CN113532462A - Monitoring system, method and device for cash truck - Google Patents
Monitoring system, method and device for cash truck Download PDFInfo
- Publication number
- CN113532462A CN113532462A CN202110806616.8A CN202110806616A CN113532462A CN 113532462 A CN113532462 A CN 113532462A CN 202110806616 A CN202110806616 A CN 202110806616A CN 113532462 A CN113532462 A CN 113532462A
- Authority
- CN
- China
- Prior art keywords
- route
- securicar
- sample
- training
- monitoring platform
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012806 monitoring device Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 65
- 230000006870 function Effects 0.000 claims description 24
- 238000010801 machine learning Methods 0.000 claims description 21
- 239000000463 material Substances 0.000 abstract description 6
- 230000001276 controlling effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000005641 tunneling Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a securicar monitoring system, a securicar monitoring method and a securicar monitoring device.A securicar terminal layer can acquire a positioning point of the securicar in real time, and a securicar monitoring platform can input the positioning point and a prescribed route of the securicar into a route deviation model, so that whether the securicar deviates the prescribed route is determined by a route deviation result output by the route deviation model. Based on the invention, whether the securicar deviates from the specified route can be accurately and effectively monitored, and the safety of material transportation is ensured.
Description
Technical Field
The invention relates to the technical field of software, in particular to a monitoring system, a monitoring method and a monitoring device for a securicar.
Background
In banking, each bank needs to make a cash escort plan according to the conditions of basic website layout, service scale, cash demand and the like, and the requirements of advanced allocation, position escort, cash box receiving and delivering and important blank voucher regulation are ensured to be met.
Securicars present a safety risk in the course of transporting important materials, which must be routed. Therefore, it is desirable to monitor the securicar in real time to quickly determine whether the securicar is off the specified route.
Disclosure of Invention
In view of the above, in order to solve the above problems, the present invention provides a monitoring system, method and device for a securicar, wherein the technical scheme is as follows:
one aspect of the present invention provides a securicar monitoring system, the system comprising: the system comprises a cash truck monitoring platform and a cash truck terminal layer arranged in the cash truck;
the terminal layer of the securicar is used for acquiring a positioning point of the securicar and uploading the positioning point to the securicar monitoring platform;
the cash truck monitoring platform is used for acquiring a specified route corresponding to the cash truck; inputting the positioning point and the specified route into a route deviation model, and acquiring a route deviation result output by the route deviation model, wherein the route deviation model is obtained by training in advance based on a machine learning technology.
Preferably, the method for obtaining the route deviation model by the securicar monitoring platform based on machine learning technology training in advance includes:
obtaining a plurality of sample specified routes for training, wherein one sample specified route corresponds to a group of sample positioning points for training, and the sample positioning points comprise negative sample positioning points which are deviated from the corresponding sample specified route and positive sample positioning points which are not deviated from the corresponding sample specified route; selecting a target sample specified route for the training from the plurality of sample specified routes; calling a base model trained last time, and inputting a negative sample positioning point and a positive sample positioning point corresponding to the target sample specified route into the base model to train network parameters of the base model; calculating a loss function value of the base model after the training; taking the basic model after the training as the route offset model under the condition that the loss function value meets the preset ending condition; and returning to the step of selecting the target sample specified route for the training from the plurality of sample specified routes when the loss function value does not meet the preset ending condition.
Preferably, the system further comprises: a client monitoring platform;
the cash truck monitoring platform is further used for issuing an alarm notification to the client monitoring platform under the condition that the route deviation result represents that the positioning point deviates from the specified route;
and the client monitoring platform is used for outputting the alarm notification.
Preferably, the client monitoring platform is further configured to:
generating a control instruction matched with the alarm notification, and uploading the control instruction to the securicar monitoring platform;
the securicar monitoring platform is also used for forwarding the control command to the securicar terminal layer;
and the terminal layer of the armor cash carrier is also used for responding to the control instruction.
Preferably, the mode of the securicar terminal layer responding to the control instruction includes:
the method comprises the steps of transferring video data currently shot by a monitor in the cash carrier, uploading the video data to a cash carrier monitoring platform, and forwarding the video data to a client monitoring platform for outputting through the cash carrier monitoring platform; and/or
Controlling an intelligent door lock of the cash truck to be closed; and/or
And controlling the brake device of the cash truck to start.
In another aspect, the present invention provides a method for monitoring an armored car, where the method is applied to an armored car monitoring platform, and the method includes:
receiving a positioning point of the securicar transmitted on a securicar terminal layer;
acquiring a specified route corresponding to the securicar;
inputting the positioning point and the specified route into a route deviation model, and acquiring a route deviation result output by the route deviation model, wherein the route deviation model is obtained by training in advance based on a machine learning technology.
Preferably, the method for obtaining the route deviation model based on machine learning technology training in advance includes:
obtaining a plurality of sample specified routes for training, wherein one sample specified route corresponds to a group of sample positioning points for training, and the sample positioning points comprise negative sample positioning points which are deviated from the corresponding sample specified route and positive sample positioning points which are not deviated from the corresponding sample specified route;
selecting a target sample specified route for the training from the plurality of sample specified routes;
calling a base model trained last time, and inputting a negative sample positioning point and a positive sample positioning point corresponding to the target sample specified route into the base model to train network parameters of the base model;
calculating a loss function value of the base model after the training;
taking the basic model after the training as the route offset model under the condition that the loss function value meets the preset ending condition;
and returning to the step of selecting the target sample specified route for the training from the plurality of sample specified routes when the loss function value does not meet the preset ending condition.
Preferably, the method further comprises:
and issuing an alarm notification to a client monitoring platform under the condition that the route deviation result represents that the positioning point deviates from the specified route, so that the client monitoring platform outputs the alarm notification.
Preferably, the method further comprises:
receiving a control instruction which is uploaded by the client monitoring platform and matched with the alarm notification;
and forwarding the control instruction to the terminal layer of the securicar so that the terminal layer of the securicar responds to the control instruction.
In another aspect, the present invention provides a monitoring apparatus for an armored car, the apparatus comprising:
the receiving module is used for receiving positioning points of the cash trucks, which are uploaded on the cash truck terminal layer;
the monitoring module is used for acquiring a specified route corresponding to the securicar; inputting the positioning point and the specified route into a route deviation model, and acquiring a route deviation result output by the route deviation model, wherein the route deviation model is obtained by training in advance based on a machine learning technology.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a securicar monitoring system, a securicar monitoring method and a securicar monitoring device.A securicar terminal layer can acquire a positioning point of the securicar in real time, and a securicar monitoring platform can input the positioning point and a prescribed route of the securicar into a route deviation model, so that whether the securicar deviates the prescribed route is determined by a route deviation result output by the route deviation model. Based on the invention, whether the securicar deviates from the specified route can be accurately and effectively monitored, and the safety of material transportation is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a system architecture diagram of an armored car monitoring system according to an embodiment of the present invention;
fig. 2 is another system architecture diagram of the armored car monitoring system according to the embodiment of the present invention;
fig. 3 is a flowchart of a method of monitoring an armored car according to an embodiment of the present invention;
fig. 4 is a flowchart of another method of monitoring an armored car according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of the monitoring device for the armored car according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
An embodiment of the present invention provides a monitoring system for an armored car, a system architecture diagram of which is shown in fig. 1, including: the monitoring platform 10 of the armor cash carrier and the armor cash carrier terminal layer 20 arranged in the armor cash carrier.
The terminal layer 20 of the securicar is used for acquiring a positioning point of the securicar and uploading the positioning point to the securicar monitoring platform 10;
the monitoring platform 10 of the securicar is used for obtaining a corresponding specified route of the securicar; and inputting the positioning point and the specified route into a route deviation model, and acquiring a route deviation result output by the route deviation model, wherein the route deviation model is obtained by training in advance based on a machine learning technology.
In the embodiment of the present invention, the terminal layer 20 of the securicar may be an existing processor/controller (such as a complete vehicle controller) in the securicar, or may be a newly provided processor/controller for the securicar, which is not limited in the embodiment of the present invention. In addition, the monitoring platform 10 of the armored car may be implemented by a server, and the server may be one server or a server cluster composed of a plurality of servers.
Generally, the armored car is provided with a Beidou satellite positioning system, which can position the position of the armored car in real time, namely a positioning point, and the positioning point is represented by two parameters of longitude and latitude on the earth. From this, through big dipper satellite positioning system, the armoured van terminal layer 20 can obtain the setpoint of armoured van in real time to upload the setpoint to armoured van monitoring platform 10 in real time based on internet of things.
For the securicar monitoring platform 10, after receiving the positioning point of the securicar uploaded by the securicar terminal layer 20, first, a specified route corresponding to the securicar is called from the background database, wherein the specified route is composed of a plurality of continuous coordinate points, and one coordinate point is represented by a group of longitude and latitude; inputting the positioning point and the specified route into a route deviation model, and predicting whether the positioning point deviates from the specified route by the route deviation model; finally, it is determined whether the securicar is currently deviated from the prescribed route based on a route deviation result predicted to be output by the route deviation model.
Therefore, for the real-time monitoring of the securicar, on one hand, the real-time position of the securicar is obtained by using the internet of things technology, and on the other hand, whether the securicar deviates from the specified route or not is predicted in real time by using the machine learning technology.
It should be noted that the route deviation model is obtained by training the basic model by using the existing machine learning technology, and the prediction result of the route deviation model for the positioning point serving as the sample approaches to the labeling result.
In the specific implementation process, the manner that the securicar monitoring platform 10 obtains the route deviation model based on the machine learning technology training in advance includes:
acquiring a plurality of sample specified routes for training, wherein one sample specified route corresponds to a group of sample positioning points for training, and the sample positioning points comprise negative sample positioning points which are deviated from the corresponding sample specified route and positive sample positioning points which are not deviated from the corresponding sample specified route; selecting a target sample specified route for the training from a plurality of sample specified routes; calling a base model trained last time, and inputting a negative sample positioning point and a positive sample positioning point corresponding to a target sample specified route into the base model to train network parameters of the base model; calculating a loss function value of the trained basic model; taking the basic model after the training as a route offset model under the condition that the loss function value meets the preset end condition; and returning to the step of selecting the target sample specified route for the training from the plurality of sample specified routes when the loss function value does not meet the preset ending condition.
In the embodiment of the invention, the route deviation model is obtained by training by using a machine learning technology, and the machine learning technology can be an STM (scanning tunneling machine) or an attention technology. The sample planned route, i.e. the planned route for training as a sample, can be obtained from the historical transport route of the securicar and can be redrawn by the relevant personnel. For the preparation of the positive sample (i.e. positive sample positioning point) and the negative sample (i.e. negative sample positioning point) of the sample specified route, the positive sample only needs to pick the positioning point on the sample specified route (or within a certain range of the sample specified route), and the negative sample only needs to pick the positioning point which is not on the sample specified route (or outside a certain range of the sample specified route), and the APIs of the general map all provide the relevant interfaces.
In the iterative training process, each sample specified route is traversed, and the sample specified route (namely, the target sample specified route) used for the current training is selected from the unselected sample specified routes. And then, inputting the positive sample and the negative sample corresponding to the target sample specified route into the basic model obtained by the last training, so as to adjust the network parameters of each layer of the basic model. Finally, if the loss function value of the basic model after the training meets the corresponding threshold value, stopping the training to obtain a route offset model; and if the loss function value of the basic model after the training does not meet the corresponding threshold value, continuing the next training.
It should be noted that, in the embodiment of the present invention, the base model and the loss function of the base model are not limited, and may be selected in combination with an application scenario.
Therefore, the embodiment of the invention can carry out real-time and whole-course monitoring on the driving route of the securicar. In other embodiments, in order to ensure that the securicar can be notified to the security department in time when deviating from the route, so as to achieve the effect of real-time monitoring and early warning of the system and reduce the labor cost, the embodiment of the present invention is further provided with a client monitoring platform 30 on the basis of the securicar monitoring system shown in fig. 1, and the system architecture diagram is shown in fig. 2:
the securicar monitoring platform 10 is further configured to issue an alarm notification to the client monitoring platform 30 when the route deviation result indicates that the positioning point deviates to a specified route;
and the client monitoring platform 30 is used for outputting alarm notification.
In the embodiment of the present invention, once the securicar monitoring platform 10 determines that the positioning point of the securicar deviates from the specified route, it can notify the client monitoring platform 30 corresponding to the securicar in the form of an alarm short message or an alarm mail based on the internet of things technology. Of course, if the location of the securicar is not off course, the relevant data is discarded. It should be noted that one securicar may correspond to a plurality of client monitoring platforms 30, and one client monitoring platform 30 may also correspond to a plurality of securicars, which is not limited in the embodiment of the present invention.
Accordingly, the client monitoring platform 30 can log in the relevant system to check the status of the securicar when receiving the alarm short message or the alarm mail sent by the securicar monitoring platform 10.
On the basis, the security department can send some instructions to the securicar monitoring platform 10 when needed, and finally the securicar can be remotely monitored/controlled. Accordingly, the client monitor platform 30 is further configured to:
generating a control instruction matched with the alarm notification, and uploading the control instruction to the securicar monitoring platform 10;
the securicar monitoring platform 10 is further configured to forward the control instruction to the securicar terminal layer 20;
the banknote transport vehicle terminal layer 20 is also used for responding to control instructions.
In the embodiment of the invention, different control instructions can be set for different alarm notifications, specifically, when the route deviation result is output by the route deviation model, on one hand, whether the positioning point deviates from the specified route or not is given, and on the other hand, the deviation degree when the positioning point deviates from the specified route is also given. At this time, the securicar monitoring platform 10 may output different levels of alarm notifications according to the deviation degree, for example, when the deviation degree is higher than the corresponding threshold value, an alarm short message is issued to the client monitoring platform 30, and when the deviation degree is lower than the corresponding threshold value, an alarm mail is issued to the client monitoring platform 30.
Accordingly, the client monitoring platform 30 may generate different control instructions when receiving alarm notifications of different levels, for example, a control instruction for instructing braking when receiving an alarm short message, and a control instruction for instructing closing the door lock when receiving an alarm mail. Certainly, after the securicar monitoring platform 10 receives the control instruction from the client monitoring platform 30, the control instruction is forwarded to the securicar terminal layer 20, and the securicar terminal layer 20 responds to the control instruction to control the securicar to complete the operation of braking or closing the door lock.
Specifically, the manner of the securicar terminal layer 20 responding to the control command includes:
the method comprises the steps of transferring video data currently shot by a monitor in the securicar, uploading the video data to the securicar monitoring platform 10, and forwarding the video data to a client monitoring platform 30 through the securicar monitoring platform 10 for output; and/or
Controlling an intelligent door lock of the cash truck to be closed; and/or
And controlling the brake device of the cash truck to start.
In the embodiment of the invention, the control instruction comprises three types of control instructions, namely a control instruction for indicating to start a video, a control instruction for indicating to close a door lock and a control instruction for indicating to brake. It is understood that several remote control modes are listed in the embodiment of the present invention, and other remote control modes not listed are also within the protection scope of the embodiment of the present invention.
For the control instruction for instructing to start the video, when the securicar terminal layer 20 responds to the control instruction, the monitor (i.e., the video monitor in the figure) in the securicar may be started to shoot the video data and then call it, or the video data currently shot by the started monitor may be called, and then the called video data may be actively uploaded to the securicar monitoring platform 10 based on the internet of things technology. The monitoring platform 10 of the armored car pushes the video data to the client monitoring platform 30 in real time for displaying and playing. Therefore, real-time monitoring videos can be uploaded when needed, a real-time uploading channel is closed when remote monitoring is not needed, network resources are saved, and the system deviation route early warning mechanism is combined to release labor cost.
For the control instruction for instructing the closing of the door lock, when the securicar terminal layer 20 responds to the control instruction, the intelligent door lock is closed to lock the door of the securicar. For the control instruction for indicating braking, when the terminal layer 20 of the securicar responds to the control instruction, the braking device is started to control the securicar to stop at a reduced speed.
Therefore, the invention utilizes the technology of the Internet of things, can realize the remote control of the securicar such as closing the door, emergency braking or flameout under emergency, and the like, and effectively combines with a route deviation alarm mechanism and a remote real-time video monitoring mechanism, finally realizes the effect of timely controlling the securicar when the securicar has risks, and reduces the risks of transporting materials.
In conclusion, the invention utilizes the mode of combining the machine learning technology and the Internet of things technology to realize the real-time monitoring of the securicar, which is a vehicle for transporting important bank materials, and can inform a security department in a way of alarm short messages or alarm mails in real time when the route deviates. When receiving the alarm, the security department can utilize the internet of things technology to remotely monitor and survey the field condition in real time, guide subsequent commands and issue instructions for remotely controlling the cash truck when necessary, thereby effectively reducing the cost of manual monitoring, reducing the network cost and effectively ensuring the safety of transported materials.
Based on the securicar monitoring system provided by the above embodiment, the embodiment of the present invention correspondingly provides a securicar monitoring method, which is applied to the securicar monitoring platform, and the flow chart of the method is shown in fig. 3, and includes the following steps:
and S10, receiving the positioning point of the securicar transmitted on the securicar terminal layer.
And S20, acquiring the corresponding regulated route of the securicar.
And S30, inputting the positioning point and the specified route into a route deviation model, and acquiring a route deviation result output by the route deviation model, wherein the route deviation model is obtained by training in advance based on a machine learning technology.
Optionally, the method for obtaining the route deviation model based on the machine learning technique training in advance includes the following steps, and a flowchart of the method is shown in fig. 4:
s301, a plurality of sample specified routes for training are obtained, wherein one sample specified route corresponds to a group of sample positioning points for training, and the sample positioning points comprise negative sample positioning points which are deviated from the corresponding sample specified route and positive sample positioning points which are not deviated from the corresponding sample specified route.
S302 selects a target sample prescribed route for the current training from the plurality of sample prescribed routes.
And S303, calling the base model trained last time, and inputting the negative sample positioning point and the positive sample positioning point corresponding to the target sample specified route into the base model to train the network parameters of the base model.
S304, calculating the loss function value of the basic model after the training.
And S305, taking the basic model after the training as a route deviation model under the condition that the loss function value meets the preset ending condition.
And S306, when the loss function value does not meet the preset ending condition, returning to the step of selecting the target sample specified route for the training from the plurality of sample specified routes.
Optionally, the method further includes the following steps:
and under the condition that the route deviation result represents that the positioning point deviates to specify the route, issuing an alarm notification to the client monitoring platform so that the client monitoring platform outputs the alarm notification.
Optionally, the method further includes the following steps:
receiving a control instruction which is uploaded by a client monitoring platform and matched with the alarm notification;
and forwarding the control instruction to the terminal layer of the securicar so that the terminal layer of the securicar responds to the control instruction.
It should be noted that, for detailed description of each step in the embodiment of the present invention, reference may be made to the corresponding disclosure part of the securicar monitoring system, and details are not described herein again.
Based on the foregoing embodiment, a method for monitoring an armored car is provided, and an embodiment of the present invention further provides an armored car monitoring apparatus, where a schematic structural diagram of the apparatus is shown in fig. 5, where the apparatus includes:
the receiving module 10 is used for receiving positioning points of the securicar, which are uploaded on a securicar terminal layer;
the monitoring module 20 is used for acquiring a specified route corresponding to the securicar; and inputting the positioning point and the specified route into a route deviation model, and acquiring a route deviation result output by the route deviation model, wherein the route deviation model is obtained by training in advance based on a machine learning technology.
Optionally, the way that the monitoring module 20 obtains the route deviation model based on the machine learning technique training in advance includes:
acquiring a plurality of sample specified routes for training, wherein one sample specified route corresponds to a group of sample positioning points for training, and the sample positioning points comprise negative sample positioning points which are deviated from the corresponding sample specified route and positive sample positioning points which are not deviated from the corresponding sample specified route; selecting a target sample specified route for the training from a plurality of sample specified routes; calling a base model trained last time, and inputting a negative sample positioning point and a positive sample positioning point corresponding to a target sample specified route into the base model to train network parameters of the base model; calculating a loss function value of the trained basic model; taking the basic model after the training as a route offset model under the condition that the loss function value meets the preset end condition; and returning to the step of selecting the target sample specified route for the training from the plurality of sample specified routes when the loss function value does not meet the preset ending condition.
Optionally, the monitoring module 20 is further configured to:
and under the condition that the route deviation result represents that the positioning point deviates to specify the route, issuing an alarm notification to the client monitoring platform so that the client monitoring platform outputs the alarm notification.
Optionally, the receiving module 10 is further configured to:
receiving a control instruction which is uploaded by a client monitoring platform and matched with the alarm notification; and forwarding the control instruction to the terminal layer of the securicar so that the terminal layer of the securicar responds to the control instruction.
The securicar monitoring system, method and device provided by the present invention are introduced in detail, and the principle and the implementation mode of the present invention are explained by applying specific examples, and the description of the above examples is only used for helping to understand the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include or include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A securicar monitoring system, the system comprising: the system comprises a cash truck monitoring platform and a cash truck terminal layer arranged in the cash truck;
the terminal layer of the securicar is used for acquiring a positioning point of the securicar and uploading the positioning point to the securicar monitoring platform;
the cash truck monitoring platform is used for acquiring a specified route corresponding to the cash truck; inputting the positioning point and the specified route into a route deviation model, and acquiring a route deviation result output by the route deviation model, wherein the route deviation model is obtained by training in advance based on a machine learning technology.
2. The system of claim 1, wherein the manner in which the securicar monitoring platform previously trained the route deviation model based on machine learning techniques comprises:
obtaining a plurality of sample specified routes for training, wherein one sample specified route corresponds to a group of sample positioning points for training, and the sample positioning points comprise negative sample positioning points which are deviated from the corresponding sample specified route and positive sample positioning points which are not deviated from the corresponding sample specified route; selecting a target sample specified route for the training from the plurality of sample specified routes; calling a base model trained last time, and inputting a negative sample positioning point and a positive sample positioning point corresponding to the target sample specified route into the base model to train network parameters of the base model; calculating a loss function value of the base model after the training; taking the basic model after the training as the route offset model under the condition that the loss function value meets the preset ending condition; and returning to the step of selecting the target sample specified route for the training from the plurality of sample specified routes when the loss function value does not meet the preset ending condition.
3. The system of claim 1, further comprising: a client monitoring platform;
the cash truck monitoring platform is further used for issuing an alarm notification to the client monitoring platform under the condition that the route deviation result represents that the positioning point deviates from the specified route;
and the client monitoring platform is used for outputting the alarm notification.
4. The system of claim 3, wherein the client monitoring platform is further configured to:
generating a control instruction matched with the alarm notification, and uploading the control instruction to the securicar monitoring platform;
the securicar monitoring platform is also used for forwarding the control command to the securicar terminal layer;
and the terminal layer of the armor cash carrier is also used for responding to the control instruction.
5. The system of claim 4, wherein the manner in which the securicar terminal level responds to the control commands comprises:
the method comprises the steps of transferring video data currently shot by a monitor in the cash carrier, uploading the video data to a cash carrier monitoring platform, and forwarding the video data to a client monitoring platform for outputting through the cash carrier monitoring platform; and/or
Controlling an intelligent door lock of the cash truck to be closed; and/or
And controlling the brake device of the cash truck to start.
6. A method for monitoring a securicar, the method being applied to a securicar monitoring platform, the method comprising:
receiving a positioning point of the securicar transmitted on a securicar terminal layer;
acquiring a specified route corresponding to the securicar;
inputting the positioning point and the specified route into a route deviation model, and acquiring a route deviation result output by the route deviation model, wherein the route deviation model is obtained by training in advance based on a machine learning technology.
7. The method of claim 6, wherein the way to obtain the route deviation model based on machine learning technique training in advance comprises:
obtaining a plurality of sample specified routes for training, wherein one sample specified route corresponds to a group of sample positioning points for training, and the sample positioning points comprise negative sample positioning points which are deviated from the corresponding sample specified route and positive sample positioning points which are not deviated from the corresponding sample specified route;
selecting a target sample specified route for the training from the plurality of sample specified routes;
calling a base model trained last time, and inputting a negative sample positioning point and a positive sample positioning point corresponding to the target sample specified route into the base model to train network parameters of the base model;
calculating a loss function value of the base model after the training;
taking the basic model after the training as the route offset model under the condition that the loss function value meets the preset ending condition;
and returning to the step of selecting the target sample specified route for the training from the plurality of sample specified routes when the loss function value does not meet the preset ending condition.
8. The method of claim 6, further comprising:
and issuing an alarm notification to a client monitoring platform under the condition that the route deviation result represents that the positioning point deviates from the specified route, so that the client monitoring platform outputs the alarm notification.
9. The method of claim 8, further comprising:
receiving a control instruction which is uploaded by the client monitoring platform and matched with the alarm notification;
and forwarding the control instruction to the terminal layer of the securicar so that the terminal layer of the securicar responds to the control instruction.
10. A securicar monitoring device, the device comprising:
the receiving module is used for receiving positioning points of the cash trucks, which are uploaded on the cash truck terminal layer;
the monitoring module is used for acquiring a specified route corresponding to the securicar; inputting the positioning point and the specified route into a route deviation model, and acquiring a route deviation result output by the route deviation model, wherein the route deviation model is obtained by training in advance based on a machine learning technology.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110806616.8A CN113532462A (en) | 2021-07-16 | 2021-07-16 | Monitoring system, method and device for cash truck |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110806616.8A CN113532462A (en) | 2021-07-16 | 2021-07-16 | Monitoring system, method and device for cash truck |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113532462A true CN113532462A (en) | 2021-10-22 |
Family
ID=78099767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110806616.8A Pending CN113532462A (en) | 2021-07-16 | 2021-07-16 | Monitoring system, method and device for cash truck |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113532462A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101786455A (en) * | 2009-11-19 | 2010-07-28 | 四维-约翰逊实业股份有限公司 | Driving route control system of securicar and method thereof |
| CN102231822A (en) * | 2011-06-24 | 2011-11-02 | 广州亿程交通信息有限公司 | Monitoring system |
| CN107816998A (en) * | 2016-09-13 | 2018-03-20 | 腾讯科技（深圳）有限公司 | Information processing method and device |
| CN110749319A (en) * | 2018-12-19 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Route deviation detection method and device and electronic equipment |
| CN111814109A (en) * | 2020-04-08 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Vehicle track deviation detection method and device, storage medium and electronic equipment |
| CN112415999A (en) * | 2020-10-29 | 2021-02-26 | 浙江吉利控股集团有限公司 | Processing method, device and equipment for automatic driving path point and storage medium |
-
2021
- 2021-07-16 CN CN202110806616.8A patent/CN113532462A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101786455A (en) * | 2009-11-19 | 2010-07-28 | 四维-约翰逊实业股份有限公司 | Driving route control system of securicar and method thereof |
| CN102231822A (en) * | 2011-06-24 | 2011-11-02 | 广州亿程交通信息有限公司 | Monitoring system |
| CN107816998A (en) * | 2016-09-13 | 2018-03-20 | 腾讯科技（深圳）有限公司 | Information processing method and device |
| CN110749319A (en) * | 2018-12-19 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Route deviation detection method and device and electronic equipment |
| CN111814109A (en) * | 2020-04-08 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Vehicle track deviation detection method and device, storage medium and electronic equipment |
| CN112415999A (en) * | 2020-10-29 | 2021-02-26 | 浙江吉利控股集团有限公司 | Processing method, device and equipment for automatic driving path point and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 杨露菁: "智能图像处理及应用", 北京：中国铁道出版社, pages: 34 - 37 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10759455B2 (en) | System, method, and computer software code for distributing and managing data for use by a plurality of vehicle subsystems | |
| US10775783B2 (en) | System for asymmetric just-in-time human intervention in automated vehicle fleets | |
| CN107944797A (en) | The monitoring method of transport task, apparatus and system | |
| US20210019699A1 (en) | Unmanned aerial vehicle (uav) delivery with drop beacon | |
| CN108171410A (en) | A kind of railway freight wisdom station total management system and its application | |
| US20190217131A1 (en) | Method and Arrangement for Identifying Obstacles on Escape Routes | |
| JP2019537159A5 (en) | ||
| US10807712B2 (en) | Systems and methods for transferring control of an unmanned aerial vehicle | |
| BR112019010721A2 (en) | autonomous vehicle monitoring using generated interfaces | |
| JP2020160708A (en) | Information processing device, information processing method and information processing program | |
| US20230182778A1 (en) | Identifying roadway concerns and taking preemptive actions | |
| US20210304617A1 (en) | Transport to transport communication initiated by user gestures | |
| CN110807615A (en) | Transportation management system and method thereof | |
| US11797949B2 (en) | Establishing connections in transports | |
| TWI707283B (en) | Fleet management method, fleet management device, fleet management system and electronic device and storage medium thereof | |
| CN114115355B (en) | Unmanned aerial vehicle set task planning method, device and system | |
| US11643114B2 (en) | Information processing device, information processing method and information processing program | |
| CN110992515A (en) | Method and system for predicting remaining useful life of a component using an accelerated time to failure model | |
| CN109087409A (en) | A kind of data processing, information acquisition method, electronic equipment and storage medium | |
| WO2020022165A1 (en) | Information processing device, information processing method, and program | |
| KR20200112610A (en) | Method and device of providing construction schedule of ocean construction | |
| CN113532462A (en) | Monitoring system, method and device for cash truck | |
| US20210304595A1 (en) | Traffic manager transports | |
| JP2023516051A (en) | Coordinating vehicle trips in an on-demand environment | |
| JP2021163360A (en) | Automatic driving vehicle and control method thereof |
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 |