CN111597999A - 4S shop sales service management method and system based on video detection - Google Patents
4S shop sales service management method and system based on video detection Download PDFInfo
- Publication number
- CN111597999A CN111597999A CN202010419216.7A CN202010419216A CN111597999A CN 111597999 A CN111597999 A CN 111597999A CN 202010419216 A CN202010419216 A CN 202010419216A CN 111597999 A CN111597999 A CN 111597999A
- Authority
- CN
- China
- Prior art keywords
- customer
- sales
- face
- store
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 60
- 238000001514 detection method Methods 0.000 title claims abstract description 57
- 238000012545 processing Methods 0.000 claims abstract description 32
- 230000006399 behavior Effects 0.000 claims description 54
- 238000012360 testing method Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 17
- 230000003993 interaction Effects 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 238000013145 classification model Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 description 6
- 238000002372 labelling Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000005034 decoration Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
Abstract
The invention relates to a 4S shop sales service management method and system based on video detection, which comprises a front-end high-speed acquisition module, a front-end high-speed acquisition module and a front-end high-speed acquisition module, wherein the front-end high-speed acquisition module acquires image data by utilizing a multi-path FPGA and a 4S shop face camera; the back-end image processing module adopts a face recognition technology to confirm the identity of a customer, track the track of the customer and track the service condition of sales personnel; the sales management module analyzes the requirements and the sales service management conditions of the 4S store; the message subscription and distribution module receives a 4S store message subscription request, can confirm store customer identity information at the first time, track customer requirements based on video detection, and track service conditions of sales personnel, can feed back relevant information of customers and store sales service management conditions in real time, manages store sales services, further helps the sales personnel to analyze customer requirements, provides accurate services, and promotes improvement of service quality and refinement of management of 4S stores.
Description
Technical Field
The invention relates to the technical field of video monitoring, analyzing and processing, in particular to a 4S shop sales service management method and system based on video detection.
Background
The remote video monitoring is widely applied to various scenes such as traffic, buildings, security, markets and the like, and the face recognition technology further expands and refines the application scenes of the video monitoring, such as entrance guard management, identity management of electronic equipment and mobile application, mobile payment, authority management of intelligent household equipment, security check identity verification and the like. Face recognition has become a hotspot of monitoring video analysis application, but is mainly focused on security and protection scenes and financial payment scenes in which individual identities need to be confirmed, and customized services for recognizing individual faces are few.
A large number of cameras are widely distributed in a sales service scene of a 4S store, are mainly used for remote monitoring and theft prevention, and cannot play a role when the camera leaves monitoring personnel. The products in the 4S store have large display fields, but the products which can be contained are still limited, and in addition, the technical content of the products is high, the configuration is complex, the transaction is highly dependent on the quality of the sales service, namely, the transaction is highly dependent on the spontaneity and the psychological game ability of the sales personnel, and the case that the order is lost due to the insufficient sales service exists.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: in order to overcome the defects in the prior art, a 4S shop sales service management method and system based on video detection are provided, identity information of a shop customer can be confirmed at the first time, a commodity browsing track of the customer can be tracked, and the service condition of sales staff can be tracked, so that the sales staff can be helped to analyze the customer requirements and provide accurate service.
The technical scheme adopted by the invention for solving the technical problems is as follows: A4S shop sales service management method based on video detection comprises the following steps:
the first step is as follows: collecting 4S shop face images and moving images: the face image is the face image data of each 4S store visiting customer and sales service personnel, and the moving image is an image in the process of browsing and consulting the goods by the 4S store visiting customer;
further: when the face images and the moving images of the 4S stores are collected, the face images and the moving images are collected through a plurality of paths of face cameras installed in the 4S stores, then the images of the 4S stores are collected and uploaded through a plurality of paths of FPGA high-speed collecting units, the plurality of paths of FPGA high-speed collecting units are achieved through an AI algorithm model trained through a public face data set, and high-precision face images are collected.
Further: the installation of people's face camera is in order to be favorable to taking a candid photograph customer face image as the criterion adjustment camera angle.
And secondly, confirming the identities of the customers and the salesmen, and tracking the behaviors of the customers and the salesmen: after the face image and the moving image are read, analyzing and confirming the identities of a customer and a salesperson, and tracking the behaviors of the customer and the salesperson;
further: when confirming the identity of a customer and tracking the behavior of the customer, a multitask processing mode is started by utilizing a message queue asynchronous framework, and multitask comprises the following steps:
image preprocessing task: the image preprocessing task adopts an MTCNN (multiple-input multiple-output) network of an open source machine learning algorithm library TensorFlow to carry out image alignment processing on the read face image and the read moving image;
a face feature recognition task: the face feature recognition task adopts a Facenet network of TensorFlow to extract a face feature matrix from the aligned images;
face identification task: the face identity recognition task is to compare the obtained face feature matrix with a face model base, determine the identities of customers and salesmen, output and mark the customers and salesmen, and store the determined new customers into the face model base; further, the face model base comprises information which is established in advance and information which is stored in a later period, the information which is established in advance in a labeling mode, and face photos are extracted and stored in the model base when 4S shop salesmen register; the later-stage storage information is that the identity of a customer detected in real time by a 4S store is determined by a mode of combining network screening and labeling of a salesperson, and the face information is automatically stored in the face model library after the identity is confirmed.
And (3) vehicle detection tasks: the method comprises the following steps that a vehicle detection task is to identify a vehicle and a vehicle type in an input image, the input image is to identify the residual part of an image marked with a human face, a target vehicle is detected and cut out through a detector trained in advance based on a vehicle type in a TensorFlow detection image, then a classification model is used for classification detection and identification of the vehicle type, and finally a vehicle type detection result is used as a vehicle mark; further, the task unit is realized by Slim classification and Object Detection.
And (3) behavior recognition task: the behavior recognition task is to detect commodity browsing tracks of customers and interaction relations between the customers and sales personnel, train two behavior relation detection models of 'customer-vehicle type' and 'customer-sales personnel' in advance, input images marked with human faces and vehicle types into the detection models, and detect external browsing, test driving and vehicle lifting behaviors of the customers on certain vehicle types through the detection models; detecting the conversation and action after the customer meets the sales staff and outputting the detection result;
tracking a customer track task: the task of tracking the track of the customer is to arrange and output the commodity browsing track of the customer and the interaction relationship between the customer and the salesperson by using the result output by the behavior recognition unit; further, the customer trajectory includes: the time that the customer browses a certain vehicle model, the time that the salesperson is consulted with a certain vehicle model, the time that the salesperson is consulted, the time that the customer stays in a certain 4S shop, the type and the time of the test-driving vehicle.
Thirdly, analyzing the requirements of customers and the conditions of sales service: reading the confirmed customer identity and the tracked customer behavior, analyzing and tracking the customer demand, and forming a customer demand report; reading the confirmed identity of the salesperson and the tracked behavior of the salesperson, analyzing the service condition of the salesperson, and forming a sales report of a 4S shop;
further: when customer requirements and sales services are analyzed, reading face identity recognition task data, behavior recognition task data and tracking customer track task data, and respectively analyzing the customer requirements and the sales services by the system; when customer needs are analyzed, the system collects all relevant information of the same customer, analyzes the needs and forms a report, and the relevant information comprises: the identity of the customer, the visited 4S store and the position and date thereof, the type and time of the browsed vehicle, the service time of the salesman and the type and time of the test-driven vehicle; when the sales service is analyzed, aiming at each 4S store, the activity information of each salesman is collected, the sales service characteristics of the whole 4S store are analyzed, and a report is formed, wherein the activity information comprises: the service condition of the salesperson is evaluated according to the service condition of the customer, the vehicle type and the service duration browsed by the accompanying person, the driving test duration of the accompanying person, whether the identity and the contact of the customer are obtained in time or not, whether the service information of the customer at each time is reported in time or not.
Reading the customer demand and the sales service condition: receiving a message subscription request of field salesmen and extracting a client demand report, and feeding back relevant information of a client; and receiving a message subscription request of the 4S store, extracting a sales report of the 4S store from the sales management module, and feeding the sales report back to the 4S store.
Further: when the 4S store detects that the customer visits for the first time, a prompt is sent to the store in time, and the salesperson can provide service in time; 4S stores or sales personnel can subscribe all information of the customer to the system, the information comes from a customer demand report, and the sales personnel are helped to accurately make sales countermeasures and improve the service quality; the 4S store can subscribe the system for the relevant information of the sales service situation of the store, and the information is derived from the sales report of the 4S store.
In order to implement the method of the invention, the application provides a 4S shop sales service management system based on video detection, which includes:
the front-end high-speed acquisition module: the face capturing device is used for capturing, collecting and uploading 4S shop face images and moving images;
a back-end image processing module: the system is used for receiving the face images and the moving images collected in the front-end high-speed acquisition module, confirming the identities of customers and salesmen and tracking the behaviors of the customers and the salesmen;
the sales management module: the client terminal is used for receiving the customer identity and the tracked customer behavior output by the back-end image processing module, analyzing the customer demand and forming a customer demand report; receiving the identity of the salesperson and the tracked behavior of the salesperson output by the rear-end image processing module, analyzing the sales service condition, and forming a sales report of the 4S shop;
the message subscription and distribution module: and the system is used for receiving the subscriber order message, extracting the customer demand report and the 4S shop sales report from the sales management module and feeding back the customer demand report and the 4S shop sales report.
Furthermore, the high-speed collection module of front end includes the high-speed collection unit of people ' S face camera and multichannel FPGA, the people ' S face camera is installed in 4S shop for gather face image and motion image, the high-speed collection unit of multichannel FPGA and people ' S face camera signal connection for gather each 4S shop face image and motion image simultaneously, and upload to rear end image processing module.
Further, the back-end image processing module includes:
an image preprocessing unit: the system comprises a face image acquisition module, a motion image acquisition module and a display module, wherein the face image acquisition module is used for acquiring a face image and a motion image and carrying out image alignment processing on the face image and the motion image;
a face feature recognition unit: extracting a face feature matrix from the aligned face image and the moving image;
a face identity recognition unit: the face feature matrix is used for comparing the obtained face feature matrix with a face model library, determining the identities of a customer and a salesperson, outputting and marking the customer and the salesperson, and storing the determined new customer into the face model library;
a vehicle detection unit: the face recognition method is used for recognizing the vehicles and the vehicle types in the rest part of the image marked with the faces, and the vehicles are not marked;
a behavior recognition unit: the system comprises a commodity browsing device, a commodity browsing system and a control device, wherein the commodity browsing device is used for detecting a commodity browsing track of a customer and an interaction relationship between the customer and a salesperson;
a tracking customer trajectory unit: and the behavior recognition unit is used for receiving the results output by the behavior recognition unit and arranging and outputting the commodity browsing of the customer and the interaction relationship between the customer and the salesperson.
Further: the sales management module is developed based on python and comprises:
customer demand analysis unit: the face identity recognition unit is used for receiving the identity of the customer determined by the face identity recognition unit, extracting the commodity browsing track of the customer sorted out by the track tracking unit, analyzing the demand of the customer and forming a customer demand report; the commodity browsing track of the customer is extracted and managed by the customer track tracking unit, the full-flow visiting information arranged according to the time sequence is extracted for each customer, the position of a shop visited by the customer and the brand preference of the customer are extracted, the commodity requirements of the customer are predicted according to the time length of the customer browsing all the vehicle types in the price, the appearance style, the interior decoration grade and the behavior track of the customer browsed vehicle types, and the trial driving condition, so that a customer requirement report is formed.
Salesperson service analysis unit: the face identity recognition unit is used for receiving the identity of the salesperson determined by the face identity recognition unit, extracting the interaction relationship between the customer and the salesperson sorted out by the customer track tracking unit, analyzing the sales service condition and forming a sales report of the 4S store. Extracting the full-flow sales service information arranged by each salesman according to the time sequence, and calculating and acquiring the daily average reception rate (the average number of customers to be received each day), the reception duration of each vehicle type, the reception duration of each time, the total test driving rate (the number of test driving times/the total number of reception times of all vehicle types), the vehicle type reception rate (the number of specific test vehicle types/the total number of reception times of specific vehicle types), and the arrival and departure time of the salesman through the flow information; aiming at the same 4S store, the number of store-arriving customers, the visit duration of the customers, the test driving rate, the number of sales personnel and the time of the sales personnel going to and going from work are collected to form a 4S store sales report.
Further: the message subscription and distribution module is developed based on python and comprises the following steps:
customer arrival reminding unit: the face feature recognition unit is used for receiving first store-arriving customer information sent by the face feature recognition unit and sending prompt information; when finding a customer visiting the 4S shop for the first time, the face recognition unit automatically sends prompt information to the customer arrival reminding unit, and the 4S shop provides service for the customer in time according to the prompt.
Customer demand report subscribing unit: the system comprises a sales management module, a data processing module and a data processing module, wherein the sales management module is used for receiving a subscription message of a subscriber to a customer and extracting a customer demand report from the sales management module; the 4S store may apply for subscription to a demand report from any customer, the report originating from the customer demand analysis unit of the sales management module.
A sales service report subscription unit: for receiving the order message of the subscriber to the salesperson and extracting the 4S shop sales report from the sales management module. The 4S store can apply for subscribing the sales service condition report of any salesman in the store, and the report is from the salesman service analysis unit of the sales management module. The 4S store can apply for the sales service report of the store and report the salesman service analysis unit from the sales management module.
The invention has the beneficial effects that the 4S shop sales service management method and the system based on video detection comprise a front-end high-speed acquisition module, a front-end high-speed acquisition module and a front-end high-speed acquisition module, wherein the front-end high-speed acquisition module acquires image data by utilizing a multi-path FPGA and a 4S shop face camera; the back-end image processing module adopts a face recognition technology to confirm the identity of a customer, track the track of the customer and track the service condition of sales personnel; the sales management module analyzes the requirements and the sales service management conditions of the 4S store; the message subscription and distribution module receives a 4S store message subscription request, can confirm store customer identity information at the first time, track customer requirements based on video detection, and track service conditions of sales personnel, can feed back relevant information of customers and store sales service management conditions in real time, manages store sales services, further helps the sales personnel to analyze customer requirements, provides accurate services, and promotes improvement of service quality and refinement of management of 4S stores.
Drawings
The invention is further illustrated with reference to the following figures and examples.
FIG. 1 is a schematic view of example 1 of the present invention;
FIG. 2 is a schematic view of example 2 of the present invention.
Detailed Description
The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic views illustrating only the basic structure of the present invention in a schematic manner, and thus show only the constitution related to the present invention.
Example 1:
as shown in fig. 1, a 4S shop sales service management system based on video detection includes a front-end high-speed acquisition module, a back-end image processing module, a sales management module, and a message subscription and distribution module:
the front-end high-speed acquisition module is used for capturing, collecting and uploading 4S shop face images and moving images; the front-end high-speed acquisition module comprises a face camera and a multi-path FPGA high-speed acquisition unit, the face camera is installed in a 4S shop and used for acquiring face images and moving images, and the multi-path FPGA high-speed acquisition unit is in signal connection with the face camera and used for acquiring the face images and the moving images of the 4S shops simultaneously and uploading the face images and the moving images to the rear-end image processing module.
The back-end image processing module is used for receiving the face images and the moving images collected by the front-end high-speed acquisition module, confirming the identities of the customers and the salesmen and tracking the behaviors of the customers and the salesmen; the rear-end image processing module comprises an image preprocessing unit, a face feature recognition unit, a face identity recognition unit, a vehicle detection unit and a behavior recognition unit:
the image preprocessing unit is used for receiving the face image and the moving image, performing image alignment processing on the face image and the moving image and tracking a customer track unit;
the face feature recognition unit is used for extracting a face feature matrix from the aligned face image and the aligned moving image;
the face identity recognition unit is used for comparing the obtained face feature matrix with a face model library, determining the identities of the customer and the salesperson, outputting and marking the customer and the salesperson, and storing the determined new customer into the face model library;
the vehicle detection unit is used for identifying the vehicle and the vehicle type in the image residual part marked with the human face and does not mark the vehicle;
the behavior recognition unit is used for detecting the commodity browsing track of the customer and the interaction relationship between the customer and the salesperson;
and the customer track tracking unit is used for receiving the result output by the behavior recognition unit and arranging and outputting the commodity browsing track of the customer and the interaction relationship between the customer and the salesperson.
The sales management module is used for receiving the customer identity and the tracked customer behavior output by the back-end image processing module, analyzing the customer demand and forming a customer demand report; receiving the identity of the salesperson and the tracked behavior of the salesperson output by the rear-end image processing module, analyzing the sales service condition, and forming a sales report of the 4S shop; the sales management module is developed based on Python (Python is a cross-platform computer programming language, which is a high-level scripting language combining interpretability, compilability, interactivity and object-oriented), and comprises a customer demand analysis unit and a salesperson service analysis unit:
the customer demand analysis unit is used for receiving the customer identity determined by the face identity recognition unit, extracting the commodity browsing track of the customer sorted by the customer track tracking unit, analyzing the customer demand and forming a customer demand report; the commodity browsing track of the customer is extracted and managed by the customer track tracking unit, the full-flow visiting information arranged according to the time sequence is extracted for each customer, the position of a shop visited by the customer and the brand preference of the customer are extracted, the commodity requirements of the customer are predicted according to the time length of the customer browsing all the vehicle types in the price, the appearance style, the interior decoration grade and the behavior track of the customer browsed vehicle types, and the trial driving condition, so that a customer requirement report is formed.
The salesman service analysis unit is used for receiving the salesman identity determined by the face identity recognition unit, extracting the interaction relationship between the customer and the salesman, which is sorted out by the customer track tracking unit, and analyzing the sales service condition to form a sales report of the 4S store. Extracting the full-flow sales service information arranged by each salesman according to the time sequence, and calculating and acquiring the daily average reception rate (the average number of customers to be received each day), the reception duration of each vehicle type, the reception duration of each time, the total test driving rate (the number of test driving times/the total number of reception times of all vehicle types), the vehicle type reception rate (the number of specific test vehicle types/the total number of reception times of specific vehicle types), and the arrival and departure time of the salesman through the flow information; aiming at the same 4S store, the number of store-arriving customers, the visit duration of the customers, the test driving rate, the number of sales personnel and the time of the sales personnel going to and going from work are collected to form a 4S store sales report.
The message subscription and distribution module is used for receiving the subscription message of the subscriber, extracting the customer demand report and the 4S shop sales report from the sales management module and feeding back the customer demand report and the 4S shop sales report. The message subscription and distribution module is developed based on Python (Python is a cross-platform computer programming language, is a high-level scripting language combining interpretability, compilability, interactivity and object-oriented), and comprises a customer-to-store reminding unit, a customer demand report subscription unit and a sales service report subscription unit:
the customer arrival reminding unit is used for receiving the first arrival customer information sent by the face feature recognition unit and sending prompt information; when finding a customer visiting the 4S shop for the first time, the face recognition unit automatically sends prompt information to the customer arrival reminding unit, and the 4S shop provides service for the customer in time according to the prompt.
The customer demand report subscribing unit is used for receiving a subscription message of a subscriber to a customer and extracting a customer demand report from the sales management module; the 4S store may apply for subscription to a demand report from any customer, the report originating from the customer demand analysis unit of the sales management module.
The sales service report subscription unit is used for receiving the subscription information of the subscriber to the salesperson and extracting the sales report of the 4S store from the sales management module. The 4S store can apply for subscribing the sales service condition report of any salesman in the store, and the report is from the salesman service analysis unit of the sales management module. The 4S store can apply for the sales service report of the store and report the salesman service analysis unit from the sales management module.
Example 2:
a 4S shop sales service management method based on video detection as shown in fig. 2 includes the following steps:
the first step is as follows: collecting 4S shop face images and moving images: the face image is the face image data of each 4S store visiting customer and sales service personnel, and the moving image is an image in the process of browsing and consulting the goods by the 4S store visiting customer; when the face images and the moving images of the 4S stores are collected, the face images and the moving images are collected through a plurality of paths of face cameras installed in the 4S stores, then the images of the 4S stores are collected and uploaded through a plurality of paths of FPGA high-speed collecting units, the plurality of paths of FPGA high-speed collecting units are achieved through an AI algorithm model trained through a public face data set, and high-precision face images are collected. The installation of the face camera is beneficial to taking the face image of the customer as a criterion to adjust the angle of the camera; FPGA (field Programmable Gate array) is a product of further development on the basis of Programmable devices such as PAL, GAL, etc. The circuit is a semi-custom circuit in the field of Application Specific Integrated Circuits (ASIC), not only overcomes the defects of the custom circuit, but also overcomes the defect that the number of gate circuits of the original programmable device is limited.
And secondly, confirming the identities of the customers and the salesmen, and tracking the behaviors of the customers and the salesmen: after the face image and the moving image are read, analyzing and confirming the identities of a customer and a salesperson, and tracking the behaviors of the customer and the salesperson;
when confirming the identity of a customer and tracking the behavior of the customer, a multitask processing mode is started by utilizing a message queue asynchronous framework, and multitask comprises the following steps:
image preprocessing task: the image preprocessing task adopts an MTCNN (multiple-input multiple-output) network of an open source machine learning algorithm library TensorFlow to carry out image alignment processing on the read face image and the read moving image; MTCNN, Multi-task connected neural network, puts face region detection together with face keypoint detection, whose topic framework is similar to cascade. The population can be divided into three-layer network structures of P-Net, R-Net, and O-Net. TensorflowTMIs a symbolic mathematical system based on data flow programming, is widely applied to programming realization of various machine learning (machine learning) algorithms, and the predecessor of the symbolic mathematical system is a neural network algorithm library DistBelef [1 ] of Google]。
A face feature recognition task: the face feature recognition task adopts a Facenet network of TensorFlow to extract a face feature matrix from the aligned images; facenet by TensorFlow is a TensorFlow-based face recognition technique, TensorFlowTMIs a symbolic mathematical system based on data flow programming, is widely applied to programming realization of various machine learning (machine learning) algorithms, and the predecessor of the symbolic mathematical system is a neural network algorithm library DistBelef [1 ] of Google]。
Face identification task: the face identity recognition task is to compare the obtained face feature matrix with a face model base, determine the identities of customers and salesmen, output and mark the customers and salesmen, and store the determined new customers into the face model base; further, the face model base comprises information which is established in advance and information which is stored in a later period, the information which is established in advance in a labeling mode, and face photos are extracted and stored in the model base when 4S shop salesmen register; the later-stage storage information is that the identity of a customer detected in real time by a 4S store is determined by a mode of combining network screening and labeling of a salesperson, and the face information is automatically stored in the face model library after the identity is confirmed.
And (3) vehicle detection tasks: the method comprises the following steps that a vehicle detection task is to identify a vehicle and a vehicle type in an input image, the input image is to identify the residual part of an image marked with a human face, a target vehicle is detected and cut out through a detector trained in advance based on a vehicle type in a TensorFlow detection image, then a classification model is used for classification detection and identification of the vehicle type, and finally a vehicle type detection result is used as a vehicle mark; further, the task unit is realized by Slim classification and Object Detection; Tensorflow-Slim image classification model library.
And (3) behavior recognition task: the behavior recognition task is to detect commodity browsing tracks of customers and interaction relations between the customers and sales personnel, train two behavior relation detection models of 'customer-vehicle type' and 'customer-sales personnel' in advance, input images marked with human faces and vehicle types into the detection models, and detect external browsing, test driving and vehicle lifting behaviors of the customers on certain vehicle types through the detection models; detecting the conversation and action after the customer meets the sales staff and outputting the detection result;
tracking a customer track task: the task of tracking the track of the customer is to arrange and output the commodity browsing of the customer and the interaction relationship between the customer and the salesperson by using the result output by the behavior recognition unit; further, the customer trajectory includes: the time that the customer browses a certain vehicle model, the time that the salesperson is consulted with a certain vehicle model, the time that the salesperson is consulted, the time that the customer stays in a certain 4S shop, the type and the time of the test-driving vehicle.
Thirdly, analyzing the requirements of customers and the conditions of sales service: reading the confirmed customer identity and the tracked customer behavior, analyzing and tracking the customer demand, and forming a customer demand report; reading the confirmed identity of the salesperson and the tracked behavior of the salesperson, analyzing the service condition of the salesperson, and forming a sales report of a 4S shop; when customer requirements and sales services are analyzed, reading face identity recognition task data, behavior recognition task data and tracking customer track task data, and respectively analyzing the customer requirements and the sales services by the system; when customer needs are analyzed, the customer need analysis unit collects all relevant information of the same customer, analyzes the needs and forms a report, and the relevant information comprises: the identity of the customer, the visited 4S store and the position and date thereof, the type and time of the browsed vehicle, the service time of the salesman and the type and time of the test-driven vehicle; each customer extracts the shop position and the vehicle type visited by the customer according to the full-flow visiting information arranged in time sequence to predict the brand hobbies of the customer, and the commodity requirements of the customer are predicted according to the time length of the customer browsing all vehicle types in the price, appearance style, interior decoration grade and behavior track of the customer browsed vehicle types and the test driving condition to form a customer requirement report; when the sales service is analyzed, the salesperson service analysis unit collects the activity information of each salesperson for each 4S store, analyzes the sales service characteristics of the whole 4S store and forms a report, and the activity information includes: the service condition of the salesperson is evaluated according to the service condition of the customer, the vehicle type and the service duration browsed by the accompanying person, the driving test duration of the accompanying person, whether the identity and the contact of the customer are obtained in time or not, whether the service information of the customer at each time is reported in time or not.
Reading the customer demand and the sales service condition: the customer demand report subscribing unit receives a message subscribing request of a field salesman and feeds back relevant information of the customer after extracting a customer demand report; the sales service report subscription unit receives a message subscription request of the 4S store, extracts a sales report of the 4S store from the sales management module, and feeds the sales report back to the 4S store. When the 4S store detects that a customer visits for the first time, a prompt is sent to the store in time, the customer arrival prompt unit receives the first arrival store customer information sent by the face feature recognition unit, and the salesperson can provide service in time; 4S stores or sales personnel can subscribe all information of the customer to the system, the information comes from a customer demand report, and the sales personnel are helped to accurately make sales countermeasures and improve the service quality; the 4S store can subscribe the system for the relevant information of the sales service situation of the store, and the information is derived from the sales report of the 4S store.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (10)
1. A4S shop sales service management method based on video detection is characterized in that: the method comprises the following steps:
s01, collecting 4S store face images and moving images: the face image is the face image data of each 4S store visiting customer and sales service personnel, and the moving image is the image of the 4S store visiting customer in the process of browsing and consulting the goods
Confirming the identity of the customer and the salesperson, tracking the behavior of the customer and the salesperson, S02: after the face image and the moving image are read, analyzing and confirming the identities of a customer and a salesperson, and tracking the behaviors of the customer and the salesperson;
s03, analyzing the requirements of the customers and the conditions of the sales service: reading the confirmed customer identity and the tracked customer behavior, analyzing and tracking the customer demand, and forming a customer demand report; reading the confirmed identity of the salesperson and the tracked behavior of the salesperson, analyzing the service condition of the salesperson, and forming a sales report of a 4S shop;
reading of customer demand and sales service conditions S04: receiving a message subscription request of field salesmen and extracting a client demand report, and feeding back relevant information of a client; and receiving a message subscription request of the 4S store, extracting a sales report of the 4S store from the sales management module, and feeding the sales report back to the 4S store.
2. The 4S shop sales service management method based on video detection according to claim 1, wherein: in step S01, when collecting the face images and the moving images of the 4S stores, the face images and the moving images are collected by a plurality of paths of face cameras installed in the 4S stores, and then the images of the 4S stores are collected and uploaded at the same time by a plurality of paths of FPGA high-speed collection units, which are realized by an AI algorithm model trained by a public face data set, to collect high-precision face images.
3. The 4S shop sales service management method based on video detection according to claim 2, wherein: in step S02, when confirming the identity of the customer and tracking the behavior of the customer, a multitask processing mode is started using the message queue asynchronous architecture, and the multitask includes:
image preprocessing task: the image preprocessing task adopts an MTCNN (multiple-input multiple-output) network of an open source machine learning algorithm library TensorFlow to carry out image alignment processing on the read face image and the read moving image;
a face feature recognition task: the face feature recognition task adopts a Facenet network of TensorFlow to extract a face feature matrix from the aligned images;
face identification task: the face identity recognition task is to compare the obtained face feature matrix with a face model base, determine the identities of customers and salesmen, output and mark the customers and salesmen, and store the determined new customers into the face model base;
and (3) vehicle detection tasks: the method comprises the following steps that a vehicle detection task is to identify a vehicle and a vehicle type in an input image, the input image is to identify the residual part of an image marked with a human face, a target vehicle is detected and cut out through a detector trained in advance based on a vehicle type in a TensorFlow detection image, then a classification model is used for classification detection and identification of the vehicle type, and finally a vehicle type detection result is used as a vehicle mark;
and (3) behavior recognition task: the behavior recognition task is to detect commodity browsing tracks of customers and interaction relations between the customers and sales personnel, train two behavior relation detection models of 'customer-vehicle type' and 'customer-sales personnel' in advance, input images marked with human faces and vehicle types into the detection models, and detect external browsing, test driving and vehicle lifting behaviors of the customers on certain vehicle types through the detection models; detecting the conversation and action after the customer meets the sales staff and outputting the detection result;
tracking a customer track task: the task of tracking the customer track is to arrange and output commodity browsing of the customer and an interaction relationship between the customer and a salesperson by using a result output by the behavior recognition unit.
4. The 4S shop sales service management method based on video detection according to claim 3, wherein: in step S03, when customer needs and sales services are analyzed, face identification task data, behavior identification task data and customer track task data are read, and the system respectively analyzes the customer needs and the sales services; when customer needs are analyzed, the system collects all relevant information of the same customer, analyzes the needs and forms a report, and the relevant information comprises: the identity of the customer, the visited 4S store and the position and date thereof, the type and time of the browsed vehicle, the service time of the salesman and the type and time of the test-driven vehicle; when the sales service is analyzed, aiming at each 4S store, the activity information of each salesman is collected, the sales service characteristics of the whole 4S store are analyzed, and a report is formed, wherein the activity information comprises: the service condition of the salesperson is evaluated according to the service condition of the customer, the vehicle type and the service duration browsed by the accompanying person, the driving test duration of the accompanying person, whether the identity and the contact of the customer are obtained in time or not, whether the service information of the customer at each time is reported in time or not.
5. The 4S shop sales service management method based on video detection according to claim 4, wherein: in step S04, when the 4S store detects that the customer visits for the first time, a prompt is sent to the store in time, and the salesperson can provide service in time; 4S stores or sales personnel can subscribe all information of the customer to the system, the information comes from a customer demand report, and the sales personnel are helped to accurately make sales countermeasures and improve the service quality; the 4S store can subscribe the system for the relevant information of the sales service situation of the store, and the information is derived from the sales report of the 4S store.
6. A4S shop sales service management system based on video detection is characterized in that: the method comprises the following steps:
the front-end high-speed acquisition module: the face capturing device is used for capturing, collecting and uploading 4S shop face images and moving images;
a back-end image processing module: the system is used for receiving the face images and the moving images collected in the front-end high-speed acquisition module, confirming the identities of customers and salesmen and tracking the behaviors of the customers and the salesmen;
the sales management module: the client terminal is used for receiving the customer identity and the tracked customer behavior output by the back-end image processing module, analyzing the customer demand and forming a customer demand report; receiving the identity of the salesperson and the tracked behavior of the salesperson output by the rear-end image processing module, analyzing the sales service condition, and forming a sales report of the 4S shop;
the message subscription and distribution module: and the system is used for receiving the subscriber order message, extracting the customer demand report and the 4S shop sales report from the sales management module and feeding back the customer demand report and the 4S shop sales report.
7. The 4S shop sales service management system based on video detection according to claim 1, wherein: the front-end high-speed acquisition module comprises a face camera and a multi-path FPGA high-speed acquisition unit, the face camera is installed in a 4S shop and used for acquiring face images and moving images, and the multi-path FPGA high-speed acquisition unit is in signal connection with the face camera and used for acquiring the face images and the moving images of the 4S shops simultaneously and uploading the face images and the moving images to the rear-end image processing module.
8. A 4S shop sales service management system based on video detection as claimed in claim 2, wherein: the back-end image processing module includes:
an image preprocessing unit: the system comprises a face image acquisition module, a motion image acquisition module and a display module, wherein the face image acquisition module is used for acquiring a face image and a motion image and carrying out image alignment processing on the face image and the motion image;
a face feature recognition unit: extracting a face feature matrix from the aligned face image and the moving image;
a face identity recognition unit: the face feature matrix is used for comparing the obtained face feature matrix with a face model library, determining the identities of a customer and a salesperson, outputting and marking the customer and the salesperson, and storing the determined new customer into the face model library;
a vehicle detection unit: the face recognition method is used for recognizing the vehicles and the vehicle types in the rest part of the image marked with the faces, and the vehicles are not marked;
a behavior recognition unit: the system comprises a commodity browsing device, a commodity browsing system and a control device, wherein the commodity browsing device is used for detecting a commodity browsing track of a customer and an interaction relationship between the customer and a salesperson;
a tracking customer trajectory unit: and the behavior recognition unit is used for receiving the result output by the behavior recognition unit and sorting and outputting the commodity browsing track of the customer and the interaction relationship between the customer and the salesperson.
9. The 4S shop sales service management system based on video detection according to claim 8, wherein: the sales management module is developed based on python and comprises:
customer demand analysis unit: the face identity recognition unit is used for receiving the identity of the customer determined by the face identity recognition unit, extracting the commodity browsing track of the customer sorted out by the track tracking unit, analyzing the demand of the customer and forming a customer demand report;
salesperson service analysis unit: the face identity recognition unit is used for receiving the identity of the salesperson determined by the face identity recognition unit, extracting the interaction relationship between the customer and the salesperson sorted out by the customer track tracking unit, analyzing the sales service condition and forming a sales report of the 4S store.
10. The 4S shop sales service management system based on video detection according to claim 1, wherein: the message subscription and distribution module is developed based on python and comprises the following steps:
customer arrival reminding unit: the face feature recognition unit is used for receiving first store-arriving customer information sent by the face feature recognition unit and sending prompt information;
customer demand report subscribing unit: the system comprises a sales management module, a data processing module and a data processing module, wherein the sales management module is used for receiving a subscription message of a subscriber to a customer and extracting a customer demand report from the sales management module;
a sales service report subscription unit: for receiving the order message of the subscriber to the salesperson and extracting the 4S shop sales report from the sales management module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010419216.7A CN111597999A (en) | 2020-05-18 | 2020-05-18 | 4S shop sales service management method and system based on video detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010419216.7A CN111597999A (en) | 2020-05-18 | 2020-05-18 | 4S shop sales service management method and system based on video detection |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111597999A true CN111597999A (en) | 2020-08-28 |
Family
ID=72182936
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010419216.7A Pending CN111597999A (en) | 2020-05-18 | 2020-05-18 | 4S shop sales service management method and system based on video detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111597999A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112183417A (en) * | 2020-09-30 | 2021-01-05 | 重庆天智慧启科技有限公司 | Business consultant service capability evaluation system and method |
CN112184497A (en) * | 2020-09-30 | 2021-01-05 | 重庆天智慧启科技有限公司 | Client visiting track tracking and passenger flow analysis system and method |
CN112200051A (en) * | 2020-09-30 | 2021-01-08 | 重庆天智慧启科技有限公司 | Case field inspection system and method |
CN112258026A (en) * | 2020-10-21 | 2021-01-22 | 国网江苏省电力有限公司信息通信分公司 | Dynamic positioning scheduling method and system based on video identity recognition |
CN112528952A (en) * | 2020-12-25 | 2021-03-19 | 合肥诚记信息科技有限公司 | Working state intelligent recognition system for electric power business hall personnel |
CN112561268A (en) * | 2020-12-07 | 2021-03-26 | 深圳市思为软件技术有限公司 | Behavior evaluation method and related equipment |
CN112766267A (en) * | 2021-02-24 | 2021-05-07 | 人机互联网络(深圳)有限公司 | Diversified automobile service O2O system based on deep operation management |
CN113076295A (en) * | 2021-04-15 | 2021-07-06 | 泉州文学士信息科技有限公司 | Integrated customer information correlation synchronization system and device matched with same |
CN113517067A (en) * | 2021-09-14 | 2021-10-19 | 迅管(深圳)科技有限公司 | Method and system for supervising early rehabilitation training of children |
CN114529229A (en) * | 2022-04-25 | 2022-05-24 | 广州市普丰科技有限公司 | Display system for bicycle sales, capable of judging priority according to monitoring picture behaviors |
CN114648371A (en) * | 2022-05-23 | 2022-06-21 | 深圳市骏丰木链网科技股份有限公司 | Production and sale integrated management platform for flame-retardant ecological board based on Internet of things |
WO2022175935A1 (en) * | 2021-02-22 | 2022-08-25 | BriefCam Ltd. | Method and system for visual analysis and assessment of customer interaction at a scene |
CN117114694A (en) * | 2022-12-29 | 2023-11-24 | 珠海深蓝网络科技有限公司 | Big data analysis system and method based on CRM |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105678591A (en) * | 2016-02-29 | 2016-06-15 | 北京时代云英科技有限公司 | Video-analysis-based commercial intelligent operation decision-making support system and method |
CN109784161A (en) * | 2018-12-12 | 2019-05-21 | 成都数之联科技有限公司 | Video monitoring intelligent analysis system and method in a kind of shop |
CN109784162A (en) * | 2018-12-12 | 2019-05-21 | 成都数之联科技有限公司 | A kind of identification of pedestrian behavior and trace tracking method |
-
2020
- 2020-05-18 CN CN202010419216.7A patent/CN111597999A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105678591A (en) * | 2016-02-29 | 2016-06-15 | 北京时代云英科技有限公司 | Video-analysis-based commercial intelligent operation decision-making support system and method |
CN109784161A (en) * | 2018-12-12 | 2019-05-21 | 成都数之联科技有限公司 | Video monitoring intelligent analysis system and method in a kind of shop |
CN109784162A (en) * | 2018-12-12 | 2019-05-21 | 成都数之联科技有限公司 | A kind of identification of pedestrian behavior and trace tracking method |
Non-Patent Citations (1)
Title |
---|
张京娟: "《中国优秀硕士学位论文全文数据库信息科技辑》", 15 January 2017 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112183417A (en) * | 2020-09-30 | 2021-01-05 | 重庆天智慧启科技有限公司 | Business consultant service capability evaluation system and method |
CN112184497A (en) * | 2020-09-30 | 2021-01-05 | 重庆天智慧启科技有限公司 | Client visiting track tracking and passenger flow analysis system and method |
CN112200051A (en) * | 2020-09-30 | 2021-01-08 | 重庆天智慧启科技有限公司 | Case field inspection system and method |
CN112183417B (en) * | 2020-09-30 | 2023-12-05 | 重庆天智慧启科技有限公司 | System and method for evaluating service capability of consultant in department of industry |
CN112184497B (en) * | 2020-09-30 | 2023-10-03 | 重庆天智慧启科技有限公司 | Customer visit track tracking and passenger flow analysis system and method |
CN112200051B (en) * | 2020-09-30 | 2023-09-29 | 重庆天智慧启科技有限公司 | Case field inspection system and method |
CN112258026A (en) * | 2020-10-21 | 2021-01-22 | 国网江苏省电力有限公司信息通信分公司 | Dynamic positioning scheduling method and system based on video identity recognition |
CN112258026B (en) * | 2020-10-21 | 2023-12-15 | 国网江苏省电力有限公司信息通信分公司 | Dynamic positioning scheduling method and system based on video identity recognition |
CN112561268A (en) * | 2020-12-07 | 2021-03-26 | 深圳市思为软件技术有限公司 | Behavior evaluation method and related equipment |
CN112561268B (en) * | 2020-12-07 | 2023-12-15 | 深圳市思为软件技术有限公司 | Behavior evaluation method and related equipment |
CN112528952A (en) * | 2020-12-25 | 2021-03-19 | 合肥诚记信息科技有限公司 | Working state intelligent recognition system for electric power business hall personnel |
CN112528952B (en) * | 2020-12-25 | 2022-02-11 | 合肥诚记信息科技有限公司 | Working state intelligent recognition system for electric power business hall personnel |
WO2022175935A1 (en) * | 2021-02-22 | 2022-08-25 | BriefCam Ltd. | Method and system for visual analysis and assessment of customer interaction at a scene |
CN112766267A (en) * | 2021-02-24 | 2021-05-07 | 人机互联网络(深圳)有限公司 | Diversified automobile service O2O system based on deep operation management |
CN113076295A (en) * | 2021-04-15 | 2021-07-06 | 泉州文学士信息科技有限公司 | Integrated customer information correlation synchronization system and device matched with same |
CN113517067A (en) * | 2021-09-14 | 2021-10-19 | 迅管(深圳)科技有限公司 | Method and system for supervising early rehabilitation training of children |
CN114529229A (en) * | 2022-04-25 | 2022-05-24 | 广州市普丰科技有限公司 | Display system for bicycle sales, capable of judging priority according to monitoring picture behaviors |
CN114648371A (en) * | 2022-05-23 | 2022-06-21 | 深圳市骏丰木链网科技股份有限公司 | Production and sale integrated management platform for flame-retardant ecological board based on Internet of things |
CN117114694A (en) * | 2022-12-29 | 2023-11-24 | 珠海深蓝网络科技有限公司 | Big data analysis system and method based on CRM |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111597999A (en) | 4S shop sales service management method and system based on video detection | |
CN107045641B (en) | Goods shelf identification method based on image identification technology | |
CN107464116B (en) | Order settlement method and system | |
US8351647B2 (en) | Automatic detection and aggregation of demographics and behavior of people | |
US10701321B2 (en) | System and method for distributed video analysis | |
EP2620896B1 (en) | System And Method For Face Capture And Matching | |
CN109657624A (en) | Monitoring method, the device and system of target object | |
CN109272347A (en) | A kind of statistical analysis technique and system of shops's volume of the flow of passengers | |
KR101779096B1 (en) | The object pursuit way in the integration store management system of the intelligent type image analysis technology-based | |
WO2018180588A1 (en) | Facial image matching system and facial image search system | |
US20160048721A1 (en) | System and method for accurately analyzing sensed data | |
WO2016190814A1 (en) | Method and system for facial recognition | |
CN101268478A (en) | Method and apparatus for detecting suspicious activity using video analysis | |
CN111814510B (en) | Method and device for detecting legacy host | |
CN108810485A (en) | A kind of monitoring system working method | |
CN110309702A (en) | A kind of shops's counter video surveillance management system | |
US11488315B2 (en) | Visual and geolocation analytic system and method | |
CN110619324A (en) | Pedestrian and safety helmet detection method, device and system | |
WO2018037355A1 (en) | A system and method for automated vehicle and face detection and their classification | |
AU2017231602A1 (en) | Method and system for visitor tracking at a POS area | |
Tian et al. | Event detection, query, and retrieval for video surveillance | |
KR20170006356A (en) | Method for customer analysis based on two-dimension video and apparatus for the same | |
CN112132057A (en) | Multi-dimensional identity recognition method and system | |
CN111723725A (en) | Multi-dimensional analysis system based on video AI | |
Łubkowski et al. | Assessment of quality of identification of data in systems of automatic licence plate recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200828 |
|
RJ01 | Rejection of invention patent application after publication |