CN112258680B - Method and system for realizing office multifunctional intelligent equipment based on raspberry group - Google Patents

Method and system for realizing office multifunctional intelligent equipment based on raspberry group Download PDF

Info

Publication number
CN112258680B
CN112258680B CN202011046218.2A CN202011046218A CN112258680B CN 112258680 B CN112258680 B CN 112258680B CN 202011046218 A CN202011046218 A CN 202011046218A CN 112258680 B CN112258680 B CN 112258680B
Authority
CN
China
Prior art keywords
module
raspberry
value
motor
rotating speed
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
CN202011046218.2A
Other languages
Chinese (zh)
Other versions
CN112258680A (en
Inventor
刘建林
于孝建
陈泽彬
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.)
South China University of Technology SCUT
Original Assignee
South China University of Technology SCUT
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 South China University of Technology SCUT filed Critical South China University of Technology SCUT
Priority to CN202011046218.2A priority Critical patent/CN112258680B/en
Publication of CN112258680A publication Critical patent/CN112258680A/en
Application granted granted Critical
Publication of CN112258680B publication Critical patent/CN112258680B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
    • G07C1/20—Checking timed patrols, e.g. of watchman
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/24—Floor-sweeping machines, motor-driven
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A47L11/4061—Steering means; Means for avoiding obstacles; Details related to the place where the driver is accommodated
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
    • G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
    • G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Theoretical Computer Science (AREA)
  • Acoustics & Sound (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Emergency Alarm Devices (AREA)

Abstract

The invention discloses a raspberry pi-based office multifunctional intelligent equipment system and an implementation method thereof, which realize the functions of intelligent patrol attendance checking, stranger alarm and security protection, mail work and rest reminding and intelligent obstacle avoidance and cleaning. The system comprises a power module, a raspberry group module, a camera module, a microphone module, an obstacle avoidance red sensing module, a tracing infrared sensing module, a motor module, a sound module, a cleaning module and a mail sending module. When the intelligent patrol attendance checking task is executed, the raspberry group receives the signal of the tracing infrared sensing module, controls the motor module to complete the tracing task, and is matched with the camera module and the microphone module to perform face recognition and voice recognition to complete the attendance checking function. When the security protection function of alarming of strangers is executed, the raspberry group collects video image information through the camera module to perform a face recognition task, and the raspberry group is matched with the sound module to complete the security protection alarming function. And when the mail work and rest reminding function is executed, the mail sending module sends mails to remind staff of work and rest time at regular time.

Description

Method and system for realizing office multifunctional intelligent equipment based on raspberry group
Technical Field
The invention belongs to the field of unmanned intelligent equipment, and particularly relates to a raspberry pi-based office multifunctional intelligent system and an implementation method and system thereof.
Background
With the progress of science and technology, intelligent products are used as one of important devices in various automatic control systems, and are used in large quantities in large-scale projects such as logistics transportation, pipeline production and the like, meanwhile, with the continuous optimization and improvement of portable intelligent products, various intelligent products are also used for continuously enriching the daily life experience of people, for example, intelligent home is used as a relatively well-developed system, and becomes a successful example of direct connection between intelligent products and daily life. Office's smart machine to basic requirements such as general office patrol attendance and security protection warning, provides intelligent unmanned service, can promote office staff work and experience, promotes office efficiency.
The intelligent unmanned robot is mainly used for patrol of exhibition halls and hotel reception services, is less applied to office scenes, is applied to the office scenes by intelligent equipment, provides intelligent services related to office work, and improves the working efficiency of office workers, so that the intelligent unmanned robot has a good development prospect and higher social requirements. For the reasons, the design of a simple and convenient office intelligent device is of great significance.
Aiming at the working environment and the requirement of daily offices, the following problems are considered and solved:
(1) the office attendance problem: nowadays, companies or human units increasingly pay more attention to attendance systems, most of the attendance methods of the companies or the human units are that attendance points are arranged at the doors of the companies, and staff need to go to the attendance points to take pictures and punch cards, so that the time of punching the cards by the staff is reduced, and the working efficiency can be improved to a certain extent.
(2) Office cleanliness issues: the clean degree of environment in office has reflected the image of a company to a certain extent, and intelligent cleaning equipment not only can maintain the clean and tidy environment in office, can also reduce the cost in the aspect of hiring the cleanup crew simultaneously, can bring certain economic benefits for office work.
(3) Office security protection problem: relevant important data in an office need to be well guaranteed, so that how to effectively prevent strangers from entering the office is a very important problem.
(4) Office staff work and rest problems: timely rest can enable the staff to keep full energy, the working efficiency of the staff can be improved, and meanwhile the image of an office is also improved.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a raspberry pi-based office multifunctional intelligent equipment system and an implementation method thereof.
The utility model provides a multi-functional smart machine system of office based on raspberry group for realize patrol attendance function, warning security protection function, intelligence and keep away barrier clean function, mail work and rest and remind the function, include:
the raspberry pi module is used for receiving execution instructions of all functions and signals of all modules and sending out signals;
the tracing infrared sensing module is used for collecting signals and transmitting the signals to the raspberry group module;
the motor module is used for receiving the control signal sent by the raspberry pi module and starting and stopping the raspberry pi module according to the control signal;
the camera module is used for acquiring a face image;
the microphone module is used for collecting an environmental audio signal;
the sound module is used for playing an alarm audio according to the instruction of the raspberry dispatching module;
the mail sending module is used for finishing the mail sending function;
the obstacle avoidance infrared sensing module is used for acquiring obstacle signals and transmitting the signals to the raspberry group module for processing;
and the cleaning module is used for cleaning.
The invention also provides a method for realizing the office multifunctional intelligent equipment system based on the raspberry pi, which comprises the following steps:
connecting the user terminal and the raspberry group to the same local area network, and performing communication connection between the user terminal and the intelligent equipment system through a push;
the user terminal visually checks the raspberry group internal engineering file through a VNC remote control tool;
and the computer executes the engineering files with corresponding functions, wherein the engineering files with corresponding functions respectively comprise engineering files with patrol attendance checking function, alarm security function and intelligent obstacle avoidance and cleaning function.
Further, when the patrol attendance function is executed, the specific steps are as follows:
s1, the raspberry dispatching module receives the execution instruction, and the system executes a patrol attendance function;
s2, the raspberry pi module receives the signal of the infrared tracking sensor module and outputs a corresponding control signal to the motor module according to the received signal;
s3, simultaneously, the raspberry pi module receives the audio signal of the microphone module and performs voice recognition, and when the voice recognition is successful, the raspberry pi module outputs a control signal to the motor module, and the motor module stops rotating; if the voice recognition is unsuccessful, repeating the steps S2 and S3;
s4, starting a camera module by the raspberry pie to collect and identify the human face;
and S5, closing the camera module, receiving the audio signal of the microphone module by the raspberry to perform voice recognition, and returning to the step S2 when the audio signal is judged to be the set awakening word by the raspberry.
Further, the S2 includes the following steps:
s201, a raspberry group module reads signals of an infrared tracing sensor module in real time, each group of infrared signals consists of a one-dimensional quintuple array, data of five detection heads in the infrared tracing sensor module are recorded, the raspberry group module obtains 10 groups of infrared signals to be read in as analog data, each group of data is weighted and averaged according to corresponding weight, and the maximum value and the minimum value in the 10 groups of data are reserved as tracing comparison data;
s202, the raspberry serving module processes a value obtained by weighted averaging of the numerical value returned by the infrared tracing sensor module, sets a processing value with a black line in the middle as a central value, compares the weighted average value with the central value, multiplies the difference value of the weighted average value and the central value by a maximum value and a minimum value according to a set coefficient to obtain corresponding adjusting rotating speeds of a left motor and a right motor, and feeds back the processing result to the motor module;
s203, adjusting the motor module to the corresponding rotating speed, and carrying out tracing patrol by the system.
Further, the S3 includes the following steps:
s301, the microphone module is connected with the raspberry pi module through a USB interface, collects environmental audio signals and transmits the environmental audio signals to the raspberry pi module in real time;
s302, the raspberry pi module processes the audio signal by using a voice awakening word recognition algorithm and monitors whether the audio signal contains a set awakening word.
S303, if the set awakening words are contained in the monitored audio, the raspberry pi module sends a control signal to the motor module;
s304, the motor module receives a signal of the raspberry pi module, the motor module stops rotating, and the system stops patrolling.
Further, the S4 includes the following steps:
s401, starting a camera module by a raspberry group module, and capturing an image in real time by the camera module;
s402, the raspberry pi module performs face recognition on the image through a face recognition algorithm, and simultaneously a VNC interface of the user terminal displays an image picture and face recognition related information;
and S403, if the captured image is judged as a system user, displaying the user name and the recognition confidence at the VNC end of the user terminal, and simultaneously modifying the personnel attendance information file by the raspberry dispatching module and updating the attendance information.
Further, when the security alarm function is executed, the steps are as follows:
s1, the raspberry dispatching module receives the execution instruction and executes the security alarm function;
s2, the raspberry pi module is connected with the sound module through Bluetooth, meanwhile, the camera module is started to capture a face image, face recognition is conducted, and if the face image is recognized as a non-system user, the raspberry pi module sends an audio playing signal;
and S3, the sound module plays an alarm audio according to the signal of the raspberry pi module.
And S4, the mail sending module sends the alarm mail to a specific mailbox and executes the automatic mail alarm reminding function.
Further, when the intelligent obstacle avoidance and cleaning function is executed, the method comprises the following steps:
s1, the raspberry dispatching module receives an execution instruction and executes an intelligent obstacle avoidance and cleaning function;
s2, the raspberry pi module receives the signal of the obstacle avoidance infrared sensor module and outputs a corresponding control signal to the motor module according to the received signal;
and S3, starting a cleaning module of the intelligent equipment system to clean the road surface.
Further, when the mail work and rest reminding function is executed, the method comprises the following steps:
s1, the mail sending module receives the raspberry dispatching instruction, sends a work and rest reminding mail according to the set time and sends the work and rest reminding mail to the designated mailbox account;
s2, when the reminding mail is sent, the raspberry pie starts the sound module to play the song;
and S3, after the playing reaches the preset time, the raspberry party closes the sound module, and the mail sending module waits for the next mail sending instruction.
Compared with the prior art, the invention can realize the following beneficial effects:
(1) by adopting a patrol card punching mode and waking up the running and stopping of the word recognition control equipment through voice, the work card punching process of the staff is more convenient and faster.
(2) The security monitoring is carried out by adopting a face recognition mode, strangers are effectively recognized and detected, office workers and stranger external personnel are distinguished, and a more effective intelligent security function is provided.
(3) Meanwhile, the intelligent mail sending service is provided, corresponding mails can be sent according to different conditions, and corresponding mail reminding services can be provided according to different office scenes and requirements.
Drawings
FIG. 1 is a system structure diagram of the implementation method of the multifunctional intelligent office equipment based on the raspberry pi.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment discloses a multi-functional intelligent equipment system of office based on raspberry group can realize patrol attendance function, warning security protection function, intelligent obstacle avoidance cleaning function, mail work and rest reminding function, and the system hardware structure is as shown in figure 1. The method comprises the following steps:
the raspberry pi module is used for receiving execution instructions of all functions and signals of all modules and sending out signals;
the tracing infrared sensing module is used for collecting ground trace signals and transmitting the ground trace signals to the raspberry group module, and comprises five detecting heads;
the motor module is used for receiving the control signal sent by the raspberry pi module and starting and stopping according to the control signal, and comprises two motors positioned on the left side and the right side;
the camera module is used for acquiring a face image;
the microphone module is used for collecting an environmental audio signal;
the sound module is used for playing an alarm audio according to the instruction of the raspberry dispatching module;
the mail sending module is used for finishing the mail sending function;
the obstacle avoidance infrared sensing module is used for acquiring obstacle signals and transmitting the signals to the raspberry group module for processing, and the obstacle avoidance infrared sensing module comprises a left side infrared sensor and a right side infrared sensor which are respectively positioned at the left side and the right side;
and the cleaning module is used for cleaning.
The power supply module is used for supplying power to the modules.
The embodiment also provides an implementation method of the office multifunctional intelligent device system based on the raspberry pi, which comprises the following steps:
step 1, connecting the user terminal and the raspberry group to the same local area network, and performing communication connection between the user terminal and the intelligent equipment system through a push.
The user terminal is a computer, a WIFI hotspot is started at the computer end, and the WIFI module in the raspberry dispatching module is connected with the hotspot. The raspberry pi and the local computer are connected with the same local area network through WIFI, and the computer end can control the raspberry pi to execute corresponding task files through corresponding connection software, so that the working mode of the equipment system is controlled.
Step 2, the user terminal views the raspberry group internal engineering file in a visual mode through a VNC remote control tool;
and 3, executing engineering files with corresponding functions by the computer, wherein the engineering files with the corresponding functions respectively comprise engineering files with a patrol attendance function, an alarm security function, an intelligent obstacle avoidance and cleaning function and a mail work and rest reminding function.
Furthermore, when the patrol attendance checking function is executed, the motion trail of the equipment needs to be planned on the ground within the use range by using a trace different from the ground color in advance, for example, the motion trail of the equipment needs to be planned by using a black adhesive tape. The method comprises the following specific steps:
and S1, the raspberry dispatching module receives the execution instruction, and the system executes the patrol attendance function.
And S2, the infrared tracing sensor is composed of five infrared sensors which are transversely arranged, the infrared sensors can detect the trace signals of the road surface, and the raspberry pi module receives the signals of the infrared tracing sensor module and outputs corresponding control signals to the motor module according to the received signals.
Specifically, the method specifically comprises the following steps:
s201, the raspberry pi module reads signals of the infrared tracing sensor module in real time, the infrared tracing sensor is composed of five infrared sensors which are transversely arranged, the infrared sensors can detect signals of the traces on the road surface, the infrared sensors which detect the traces return first signals, if the signals return to 1, the infrared sensors which do not detect the traces return second signals, if the signals return to 0. Each group of infrared signals returned to the raspberry pi module consists of a one-dimensional quintuple array and respectively corresponds to the return value of each infrared sensor.
S202, the raspberry pi module respectively gives the weight of 0, 1000, 2000, 3000 and 4000 to each infrared sensor from left to right. And the raspberry pi module carries out weighting processing on the arrays returned by the infrared tracking sensor module, and divides the sum of the weighted arrays by the sum of unweighted arrays to obtain an absolute deviation value. When the absolute offset value is equal to 2000, it represents that the ground trace is located at the midpoint of the infrared tracking sensor, and this value is called the center value.
S203, the raspberry pi module compares the absolute offset value with the central value, and the difference value is called a relative offset value. The difference between the current relative offset value and the previous relative offset value is called an azimuth adjusting value, and the value obtained by cumulatively summing all the previous relative offset values is called a cumulative offset value. The (relative offset/25 + azimuth adjusted value/100 + cumulative offset/1000) value is referred to as the speed difference. Setting a maximum value of the rotation speed of the motor, setting the rotation speed difference value as the maximum value of the rotation speed of the motor if the rotation speed difference value is larger than the maximum value of the rotation speed of the motor, and setting the rotation speed difference value as the opposite number of the maximum value of the rotation speed of the motor if the rotation speed difference value is smaller than the opposite number of the maximum value of the rotation speed of the motor. If the absolute value of the rotating speed difference is smaller than the maximum rotating speed of the motor, the rotating speed difference is kept unchanged. And updating the rotation speed difference value according to the algorithm.
And S204, judging the updated rotation speed difference, and if the rotation speed difference is smaller than zero, setting the left motor rotation speed value as the maximum motor rotation speed plus the rotation speed difference, and setting the right motor rotation speed value as the maximum motor rotation speed. Otherwise, if the rotation speed difference is larger than zero, the rotation speed of the left side motor is set as the maximum rotation speed of the motor, and the rotation speed of the right side motor is set as the maximum rotation speed of the motor minus the rotation speed difference.
S205, the raspberry pi module feeds the updated motor rotating speed value back to the motor module, and the motor module adjusts the rotating speeds of the motors on two sides according to the set value, so that the system is patrolled in a tracing mode.
And S3, receiving the audio signal of the microphone module by the raspberry pi module, and performing voice recognition.
Specifically, the method comprises the following steps:
s301, the microphone module is connected with the raspberry pi through the USB interface, and the microphone collects environmental audio signals and transmits the environmental audio signals to the raspberry pi module in real time;
s302, introducing a raspberry group module into a Snowboy awakening word monitoring engine developed by KITT.AI, processing an audio signal by utilizing a voice awakening word recognition algorithm in the engine, monitoring whether the audio signal contains a set awakening word or not, training a specific awakening word model required by a user according to the requirement of the user through an awakening word training model provided by a Snowboy official website, and replacing the required awakening word by replacing a corresponding awakening word model in the awakening word recognition algorithm;
s4, when the voice recognition is successful, the raspberry pi module outputs a control signal to the motor module, and the motor module stops rotating; if the voice recognition is not successful, repeating the steps S2 and S3.
Specifically, the method comprises the following steps:
s401, if the condition that the audio contains the set awakening word (for example, the awakening word can be set to stop) is monitored, the raspberry dispatching module sends a control signal to the motor module;
s402, after the motor module receives the signal of the raspberry pi module, the motor module stops rotating, namely the motors on the left side and the right side stop rotating, and the system stops patrolling.
And S5, starting the camera module by the raspberry group to collect and identify the human face.
Specifically, the method comprises the following steps:
s501, starting a camera module by the raspberry group, and capturing images in real time by the camera module;
s502, performing face recognition on the image by the raspberry through an LBPH face recognition algorithm in OpenCV face recognition, and simultaneously displaying an image picture and face recognition related information on a computer VNC interface;
s503, if the image captured by the camera shooting is judged as a system user, displaying the user name and the recognition confidence at the VNC end of the computer, and meanwhile, dispatching the raspberry to modify a personnel attendance information file and updating attendance information; if the user is determined to be a non-system user, "Unknown" is displayed on the VNC side of the computer.
S6, the camera module is turned off, and the raspberry group receives the audio signal of the microphone module to perform the wake word tone recognition, and when the raspberry group determines that the audio signal is the set wake word (for example, the wake word can be set to "go"), the method returns to step S2.
Specifically, the method comprises the following steps:
s601: closing the camera module at fixed time;
s602: the microphone module collects an environmental audio signal and transmits the environmental audio signal to the raspberry pi module in real time;
s603: the raspberry pi module processes the audio signal by using a voice recognition algorithm and monitors whether the audio signal contains a set awakening word;
s604, if the set awakening words are contained in the monitored audio signals, the raspberry pi module sends control signals to the motor module;
s605, the motor module receives the signal of the raspberry pi module, and the system recovers the tracing patrol.
When the equipment is in a patrol attendance mode, the raspberry pi module writes a txt file for initializing and recording equipment activities into 'start'. And the raspberry pi module updates and reads the txt file in real time, allows the motor to be started when the file is recorded as 'start', and forbids the motor to be started when the file is recorded as 'stop'. Meanwhile, the infrared tracing sensing module returns signals to the raspberry pi module for processing, and the raspberry pi module calculates the rotating speeds of the two motors through the received infrared signals and feeds the rotating speeds back to the motor module, so that the device tracing is realized. Meanwhile, the microphone module collects environmental audio in real time, the audio signal is transmitted to the raspberry group module through the USB interface, the raspberry group module uses a voice awakening word recognition algorithm to recognize and detect the audio, when an appointed awakening word is detected, stop is written in a txt file of recording equipment activity, the equipment stops running, meanwhile, a camera of the equipment is started, captured image data is transmitted to the raspberry group module to perform face recognition, the captured image is compared with a face stored in advance, if the face is recognized to be company working hours, the raspberry group module updates an employee attendance webpage file, employee card punching information is updated, a user can see the image captured by the camera at a computer end, and meanwhile, face detection and face recognition results are displayed on a computer screen to display face positions, face names and recognition confidence levels. And the camera is automatically closed 10 seconds after being opened. And if the raspberry pi module detects that the audio collected by the microphone contains the specific awakening word again, writing 'start' into the device activity txt file, and performing trace-seeking patrol work again by the device. And finishing the attendance cycle once. The user can check the attendance information of the staff through a webpage at the computer terminal.
When the security alarm function is executed, the steps are as follows:
and S1, the raspberry dispatching module receives the execution instruction and executes the security alarm function.
S2, the raspberry pi module is connected with the sound module through Bluetooth, the camera module is started to capture a face image, face recognition is conducted, and if the face image is recognized as a non-system user, the raspberry pi module sends an audio playing signal.
Specifically, the method comprises the following steps:
s201, starting a camera module by a raspberry pi module, and capturing an image in real time by the camera module;
s202, the raspberry group module performs face recognition on the image through a face recognition algorithm, and simultaneously a computer-side VNC interface displays an image picture and face recognition related information;
s203, if the captured image is judged to be a non-system user, the raspberry sending module sends a signal for executing the audio playing function to the sound module, and simultaneously sends an automatic mail alarming and reminding function to the mail sending module.
And S3, the sound module plays an alarm audio according to the signal of the raspberry pi module.
And S4, the mail sending module sends the alarm mail to the appointed mailbox according to the raspberry dispatching signal.
Specifically, the method comprises the following steps:
s401, the mail sending module sends an instruction to the mail sending module and executes an automatic mail alarm reminding function;
s402: the mail sending module is connected with the STMP server by using an STMP protocol;
s403: the mail sending module uses corresponding security protocols such as TLS and the like to log in a designated sender mailbox;
s404: and sending the corresponding mail content to a designated recipient mailbox.
When the device is in the security alarm function of strangers, the raspberry group module is connected with the sound module in a Bluetooth mode, the camera module is opened for a long time to capture pictures in real time, picture data are transmitted to the raspberry group module in real time to carry out face detection and face identification, if the faces are detected, the face identification is carried out, if the identification result is company staff, processing is not carried out, if the identification result is strangers, the raspberry group module carries out alarm audio playing through the sound, meanwhile, the automatic mail alarm reminding function is started through the mail sending module, the mail sending module sends alarm mails to an appointed mailbox, and the stranger alarm reminding function is completed.
When the intelligent obstacle avoidance and cleaning function is executed, the method comprises the following steps:
and S1, the raspberry dispatching module receives the execution instruction and executes the intelligent obstacle avoidance and cleaning function.
And S2, the raspberry pi module receives the signal of the obstacle avoidance infrared sensor module and outputs a corresponding control signal to the motor module according to the received signal.
Specifically, the method comprises the following steps:
s201: the raspberry group reads signals of the obstacle avoidance infrared sensor module in real time, obstacle information is judged, and meanwhile the motor module keeps running at a set speed.
S202: if the infrared sensor on the right side returns a barrier signal, if the infrared sensor on the right side returns 0, the fact that a barrier exists on the right side in front is judged, the raspberry sending module sends a corresponding instruction to the motor module, the motor on the left side stops rotating, and the motor on the left side is set to stop rotating for 1 second in the embodiment;
s203: if the infrared sensor on the left side returns a barrier signal, if the infrared sensor on the left side returns 0, the fact that a barrier exists on the left side in front is judged, the raspberry sending module sends a corresponding instruction to the motor module, the motor on the right side stops rotating, and the motor on the right side is set to stop rotating for 1 second in the embodiment;
s204: if the left side infrared sensor and the right side infrared sensor return barrier signals at the same time, if the barrier signals return to 0, the fact that a barrier exists right ahead is judged, the raspberry dispatching module sends a corresponding instruction to the motor module, the left side motor and the right side motor rotate reversely at the same speed for a preset time, if the time is 2 seconds, the right side motor stops rotating for a preset time, if the time is 1 second.
And S3, starting a cleaning module of the intelligent equipment system to clean the road surface.
In the running process of the equipment, the cleaning module cleans and cleans the road surface to finish intelligent obstacle avoidance and cleaning.
When the mail work and rest reminding function is executed, the method comprises the following steps:
s1, the mail sending module receives the raspberry dispatching instruction, sends the work and rest reminding mail according to the set time, and sends the work and rest reminding mail to the appointed mailbox account (such as the mailbox of the office staff), and the mail content is used for reminding the staff to have a rest properly.
Specifically, the method comprises the following steps:
s101: the mail sending module is connected with the STMP server by using an STMP protocol;
s102: the mail sending module uses corresponding security protocols such as TLS and the like to log in a designated sender mailbox;
s103: and sending the corresponding mail content to a designated recipient mailbox.
S2, when the reminding mail is sent, the raspberry pi starts the sound module to play the relaxing song, so that the staff can easily and pleasantly rest.
And S3, after a certain time, the raspberry party closes the sound module, and the mail sending module waits for the next mail sending instruction.
Through the system and the method provided by the embodiment, convenient card punching can be realized by executing the patrol attendance function, so that the attendance of staff is more convenient, the security function can be executed by acquiring the face image and identifying the face image, strangers can be automatically identified, the warning is timely realized, the security is improved, the intelligent obstacle avoidance cleaning function is executed, the obstacle information can be automatically identified by a sensor in the cleaning process, and obstacles can be avoided in time, so that the cleaning function can be automatically completed, and the staff can be timely reminded to have a rest by executing the mail work and rest reminding function.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.

Claims (7)

1. The utility model provides a multi-functional smart machine system of office based on raspberry group for realize patrol attendance function, warning security protection function, intelligence and keep away barrier clean function and mail work and rest and remind the function, include:
the raspberry pi module is used for receiving execution instructions of all functions and signals of all modules and sending out signals;
the tracing infrared sensing module is used for collecting signals and transmitting the signals to the raspberry group module;
the motor module is used for receiving the control signal sent by the raspberry pi module and starting and stopping the raspberry pi module according to the control signal;
the camera module is used for acquiring a face image;
the mail sending module is used for finishing the mail sending function;
the microphone module is used for collecting an environmental audio signal;
the sound module is used for playing an alarm audio according to the instruction of the raspberry dispatching module;
the obstacle avoidance infrared sensing module is used for acquiring obstacle signals and transmitting the signals to the raspberry group module for processing;
a cleaning module for cleaning;
when the patrol attendance function is executed, the method specifically comprises the following steps:
s1, the raspberry dispatching module receives the execution instruction, and the system executes a patrol attendance function;
s2, the raspberry pi module receives the signal of the infrared tracking sensor module and outputs a corresponding control signal to the motor module according to the received signal;
s3, simultaneously, the raspberry pi module receives the audio signal of the microphone module and performs voice recognition, and when the voice recognition is successful, the raspberry pi module outputs a control signal to the motor module, and the motor module stops rotating; if the voice recognition is unsuccessful, repeating the steps S2 and S3;
s4, starting a camera module by the raspberry pie to collect and identify the human face;
s5, the camera module is closed, meanwhile, the raspberry pi module receives the audio signal of the microphone module for voice recognition, and when the raspberry pi module judges that the audio signal is a set awakening word, the step S2 is returned;
the S2 includes the steps of:
s201, reading signals of an infrared tracing sensor module in real time by a raspberry group module, wherein the infrared tracing sensor comprises five infrared sensors which are transversely arranged, the infrared sensors detect road surface trace signals, the infrared sensors which detect the traces return first signals, the infrared sensors which do not detect the traces return second signals, and each group of infrared signals returned to the raspberry group module consists of a one-dimensional quinary array which respectively corresponds to the return value of each infrared sensor;
s202, the raspberry group module carries out weighting processing on the arrays returned by the infrared tracing sensor module, the sum of the weighted arrays is divided by the sum of unweighted arrays to obtain an absolute deviation value, and a central value is obtained based on the absolute deviation value;
s203, the raspberry pi module compares the absolute deviation value with the central value, the difference value of the absolute deviation value and the central value is called a relative deviation value, the difference value of the current relative deviation value and the previous relative deviation value is called an azimuth adjusting value, the accumulated sum value of all previous relative deviation values is called an accumulated deviation value, the value (relative deviation value/25 + azimuth adjusting value/100 + accumulated deviation value/1000) is called a rotating speed difference value, the maximum rotating speed of the motor is set, if the rotating speed difference value is larger than the maximum rotating speed of the motor, the rotating speed difference value is set as the maximum rotating speed of the motor, if the rotating speed difference value is smaller than the opposite number of the maximum rotating speed of the motor, the rotating speed difference value is set as the opposite number of the maximum rotating speed of the motor, if the absolute value of the rotating speed difference value is smaller than the maximum rotating speed of the motor, the rotating speed difference value is kept unchanged, and the rotating speed difference value is updated according to the algorithm;
s204, judging the updated rotation speed difference, setting the left motor rotation speed value as the maximum motor rotation speed plus the rotation speed difference if the rotation speed difference is smaller than zero, and setting the right motor rotation speed value as the maximum motor rotation speed, otherwise, setting the left motor rotation speed as the maximum motor rotation speed and setting the right motor rotation speed as the maximum motor rotation speed minus the rotation speed difference if the rotation speed difference is larger than zero;
s205, the raspberry pi module feeds the updated motor rotating speed value back to the motor module, and the motor module adjusts the rotating speeds of the motors on two sides according to the set value, so that the system is patrolled in a tracing mode.
2. A realization method of a raspberry pi-based office multifunctional intelligent device system is characterized by comprising the following steps:
connecting the user terminal and the raspberry group to the same local area network, and performing communication connection between the user terminal and the intelligent equipment system through a push;
the user terminal visually checks the raspberry group internal engineering file through a VNC remote control tool;
the computer executes the engineering files with corresponding functions, wherein the engineering files with corresponding functions respectively comprise engineering files with a patrol attendance function, an alarm security function, an intelligent obstacle avoidance and cleaning function and a mail work and rest reminding function;
when the patrol attendance function is executed, the specific steps are as follows:
s1, the raspberry dispatching module receives the execution instruction, and the system executes a patrol attendance function;
s2, the raspberry pi module receives the signal of the infrared tracking sensor module and outputs a corresponding control signal to the motor module according to the received signal;
s3, simultaneously, the raspberry pi module receives the audio signal of the microphone module and performs voice recognition, and when the voice recognition is successful, the raspberry pi module outputs a control signal to the motor module, and the motor module stops rotating; if the voice recognition is unsuccessful, repeating the steps S2 and S3;
s4, starting a camera module by the raspberry pie to collect and identify the human face;
s5, the camera module is closed, meanwhile, the raspberry pi module receives the audio signal of the microphone module for voice recognition, and when the raspberry pi module judges that the audio signal is a set awakening word, the step S2 is returned;
the S2 includes the steps of:
s201, reading signals of an infrared tracing sensor module in real time by a raspberry group module, wherein the infrared tracing sensor comprises five infrared sensors which are transversely arranged, the infrared sensors detect road surface trace signals, the infrared sensors which detect the traces return first signals, the infrared sensors which do not detect the traces return second signals, and each group of infrared signals returned to the raspberry group module consists of a one-dimensional quinary array which respectively corresponds to the return value of each infrared sensor;
s202, the raspberry group module carries out weighting processing on the arrays returned by the infrared tracing sensor module, the sum of the weighted arrays is divided by the sum of unweighted arrays to obtain an absolute deviation value, and a central value is obtained based on the absolute deviation value;
s203, the raspberry pi module compares the absolute deviation value with the central value, the difference value of the absolute deviation value and the central value is called a relative deviation value, the difference value of the current relative deviation value and the previous relative deviation value is called an azimuth adjusting value, the accumulated sum value of all previous relative deviation values is called an accumulated deviation value, the value (relative deviation value/25 + azimuth adjusting value/100 + accumulated deviation value/1000) is called a rotating speed difference value, the maximum rotating speed of the motor is set, if the rotating speed difference value is larger than the maximum rotating speed of the motor, the rotating speed difference value is set as the maximum rotating speed of the motor, if the rotating speed difference value is smaller than the opposite number of the maximum rotating speed of the motor, the rotating speed difference value is set as the opposite number of the maximum rotating speed of the motor, if the absolute value of the rotating speed difference value is smaller than the maximum rotating speed of the motor, the rotating speed difference value is kept unchanged, and the rotating speed difference value is updated according to the algorithm;
s204, judging the updated rotation speed difference, setting the left motor rotation speed value as the maximum motor rotation speed plus the rotation speed difference if the rotation speed difference is smaller than zero, and setting the right motor rotation speed value as the maximum motor rotation speed, otherwise, setting the left motor rotation speed as the maximum motor rotation speed and setting the right motor rotation speed as the maximum motor rotation speed minus the rotation speed difference if the rotation speed difference is larger than zero;
s205, the raspberry pi module feeds the updated motor rotating speed value back to the motor module, and the motor module adjusts the rotating speeds of the motors on two sides according to the set value, so that the system is patrolled in a tracing mode.
3. The method for implementing a raspberry pi based office multifunctional intelligent device system as claimed in claim 2, wherein said S3 includes the following steps:
s301, the microphone module is connected with the raspberry pi module through a USB interface, collects environmental audio signals and transmits the environmental audio signals to the raspberry pi module in real time;
s302, the raspberry pi module processes the audio signal by using a voice awakening word recognition algorithm and monitors whether the audio signal contains a set awakening word;
s303, if the set awakening words are contained in the monitored audio, the raspberry pi module sends a control signal to the motor module;
s304, the motor module receives a signal of the raspberry pi module, the motor module stops rotating, and the system stops patrolling.
4. The method for implementing a raspberry pi based office multifunctional intelligent device system as claimed in claim 2, wherein said S4 includes the following steps:
s401, starting a camera module by a raspberry group module, and capturing an image in real time by the camera module;
s402, the raspberry pi module performs face recognition on the image through a face recognition algorithm, and simultaneously a VNC interface of the user terminal displays an image picture and face recognition related information;
and S403, if the captured image is judged as a system user, displaying the user name and the recognition confidence at the VNC end of the user terminal, and simultaneously modifying the personnel attendance information file by the raspberry dispatching module and updating the attendance information.
5. The method for implementing the raspberry pi based office multifunctional intelligent device system according to claim 2, wherein when the security alarm function is executed, the steps are as follows:
s1, the raspberry dispatching module receives the execution instruction and executes the security alarm function;
s2, the raspberry pi module is connected with the sound module through Bluetooth, meanwhile, the camera module is started to capture a face image, face recognition is conducted, and if the face image is recognized as a non-system user, the raspberry pi module sends an audio playing signal;
s3, the sound module plays an alarm audio according to the signal of the raspberry pi module;
and S4, the mail sending module sends the alarm mail to a specific mailbox.
6. The method for implementing the raspberry pi based office multifunctional intelligent device system as claimed in claim 2, wherein when the intelligent obstacle avoidance and cleaning function is executed, the method comprises the following steps:
s1, the raspberry dispatching module receives an execution instruction and executes an intelligent obstacle avoidance and cleaning function;
s2, the raspberry pi module receives the signal of the obstacle avoidance infrared sensor module and outputs a corresponding control signal to the motor module according to the received signal;
and S3, starting a cleaning module of the intelligent equipment system to clean the road surface.
7. The method for implementing the raspberry pi based office multifunctional intelligent device system as claimed in claim 2, wherein when the mail work and rest reminding function is executed, the method comprises the following steps:
s1, the mail sending module receives the raspberry sending module instruction, sends a work and rest reminding mail according to the set time and sends the work and rest reminding mail to the designated mailbox account;
s2, when the reminding mail is sent, the raspberry pie starts the sound module to play the song;
and S3, after the playing reaches the preset time, the raspberry party closes the sound module, and the mail sending module waits for the next mail sending instruction.
CN202011046218.2A 2020-09-29 2020-09-29 Method and system for realizing office multifunctional intelligent equipment based on raspberry group Active CN112258680B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011046218.2A CN112258680B (en) 2020-09-29 2020-09-29 Method and system for realizing office multifunctional intelligent equipment based on raspberry group

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011046218.2A CN112258680B (en) 2020-09-29 2020-09-29 Method and system for realizing office multifunctional intelligent equipment based on raspberry group

Publications (2)

Publication Number Publication Date
CN112258680A CN112258680A (en) 2021-01-22
CN112258680B true CN112258680B (en) 2021-12-21

Family

ID=74234928

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011046218.2A Active CN112258680B (en) 2020-09-29 2020-09-29 Method and system for realizing office multifunctional intelligent equipment based on raspberry group

Country Status (1)

Country Link
CN (1) CN112258680B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113915449B (en) * 2021-10-22 2023-01-17 安庆师范大学 Robot system and method suitable for detecting defects of inner wall of pipeline
CN115410325B (en) * 2022-11-01 2023-01-31 湖南文宏电子科技有限公司 Security protection system of patrolling and defending based on unmanned aerial vehicle

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050063543A (en) * 2003-12-22 2005-06-28 엘지전자 주식회사 Position confirmation apparatus and method for mobile robot
CN103324199A (en) * 2013-07-10 2013-09-25 贵州大学 Intelligent tracing trolley
CN105856260A (en) * 2016-06-24 2016-08-17 深圳市鑫益嘉科技股份有限公司 On-call robot
CN107316184A (en) * 2017-07-10 2017-11-03 三峡大学 Based on the interactive office assistant of distributed cloud and operating method
CN108537910A (en) * 2018-04-13 2018-09-14 上海思依暄机器人科技股份有限公司 A kind of employee work attendance method, device and Work attendance management system based on recognition of face
CN109514566A (en) * 2018-11-07 2019-03-26 杭州电子科技大学 A kind of intelligent monitoring machine people based on raspberry pie
CN109753074A (en) * 2019-01-28 2019-05-14 北京猎户星空科技有限公司 A kind of robot cruise control method, device, control equipment and storage medium

Also Published As

Publication number Publication date
CN112258680A (en) 2021-01-22

Similar Documents

Publication Publication Date Title
CN112258680B (en) Method and system for realizing office multifunctional intelligent equipment based on raspberry group
CN103281223B (en) A kind of modern intelligent household security system
US10997430B1 (en) Dangerous driver detection and response system
CN107454364B (en) Distributed real-time image acquisition and processing system in video monitoring field
CN104330985B (en) Information processing method and device
US11200435B1 (en) Property video surveillance from a vehicle
CN102055859A (en) Monitoring method for handheld school message system and monitoring equipment thereof
US11935297B2 (en) Item monitoring for doorbell cameras
CN108762172A (en) A kind of cruising inspection system of dispatching automation computer room robot
EP3999967B1 (en) Notifications for camera tampering
AU2023248156A1 (en) Arrival detection for battery-powered optical sensors
WO2023060056A2 (en) Spatial motion attention for intelligent video analytics
US20220147749A1 (en) Adversarial masks for scene-customized false detection removal
CN113554794A (en) Community permanent user and visitor access management system based on intelligent property
CN111445592A (en) Teaching attendance system for teaching management
US20240070932A1 (en) Method for detecting and visualizing objects within a space
US20220394315A1 (en) Recording video quality
CN217238835U (en) Low-power access control monitoring system based on Internet of things
US20240021067A1 (en) Consolidation of alerts based on correlations
US20240046485A1 (en) Real-motion prediction
CN212675424U (en) Smart city facility operation and maintenance guard
CN203219425U (en) Image security monitoring system based on wireless internet
US20230011337A1 (en) Progressive deep metric learning
CN112396996B (en) Multifunctional control system for sand table demonstration
CN220913571U (en) Intelligent terminal for intelligent campus online examination

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