CN113012386A - Security alarm multi-level linkage rapid pushing method - Google Patents
Security alarm multi-level linkage rapid pushing method Download PDFInfo
- Publication number
- CN113012386A CN113012386A CN202011564509.0A CN202011564509A CN113012386A CN 113012386 A CN113012386 A CN 113012386A CN 202011564509 A CN202011564509 A CN 202011564509A CN 113012386 A CN113012386 A CN 113012386A
- Authority
- CN
- China
- Prior art keywords
- decibel
- event
- database
- processing
- acquisition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 51
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 238000006243 chemical reaction Methods 0.000 claims abstract description 10
- 230000001960 triggered effect Effects 0.000 claims description 13
- 230000000737 periodic effect Effects 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 6
- 206010039740 Screaming Diseases 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 238000010191 image analysis Methods 0.000 claims description 2
- 230000006399 behavior Effects 0.000 description 21
- 238000005516 engineering process Methods 0.000 description 6
- 210000003414 extremity Anatomy 0.000 description 4
- 230000036544 posture Effects 0.000 description 4
- 230000009429 distress Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010001488 Aggression Diseases 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 210000003423 ankle Anatomy 0.000 description 1
- 210000001217 buttock Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 210000001513 elbow Anatomy 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002832 shoulder Anatomy 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/004—Alarm propagated along alternative communication path or using alternative communication medium according to a hierarchy of available ways to communicate, e.g. if Wi-Fi not available use GSM
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the field of security protection, in particular to a security protection alarm multi-level linkage quick pushing method, which comprises the following steps: s1, establishing a database; s2, setting early warning decibels; s3, decibel detection; s4, voice data acquisition and processing; s5, image acquisition processing: collecting image information of the pedestrian; s6, human behavior recognition: judging behavior reaction of the onlooker; s7, graded triggering and reporting: triggering different levels to report according to the judgment result of the behavior reaction of the onlooker; the first-level report is automatic dialing report call, the second-level report is to inform security personnel of the affiliated cell, and the third-level report is to trigger alarm report. The invention provides a security alarm multi-level linkage rapid pushing method which can report events with different severity levels in a grading manner aiming at the problem that the existing alarm device cannot distinguish the severity levels of the events.
Description
Technical Field
The invention relates to the field of security and protection, in particular to a security and protection alarm multi-level linkage quick pushing method.
Background
With the great investment of the country on the construction of safe cities, the surrounding of our lives, such as communities, business centers, public leisure places and roads, are all fully monitored, so that strict security and protection really bring great safety guarantee to the public of the society, and once any case or event occurs, related organizations can rapidly solve the case through clues obtained by video monitoring. However, the responsibility of the user to the relevant personnel after the event occurs is only studied, and the user cannot timely stop or prevent the event from occurring or even before the event occurs, and it is difficult to provide a guarantee for the life safety and property safety of the user in time when the user is in distress.
For sudden events, the investigation of the responsibility of the non-molecule-emitting part is sometimes difficult to make up for the physical harm of the user, and the most important is to stop violent behavior in time when the sudden events occur. Aiming at an alarm device which reports in time when an event occurs, a security alarm device in the prior art generally adopts the arrangement of a reporting pile, and a reporting button is arranged on the reporting pile, but when the real event occurs, a user can hardly press the reporting button to report the event independently.
For the above situation, it is necessary to be able to automatically recognize the occurrence of an event and perform an automatic alarm device, but the automatic alarm device has only one reporting mode, or multiple reporting modes are triggered simultaneously, such as only triggering an alarm, or triggering an alarm and making a report call simultaneously; although the problem of timely reporting can be effectively solved, the severity or danger of the event is easily solved only by the alarm device, the effect of frightening a pest is not enough, or an alarm is triggered and a reporting call is made at the same time, but the severity or danger of the event does not require manual work, so that the situation of manpower waste exists.
Aiming at the situation that the deterrence effect is insufficient or manpower is wasted possibly occurs when the reporting of which degree is required by the difference of the severity and the danger of the event cannot be distinguished, a security alarm multi-level linkage quick pushing method capable of carrying out graded reporting on the difference of the severity and the danger of the event is urgently needed.
Disclosure of Invention
The invention provides a security alarm multi-level linkage quick pushing method, which aims at the problem that the existing security alarm method cannot carry out graded reporting according to different severity and dangerousness of an event.
In order to solve the technical problem, the present application provides the following technical solutions:
a security alarm multi-level linkage rapid pushing method comprises the following steps:
s1, establishing a database: establishing a database, wherein keywords are prestored in the database;
s2, early warning decibel setting: measuring the noise decibel generated by daily activities of 24 hours in a day on working days and non-working days of a cell in advance to obtain the periodic noise decibel varying with the date and time, and setting periodic early warning decibels exceeding the periodic noise decibel;
s3, decibel detection: the decibel tester is kept on, continuously detects the decibel of the sound, and starts voice acquisition when the decibel exceeds the early warning decibel;
s4, voice data acquisition and processing: when decibel exceeds early warning decibel, acquiring pedestrian voice data, analyzing information content of the voice data, sending the information content to a database, matching the information content with keywords prestored in the database, and starting image acquisition processing if matching is successful;
s5, image acquisition processing: collecting image information of pedestrians, carrying out image analysis and processing on the collected images, and dividing the pedestrians into surrounding persons and event participation persons; separating the image of the onlooker to obtain image data of the onlooker; separating the images of the persons participating in the event to obtain image data of the persons participating in the event, and identifying the number of the persons participating in the event;
s6, human behavior recognition: if the image data of the onlooker is collected, carrying out human behavior recognition on the obtained image data of the onlooker, and judging whether the onlooker is in a gathering or escaping event scene in response to the behavior of the event;
s7, graded triggering and reporting: according to the judgment result of the behavior reaction of the onlooker, triggering primary reporting if the onlooker has the behavior of escaping from the scene of the event; if the onlooker is gathered at the event site, triggering the second-level report, and simultaneously triggering the third-level report; the first-level report is automatic dialing report call, the second-level report is to inform security personnel of the affiliated cell, and the third-level report is to trigger alarm report.
Has the advantages that: by setting a database, keywords are stored in advance, so that matching at the later stage is facilitated; acquiring the daily noise of different time periods of 24 hours in working days and non-working days, and setting an early warning decibel exceeding the daily noise; when the decibel detector detects that the early warning decibel is exceeded, whether the early warning decibel is exceeded or not can be judged; keeping the decibel detector on in a daily state, monitoring the decibels, and timely detecting when events possibly occur when the noise exceeds the daily noise; the voice data acquisition is started after decibel detection, so that energy can be saved, and the voice data acquisition is not started under the condition that the early warning decibel is not detected; the method comprises the steps of starting voice data acquisition, starting image acquisition according to a voice data processing result, analyzing and processing image data acquired by the image, obtaining behavior reaction of surrounding personnel when an event occurs, gathering the surrounding personnel under the condition of low event severity generally, and escaping from an event site for guaranteeing self safety of the surrounding personnel under the conditions of high event severity and high risk; if the situation that the onlooker is gathered occurs, judging the severity and the danger to trigger secondary reporting, and triggering tertiary reporting at the same time of triggering the secondary reporting; the invention can identify the occurrence of danger in time and carry out grading reporting rapidly, can effectively ensure the timeliness of reporting when the dangerous event occurs, and better ensure the safety of users.
The method comprises the steps of setting up a database, setting early warning decibels, detecting decibels, collecting and processing voice data, collecting and processing images, identifying human body behaviors and triggering classified reporting, obtaining behavior reactions of surrounding personnel when an event occurs by combining the steps, distinguishing the severity of the event according to the behavior reactions of the surrounding personnel, identifying participants when the dangerous event occurs by common reporting, accurately judging whether the behavior belongs to alarming or dangerous behaviors, having higher identification difficulty and possibly causing misjudgment, judging the severity of the event based on the behavior reactions of the surrounding personnel to the event by identifying the behaviors of the surrounding personnel, avoiding misjudgment caused by simple personnel behavior identification, and timely performing the classified reporting according to different severity and dangerousness of the event.
Further, the database established in S1 includes a primary database and a secondary database, the keywords with low risk factors are prestored in the primary database, and the primary database includes abuse and threatening vocabulary; keywords with high risk coefficients are pre-stored in a secondary database, and the secondary database comprises words of asking for help, screaming and violent statements.
Has the advantages that: by ranking the databases, a preliminary estimate of the severity of an event can be made when matching within the database as speech data is collected and processed.
Further, the step S2 further includes step S201, setting a predetermined time length and a predetermined frequency: and setting the time when the detection decibel exceeds the early warning decibel for a certain time as preset time, and setting the frequency of detecting the exceeding of the early warning decibel in the certain time as preset frequency.
Has the advantages that: the preset duration and the preset frequency are preset for decibel detection, if a user strongly responds, the user can call for help for a long time or the frequency of calling for help is extremely high, and the user is provided with the classification of the severity of the event during the calling for help by setting the preset duration and the preset frequency when the user calls for help.
Further, the S3 further includes S301, decibel frequency detection: when the decibel detector detects the decibel of the sound daily, when the decibel exceeds the early warning decibel and reaches the preset time length, or the frequency of the early warning decibel is larger than the preset frequency, triggering secondary reporting.
Has the advantages that: if an emergent event occurs, the user usually makes a response of calling or calling for help, the decibel tester can quickly detect the emergency degree and danger coefficient of the event are high when the preset time or the preset frequency is reached, and secondary reporting is quickly triggered before image acquisition, so that the user can be conveniently and timely rescued.
Further, the S4 further includes S401, setting a safety frequency: when voice data acquisition and processing are carried out, the security frequency of successfully matched keywords is preset.
Has the advantages that: by setting the safety frequency, when the matching result rate of the key words is higher than the normal safety frequency during voice data acquisition and processing, the severity and the danger of the event are higher.
Further, the step S4 includes a step S402 of frequency detection, in which, when the pedestrian voice data is acquired and processed, if the success rate of matching the keywords is greater than the preset safety frequency, secondary reporting is preferentially triggered when the pedestrian image is not acquired yet.
Has the advantages that: if the success rate of keyword matching is greater than the safety frequency, the severity of the event and the dangerous line exceed the preset safety range, and secondary reporting is preferentially triggered before image acquisition is started, so that the safety of a user is better guaranteed.
Further, the S5 further includes S501, the step of triggering and reporting the number of people: if the image data of the surrounding personnel is not acquired, the following steps are carried out:
when the pedestrian voice data is matched with the keywords in the primary database during acquisition and processing, and the number of people participating in the event is identified as 2 people during acquisition and processing of the pedestrian image, triggering three-level reporting;
when the pedestrian voice data is matched with the keywords in the primary database during acquisition and processing, and the number of people who participate in the event is greater than 2 people during acquisition and processing of the pedestrian image, triggering secondary reporting;
when the pedestrian voice data is matched with the keywords in the secondary database during the acquisition and the processing of the pedestrian voice data, and the number of people participating in the event is identified as 2 people during the acquisition and the processing of the pedestrian image, triggering secondary reporting;
and triggering the primary report when the pedestrian voice data is matched with the keywords in the secondary database during the acquisition and processing of the pedestrian voice data and the number of people who are identified to participate in the event is more than 2 people during the acquisition and processing of the pedestrian image.
Has the advantages that: under the condition that no onlooker exists, when the human body behavior of the onlooker cannot be identified, the keyword grade matched in the voice data acquisition processing and the number of people participating in the event identified in the pedestrian image acquisition processing are combined to perform basic severity grade division, the higher the keyword grade matched in the database is, the more the number of identified people is, the higher the possibility that a user is possibly in danger is, and the higher the triggered reporting grade is; moreover, the participators are usually nervous when being used by a single person, and the primary reporting trigger alarm can well play a role in warning and frightening harm-applying people; however, if the simple alarm hardly plays an effective role under the condition of multiple persons, the secondary report is triggered to timely inform security personnel of the occurrence of dangerous events, and the safety of users can be timely and effectively guaranteed.
Drawings
Fig. 1 is a flowchart of a security alarm multi-level linkage fast push method of the present invention.
Detailed Description
The following is further detailed by way of specific embodiments:
as shown in fig. 1, the method for multi-level linkage fast pushing of security alarm of the embodiment includes the following steps:
s1, establishing a database: adopting Microsoft Access to establish a database, wherein keywords are prestored in the database; the database comprises a primary database and a secondary database, wherein the keywords with low risk coefficients are prestored in the primary database, and the primary database comprises abuse and terrifying words; keywords with high risk coefficients are pre-stored in a secondary database, and the secondary database comprises words of help seeking, winding seeking, screaming and violent statements. By ranking the databases, a preliminary estimate of the severity of an event can be made when matching within the database as speech data is collected and processed.
S2, early warning decibel setting: the method comprises the steps that an LB-ZS50 noise meter of LOOBO is adopted to measure noise decibels generated by daily activities of 24 hours in a working day and a non-working day of a cell in advance, the working day is Monday to Friday except for legal holidays, the non-working day is double-break and legal holidays, 24 hours are divided into 6 time periods, the first time period is 7 to 11 points, the second event period is 11 to 13 points, the third time period is 13 to 18 points, the fourth time period is 18 to 22 points, and the fifth time period is 22 to 7 points, daily noises of five time periods of working days and non-working days of Hongfeng cell in Chongxing are collected respectively, and the average periodic noise decibels of the working day in the five time periods are respectively 42dB, 68dB, 52dB, 65dB and 37 dB; the average periodic noise decibel values in five time periods on a non-working day are respectively 36dB, 72dB, 66dB, 75dB and 43 dB; and setting early warning decibels when the working day and the non-working day exceed the noise decibels of the corresponding time periods, setting the corresponding early warning decibels in the five time periods of the working day to be 65dB, 75dB, 70dB, 80dB and 60dB respectively, and setting the corresponding early warning decibels in the five time periods of the non-working day to be 65dB, 80dB, 70dB, 80dB and 60dB respectively.
S201, setting a preset time length and a preset frequency: if the user responds strongly, the user can call for help for a long time or the frequency of calling for help is extremely high, so that the preset time length and the preset frequency are set for decibel detection in advance. The preset time is set when the detection decibel exceeds the early warning decibel for a certain time, in this embodiment, the preset time is set to 10 seconds, the frequency of detecting the exceeding of the early warning decibel within a certain time is set to be the preset frequency, and in this embodiment, the preset frequency is set to be 3 times per minute.
For example, on the way that a woman returns home in a district at two or half of the morning on every thursday, the woman happens to hit a thief who intends to steal by turning over a window, after the thief is hit, the woman is tried to be threatened violently to avoid the trail exposure, after the threat of violence, the woman is scared and scream, the decibel of the instant scared woman exceeds 60dB, and the continuous scream and the distress sound are as long as more than ten seconds, secondary reporting is triggered, and security personnel in the district receive the information and timely develop and rescue for the woman.
S3, decibel detection: the noise meter is installed at a position 160cm away from the ground of a street lamp in a community, the noise meter detects the decibel of sound daily, and when the decibel exceeds the early warning decibel, the recording equipment is started to carry out voice acquisition.
S301, decibel frequency detection: when the noise meter daily detects the decibel of the sound, when the decibel exceeds the early warning decibel and reaches the preset time for 10 seconds, or the frequency of the early warning decibel is greater than the preset frequency for 5 times per minute, triggering secondary reporting. If sudden events such as violence and robbery occur, the user usually makes a response of screaming or calling for help, the noise meter can quickly detect the sudden events, when the sudden events reach a preset time or a preset frequency, the emergency degree and the danger coefficient of the sudden events are higher, secondary reporting is quickly triggered before image acquisition, and the sudden events are convenient for timely rescue of the user.
S4, voice data acquisition and processing: when decibel exceeds early warning decibel, starting recording equipment to collect pedestrian voice data, analyzing information content of the voice data by adopting the existing intelligent voice data analysis technology of Beijing Aidigital smart technology, sending the information content to a database, matching the information content with keywords prestored in the database, and starting pedestrian image collection after matching the keywords.
S401, safe frequency setting: when voice data acquisition and processing are carried out, the security frequency of successfully matched keywords is preset. The safety frequency set in this embodiment is 3 times per minute, and when the matching result rate of the keyword is higher than the safety frequency during the voice data acquisition and processing, it indicates that the severity and the risk of the event are high.
S402, frequency detection is further included, wherein when pedestrian voice data acquisition processing is carried out, if the success rate of keyword matching is greater than the preset safety frequency, secondary reporting is triggered preferentially under the condition that pedestrian image acquisition processing is not carried out yet. If the success rate of keyword matching is greater than the safety frequency, the severity of the event and the dangerous line exceed the preset safety range, and secondary reporting is preferentially triggered before image acquisition is started, so that the safety of a user is better guaranteed.
S5, image acquisition processing: the method comprises the steps that image information of a pedestrian is collected by a camera, the collected image is sent to a science popularization flight, image data of the pedestrian is extracted from the image data by adopting the existing face recognition technology of the science popularization flight, the posture in the image data of the pedestrian is recognized by adopting the existing posture capturing technology of an extreme viewing angle according to the human body posture result detected and captured by 18 key points of a human body in real time, whether large-amplitude limb actions exist or not is judged, and surrounding personnel and event participation personnel are recognized according to whether the large-amplitude limb actions exist or not; separating the image of the onlooker to obtain image data of the onlooker; and separating the images of the persons participating in the event to obtain image data of the persons participating in the event, and identifying the number of the persons participating in the event.
S501, triggering and reporting the number of people: if the image data of the surrounding personnel is not collected, the number of the collected personnel participating in the event is identified based on the face identification technology in the prior art:
when the pedestrian voice data is matched with the keywords in the primary database during the acquisition and processing of the pedestrian voice data, and the number of people participating in the event is identified as 2 people during the acquisition and processing of the pedestrian image, triggering primary reporting;
when the pedestrian voice data is matched with the keywords in the primary database during acquisition and processing, and the number of people who participate in the event is greater than 2 people during acquisition and processing of the pedestrian image, triggering secondary reporting;
when the pedestrian voice data is matched with the keywords in the secondary database during the acquisition and the processing of the pedestrian voice data, and the number of people participating in the event is identified as 2 people during the acquisition and the processing of the pedestrian image, triggering secondary reporting;
and triggering secondary reporting when the pedestrian voice data is matched with the keywords in the secondary database during acquisition and processing of the pedestrian voice data and the number of people who are identified to participate in the event is more than 2 people during acquisition and processing of the pedestrian image.
Under the condition that no onlooker exists, when the onlooker cannot be identified through human body behaviors, a basic severity level is classified by combining the keyword level matched in the voice data acquisition processing and the number of people participating in the event identified in the pedestrian image acquisition processing, the higher the keyword level matched in the database is, the more the number of people is identified, the higher the possibility that a user is possibly in danger is, and the higher the reporting level is triggered.
S6, human behavior recognition: if the image data of the onlooker is collected, human behavior recognition is carried out on the obtained image data of the onlooker, the directions and the positions of four limbs (for example, 18 key points such as elbows, shoulders, wrists, knees, ankles, buttocks and the like) are judged through connecting lines of key points of the human body in the image according to the motion capture technology in the extreme visual angle prior art, the postures of the onlooker are judged to be standing, walking or running through the directions and the positions of the four limbs, the directions of the onlooker during walking or running are obtained, and whether the behavior reaction of the onlooker is gathering or escaping from the incident scene is obtained.
S7, graded triggering and reporting: according to the judgment result of the behavior reaction of the onlooker, triggering primary reporting if the onlooker has the behavior of escaping from the scene of the event; if the onlooker is gathered at the event site, triggering the second-level report, and simultaneously triggering the third-level report; the first-level reporting is automatic dialing of a reporting telephone, the second-level reporting is informing of security personnel in the cell, the informing mode comprises dialing of the telephone of the security room and triggering of an alarm bell of the security room, the third-level reporting is triggering of alarm reporting, the alarm can adopt an HXA-B02 intelligent audible and visual alarm, and the alarm is installed on a street lamp in the cell at a height of 200cm above the ground.
The foregoing is merely an example of the present invention, and common general knowledge in the field of known specific structures and characteristics is not described herein in any greater extent than that known in the art at the filing date or prior to the priority date of the application, so that those skilled in the art can now appreciate that all of the above-described techniques in this field and have the ability to apply routine experimentation before this date can be combined with one or more of the present teachings to complete and implement the present invention, and that certain typical known structures or known methods do not pose any impediments to the implementation of the present invention by those skilled in the art. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (7)
1. A security alarm multi-level linkage rapid pushing method is characterized by comprising the following steps:
s1, establishing a database: establishing a database, wherein keywords are prestored in the database;
s2, early warning decibel setting: measuring the noise decibel generated by daily activities of 24 hours in a day on working days and non-working days of a cell in advance to obtain the periodic noise decibel varying with the date and time, and setting periodic early warning decibels exceeding the periodic noise decibel;
s3, decibel detection: the decibel tester is kept on, continuously detects the decibel of the sound, and starts voice acquisition when the decibel exceeds the early warning decibel;
s4, voice data acquisition and processing: when decibel exceeds early warning decibel, acquiring pedestrian voice data, analyzing information content of the voice data, sending the information content to a database, matching the information content with keywords prestored in the database, and starting image acquisition processing if matching is successful;
s5, image acquisition processing: collecting image information of pedestrians, carrying out image analysis and processing on the collected images, and dividing the pedestrians into surrounding persons and event participation persons; separating the image of the onlooker to obtain image data of the onlooker; separating the images of the persons participating in the event to obtain image data of the persons participating in the event, and identifying the number of the persons participating in the event;
s6, human behavior recognition: if the image data of the onlooker is collected, carrying out human behavior recognition on the obtained image data of the onlooker, and judging whether the onlooker is in a gathering or escaping event scene in response to the behavior of the event;
s7, graded triggering and reporting: according to the judgment result of the behavior reaction of the onlooker, triggering primary reporting if the onlooker has the behavior of escaping from the scene of the event; if the onlooker is gathered at the event site, triggering the second-level report, and simultaneously triggering the third-level report; the first-level report is automatic dialing report call, the second-level report is to inform security personnel of the affiliated cell, and the third-level report is to trigger alarm report.
2. The security alarm multi-level linkage rapid pushing method according to claim 1, characterized in that: the database established in the step S1 comprises a primary database and a secondary database, wherein the keywords with low risk coefficients are prestored in the primary database, and the primary database contains abuse and terrifying words; keywords with high risk coefficients are pre-stored in a secondary database, and the secondary database comprises words of asking for help, screaming and violent statements.
3. The security alarm multi-level linkage rapid pushing method according to claim 1, characterized in that: the step S2 further includes step S201, setting a predetermined time length and a predetermined frequency: and setting the time when the detection decibel exceeds the early warning decibel for a certain time as preset time, and setting the frequency of detecting the exceeding of the early warning decibel in the certain time as preset frequency.
4. The security alarm multi-level linkage rapid pushing method according to claim 1, characterized in that: the S3 further includes S301, decibel frequency detection: when the decibel detector detects the decibel of the sound daily, when the decibel exceeds the early warning decibel and reaches the preset time length, or the frequency of the early warning decibel is larger than the preset frequency, triggering secondary reporting.
5. The security alarm multi-level linkage rapid pushing method according to claim 1, characterized in that: the S4 further includes S401, setting of safety frequency: when voice data acquisition and processing are carried out, the security frequency of successfully matched keywords is preset.
6. The security alarm multi-level linkage rapid pushing method according to claim 5, characterized in that: the S4 further comprises S402 and frequency detection, wherein when the pedestrian voice data is collected and processed, if the success rate of matching the keywords is greater than the preset safety frequency, secondary reporting is preferentially triggered under the condition that the pedestrian image is not collected and processed.
7. The security alarm multi-level linkage rapid pushing method according to claim 1, characterized in that: the step S5 further includes a step S501 of triggering and reporting the number of people: if the image data of the surrounding personnel is not acquired, the following steps are carried out:
when the pedestrian voice data is matched with the keywords in the primary database during acquisition and processing, and the number of people participating in the event is identified as 2 people during acquisition and processing of the pedestrian image, triggering three-level reporting;
when the pedestrian voice data is matched with the keywords in the primary database during acquisition and processing, and the number of people who participate in the event is greater than 2 people during acquisition and processing of the pedestrian image, triggering secondary reporting;
when the pedestrian voice data is matched with the keywords in the secondary database during the acquisition and the processing of the pedestrian voice data, and the number of people participating in the event is identified as 2 people during the acquisition and the processing of the pedestrian image, triggering secondary reporting;
and triggering the primary report when the pedestrian voice data is matched with the keywords in the secondary database during the acquisition and processing of the pedestrian voice data and the number of people who are identified to participate in the event is more than 2 people during the acquisition and processing of the pedestrian image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011564509.0A CN113012386A (en) | 2020-12-25 | 2020-12-25 | Security alarm multi-level linkage rapid pushing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011564509.0A CN113012386A (en) | 2020-12-25 | 2020-12-25 | Security alarm multi-level linkage rapid pushing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113012386A true CN113012386A (en) | 2021-06-22 |
Family
ID=76383744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011564509.0A Pending CN113012386A (en) | 2020-12-25 | 2020-12-25 | Security alarm multi-level linkage rapid pushing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113012386A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101777114A (en) * | 2009-01-08 | 2010-07-14 | 北京中星微电子有限公司 | Intelligent analysis system and intelligent analysis method for video monitoring, and system and method for detecting and tracking head and shoulder |
| CN101872418A (en) * | 2010-05-28 | 2010-10-27 | 电子科技大学 | Detection method based on group environment abnormal behavior |
| CN103189758A (en) * | 2010-08-30 | 2013-07-03 | 高通股份有限公司 | Audio-based environment awareness |
| CN103632504A (en) * | 2013-12-17 | 2014-03-12 | 上海电机学院 | Silence reminder for library |
| CN103679215A (en) * | 2013-12-30 | 2014-03-26 | 中国科学院自动化研究所 | Video monitoring method based on group behavior analysis driven by big visual big data |
| CN105138982A (en) * | 2015-08-21 | 2015-12-09 | 中南大学 | Crowd abnormity detection and evaluation method based on multi-characteristic cluster and classification |
| CN105308657A (en) * | 2013-04-23 | 2016-02-03 | 卡纳里连接公司 | Security and/or monitoring devices and systems |
| CN105989683A (en) * | 2015-02-12 | 2016-10-05 | 贝斯科技国际有限公司 | Enhanced residence security system |
| CN106161798A (en) * | 2016-07-25 | 2016-11-23 | 吉林省万和电力设备有限公司 | A kind of intelligent radio LED street lamp |
| CN106331657A (en) * | 2016-11-02 | 2017-01-11 | 北京弘恒科技有限公司 | Video analysis and detection method and system for crowd gathering and moving |
| CN108154108A (en) * | 2017-12-22 | 2018-06-12 | 触景无限科技（北京）有限公司 | The monitoring method and device of a kind of emergency |
| CN108647582A (en) * | 2018-04-19 | 2018-10-12 | 河南科技学院 | Goal behavior identification and prediction technique under a kind of complex dynamic environment |
| CN111354144A (en) * | 2018-12-24 | 2020-06-30 | 阿里巴巴集团控股有限公司 | Security early warning system, method, equipment and storage medium |
| KR20200104548A (en) * | 2019-02-27 | 2020-09-04 | 동명대학교산학협력단 | Risk alarm system with the safety block |
-
2020
- 2020-12-25 CN CN202011564509.0A patent/CN113012386A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101777114A (en) * | 2009-01-08 | 2010-07-14 | 北京中星微电子有限公司 | Intelligent analysis system and intelligent analysis method for video monitoring, and system and method for detecting and tracking head and shoulder |
| CN101872418A (en) * | 2010-05-28 | 2010-10-27 | 电子科技大学 | Detection method based on group environment abnormal behavior |
| CN103189758A (en) * | 2010-08-30 | 2013-07-03 | 高通股份有限公司 | Audio-based environment awareness |
| CN105308657A (en) * | 2013-04-23 | 2016-02-03 | 卡纳里连接公司 | Security and/or monitoring devices and systems |
| CN103632504A (en) * | 2013-12-17 | 2014-03-12 | 上海电机学院 | Silence reminder for library |
| CN103679215A (en) * | 2013-12-30 | 2014-03-26 | 中国科学院自动化研究所 | Video monitoring method based on group behavior analysis driven by big visual big data |
| CN105989683A (en) * | 2015-02-12 | 2016-10-05 | 贝斯科技国际有限公司 | Enhanced residence security system |
| CN105138982A (en) * | 2015-08-21 | 2015-12-09 | 中南大学 | Crowd abnormity detection and evaluation method based on multi-characteristic cluster and classification |
| CN106161798A (en) * | 2016-07-25 | 2016-11-23 | 吉林省万和电力设备有限公司 | A kind of intelligent radio LED street lamp |
| CN106331657A (en) * | 2016-11-02 | 2017-01-11 | 北京弘恒科技有限公司 | Video analysis and detection method and system for crowd gathering and moving |
| CN108154108A (en) * | 2017-12-22 | 2018-06-12 | 触景无限科技（北京）有限公司 | The monitoring method and device of a kind of emergency |
| CN108647582A (en) * | 2018-04-19 | 2018-10-12 | 河南科技学院 | Goal behavior identification and prediction technique under a kind of complex dynamic environment |
| CN111354144A (en) * | 2018-12-24 | 2020-06-30 | 阿里巴巴集团控股有限公司 | Security early warning system, method, equipment and storage medium |
| KR20200104548A (en) * | 2019-02-27 | 2020-09-04 | 동명대학교산학협력단 | Risk alarm system with the safety block |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109064698B (en) | Resident security early warning method and resident security early warning system | |
| US4843377A (en) | Remote confinement system | |
| US7298256B2 (en) | Crisis monitoring system | |
| US7876351B2 (en) | Methods and systems for alerting by weighing data based on the source, time received, and frequency received | |
| Skolnick | Deception by police | |
| Cretney et al. | Punishing violence | |
| CN110245630A (en) | Monitoring data processing method, device and readable storage medium storing program for executing | |
| CN107320081A (en) | To drug addict relapse the method and system of monitoring | |
| Fox | Dr Schwitzgebel's machine revisited: Electronic monitoring of offenders | |
| CN106056843A (en) | Intelligent alarm bracelet for identifying cry for help and abnormal pulse, and intelligent alarm method thereof | |
| CN112349015B (en) | Shelter management and control system and method based on Internet of things | |
| CN106327813A (en) | Intelligent voice recognition and alarm method and system thereof | |
| CN110222216B (en) | Multifunctional intelligent defense system | |
| Ferguson et al. | Murder by pushing: an exploratory analysis of homicidal falls from a height | |
| JP2008158745A (en) | Automatic abnormal bird behavior analysis system and construction work management method using the same | |
| CN113012386A (en) | Security alarm multi-level linkage rapid pushing method | |
| CN111820880A (en) | Campus overlord early warning system and method | |
| CN111047828A (en) | Household intelligent security alarm system | |
| Lee | No Exigency, No Consent: Protecting Innocent Suspects from the Consequences of Non-Exigent Show-Ups | |
| CN114627581B (en) | Coerced fingerprint linkage alarm method and system for intelligent door lock | |
| CN114694344A (en) | Campus violence monitoring method and device and electronic equipment | |
| CN115762046A (en) | Early warning and intervention device for building top light life person | |
| CN113158847A (en) | Unsafe behavior detection method based on artificial intelligence | |
| Stone | Past-Acts Evidence in Excessive Force Litigation | |
| Joshua | Achieving quick, fair and effective administration of criminal justice in Ondo State under OSACJL 2015: The role of the police |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210622 |
|
| RJ01 | Rejection of invention patent application after publication |