CN115881136B

CN115881136B - Voice information processing method and related device based on conflict event in campus scene

Info

Publication number: CN115881136B
Application number: CN202310044598.3A
Authority: CN
Inventors: 王一
Original assignee: Shenzhen Renma Interactive Technology Co Ltd
Current assignee: Shenzhen Renma Interactive Technology Co Ltd
Priority date: 2023-01-30
Filing date: 2023-01-30
Publication date: 2023-08-18
Anticipated expiration: 2043-01-30
Also published as: CN115881136A

Abstract

The embodiment of the application provides a voice information processing method and a related device based on an event under a scene, which can acquire environment sound information when a monitoring condition is met, then determine the role played by a user in the event according to a target word in the environment sound information, conduct targeted guidance according to the identity of the user, prompt the user in time to stop the user behavior when the user is an event initiator, acquire the idea of the user for the event through dialogue with the user when the user is an event receiver, and propose corresponding suggestions, fully respect the user will, enable the user to accept the suggestions more easily, and reduce the data processing complexity when judging the event.

Description

Voice information processing method and related device based on conflict event in campus scene

Technical Field

The application belongs to the technical field of general data processing in the Internet industry, and particularly relates to a voice information processing method based on conflict events in a campus scene and a related device.

Background

Campus violence refers to an aggressive behavior occurring outside and inside a school, which may cause physical, psychological, etc. injuries to victims, and its common manifestations include physical violence, emotional or psychological violence, and spoofing. Because minors' mind and the like are not mature enough, the minors are difficult to get external timely intervention no matter whether they apply or suffer from campus violence, so that the campus violence can not be stopped. Therefore, a scheme capable of accurately identifying the campus violence and guiding minors to accurately solve the campus violence when the campus violence occurs is urgently needed.

Disclosure of Invention

The embodiment of the application provides a voice information processing method based on a conflict event in a campus scene and a related device, aiming at improving the accuracy and timeliness of identifying the conflict event in the campus and guiding a user in a targeted manner.

In a first aspect, an embodiment of the present application provides a method for processing voice information based on a collision event in a campus scenario, which is applied to a man-machine conversation server in a security protection system, where the security protection system includes the man-machine conversation server and a first electronic device, and the method includes:

acquiring environmental sound information from the first electronic device under the condition that monitoring conditions are met, wherein the meeting of the monitoring conditions comprises acquiring a monitoring instruction or meeting monitoring time;

determining whether at least one target word exists in the environmental sound information, wherein the word type of the target word belongs to a threat disfiguring word type or a distress word type;

if the at least one target word exists, determining whether sound information of a user exists in sound information corresponding to the at least one target word;

if the voice information of the user exists, determining the identity of the user according to the word type of the target word, wherein the identity comprises a conflict event initiator or a conflict event receiver;

Sending first prompt information to the first electronic equipment under the condition that the identity of the user is the conflict event initiator, wherein the first prompt information is used for prompting the user to stop the behavior of injuring other people;

storing environment sound information containing the target words and sending first inquiry information to the first electronic equipment under a safety environment under the condition that the identity of the user is the collision event carrier, wherein the safety environment is an environment without collision event, and the first inquiry information is used for inquiring whether the user suffers personal damage or not;

acquiring first reply information from the first electronic equipment;

transmitting second inquiry information to the first electronic device in case that the first reply information indicates that the user suffers personal damage, wherein the second inquiry information is used for inquiring whether the user needs help or not;

acquiring second reply information from the first electronic equipment;

sending second prompt information to the first electronic device when the second reply information indicates that the user needs help, wherein the second prompt information is used for prompting the user that voice evidence is saved and prompting measures which can be taken by the user;

Transmitting third query information to the first electronic device, the third query information being used to query the user for a solution, if the second reply information indicates that the user does not need assistance;

acquiring third reply information from the first electronic equipment, wherein the third reply information is used for indicating a solution mode of the user;

determining attitudes of the users according to the solution modes, wherein the attitudes comprise positive solution attitudes or negative solution attitudes;

sending third prompt information to the first electronic device when the attitude is a negative solution attitude, wherein the third prompt information is used for encouraging the user to positively solve the problem and prompting measures which can be taken by the user;

under the condition that the attitude is an active solution attitude, determining whether a solution mode of the user is feasible according to the third reply information;

if the solution is not feasible, a fourth prompt message is sent to the first electronic device, wherein the fourth prompt message is used for prompting the user that the solution is not feasible and prompting the user to take measures.

In a second aspect, an embodiment of the present application provides a voice information processing apparatus based on a collision event in a campus scenario, which is applied to a man-machine conversation server in a security protection system, where the security protection system includes the man-machine conversation server and a first electronic device, and the apparatus includes:

The first acquisition unit is used for acquiring the environmental sound information from the first electronic equipment under the condition that the monitoring condition is met, wherein the meeting of the monitoring condition comprises acquiring a monitoring instruction or meeting the monitoring time;

the first determining unit is used for determining whether at least one target word exists in the environment sound information, and the word type of the target word belongs to a threat and anti-foul word type or a distress word type;

a second determining unit, configured to determine whether sound information of a user exists in sound information corresponding to the at least one target word if the at least one target word exists;

a third determining unit, configured to determine, if there is voice information of the user, an identity of the user according to a word type of the target word, where the identity includes a conflict event initiator or a conflict event receiver;

the first sending unit is used for sending first prompt information to the first electronic equipment under the condition that the identity of the user is the conflict event initiator, wherein the first prompt information is used for prompting the user to stop the behavior of injuring other people;

the second sending unit is used for storing the environment sound information containing the target words and sending first inquiry information to the first electronic equipment under a safety environment when the identity of the user is the collision event carrier, wherein the safety environment is an environment without collision event, and the first inquiry information is used for inquiring whether the user suffers personal damage or not;

A second obtaining unit, configured to obtain first reply information from the first electronic device;

a third sending unit, configured to send second query information to the first electronic device, where the first reply information indicates that the user suffers personal injury, where the second query information is used to query whether the user needs help;

a third obtaining unit, configured to obtain second reply information from the first electronic device;

a fourth sending unit, configured to send, if the second reply information indicates that the user needs help, second prompt information to the first electronic device, where the second prompt information is used to prompt the user that voice evidence has been saved, and prompt measures that the user can take;

a fifth transmitting unit configured to transmit third query information to the first electronic device, the third query information being used to query the user solution, in a case where the second reply information indicates that the user does not need help;

a fourth obtaining unit configured to obtain third reply information from the first electronic device, the third reply information being used to indicate a solution of the user;

A fourth determining unit, configured to determine an attitude of the user according to the solution, where the attitude includes a positive solution attitude or a negative solution attitude;

a sixth sending unit, configured to send, to the first electronic device, third prompting information, where the third prompting information is used to encourage the user to actively solve the problem, and prompt the user for a measure that can be taken;

a fifth determining unit, configured to determine, according to the third reply information, whether a solution of the user is feasible, in a case where the attitude is an active solution attitude;

a seventh sending unit, configured to send, if not feasible, a fourth prompting message to the first electronic device, where the fourth prompting message is configured to prompt the user that the solution is not feasible, and prompt the user of measures that can be taken.

In a third aspect, embodiments of the present application provide a server comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the first aspect of embodiments of the present application.

In a fourth aspect, embodiments of the present application provide a computer storage medium having stored thereon a computer program/instruction for execution by a processor to perform the steps of the method of the first aspect described above.

In a fifth aspect, embodiments of the present application provide a computer program product, wherein the computer program product comprises a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

It can be seen that, in this embodiment of the present application, a human-machine dialogue server obtains environmental sound information from the first electronic device when a monitoring condition is satisfied, then determines whether at least one target word exists in the environmental sound information, if at least one target word exists, determines whether there is sound information of the user in sound information corresponding to the at least one target word, if there is sound information of the user, then determines an identity of the user according to a word type of the target word, the identity includes a conflicting event initiator or a conflicting event receiver, in case that the identity of the user is the conflicting event initiator, sends a first prompt message to the first electronic device, the first prompt message is used for prompting the user to stop damaging other people, in case that the identity of the user is the conflicting event receiver, saves environmental sound information including the target word, and sends a first query message to the first electronic device in a secure environment, the secure environment is a non-conflicting environment, the first query message is used for acquiring personal information, then sends a second query message to the first electronic device, and then sends a second query message to the second electronic device, and the second query message is sent to the first electronic device in response to the response message, the second prompt message is used for prompting the user to save voice evidence and prompting measures which can be taken by the user, in the case that the second reply message indicates that the user does not need help, third query message is sent to the first electronic device, the third query message is used for querying the solution mode of the user, then third reply message from the first electronic device is obtained, the third reply message is used for indicating the solution mode of the user, then attitude of the user is determined according to the solution mode, the attitude comprises an active solution attitude or a passive solution attitude, in the case that the attitude is the passive solution attitude, third prompt message is sent to the first electronic device, the third prompt message is used for encouraging the user to actively solve, and prompting measures which can be taken by the user, in the case that the attitude is the active solution attitude, whether the solution mode of the user is feasible or not is determined according to the third reply message, and if not feasible, fourth prompt message is sent to the first electronic device, and in the case that the fourth prompt message is not feasible for the user to solve the problem.

Therefore, whether the user is in a conflict event can be accurately and timely judged according to the voice information, and the complexity of data processing is reduced. The scheme can also determine the role played by the user in the conflict event, conduct targeted guidance according to the identity of the user, acquire the idea of the user aiming at the conflict event through dialogue with the user and propose corresponding suggestions when the user is a conflict event receiver, fully respect the user will, enable the user to accept the suggestions more easily, and enable the conflict event to be resolved more timely and efficiently.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of a security system according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of a server according to an embodiment of the present application;

Fig. 3 is a schematic flow diagram of a method for processing voice information based on a collision event in a campus scenario according to an embodiment of the present application;

FIG. 4 is a schematic illustration of a man-machine conversation page provided by an embodiment of the present application;

FIG. 5 is a functional block diagram of a speech information processing device based on a collision event in a campus scenario according to an embodiment of the present application;

fig. 6 is a functional unit composition block diagram of a voice information processing device based on a collision event in another campus scenario according to an embodiment of the present application.

Detailed Description

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

When the campus conflict event or the campus violence is judged, the information is directly sent to the contact corresponding to the user only after the user is subjectively judged to suffer from the campus violence, whether the judgment is correct or not is not verified, and the opinion of the user is not asked, so that the contradiction between the user and other people is easily aggravated, and the influence on other classmates is caused under the condition of misjudgment. And the contact person is directly informed, so that the user can have inverse psychology or aggravate the spell state of the user, and the like, which is not beneficial to protecting the mental health of the user. And the coping strategy after determining the campus violence is single, reasonable advice can not be given by combining the actual situation of the user, and the current conflict event is not solved by the user.

In view of the above problems, the embodiments of the present application provide a method and a related device for processing voice information based on a collision event in a campus scenario, and the embodiments of the present application are described in detail below with reference to the accompanying drawings.

Referring to fig. 1, fig. 1 is a schematic diagram illustrating a safety protection system according to an embodiment of the application. The security protection system 10 includes a human-machine interaction server 101 and a first electronic device 102, where the human-machine interaction server 101 is communicatively connected to the first electronic device 102, and the first electronic device 102 may include a plurality of first electronic devices, that is, a plurality of first electronic devices are respectively communicatively connected to the human-machine interaction server 101. The chat robots are deployed in the man-machine conversation server 101 and are used for carrying out information interaction with the first electronic device 102, the first electronic device 102 is provided with a corresponding program, instructions of the chat robots can be adapted and interacted with the chat robots, the chat robots can analyze voice information from the first electronic device 102, user semantics are determined, reply sentences are determined according to the user semantics and are output through the first electronic device 102, and man-machine interaction with a user is achieved. In particular, the security protection system 10 may further include a plurality of second electronic devices 103, where the plurality of second electronic devices 103 are respectively communicatively connected to the human-machine interaction server 101 and the first electronic device 102, that is, one first electronic device 102 may correspond to at least one second electronic device 103, and each second electronic device 103 is communicatively connected to the human-machine interaction server 101 and the first electronic device 102. The security protection system 10 may further include a campus security platform server 104, where the campus security platform server 104 is communicatively connected to the man-machine interaction server 101, so that when a condition is met, the man-machine interaction server 101 sends corresponding event information to the campus security platform server 104.

Referring to fig. 2, fig. 2 is a schematic structural diagram of a server according to an embodiment of the application. As shown, the server 110 may be the man-machine conversation server 101 or the campus security platform server 104 according to the present embodiment, where the server 110 includes a processor 120, a memory 130, a communication interface 140, and one or more programs 131, where the one or more programs 131 are stored in the memory 130 and configured to be executed by the processor 120, and the one or more programs 131 include instructions for executing any of the following method embodiments. In a specific implementation, the processor 120 is configured to perform any step performed by a server in a method embodiment described below, and when performing data transmission such as sending, the communication interface 140 is optionally invoked to complete a corresponding operation.

The electronic device according to the embodiment of the present application may be the first electronic device 102 or the second electronic device 103, where the electronic device may be an electronic device with communication capability, and the electronic device may include various handheld devices with wireless communication functions, an in-vehicle device, a wearable device, a computing device, or other processing devices connected to a wireless modem, and various types of User Equipment (UE), a Mobile Station (MS), a terminal device (terminal device), and so on.

Referring to fig. 3, fig. 3 is a flowchart of a method for processing voice information based on a collision event in a campus scenario, where the method for processing voice information based on a collision event in a campus scenario is applied to a man-machine conversation server in a security protection system, and the security protection system includes the man-machine conversation server and a first electronic device, and the method includes the following steps.

S201, acquiring environment sound information from the first electronic equipment when the monitoring condition is met.

Wherein, the meeting the monitoring condition comprises obtaining a monitoring instruction or meeting monitoring time. The acquiring the monitoring instruction may be that the user clicks a control on the first electronic device, and opens the monitoring function. Or the safety protection system also comprises second electronic equipment, the second electronic equipment is respectively in communication connection with the first electronic equipment and the man-machine conversation server, and a monitoring instruction is sent to the first electronic equipment through the second electronic equipment, so that the first electronic equipment meets the monitoring condition. Because the user corresponding to the first electronic device is usually a minor, especially a student, the user of the second electronic device can be a guardian of the user of the corresponding first electronic device, and the guardian opens the monitoring function, so that the first electronic device can collect the environmental sound information, and the protection of the student is realized. The monitoring time can be the time which is set by the user and corresponds to the first electronic equipment, or the time which is set by the user of the second electronic equipment, or the time is determined according to a learning time table of the user. The meeting of the monitoring condition may also be to acquire a target word and then wake up the monitoring function, i.e. the monitoring function of the first electronic device is in a dormant state under normal conditions, but after receiving a corresponding wake up word, for example, when a word with a word type threatening over-insulation is acquired, the monitoring function is woken up. It should be noted that the user or the guardian of the user is authorized in advance before the monitoring function is turned on.

In one possible example, before the acquiring the environmental sound information from the first electronic device, the method further includes: acquiring course time information of the user; determining the learning time, the learning time and the inter-class time of the user according to the course time information; and determining the school time, the school time and the inter-class time as the monitoring time.

The lesson time information can be used for determining the lesson time of the user, and the departure time and the arrival time of the user can be determined according to the habit of the user or the time set by the user, and then the learning time and the learning time of the user can be determined. The learning time refers to the time from home departure to start of a lesson, and the learning time refers to the time from the last lesson to home. The user going out time may be set by the second electronic device, and the user going out time may be determined according to user habit, for example, the user going out time set by the second electronic device, or when sound information of a guardian of the user or a big person frequently appearing around the user is detected in ambient sound, the user is judged to go out of home, at this time, the user may not go out of home yet, but because guardians exist around the user, the user is almost impossible to encounter a conflict event, and therefore, no longer monitoring is needed.

Therefore, in the example, the automatic acquisition of the environmental sound information can be carried out in the middle of learning, the middle of learning and the course of teaching and in the course of teaching, so that the user can be automatically protected in the period of the possible campus conflict event, the comprehensiveness and timeliness of the acquisition of the environmental sound information are improved, and the user can be guided in time when the user encounters the campus conflict event.

S202, determining whether at least one target word exists in the environment sound information.

Wherein, the word type of the target word belongs to the type of the threat insulting word or the type of the help seeking word. The offensive insult words are words that are used to indicate negative emotion. When determining whether a word is a threat-to-be-abused word, the official definition of the word can be determined first, if the official definition is determined not to belong to the threat-to-be-abused word, whether the word comprises a network extension is determined, and if the word has a negative emotion in the network extension, the official definition belongs to the threat-to-be-abused word. The help-seeking words can be general words such as "ask you for help", "rescue", and the like, and also can comprise help-seeking words set by the user independently, namely, the help-seeking words comprise general words with help-seeking meaning and special help-seeking words set by the user. Only the abuse threat words or the help seeking words may exist in the environmental sound, and the abuse threat words and the help seeking words may also occur at the same time.

S203, if the at least one target word exists, determining whether the voice information corresponding to the at least one target word contains voice information of a user.

The voice information may indicate the voiceprint feature of the user, that is, the voice information may indicate the content of the utterance and the speaker corresponding to the content at the same time. The sound characteristics of the user can be acquired in advance, then in the acquired environment sound information, the sound characteristics contained in the sound information corresponding to the target words are determined, then matching is carried out according to the sound characteristics and the sound characteristics of the user, whether the target words are sent by the user or not is determined, or when a plurality of target words exist, which target word is sent by the user is determined.

S204, if the voice information of the user exists, determining the identity of the user according to the word type of the target word.

Wherein the identity comprises a conflict event initiator or a conflict event carrier. When the voice information of the user exists, determining a target word corresponding to the user according to the voice information of the user, and then determining the word type of the target word corresponding to the user, so as to determine the identity of the user. If the target word corresponding to the user is a threat and profoundly-used word, the identity of the user is a conflict event initiator, and if the target word corresponding to the user is a distress word, the identity of the user is a conflict event carrier. The conflict event in the scheme can be campus violence, when the voice information of the user exists in the voice information corresponding to the target word, the identity of the user can be the person who implements the campus violence, or the user is the person suffering from the campus violence, namely the person suffering from the personal injury, and the personal injury in the scheme comprises physical and psychological injuries.

S205, sending first prompt information to the first electronic equipment under the condition that the identity of the user is the conflict event initiator.

The first prompt information is used for prompting the user to stop the action of injuring others. Namely, when the identity of the user is a person injuring other people, the behavior of the user needs to be stopped in time. The content in the first prompt information can be of a warning type or a counseling type, and different types of first prompt information can be sent out according to the individuality of the user. For example, if the personality of the user is good for hearing the opinion according to the historical man-machine conversation record of the user, the first prompt information may be a counseling class, and if the personality of the user is bad for hearing the opinion according to the historical man-machine conversation record, the first prompt information is a warning class. The user can be guided in a targeted manner according to different types of the first prompt information output by different individuality, the probability that the user stops injuring other people after the first prompt information is acquired is increased, and the timeliness and effectiveness of guiding the user are enhanced.

And S206, if the identity of the user is the conflict event carrier, storing the environment sound information containing the target words, and sending first inquiry information to the first electronic equipment in a safe environment.

The safety environment is an environment without a conflict event, and the first inquiry information is used for inquiring whether the user suffers personal damage or not. When the user is determined to be a person suffering from the violence of the campus, the environmental sound information containing the target word is firstly stored, and the stored environmental sound information can be a period of time before the target word is acquired and until only the sound information of the user in the environmental sound information. Determining whether the user is in a secure environment includes: after the target word preset period is acquired, analyzing the current environment sound information to determine that the current environment is a quiet environment, or determining that the user is in a safe environment if the current environment sound information only comprises the sound information of the user. When the first inquiry information is sent to the user, the user is required to be in an environment with stable mind and no other threat around, namely, when the user suffers from campus violence for a period of time, the emotion is stable, other people who implement the campus violence leave, and the user is inquired whether the user suffers from personal damage or not, at this time, a more accurate and objective answer can be obtained, and the user can be guided conveniently and correctly. The first inquiry information may be generated according to the age of the user, for example, if the user is older, the first inquiry information is "whether someone is cheating your" and if the user is older, the existence of campus violence can be recognized, the first inquiry information is "whether you are suffering from campus violence".

S207, first reply information from the first electronic equipment is acquired.

S208, sending second inquiry information to the first electronic equipment under the condition that the first reply information indicates that the user suffers personal damage.

Wherein the second inquiry information is used for inquiring whether the user needs help. The first reply information is voice information input by a user through the first electronic equipment, after the first reply information is acquired by the man-machine conversation server, semantic analysis is carried out on the first reply information, user semantics are determined, and whether the user suffers personal damage or not is determined according to the combination of the user semantics and the first inquiry information, namely whether the user suffers campus violence or not is determined.

S209, obtaining second reply information from the first electronic equipment.

And S210, sending second prompt information to the first electronic equipment under the condition that the second reply information indicates that the user needs help.

Wherein, for example, as shown in fig. 4, the second prompt message is used for prompting the user to save voice evidence and prompting the user to take measures. The prompt user can store voice evidence to give the user more security sense, so that the user can more easily receive the second prompt information to inform the user of the possibility of taking measures. Due to the information acquisition difference and the age mental problem of the user, the user may not know what to do after suffering from campus violence even if trying to seek help, and there may be a home reason of the user, so that only the available measures known by the user but not actually realized. For example, the user is a left-behind child, the home guardian is a grandmaster of the user, and the grandmaster can only be used as a normal alarm for a child even if the user informs the grandmaster, so that the user cannot solve the current conflict event. The method can be used for informing parents, informing the executive entrepreneurs, and the school security platform telephones and the like in the adoptable measures sent to the users, so that the users can select the mode which is most suitable for the actual situation of the users in the adoptable measures, and the feasibility and efficiency of solving the conflict event problem are improved.

S211, sending third inquiry information to the first electronic equipment under the condition that the second reply information indicates that the user does not need assistance.

Wherein the third query information is used to query the user for a solution. I.e. the third inquiry information is used to ask the user how to prepare.

S212, obtaining third reply information from the first electronic equipment.

S213, determining the attitude of the user according to the solution mode.

Wherein the third reply information is used for indicating a solution of the user, and the attitudes comprise an active solution attitudes or a passive solution attitudes. The positive solution attitude, i.e. whether the user's solution is viable or not, is that the user wants to solve this thing, not silently, but rather the negative solution attitude, i.e. that the user is not ready to resolve the conflicting event.

And S214, sending third prompt information to the first electronic equipment under the condition that the attitude is the negative solution attitude.

And S215, determining whether the solution of the user is feasible according to the third reply information in the case that the attitude is the positive solution attitude.

And S216, if not, sending fourth prompt information to the first electronic equipment.

Wherein the third prompt message is used for encouraging the user to positively solve the problem and prompting the user to take measures. The fourth prompting information is used for prompting the user that the solution is not feasible and notifying the user of measures which can be taken. When the user is ready to silently bear the violence of the campus, the user is encouraged to actively solve and feasible measures are provided, when the user solution is feasible, the user does not insert the current event any more, the user can autonomously solve the problem, and if the user solution is not feasible, the user is informed in time and a feasible solution is provided for the user to select. Thus, not only the user will be fully respected, but also the guiding user can be encouraged to take correct measures to solve the problem of campus violence. Determining whether it is feasible includes: and carrying out semantic analysis on the third reply information, extracting keywords, determining the user intention according to the keywords, matching the user intention with the applicable measures, determining that the matching is feasible if the matching is successful, inquiring the reason why the solution is adopted by the user if the matching is unsuccessful, analyzing whether the logic of the reason why the user answers is correct or not, and determining that the matching is feasible if the logic is correct.

It can be seen that, in this example, the human-machine dialogue server obtains the environmental sound information from the first electronic device under the condition that the monitoring condition is met, then determines whether at least one target word exists in the environmental sound information, if at least one target word exists, determines whether the sound information of the user exists in the sound information corresponding to the at least one target word, if the sound information of the user exists, then determines the identity of the user according to the word type of the target word, the identity includes a conflict event initiator or a conflict event receiver, in the case that the identity of the user is the conflict event initiator, sends a first prompt message to the first electronic device, the first prompt message is used for prompting the user to stop the action of damaging other people, in the case that the identity of the user is the conflict event receiver, stores the environmental sound information including the target word, and sends a first query message to the first electronic device under the security environment in which is damaged by the damage, the security environment in which no conflict event exists, the first query message is used for querying whether the user is used for acquiring the personal information of the user, then sends a second query message to the second electronic device under the condition that the first query message is required to be sent to the second electronic device, and then sends a second query message to the first electronic device under the condition that the response message is required to the first query message is sent to the first response message, the second prompt message is used for prompting the user to save voice evidence and prompting measures which can be taken by the user, in the case that the second reply message indicates that the user does not need help, third query message is sent to the first electronic device, the third query message is used for querying the solution mode of the user, then third reply message from the first electronic device is obtained, the third reply message is used for indicating the solution mode of the user, then attitude of the user is determined according to the solution mode, the attitude comprises an active solution attitude or a passive solution attitude, in the case that the attitude is the passive solution attitude, third prompt message is sent to the first electronic device, the third prompt message is used for encouraging the user to actively solve, and prompting measures which can be taken by the user, in the case that the attitude is the active solution attitude, whether the solution mode of the user is feasible or not is determined according to the third reply message, and if not feasible, fourth prompt message is sent to the first electronic device, and in the case that the fourth prompt message is not feasible for the user to solve the problem.

Therefore, whether the user is in the conflict event scene can be accurately and timely judged according to the voice information, and the complexity of data processing is reduced. The scheme can also determine the role played by the user in the conflict event scene, conduct targeted guidance according to the identity of the user, acquire the idea of the user aiming at the conflict event through dialogue with the user and propose corresponding suggestions when the user is a conflict event bearer, fully respect the user will, and enable the user to accept the suggestions more easily, so that the conflict event can be resolved more timely and efficiently under the condition of protecting the psychological health of the user.

In one possible example, the security protection system further includes a second electronic device, where the second electronic device is an associated device of the first electronic device, and after the first prompt information is sent to the first electronic device, the method further includes: determining the times of sending the first prompt information to the first electronic equipment in a preset period; and sending notification information to the second electronic equipment under the condition that the times are larger than the first preset times, wherein the notification information is used for indicating that the user is performing the action of injuring other people.

The user corresponding to the second electronic device may be a guardian of the user corresponding to the first electronic device. The preset period may refer to a period after determining that the user speaks the target word for the first time and prompting the user to the current time. The first preset number may be one or more times. The notification information may further include environmental sound information including the target word. That is, when the notification information is sent to the guardian of the user, the record of the target word uttered by the user can be sent to the guardian of the user at the same time.

In this example, the user of the first electronic device is mostly students or minors, so that when the user performs campus violence, the user may not be aware of the user himself, and therefore the user may be informed that the current behavior is not feasible through the first prompt information. If the user does not implement the campus violence again later, the guardian is not required to be informed, and if the user implements the campus violence again later, the first prompt information output by the first electronic device is determined to be insufficient to restrict the user, so that the guardian is required to be informed. According to the scheme, when the user is a conflict event initiator, the user behavior can be effectively interfered and guided in time, and the guardian can know the current state of the user in time. The intelligence of the handling of conflict events is improved.

In one possible example, the method further comprises: acquiring reference sound information corresponding to each target word in the at least one target word under the condition that the sound information corresponding to the at least one target word does not exist in the sound information of the user; determining whether first target sound information exists in the reference sound information, wherein the first target sound information is sound information with occurrence times larger than second preset times except for the sound information of the user in environment sound information obtained in a history mode; if the first target sound information exists, determining the word type of a target word corresponding to the first target sound information; when the word type is the threat and insulting word type, determining the identity of the user as the conflict event initiator; and when the word type is the help-seeking word type, determining the identity of the user as the conflict event carrier.

The environmental sound information acquired by the history may be environmental sound information acquired in a recent period of time, for example, in a week or a month. After the environmental sound information is acquired, sound characteristic analysis is carried out on other sound information except the user, a plurality of sound information with more occurrence time or times in the near-period time is determined, and then the plurality of sound information is determined to be the first target sound information. I.e. the same passerby when the user is on school or is learning, or the person most commonly contacted by the user during the class, such person is generally a good friend of the user, so if the environmental sound information is obtained, including the target word, but the sound information of the user is not obtained, but the sound information of the friend of the user is obtained, the current position of the user can be determined to be consistent with the friend of the user.

In this example, the identity of the user can be determined even if the user does not make a sound, so that the accuracy of the identity recognition of the user is improved.

In one possible example, the at least one target term includes a threat disfiguring term and the identity of the user is a conflicted event carrier, the method further comprising, after sending the second query to the first electronic device: determining sound information corresponding to target words of which the word types belong to the profoundly threatening words as second target sound information; and when the second target sound information appears again in the environment sound information and the at least one target word exists in the environment sound information, determining that the user suffers personal damage again.

If the user is a person suffering from campus violence and the environmental sound information has target words including profoundly-priced threat words, the sound characteristics of the person implementing the campus violence can be determined according to the target words, and when the target words are detected in the environmental sound next time and the second target sound information exists, the user can be directly determined to suffer from the campus violence without querying the user. And even if the target word is not said by the person corresponding to the second target sound information, the presence of the person who has implemented the campus violence can determine whether the person who implements the campus violence is more than the person who implements the campus violence, and can also determine that the user is currently suffering from the campus violence. And when the user suffers personal damage again, the second inquiry information may be sent to the user again.

It can be seen that in this example, determining whether the user suffers personal damage again according to the second sound information can improve the efficiency and accuracy of identifying the collision event.

In one possible example, after the determining that the sound information corresponding to the target word of the word type belonging to the profoundly threatening word is the second target sound information, the method further includes: transmitting fourth inquiry information to the first electronic equipment, wherein the fourth inquiry information is used for inquiring the sensitive words to the user; acquiring fourth reply information from the first electronic equipment, wherein the fourth reply information comprises the sensitive words; determining the sensitive word as the target word; after said determining that the user is again suffering personal injury, the method further comprises: and sending warning information to the first electronic equipment, wherein the warning information is used for warning the conflict event initiator to stop the action of injuring other people.

In this case, because some special words, even words that are not of the class of the insulting threat, may cause psychological injury to the user, the user may be queried for sensitive words, such as names, after determining that the user is exposed to the violence of the campus. In particular, when the sensitive word is a name, the sensitive word and the second target sound information can be bound, and only when the sound information corresponding to the sensitive word appearing in the environment sound information is the second target sound information, it is determined that the user suffers personal damage again, namely, is subjected to campus violence. Thus, misjudgment caused by normal communication can be avoided. And when it is determined that the user is again suffering from personal injury, a warning may be issued by the first electronic device through the speaker so that the person performing the campus violence may be concerned, thereby protecting the user.

In this example, it can be seen that adding a sensitive word for the user as a target word can improve accuracy and flexibility of determining the conflict event.

In one possible example, the security protection system further includes a campus security platform server, the man-machine conversation server is communicatively connected to the campus security platform server, and the method further includes: determining a number of times the user is again subjected to personal injury; acquiring identity information of the user when the number of times of personal damage again is greater than a third preset number of times, wherein the identity information is used for indicating schools, classes and names of the user; and sending fifth prompt information to the campus security platform server, wherein the fifth prompt information comprises the identity information and is used for prompting that the user is suffering personal injury to a school where the user is located.

When the number of times that the user suffers personal damage is more than the third preset number of times, whether the user seeks help or not, prompt information is directly sent to the campus security platform server so as to inform the user of the current situation. The campus security platform server can correspond to a plurality of schools, after receiving the prompt information, the campus security platform server can determine the condition of the user according to the schools, classes and names of the user, and can perform forced external intervention on the condition, so that physical and mental health of the user is ensured. Before sending the prompt information to the campus security platform server, the prompt information can also be sent to the second electronic device, and if the user suffers personal damage again after the prompt information is sent to the second electronic device, the prompt information is directly sent to the campus security platform server.

In this example, when the user suffers personal damage many times, the conflict event is resolved by external forced intervention, so that the flexibility of coping with the conflict event can be improved.

In accordance with the foregoing embodiments, referring to fig. 5, fig. 5 is a functional unit block diagram of a voice information processing apparatus based on a collision event in a campus scenario according to an embodiment of the present application. The voice information processing device 40 based on the collision event in the campus scenario is applied to a man-machine dialogue server in a security protection system, wherein the security protection system includes the man-machine dialogue server and a first electronic device, and the voice information processing device 40 based on the collision event in the campus scenario includes: a first obtaining unit 401, configured to obtain environmental sound information from the first electronic device when a monitoring condition is met, where the meeting of the monitoring condition includes obtaining a monitoring instruction or meeting a monitoring time; a first determining unit 402, configured to determine whether at least one target word exists in the environmental sound information, where a word type of the target word belongs to a threat countering type word or a distress type word; a second determining unit 403, configured to determine whether the sound information corresponding to the at least one target word includes sound information of a user if the at least one target word includes sound information of a user; a third determining unit 404, configured to determine, if there is voice information of the user, an identity of the user according to a word type of the target word, where the identity includes a conflict event initiator or a conflict event carrier; a first sending unit 405, configured to send, when the identity of the user is the conflict event initiator, first prompt information to the first electronic device, where the first prompt information is used to prompt the user to stop the act of injuring others; a second sending unit 406, configured to store, if the identity of the user is the collision event carrier, environmental sound information including the target word, and send, under a secure environment, first query information to the first electronic device, where the secure environment is an environment in which no collision event exists, where the first query information is used to query whether the user suffers personal damage; a second obtaining unit 407, configured to obtain first reply information from the first electronic device; a third sending unit 408, configured to send, to the first electronic device, second query information for querying whether the user needs help if the first reply information indicates that the user suffers personal injury; a third acquiring unit 409 configured to acquire second reply information from the first electronic device; a fourth sending unit 410, configured to send, if the second reply information indicates that the user needs help, second prompt information to the first electronic device, where the second prompt information is used to prompt the user that voice evidence has been saved, and prompt the user for measures that can be taken; a fifth transmitting unit 411 configured to transmit third query information to the first electronic device, where the second reply information indicates that the user does not need help, the third query information being used to query the user for a solution; a fourth obtaining unit 412, configured to obtain third reply information from the first electronic device, where the third reply information is used to indicate a solution of the user; a fourth determining unit 413, configured to determine an attitude of the user according to the solution, where the attitude includes a positive solution attitude or a negative solution attitude; a sixth sending unit 414, configured to send, to the first electronic device, third prompting information, where the attitude is a negative solution attitude, where the third prompting information is used to encourage the user to actively solve the problem, and prompt the user for a measure that can be taken; a fifth determining unit 415, configured to determine, according to the third reply information, whether a solution of the user is feasible, in a case where the attitude is an active solution attitude; a seventh sending unit 416, configured to send, if not feasible, a fourth prompting message to the first electronic device, where the fourth prompting message is configured to prompt the user that the solution is not feasible, and prompt the user of measures that can be taken.

In a possible example, the security protection system further includes a second electronic device, where the second electronic device is an associated device of the first electronic device, and after the sending of the first prompt information to the first electronic device, the first sending unit 405 is specifically configured to: determining the times of sending the first prompt information to the first electronic equipment in a preset period; and sending notification information to the second electronic equipment under the condition that the times are larger than the first preset times, wherein the notification information is used for indicating that the user is performing the action of injuring other people.

In one possible example, the voice information processing apparatus 40 based on the collision event in the campus scenario is further configured to: acquiring reference sound information corresponding to each target word in the at least one target word under the condition that the sound information corresponding to the at least one target word does not exist in the sound information of the user; determining whether first target sound information exists in the reference sound information, wherein the first target sound information is sound information with occurrence times larger than second preset times except for the sound information of the user in environment sound information obtained in a history mode; if the first target sound information exists, determining the word type of a target word corresponding to the first target sound information; when the word type is the threat and insulting word type, determining the identity of the user as the conflict event initiator; and when the word type is the help-seeking word type, determining the identity of the user as the conflict event carrier.

In one possible example, the at least one target term includes a threat profoundly term, and the identity of the user is a conflicted event carrier, and after the sending of the second query information to the first electronic device, the conflicted event-based voice information processing apparatus 40 in the campus scenario is further configured to: determining sound information corresponding to target words of which the word types belong to the profoundly threatening words as second target sound information; and when the second target sound information appears again in the environment sound information and the at least one target word exists in the environment sound information, determining that the user suffers personal damage again.

In one possible example, after the determining that the sound information corresponding to the target word of the word type belongs to the counterattack threat word is the second target sound information, the voice information processing apparatus 40 based on the collision event in the campus scenario is further configured to: transmitting fourth inquiry information to the first electronic equipment, wherein the fourth inquiry information is used for inquiring the sensitive words to the user; acquiring fourth reply information from the first electronic equipment, wherein the fourth reply information comprises the sensitive words; determining the sensitive word as the target word; after said determining that the user is again suffering personal injury, the method further comprises: and sending warning information to the first electronic equipment, wherein the warning information is used for warning the conflict event initiator to stop the action of injuring other people.

In one possible example, the security protection system further includes a campus security platform server, the man-machine interaction server is communicatively connected to the campus security platform server, and the voice information processing device 40 based on the collision event in the campus scenario is further configured to: determining a number of times the user is again subjected to personal injury; acquiring identity information of the user when the number of times of personal damage again is greater than a third preset number of times, wherein the identity information is used for indicating schools, classes and names of the user; and sending fifth prompt information to the campus security platform server, wherein the fifth prompt information comprises the identity information and is used for prompting that the user is suffering personal injury to a school where the user is located.

In one possible example, before the acquiring the environmental sound information from the first electronic device, the voice information processing apparatus 40 based on the collision event in the campus scenario is further configured to: acquiring course time information of the user; determining the learning time, the learning time and the inter-class time of the user according to the course time information; and determining the school time, the school time and the inter-class time as the monitoring time.

It can be understood that, since the method embodiment and the apparatus embodiment are different presentation forms of the same technical concept, the content of the method embodiment portion in the present application should be synchronously adapted to the apparatus embodiment portion, which is not described herein.

In the case of adopting integrated units, referring to fig. 6, fig. 6 is a functional unit block diagram of a voice information processing apparatus based on a collision event in another campus scenario according to an embodiment of the present application. In fig. 6, a voice information processing apparatus 500 based on a collision event in a campus scenario includes: a processing module 512 and a communication module 511. The processing module 512 is configured to control and manage actions of the voice information processing apparatus 500 based on the collision event in the campus scenario, for example, perform steps of the first acquiring unit 401, the first determining unit 402, the second determining unit 403, the third determining unit 404, the first transmitting unit 405, the second transmitting unit 406, the second acquiring unit 407, the third transmitting unit 408, the third acquiring unit 409, the fourth transmitting unit 410, the fifth transmitting unit 411, the fourth acquiring unit 412, the fourth determining unit 413, the sixth transmitting unit 414, the fifth determining unit 415, and the seventh transmitting unit 416, and/or perform other processes of the technology described herein. The communication module 511 is used for interaction between the voice information processing apparatus 500 and other devices based on the collision event in the campus scenario. As shown in fig. 6, the voice information processing apparatus 500 based on the collision event in the campus scenario may further include a storage module 513, where the storage module 513 is configured to store program codes and data of the voice information processing apparatus 500 based on the collision event in the campus scenario.

The processing module 512 may be a processor or controller, such as a central processing unit (Central Processing Unit, CPU), a general purpose processor, a digital signal processor (DigitalSignalProcessor, DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. The processor may also be a combination that performs the function of a computation, e.g., a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 511 may be a transceiver, an RF circuit, a communication interface, or the like. The memory module 513 may be a memory.

All relevant contents of each scenario related to the above method embodiment may be cited to the functional description of the corresponding functional module, which is not described herein. The voice information processing device 500 based on the collision event in the campus scenario may execute the voice information processing method based on the collision event in the campus scenario shown in fig. 3.

The foregoing description of the embodiments of the present application has been presented primarily in terms of a method-side implementation. It will be appreciated that, in order to achieve the above-described functions, the electronic device includes a hardware structure and a software module for performing the respective functions. Those of skill in the art will readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The embodiment of the application can divide the functional units of the electronic device according to the method example, for example, each functional unit can be divided corresponding to each function, and two or more functions can be integrated in one processing unit. The integrated units may be implemented in hardware or in software functional units. It should be noted that, in the embodiment of the present application, the division of the units is schematic, which is merely a logic function division, and other division manners may be implemented in actual practice.

The embodiment of the application also provides a chip, wherein the chip comprises a processor, and the processor is used for calling and running the computer program from the memory, so that the device provided with the chip executes part or all of the steps described in the electronic device in the embodiment of the method.

The embodiment of the application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program makes a computer execute part or all of the steps of any one of the above method embodiments, and the computer includes an electronic device.

Embodiments of the present application also provide a computer program product comprising a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform part or all of the steps of any one of the methods described in the method embodiments above. The computer program product may be a software installation package, said computer comprising an electronic device.

It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, such as the above-described division of units, merely a division of logic functions, and there may be additional manners of dividing in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units described above, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, comprising several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the above-mentioned method of the various embodiments of the present application. And the aforementioned memory includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be implemented by a program that instructs associated hardware, and the program may be stored in a computer readable memory, which may include: flash disk, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.

The foregoing has outlined rather broadly the more detailed description of embodiments of the application, wherein the principles and embodiments of the application are explained in detail using specific examples, the above examples being provided solely to facilitate the understanding of the method and core concepts of the application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Although the present application is disclosed above, the present application is not limited thereto. Variations and modifications, including combinations of the different functions and implementation steps, as well as embodiments of the software and hardware, may be readily apparent to those skilled in the art without departing from the spirit and scope of the application.

Claims

1. The voice information processing method based on the conflict event in the campus scene is characterized by being applied to a man-machine conversation server in a security protection system, wherein the security protection system comprises the man-machine conversation server and first electronic equipment, and the method comprises the following steps:

acquiring first reply information from the first electronic equipment;

acquiring second reply information from the first electronic equipment;

2. The method of claim 1, wherein the security protection system further comprises a second electronic device, the second electronic device being an associated device of the first electronic device, the method further comprising, after sending the first alert message to the first electronic device:

Determining the times of sending the first prompt information to the first electronic equipment in a preset period;

and sending notification information to the second electronic equipment under the condition that the times are larger than the first preset times, wherein the notification information is used for indicating that the user is performing the action of injuring other people.

3. The method according to claim 2, wherein the method further comprises:

acquiring reference sound information corresponding to each target word in the at least one target word under the condition that the sound information corresponding to the at least one target word does not exist in the sound information of the user;

determining whether first target sound information exists in the reference sound information, wherein the first target sound information is sound information with occurrence times larger than second preset times except for the sound information of the user in environment sound information obtained in a history mode;

if the first target sound information exists, determining the word type of a target word corresponding to the first target sound information;

when the word type is the threat and insulting word type, determining the identity of the user as the conflict event initiator;

And when the word type is the help-seeking word type, determining the identity of the user as the conflict event carrier.

4. The method of claim 3, wherein the at least one target term includes a counter-productive term and the identity of the user is a conflicted event carrier, the method further comprising, after transmitting second query information to the first electronic device:

determining sound information corresponding to target words of which the word types belong to the threat profoundly words as second target sound information;

and when the second target sound information appears again in the environment sound information and the at least one target word exists in the environment sound information, determining that the user suffers personal damage again.

5. The method of claim 4, wherein after the determining that the sound information corresponding to the target word for which the word type belongs to the threat insulting word is the second target sound information, the method further comprises:

transmitting fourth inquiry information to the first electronic equipment, wherein the fourth inquiry information is used for inquiring the sensitive words to the user;

Acquiring fourth reply information from the first electronic equipment, wherein the fourth reply information comprises the sensitive words;

determining the sensitive word as the target word;

after said determining that the user is again suffering personal injury, the method further comprises:

and sending warning information to the first electronic equipment, wherein the warning information is used for warning the conflict event initiator to stop the action of injuring other people.

6. The method of claim 5, wherein the security protection system further comprises a campus security platform server, the man-machine conversation server communicatively coupled to the campus security platform server, the method further comprising:

determining a number of times the user is again subjected to personal injury;

acquiring identity information of the user when the number of times of personal damage again is greater than a third preset number of times, wherein the identity information is used for indicating schools, classes and names of the user;

and sending fifth prompt information to the campus security platform server, wherein the fifth prompt information comprises the identity information and is used for prompting that the user is suffering personal injury to a school where the user is located.

7. The method of claim 6, wherein prior to the obtaining the ambient sound information from the first electronic device, the method further comprises:

acquiring course time information of the user;

determining the learning time, the learning time and the inter-class time of the user according to the course time information;

and determining the school time, the school time and the inter-class time as the monitoring time.

8. A voice information processing device based on a collision event in a campus scenario, which is applied to a man-machine conversation server in a security protection system, wherein the security protection system comprises the man-machine conversation server and a first electronic device, and the device comprises:

9. A server comprising a processor, a memory, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the method of any of claims 1-7.

10. A computer readable storage medium having stored thereon a computer program/instructions, characterized in that the computer program/instructions are executed by a processor for carrying out the steps of the method according to any of claims 1-7.