The input unit 1060 may be used to receive information such as numbers or characters input by the user. The input unit 1060 may include a touch panel 1070 and other input devices 1080. The touch panel 1070, also known as a touch screen, may collect touch operations of the user on or near it (such as operations of the user using a finger, a stylus, or any other suitable object or accessory on or near the touch panel 1070).

[0124] Specifically, the touch panel 1070 can detect the user's touch operation, detect the signal brought by the touch operation, convert these signals into touch point coordinates, send them to the processor 1010, and receive and execute the command sent by the processor 1010. In addition, the touch panel 1070 can be implemented in various types such as resistive, capacitive, infrared and surface acoustic wave. Other input devices 1080 can include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, power on / off keys, etc.), a trackball, a mouse, a joystick, etc.

[0125] Of course, the touch panel 1070 can cover the display panel 1050. When the touch panel 1070 detects a touch operation on or near it, it is transmitted to the processor 1010 to determine the type of touch event, and then the processor 1010 provides a corresponding visual output on the display panel 1050 according to the type of touch event. Figure 6 In the embodiment, the touch panel 1070 and the display panel 1050 are two independent components to realize the input and output functions of the security monitoring device 1000 based on audio data. However, in some embodiments, the touch panel 1070 and the display panel 1050 can be integrated to realize the input and output functions of the security monitoring device 1000 based on audio data.

[0126] The security monitoring device 1000 based on audio data may also include one or more sensors, such as a pressure sensor, a gravity acceleration sensor, a proximity light sensor, etc. Of course, according to the needs of specific applications, the security monitoring device 1000 based on audio data may also include other components such as a camera.

[0127] The embodiment of the present application also provides a computer-readable storage medium, in which instructions are stored. When one or more processors execute the instructions, the above-mentioned device can perform the above-mentioned Figure 1 The method described.

[0128] It can be understood by those skilled in the art that Figure 6 This is only an example of a security monitoring device based on audio data and does not constitute a limitation on the device. The device may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For the convenience of description, the above parts are divided into modules (or units) according to their functions and described separately. Of course, when implementing this application, the functions of each module (or unit) can be implemented in the same or multiple software or hardware.

[0129] Those skilled in the art should understand that the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be applied 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 functions in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0130] It should be understood that, although the terms first, second, third, etc. may be used to describe preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0131] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A security monitoring method based on audio data, characterized in that: The method comprises the following steps: Acquire audio data collected by an audio collection device and coordinate information of the audio collection device; Identifying whether a target word exists in the audio data; If the target vocabulary exists in the audio data, generating an alarm notification; Reviewing the audio data according to the alarm notification, and determining whether security monitoring of a target object associated with the audio acquisition device is required based on the review result; If security monitoring of the target object is required, the motion information of the target object is generated according to the coordinate information of the audio acquisition device; wherein the motion information at least includes the motion time and the motion route; Security monitoring is performed on the target object according to the motion information, wherein the security monitoring of the target object at least includes mobilizing rescue forces to rescue the target object; the process of security monitoring of the target object according to the motion information also includes: calculating the difference in moving distances of the target object in two adjacent time periods according to the coordinate information of the audio acquisition device; determining the moving speed of the target object based on the moving distance difference; if the moving speed is greater than a preset speed threshold, obtaining images and / or videos taken by all monitoring devices covering the movement route; screening out the top K motor vehicles with the largest number of appearances from the images and / or videos taken by all monitoring devices covering the movement route; comparing the movement route of each screened motor vehicle with the movement route of the target object, and performing security monitoring on the top K motor vehicles according to the comparison result.

2. The security monitoring method based on audio data according to claim 1, characterized in that: The process of performing security monitoring on the target object according to the motion information further includes: Acquire images and / or videos captured by all monitoring devices covering the movement route; The movement route is associated with the acquired image and / or video, and security monitoring of the target object is performed based on the association result.

3. The security monitoring method based on audio data according to claim 2 is characterized in that: After acquiring the images and / or videos captured by all monitoring devices covering the movement route, the method further includes: A fire warning message is issued based on the acquired images and / or videos, and / or a medical emergency message is issued based on the acquired images and / or videos.

4. The security monitoring method based on audio data according to claim 1, characterized in that: Before acquiring the audio data collected by the audio collection device and the coordinate information of the audio collection device, the method further includes: Inputting the identity information of the target object into the audio acquisition device; The audio acquisition device is activated using the input identity information of the target object, and the target object is associated with the audio acquisition device.

5. The security monitoring method based on audio data according to claim 1, characterized in that: When collecting audio data, the audio collection device also includes: Recording coordinate information, wherein the coordinate information includes at least longitude information and latitude information; A communication connection is established with a cloud server, and the collected audio data and recorded coordinate information are transmitted to the cloud server for storage.

6. The security monitoring method based on audio data according to claim 1, characterized in that: The target objects include persons located in monitoring blind spots.

7. A security monitoring system based on audio data, characterized in that: The system comprises: A collection module, used to obtain audio data collected by an audio collection device and coordinate information of the audio collection device; An audio recognition module, used to identify whether a target word exists in the audio data; An alarm module, used for generating an alarm notification when the target vocabulary exists in the audio data; A review module, used for reviewing the audio data according to the alarm notification; A security monitoring judgment module, used to determine whether it is necessary to perform security monitoring on the target object associated with the audio acquisition device according to the review result; A security monitoring module is used to generate motion information of the target object according to the coordinate information of the audio acquisition device when security monitoring of the target object is required, and to use the motion information to perform security monitoring on the target object; wherein the motion information at least includes motion time and motion route, and security monitoring of the target object at least includes mobilizing rescue forces to rescue the target object; the process of performing security monitoring on the target object according to the motion information also includes: calculating the difference in moving distances of the target object in two adjacent time periods according to the coordinate information of the audio acquisition device; determining the moving speed of the target object based on the moving distance difference; if the moving speed is greater than a preset speed threshold, obtaining images and / or videos captured by all monitoring devices covering the motion route; screening out the top K motor vehicles with the most appearances from the images and / or videos captured by all monitoring devices covering the motion route; comparing the motion route of each screened motor vehicle with the motion route of the target object, and performing security monitoring on the top K motor vehicles according to the comparison result.

8. A security monitoring device based on audio data, characterized in that: include: processor; and A computer-readable medium storing instructions, when the processor executes the instructions, causes the device to perform the method according to any one of claims 1 to 6.

9. A computer-readable medium, characterized in that Instructions are stored thereon, and the instructions are loaded by a processor to execute the method according to any one of claims 1 to 6.

Images