CN111275909B

CN111275909B - Security early warning method and device

Info

Publication number: CN111275909B
Application number: CN201811475548.6A
Authority: CN
Inventors: 陈建平
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2018-12-04
Filing date: 2018-12-04
Publication date: 2021-12-28
Anticipated expiration: 2038-12-04
Also published as: CN111275909A

Abstract

The embodiment of the invention provides a security early warning method and a security early warning device, wherein the method comprises the following steps: collecting environmental sound information in a target place; acquiring a first voiceprint characteristic of the environmental sound information; determining whether the target place is suspicious or not based on the first voiceprint features and second voiceprint features stored in advance; and if the target place is determined to have a suspicious situation, entering a prepared warning state. Therefore, the intelligent device collects the environmental sound information of the target place to realize security early warning, extra hardware equipment does not need to be added, the safety early warning cost is reduced, and the intelligent device is very convenient to use.

Description

Security early warning method and device

Technical Field

The embodiment of the invention relates to the technical field of electronic equipment, in particular to a security early warning method and device.

Background

With the continuous development of science and technology and the continuous improvement of living standard, people put forward higher and higher requirements on the safety and convenience of living environment. Along with the rapid development of electronic technology, the types and functions of intelligent equipment are more and more diversified, and people can enjoy the convenience brought by the scientific and technological development.

In order to prevent the illegal secret intrusion of the foreign people into important target places such as homes and the like, personal injury and property loss are caused to people, the situation of the target places needs to be monitored in real time when no people exist in the target places. Therefore, various security systems come along with the existing security system, but the existing security system is often built by a user purchasing special hardware equipment, the security early warning cost is high, and a professional person is needed to build the security early warning system, so that the building process is very inconvenient.

Disclosure of Invention

In view of this, embodiments of the present invention provide a security and protection early warning method and apparatus, where security and protection early warning is implemented by acquiring environmental sound information of a target location through an intelligent device, and no additional hardware device is needed, so that the security and protection early warning cost is reduced, and the use is very convenient.

In order to solve the above technical problems, embodiments of the present invention provide the following technical solutions:

in a first aspect, an embodiment of the present invention provides a security early warning method, which is applied to an intelligent device, and the method includes: collecting environmental sound information in a target place; acquiring a first voiceprint characteristic of the environmental sound information; determining whether the target place is suspicious or not based on the first voiceprint features and second voiceprint features stored in advance; and if the target place is determined to have a suspicious situation, entering a prepared warning state.

In a second aspect, an embodiment of the present invention provides a security and protection early warning method, which is applied to a server, and the method includes: when a suspicious situation occurs in a target place, receiving environmental sound information in the target place sent by intelligent equipment; confirming whether the suspicious situation is a normal situation or not based on the environmental sound information; if the situation is normal, sending a judgment result for indicating that formal early warning is not needed to the client so that the client releases the prepared warning state; otherwise, sending a judgment result for indicating that formal early warning is needed to be carried out to the client so as to enable the client to start outputting early warning information

In a third aspect, an embodiment of the present invention provides a security and protection early warning apparatus, which is applied to an intelligent device, where the apparatus includes: the acquisition unit is used for acquiring environmental sound information in a target place; the acquisition unit is used for acquiring a first voiceprint characteristic of the environmental sound information; the determining unit is used for determining whether the target place is suspicious or not based on the first voiceprint characteristics and second voiceprint characteristics stored in advance; and the first early warning unit is used for entering a prepared warning state if the determining unit determines that the target site has a suspicious situation.

In a fourth aspect, an embodiment of the present invention provides a security and protection early warning apparatus, which is applied to a server, and the apparatus includes: the first receiving unit is used for receiving environmental sound information in a target place sent by the intelligent equipment when the target place is in a suspicious situation; the confirming unit is used for confirming whether the suspicious situation is a normal situation or not based on the environmental sound information; a first sending unit, configured to send, to the client, a determination result indicating that a formal warning is not needed if the suspicious situation is determined to be a normal situation by the determining unit, so that the client releases a preliminary warning state; otherwise, sending a judgment result for indicating that formal early warning is needed to the client so that the client starts to output early warning information.

In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, where the storage medium includes a stored program, and when the program runs, the device where the storage medium is located is controlled to execute the steps of the security early warning method.

In a sixth aspect, an embodiment of the present invention provides an electronic device, where the electronic device includes: at least one processor; and at least one memory, bus connected with the processor; the processor and the memory complete mutual communication through the bus; the processor is used for calling the program instruction in the memory so as to execute the steps of the security early warning method.

According to the security early warning method and device provided by the embodiment of the invention, after the intelligent device collects the environmental sound information in the target place, the intelligent device can extract the first voiceprint feature of the environmental sound information, then the intelligent device can determine whether the target place is suspicious or not based on the first voiceprint feature and the second voiceprint feature which is stored in advance, and then the intelligent device can enter the prepared warning state when determining that the target place is suspicious. Like this, gather the environmental sound information in target place through smart machine and realize the security protection early warning, can effectively utilize idle smart machine such as intelligent audio amplifier, panel computer in the target place to realize the security protection early warning, need not to increase any extra hardware equipment, can reduce the safety early warning cost, it is very convenient to use.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 is a schematic diagram of a security early warning system in an embodiment of the present invention;

FIG. 2 is a first schematic flow chart of a security early warning method in an embodiment of the present invention;

FIG. 3 is a second schematic flow chart of a security early warning method in the embodiment of the present invention;

FIG. 4 is a third schematic flow chart of a security early warning method in the embodiment of the present invention;

FIG. 5 is a first schematic structural diagram of a security early warning device in an embodiment of the present invention;

FIG. 6 is a schematic structural diagram II of the security early warning device in the embodiment of the present invention;

fig. 7 is a schematic structural diagram of an electronic device in an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

An embodiment of the present invention provides a security and protection early warning system, fig. 1 is a schematic diagram of a security and protection early warning system in an embodiment of the present invention, and referring to fig. 1, the security and protection early warning system may include: the intelligent device comprises an intelligent device 11, a server 12 and a user terminal 13 bound with the intelligent device 11, wherein the server 12 can respectively carry out data communication with the intelligent device 11 and the user terminal 13 through a network, and the user terminal 13 can remotely control the intelligent device 13 through the server 12.

Specifically, in order to perform security early warning on a target location, the intelligent device needs to be located in the target location to be monitored. In daily life, in target places such as homes, intelligent devices such as intelligent sound boxes and intelligent televisions can be placed for a long time by most users, and even intelligent devices such as smart phones, notebook computers and tablet computers which are replaced by users can be placed.

Therefore, in practical applications, the above-described smart device may be implemented in various forms. For example, the smart device described in the present invention may be a smart home device such as a smart sound box, a smart television, or a mobile terminal such as a smart phone, a tablet computer, a smart watch, and a notebook computer, or may also be a vehicle-mounted device such as a vehicle-mounted audio device, a vehicle-mounted front-mounted device, and an integrated vehicle, or may also be other types of electronic devices capable of acquiring sound information and processing and analyzing the sound information, where embodiments of the present invention are not limited specifically herein.

Accordingly, in practical applications, the user terminal may be implemented in various forms. In general, the user terminal may be a portable device such as a smart phone, a smart watch, and a wearable device, and certainly, may also be other types of devices capable of receiving the warning information from the smart device, such as a tablet computer, a notebook computer, and a personal computer. Here, the embodiments of the present invention are not particularly limited.

Further, in combination with the security early warning system, the embodiment of the invention provides a security early warning method. In practical application, the security early warning method can be applied to various occasions where security early warning is required to be realized by monitoring sound through intelligent equipment, for example, under the conditions that no person is in the places such as home, office, warehouse and the like or all target users in the places are in a rest state and the like, security early warning is required to be performed on the places so as to ensure the safety of finance and personnel in the target places.

Then, fig. 2 is a first schematic flow diagram of a security early warning method in an embodiment of the present invention, and referring to fig. 2, the security early warning method may include:

s201: the intelligent equipment collects environmental sound information in a target place;

specifically, the smart device may collect ambient sound information within the target site in real-time or periodically through the sensor array at a sampling frequency.

In practical applications, the sensor array is composed of a number of acoustic sensors (e.g., microphones) for sampling the spatial characteristics of the sound field in the target site to obtain the environmental sound information in the target site.

For example, if the sensor Array is implemented by a Microphone Array (Microphone Array), the sensor Array may be an Array composed of 4 linear uniformly-spaced microphones, an Array composed of 6 linear uniformly-spaced microphones, an Array composed of 8 circular uniformly-spaced microphones, or an Array composed of other numbers and arrangements of microphones, for example, an Array composed of 12 circular, rectangular, crescent uniformly-spaced microphones, etc. Here, the number and arrangement of the microphones in the sensor array are not specifically limited in the embodiments of the present invention.

In practical application, the target places needing security monitoring are different according to different application scenes. For example, the target location may be a home, an office, a warehouse, or other sealable environments, such as an automobile. Here, the embodiments of the present invention are not particularly limited.

In another embodiment of the invention, in order to save resources and reduce power consumption, the intelligent device can collect the environmental sound information only when the security early warning function is started, and does not need to collect the environmental sound information in real time at any time. Then, in a specific implementation process, the foregoing S201 may include: and when a triggering event for activating the security early warning function is detected, activating the security early warning function and starting to collect environmental sound information, wherein the triggering event comprises the step of detecting that the preset security early warning time is reached or receiving an activation instruction forwarded by the server and coming from the user terminal bound with the intelligent equipment.

Here, when the intelligent device activates the security early warning function, it indicates that security early warning needs to be performed on the target site at this time, and then the intelligent device starts to collect environmental sound information in the target site so as to perform security early warning on the target site. Correspondingly, when the security early warning function is not activated by the intelligent device, the intelligent device mainly completes other original functions, for example, when the intelligent sound box is started but the security early warning function is not activated, the audio playing function is mainly completed, and the security early warning is not performed.

In a specific implementation process, an implementation manner for triggering the intelligent device to activate the security early warning function may be implemented by, but not limited to, the following method.

The first implementation mode is that when the intelligent device determines that security early warning needs to be carried out on a target place, the security early warning function is automatically activated.

Specifically, when the intelligent device detects a trigger event such as that a target user leaves a target place to go out, the target user in the target place is in a rest state, and a preset security early warning time is reached, the intelligent device can determine that security early warning needs to be performed on the target place, and at the moment, the security early warning function is automatically activated, so that the intelligent device can collect environmental sound information in the target place in real time or at regular time.

For example, taking a home of which the target location is the target user as an example, the target user may preset a user work and rest schedule, and when the intelligent device detects that the current time reaches the working time in the user work and rest schedule, it indicates that the target user has gone out from home to work, that is, the target user is not in the home, and at this time, the intelligent device may determine that a trigger event is detected, and then activate the security early warning function; for example, when the intelligent device determines that the current time reaches the night rest time in the work and rest schedule of the user, the intelligent device can determine that legal personnel in the target site are in a rest state, and at the moment, the intelligent device can also determine that a trigger event is detected and then activate the security early warning function.

For example, the target user may bind the wearable device with the smart device, so that the smart device may determine whether the target user leaves the target location according to the geographic location information of the user sent by the wearable device, or the smart device may determine whether the target user is currently in a night rest state according to the physiological information of the user sent by the wearable device, such as a heart rate.

In the second implementation mode, the target user manually controls the intelligent device to activate the security early warning function.

Specifically, the target user can remotely control the intelligent device to passively activate the security early warning function through the user terminal bound with the intelligent device. Or, the target user can manually start the security early warning function of the intelligent device when needing to leave the target place to go out, and at the moment, the intelligent device can activate the security early warning function.

For example, the target user may send an activation instruction to the server using a user terminal such as a smart phone or a tablet computer bound to the smart device, and after the smart device receives the activation instruction from the user terminal forwarded by the server, the smart device activates the security early warning function.

Of course, besides the two implementation manners listed above, the implementation manners may also be implemented in other manners, for example, the two implementation manners are used in combination, and the embodiment of the present invention is not particularly limited herein.

S202: the intelligent equipment acquires a first voiceprint characteristic of the environmental sound information;

specifically, after the environmental sound information of the target place is collected, in order to determine whether the target place is abnormal, the intelligent device may perform voiceprint analysis on the environmental sound information, and extract a first voiceprint feature of the environmental sound information.

In practical applications, when the environmental sound information collected by the smart device includes a plurality of sound information segments, correspondingly, the first voiceprint feature may include a plurality of sub-voiceprint features, and each sub-voiceprint feature may correspond to one sound information segment.

In another embodiment of the present invention, in order to save system resources, the smart device may obtain the first voiceprint feature only when the sound intensity value of the environmental sound information is abnormal, so as to further accurately determine whether a suspected abnormal condition occurs in the target location according to the first voiceprint feature and the second voiceprint feature stored in advance. Then, in a specific implementation process, the step S202 may include: detecting whether the sound intensity value of the environmental sound information exceeds a preset sound intensity value; when the sound intensity value of the environment sound information is detected to exceed the preset sound intensity value, carrying out voiceprint analysis on the environment sound information to obtain a first voiceprint characteristic of the environment sound information.

In practical applications, the preset sound intensity value may be one, such as 20 db, or multiple, such as two, three, four, etc. For example, assuming that the preset sound intensity values are set to two, when the smart device needs to perform security early warning in the daytime, the smart device may correspond to one preset sound intensity value, such as 40 db, and when the smart device performs security early warning in the night, the smart device may correspond to another preset sound intensity value, such as 20 db. The number and size of the preset sound intensity values can be determined by those skilled in the art according to actual situations, and embodiments of the present invention are not particularly limited.

S203: and the intelligent equipment determines whether the target place is suspicious or not based on the first voiceprint characteristics and the second voiceprint characteristics stored in advance.

S204: and if the suspicious situation of the target place is determined, the intelligent equipment enters a prepared warning state.

Here, the second voiceprint feature refers to a previously stored voiceprint feature that can indicate whether or not a suspicious situation has occurred in the target site. In practical applications, the second voiceprint feature can be implemented by a voiceprint feature of the target user or a voiceprint feature of the target object in the target place, wherein the voiceprint feature of the target object comprises one or more of a voiceprint feature representing that the target object is opened, a voiceprint feature representing that the target object is broken, and a voiceprint feature representing that the target object falls down. Of course, the second voiceprint feature can be other voiceprint features, such as a combination of the voiceprint feature corresponding to the target user and the voiceprint feature of the target object. Here, the embodiments of the present invention are not particularly limited.

In a specific implementation process, the voiceprint feature of the target user is a voiceprint feature of a voice of the target user. Specifically, the target user may enter his/her voice through the smart device in advance, so that the smart device extracts the voiceprint feature of the target user and stores the voiceprint feature of the target user.

In practical application, according to the difference of the number of target users, the voiceprint features of the users may be one or multiple, for example, when the number of family members in a family is 3, the smart device may respectively record the respective corresponding voices of the 3 family members in advance, so as to respectively extract the respective voiceprint features of the users corresponding to the 3 family members.

In the implementation process, the voiceprint characteristics of the target objects are different according to different types of the target objects. Specifically, the object voiceprint feature may be a voiceprint feature of a sound of opening the target object, such as a voiceprint feature corresponding to a sound of opening a door, a window, a cabinet, or the like, may also be a voiceprint feature of a sound of breaking the target object, such as a voiceprint feature corresponding to a sound of breaking glass, and may also be another type of voiceprint feature, such as a voiceprint feature of a sound of falling down from the target object, a voiceprint feature of a sound of moving the target object, or the like. Here, the embodiments of the present invention are not particularly limited.

In another embodiment of the present invention, the above S203 may exist, but is not limited to, include the following two implementations according to different suspicious situations occurring in the target site.

In a first implementation manner, when the second voiceprint feature is the voiceprint feature of the target user, then, in a specific implementation process, the step S203 may include the following steps a1 to a 2:

step A1: determining whether the environmental sound information contains voice information for representing suspicious people in the target place or not based on the first voiceprint characteristics and the voiceprint characteristics of the target user;

step A2: and if the environmental sound information contains voice information for representing suspicious persons in the target place, determining that the target place has suspicious conditions.

Specifically, when a non-target user speaks in a target place, the environmental sound information collected by the intelligent device includes the voice information of the non-target user, but since it is unclear whether the non-target user legally enters the target place, at this time, the intelligent device can only determine that suspicious people appear in the target place, and thus, the intelligent device can only determine that the target place is suspicious. At this time, the intelligent device may execute step S204 to enter a preliminary warning state, so as to quickly respond when it is determined that the suspicious situation is an abnormal situation and needs to perform formal warning, and output warning information to implement formal warning.

In a second implementation manner, when the second voiceprint feature is the voiceprint feature of the target object, then, in a specific implementation process, the step S203 may include the following steps B1 to B2:

step B1: determining whether the environmental sound information contains sound information used for representing the suspicious situation of the target object or not based on the first voiceprint characteristics and the voiceprint characteristics of the target object;

wherein, the preset sound condition comprises: the voice recognition method comprises one or more of a preset voice speed condition used for representing abnormal emotion of a user, a preset volume condition used for representing abnormal emotion of the user and preset keyword information used for representing that the user is in a dangerous state.

Step B2: and if the environmental sound information contains sound information used for representing the suspicious situation of the target object, determining that the suspicious situation occurs in the target place.

Specifically, when suspicious people appear in the target site, a target object in the target site may be caused to generate sound, and then the environmental sound information collected by the intelligent device includes sound information indicating that the target object generates sound, but it is unclear whether the target object generates sound by natural accident or whether the target object generates sound by human touch of a non-target user, so that it cannot be directly determined whether the target object is in a normal state or an abnormal state, at this time, the intelligent device can only determine that the target object generates suspicious situation, and at this time, the intelligent device may perform step S204 to enter a preliminary warning state, so that it may promptly respond when it is determined that the suspicious situation is an abnormal situation and needs to perform a warning, and output a warning message to implement a formal warning.

Of course, besides the two implementation manners listed above, other implementation manners, such as an implementation manner combining the two implementation manners, may also be adopted. For example, when the smart device performs the step B2 to determine that the environmental sound information does not include the sound information indicating the suspicious situation of the target object, the smart device may continue to perform the step a1 to make the determination. Here, the embodiments of the present invention are not particularly limited.

Based on the foregoing embodiment, after the smart device enters the preliminary warning state after executing S204, in order to determine whether to output warning information for performing formal warning, the smart device further needs to determine whether a suspicious situation occurring in the target location is a normal situation or an abnormal situation. In a specific implementation process, referring to fig. 3, the security early warning method may further include:

s301: the intelligent equipment confirms whether the suspicious situation occurring in the target place is a normal situation or not;

s302: the intelligent equipment starts to output early warning information;

the early warning information is used for warning the target place of abnormal conditions.

In practical applications, the step of outputting the warning information by the intelligent device may include the following steps: sending one or more of environmental sound information to a user terminal bound with the intelligent equipment, sending a start early warning notification message to the user terminal bound with the intelligent equipment, playing preset alarm audio, and controlling an electric lamp bound with the intelligent equipment and positioned in a target place to display preset light effects.

S303: the smart device disarms the ready alert state.

Specifically, when the intelligent device preliminarily determines that suspected abnormal conditions such as suspicious people occurring in the target site and suspicious situations occurring in the target object occur according to the environmental sound information, the intelligent device may enter a preliminary warning state. Next, in order to more accurately determine whether the suspicious situation occurring at the target location needs to be subjected to formal early warning, the intelligent device is required to further confirm whether the suspicious situation occurring at the target location is an abnormal situation requiring the formal early warning or a normal situation requiring no formal early warning according to the environmental sound information. Finally, when the intelligent device determines that the target place has an abnormal condition requiring formal early warning, the intelligent device quickly enters into a formal early warning state and executes S302 to start outputting early warning information, or when the intelligent device determines that the target place has a normal condition requiring no formal early warning, the intelligent device executes S303 to remove a prepared early warning state.

How the intelligent device determines whether formal early warning is needed, that is, whether a suspicious situation is a normal situation or an abnormal situation, is described below.

In a specific implementation process, the step S301 may be implemented by, but not limited to, the following two methods.

In the first method, the intelligent device sends the environmental sound information to the server, so that the server further determines whether to perform formal early warning based on the environmental sound information, and thus, the intelligent device indirectly confirms whether the suspicious situation is a normal situation or an abnormal situation according to a determination result sent by the server.

In other embodiments of the present invention, the above S301 may include: the intelligent equipment sends the environmental sound information to the server so that the server can confirm whether the suspicious situation is a normal situation or not; the intelligent equipment receives a judgment result sent by the server; and the intelligent equipment confirms whether the suspicious situation is a normal situation or not according to the received judgment result.

In practical application, when the server determines that the suspicious situation occurring in the target location is an abnormal situation requiring formal early warning according to the environmental sound information, the intelligent device may receive a determination result sent by the server to indicate that the formal early warning is required, and then the intelligent device may determine that the suspicious situation occurring in the target location is an abnormal situation, and at this time, the formal early warning is required, so that the intelligent device may execute S302 to start outputting the early warning information. When the server determines that the suspicious situation occurring in the target location is a normal situation that does not need to be subjected to formal early warning according to the environmental sound information, the intelligent device may receive a determination result sent by the server to indicate that the formal early warning is not needed, and then the intelligent device may determine that the suspicious situation occurring in the target location is a normal situation, and at this time, the formal early warning is not needed, so that the intelligent device may execute S303 to release the preliminary warning state.

In the second method, the intelligent device directly determines whether to carry out formal early warning according to the environmental sound information.

In another embodiment of the present invention, the step S301 may include the following steps C1 to C4:

step C1: the intelligent device determines whether the environmental sound information contains the sound information of the target user or not based on the first voiceprint characteristics and the voiceprint characteristics of the target user;

specifically, after the intelligent device preliminarily determines that suspicious situations such as suspicious people occurring in the target location and suspicious situations occurring in the target object occur in the target location, in order to further determine whether to perform formal early warning, the intelligent device needs to first determine whether the target user is in the target location when the suspicious situation occurs in the target location. Then, in order to determine whether the target user is within the target site, the smart device may perform step C1 to determine whether the environmental sound information includes the sound information of the target user.

Step C2: if the environmental sound information contains the sound information of the target user, determining whether the target user is in a normal state or not based on the sound information of the target user;

step C3: determining whether the suspicious situation is a normal situation or not based on whether the target user is in a normal state or not;

specifically, if it is determined that the environmental sound information includes the sound information of the target user, the smart device performs steps C2 through C3 to further determine whether the suspicious situation currently occurring at the target location is a normal situation according to whether the target user is in a normal state. Next, if it is determined that the target user is in a normal state, it is determined that the suspicious situation occurring in the target location is a normal situation that does not need to perform formal early warning, and at this time, formal early warning is not needed, so that the intelligent device can execute S303 to release the preliminary warning state; if the target user is determined to be in an abnormal state, the suspicious situation occurring in the target place is determined to be an abnormal situation requiring formal early warning, and at the moment, the formal early warning is required, so that the intelligent device can execute S302 to start outputting early warning information.

In a specific implementation process, in order to determine whether the target user is in a normal state, the step C2 may include: determining whether the sound information of the target user meets a preset sound condition, wherein the preset sound condition comprises: one or more of preset speech speed conditions for representing user emotion abnormity, preset volume conditions for representing user emotion abnormity and preset keyword information for representing that the user is in a dangerous state; if so, determining that the target user is in an abnormal state; otherwise, determining that the target user is in a normal state.

Specifically, when the target user and the suspicious person are both in the target place, if the intelligent device determines that the sound information of the target user indicates that the speech rate of the user is abnormal, or if the intelligent device determines that the sound information of the target user indicates that the volume of the user is abnormal, or if the intelligent device determines that the sound information of the target user contains security-related sensitive keyword information such as rescue, fast-moving alarm, and the like, the intelligent device may determine that the target user is currently in an abnormal state.

In practical application, voice recognition can be performed on the voice information of the target user to obtain corresponding text information, so that voice endpoint information, voice duration and total word number in the voice information of the target user are analyzed, next, an average speed (unit may be: word/second) of the target user is determined, when the average speed exceeds a preset speed threshold, it is indicated that the current emotion of the user is abnormal, then, the intelligent device can determine that the voice information of the target user meets a preset speed condition for representing the emotion abnormality of the user, and at this time, it is determined that the target user is in an abnormal state.

In practical application, whether preset keyword information used for representing that a user is in a dangerous state, such as sensitive words related to user safety, such as rescue, hurry alarm and the like, exists or not can be searched from text information corresponding to sound information of a target user, and when the text information contains the preset keyword information, the user is indicated to be in the dangerous state currently, and then the intelligent device can determine that the target user is in an abnormal state.

In practical application, the sound information of the target user can be subjected to waveform analysis and other processing, the volume information such as the maximum sound intensity value, the maximum frequency value, the maximum amplitude value and the like corresponding to the sound information is detected, when the volume information exceeds a preset volume threshold value, the current emotion of the user is abnormal, then, the intelligent device can determine that the sound information of the target user meets a preset volume condition for representing the emotion abnormality of the user, and at the moment, the target user is determined to be in an abnormal state.

Step C4: determining that the suspicious situation is an abnormal situation;

specifically, if it is determined that the environmental sound information does not include the sound information of the target user, the intelligent device may execute step C4 to directly determine that the suspicious situation currently occurring at the target location is an abnormal situation, at this time, a formal warning needs to be performed, and thus, the intelligent device may execute step S302 to start outputting the warning information.

How the intelligent device performs early warning is explained below.

In another embodiment of the present invention, according to different warning manners adopted by the smart device, the above S302 may exist but is not limited to include the following three cases.

In a first case, the step S302 may include: the intelligent device sends a warning starting notification message to the user terminal bound with the intelligent device, wherein the warning starting notification message is used for warning a target user using the user terminal that the target place is abnormal so as to warn the target user using the user terminal to check the abnormal situation of the target place.

In the second case, in order to frighten abnormal persons who illegally enter the target location, or warn relevant persons such as guard persons and neighbors that the target location is abnormal, the step S302 may further include: and the intelligent equipment plays preset alarm audio.

In the third method, in order to frighten abnormal persons who illegally enter the target location, or warn relevant persons such as guard persons and neighbors that the target location is abnormal, the step S302 may further include: the intelligent device controls the electric lamp bound with the intelligent device and located in the target place to display the preset light effect.

Specifically, when the intelligent device determines that the abnormal condition that needs to be officially pre-warned occurs in the target place, the intelligent device can warn by playing a preset warning audio and/or controlling the electric lamp to display a preset lighting effect, so that abnormal personnel illegally entering the target place can be deterred, the abnormal personnel can immediately stop criminal activities, or alarms are sent to relevant personnel such as guard personnel and neighbors, the relevant personnel can rapidly discover and stop the criminal activities of the abnormal personnel, and the safety of finance and personnel in the target place can be guaranteed.

Of course, besides the three methods listed above, the early warning may be performed in other manners, for example, the above combination, the intelligent device may perform the early warning by sending the environmental sound information to the target user, and the like, where the embodiment of the present invention is not particularly limited.

In another embodiment of the present invention, after the step S302, the method may further include: receiving a control instruction sent by a user terminal bound with the intelligent equipment, wherein the control instruction is used for controlling the intelligent equipment to stop outputting the early warning information; and responding to the control instruction, and stopping outputting the early warning information.

Specifically, when the intelligent device determines that the suspicious situation occurring in the target place is an abnormal situation requiring formal early warning, the intelligent device may start playing a preset alarm audio and/or control the electric lamp to stop displaying the preset light effect. If the target user does not need to continue to perform early warning, for example, the target user returns home to check abnormal conditions, the target user reports to police officers, and the like, the intelligent device receives a control instruction from the user terminal for controlling the intelligent device to stop outputting early warning information, and at the moment, the intelligent device executes an early warning cancellation instruction, stops playing preset warning audio and/or controls the electric lamp to stop displaying preset light effects.

Therefore, the process of carrying out security early warning on the target place based on the intelligent equipment is completed.

As can be seen from the above, according to the security and protection early warning method provided in the embodiment of the present invention, after the intelligent device acquires the environmental sound information in the target location, the intelligent device may obtain the first voiceprint feature of the environmental sound information, and then, the intelligent device may determine whether the target location is suspicious based on the first voiceprint feature and the second voiceprint feature stored in advance, and then, when the intelligent device determines that the target location is suspicious, the intelligent device may enter the preliminary warning state, so that when the suspicious situation occurring in the target location is determined to be an abnormal situation, the intelligent device may output the early warning information quickly, or when the suspicious situation occurring in the target location is a normal situation, the preliminary warning state may be released to reduce the false alarm rate. Like this, gather the environmental sound information in target place through current smart machine in the target place and realize the security protection early warning, need not to increase any extra hardware equipment, also need not to reform transform the hardware of current smart machine, can reduce the safety early warning cost, it is very convenient to use. Therefore, when the method is applied to a home security scene, when a target user goes out or is in a rest state, security early warning can be realized by monitoring the voice of the home through the intelligent equipment which is idle in the home, great convenience can be brought to home security, the intelligent equipment which is idle in the home can be effectively utilized, and resource waste is reduced.

Based on the same inventive concept, an embodiment of the present invention provides a security and protection early warning method, fig. 4 is a schematic flow diagram of the security and protection early warning method in the embodiment of the present invention, and as shown in fig. 4, the security and protection early warning method may include:

s401: when a suspicious situation occurs in a target place, a server receives environmental sound information in the target place sent by an intelligent device;

specifically, when the intelligent device determines that a target place is suspicious, in order to quickly and accurately confirm whether formal early warning is needed or not, the intelligent device sends the collected environmental sound information to the server, and thus, the server receives the environmental sound information.

S402: the server confirms whether the suspicious situation of the target place is a normal situation or not based on the environmental sound information;

s403: the server sends a judgment result for indicating that formal early warning is not needed to be carried out to the client;

s404: and the server sends a judgment result for indicating that formal early warning is required to be carried out to the client.

Specifically, after the server receives the environmental sound information, if the server determines that the suspicious situation occurring in the target location is a normal situation in which the formal warning is not required, the server executes S403 to send a determination result indicating that the formal warning is not required to be performed to the client, so that the client releases the preliminary warning state; if the server determines that the suspicious situation occurring in the target location is an abnormal situation requiring formal early warning, the server executes step S404 to send a determination result indicating that the formal early warning is required to the client, so that the client starts outputting the early warning information.

In a specific implementation process, the step S402 can be implemented by, but not limited to, the following two methods.

In the first method, the intelligent device sends the environmental sound information to the user terminal bound with the intelligent device, so that a user target user of the user terminal further determines whether to carry out formal early warning based on the environmental sound information, and then the server indirectly confirms whether the suspicious situation is a normal situation or an abnormal situation according to an indication message sent by the user terminal.

In other embodiments of the present invention, the above S402 may include: the server sends the environmental sound information to the user terminal bound with the intelligent equipment, so that a user using the user terminal can confirm whether the suspicious situation is normal or not; the server receives an indication message sent by a user terminal; and the server confirms whether the suspicious situation is a normal situation or not according to the received indication message.

In practical application, after the user terminal receives the environmental sound information sent by the server, the target user can confirm whether the suspicious situation of the target place carries out formal early warning or not according to the environmental sound information in response to the environmental sound information. Next, when the target user confirms that the suspicious situation occurring in the target location is an abnormal situation requiring formal early warning, the server may receive an indication message sent by the user terminal to indicate that the suspicious situation occurring in the target location is an abnormal situation requiring formal early warning, and then the server may determine that the suspicious situation occurring in the target location is an abnormal situation, and at this time, the server needs formal early warning, so that the server may send a determination result indicating that the suspicious situation requires formal early warning to the intelligent device, so that the intelligent device executes S302 to start outputting early warning information. When the target user confirms that the suspicious situation occurring in the target place is a normal situation which does not need to be subjected to formal early warning, the server can receive an indication message which is sent by the user terminal and used for indicating that the formal early warning is not needed, then the server can determine that the suspicious situation occurring in the target place is the normal situation, at the moment, the formal early warning is not needed, and therefore the server can send a judgment result which is used for indicating that the formal early warning is not needed to be carried out to the intelligent equipment so that the intelligent equipment can execute S303 to remove the preliminary warning state.

In the second method, the server directly determines whether to carry out formal early warning according to the environmental sound information.

In other embodiments of the present invention, the step S402 may include steps D1-D5:

step D1: the server acquires a first voiceprint characteristic of the environmental sound information;

step D2: the server determines whether the environmental sound information contains the sound information of the target user or not based on the first voiceprint characteristics and the prestored voiceprint characteristics of the target user;

specifically, after the intelligent device preliminarily determines that suspicious situations such as suspicious people occurring in the target location and suspicious situations occurring in the target object occur in the target location, in order to further determine whether to perform formal early warning, the server needs to first determine whether the target user is in the target location when the suspicious situation occurs in the target location. Then, to determine whether the target user is within the target location, the smart device may perform step D2 to determine whether the environmental sound information includes the sound information of the target user.

Step D3: if the environmental sound information contains the sound information of the target user, the server determines whether the target user is in a normal state or not based on the sound information of the target user;

step D4: determining whether the suspicious situation is a normal situation or not based on whether the target user is in a normal state or not;

specifically, if it is determined that the environmental sound information includes the sound information of the target user, the smart device performs steps D3 through C4 to further confirm whether the suspicious situation currently occurring at the target location is a normal situation according to whether the target user is in a normal state. Next, if the target user is determined to be in a normal state, determining that the suspicious situation occurring in the target place is a normal situation without formal early warning; and if the target user is determined to be in an abnormal state, determining that the suspicious situation occurring in the target place is an abnormal situation requiring formal early warning.

In a specific implementation process, in order to determine whether the target user is in a normal state, the step D3 may include: determining whether the sound information of the target user meets a preset sound condition, wherein the preset sound condition comprises: one or more of preset speech speed conditions for representing user emotion abnormity, preset volume conditions for representing user emotion abnormity and preset keyword information for representing that the user is in a dangerous state; if so, determining that the target user is in an abnormal state; otherwise, determining that the target user is in a normal state.

Step D5: the server determines that the suspicious situation is an abnormal situation.

Specifically, if it is determined that the environmental sound information does not include the sound information of the target user, the intelligent device may execute step D5 to directly determine that the suspicious situation currently occurring at the target location is an abnormal situation requiring a formal early warning.

In another embodiment of the present invention, in order to save resources and reduce power consumption, the intelligent device may collect the environmental sound information only when the security and protection early warning function is turned on, and does not need to collect the environmental sound information in real time at any time, so that, in a specific implementation process, when the user manually controls the intelligent device to activate the security and protection early warning function, the method may further include: the method comprises the steps that a server receives an activation instruction sent by a user terminal bound with intelligent equipment, wherein the activation instruction is used for controlling the intelligent equipment to activate a security early warning function; and the server sends an activation instruction to the intelligent equipment so that the intelligent equipment starts to collect the environmental sound information.

As can be seen from the above, according to the security early warning method provided in the embodiment of the present invention, after the intelligent device acquires the environmental sound information in the target location, the intelligent device may obtain the first voiceprint feature of the environmental sound information, and then, the intelligent device may determine whether the target location is suspicious based on the first voiceprint feature and the second voiceprint feature stored in advance, and then, when the intelligent device determines that the target location is suspicious, the intelligent device may enter the preliminary warning state. Next, in order to quickly and accurately confirm whether the suspicious situation occurring in the target location is an abnormal situation or a normal situation, the intelligent device sends the collected environmental sound information to the server, so that the server confirms whether the suspicious situation is a normal situation. Then, after the intelligent device receives the determination result sent by the server, the intelligent device can rapidly output the early warning information when the suspicious situation of the target place is determined to be abnormal according to the determination result, or can remove the prepared warning state to reduce the false alarm rate when the suspicious situation of the target place is determined to be normal according to the determination result. Like this, gather the environmental sound information in target place through current smart machine in the target place and realize the security protection early warning, need not to increase any extra hardware equipment, also need not to reform transform the hardware of current smart machine, can reduce the safety early warning cost, it is very convenient to use. Moreover, the server further judges whether the suspicious situation occurring in the target place is a normal situation or an abnormal situation, so that the early warning speed can be increased or the false warning rate can be reduced.

Based on the same inventive concept, as an implementation of the method, the embodiment of the invention provides a security early warning device, and in practical application, the security early warning device can be applied to intelligent equipment.

Fig. 5 is a schematic structural diagram of a security early warning device in an embodiment of the present invention, and referring to fig. 5, the device 50 may include: the acquisition unit 501 is used for acquiring environmental sound information in a target place; an obtaining unit 502, configured to obtain a first voiceprint feature of environmental sound information; a determining unit 503, configured to determine whether a suspicious situation occurs in the target location based on the first voiceprint feature and a second voiceprint feature stored in advance; the first warning unit 504 is configured to enter a preliminary warning state if the determining unit 503 determines that the target location is suspicious.

In other embodiments of the present invention, the apparatus further comprises: the confirming unit is used for confirming whether the suspicious situation is a normal situation or not; the second early warning unit is used for removing the prepared warning state if the suspicious situation of the target place is confirmed to be a normal situation by the confirming unit; or, the device is also used for starting to output the early warning information if the confirmation unit confirms that the suspicious situation occurring in the target place is an abnormal situation.

In the embodiment of the present invention, the confirming unit is further configured to send the ambient sound information to the server, so that the server confirms whether the suspicious situation is a normal situation; receiving a judgment result sent by the server; and confirming whether the suspicious situation is a normal situation or not according to the received judgment result.

In the embodiment of the present invention, the determining unit is further configured to determine, when the second voiceprint feature is a voiceprint feature of the target user, whether the environmental sound information includes voice information for characterizing suspicious people appearing in the target location based on the first voiceprint feature and the voiceprint feature of the target user; and if so, determining that the target place has a suspicious situation.

In an embodiment of the present invention, the determining unit is further configured to determine, when the second voiceprint feature is a voiceprint feature of the target object, whether sound information for characterizing that the target object is suspicious is included in the environmental sound information based on the first voiceprint feature and the voiceprint feature of the target object, where the voiceprint feature of the target object includes one or more of a voiceprint feature for characterizing that the target object is opened, a voiceprint feature for characterizing that the target object is broken, and a voiceprint feature for characterizing that the target object falls over; and if so, determining that the target place has a suspicious situation.

In the embodiment of the present invention, the determining unit is further configured to determine whether the environmental sound information includes sound information of the target user based on the first voiceprint feature and the voiceprint feature of the target user; if yes, determining whether the target user is in a normal state or not based on the sound information of the target user; determining whether the suspicious situation is a normal situation or not based on whether the target user is in a normal state or not; otherwise, determining the suspicious situation as an abnormal situation.

In an embodiment of the present invention, the determining unit is further configured to determine whether the sound information of the target user satisfies a preset sound condition, where the preset sound condition includes: one or more of preset speech speed conditions for representing user emotion abnormity, preset volume conditions for representing user emotion abnormity and preset keyword information for representing that the user is in a dangerous state; if so, determining that the target user is in an abnormal state; otherwise, determining that the target user is in a normal state.

In other embodiments of the present invention, the apparatus further comprises: the intelligent equipment comprises a receiving unit, a processing unit and a processing unit, wherein the receiving unit is used for receiving a control instruction sent by a user terminal bound with the intelligent equipment, and the control instruction is used for controlling the intelligent equipment to stop outputting early warning information; and the response unit is used for responding to the control instruction and stopping outputting the early warning information.

In the embodiment of the present invention, the obtaining unit is further configured to detect whether a sound intensity value of the environmental sound information exceeds a preset sound intensity value; when the sound intensity value of the environment sound information is detected to exceed the preset sound intensity value, carrying out voiceprint analysis on the environment sound information to obtain a first voiceprint characteristic.

In the embodiment of the present invention, the acquisition unit is further configured to activate the security early warning function and start acquiring environmental sound information when detecting a trigger event for activating the security early warning function, where the trigger event includes detecting that a preset security early warning time is reached or receiving an activation instruction from a user terminal bound to the intelligent device and forwarded by the server.

Based on the same inventive concept, as an implementation of the method, the embodiment of the invention provides a security early warning device, and in practical application, the security early warning device can be applied to a server.

Fig. 6 is a schematic structural diagram of a security early warning device in an embodiment of the present invention, and referring to fig. 6, the device 60 may include: a first receiving unit 601, configured to receive, when a suspicious situation occurs in a target location, environmental sound information in the target location sent by an intelligent device; a confirming unit 602, configured to confirm whether the suspicious situation is a normal situation based on the environmental sound information; a first sending unit 603, configured to send, to the client, a determination result indicating that formal warning is not needed if the suspicious situation is determined to be a normal situation by the determining unit, so that the client releases the preliminary warning state; otherwise, sending a judgment result for indicating that formal early warning is needed to the client so that the client starts to output early warning information.

In the embodiment of the present invention, the confirming unit is further configured to send the environmental sound information to the user terminal bound to the smart device, so that a user using the user terminal confirms whether the suspicious situation is a normal situation; receiving an indication message sent by a user terminal; and confirming whether the suspicious situation is a normal situation or not according to the received indication message.

In the embodiment of the present invention, the confirming unit is further configured to obtain a first voiceprint feature of the environmental sound information; determining whether the environmental sound information contains sound information of the target user or not based on the first voiceprint characteristics and the prestored voiceprint characteristics of the target user; if yes, determining whether the target user is in a normal state or not based on the sound information of the target user; determining whether the suspicious situation is a normal situation or not based on whether the target user is in a normal state or not; otherwise, determining the suspicious situation as an abnormal situation.

In other embodiments of the present invention, the apparatus further comprises: the second receiving unit is used for receiving an activation instruction sent by a user terminal bound with the intelligent equipment, wherein the activation instruction is used for controlling the intelligent equipment to activate a security early warning function; and the second sending unit is used for sending the activation instruction to the intelligent equipment so that the intelligent equipment starts to collect the environmental sound information.

Based on the same inventive concept, the embodiment of the invention provides electronic equipment. Fig. 7 is a schematic structural diagram of an electronic device in an embodiment of the present invention, and referring to fig. 7, the electronic device 70 includes: at least one processor 71; and at least one memory 72, a bus 73 connected to the processor 71; wherein, the processor 71 and the memory 72 complete the communication with each other through the bus 73; the processor 71 is configured to call program instructions in the memory 72 to perform the steps of the security pre-warning method in one or more embodiments described above.

Correspondingly, based on the same inventive concept, the embodiment of the invention further provides a processor, wherein the processor is used for running the program, and the steps of the security early warning method in one or more embodiments are executed when the program runs.

The Processor may be implemented by a Central Processing Unit (CPU), a microprocessor Unit (MPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), or the like. The Memory may include volatile Memory in a computer readable medium, Random Access Memory (RAM), and/or nonvolatile Memory such as Read Only Memory (ROM) or Flash Memory (Flash RAM), and the Memory includes at least one Memory chip.

It should be noted that, in the embodiment of the present invention, if the security early warning method in one or more embodiments is implemented in the form of a software functional module, and is sold or used as an independent product, the security early warning method may also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially or partially implemented in the form of a software product, which is stored in a storage medium and includes instructions for enabling a computer device (which may be a smart phone, a smart speaker, a personal computer, a server, or a network device) to execute all or part of the methods of the embodiments of the present invention.

Accordingly, based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored program, and when the program runs, the apparatus where the storage medium is located is controlled to execute the steps of the security early warning method in one or more embodiments.

Here, it should be noted that: the above description of the apparatus, electronic device or computer-readable storage medium embodiments is similar to the description of the method embodiments above, with similar beneficial effects as the method embodiments. For technical details not disclosed in embodiments of the apparatus, the electronic device or the computer-readable storage medium of the present invention, reference is made to the description of embodiments of the method of the present invention for understanding.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, Compact disk Read-Only Memory (CD-ROM), optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, RAM and/or non-volatile memory, such as ROM or Flash RAM. The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. The computer-readable storage medium may be a ROM, a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a magnetic Random Access Memory (FRAM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical Disc, or a Compact Disc Read-Only Memory (CD-ROM), among other memories; or flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium which can be used to store information and which can be accessed by a computing device; but may also be various electronic devices such as mobile phones, computers, tablet devices, personal digital assistants, etc., that include one or any combination of the above-mentioned memories. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The above are merely examples of the present invention, and are not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A security early warning method is characterized by being applied to intelligent equipment and comprising the following steps:

collecting environmental sound information in a target place;

acquiring a first voiceprint characteristic of the environmental sound information;

determining whether the target place is suspicious or not based on the first voiceprint features and second voiceprint features stored in advance; the second voiceprint feature is a voiceprint feature of a target user, and whether the voice information used for representing suspicious people in the target place is contained in the environment voice information is determined based on the first voiceprint feature and the voiceprint feature of the target user; if yes, determining that the target place has a suspicious situation;

if the target place is determined to have a suspicious situation, entering a prepared warning state;

confirming whether the suspicious situation is a normal situation, specifically: determining whether the environmental sound information contains sound information of the target user or not based on the first voiceprint characteristics and the voiceprint characteristics of the target user; if yes, determining whether the target user is in a normal state or not based on the sound information of the target user; determining whether the suspicious situation is a normal situation or not based on whether the target user is in a normal state or not; otherwise, determining the suspicious situation as an abnormal situation; if the situation is normal, the preparation warning state is released; otherwise, the early warning information is output.

2. The method of claim 1, wherein said confirming whether said suspicious condition is a normal condition comprises:

sending the environmental sound information to a server so that the server can confirm whether the suspicious situation is a normal situation or not;

receiving a judgment result sent by the server;

and confirming whether the suspicious situation is a normal situation or not according to the received judgment result.

3. The method of claim 1, wherein determining whether the target site is suspicious based on the first voiceprint feature and a second prestored voiceprint feature comprises:

when the second voiceprint feature is a voiceprint feature of the target object, determining whether sound information for representing that the target object is suspicious is contained in the environment sound information or not based on the first voiceprint feature and the voiceprint feature of the target object, wherein the voiceprint feature of the target object comprises one or more of a voiceprint feature for representing that the target object is opened, a voiceprint feature for representing that the target object is broken and a voiceprint feature for representing that the target object falls down;

and if so, determining that the target place has a suspicious situation.

4. The method of claim 1, wherein the determining whether the target user is in a normal state based on the voice information of the target user comprises:

determining whether the sound information of the target user meets a preset sound condition, wherein the preset sound condition comprises: one or more of preset speech speed conditions for representing user emotion abnormity, preset volume conditions for representing user emotion abnormity and preset keyword information for representing that the user is in a dangerous state;

if so, determining that the target user is in an abnormal state; otherwise, determining that the target user is in a normal state.

5. The method of claim 1, wherein after the beginning of outputting pre-alarm information, the method further comprises:

receiving a control instruction from a user terminal bound with the intelligent equipment, wherein the control instruction is used for controlling the intelligent equipment to stop outputting early warning information;

and responding to the control instruction, and stopping outputting the early warning information.

6. The method of claim 1, wherein the obtaining the first voiceprint feature of the ambient sound information comprises:

detecting whether the sound intensity value of the environmental sound information exceeds a preset sound intensity value;

and when the sound intensity value of the environment sound information is detected to exceed a preset sound intensity value, carrying out voiceprint analysis on the environment sound information to obtain the first voiceprint characteristic.

7. The method of claim 1, wherein the collecting environmental sound information within the target site comprises:

and when a triggering event for activating the security early warning function is detected, activating the security early warning function and starting to collect the environmental sound information, wherein the triggering event comprises the detection of the arrival of preset security early warning time or the reception of an activation instruction forwarded by a server and coming from a user terminal bound with the intelligent equipment.

8. A security early warning method is characterized by being applied to a server and comprising the following steps:

acquiring environmental sound information in a target place, comparing the environmental sound information with sound information of a target user, and determining whether the environmental sound information contains voice information for representing suspicious people in the target place; if yes, determining that the target place has a suspicious situation; when a suspicious situation occurs in a target place, receiving environmental sound information in the target place sent by intelligent equipment;

based on the environmental sound information, determining whether the suspicious situation is a normal situation, specifically: acquiring a first voiceprint characteristic of the environmental sound information; determining whether the environmental sound information contains sound information of the target user or not based on the first voiceprint characteristics and prestored voiceprint characteristics of the target user; if yes, determining whether the target user is in a normal state or not based on the sound information of the target user; determining whether the suspicious situation is a normal situation or not based on whether the target user is in a normal state or not; otherwise, determining the suspicious situation as an abnormal situation;

if the situation is normal, sending a judgment result for indicating that formal early warning is not needed to the client so that the client releases the prepared warning state; otherwise, sending a judgment result for indicating that formal early warning is needed to the client so that the client starts to output early warning information.

9. The method of claim 8, wherein the confirming whether the suspicious situation is a normal situation based on the environmental sound information comprises:

sending the environmental sound information to a user terminal bound with the intelligent equipment so that a user using the user terminal can confirm whether the suspicious situation is normal or not;

receiving an indication message sent by the user terminal;

and confirming whether the suspicious situation is a normal situation or not according to the received indication message.

10. The method of claim 8, wherein the determining whether the target user is in a normal state based on the voice information of the target user comprises:

11. The method according to claim 8, wherein before receiving the ambient sound information in the target site sent by the smart device when the suspicious situation occurs in the target site, the method further comprises:

receiving an activation instruction sent by a user terminal bound with the intelligent equipment, wherein the activation instruction is used for controlling the intelligent equipment to activate a security early warning function;

and sending the activation instruction to the intelligent equipment so that the intelligent equipment starts to acquire the environmental sound information.

12. The utility model provides a security protection early warning device which characterized in that is applied to smart machine, the device includes:

the acquisition unit is used for acquiring environmental sound information in a target place;

the acquisition unit is used for acquiring a first voiceprint characteristic of the environmental sound information;

the determining unit is used for determining whether the target place is suspicious or not based on the first voiceprint characteristics and second voiceprint characteristics stored in advance; the second voiceprint feature is a voiceprint feature of a target user, and whether the voice information used for representing suspicious people in the target place is contained in the environment voice information is determined based on the first voiceprint feature and the voiceprint feature of the target user; if yes, determining that the target place has a suspicious situation;

the first early warning unit is used for entering a prepared warning state if the determining unit determines that the target site has a suspicious situation;

the confirming unit is used for confirming whether the suspicious situation is a normal situation, and is specifically used for: determining whether the environmental sound information contains sound information of the target user or not based on the first voiceprint characteristics and the voiceprint characteristics of the target user; if yes, determining whether the target user is in a normal state or not based on the sound information of the target user; determining whether the suspicious situation is a normal situation or not based on whether the target user is in a normal state or not; otherwise, determining the suspicious situation as an abnormal situation;

the second early warning unit is used for removing the prepared warning state if the suspicious situation of the target place is confirmed to be a normal situation by the confirming unit; or, the device is also used for starting to output the early warning information if the confirmation unit confirms that the suspicious situation occurring in the target place is an abnormal situation.

13. The utility model provides a security protection early warning device which characterized in that is applied to the server, the device includes:

the first receiving unit is used for acquiring environmental sound information in a target place, comparing the environmental sound information with sound information of a target user, and determining whether the environmental sound information contains voice information for representing suspicious people in the target place; if yes, determining that the target place has a suspicious situation; when a suspicious situation occurs in a target place, receiving environmental sound information in the target place sent by intelligent equipment;

a confirming unit, configured to confirm whether the suspicious situation is a normal situation based on the environmental sound information, and specifically configured to: acquiring a first voiceprint characteristic of the environmental sound information; determining whether the environmental sound information contains sound information of the target user or not based on the first voiceprint characteristics and prestored voiceprint characteristics of the target user; if yes, determining whether the target user is in a normal state or not based on the sound information of the target user; determining whether the suspicious situation is a normal situation or not based on whether the target user is in a normal state or not; otherwise, determining the suspicious situation as an abnormal situation;

a first sending unit, configured to send, to a client, a determination result indicating that a formal warning is not needed if the suspicious situation is determined to be a normal situation by the determining unit, so that the client releases a preliminary warning state; otherwise, sending a judgment result for indicating that formal early warning is needed to the client so that the client starts to output early warning information.

14. A computer-readable storage medium, characterized in that the storage medium includes a stored program, wherein when the program runs, the apparatus on which the storage medium is located is controlled to execute the steps of the security early warning method according to any one of claims 1 to 11.

15. An electronic device, characterized in that the electronic device comprises:

at least one processor;

and at least one memory, bus connected with the processor;

the processor and the memory complete mutual communication through the bus; the processor is configured to call program instructions in the memory to perform the steps of the security pre-warning method of any one of claims 1 to 11.