CN114475620B - Driver verification method and system for money box escort system - Google Patents

Driver verification method and system for money box escort system Download PDF

Info

Publication number
CN114475620B
CN114475620B CN202210092862.6A CN202210092862A CN114475620B CN 114475620 B CN114475620 B CN 114475620B CN 202210092862 A CN202210092862 A CN 202210092862A CN 114475620 B CN114475620 B CN 114475620B
Authority
CN
China
Prior art keywords
driver
current
information
image
gear
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.)
Active
Application number
CN202210092862.6A
Other languages
Chinese (zh)
Other versions
CN114475620A (en
Inventor
陈兵
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Financial Data Systems Ltd By Share Ltd
Original Assignee
Nanjing Financial Data Systems Ltd By Share Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing Financial Data Systems Ltd By Share Ltd filed Critical Nanjing Financial Data Systems Ltd By Share Ltd
Priority to CN202210092862.6A priority Critical patent/CN114475620B/en
Publication of CN114475620A publication Critical patent/CN114475620A/en
Application granted granted Critical
Publication of CN114475620B publication Critical patent/CN114475620B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
    • H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B60W2040/0809—Driver authorisation; Driver identity check

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Mathematical Physics (AREA)
  • Automation & Control Theory (AREA)
  • Biomedical Technology (AREA)
  • Computer Hardware Design (AREA)
  • Computer Security & Cryptography (AREA)
  • General Engineering & Computer Science (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application relates to a driver verification method and a driver verification system for a money box escort system, which sequentially acquire current real communication terminal information in real time, judge whether the current real communication terminal is a preset escort in-car communication terminal, and send a shooting acquisition instruction if the current real communication terminal is judged to be the escort in-car communication terminal; extracting characteristic points, fitting the characteristic points, respectively generating current state curve information of a driver, judging whether the current driver is an authenticated driver according to the current state curve information of each driver, judging whether the driver has preset warning expression information according to the current state curve information of the driver if the current state curve information of each driver is the authenticated driver, generating information warning if the driver has preset warning expression information, and generating a normal prompt of the current environment if the driver has preset warning expression information. The invention realizes high security of authentication.

Description

Driver verification method and system for money box escort system
Technical Field
The application relates to the technical field of computers, in particular to a driver verification method and system for a money box escort system.
Background
At present, a personnel verification mode is mainly performed in a fingerprint or face mode, and a driver cannot get off the vehicle when the website or the treasury executes a handover task, so that the identification of the driver must meet the requirement of mobile verification, and the communication of information in a mobile environment is critical. When the fingerprint is verified, if the fingerprint machine is installed on the wall of an external vehicle channel, the driver can only stretch the arm out of a short distance through a small opening below the window because the window of the securicar cannot be opened, and the operation difficulty of verifying the fingerprint is very high.
In addition, other technical schemes for fingerprint verification are also available in the market, such as the invention patent with the application number of CN201710363461.9, and a driver identity authentication system and an authentication method based on fingerprint identification are disclosed, wherein the system comprises a vehicle-mounted driving terminal and a driver management background, the vehicle-mounted driving terminal comprises a fingerprint acquisition module and a terminal processing module, and the driver management background comprises a background processing module and a driver information base; the fingerprint acquisition module is connected with the terminal processing module, the terminal processing module is connected with the background processing module through network communication, and the background processing module is connected with the driver information base. The invention provides a driver identity authentication system and an authentication method based on fingerprint identification, which are used for collecting an authentication fingerprint image of a driver and comparing the collected image with a standard fingerprint image provided by a driver management background, so that the driver identity authentication is realized, the comprehensive management of a carrier is facilitated, the identity authentication of the driver before the driving of a vehicle is facilitated, and the working efficiency of the driver is improved.
In another patent application number CN201810311437.5, a method, device, system and server for authenticating driver identity are disclosed. The driver identity authentication method provided by the application is applied to a server, and comprises the following steps: receiving identity authentication information of a current driver sent by a vehicle-mounted terminal; matching the face information in the identity authentication information with the stored face information of the legal driver; and if the matching is successful, sending a vehicle starting command to the vehicle-mounted terminal so as to instruct the vehicle-mounted terminal to start the vehicle when the vehicle starting command is received. The driver identity authentication method, the device, the system and the server can not only avoid an illegal driver from driving the vehicle, but also reduce the cost of driver identity authentication.
Although the technical scheme realizes the related authentication, the method still has great hidden danger and problems when applied to the driver authentication of the money box escort system.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a driver verification method and system for a money box escort system that can improve authentication security.
The technical scheme of the invention is as follows:
A driver verification method for a money box escort system, the method comprising:
during escort, sending a shooting acquisition instruction to the communication terminal in the escort vehicle based on the network point end information communication terminal, wherein the shooting acquisition instruction is used for controlling a vehicle-mounted lens to carry out shooting acquisition and obtaining a plurality of current state images of drivers, and each current state image of the driver is used for being sent to the network point end information communication terminal; extracting characteristic points of the current state images of the drivers sent to the network point information communication terminal, fitting the characteristic points of the current state images of the drivers, and generating current state curve information of the drivers; judging whether the current driver is an authenticated driver according to the current state curve information of each driver, if yes, judging whether the driver has preset warning expression information according to the current state curve information of the driver, and if yes, generating information warning.
Specifically, a sound collector is also preset in the escort vehicle, and the sound collector is in communication connection with the communication terminal in the escort vehicle;
judging whether the current driver is an authenticated driver according to the current state curve information of each driver, judging whether the driver has preset warning expression information according to the current state curve information of the driver if the current state curve information of the driver is judged to be positive, generating information warning if the current state curve information of the driver is judged to be positive, wherein the information warning is used for providing staff at a receiving website, generating a normal prompt of the current environment if the current state curve information of the driver is judged to be negative, and further comprising:
Acquiring current actual position information of the escort vehicle according to the communication terminal in the escort vehicle, and judging whether the escort vehicle reaches a preset deposit receiving escort point according to the current actual position information; if the escort vehicle is judged to reach a preset deposit receiving escort point, generating a sound collection starting instruction, and sending the sound collection starting instruction to the communication terminal in the escort vehicle based on the network point information communication terminal, wherein the sound collection starting instruction is used for controlling the sound collector to collect sound information of a driver; acquiring a sound collection information set in a preset time period collected by the sound collector; acquiring the current driver speech speed and current driver sound characteristic information according to the sound acquisition information set; judging whether the emotion of the driver is normal or not according to the current driver speech speed and the current driver voice characteristic information; if the emotion of the driver is judged to be normal according to the current driver speech speed and the current driver sound characteristic information, a current acceptance opening prompt is generated, and the current acceptance opening prompt is used for reminding a worker at a acceptance site of receiving money to carry out the cash receiving work.
Specifically, judging whether the emotion of the driver is normal or not according to the current driver speech speed and the current driver voice characteristic information; the method specifically comprises the following steps:
comparing the current driver speech speed with a preset normal state speech speed range according to the current driver speech speed, and judging whether the current driver speech speed is in the normal state speech speed range; if the current driver speech speed is not in the normal state speech speed range, judging that the emotion of the driver is abnormal, and generating a current receiving money stop prompt; if the current driver speech speed is in the normal state speech speed range, judging whether the current driver sound characteristic information is matched with preset standard driver sound characteristic information according to the current driver sound characteristic information; if the current driver voice characteristic information is judged not to be matched with the preset standard driver voice characteristic information, and the emotion abnormality of the driver is judged, generating a current receiving money stop prompt; and if the current driver voice characteristic information is matched with the preset standard driver voice characteristic information, judging that the emotion of the driver is normal.
Specifically, feature point extraction is performed on the current state images of the drivers sent to the network point information communication terminal, fitting is performed on each feature point of each current state image of the driver, and current state curve information of the drivers is generated, wherein one current state curve information of the drivers corresponds to one current state image of the drivers, and the method specifically comprises the following steps:
the resolution extraction is carried out on the current state images of the drivers sent to the network point information communication terminal, and the current actual resolution of each current state image of the drivers is respectively obtained; classifying the corresponding current state images of the drivers according to the current actual resolutions, and generating a first-gear driver image set and a second-gear driver image set, wherein the resolution of the images in the first-gear driver image set is higher than that of the images in the second-gear driver image set; extracting characteristic points of images in the first-gear driver image set respectively, and acquiring first-gear image characteristic point data sets respectively, wherein the first-gear image characteristic point data sets comprise a plurality of first-gear image characteristic point units, and one first-gear image characteristic point unit corresponds to one image in the first-gear driver image set; extracting characteristic points of images in the second-gear driver image set respectively, and acquiring second-gear image characteristic point data sets respectively, wherein each second-gear image characteristic point data set comprises a plurality of second-gear image characteristic point units, and one second-gear image characteristic point unit corresponds to one image in the second-gear driver image set; comparing the first-grade image characteristic point data set with the second-grade image characteristic point data set, and generating a current difference characteristic point; screening the current difference characteristic points belonging to the second-gear image characteristic point unit, and marking the current difference characteristic points as the difference points to be supplemented currently; performing differential point supplementation on the first-grade image characteristic point data set by the current differential point to be supplemented, and generating a complete image characteristic point data set; and fitting characteristic points based on the complete image characteristic point data set and respectively generating current state curve information of the driver.
Specifically, whether the current driver is an authenticated driver is judged according to the current state curve information of each driver, if yes, whether the driver has preset warning expression information is judged according to the current state curve information of the driver, if yes, information warning is generated, the information warning is used for providing staff at a receiving website, if no, a normal prompt of the current environment is generated, and then the method further comprises the following steps:
acquiring current acceptance type use feeling feedback information made by a driver and staff at a receiving type website; judging whether the current preset monitoring area is proper or not according to the current accepted money using experience feedback information; if the current preset monitoring area is judged to be proper according to the current acceptance money using experience feedback information, a current area constant instruction is generated; if the current preset monitoring area is judged to be inappropriate according to the current acceptance money using experience feedback information, generating a current area adjusting instruction, adjusting the current preset monitoring area based on the current area adjusting instruction, and generating an updated preset monitoring area after adjustment.
Specifically, a driver verification system for a money box escort system, the system comprising:
the communication terminal module is used for acquiring current real communication terminal information connected with a network point end information communication terminal preset at a receiving network point in a current preset monitoring area in real time, and judging whether the current real communication terminal is a preset communication terminal in a escort vehicle, wherein the network point end information communication terminal is preset at the receiving network point, the communication terminal in the escort vehicle is preset in the escort vehicle, and a vehicle-mounted lens is arranged in the escort vehicle;
the camera shooting acquisition module is used for sending a camera shooting acquisition instruction to the communication terminal in the escort vehicle based on the network point end information communication terminal if the current real communication terminal is judged to be the communication terminal in the escort vehicle, wherein the camera shooting acquisition instruction is used for controlling the vehicle-mounted lens to carry out multi-angle camera shooting acquisition on a driver in the escort vehicle and obtaining a plurality of current state images of the driver, and each current state image of the driver is used for being sent to the network point end information communication terminal, wherein one angle corresponds to one current state image of the driver;
The characteristic fitting module is used for respectively extracting characteristic points of the current state images of the drivers sent to the network point information communication terminal, fitting the characteristic points of the current state images of the drivers and respectively generating current state curve information of the drivers, wherein one current state curve information of the drivers corresponds to one current state image of the drivers;
the information generation module is used for judging whether the current driver is an authenticated driver according to the current state curve information of each driver, if yes, judging whether the driver has preset warning expression information according to the current state curve information of the driver, if yes, generating information warning, wherein the information warning is used for providing staff at a receiving website, and if no, generating a normal prompt of the current environment.
Specifically, the information generation module is further configured to:
acquiring current actual position information of the escort vehicle according to the communication terminal in the escort vehicle, and judging whether the escort vehicle reaches a preset deposit receiving escort point according to the current actual position information; if the escort vehicle is judged to reach a preset deposit receiving escort point, generating a sound collection starting instruction, and sending the sound collection starting instruction to the communication terminal in the escort vehicle based on the network point information communication terminal, wherein the sound collection starting instruction is used for controlling the sound collector to collect sound information of a driver; acquiring a sound collection information set in a preset time period collected by the sound collector; acquiring the current driver speech speed and current driver sound characteristic information according to the sound acquisition information set; judging whether the emotion of the driver is normal or not according to the current driver speech speed and the current driver voice characteristic information; if the emotion of the driver is judged to be normal according to the current driver speech speed and the current driver sound characteristic information, generating a current acceptance opening prompt, wherein the current acceptance opening prompt is used for reminding a worker at a acceptance website of carrying out acceptance work;
Comparing the current driver speech speed with a preset normal state speech speed range according to the current driver speech speed, and judging whether the current driver speech speed is in the normal state speech speed range; if the current driver speech speed is not in the normal state speech speed range, judging that the emotion of the driver is abnormal, and generating a current receiving money stop prompt; if the current driver speech speed is in the normal state speech speed range, judging whether the current driver sound characteristic information is matched with preset standard driver sound characteristic information according to the current driver sound characteristic information; if the current driver voice characteristic information is judged not to be matched with the preset standard driver voice characteristic information, and the emotion abnormality of the driver is judged, generating a current receiving money stop prompt; and if the current driver voice characteristic information is matched with the preset standard driver voice characteristic information, judging that the emotion of the driver is normal.
Specifically, the feature fitting module is further configured to:
the resolution extraction is carried out on the current state images of the drivers sent to the network point information communication terminal, and the current actual resolution of each current state image of the drivers is respectively obtained; classifying the corresponding current state images of the drivers according to the current actual resolutions, and generating a first-gear driver image set and a second-gear driver image set, wherein the resolution of the images in the first-gear driver image set is higher than that of the images in the second-gear driver image set; extracting characteristic points of images in the first-gear driver image set respectively, and acquiring first-gear image characteristic point data sets respectively, wherein the first-gear image characteristic point data sets comprise a plurality of first-gear image characteristic point units, and one first-gear image characteristic point unit corresponds to one image in the first-gear driver image set; extracting characteristic points of images in the second-gear driver image set respectively, and acquiring second-gear image characteristic point data sets respectively, wherein each second-gear image characteristic point data set comprises a plurality of second-gear image characteristic point units, and one second-gear image characteristic point unit corresponds to one image in the second-gear driver image set; comparing the first-grade image characteristic point data set with the second-grade image characteristic point data set, and generating a current difference characteristic point; screening the current difference characteristic points belonging to the second-gear image characteristic point unit, and marking the current difference characteristic points as the difference points to be supplemented currently; performing differential point supplementation on the first-grade image characteristic point data set by the current differential point to be supplemented, and generating a complete image characteristic point data set; performing feature point fitting based on the complete image feature point data set and respectively generating current state curve information of a driver;
Acquiring current acceptance type use feeling feedback information made by a driver and staff at a receiving type website; judging whether the current preset monitoring area is proper or not according to the current accepted money using experience feedback information; if the current preset monitoring area is judged to be proper according to the current acceptance money using experience feedback information, a current area constant instruction is generated; if the current preset monitoring area is judged to be inappropriate according to the current acceptance money using experience feedback information, generating a current area adjusting instruction, adjusting the current preset monitoring area based on the current area adjusting instruction, and generating an updated preset monitoring area after adjustment.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of the driver verification method for a money box escort system described above when the computer program is executed.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above-described driver verification method for a money box escort system.
The invention has the following technical effects:
According to the driver verification method and system for the money box escort system, when escort is carried out, the shooting acquisition instructions are sent to the escort in-car communication terminal based on the website end information communication terminal in sequence, wherein the shooting acquisition instructions are used for controlling the vehicle-mounted lens to carry out multi-angle shooting acquisition on a driver in the escort car and obtaining a plurality of current state images of the driver, and each current state image of the driver is used for being sent to the website end information communication terminal, wherein one angle corresponds to one current state image of the driver; extracting characteristic points of the current state images of the drivers sent to the network point information communication terminal, fitting the characteristic points of the current state images of the drivers, and generating current state curve information of the drivers respectively, wherein one current state curve information of the drivers corresponds to one current state image of the drivers; judging whether the current driver is an authenticated driver according to the current state curve information of each driver, judging whether the driver has preset warning expression information according to the current state curve information of the driver if so, generating information warning for providing staff at a receiving point, generating a current environment normal prompt if not, namely, in order to improve the safety performance of driver authentication, presetting a point end information communication terminal at the receiving point, presetting an in-car communication terminal in the pressing car, wherein the point end information communication terminal and the in-car communication terminal are respectively provided with a specific identification code for representing the respective identity, judging whether the current real communication terminal is the preset in-car communication terminal when the respective specific identification codes are matched, acquiring images through multiple angles, controlling the in-car lens to perform multiple angles on the driver in the in-car communication terminal, acquiring multiple current state images, further acquiring the facial features, such as the five sense of eyes, and the like, and further identifying the five sense of eyes, and the like, and further extracting the characteristics according to the characteristics when the characteristics, if the five sense of eyes, if the nose and the nose are not accurately acquired, fitting each characteristic point of each current state image of the driver and respectively generating current state curve information of the driver. The current state curve information of the driver is used for representing the emotion and the state characteristics of the driver, so that for accurate judgment and high safety judgment, whether the current driver is an authenticated driver or not is judged according to the current state curve information of each driver, if so, in order to eliminate dangerous situations such as the driver not being clamped, whether the driver has preset warning expression information or not is judged according to the current state curve information of the driver, if so, information warning is generated, the information warning is used for providing staff at a receiving money network point, if not, normal prompt of the current environment is generated, and high safety of authentication is further realized.
Drawings
FIG. 1 is a flow diagram of a method of driver verification for a money box escort system in one embodiment;
FIG. 2 is a block diagram of a driver verification system for a money box escort system in one embodiment;
FIG. 3 is an internal block diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, there is provided a driver verification method for a money box escort system, the method comprising:
step S001: acquiring current real communication terminal information connected with a network point end information communication terminal preset at a receiving network point in a current preset monitoring area in real time, and judging whether the current real communication terminal is a preset communication terminal in an escort vehicle, wherein the network point end information communication terminal is preset at the receiving network point, the communication terminal in the escort vehicle is preset in the escort vehicle, a vehicle-mounted lens is arranged in the escort vehicle, and the vehicle-mounted lens is in communication connection with the communication terminal in the escort vehicle;
Further, in order to improve the safety performance of driver authentication, a network point end information communication terminal is preset at a receiving network point, and an escort in-vehicle communication terminal is preset in the escort vehicle.
And when judging that the specific identification codes are matched, judging whether the current real communication terminal is a preset communication terminal in the escort vehicle or not.
Step S002: if the current real communication terminal is judged to be the communication terminal in the escort vehicle, the step S100 is shifted, namely if the current real communication terminal is judged to be the communication terminal in the escort vehicle, a shooting acquisition instruction is sent to the communication terminal in the escort vehicle based on a preset website end information communication terminal.
Step S100: during escort, sending a shooting acquisition instruction to the communication terminal in the escort vehicle based on a preset website end information communication terminal, wherein the shooting acquisition instruction is used for controlling the vehicle-mounted lens to carry out multi-angle shooting acquisition on a driver in the escort vehicle and obtaining a plurality of current state images of the driver, and each current state image of the driver is used for being sent to the website end information communication terminal, wherein one angle corresponds to one current state image of the driver;
Further, in order to accurately acquire information, image acquisition is performed through multiple angles, that is, the vehicle-mounted lens is controlled to perform multi-angle shooting acquisition on the driver in the escort vehicle, multiple current state images of the driver are acquired, and one angle corresponds to one current state image of the driver.
Step S200: extracting characteristic points of the current state images of the drivers sent to the network point information communication terminal, fitting the characteristic points of the current state images of the drivers, and generating current state curve information of the drivers respectively, wherein one current state curve information of the drivers corresponds to one current state image of the drivers;
further, in order to avoid inaccurate data acquisition caused by light, angle and bump, relevant information is acquired through feature point extraction, further, during feature point extraction, identification is performed according to preset identification, for example, identification is performed according to five sense organs, such as nose eyes and mouths, after five sense organs are identified, identification is performed on feature areas around the five sense organs, such as facial curve features and the like, feature point extraction is further realized, and fitting is performed on each feature point of each current state image of the driver to generate current state curve information of the driver respectively. The current mental curve information of the driver is used for representing the emotion and the mental characteristics of the driver.
Step S300: judging whether the current driver is an authenticated driver according to the current state curve information of each driver, if yes, judging whether the driver has preset warning expression information according to the current state curve information of the driver, if yes, generating information warning, wherein the information warning is used for providing staff at a receiving website, and if no, generating normal prompt of the current environment.
Further, in order to accurately judge and realize high safety judgment, whether the current driver is an authenticated driver is judged according to the current state curve information of each driver, if the current driver is an authenticated driver, in order to eliminate dangerous situations such as the driver not being clamped, whether the driver has preset warning expression information is judged according to the current state curve information of the driver, if the driver is judged to be the current state curve information, information warning is generated, the information warning is used for providing staff at a receiving website, and if the driver is judged to be the negative, a normal prompt of the current environment is generated.
In one embodiment, a sound collector is also preset in the escort vehicle, and the sound collector is in communication connection with the communication terminal in the escort vehicle;
Further, the sound collector comprises a headset and the like.
Step S300: judging whether the current driver is an authenticated driver according to the current state curve information of each driver, judging whether the driver has preset warning expression information according to the current state curve information of the driver if the current state curve information of the driver is judged to be positive, generating information warning if the current state curve information of the driver is judged to be positive, wherein the information warning is used for providing staff at a receiving website, generating a normal prompt of the current environment if the current state curve information of the driver is judged to be negative, and further comprising:
step S410: acquiring current actual position information of the escort vehicle according to the communication terminal in the escort vehicle, and judging whether the escort vehicle reaches a preset deposit receiving escort point according to the current actual position information;
step S420: if the escort vehicle is judged to reach a preset deposit receiving escort point, generating a sound collection starting instruction, and sending the sound collection starting instruction to the communication terminal in the escort vehicle based on the network point information communication terminal, wherein the sound collection starting instruction is used for controlling the sound collector to collect sound information of a driver;
step S430: acquiring a sound collection information set in a preset time period collected by the sound collector;
Step S440: acquiring the current driver speech speed and current driver sound characteristic information according to the sound acquisition information set;
further, the current driver sound characteristic information includes a timbre characteristic, an audio characteristic, and a tone of the driver.
Step S450: judging whether the emotion of the driver is normal or not according to the current driver speech speed and the current driver voice characteristic information;
further, a person skilled in the art can set an emotion judgment neural network model according to needs, so that emotion judgment based on a neural network is achieved, after the current driver speech speed and the current driver sound characteristic information are obtained, whether the emotion of the driver is normal or not is judged according to the current driver speech speed and the current driver sound characteristic information, and further information processing efficiency is improved.
Step S460: if the emotion of the driver is judged to be normal according to the current driver speech speed and the current driver sound characteristic information, a current acceptance opening prompt is generated, and the current acceptance opening prompt is used for reminding a worker at a acceptance site of receiving money to carry out the cash receiving work.
Further, in order to further judge whether the condition of the driver is normal, further, the current actual position information of the escort vehicle is obtained according to the communication terminal in the escort vehicle, and whether the escort vehicle reaches a preset deposit receiving escort point is judged according to the current actual position information; then, if the escort vehicle is judged to reach a preset deposit receiving escort point, a sound collection starting instruction is generated, and the sound collection starting instruction is sent to the communication terminal in the escort vehicle based on the network point information communication terminal, wherein the sound collection starting instruction is used for controlling the sound collector to collect sound information of a driver; then, acquiring a sound collection information set in a preset time period collected by the sound collector;
acquiring the current driver speech speed and current driver sound characteristic information according to the sound acquisition information set; then judging whether the emotion of the driver is normal or not according to the current driver speech speed and the current driver voice characteristic information; and finally, if the emotion of the driver is judged to be normal according to the current driver speech speed and the current driver sound characteristic information, generating a current acceptance opening prompt, wherein the current acceptance opening prompt is used for reminding a worker at a receiving money website to carry out the cash receiving work.
In one embodiment, step S450: judging whether the emotion of the driver is normal or not according to the current driver speech speed and the current driver voice characteristic information; the method specifically comprises the following steps:
step S451: comparing the current driver speech speed with a preset normal state speech speed range according to the current driver speech speed, and judging whether the current driver speech speed is in the normal state speech speed range;
the normal state speech speed range is preset, that is, information acquisition and other works are performed on the authenticated driver in advance, so that the normal state speech speed range is obtained.
Step S452: if the current driver speech speed is not in the normal state speech speed range, judging that the emotion of the driver is abnormal, and generating a current receiving money stop prompt;
step S453: if the current driver speech speed is in the normal state speech speed range, judging whether the current driver sound characteristic information is matched with preset standard driver sound characteristic information according to the current driver sound characteristic information;
further, when judging whether the current driver voice feature information is matched with the preset standard driver voice feature information, judging according to tone color features, audio features and tones respectively.
And the method also comprises the steps of carrying out information acquisition on the authenticated driver in advance, acquiring tone characteristics, audio characteristics and tones of the driver under normal conditions, storing the tone characteristics, the audio characteristics and the tones as standard information, further comparing the current driver sound characteristic information with pre-stored standard information in sequence according to the current driver sound characteristic information, judging the similarity after comparison, and if the similarity meets a fixed threshold value, matching, and if the similarity does not meet the fixed threshold value, not matching.
Step S454: if the current driver voice characteristic information is judged not to be matched with the preset standard driver voice characteristic information, and the emotion abnormality of the driver is judged, generating a current receiving money stop prompt;
step S455: and if the current driver voice characteristic information is matched with the preset standard driver voice characteristic information, judging that the emotion of the driver is normal.
Further, in order to accurately judge whether the situation of the driver is normal, comparing the current driver speech speed with a preset normal state speech speed range according to the current driver speech speed, and judging whether the current driver speech speed is in the normal state speech speed range; then, if the current driver speech speed is judged not to be in the normal state speech speed range, and the emotion abnormality of the driver is judged, generating a current receiving money stop prompt; since, at this time, there is a problem in the driver's voice, there is a possibility that the safety problem may cause confusion, and the voice may not coincide with the usual one.
Then, if the current driver speech speed is in the normal state speech speed range, judging whether the current driver sound characteristic information is matched with preset standard driver sound characteristic information according to the current driver sound characteristic information; then, if the current driver voice characteristic information is judged not to be matched with the preset standard driver voice characteristic information, and the emotion abnormality of the driver is judged, generating a current receiving money stop prompt; and if the current driver voice characteristic information is matched with the preset standard driver voice characteristic information, judging that the emotion of the driver is normal, further realizing repeated judgment for a plurality of times, accurately acquiring the actual situation of the driver, and improving the safety performance.
In one embodiment, step S200: extracting characteristic points of a driver current state image sent to the network point information communication terminal, fitting each characteristic point of each driver current state image, and generating driver current state curve information respectively, wherein one driver current state curve information corresponds to one driver current state image, and the method specifically comprises the following steps:
Step S310: the resolution extraction is carried out on the current state images of the drivers sent to the network point information communication terminal, and the current actual resolution of each current state image of the drivers is respectively obtained;
further, in order to achieve the screening of the images with the too low resolution, the current actual resolution of each of the driver's current state images is obtained by separately obtaining the current actual resolution of each of the driver's current state images.
Step S320: classifying the corresponding current state images of the drivers according to the current actual resolutions, and generating a first-gear driver image set and a second-gear driver image set, wherein the resolution of the images in the first-gear driver image set is higher than that of the images in the second-gear driver image set;
further, a gear calibration threshold is preset, when the gear calibration threshold is greater than the gear calibration threshold, the corresponding image belongs to a first gear driver image set, and when the gear calibration threshold is less than or equal to the gear calibration threshold, the corresponding image belongs to a second gear driver image set, namely in the step: the resolution of the first-gear driver image set image is higher than the resolution of the second-gear driver image set image.
Step S330: extracting characteristic points of images in the first-gear driver image set respectively, and acquiring first-gear image characteristic point data sets respectively, wherein the first-gear image characteristic point data sets comprise a plurality of first-gear image characteristic point units, and one first-gear image characteristic point unit corresponds to one image in the first-gear driver image set;
step S340: extracting characteristic points of images in the second-gear driver image set respectively, and acquiring second-gear image characteristic point data sets respectively, wherein each second-gear image characteristic point data set comprises a plurality of second-gear image characteristic point units, and one second-gear image characteristic point unit corresponds to one image in the second-gear driver image set;
further, the second-order image feature point unit and the first-order image feature point unit each include a plurality of feature points.
Step S350: comparing the first-grade image characteristic point data set with the second-grade image characteristic point data set, and generating a current difference characteristic point;
step S360: screening the current difference characteristic points belonging to the second-gear image characteristic point unit, and marking the current difference characteristic points as the difference points to be supplemented currently;
Further, assuming that the number of feature points in the first-stage image feature point data set is 100, and each feature point has a corresponding specific label, for example, the specific label of the nose is "nose", the specific label of the mouth is "mouth", and similarly, the number of feature points in the second-stage image feature point data set is 66, each feature point also has a specific label, then the feature points of the same feature label are not processed, the feature points with different feature labels are current difference feature points, and the current difference feature points may belong to the second-stage image feature point unit or the first-stage image feature point unit, at this time, by screening the current difference feature points belonging to the second-stage image feature point unit and recording the current difference point to be supplemented, effective utilization of the feature points of the image with low resolution and effective supplementation of the feature points of the image with high resolution are realized, and the information acquisition accuracy is improved.
Step S370: performing differential point supplementation on the first-grade image characteristic point data set by the current differential point to be supplemented, and generating a complete image characteristic point data set;
step S380: and fitting characteristic points based on the complete image characteristic point data set and respectively generating current state curve information of the driver.
Further, in order to accurately obtain the feature points, resolution extraction is performed on the current state images of the drivers sent to the network point information communication terminal, and the current actual resolutions of the current state images of the drivers are obtained respectively; then, classifying the corresponding current state images of the drivers according to the current actual resolutions, and generating a first-gear driver image set and a second-gear driver image set, wherein the resolution of the images in the first-gear driver image set is higher than that of the images in the second-gear driver image set; then, extracting characteristic points of the images in the first-gear driver image set respectively, and acquiring first-gear image characteristic point data sets respectively, wherein the first-gear image characteristic point data sets comprise a plurality of first-gear image characteristic point units, and one first-gear image characteristic point unit corresponds to one image in the first-gear driver image set;
further, in order to obtain more accurate information, feature point extraction is performed on the images in the second-gear driver image set, and second-gear image feature point data sets are obtained, wherein each second-gear image feature point data set comprises a plurality of second-gear image feature point units, and one second-gear image feature point unit corresponds to one image in the second-gear driver image set; then, comparing the first-grade image characteristic point data set with the second-grade image characteristic point data set, and generating a current difference characteristic point; then screening the current difference characteristic points belonging to the second-gear image characteristic point unit, and marking the current difference characteristic points as the difference points to be supplemented currently; and then, performing differential point supplementation on the first-grade image characteristic point data set by using the current differential point to be supplemented, generating a complete image characteristic point data set, and finally, performing characteristic point fitting based on the complete image characteristic point data set and respectively generating current state curve information of a driver.
In one embodiment, step S300: judging whether the current driver is an authenticated driver according to the current state curve information of each driver, judging whether the driver has preset warning expression information according to the current state curve information of the driver if the current state curve information of the driver is judged to be positive, generating information warning if the current state curve information of the driver is judged to be positive, wherein the information warning is used for providing staff at a receiving website, generating a normal prompt of the current environment if the current state curve information of the driver is judged to be negative, and further comprising:
step S510: acquiring current acceptance type use feeling feedback information made by a driver and staff at a receiving type website;
step S520: judging whether the current preset monitoring area is proper or not according to the current accepted money using experience feedback information;
further, the current acceptance type use feeling feedback information has description of the current preset monitoring area, such as information describing whether the current preset monitoring area is large enough, so as to judge whether the current preset monitoring area is proper.
Step S530: if the current preset monitoring area is judged to be proper according to the current acceptance money using experience feedback information, a current area constant instruction is generated;
Step S540: if the current preset monitoring area is judged to be inappropriate according to the current acceptance money using experience feedback information, generating a current area adjusting instruction, adjusting the current preset monitoring area based on the current area adjusting instruction, and generating an updated preset monitoring area after adjustment.
Further, in order to realize the setting of the accurate area, whether the current preset monitoring area is proper or not is judged by using the feedback information according to the current acceptance money; then, if the current preset monitoring area is judged to be proper according to the current accepted money using experience feedback information, a current area constant instruction is generated; and then, if the current preset monitoring area is judged to be inappropriate according to the current accepted money using experience feedback information, generating a current area adjusting instruction, adjusting the current preset monitoring area based on the current area adjusting instruction, and generating an updated preset monitoring area after adjustment.
In summary, the driver verification method and system for the money box escort system sequentially send the camera shooting acquisition instructions to the communication terminal in the escort vehicle based on the network point information communication terminal during escort, wherein the camera shooting acquisition instructions are used for controlling the vehicle-mounted lens to carry out multi-angle camera shooting acquisition on a driver in the escort vehicle and obtaining a plurality of current state images of the driver, and each current state image of the driver is used for being sent to the network point information communication terminal, wherein one angle corresponds to one current state image of the driver; extracting characteristic points of the current state images of the drivers sent to the network point information communication terminal, fitting the characteristic points of the current state images of the drivers, and generating current state curve information of the drivers respectively, wherein one current state curve information of the drivers corresponds to one current state image of the drivers; judging whether the current driver is an authenticated driver according to the current state curve information of each driver, judging whether the driver has preset warning expression information according to the current state curve information of the driver if so, generating information warning for providing staff at a receiving point, generating a current environment normal prompt if not, namely, in order to improve the safety performance of driver authentication, presetting a point end information communication terminal at the receiving point, presetting an in-car communication terminal in the pressing car, wherein the point end information communication terminal and the in-car communication terminal are respectively provided with a specific identification code for representing the respective identity, judging whether the current real communication terminal is the preset in-car communication terminal when the respective specific identification codes are matched, acquiring images through multiple angles, controlling the in-car lens to perform multiple angles on the driver in the in-car communication terminal, acquiring multiple current state images, further acquiring the facial features, such as the five sense of eyes, and the like, and further identifying the five sense of eyes, and the like, and further extracting the characteristics according to the characteristics when the characteristics, if the five sense of eyes, if the nose and the nose are not accurately acquired, fitting each characteristic point of each current state image of the driver and respectively generating current state curve information of the driver. The current state curve information of the driver is used for representing the emotion and the state characteristics of the driver, so that for accurate judgment and high safety judgment, whether the current driver is an authenticated driver or not is judged according to the current state curve information of each driver, if so, in order to eliminate dangerous situations such as the driver not being clamped, whether the driver has preset warning expression information or not is judged according to the current state curve information of the driver, if so, information warning is generated, the information warning is used for providing staff at a receiving money network point, if not, normal prompt of the current environment is generated, and high safety of authentication is further realized.
In one embodiment, as shown in FIG. 2, a driver verification system for a money box escort system, the system comprising:
the communication terminal module is used for acquiring current real communication terminal information connected with a network point end information communication terminal preset at a receiving network point in a current preset monitoring area in real time, and judging whether the current real communication terminal is a preset communication terminal in a escort vehicle, wherein the network point end information communication terminal is preset at the receiving network point, the communication terminal in the escort vehicle is preset in the escort vehicle, and a vehicle-mounted lens is arranged in the escort vehicle;
the camera shooting acquisition module is used for sending a camera shooting acquisition instruction to the communication terminal in the escort vehicle based on the network point end information communication terminal if the current real communication terminal is judged to be the communication terminal in the escort vehicle, wherein the camera shooting acquisition instruction is used for controlling the vehicle-mounted lens to carry out multi-angle camera shooting acquisition on a driver in the escort vehicle and obtaining a plurality of current state images of the driver, and each current state image of the driver is used for being sent to the network point end information communication terminal, wherein one angle corresponds to one current state image of the driver;
The characteristic fitting module is used for respectively extracting characteristic points of the current state images of the drivers sent to the network point information communication terminal, fitting the characteristic points of the current state images of the drivers and respectively generating current state curve information of the drivers, wherein one current state curve information of the drivers corresponds to one current state image of the drivers;
the information generation module is used for judging whether the current driver is an authenticated driver according to the current state curve information of each driver, if yes, judging whether the driver has preset warning expression information according to the current state curve information of the driver, if yes, generating information warning, wherein the information warning is used for providing staff at a receiving website, and if no, generating a normal prompt of the current environment.
In one embodiment, the information generation module is further configured to:
acquiring current actual position information of the escort vehicle according to the communication terminal in the escort vehicle, and judging whether the escort vehicle reaches a preset deposit receiving escort point according to the current actual position information; if the escort vehicle is judged to reach a preset deposit receiving escort point, generating a sound collection starting instruction, and sending the sound collection starting instruction to the communication terminal in the escort vehicle based on the network point information communication terminal, wherein the sound collection starting instruction is used for controlling the sound collector to collect sound information of a driver; acquiring a sound collection information set in a preset time period collected by the sound collector; acquiring the current driver speech speed and current driver sound characteristic information according to the sound acquisition information set; judging whether the emotion of the driver is normal or not according to the current driver speech speed and the current driver voice characteristic information; if the emotion of the driver is judged to be normal according to the current driver speech speed and the current driver sound characteristic information, generating a current acceptance opening prompt, wherein the current acceptance opening prompt is used for reminding a worker at a acceptance website of carrying out acceptance work;
Comparing the current driver speech speed with a preset normal state speech speed range according to the current driver speech speed, and judging whether the current driver speech speed is in the normal state speech speed range; if the current driver speech speed is not in the normal state speech speed range, judging that the emotion of the driver is abnormal, and generating a current receiving money stop prompt; if the current driver speech speed is in the normal state speech speed range, judging whether the current driver sound characteristic information is matched with preset standard driver sound characteristic information according to the current driver sound characteristic information; if the current driver voice characteristic information is judged not to be matched with the preset standard driver voice characteristic information, and the emotion abnormality of the driver is judged, generating a current receiving money stop prompt; and if the current driver voice characteristic information is matched with the preset standard driver voice characteristic information, judging that the emotion of the driver is normal.
In one embodiment, the feature fitting module is further configured to:
the resolution extraction is carried out on the current state images of the drivers sent to the network point information communication terminal, and the current actual resolution of each current state image of the drivers is respectively obtained; classifying the corresponding current state images of the drivers according to the current actual resolutions, and generating a first-gear driver image set and a second-gear driver image set, wherein the resolution of the images in the first-gear driver image set is higher than that of the images in the second-gear driver image set; extracting characteristic points of images in the first-gear driver image set respectively, and acquiring first-gear image characteristic point data sets respectively, wherein the first-gear image characteristic point data sets comprise a plurality of first-gear image characteristic point units, and one first-gear image characteristic point unit corresponds to one image in the first-gear driver image set; extracting characteristic points of images in the second-gear driver image set respectively, and acquiring second-gear image characteristic point data sets respectively, wherein each second-gear image characteristic point data set comprises a plurality of second-gear image characteristic point units, and one second-gear image characteristic point unit corresponds to one image in the second-gear driver image set; comparing the first-grade image characteristic point data set with the second-grade image characteristic point data set, and generating a current difference characteristic point; screening the current difference characteristic points belonging to the second-gear image characteristic point unit, and marking the current difference characteristic points as the difference points to be supplemented currently; performing differential point supplementation on the first-grade image characteristic point data set by the current differential point to be supplemented, and generating a complete image characteristic point data set; performing feature point fitting based on the complete image feature point data set and respectively generating current state curve information of a driver;
Acquiring current acceptance type use feeling feedback information made by a driver and staff at a receiving type website; judging whether the current preset monitoring area is proper or not according to the current accepted money using experience feedback information; if the current preset monitoring area is judged to be proper according to the current acceptance money using experience feedback information, a current area constant instruction is generated; if the current preset monitoring area is judged to be inappropriate according to the current acceptance money using experience feedback information, generating a current area adjusting instruction, adjusting the current preset monitoring area based on the current area adjusting instruction, and generating an updated preset monitoring area after adjustment.
In one embodiment, as shown in fig. 3, a computer device includes a memory storing a computer program and a processor that when executed implements the steps described above for a driver verification method for a money box escort system.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above-described driver verification method for a money box escort system.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims (8)

1. A driver verification method for a money box escort system, the method comprising:
during escort, sending a shooting acquisition instruction to an in-escort vehicle communication terminal based on the website end information communication terminal, wherein the shooting acquisition instruction is used for controlling a vehicle-mounted lens to carry out shooting acquisition and obtaining a plurality of current state images of drivers, and each current state image of the driver is used for being sent to the website end information communication terminal; extracting characteristic points of the current state images of the drivers sent to the network point information communication terminal, fitting the characteristic points of the current state images of the drivers, and generating current state curve information of the drivers; judging whether the current driver is an authenticated driver according to the current state curve information of each driver, if so, judging whether the driver has preset warning expression information according to the current state curve information of the driver, and if so, generating information warning;
Extracting characteristic points of a driver current state image sent to the network point information communication terminal, fitting each characteristic point of each driver current state image, and generating driver current state curve information respectively, wherein one driver current state curve information corresponds to one driver current state image, and the method specifically comprises the following steps:
the resolution extraction is carried out on the current state images of the drivers sent to the network point information communication terminal, and the current actual resolution of each current state image of the drivers is respectively obtained; classifying the corresponding current state images of the drivers according to the current actual resolutions, and generating a first-gear driver image set and a second-gear driver image set, wherein the resolution of the images in the first-gear driver image set is higher than that of the images in the second-gear driver image set; extracting characteristic points of images in the first-gear driver image set respectively, and acquiring first-gear image characteristic point data sets respectively, wherein the first-gear image characteristic point data sets comprise a plurality of first-gear image characteristic point units, and one first-gear image characteristic point unit corresponds to one image in the first-gear driver image set; extracting characteristic points of images in the second-gear driver image set respectively, and acquiring second-gear image characteristic point data sets respectively, wherein each second-gear image characteristic point data set comprises a plurality of second-gear image characteristic point units, and one second-gear image characteristic point unit corresponds to one image in the second-gear driver image set; comparing the first-grade image characteristic point data set with the second-grade image characteristic point data set, and generating a current difference characteristic point; screening the current difference characteristic points belonging to the second-gear image characteristic point unit, and marking the current difference characteristic points as the difference points to be supplemented currently; performing differential point supplementation on the first-grade image characteristic point data set by the current differential point to be supplemented, and generating a complete image characteristic point data set; and fitting characteristic points based on the complete image characteristic point data set and respectively generating current state curve information of the driver.
2. The method for verifying a driver of a money box escort system according to claim 1, wherein a sound collector is further provided in the escort vehicle in advance, and the sound collector is in communication connection with a communication terminal in the escort vehicle;
judging whether the current driver is an authenticated driver according to the current state curve information of each driver, judging whether the driver has preset warning expression information according to the current state curve information of the driver if the current state curve information of the driver is judged to be positive, generating information warning if the current state curve information of the driver is judged to be positive, wherein the information warning is used for providing staff at a receiving website, generating a normal prompt of the current environment if the current state curve information of the driver is judged to be negative, and further comprising:
acquiring current actual position information of the escort vehicle according to the communication terminal in the escort vehicle, and judging whether the escort vehicle reaches a preset deposit receiving escort point according to the current actual position information; if the escort vehicle is judged to reach a preset deposit receiving escort point, generating a sound collection starting instruction, and sending the sound collection starting instruction to the communication terminal in the escort vehicle based on the network point information communication terminal, wherein the sound collection starting instruction is used for controlling the sound collector to collect sound information of a driver; acquiring a sound collection information set in a preset time period collected by the sound collector; acquiring the current driver speech speed and current driver sound characteristic information according to the sound acquisition information set; judging whether the emotion of the driver is normal or not according to the current driver speech speed and the current driver voice characteristic information; if the emotion of the driver is judged to be normal according to the current driver speech speed and the current driver sound characteristic information, a current acceptance opening prompt is generated, and the current acceptance opening prompt is used for reminding a worker at a acceptance site of receiving money to carry out the cash receiving work.
3. The driver verification method for money box escort system according to claim 2, wherein judging whether the emotion of the driver is normal or not according to the current driver speech speed and the current driver sound feature information; the method specifically comprises the following steps:
comparing the current driver speech speed with a preset normal state speech speed range according to the current driver speech speed, and judging whether the current driver speech speed is in the normal state speech speed range; if the current driver speech speed is not in the normal state speech speed range, judging that the emotion of the driver is abnormal, and generating a current receiving money stop prompt; if the current driver speech speed is in the normal state speech speed range, judging whether the current driver sound characteristic information is matched with preset standard driver sound characteristic information according to the current driver sound characteristic information; if the current driver voice characteristic information is judged not to be matched with the preset standard driver voice characteristic information, and the emotion abnormality of the driver is judged, generating a current receiving money stop prompt; and if the current driver voice characteristic information is matched with the preset standard driver voice characteristic information, judging that the emotion of the driver is normal.
4. The driver verification method for money box escort system according to any one of claims 1-2, wherein judging whether the current driver is an authenticated driver based on the current state curve information of each driver, if yes, judging whether the driver has a preset warning expression information based on the current state curve information of the driver, if yes, generating an information alert for providing a worker at a receiving money net point, if no, generating a current environment normal prompt, and then further comprising:
acquiring current acceptance type use feeling feedback information made by a driver and staff at a receiving type website; judging whether a current preset monitoring area is proper or not according to the current accepted money using experience feedback information; if the current preset monitoring area is judged to be proper according to the current acceptance money using experience feedback information, a current area constant instruction is generated; if the current preset monitoring area is judged to be inappropriate according to the current acceptance money using experience feedback information, generating a current area adjusting instruction, adjusting the current preset monitoring area based on the current area adjusting instruction, and generating an updated preset monitoring area after adjustment.
5. A driver verification system for a money box escort system, the system comprising:
the system comprises a camera shooting acquisition module, a network point information communication terminal and a network point information communication terminal, wherein the camera shooting acquisition module is used for transmitting a camera shooting acquisition instruction to the network point information communication terminal in the escort vehicle based on the network point information communication terminal during escort, the camera shooting acquisition instruction is used for controlling a vehicle-mounted lens to carry out multi-angle camera shooting acquisition on a driver in the escort vehicle and acquiring a plurality of current state images of the driver, and each current state image of the driver is used for being transmitted to the network point information communication terminal, wherein one angle corresponds to one current state image of the driver;
the characteristic fitting module is used for respectively extracting characteristic points of the current state images of the drivers sent to the network point information communication terminal, fitting the characteristic points of the current state images of the drivers and respectively generating current state curve information of the drivers, wherein one current state curve information of the drivers corresponds to one current state image of the drivers;
the information generation module is used for judging whether the current driver is an authenticated driver according to the current state curve information of each driver, if yes, judging whether the driver has preset warning expression information according to the current state curve information of the driver, if yes, generating information warning, wherein the information warning is used for providing staff at a receiving website, and if no, generating a normal prompt of the current environment;
The feature fitting module is further configured to:
the resolution extraction is carried out on the current state images of the drivers sent to the network point information communication terminal, and the current actual resolution of each current state image of the drivers is respectively obtained; classifying the corresponding current state images of the drivers according to the current actual resolutions, and generating a first-gear driver image set and a second-gear driver image set, wherein the resolution of the images in the first-gear driver image set is higher than that of the images in the second-gear driver image set; extracting characteristic points of images in the first-gear driver image set respectively, and acquiring first-gear image characteristic point data sets respectively, wherein the first-gear image characteristic point data sets comprise a plurality of first-gear image characteristic point units, and one first-gear image characteristic point unit corresponds to one image in the first-gear driver image set; extracting characteristic points of images in the second-gear driver image set respectively, and acquiring second-gear image characteristic point data sets respectively, wherein each second-gear image characteristic point data set comprises a plurality of second-gear image characteristic point units, and one second-gear image characteristic point unit corresponds to one image in the second-gear driver image set; comparing the first-grade image characteristic point data set with the second-grade image characteristic point data set, and generating a current difference characteristic point; screening the current difference characteristic points belonging to the second-gear image characteristic point unit, and marking the current difference characteristic points as the difference points to be supplemented currently; performing differential point supplementation on the first-grade image characteristic point data set by the current differential point to be supplemented, and generating a complete image characteristic point data set; performing feature point fitting based on the complete image feature point data set and respectively generating current state curve information of a driver;
Acquiring current acceptance type use feeling feedback information made by a driver and staff at a receiving type website; judging whether a current preset monitoring area is proper or not according to the current accepted money using experience feedback information; if the current preset monitoring area is judged to be proper according to the current acceptance money using experience feedback information, a current area constant instruction is generated; if the current preset monitoring area is judged to be inappropriate according to the current acceptance money using experience feedback information, generating a current area adjusting instruction, adjusting the current preset monitoring area based on the current area adjusting instruction, and generating an updated preset monitoring area after adjustment.
6. The driver verification system for a money box escort system of claim 5, wherein the information generating module is further configured to:
acquiring current actual position information of the escort vehicle according to the communication terminal in the escort vehicle, and judging whether the escort vehicle reaches a preset deposit receiving escort point according to the current actual position information; if the escort vehicle is judged to reach a preset deposit receiving escort point, generating a sound collection starting instruction, and sending the sound collection starting instruction to the communication terminal in the escort vehicle based on the network point information communication terminal, wherein the sound collection starting instruction is used for controlling a sound collector in the escort vehicle to collect sound information of a driver; acquiring a sound collection information set in a preset time period collected by the sound collector; acquiring the current driver speech speed and current driver sound characteristic information according to the sound acquisition information set; judging whether the emotion of the driver is normal or not according to the current driver speech speed and the current driver voice characteristic information; if the emotion of the driver is judged to be normal according to the current driver speech speed and the current driver sound characteristic information, generating a current acceptance opening prompt, wherein the current acceptance opening prompt is used for reminding a worker at a acceptance website of carrying out acceptance work;
Comparing the current driver speech speed with a preset normal state speech speed range according to the current driver speech speed, and judging whether the current driver speech speed is in the normal state speech speed range; if the current driver speech speed is not in the normal state speech speed range, judging that the emotion of the driver is abnormal, and generating a current receiving money stop prompt; if the current driver speech speed is in the normal state speech speed range, judging whether the current driver sound characteristic information is matched with preset standard driver sound characteristic information according to the current driver sound characteristic information; if the current driver voice characteristic information is judged not to be matched with the preset standard driver voice characteristic information, and the emotion abnormality of the driver is judged, generating a current receiving money stop prompt; and if the current driver voice characteristic information is matched with the preset standard driver voice characteristic information, judging that the emotion of the driver is normal.
7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 4.
CN202210092862.6A 2022-01-26 2022-01-26 Driver verification method and system for money box escort system Active CN114475620B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210092862.6A CN114475620B (en) 2022-01-26 2022-01-26 Driver verification method and system for money box escort system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210092862.6A CN114475620B (en) 2022-01-26 2022-01-26 Driver verification method and system for money box escort system

Publications (2)

Publication Number Publication Date
CN114475620A CN114475620A (en) 2022-05-13
CN114475620B true CN114475620B (en) 2024-03-12

Family

ID=81474592

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210092862.6A Active CN114475620B (en) 2022-01-26 2022-01-26 Driver verification method and system for money box escort system

Country Status (1)

Country Link
CN (1) CN114475620B (en)

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108294759A (en) * 2017-01-13 2018-07-20 天津工业大学 A kind of Driver Fatigue Detection based on CNN Eye state recognitions
CN109740477A (en) * 2018-12-26 2019-05-10 联创汽车电子有限公司 Study in Driver Fatigue State Surveillance System and its fatigue detection method
CN109801220A (en) * 2019-01-23 2019-05-24 北京工业大学 Mapping parameters method in a kind of splicing of line solver Vehicular video
CN110119676A (en) * 2019-03-28 2019-08-13 广东工业大学 A kind of Driver Fatigue Detection neural network based
CN110395260A (en) * 2018-04-20 2019-11-01 比亚迪股份有限公司 Vehicle, safe driving method and device
CN111277575A (en) * 2020-01-14 2020-06-12 广州交通信息化建设投资营运有限公司 Driver identity recognition method and device, computer equipment and storage medium
CN111368640A (en) * 2020-02-10 2020-07-03 上海应用技术大学 Illegal driving auxiliary identification method based on identity authentication
CN112084942A (en) * 2018-03-09 2020-12-15 西安艾润物联网技术服务有限责任公司 Method and device for online monitoring of driver identity in vehicle and storage medium
CN112078590A (en) * 2019-05-27 2020-12-15 郑州宇通客车股份有限公司 Driving behavior monitoring method and system
WO2020253349A1 (en) * 2019-06-19 2020-12-24 深圳壹账通智能科技有限公司 Image recognition-based driving behavior warning method and apparatus, and computer device
JP2021026748A (en) * 2019-08-01 2021-02-22 肇▲慶▼学院 Overstrained driving detection warning system and method based on machine vision
CN112699802A (en) * 2020-12-31 2021-04-23 青岛海山慧谷科技有限公司 Driver micro-expression detection device and method
CN112785837A (en) * 2019-11-11 2021-05-11 上海博泰悦臻电子设备制造有限公司 Method and device for recognizing emotion of user when driving vehicle, storage medium and terminal
CN113331841A (en) * 2021-08-05 2021-09-03 深圳市爱深盈通信息技术有限公司 Bus risk coefficient evaluation method, algorithm box and system
CN113449592A (en) * 2021-05-18 2021-09-28 浙江大华技术股份有限公司 Escort task detection method, escort task detection system, electronic device and storage medium

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108294759A (en) * 2017-01-13 2018-07-20 天津工业大学 A kind of Driver Fatigue Detection based on CNN Eye state recognitions
CN112084942A (en) * 2018-03-09 2020-12-15 西安艾润物联网技术服务有限责任公司 Method and device for online monitoring of driver identity in vehicle and storage medium
CN110395260A (en) * 2018-04-20 2019-11-01 比亚迪股份有限公司 Vehicle, safe driving method and device
CN109740477A (en) * 2018-12-26 2019-05-10 联创汽车电子有限公司 Study in Driver Fatigue State Surveillance System and its fatigue detection method
CN109801220A (en) * 2019-01-23 2019-05-24 北京工业大学 Mapping parameters method in a kind of splicing of line solver Vehicular video
CN110119676A (en) * 2019-03-28 2019-08-13 广东工业大学 A kind of Driver Fatigue Detection neural network based
CN112078590A (en) * 2019-05-27 2020-12-15 郑州宇通客车股份有限公司 Driving behavior monitoring method and system
WO2020253349A1 (en) * 2019-06-19 2020-12-24 深圳壹账通智能科技有限公司 Image recognition-based driving behavior warning method and apparatus, and computer device
JP2021026748A (en) * 2019-08-01 2021-02-22 肇▲慶▼学院 Overstrained driving detection warning system and method based on machine vision
CN112785837A (en) * 2019-11-11 2021-05-11 上海博泰悦臻电子设备制造有限公司 Method and device for recognizing emotion of user when driving vehicle, storage medium and terminal
CN111277575A (en) * 2020-01-14 2020-06-12 广州交通信息化建设投资营运有限公司 Driver identity recognition method and device, computer equipment and storage medium
CN111368640A (en) * 2020-02-10 2020-07-03 上海应用技术大学 Illegal driving auxiliary identification method based on identity authentication
CN112699802A (en) * 2020-12-31 2021-04-23 青岛海山慧谷科技有限公司 Driver micro-expression detection device and method
CN113449592A (en) * 2021-05-18 2021-09-28 浙江大华技术股份有限公司 Escort task detection method, escort task detection system, electronic device and storage medium
CN113331841A (en) * 2021-08-05 2021-09-03 深圳市爱深盈通信息技术有限公司 Bus risk coefficient evaluation method, algorithm box and system

Also Published As

Publication number Publication date
CN114475620A (en) 2022-05-13

Similar Documents

Publication Publication Date Title
CN111191567B (en) Identity data processing method, device, computer equipment and storage medium
US10880299B2 (en) Machine learning for document authentication
CN109214821B (en) Identity remote authentication method and terminal equipment
US11482012B2 (en) Method for driving assistance and mobile device using the method
WO2022142319A1 (en) False insurance claim report processing method and apparatus, and computer device and storage medium
CN110942776B (en) Audio splicing prevention detection method and system based on GRU
CN111675059A (en) Elevator control method and device based on face recognition and computer equipment
CN114475620B (en) Driver verification method and system for money box escort system
CN113204619B (en) Sentence completion method, device, equipment and medium based on natural language processing
CN110991558B (en) Accident handling method and device based on image recognition and computer equipment
KR102447961B1 (en) Server and Method for Detecting Hologram
CN113873088A (en) Voice call interaction method and device, computer equipment and storage medium
CN103699887A (en) Portrait identification method and device
CN111540208A (en) Method for preventing driving without license and fatigue driving based on block chain technology
CN110472656B (en) Vehicle image classification method, device, computer equipment and storage medium
CN113064997B (en) Intention analysis method, device, equipment and medium based on BERT model
CN111883112B (en) Semantic recognition method and device based on multi-mode identification and computer equipment
CN110717166A (en) Vehicle-mounted identity recognition method and system
KR102384253B1 (en) Method for performing video call certification
CN114549221A (en) Vehicle accident loss processing method and device, computer equipment and storage medium
CN113792683B (en) Training method, training device, training equipment and training storage medium for text recognition model
CN113178197B (en) Training method and device of voice verification model and computer equipment
CN113313129B (en) Training method, device, equipment and storage medium for disaster damage recognition model
CN111476279B (en) Similarity value-based identification method and device and computer equipment
CN115424349A (en) Violation behavior recognition method and violation prediction model training method and system

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