CN113920660A - Safety monitoring method and system suitable for safety storage equipment - Google Patents
Safety monitoring method and system suitable for safety storage equipment Download PDFInfo
- Publication number
- CN113920660A CN113920660A CN202111158338.6A CN202111158338A CN113920660A CN 113920660 A CN113920660 A CN 113920660A CN 202111158338 A CN202111158338 A CN 202111158338A CN 113920660 A CN113920660 A CN 113920660A
- Authority
- CN
- China
- Prior art keywords
- safe
- preset
- information
- data
- safe box
- 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.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000003860 storage Methods 0.000 title claims abstract description 48
- 230000002159 abnormal effect Effects 0.000 claims abstract description 53
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 50
- 239000003999 initiator Substances 0.000 claims abstract description 7
- 230000001960 triggered effect Effects 0.000 claims abstract description 7
- 230000003287 optical effect Effects 0.000 claims description 43
- 230000006399 behavior Effects 0.000 claims description 29
- 238000004458 analytical method Methods 0.000 claims description 27
- 238000012795 verification Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 12
- 238000013145 classification model Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 29
- 238000005516 engineering process Methods 0.000 description 21
- 238000010586 diagram Methods 0.000 description 15
- 238000012545 processing Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 10
- 230000003993 interaction Effects 0.000 description 9
- 238000012546 transfer Methods 0.000 description 9
- 239000011229 interlayer Substances 0.000 description 8
- 239000010410 layer Substances 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 6
- 238000005192 partition Methods 0.000 description 6
- 230000003068 static effect Effects 0.000 description 6
- 206010000117 Abnormal behaviour Diseases 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 238000011835 investigation Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000010191 image analysis Methods 0.000 description 4
- 239000003795 chemical substances by application Substances 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000001125 extrusion Methods 0.000 description 3
- 238000007639 printing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000004821 distillation Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000005389 magnetism Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F19/00—Complete banking systems; Coded card-freed arrangements adapted for dispensing or receiving monies or the like and posting such transactions to existing accounts, e.g. automatic teller machines
- G07F19/20—Automatic teller machines [ATMs]
- G07F19/209—Monitoring, auditing or diagnose of functioning of ATMs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
-
- 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
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B3/00—Audible signalling systems; Audible personal calling systems
- G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Emergency Management (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Child & Adolescent Psychology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Finance (AREA)
- Electromagnetism (AREA)
- Alarm Systems (AREA)
Abstract
A safety monitoring method and system suitable for safety storage equipment relates to the field of safety equipment, can be applied to the financial field and other fields, and comprises the following steps: acquiring a safe box use request, generating reservation success information after a corresponding safe box is placed in a safe box according to the safe box use request, and feeding back the reservation success information to a safe box use request initiator; collecting operation information of a user on the safe box, comparing the operation information with a preset abnormal rule, and constructing an alarm prompt task triggered after a preset period according to a comparison result; acquiring position information of the safe box according to the comparison result, acquiring video data and audio data of a corresponding area according to the position information, and analyzing according to the video data and the audio data through a risk identification algorithm to obtain a first risk coefficient; and terminating or maintaining the alarm prompt task according to the comparison result of the first risk coefficient and a preset first risk threshold.
Description
Technical Field
The invention relates to the field of safety equipment, can be applied to the financial field and other fields, and particularly relates to a safety monitoring method and a safety monitoring system suitable for safety storage equipment.
Background
The safety box business of the bank only supports the use of the business by the client in the business hours of the bank network and needs the guard of bank staff because the safety verification mode of the bank safety box is single at present. In the client pickup process, bank staff need to firstly carry out technical verification and verification on the real identity of a client, and after the client identity verification is passed, the bank staff still has to carry a secret key to be put in storage together with the client for whole-process accompanying and opening a box door to help the client pick up the piece. This get a process, not only the human cost input is higher, and to the customer, the autonomous operability of customer is not strong, gets a inconvenient. The privacy of the customer is not guaranteed due to the need for accompanying staff.
If the client operates in a self-service mode, the safety and the monitoring of the safe service site need to be monitored and managed more carefully. Due to the limitation of business places provided by banks, when a large number of customers exist, the safe boxes of the customers cannot be placed in all business outlets of the banks and need to be stored in a large safe bank of the banks in a centralized manner, and because the large safe bank and the business outlets of the banks are generally not in the same place, potential safety hazards exist when the customers deposit articles and carry the articles. In addition, because bank safe deposit box area is big, the safe deposit box is many, because focus and angle, the condition of specific certain article case can't clearly accurately be shot to the control often, if the case takes place, the investigation personnel want to trace back the source and look over the surveillance video of involved in the case safe, it is difficult to find the video of making a video recording of the best angle, and still need watch whole-course surveillance video, can't find the key video frequency section fast, the video can not jump and watch, otherwise the video key video that misses easily, the process of looking over is very time consuming, it is lower to trace back the source investigation work efficiency.
Therefore, the current bank safe business has the problems of high labor cost, low efficiency and poor safety and privacy.
Disclosure of Invention
The invention aims to provide a safety monitoring method and a safety monitoring system suitable for safety storage equipment, which solve the problems of high labor cost, low efficiency and poor safety and privacy in the existing bank safe business, not only can store valuables, but also organically combine a safe box with a security system of a financial institution through the Internet of things technology, fully play the role of the security system of the financial institution and improve the capability of the institution in dealing with emergent and serious safety incidents.
To achieve the above object, the present invention provides a security monitoring method for a secure storage device, the method comprising: acquiring a safe box use request, generating reservation success information after a corresponding safe box is placed in a safe box according to the safe box use request, and feeding back the reservation success information to a safe box use request initiator; collecting operation information of a user on the safe box, comparing the operation information with a preset abnormal rule, and constructing an alarm prompt task triggered after a preset period according to a comparison result; acquiring position information of the safe box according to the comparison result, acquiring video data and audio data of a corresponding area according to the position information, and analyzing according to the video data and the audio data through a risk identification algorithm to obtain a first risk coefficient; and terminating or maintaining the alarm prompt task according to the comparison result of the first risk coefficient and a preset first risk threshold.
In the above method for monitoring security of a secure storage device, preferably, before collecting the operation information of the safe by the user, the method further includes: and acquiring identity authentication information provided by a user, and opening a corresponding safe box for placing the safe box according to the identity authentication information.
In the above safety monitoring method for a safety storage device, preferably, the collecting operation information of the safe by the user further includes: collecting video data and audio data of a preset area, and analyzing through a risk identification algorithm according to the video data and the audio data to obtain a second risk coefficient; and when the second risk coefficient is higher than a preset second risk threshold, generating an alarm prompt signal.
In the above security monitoring method for a secure storage device, preferably, the method further includes: and according to the comparison result of the first risk coefficient and a preset first risk threshold, archiving and storing the video data and the audio data to a preset position according to a preset path through the acquisition time of the video data and the audio data and the number information of acquisition equipment.
In the above method for monitoring security of a secure storage device, preferably, the collecting location information of the safe according to the comparison result includes: broadcasting the equipment identification of the safe to a positioning base station in a preset area through an ultra-wideband pulse signal according to the comparison result; and calculating and obtaining the position information by the positioning base station according to the TDOA and AOA positioning algorithm.
In the above safety monitoring method for a safety storage device, preferably, the preset abnormal rule includes a plurality of abnormal event comparison items, where the abnormal event comparison items include one or more combinations of a moving distance of a safe, an abnormal opening distance of a safe cover body, an error frequency of inputting a password, a collision condition of the safe, and a change condition of an object in the safe.
In the above method for security monitoring applicable to a secure storage device, preferably, the obtaining a first risk coefficient by analyzing the video data and the audio data through a risk identification algorithm includes: capturing face data in the video data through a face recognition algorithm; comparing the face data with preset face data to obtain a face similarity value, and obtaining target identity information according to the comparison result of the face similarity value and a preset similarity threshold value; analyzing and obtaining depth three-dimensional information of a target person in the video data through a depth vision algorithm; analyzing the video data through preset behavior category definition and the depth three-dimensional information to obtain behavior data of a target person; and calculating to obtain a first risk coefficient through a preset risk identification model according to the target identity information and the behavior data.
In the above safety monitoring method for a safety storage device, preferably, the obtaining of the behavior data of the target person by analyzing the video data according to the preset behavior category definition and the depth three-dimensional information includes: extracting and collecting the video data according to preset behavior category definition to obtain source video data, and extracting image frame data according to the source video data in a classification mode according to behavior intervals; calculating image frame data through a full variation 1 normal form algorithm to obtain optical flow image frame data, and training by adopting cross entropy as a loss function according to the optical flow image frame data to obtain an optical flow branch model; establishing a bridging relation between the optical flow branches and the image frame branches according to preset weight parameters of the optical flow branches, and training a preset image classification model through image frame data according to the bridging relation to obtain an image branch model; and acquiring behavior data of the target person according to the image frame data, the optical flow branch model and the image branch model.
In the above method for security monitoring applicable to a secure storage device, preferably, the obtaining a first risk coefficient by analyzing the video data and the audio data through a risk identification algorithm includes: converting the audio data into text data; performing abnormal semantic recognition on the character text data through a preset abnormal keyword and a preset semantic recognition algorithm to obtain an abnormal semantic recognition result; and obtaining a first risk coefficient according to the abnormal semantic recognition result.
The invention also provides a safety monitoring system, which comprises a safe box, a control terminal, a prompt module, an analysis module and a plurality of operation modules; the operation module comprises a safety box, a verification module and a safety door; the safe box is used for placing a safe box; the verification module is used for verifying the identity authentication information provided by the user and opening the corresponding safe case according to the verification result; the safety door is used for opening and closing the access passage of the operation module; the control terminal is used for acquiring a safe box use request, generating reservation success information after a corresponding safe box is placed in the safe box according to the safe box use request, and feeding the reservation success information back to a safe box use request initiator; the prompt module is used for acquiring operation information of a user on the safe box, comparing the operation information with a preset abnormal rule, and constructing an alarm prompt task triggered after a preset period according to a comparison result; the analysis module is used for acquiring position information of the safe box according to the comparison result, acquiring video data and audio data of a corresponding area according to the position information, and analyzing the video data and the audio data through a risk identification algorithm to obtain a first risk coefficient; and terminating or maintaining the alarm prompt task according to the comparison result of the first risk coefficient and a preset first risk threshold.
In the above security monitoring system, preferably, the analysis module includes a positioning base station, and the positioning base station is configured to receive the device identifier of the safe, which is broadcast by the positioning tag on the safe through the ultra-wideband pulse signal, and calculate and obtain the location information by using a TDOA and AOA positioning algorithm.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method when executing the computer program.
The present invention also provides a computer-readable storage medium storing a computer program for executing the above method by a computer.
The invention has the beneficial technical effects that: the safe box can be used for storing valuables, and the safe box is organically combined with a security system of a financial mechanism through the Internet of things technology, so that the security system of the financial mechanism is fully exerted, and the capability of the mechanism for dealing with emergency severe safety events is improved. Meanwhile, the image recognition technology and the Internet of things technology are automatically discriminated, so that the false alarm condition caused by equipment misinformation is prevented, when the safe box is opened, moved and abnormal conditions occur, the monitoring system can rapidly record to form a short video, and the short video files are classified and stored by the system according to the serial numbers of the safe box. Because the system can accurately judge the abnormal condition, only record and store the monitoring video of the abnormal condition, and carry out numbering and filing according to the safe box number and the date and time of the abnormal condition, investigators can quickly look over the short video of the moved and opened safe box according to the safe box number and the time of the abnormal event, and the invalid video of the static safe box is automatically filtered by the system and skipped without special storage, thereby greatly reducing the storage pressure of the video monitoring system and improving the investigation efficiency.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
fig. 1 is a schematic flowchart of a security monitoring method applied to a secure storage device according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a position location principle according to an embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating a process of obtaining a first risk coefficient by using video data according to an embodiment of the present invention;
FIG. 4 is a flow chart illustrating behavior data acquisition using video data according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a training process of an optical flow branch according to an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating bridging of optical flow branches and RGB branches according to an embodiment of the present invention;
FIG. 7 is a flowchart illustrating a process of obtaining a first risk factor using audio data according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a security monitoring system according to an embodiment of the present invention;
fig. 9 is a schematic application flow diagram of a security monitoring system according to an embodiment of the present invention;
fig. 10A to 10C are schematic structural views of a safe device according to an embodiment of the present invention;
FIG. 11 is a schematic circuit logic diagram of a safe device according to an embodiment of the present invention;
figure 12 is a schematic structural view of a safe provided by an embodiment of the invention;
fig. 13 is a schematic circuit logic diagram of the safe according to an embodiment of the present invention.
Detailed Description
The following detailed description of the embodiments of the present invention will be provided with reference to the drawings and examples, so that how to apply the technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented. It should be noted that, unless otherwise specified, the embodiments and features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are within the scope of the present invention.
Additionally, the steps illustrated in the flow charts of the figures may be performed in a computer system such as a set of computer-executable instructions and, although a logical order is illustrated in the flow charts, in some cases, the steps illustrated or described may be performed in an order different than here.
Referring to fig. 1, the present invention provides a security monitoring method for a secure storage device, the method comprising:
s101, acquiring a safe box use request, generating reservation success information after a corresponding safe box is placed in a safe box according to the safe box use request, and feeding back the reservation success information to a safe box use request initiator;
s102, collecting operation information of a user on the safe box, comparing the operation information with a preset abnormal rule, and constructing an alarm prompt task triggered after a preset period according to a comparison result;
s103, acquiring position information of the safe box according to the comparison result, acquiring video data and audio data of a corresponding area according to the position information, and analyzing according to the video data and the audio data through a risk identification algorithm to obtain a first risk coefficient;
s104, terminating or maintaining the alarm prompt task according to the comparison result of the first risk coefficient and a preset first risk threshold.
Therefore, the safety monitoring method suitable for the safety storage device not only can store valuables, but also organically combines the safe box with the security system of the financial institution through the internet of things technology, fully plays the role of the security system of the financial institution and improves the capability of the institution in dealing with sudden emergency serious safety events; meanwhile, the image recognition technology and the Internet of things technology are automatically discriminated, so that the false alarm condition caused by equipment misinformation is prevented, when the safe box is opened, moved and abnormal conditions occur, the monitoring system can rapidly record to form a short video, and the short video files are classified and stored by the system according to the serial numbers of the safe box.
In an embodiment of the present invention, before collecting the operation information of the safe from the user, the method further includes: and acquiring identity authentication information provided by a user, and opening a corresponding safe box for placing the safe box according to the identity authentication information. Further, collecting the operation information of the safe box by the user further comprises: collecting video data and audio data of a preset area, and analyzing through a risk identification algorithm according to the video data and the audio data to obtain a second risk coefficient; and when the second risk coefficient is higher than a preset second risk threshold, generating an alarm prompt signal. In actual work, the risk identification algorithm can adopt a simple comparison algorithm, for example, a user comes to a designated website within the appointed service time limit to find a designated safe and passes identity verification (password input, fingerprint, identity card, bank card verification and the like), and the safe is opened after the verification is passed so that the user can extract the safe; at the moment, whether the process of extracting the safe box by the user is coerced or whether a plurality of persons are present is required to be confirmed, the operator is not a target user, and therefore the operation can be confirmed according to the video data and the audio data, and whether risks exist is judged; a risk is present when the risk, i.e. the second risk factor, is higher than the second risk threshold; aiming at the danger, the invention adopts a warning prompt signal mode to prompt related working personnel to intervene so as to ensure the operation safety and property safety of users. Of course, there are many ways and kinds of risk identification algorithms, and those skilled in the art can select an appropriate way according to actual needs to determine whether the user is at risk according to the video and audio data, and the present invention is not limited further.
In the above embodiment, the method may further include: and according to the comparison result of the first risk coefficient and a preset first risk threshold, archiving and storing the video data and the audio data to a preset position according to a preset path through the acquisition time of the video data and the audio data and the number information of acquisition equipment. Therefore, the classified storage of the abnormal audio and video data is completed, and effective evidence is provided for follow-up responsibility confirmation; the specific classification saving method will be described in detail in the following examples, and will not be described in detail here.
In an embodiment of the present invention, the collecting the location information of the safe according to the comparison result includes: broadcasting the equipment identification of the safe to a positioning base station in a preset area through an ultra-wideband pulse signal according to the comparison result; and calculating and obtaining the position information by the positioning base station according to the TDOA and AOA positioning algorithm. In actual work, a positioning tag can be arranged in an interlayer of a box body of the safe box, and a positioning data signal is sent by using the positioning tag, so that positioning base stations in different directions capture the signal, the three-dimensional space coordinate of the tag can be accurately positioned, and the position of the positioning tag can be accurately judged. This location label technique is totally different with traditional RFID, bluetooth, WIFI data location mode, and above several kinds of traditional modes can only fix a position in certain regional scope, also can't give accurate position on three-dimensional space, and WIFI can only reach about 2 meters at the precision of indoor location for example, can't accomplish accurate location. The present invention uses UWB (ultra wide band) pulse signals, as shown in fig. 2, and the ultra wide band positioning technique is a new technique that is completely new and greatly different from the conventional communication positioning technique. The method uses anchor nodes and bridge nodes with known directions which are arranged in advance to communicate with newly joined blind nodes, uses a triangle positioning or perhaps 'fingerprint' positioning method to confirm the directions, uses a plurality of sensors to select TDOA and AOA positioning algorithms to analyze the label directions, and has strong multipath resolution and high precision, and the positioning precision can reach centimeter level. The three-dimensional space coordinate acquisition system can accurately acquire three-dimensional space coordinates, assist a bank safety system to accurately adjust a camera to acquire monitoring images and audio data, greatly improve monitoring accuracy and avoid frequent false alarm.
In an embodiment of the present invention, the preset exception rule includes a plurality of exception event comparison items, where the exception event comparison items include one or more combinations of a moving distance of the safe, an abnormal opening distance of the safe cover, a number of times of password error input, a collision condition of the safe, and a change condition of an object in the safe. In actual work, the short video data classified storage can be performed by using the abnormal event comparison items, for example, short video data files of abnormal situations such as continuous password error, opening of a box cover, severe collision of a safe box or triggering of a collision sensor due to extrusion are stored in a partition (block or folder) according to the safe box number, the video files of one safe box are uniformly placed in an independent partition (block or folder), the partition (block or folder) is named by the safe box number, and the short video data files are named according to the following rules, as shown in table 1:
TABLE 1
Because the invention accurately judges the abnormal condition, records and stores only the monitoring video of the abnormal condition, and carries out numbering and filing according to the safe box number and the date and time of the abnormal condition, investigators can quickly look over the short video of the moved and opened safe box according to the safe box number and the time of the abnormal event, and the invalid video of the static safe box is automatically filtered and skipped by the system without special storage, thereby greatly reducing the storage pressure of the video monitoring system and improving the investigation efficiency.
Referring to fig. 3, in an embodiment of the present invention, the obtaining the first risk coefficient by analyzing the video data and the audio data through a risk identification algorithm includes:
s301, capturing face data in the video data through a face recognition algorithm;
s302, comparing the face data with preset face data to obtain a face similarity value, and obtaining target identity information according to the comparison result of the face similarity value and a preset similarity threshold value;
s303, analyzing and obtaining depth three-dimensional information of a target person in the video data through a depth vision algorithm, and analyzing the video data through preset behavior type definition and the depth three-dimensional information to obtain behavior data of the target person;
s304, calculating according to the target identity information and the behavior data through a preset risk identification model to obtain a first risk coefficient.
In the embodiment, the face image is captured from the image data, the face recognition is performed according to the similarity between the pre-stored face image and the captured face image, the depth three-dimensional information of the target person is acquired from the image based on a depth vision algorithm, and the abnormal behavior analysis is performed according to the depth three-dimensional information of the target person. Specifically, the image analysis module calculates the similarity between the captured face image and a pre-stored face image, if the similarity between the captured face image and a pre-stored image reaches a preset similarity threshold, the face recognition is judged to be successful, and the information of the captured face image is determined according to the pre-stored image information. And then based on a depth vision algorithm, acquiring depth three-dimensional information (target height information, accuracy of target behavior analysis and multi-target detection, target position information, multi-target detection, especially target distance detection, target depth information and judgment of multi-target position distance) of the target personnel from the image, and realizing abnormal behavior analysis such as border crossing, entering/leaving area, area intrusion, loitering, personnel focusing, quick movement, illegal parking, object leaving/taking and the like. For example, at this time, the time is night non-business hours, but a face which is not on the white list appears in the monitoring picture or video, namely, the suspicious state is judged, and the remote security monitoring agent equipment is notified to carry out follow-up processing. If the picture shows that the communication device is in a static state or no suspicious people exist nearby the user, the judgment is that the safe box reports the wrong.
Referring to fig. 4, in an embodiment of the present invention, analyzing the video data to obtain behavior data of a target person according to a preset behavior category definition and the depth three-dimensional information includes:
s401, extracting and collecting the video data according to preset behavior category definition to obtain source video data, and extracting image frame data according to the source video data in a classification mode according to behavior intervals;
s402, calculating image frame data through a full variational 1 normal form algorithm to obtain optical flow image frame data, and training by adopting cross entropy as a loss function according to the optical flow image frame data to obtain an optical flow branch model;
s403, establishing a bridging relation between the optical flow branches and the image frame branches according to preset weight parameters of the optical flow branches, and training a preset image classification model through image frame data according to the bridging relation to obtain an image branch model;
s404, acquiring behavior data of a target person according to the image frame data, the optical flow branch model and the image branch model.
In actual work, the flow of fig. 4 may include three parts, namely, preprocessing the acquired video data, defining behavior categories, searching for source videos, acquiring data, and storing in a classified manner; and determining a video key behavior interval, determining a frame rate, an image position and an image resolution, and extracting and storing an image frame of the trimmed video. And cleaning and training video light stream data, including light stream branch training, light stream feature transfer and RGB training. And respectively inputting the RGB image and the optical flow image into the trained RGB branch and optical flow branch to obtain behavior classification.
The specific implementation modes of optical flow branch training, optical flow feature transfer and RGB training are as follows: firstly, the optical flow branch training utilizes a full variation 1 model algorithm to calculate RGB image frames of a source video, and optical flow image frames in the horizontal direction and the vertical direction are respectively obtained from two adjacent frames. And 3-dimensional convolution and pooling expansion are carried out on the pre-trained optical flow image classification model according to the expansion 3D operation. The corresponding horizontal optical flow graph and vertical optical flow graph are input into the model for training, and cross entropy is used as a loss function to obtain trained optical flow branches, which can be specifically referred to as fig. 5.
Secondly, the optical flow feature transfer firstly fixes the trained optical flow branch weight parameters, and then establishes the bridge connection between the optical flow branches and the RGB branches to realize the transfer of the optical flow feature information, which can be referred to as the graph shown in FIG. 6; adding intermediate layer features, namely optical flow features, obtained by branching the optical flow of the same video, into intermediate layer features of RGB branches in a distillation calculation mode for splicing to obtain intermediate layer features with increased dimensionality, and then training according to a normal path; performing gradient reduction on the weighting loss function, and optimizing training parameters in multiple rounds to obtain trained RGB branches; and integrating the optical flow branch and the RGB branch through a full connection layer to obtain final output. The transfer comprises two bridging links, the first bridging link being a transfer during the 3D convolutional layer, the bridging link being selected from 9 links a to i according to the experimental results of a particular video set, denoted Feature1flowTo Feature1RGBTransferring;
finally, performing RGB training, selecting a pre-trained RGB image classification model, performing 3-dimensional convolution and pooling expansion according to expansion 3D operation, and inputting RGB image frames; connecting the optical flow branches, calculating the characteristics of the RGB branches and the optical flow branches by using a full-connection classifier, and outputting classification probability; and constructing a loss function, wherein the loss function consists of three parts, namely the 2 norm of the first transfer line, the 2 norm of the second transfer line and the cross entropy of the final classification.
losstotal＝α1L1+β1L2+γ1L3
＝α1||Feature1RGB-Feature1flow||2
+β1||Feature2RGB-Feature2flow||2
+γ1CroSSEntropy(p，y).
In the above equation, the loss function includes three terms, the first term represents the portion of the first transfer line, L1 is the 2 norm of the difference between the RGB features and the optical flow features at this stage, α1Is L1 corresponds to a weight; the second term represents the second portion of the transmission line, L2 being the 2 norm, β, of the difference between the two characteristics at this stage1Is L2 corresponds to a weight; the third term L3 is the cross entropy of the final classification, γ1Is L3 corresponds to a weight; feature1RGBIs a first piece of RGB information; feature1flowIs a first piece of optical flow information; feature2RGBFeature2 as a second piece of RGB informationflowIs the second optical flow information.
Referring to fig. 7, in an embodiment of the present invention, the obtaining the first risk coefficient by analyzing the video data and the audio data through a risk identification algorithm includes:
s701, converting the audio data into text data;
s702, carrying out abnormal semantic recognition on the character text data through a preset abnormal keyword and a preset semantic recognition algorithm to obtain an abnormal semantic recognition result;
s703, obtaining a first risk coefficient according to the abnormal semantic recognition result.
In actual work, the abnormal keywords can be life saving, robbery and the like, the semantic recognition algorithm can be an existing speech recognition model, and the method is not described in detail herein. Further, the first risk coefficients respectively obtained based on the video data and the audio data can be weighted and accumulated to obtain a comprehensive risk coefficient; therefore, whether the current early warning is false warning or not is accurately analyzed by utilizing the comprehensive risk coefficient. Furthermore, the worker may also activate safety protection measures, such as locking a safety door, contacting with law enforcement, alarming, etc., according to the calculation result, and the related technical personnel in the field may select the setting according to the actual needs, and the invention is not further limited herein.
The invention also provides a safety monitoring system, which comprises a safe box, a control terminal, a prompt module, an analysis module and a plurality of operation modules; the operation module comprises a safety box, a verification module and a safety door; the safe box is used for placing a safe box; the verification module is used for verifying the identity authentication information provided by the user and opening the corresponding safe case according to the verification result; the safety door is used for opening and closing the access passage of the operation module; the control terminal is used for acquiring a safe box use request, generating reservation success information after a corresponding safe box is placed in the safe box according to the safe box use request, and feeding the reservation success information back to a safe box use request initiator; the prompt module is used for acquiring operation information of a user on the safe box, comparing the operation information with a preset abnormal rule, and constructing an alarm prompt task triggered after a preset period according to a comparison result; the analysis module is used for acquiring position information of the safe box according to the comparison result, acquiring video data and audio data of a corresponding area according to the position information, and analyzing the video data and the audio data through a risk identification algorithm to obtain a first risk coefficient; and terminating or maintaining the alarm prompt task according to the comparison result of the first risk coefficient and a preset first risk threshold. Wherein the analysis module may comprise a location base station for receiving the equipment identification of the safe broadcast by the location tag on the safe through an ultra-wideband pulse signal, and calculating to obtain the position information by using TDOA and AOA location algorithm.
Specifically referring to fig. 8, in actual work, the security monitoring system provided by the invention organically combines the safe device with the security system of the financial institution through the internet of things technology, and automatically discriminates through the image recognition technology, so as to prevent the false alarm condition caused by the false alarm of the equipment, fully play the role of the security system of the financial institution, and improve the capability of the bank safe operating financial place for dealing with the emergency severe security event; the method specifically comprises the following steps: the system comprises a safe box device 100, a positioning base station 200, a high-definition monitoring camera 300, a bank security system server 400 (the bank security system server integrates a control terminal, a prompt module and an analysis module), remote security monitoring seat equipment 500 and a security door 600.
The safe box device 100 is placed in safe boxes of a bank, each safe box is arranged in an operation network point of the safe box, an independent small operation room is arranged in the safe box, a safety door capable of being locked is arranged in the room, and before a user opens the safe box, a system automatically checks whether the safety door of the operation room is locked or not so as to protect the privacy of the client and the operation safety.
The positioning base station 200 is an important component of the safety protection system, is responsible for data communication with the safe device 100, and performs "dual-channel" data interaction with the wireless communication module and the positioning tag on the safe device 100. The safety protection system adopts an indoor positioning technology of an ultra-wideband technology, and can accurately judge the spatial position of the safe box device by matching with the positioning label on the safe box device 100. As shown in fig. 6, the security protection system of the present invention uses anchor nodes and bridge nodes with known locations, which are arranged in advance, to communicate with newly participating blind nodes, and uses triangulation location or "fingerprint" location method to determine the location of the location tag, wherein the location system uses N location base stations (N > -3), and uses TDOA and AOA location algorithm to analyze the location of the tag, so that multipath resolution is strong, accuracy is high, and location accuracy can reach centimeter level. The TDOA location algorithm is a method that uses time difference of arrival to perform location. The positioning tag continuously sends information to the periphery, and the information contains the ID value of the tag. When the safety protection system is deployed nearby and at least three base stations receive the information, the current position of the tag can be calculated according to the time difference of the information reaching the three base stations. The safety protection system acquires X, Y, Z three-dimensional coordinates of the safe box equipment, and when the positioning base station is installed, the height difference of the Z axis needs to be particularly pulled to ensure the accuracy on the Z axis.
The high-definition monitoring camera 300 precisely adjusts the direction and the focal length of the camera according to the X, Y, Z three-dimensional coordinates calculated by the bank security system server 400, and more clearly and accurately captures the image information of the position of the safe and the surrounding environment. The high-definition monitoring camera can comprise a binocular pan-tilt camera and an intelligent vision analysis module. The binocular tripod head is provided with two cameras of visible light and infrared thermal imaging, and can operate in all weather. The intelligent visual analysis module can analyze image information acquired by the camera in real time based on a deep visual algorithm, can finish face recognition and abnormal behavior analysis, wherein abnormal behaviors comprise border crossing, entering/leaving of areas, regional invasion, wandering, personnel focusing, rapid movement, article leaving/taking and the like, and transmits analysis results to the main control analysis unit, and deep learning refers to an algorithm set for solving various problems such as images, texts and the like by applying various machine learning algorithms on a multilayer neural network. The core of deep learning is feature learning, and aims to obtain hierarchical feature information through a hierarchical network, so that the important problem that features need to be designed manually in the past is solved. Deep learning is a framework, and comprises a plurality of important algorithms, such as a Convolutional Neural Network (CNN), a Deep Belief Network (DBN), a Recursive Neural Network (RNN) and the like, and for different problems (images, voice and text), different Network models are required to achieve better effects. The camera also comprises a microphone and a loudspeaker, wherein the microphone can collect on-site indoor sound, and the loudspeaker is used for carrying out voice communication with indoor personnel or giving out alarm sound.
The bank security system server 400 accurately monitors and analyzes the indoor security environment condition of the financial institution through the positioning base station 200 and the high-definition monitoring camera 300, and the server notifies the remote security monitoring agent equipment 500 after judging that a security event occurs.
The remote security monitoring seat device remotely controls the bank security system server and moves the high-definition monitoring camera 300 to monitor the field situation according to the security prompt reported by the bank security system server 400, and if an emergency security event occurs, a series of security measures such as alarming or controlling to close the security door 600 and start an indoor alarm bell can be taken.
The system can solve the problems that the traditional technologies such as RFID, Bluetooth, WIFI and the like can only identify the monitored object in the monitoring range, but cannot accurately identify the specific direction of the monitored object, are inaccurate in positioning, cannot rapidly command the camera to accurately position the emergency occurrence position when the emergency occurs, cannot automatically identify through system intelligence, automatically eliminates the situation of false alarm, reduces manual participation, improves the emergency response efficiency and the like.
For facilitating understanding of the practical application process of the safety monitoring system provided by the present invention, please refer to fig. 9 for further explanation of the overall process flow of the system, and it should be understood by those skilled in the art that the embodiment is not limited to any technical limitations.
Step S901: the customer can reserve the safe deposit box business in advance through channels such as a mobile phone bank, a telephone bank and the like, and selects a service network point. The bank staff puts the safe of the customer into the safe, the safe information reading unit 401 of the safe is used for reading the data in the electronic tag on the RFID chip on the safe, and sends the reservation success information to the customer through APP information or short message, and informs the customer to come the appointed network to get the safe service, and the information data of the notice includes network address, safe number, service time limit and the like.
Step S902: the customer comes to a designated network point within the service time limit of the appointment, finds a designated safe, and opens the cabinet door after the system detects the environmental security of the operating room through identity verification (password input, fingerprint, identity card, bank card verification and the like).
Optionally, after the bank system receives the instruction input information of the numeric keypad or the touch screen of the customer, the safe system automatically checks whether the safety door of the operating room is locked, and if the safety door is unlocked, locking processing is performed to protect privacy of the customer and operation safety. Further, after the bank system receives the instruction input information of a digital keyboard or a touch screen of a client, the safety box system starts a bank safety system to collect field video and audio data, and whether the client is abnormal or not is automatically and intelligently analyzed through the image analysis module and the voice analysis module, for example, whether a plurality of persons are present or not is judged by the system, and if the system is judged to be abnormal, the safety of the client operating field is ensured by informing a remote seat to automatically intervene.
Step S903: the customer takes out the safe and opens the cover for operation by checking the identity of the safe (password or fingerprint). And starting to operate the safe box from the client, and sending a starting signal to the outside by the control module through the wireless communication module, wherein the starting signal comprises positioning label data. And N (N > -3) positioning base stations deployed at the periphery of the room acquire the data transmitted by the wireless communication module and the positioning tag on the safe box device. Meanwhile, the positioning calculation module analyzes and calculates data acquired by different positioning base stations, calculates the position of the label at the time according to the time difference of information reaching the N base stations, and acquires X, Y, Z three-dimensional coordinates of the safe box equipment.
Step S904: the camera shooting control module adjusts the direction and the focal length of the camera according to the three-dimensional coordinates of the safe box equipment obtained by calculation of the positioning calculation module, so that the image information of the position of the safe box device and the surrounding environment can be clearly and accurately captured, and the main control module controls the camera to collect field video images and voice data. The main control module collects image data until the safe box recovers to a static state or the abnormal state is relieved for a period of time (for example, 5 minutes), names and numbers the short video data files according to requirements, and stores the short video data files in the video storage module.
Step S905: the image analysis module captures a face image from the image, performs face recognition according to the similarity between the pre-stored face image and the captured face image, acquires depth three-dimensional information of a target person from the image based on a depth vision algorithm, and performs abnormal behavior analysis according to the depth three-dimensional information of the target person.
Step S906: the voice analysis module analyzes the voice of the security inspection area collected by the microphone, performs abnormal semantic analysis according to the voice, and sends an abnormal semantic analysis result to the main control module.
Step S907: the main control module judges whether the alarm is false alarm or not according to the analysis results of the image analysis module and the voice analysis module, and if the alarm is false alarm, the main control module sends a closing instruction to a power switch of the safe box to close the alarm; and if the situation is suspicious, the remote security monitoring agent is notified to carry out follow-up confirmation processing. The remote security monitoring seat watches the field condition through the monitoring camera or carries out voice communication with the user, and if the remote security monitoring seat is abnormal, a series of safety measures such as alarming or controlling to close the safety door can be taken. Furthermore, in order to avoid that the remote seat cannot timely handle the abnormal situation due to off duty or other reasons, the method allows that the remote seat has no feedback confirmation information in a certain period, and the main control module automatically starts to take a series of safety measures such as alarming or controlling to close the safety door.
Step S908: if the main control module judges that the field condition is normal and the client belongs to a white list operator, only an instruction is sent to the camera control module to control the camera and the microphone to collect image and sound data, the image data is collected until the safe box recovers the static state or the abnormal state is relieved for a period of time (for example, 5 minutes), and the short video data files are named and numbered according to requirements and are stored in the video storage module. The video storage module is used for classifying and storing short video data files in abnormal conditions (such as continuous password errors, cover opening, violent collision of a safe box or collision sensor triggering caused by extrusion), the files are stored in a partition (block or folder) according to safe box numbers, the video files of one safe box are uniformly placed in an independent partition (block or folder), the partition (block or folder) is named by the safe box numbers, and the short video data files are named according to a rule of 'table 1'.
After the customer finishes the operation, the safe box is covered and put back into the safe box, and after the system checks that the safe box is correct, the safety door is unlocked, and the service is finished.
In an embodiment of the present invention, the safe device may include a main control chip, an alarm module, an input module, a safe box, a positioning tag, a collision sensor, and a time delay; the safe box body comprises a box body structure, a box cover structure and an electronic lock catch; the box body structure is a hollow square box body with an opening on one side and is used for placing deposited articles; the box cover structure is arranged corresponding to the opening position of the square box body and used for closing the hollow square box body through the electronic lock catch; the input module is arranged on one side of the hollow square box body and used for receiving input information provided by a user; the collision sensor is arranged in an interlayer in the hollow square box body and used for collecting collision information received by the safe box body; the main control chip is respectively connected with the collision sensor, the input module, the alarm module, the positioning tag, the electronic lock catch, the input module and the delayer and is used for outputting an electric signal to the delayer and the positioning tag according to the collision information; outputting an electric signal to the alarm module according to the electric signal fed back by the delayer; controlling the electronic lock catch to open the hollow square box body according to the input information; the delayer is used for establishing a delay triggering task according to the received electric signal and feeding back an electric signal after a preset period according to the delay triggering task; the alarm module is used for sending out alarm prompt information according to the received electric signal; the positioning tag is used for broadcasting the pre-stored tag information to a preset area according to the received electric signal.
In the above embodiment, the device may further include a display screen, an RFID chip, and an RFID antenna, where the display screen is connected to the main control chip and is configured to display the interactive information output by the main control chip; the RFID chip is arranged in an interlayer of the box cover structure, is respectively connected with the main control chip and the RFID antenna, and is used for prestoring the associated information of the safe box device; and performing data interaction with an external RFID read-write device through the RFID antenna. Specifically, as shown in fig. 10A to 10C, in actual operation, the safe device may include a main control chip, a power supply module, a display 101, an electronic lock 102, a buzzer alarm speaker, a safe box 108 and a box cover 103, a positioning tag, a collision sensor, an RFID chip 104, and an RFID antenna. Wherein the case lid carries out zonulae occludens through the electron hasp with the box, is equipped with pull ring handle 105 on the box left and right sides to make things convenient for the safe transport to remove, is provided with RFID electronic tags's chip in the case lid intermediate layer, is equipped with a plurality of collision sensor of location label and dispersion distribution in the box intermediate layer, is equipped with display screen and button on the case lid.
In another embodiment of the present invention, the input module includes a key unit 106 and a fingerprint collector 107; the key unit 106 is configured to receive key information input by a user; the fingerprint collector 107 is used for obtaining fingerprint information input by a user. Furthermore, the device also comprises a communication module, wherein the communication module is connected with the main control chip and used for establishing a communication channel between the main control chip and an external system in a mode of one or more combinations of WIFI, zigbee, LoRaWAN and Bluetooth. Therefore, the key information and the fingerprint information input by the user can be transmitted to the remote server through the communication module for identity verification, so that whether the user can open the safe box device is determined; specifically, referring to fig. 11, in practical work, the safe device provided by the present invention may include a main control chip, a power supply module, a display screen, a key, an electronic lock, a buzzer alarm speaker, a safe body and a safe cover, a positioning tag, a collision sensor, a time delay, a wireless communication module, an RFID chip, and an RFID antenna.
The main control chip is connected with the keys on the box cover through a circuit and is responsible for collecting information input by the keys; the display screen is connected with the circuit and is responsible for displaying related information on the display screen; the electronic lock catch is connected with the electronic lock catch through a circuit and is responsible for opening and closing the electronic lock catch; the RFID chip is connected with the circuit and is responsible for data interaction with the RFID chip; the positioning tag and the collision sensor are connected through a circuit; the circuit is connected with the buzzing alarm horn and is responsible for data interaction with the buzzing alarm horn.
The key is responsible for collecting input information of bank customers or bank personnel and is connected with the main control chip through a circuit. The display screen is responsible for displaying information to a user or bank personnel and is connected with the main control chip through a circuit. The buzzing alarm horn is responsible for sounding and alarming when receiving continuous errors of passwords or receiving electronic signals excited by the collision sensor.
The electronic lock catches are responsible for tightly connecting the box cover and the box body, the number of the electronic lock catches is more than 4, the electronic lock catches are uniformly distributed at the connecting positions of the box cover and the box body, the lock catches are connected with the main control chip through circuits and receive command signals of the main control chip to be opened and closed, and when any one lock catch is damaged by external force, a damaged signal is transmitted to the main control chip.
The RFID chip is arranged in the box cover interlayer, is connected with the main control chip and the RFID antenna through a circuit, can perform data interaction with an external RFID read-write device through the RFID antenna, and records data such as specific safe serial numbers, storage time, information (including height and fingerprints of a client) of clients belonging to the safe and the like in the chip. Data such as the serial number of the safe box, the time of deposit, the information of a client to which the safe box belongs and the like are synchronously updated with data on an external bank monitoring server through a wireless communication module; the RFID antenna is connected with the RFID chip through a circuit, receives and sends wireless signals, and realizes data interaction between an external RFID read-write device and the RFID chip. The safe box body is a square box body made of firm and damage-resistant materials, is used for storing deposited articles of bank users, and can be flexibly set and distributed by banks according to the safe box purchasing service and the space size of the bank users. One or more collision sensors are dispersedly distributed in the interlayer of the box body.
The wireless communication module is responsible for wireless data interaction with an external bank monitoring system. Further, the wireless communication module may use communication modules of technologies such as WIFI, zigbee, LoRaWAN, bluetooth, and the like. The fingerprint collector is used for collecting the fingerprint of the client when the client opens the safe box and carrying out identity authentication on the client. The collision sensors can be arranged in one or more than one box body interlayer in a dispersing way and are used for sending out excitation electronic signals when the safe box collides or extrudes violently, the buzzing alarm loudspeaker on the box body gives out an alarm immediately, and the bank monitoring system receives the electronic signals and then immediately responds to the signals, calls the camera and the monitoring alarm system to respond. The time delay device is used for the conditions that the collision sensor collides or extrudes, the electronic lock catch is forcedly damaged, the password is continuously wrong and the like, the alarm system is not started immediately to give an alarm, the time is timed through the time delay device, during the timing period, the bank monitoring system judges whether the alarm is misinformed through video and audio analysis, if the alarm is misinformed, the alarm is cancelled through the controller before the time delay device finishes timing, and the misinformation is avoided.
The positioning tag is arranged in the interlayer of the box body and can send out positioning data signals, so that positioning base stations in different directions can capture the signals, the three-dimensional space coordinates of the tag can be accurately positioned, and the position of the positioning tag can be accurately judged. This location label technique is totally different with traditional RFID, bluetooth, WIFI data location mode, and above several kinds of traditional modes can only fix a position in certain regional scope, also can't give accurate position on three-dimensional space, and WIFI can only reach about 2 meters at the precision of indoor location for example, can't accomplish accurate location. The invention adopts UWB (ultra wide band) pulse signals, and the ultra wide band positioning technology is a brand new technology which is greatly different from the traditional communication positioning technology. The method uses anchor nodes and bridge nodes with known directions which are arranged in advance to communicate with newly joined blind nodes, uses a triangle positioning or perhaps 'fingerprint' positioning method to confirm the directions, uses a plurality of sensors to select TDOA and AOA positioning algorithms to analyze the label directions, and has strong multipath resolution and high precision, and the positioning precision can reach centimeter level. The three-dimensional space coordinate acquisition system can accurately acquire three-dimensional space coordinates, assist a bank safety system to accurately adjust a camera to acquire monitoring images and audio data, greatly improve monitoring accuracy and avoid frequent false alarm.
As shown in fig. 12, the safe provided by the present invention includes: a plurality of sub-cabinets 301 (each sub-cabinet is provided with an electronic lock 308), a receipt printing outlet 302, a display screen, a bank card reader-writer 303, a fingerprint collector 304, a digital code keyboard 305, an RFID electronic tag read-write device 306 and a radio frequency IC card read-write device 307.
The electronic lock is used for controlling the switch of each sub-locker; the sub-storage cabinets are used for storing safes with different sizes, and the sizes of the safes can be freely selected according to services purchased by customers; one or more collision sensors are dispersedly distributed in the interlayer of the cabinet body. The operation condition of each sub-locker can be monitored by a plurality of cameras distributed in a hash way; the fingerprint collector is used for fingerprints of bank personnel or clients; the RFID electronic tag reading-writing devices can be arranged in a plurality of numbers and are distributed in different positions of the cash box (such as the outside of the cash box or the inside of a sub-locker), so that information of RFID chips placed in the safe box can be accurately read; the radio frequency IC card read-write device can read and write the work radio frequency IC card of bank personnel or the identity card information of a client.
In order to more clearly understand the structure of the safe provided by the present invention, please refer to fig. 13 below, the safe logically includes a safe information reading unit 401, an identity information reading unit 402, a bank card information reading and writing unit 403, a display unit 404, a communication unit 405, a sub-locker array control unit 406, a sub-locker array 407, and a printing unit 408.
The safe information reading unit 401 is connected with the communication unit 405, and the safe information reading unit 401 acquires information on the safe RFID chip and then sends the information to the communication unit 405 for processing. The safe information reading unit 401 is configured to read an electronic tag on an RFID chip on a safe, and may be an RFID electronic tag reading/writing device or other wireless data interaction technologies. The safe information reading unit 401 is an RFID electronic tag reading and writing device, and RFID (Radio Frequency Identification) is a non-contact automatic Identification technology, automatically identifies a target object and obtains related data through a Radio Frequency signal, and has the advantages of water resistance, magnetism prevention, large reading distance, large amount of information stored in a tag and the like.
The identity information reading unit 402 is connected to the communication unit 405, and the identity information reading unit 402 acquires the identity information and then sends the identity information to the communication unit 405 for processing. The identity information reading unit 402 is used for collecting the identity information of the client and the bank worker to which the safe belongs. The identity information reading unit 402 comprises a radio frequency IC card reader-writer, a fingerprint collector and a digital password keyboard, wherein the radio frequency IC card reader-writer is used for collecting information accessed in a client identity card of a safe box and can also collect work IC card information of bank workers, the fingerprint collector is used for collecting fingerprints of the client or the bank workers of the safe box, and the digital password keyboard is used for collecting a client bank card password of the safe box or a bank worker box-taking password.
The bank card information reading and writing unit 403 is connected with the communication unit 405, and the bank card information reading and writing unit 403 acquires the bank card information and then sends the bank card information to the communication unit 405 for processing. The bank card information reading and writing unit 403 includes a bank card reading and writing device and a digital password keyboard. The bank card reading and writing device can be used for reading information of a bank card, and the digital password keyboard is used for collecting a customer bank card password.
The display unit 404 is connected with the communication unit 405 for displaying a human-computer interaction interface.
The communication unit 405 is connected to the safe information reading unit 401, the identity information reading unit 402, the bank card information reading and writing unit 403, the display unit 404, and the sub-locker array control unit 406, and is configured to send information collected by the safe information reading unit 401, the identity information reading unit 402, and the bank card information reading and writing unit 403 to the bank server system for processing, send a processing result returned by the bank server system to the sub-locker array control unit 406, and display content on the display unit 404.
The sub-locker array control unit 406 is connected with the communication unit 405, and the sub-locker array control unit 406 receives a processing result returned by the bank server system and opens the electronic lock and the camera in the corresponding sub-locker in the sub-locker array. When the door of the sub-locker is closed, the sub-locker array control unit 406 closes the electronic lock and the camera in the sub-locker, and transmits the sub-locker status and the video file to the bank server system through the communication unit 405 for updating and storing. The sub-locker array control unit comprises a delayer, the delayer is used for collision or extrusion of a collision sensor, forced damage of an electronic lock, continuous error of passwords and the like, an alarm system cannot be started immediately to give an alarm, timing is carried out through the delayer, during timing, the bank monitoring system judges whether misinformation exists through video and audio analysis, if the misinformation exists, the alarm is cancelled through the controller before timing of the delayer is finished, and the misinformation is avoided.
The sub-locker array 407 comprises a plurality of independently spaced sub-lockers, each of which may be of a different size to accommodate safes of different sizes, each of which has a unique number in the banking system. Each sub-locker is provided with an electronic lock, and the sub-locker array 407 is distributed with a plurality of cameras in a hash manner, so that the operation condition of each sub-locker can be monitored. All electronic locks and cameras of the sub-locker array 407 are controlled by the sub-locker array control unit 406.
The printing unit 408 is used to print the customer's stored credentials.
The invention has the beneficial technical effects that: the safe box can be used for storing valuables, and the safe box is organically combined with a security system of a financial mechanism through the Internet of things technology, so that the security system of the financial mechanism is fully exerted, and the capability of the mechanism for dealing with emergency severe safety events is improved. Meanwhile, the image recognition technology and the Internet of things technology are automatically discriminated, so that the false alarm condition caused by equipment misinformation is prevented, when the safe box is opened, moved and abnormal conditions occur, the monitoring system can rapidly record to form a short video, and the short video files are classified and stored by the system according to the serial numbers of the safe box. Because the system can accurately judge the abnormal condition, only record and store the monitoring video of the abnormal condition, and carry out numbering and filing according to the safe box number and the date and time of the abnormal condition, investigators can quickly look over the short video of the moved and opened safe box according to the safe box number and the time of the abnormal event, and the invalid video of the static safe box is automatically filtered by the system and skipped without special storage, thereby greatly reducing the storage pressure of the video monitoring system and improving the investigation efficiency.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method when executing the computer program.
The present invention also provides a computer-readable storage medium storing a computer program for executing the above method by a computer.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (13)
1. A security monitoring method for a secure storage device, the method comprising:
acquiring a safe box use request, generating reservation success information after a corresponding safe box is placed in a safe box according to the safe box use request, and feeding back the reservation success information to a safe box use request initiator;
collecting operation information of a user on the safe box, comparing the operation information with a preset abnormal rule, and constructing an alarm prompt task triggered after a preset period according to a comparison result;
acquiring position information of the safe box according to the comparison result, acquiring video data and audio data of a corresponding area according to the position information, and analyzing according to the video data and the audio data through a risk identification algorithm to obtain a first risk coefficient;
and terminating or maintaining the alarm prompt task according to the comparison result of the first risk coefficient and a preset first risk threshold.
2. The security monitoring method for a security storage device according to claim 1, wherein before collecting the operation information of the safe by the user, further comprising:
and acquiring identity authentication information provided by a user, and opening a corresponding safe box for placing the safe box according to the identity authentication information.
3. The security monitoring method for a secure storage device of claim 2, wherein collecting user operation information for the safe further comprises:
collecting video data and audio data of a preset area, and analyzing through a risk identification algorithm according to the video data and the audio data to obtain a second risk coefficient;
and when the second risk coefficient is higher than a preset second risk threshold, generating an alarm prompt signal.
4. The security monitoring method for a secure storage device of claim 1, further comprising:
and according to the comparison result of the first risk coefficient and a preset first risk threshold, archiving and storing the video data and the audio data to a preset position according to a preset path through the acquisition time of the video data and the audio data and the number information of acquisition equipment.
5. The security monitoring method for a secure storage device according to any one of claims 1 to 4, wherein the collecting the location information of the safe according to the comparison result comprises:
broadcasting the equipment identification of the safe to a positioning base station in a preset area through an ultra-wideband pulse signal according to the comparison result;
and calculating and obtaining the position information by the positioning base station according to the TDOA and AOA positioning algorithm.
6. The security monitoring method for the secure storage device according to claim 1, wherein the preset exception rule comprises a plurality of exception event comparison items, and the exception event comparison items comprise one or more combinations of a moving distance of the safe, an abnormal opening distance of the safe cover body, a password input error frequency, a collision condition of the safe and a change condition of an object in the safe.
7. The security monitoring method for a secure storage device according to claim 1, wherein obtaining the first risk factor from the video data and the audio data by analyzing the video data and the audio data through a risk identification algorithm comprises:
capturing face data in the video data through a face recognition algorithm;
comparing the face data with preset face data to obtain a face similarity value, and obtaining target identity information according to the comparison result of the face similarity value and a preset similarity threshold value;
analyzing and obtaining depth three-dimensional information of a target person in the video data through a depth vision algorithm;
analyzing the video data through preset behavior category definition and the depth three-dimensional information to obtain behavior data of a target person;
and calculating to obtain a first risk coefficient through a preset risk identification model according to the target identity information and the behavior data.
8. The security monitoring method for a security storage device according to claim 7, wherein analyzing the video data to obtain behavior data of a target person according to a preset behavior category definition and the depth three-dimensional information comprises:
extracting and collecting the video data according to preset behavior category definition to obtain source video data, and extracting image frame data according to the source video data in a classification mode according to behavior intervals;
calculating image frame data through a full variation 1 normal form algorithm to obtain optical flow image frame data, and training by adopting cross entropy as a loss function according to the optical flow image frame data to obtain an optical flow branch model;
establishing a bridging relation between the optical flow branches and the image frame branches according to preset weight parameters of the optical flow branches, and training a preset image classification model through image frame data according to the bridging relation to obtain an image branch model;
and acquiring behavior data of the target person according to the image frame data, the optical flow branch model and the image branch model.
9. The security monitoring method for a secure storage device according to claim 7, wherein obtaining the first risk factor from the video data and the audio data by analyzing the video data and the audio data through a risk identification algorithm comprises:
converting the audio data into text data;
performing abnormal semantic recognition on the character text data through a preset abnormal keyword and a preset semantic recognition algorithm to obtain an abnormal semantic recognition result;
and obtaining a first risk coefficient according to the abnormal semantic recognition result.
10. A security monitoring system comprising the security monitoring method for a secure storage device according to any one of claims 1 to 9, wherein the system comprises a safe, a control terminal, a prompt module, an analysis module, and a plurality of job modules;
the operation module comprises a safety box, a verification module and a safety door;
the safe box is used for placing a safe box; the verification module is used for verifying the identity authentication information provided by the user and opening the corresponding safe case according to the verification result; the safety door is used for opening and closing the access passage of the operation module;
the control terminal is used for acquiring a safe box use request, generating reservation success information after a corresponding safe box is placed in the safe box according to the safe box use request, and feeding the reservation success information back to a safe box use request initiator;
the prompt module is used for acquiring operation information of a user on the safe box, comparing the operation information with a preset abnormal rule, and constructing an alarm prompt task triggered after a preset period according to a comparison result;
the analysis module is used for acquiring position information of the safe box according to the comparison result, acquiring video data and audio data of a corresponding area according to the position information, and analyzing the video data and the audio data through a risk identification algorithm to obtain a first risk coefficient; and terminating or maintaining the alarm prompt task according to the comparison result of the first risk coefficient and a preset first risk threshold.
11. The security monitoring system of claim 10, wherein the analysis module comprises a location base station for receiving the device identification of the safe broadcast by a location tag on the safe via an ultra-wideband pulsed signal, and calculating the location information using TDOA and AOA location algorithms.
12. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 9 when executing the computer program.
13. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 9 by a computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111158338.6A CN113920660B (en) | 2021-09-30 | 2021-09-30 | Safety monitoring method and system suitable for safety storage equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111158338.6A CN113920660B (en) | 2021-09-30 | 2021-09-30 | Safety monitoring method and system suitable for safety storage equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113920660A true CN113920660A (en) | 2022-01-11 |
| CN113920660B CN113920660B (en) | 2023-04-18 |
Family
ID=79237504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111158338.6A Active CN113920660B (en) | 2021-09-30 | 2021-09-30 | Safety monitoring method and system suitable for safety storage equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113920660B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114898490A (en) * | 2022-03-31 | 2022-08-12 | 珠海汇金科技股份有限公司 | Security protection method, system, device and storage medium for isolation door |
| CN115223284A (en) * | 2022-08-22 | 2022-10-21 | 广东维信智联科技有限公司 | Management and control method and platform capable of improving authentication accuracy |
Citations (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6191690B1 (en) * | 1999-07-15 | 2001-02-20 | Fujitsu Limited | Cash cassette burglary prevention system and cash cassette burglary prevention method |
| US20060227237A1 (en) * | 2005-03-31 | 2006-10-12 | International Business Machines Corporation | Video surveillance system and method with combined video and audio recognition |
| CA2520350A1 (en) * | 2005-09-21 | 2007-03-21 | International Business Machines Corporation | System and method for surveillance of suspects of automated banking machine fraud |
| CN101501564A (en) * | 2006-08-03 | 2009-08-05 | 国际商业机器公司 | Video surveillance system and method with combined video and audio recognition |
| US20100026808A1 (en) * | 2007-04-19 | 2010-02-04 | Hitachi Ltd. | Surveillance System for Terminals |
| JP2010150822A (en) * | 2008-12-25 | 2010-07-08 | Secom Co Ltd | Safe-deposit box system and program for management of the safe-deposit box |
| CN102518355A (en) * | 2011-10-28 | 2012-06-27 | 深圳市赛格导航科技股份有限公司 | Method and system for managing safe box |
| CN103233646A (en) * | 2013-04-26 | 2013-08-07 | 张路遥 | Safety box safety monitoring method and system |
| CN104794827A (en) * | 2014-01-17 | 2015-07-22 | 温科尼克斯多夫国际有限公司 | Method and apparatus for prevention of false alarms in monitoring systems |
| CA2909766A1 (en) * | 2014-11-21 | 2016-05-21 | Ingenico Group | Method for detecting a risk of replacement of a terminal, corresponding device, program and recording medium |
| CN106150271A (en) * | 2015-04-10 | 2016-11-23 | 北京智普信科技股份有限公司 | A kind of anti-theft device, system and safety cabinet |
| CN108073858A (en) * | 2016-11-14 | 2018-05-25 | 北京航天长峰科技工业集团有限公司 | Crowd massing monitoring identifying system based on depth camera |
| CN109031187A (en) * | 2018-05-24 | 2018-12-18 | 国网四川省电力公司宜宾供电公司 | A kind of wireless positioning monitoring system and method based on UWB technology |
| CN109823346A (en) * | 2019-01-23 | 2019-05-31 | 广州德晟人工智能科技有限公司 | Based on big data active safety early warning system and method |
| CN109882025A (en) * | 2019-04-16 | 2019-06-14 | 中国银行股份有限公司 | A kind of Bank Insurance cabinet device and bank custody control system |
| CN109903434A (en) * | 2019-02-01 | 2019-06-18 | 广州子祥信息科技有限公司 | A kind of safety cabinet background management system |
| CN109914969A (en) * | 2018-11-20 | 2019-06-21 | 深圳市合凡科技有限公司 | From anti-theft intelligent safety cabinet |
| TW201935404A (en) * | 2018-01-31 | 2019-09-01 | 合作金庫商業銀行股份有限公司 | Bank safe management system and client device for using the same |
| CN110219546A (en) * | 2019-06-30 | 2019-09-10 | 杭州市安保服务集团有限公司 | Intelligent specific store machine and its control method |
| CN110490126A (en) * | 2019-08-15 | 2019-11-22 | 成都睿晓科技有限公司 | A kind of safety cabinet security management and control system based on artificial intelligence |
| CN210042025U (en) * | 2019-03-18 | 2020-02-07 | 广东创尔樵安防科技有限公司 | Intelligent video monitoring system for safe |
| CN111083642A (en) * | 2019-12-10 | 2020-04-28 | 浩云科技股份有限公司 | Method for positioning personnel in treasury |
| CN111161054A (en) * | 2020-01-02 | 2020-05-15 | 中国银行股份有限公司 | Operation risk monitoring method and system |
| CN111709410A (en) * | 2020-08-20 | 2020-09-25 | 深兰人工智能芯片研究院（江苏）有限公司 | Behavior identification method for strong dynamic video |
| CN112686090A (en) * | 2020-11-04 | 2021-04-20 | 北方工业大学 | Intelligent monitoring system for abnormal behaviors in bus |
| CN113256851A (en) * | 2021-04-30 | 2021-08-13 | 深圳市展拓电子技术有限公司 | Verification method and verification system for security cabinet of bank system |
-
2021
- 2021-09-30 CN CN202111158338.6A patent/CN113920660B/en active Active
Patent Citations (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6191690B1 (en) * | 1999-07-15 | 2001-02-20 | Fujitsu Limited | Cash cassette burglary prevention system and cash cassette burglary prevention method |
| US20060227237A1 (en) * | 2005-03-31 | 2006-10-12 | International Business Machines Corporation | Video surveillance system and method with combined video and audio recognition |
| CA2520350A1 (en) * | 2005-09-21 | 2007-03-21 | International Business Machines Corporation | System and method for surveillance of suspects of automated banking machine fraud |
| CN101501564A (en) * | 2006-08-03 | 2009-08-05 | 国际商业机器公司 | Video surveillance system and method with combined video and audio recognition |
| US20100026808A1 (en) * | 2007-04-19 | 2010-02-04 | Hitachi Ltd. | Surveillance System for Terminals |
| JP2010150822A (en) * | 2008-12-25 | 2010-07-08 | Secom Co Ltd | Safe-deposit box system and program for management of the safe-deposit box |
| CN102518355A (en) * | 2011-10-28 | 2012-06-27 | 深圳市赛格导航科技股份有限公司 | Method and system for managing safe box |
| CN103233646A (en) * | 2013-04-26 | 2013-08-07 | 张路遥 | Safety box safety monitoring method and system |
| CN104794827A (en) * | 2014-01-17 | 2015-07-22 | 温科尼克斯多夫国际有限公司 | Method and apparatus for prevention of false alarms in monitoring systems |
| EP2897112A1 (en) * | 2014-01-17 | 2015-07-22 | Wincor Nixdorf International GmbH | Method and apparatus for the prevention of false alarms in monitoring systems |
| CA2909766A1 (en) * | 2014-11-21 | 2016-05-21 | Ingenico Group | Method for detecting a risk of replacement of a terminal, corresponding device, program and recording medium |
| CN106150271A (en) * | 2015-04-10 | 2016-11-23 | 北京智普信科技股份有限公司 | A kind of anti-theft device, system and safety cabinet |
| CN108073858A (en) * | 2016-11-14 | 2018-05-25 | 北京航天长峰科技工业集团有限公司 | Crowd massing monitoring identifying system based on depth camera |
| TW201935404A (en) * | 2018-01-31 | 2019-09-01 | 合作金庫商業銀行股份有限公司 | Bank safe management system and client device for using the same |
| CN109031187A (en) * | 2018-05-24 | 2018-12-18 | 国网四川省电力公司宜宾供电公司 | A kind of wireless positioning monitoring system and method based on UWB technology |
| CN109914969A (en) * | 2018-11-20 | 2019-06-21 | 深圳市合凡科技有限公司 | From anti-theft intelligent safety cabinet |
| CN109823346A (en) * | 2019-01-23 | 2019-05-31 | 广州德晟人工智能科技有限公司 | Based on big data active safety early warning system and method |
| CN109903434A (en) * | 2019-02-01 | 2019-06-18 | 广州子祥信息科技有限公司 | A kind of safety cabinet background management system |
| CN210042025U (en) * | 2019-03-18 | 2020-02-07 | 广东创尔樵安防科技有限公司 | Intelligent video monitoring system for safe |
| CN109882025A (en) * | 2019-04-16 | 2019-06-14 | 中国银行股份有限公司 | A kind of Bank Insurance cabinet device and bank custody control system |
| CN110219546A (en) * | 2019-06-30 | 2019-09-10 | 杭州市安保服务集团有限公司 | Intelligent specific store machine and its control method |
| CN110490126A (en) * | 2019-08-15 | 2019-11-22 | 成都睿晓科技有限公司 | A kind of safety cabinet security management and control system based on artificial intelligence |
| CN111083642A (en) * | 2019-12-10 | 2020-04-28 | 浩云科技股份有限公司 | Method for positioning personnel in treasury |
| CN111161054A (en) * | 2020-01-02 | 2020-05-15 | 中国银行股份有限公司 | Operation risk monitoring method and system |
| CN111709410A (en) * | 2020-08-20 | 2020-09-25 | 深兰人工智能芯片研究院（江苏）有限公司 | Behavior identification method for strong dynamic video |
| CN112686090A (en) * | 2020-11-04 | 2021-04-20 | 北方工业大学 | Intelligent monitoring system for abnormal behaviors in bus |
| CN113256851A (en) * | 2021-04-30 | 2021-08-13 | 深圳市展拓电子技术有限公司 | Verification method and verification system for security cabinet of bank system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114898490A (en) * | 2022-03-31 | 2022-08-12 | 珠海汇金科技股份有限公司 | Security protection method, system, device and storage medium for isolation door |
| CN115223284A (en) * | 2022-08-22 | 2022-10-21 | 广东维信智联科技有限公司 | Management and control method and platform capable of improving authentication accuracy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113920660B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7683929B2 (en) | System and method for video content analysis-based detection, surveillance and alarm management | |
| US7542588B2 (en) | System and method for assuring high resolution imaging of distinctive characteristics of a moving object | |
| US7504942B2 (en) | Local verification systems and methods for security monitoring | |
| JP5962916B2 (en) | Video surveillance system | |
| CN113920660B (en) | Safety monitoring method and system suitable for safety storage equipment | |
| EP1533768B1 (en) | Portable security system | |
| USRE43147E1 (en) | Abnormality detection and surveillance system | |
| CN113902074A (en) | File management method and system | |
| US20040240542A1 (en) | Method and apparatus for video frame sequence-based object tracking | |
| US20140098233A1 (en) | Access Control Reader with Audio Spatial Filtering | |
| WO2019090106A1 (en) | Methods and system for employee monitoring and business rule and quorum compliance monitoring | |
| CN109658554A (en) | A kind of intelligent residential district security system based on big data | |
| CN110490126B (en) | Safe deposit box safety control system based on artificial intelligence | |
| US20240161592A1 (en) | Proactive loss prevention system | |
| CN113781702B (en) | Cash box management method and system based on internet of things | |
| KR101936390B1 (en) | Method And Apparatus for Providing Tracking Service based on Closed Circuit Tele-Vision | |
| US20160378268A1 (en) | System and method of smart incident analysis in control system using floor maps | |
| JP6739119B6 (en) | Risk determination program and system | |
| CN216122688U (en) | Bank note storage device and security system based on Internet of things | |
| CN215830298U (en) | Safe box device and safety monitoring system | |
| CN115836516A (en) | Monitoring system | |
| WO2015173836A2 (en) | An interactive system that enhances video surveillance systems by enabling ease of speedy review of surveillance video and/or images and providing means to take several next steps, backs up surveillance video and/or images, as well as enables to create standardized intelligent incident reports and derive patterns | |
| CN216401018U (en) | File box device, file cabinet device and file management system | |
| KR102635351B1 (en) | Crime prevention system | |
| CN113838262B (en) | Near field communication method, device and system based on Internet of things |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |