CN113487356B - Customer management method and system based on face recognition - Google Patents
Customer management method and system based on face recognition Download PDFInfo
- Publication number
- CN113487356B CN113487356B CN202110775052.6A CN202110775052A CN113487356B CN 113487356 B CN113487356 B CN 113487356B CN 202110775052 A CN202110775052 A CN 202110775052A CN 113487356 B CN113487356 B CN 113487356B
- Authority
- CN
- China
- Prior art keywords
- client
- area
- potential value
- monitoring area
- face recognition
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a customer management method and system based on face recognition. Wherein the method comprises the following steps: s1, receiving a video image of a client entering a monitoring area acquired by a camera; s2, carrying out face recognition on the client based on the video image, and storing the face recognition result; s3, analyzing the activity characteristics of the client in the monitoring area based on the video image; s4, judging whether the client is a potential client or not based on the activity characteristics, if so, turning to S5; otherwise, turning to S1; and S5, creating a client profile for the client based on the face recognition result. According to the scheme, on one hand, the identity information is automatically acquired by using a face recognition technology, on the other hand, whether the client is a potential client or not is analyzed by using the activity characteristics of the client, and then the client file can be quickly created.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a customer management method, a customer management system, electronic equipment and a computer storage medium based on face recognition.
Background
With the advancement of technology, more and more businesses begin to manage the customer's file information electronically, but the existing customer file management method still creates a customer file by manually inputting customer information, and then manages and uses the customer file. Obviously, compared with the traditional papery file management method, the method only changes the management medium and the input and output means of the file, and does not bring more efficient and convenient experience to the merchant on file creation and management.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a customer management method, a system, electronic equipment and a computer storage medium based on face recognition, so as to realize high efficiency and convenience in customer file management.
The invention provides a customer management method based on face recognition in a first aspect, which comprises the following steps:
s1, receiving a video image of a client entering a monitoring area acquired by a camera;
s2, carrying out face recognition on the client based on the video image, and storing the face recognition result;
s3, analyzing the activity characteristics of the client in the monitoring area based on the video image;
s4, judging whether the client is a potential client or not based on the activity characteristics, if so, turning to S5; otherwise, turning to S1;
and S5, creating a client profile for the client based on the face recognition result.
Preferably, the camera is a distributed camera disposed in the monitored area.
Preferably, the activity features include track features and communication features;
analyzing the activity characteristics of the client in the monitoring area based on the video image in step S3 includes:
tracking and identifying the client to determine the active position point of the client in the monitoring area so as to obtain the track characteristic; when the business personnel and the client are in the accompanying state, the communication state of the client is identified to obtain communication characteristics;
and associating the track characteristic and the communication characteristic to serve as the activity characteristic.
Preferably, the determining whether the client is a potential client based on the activity feature in step S4 includes:
s40, performing cluster analysis on the activity position points in the track characteristics to identify the activity area of the client in the monitoring area, and obtaining a first potential value based on the attribute of the activity area;
s41, obtaining a second potential value based on the alternating current state in the alternating current feature;
s42, calculating a third potential value based on the first potential value and the second potential value; and if the third potential value is larger than the threshold value, determining that the client is a potential client.
Preferably, the communication feature further includes a time correlation with the trajectory feature, and the third potential value is corrected based on the time correlation.
Preferably, after step S5, the method further includes:
and sending the created customer file to the service personnel terminal, generating a service menu based on the customer file if feedback of the service personnel terminal is received within a set time period, and sending the service menu to a specified terminal.
Preferably, the designated terminal includes a service personnel terminal, a monitoring area sub-area terminal and a warehouse terminal.
The invention provides a customer management system based on face recognition, which comprises a camera, a processing module, a display module and a display module, wherein the camera is used for acquiring the face information; wherein,
the camera is used for acquiring a video image of a client entering a monitoring area;
the processing module is used for carrying out face recognition on the client based on the video image and storing the face recognition result; analyzing the activity characteristics of the client in the monitoring area based on the video image; and judging whether the client is a potential client or not based on the activity characteristics, and if so, creating a client file for the client based on the face recognition result.
Preferably, the camera is a distributed camera disposed in the monitored area.
Preferably, the activity features include track features and communication features;
the processing module analyzes the activity characteristics of the client in the monitoring area based on the video image, and comprises the following steps:
tracking and identifying the client to determine the active position point of the client in the monitoring area so as to obtain the track characteristic; when the business personnel and the client are in the accompanying state, the communication state of the client is identified to obtain communication characteristics;
and associating the track characteristic and the communication characteristic to serve as the activity characteristic.
Preferably, the processing module determines whether the client is a potential client based on the activity characteristics, including:
performing cluster analysis on the activity position points in the track characteristics to identify an activity area of the client in the monitoring area, and obtaining a first potential value based on the attribute of the activity area;
deriving a second potential value based on the emotional state in the communication feature;
calculating a third potential value based on the first potential value and the second potential value; and if the third potential value is larger than the threshold value, determining that the client is a potential client.
Preferably, the communication feature further includes a time association relationship with the trajectory feature, and the processing module further corrects the third potential value based on the time association relationship.
Preferably, the processing module is further configured to:
and sending the created customer file to the service personnel terminal, generating a service menu based on the customer file if feedback of the service personnel terminal is received within a set time period, and sending the service menu to a specified terminal.
Preferably, the designated terminal includes a service personnel terminal, a monitoring area sub-area terminal and a warehouse terminal.
A third aspect of the invention provides an electronic device, the device comprising:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to perform the method of any of the preceding claims.
A fourth aspect of the invention provides a computer storage medium having stored thereon a computer program which, when executed by a processor, performs a method as set forth in any one of the preceding claims.
The invention has the beneficial effects that:
the identity information of the client who enters the field is directly obtained at the first time by using a face recognition technology; the potential client is identified by analyzing the activity characteristics of the client after entering the field, so that the client file can be directly created on the basis of the face identification result and the potential client judgment result background, the trouble of manually creating the client file by business personnel is avoided, and the method is efficient, convenient and fast and is favorable for providing more timely service for the client.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of a customer management method based on face recognition according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a customer management system based on face recognition according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
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. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the 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.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. indicate an orientation or a positional relationship based on that shown in the drawings or that the product of the present invention is used as it is, this is only for convenience of description and simplification of the description, and it does not indicate or imply that the device or the element referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention.
Furthermore, the appearances of the terms "first," "second," and the like, if any, are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
Example one
Referring to fig. 1, fig. 1 is a schematic flowchart of a customer management method based on face recognition according to an embodiment of the present invention. As shown in fig. 1, a customer management method based on face recognition in the embodiment of the present invention includes:
s1, receiving a video image of a client entering a monitoring area acquired by a camera;
s2, carrying out face recognition on the client based on the video image, and storing the face recognition result;
s3, analyzing the activity characteristics of the client in the monitoring area based on the video image;
s4, judging whether the client is a potential client or not based on the activity characteristics, if so, turning to S5; otherwise, turning to S1;
and S5, creating a client profile for the client based on the face recognition result.
In the embodiment of the invention, on one hand, the technical scheme of the invention can directly obtain the identity information of the entering client at the first time by using the face recognition technology, and simultaneously, the activity characteristics of the client after entering the field are analyzed, and whether the client is a potential client (for example, the client is interested in the service provided by the merchant, or wants to experience, or even needs to transact a member and the like) can be judged based on the activity characteristic analysis, so that the scheme of the invention can directly create the client file in the background based on the face recognition result and the judgment result of the potential client, thereby avoiding the complexity of manually creating the client file by business personnel, being efficient and convenient, and being beneficial to providing more timely service for the client. Of course, other information needed in the created customer profile may be later supplemented or modified by the associated business personnel.
The approach clients may be subjected to face Recognition by using a Feature-based Recognition algorithm (Feature-based Recognition algorithms), an entire face image-based Recognition algorithm (application-based Recognition algorithms), a Template-based Recognition algorithm (Template-based Recognition algorithms), a neural network Recognition algorithm (registration algorithms using neural network), and a Recognition algorithm based on an illumination estimation model theory.
Preferably, the camera is a distributed camera disposed in the monitored area.
In the embodiment of the invention, the merchant can lay the cameras in the appointed rooms of the business place in advance, for example, the reception hall, the service room, the rest room and the like, so that the activity characteristics of the customers can be fully mastered, and the accuracy of analyzing and identifying results of potential customers can be improved.
Preferably, the activity features include track features and communication features;
analyzing the activity characteristics of the client in the monitoring area based on the video image in step S3 includes:
tracking and identifying the client to determine the active position point of the client in the monitoring area so as to obtain the track characteristic; when the business personnel and the client are in the accompanying state, the communication state of the client is identified to obtain communication characteristics;
and associating the track characteristic and the communication characteristic to serve as the activity characteristic.
In an embodiment of the present invention, the present invention relies on two factors in identifying potential customers, namely, trajectory characteristics and communication characteristics. Specifically, the inventors of the present invention have found that potential customers who enter the store (i.e., people who have not consumed or experienced the service at the store) will actively talk to business personnel to learn about information about merchants, services, etc., on the one hand, and will enjoy the business within the store, such as holding at walls where merchants hang various qualifications to observe to confirm merchant qualifications, entering a service room, and holding at feet to learn about the service environment; the acquaintances basically do not have the actions, and even if the acquaintances have the actions, the acquaintances can be eliminated by comparing the face recognition result with the customer files stored in the database. Based on the remarkable characteristics of the two aspects, the invention tracks the client by utilizing the image recognition technology to further obtain the activity track of the client, meanwhile, when the client and the service personnel are in the accompanying conversation state, the communication characteristics of the client are obtained by utilizing the expression and action recognition technology, and the client can be accurately determined whether to have the consumption intention or not by comprehensive judgment, namely whether to be a potential client or not. The image recognition tracking, expression and motion recognition technologies are all conventional means in the field of image analysis and recognition, the invention is not particularly limited to this, and a person skilled in the art can freely select a suitable recognition algorithm. The accompanying state can also be analyzed by an image recognition technology, for example, when it is detected that the distance between the service person and the client is within a preset range and the service person and the client face each other, it can be determined that the service person is in the accompanying state.
Preferably, the determining whether the client is a potential client based on the activity feature in step S4 includes:
s40, performing cluster analysis on the activity position points in the track characteristics to identify the activity area of the client in the monitoring area, and obtaining a first potential value based on the attribute of the activity area;
s41, obtaining a second potential value based on the alternating current state in the alternating current feature;
s42, calculating a third potential value based on the first potential value and the second potential value; and if the third potential value is larger than the threshold value, determining that the client is a potential client.
In an embodiment of the invention, 1) for a first potential value: different first initial sub-values are given to the sub-areas of each monitoring area in advance, for example, different values are set according to the sequence of 'between service orders', 'qualification posting area', 'reception hall', 'rest room', 'toilet', and then the values of the sub-areas which the client has passed through are accumulated to obtain a first potential value.
In order to more accurately track customers, the sampling interval during tracking identification is generally reduced to obtain enough position point data, so that the position point data of the customers need to be clustered by adopting a clustering algorithm to realize that each position point belongs to a corresponding monitoring area sub-area, namely each closed area of a merchant. In addition, when a customer visits in a store, the customer does not necessarily directly enter a certain room, and may only visit by standing at the doorway, and in order to solve the problem, when clustering is performed, a location point which is located in a set area outside a sub-area of a monitoring area and has a residence time reaching a first time threshold value is assigned to the sub-area of the monitoring area. Obviously, the set area should exclude areas that are not visually observable inside the sub-area of the surveillance area, although in the doorway area.
2) For the second potential value: when the customer and the business personnel are in the accompanying conversation state, the expression and action recognition technology is used for obtaining the expression characteristics and the action characteristics of the customer, and the positive attitude or the negative attitude presented by the customer can be determined based on the expression characteristics and the action characteristics. For example, if the characteristics of smile, high-frequency expression (mouth opening), frequent and noded head and the like of the face of the client are recognized, the attitude of the client is positive, and conversely, if the characteristics of negative expression (such as impatience), long-time (the time can be timed for the face not being recognized), head lowering, long-time mobile phone operation, gesture rejection and the like of the client are recognized, the attitude of the client is negative. Similar to the first potential value, each expression, action and combination of the expression and the action may be given a second initial sub-value in advance according to a certain sequence, and then scores of the expressions and/or actions of the customer in a specified time period are accumulated to obtain a second potential value.
3) For the third potential value: the third potential value is calculated by means of coefficient adjustment, see the following formula:
Sthr＝α*Sfir+β*Ssec
in the formula, Sfir、Ssec、SthrRespectively representing a first potential value, a second potential value and a third potential value, wherein alpha and beta represent regulating coefficients of the first potential value and the second potential value respectively; wherein both alpha and beta are non-constant values.
Alpha and beta set in the invention are not weights in the traditional sense, namely alpha + beta is not equal to 1, and alpha and beta are adjustable adjusting coefficients and are respectively equal to Sfir、SsecThe corresponding first initial sub-value and second initial sub-value are associated. For example, it is assumed that the initial values α ═ 0 and β ═ 0, and that sub adjustment coefficients having an average value of 1, such as 1.5, 1.2, 1.0, 0.7, 0.6, are respectively set for the first initial sub-values corresponding to the sub-regions of the monitoring region in the aforementioned order, so that α ═ 1.5+1.2+1.0+0.7+0.6 ═ 4, and of course, if no customer visit to a toilet is detected, for example, then 0.6 is not calculated, i.e., α ═ 1.5+1.2+1.0+0.7 ═ 3.4; similarly, the second initial sub-values of the expressions and/or movements are each assigned a sub-adjustment factor in the aforementioned order, which also has an average value of 1, such as 1.5, 1.3, 0.9, 0.6, 0.1 (e.g. corresponding to a facial smile + frequent nodding, facial smile, long head, restless expression, or rejection gesture), respectively, so that β -1.5 + 1.3-2.8, or β -0.1, or β -0.9 + 0.6-1.5, where the expressions and/or movements are generally not detected simultaneously, since the mood of the customer should not be contentious. At this time, Sthr＝4*Sfir+1.5*Ssec. Of course, the above calculation manner of the third potential value is only used for example, and the present invention does not exclude other mathematical calculation methods, and is not used for limiting the specific contents of the above mentioned sub-items, and those skilled in the art can select and design the calculation method according to the design requirements.
Preferably, the communication feature further includes a time correlation with the trajectory feature, and the third potential value is corrected based on the time correlation.
In the embodiment of the present invention, for a merchant, for example, a delivery person, a service person, and other persons who enter the field often include, but are obviously not the analysis scope of a potential customer, but the foregoing potential customer identification method actually performs analysis based on only a track feature and a communication feature, and lacks consideration of the correlation relationship between the track feature and the communication feature, and the track feature and the communication feature of the person may be misrecognized as a potential customer, for example, the delivery person may also talk with the service person and enter a sub-area of a monitoring area to place goods, and the like, so as to create an unnecessary customer profile. Aiming at the technical problem, the invention adopts the following means to distinguish:
s43, analyzing the tracking continuity of the client in the video image;
s44, if the tracking continuity does not satisfy the predetermined condition, making the third potential value γ ═ γ1A third potential value; otherwise, let the third potential value be γ2A third potential value, wherein γ1<1，γ2>1。
The distributed cameras are distributed in the business areas of the merchants, so that the monitoring of each area is almost free of dead angles, and normal customers generally do not break away from the monitoring of the distributed cameras, namely, the customers can move in the business areas all the time or leave the business areas rarely. The delivery person is different from the others, and the delivery person often frequently enters and exits the business area for transporting goods, so the invention distinguishes the customers and the delivery person based on the characteristic. Accordingly, the tracking continuity may be the number of times that the customer lost the tracking identification, i.e. was not identified, and the predetermined condition is a reasonable threshold corresponding to the number of times, e.g. the customer leaves the tracking 1 time during the study period, possibly going to a restroom or leaving after the negotiation (just at the end of the study period), and may be determined to satisfy the predetermined condition, γ2To increase the third potential value; if the customer leaves the tracking more than 4 times, the customer is proved to be the delivery person with a high probability, and the customer is judged not to meet the preset condition at the moment and gamma is used1To lower the third potential value; in addition, if the client has, for example, more than 10 timesIf the client is out of track, it can be directly determined as a non-potential client, and at this time, the third potential value γ can also be directly set1A third potential value, wherein γ1And may be 0 or even negative. By adopting the method, the delivery personnel can be easily distinguished from the normal customers.
In addition, workers such as service personnel and cleaning personnel can be easily distinguished based on dressing without using motion trail characteristics and conversation characteristics, so that the data processing amount can be reduced. Furthermore, people in the field which are not loaded towards the working personnel can be set to carry out face recognition, and the processing load of the system can be further reduced.
In addition, there is a situation where a customer may travel with a child and the service offered by the merchant is not suitable for the child, so it is obviously unreasonable to profile the child in such a situation. Aiming at the problem, the invention can also identify the age of the approaching client, and does not create a client file for the client with the age meeting the exclusion condition. The specific implementation mode is as follows:
s45, extracting appearance features and wearing features of the client based on the video image, wherein the appearance features comprise face information and height information;
s46, comparing the appearance characteristic and the wearing characteristic with exclusion conditions, wherein the exclusion conditions are determined based on age; if the comparison result is not matched, turning to S47;
and S47, sending a confirmation request to the service personnel terminal, and if the feedback of the service personnel terminal is yes, turning to S5.
The method is characterized in that the appearance characteristics and wearing characteristics of the clients are compared with preset exclusion conditions, so that the clients which are obviously children can be excluded, the clients which do not meet the exclusion conditions (namely whether the clients are children or not can be determined temporarily) request service personnel on site to confirm, and if the service personnel feedback that the clients are children or not, the client files are created for the clients. In addition, for a merchant, the merchant may select to manually set the function in the background program based on the business scope of the merchant, for example, if the service provided by the merchant is not suitable for children, the function may be turned on, otherwise, the function is set to be turned off, and a specific implementation manner of the function setting belongs to a conventional means in the field, and the present invention is not limited to this.
Preferably, after step S5, the method further includes:
and sending the created customer file to the service personnel terminal, generating a service menu based on the customer file if feedback of the service personnel terminal is received within a set time period, and sending the service menu to a specified terminal.
In the embodiment of the invention, after the client file is established, the file can be sent to the business personnel in conversation, if the business personnel successfully persuade the client to transact the member or experience the service, the business personnel can feed back and confirm according to the actual situation, and then the system can send the service menu to the appointed terminal so as to provide the service in time.
Preferably, the designated terminal includes a service personnel terminal, a monitoring area sub-area terminal and a warehouse terminal.
In the embodiment of the invention, the appointed terminal can also be a terminal of a sub-area of a monitoring area and a terminal of a storehouse besides a service staff terminal, so that timely service can be provided in an all-round way, namely after a client enters the sub-area of the monitoring area (such as a service room), the arranged terminal can directly display and view detailed service menu contents, and the storehouse can be prepared and distributed to the appointed service room in time according to the received service menu. Thus, a better experience is provided for the customer.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of a customer management system based on face recognition according to an embodiment of the present invention. As shown in fig. 2, a customer management system based on face recognition according to an embodiment of the present invention includes a camera and a processing module; wherein,
the camera is used for acquiring a video image of a client entering a monitoring area;
the processing module is used for carrying out face recognition on the client based on the video image and storing the face recognition result; analyzing the activity characteristics of the client in the monitoring area based on the video image; and judging whether the client is a potential client or not based on the activity characteristics, and if so, creating a client file for the client based on the face recognition result.
For the specific functions of the client management system based on face recognition in this embodiment, reference is made to the first embodiment, and since the system in this embodiment adopts all the technical solutions of the above embodiments, at least all the beneficial effects brought by the technical solutions of the above embodiments are achieved, and details are not repeated here.
Preferably, the camera is a distributed camera disposed in the monitored area.
Preferably, the activity features include track features and communication features;
the processing module analyzes the activity characteristics of the client in the monitoring area based on the video image, and comprises the following steps:
tracking and identifying the client to determine the active position point of the client in the monitoring area so as to obtain the track characteristic; when the business personnel and the client are in the accompanying state, the communication state of the client is identified to obtain communication characteristics;
and associating the track characteristic and the communication characteristic to serve as the activity characteristic.
Preferably, the processing module determines whether the client is a potential client based on the activity characteristics, including:
performing cluster analysis on the activity position points in the track characteristics to identify an activity area of the client in the monitoring area, and obtaining a first potential value based on the attribute of the activity area;
deriving a second potential value based on the AC state in the AC signature;
calculating a third potential value based on the first potential value and the second potential value; and if the third potential value is larger than the threshold value, determining that the client is a potential client.
Preferably, the communication feature further includes a time association relationship with the trajectory feature, and the processing module further corrects the third potential value based on the time association relationship.
Preferably, the processing module is further configured to:
extracting appearance features and wearing features of the client based on the video image, wherein the appearance features comprise face information and height information;
comparing the appearance feature and the wear feature with exclusion conditions, wherein the exclusion conditions are determined based on age; if the comparison result is not matched, a confirmation request is sent to a service personnel terminal, and if the feedback of the service personnel terminal is yes, a client file is created for the client based on the face recognition result.
Preferably, the processing module is further configured to:
and sending the created customer file to the service personnel terminal, generating a service menu based on the customer file if feedback of the service personnel terminal is received within a set time period, and sending the service menu to a specified terminal.
Preferably, the designated terminal includes a service personnel terminal, a monitoring area sub-area terminal and a warehouse terminal.
EXAMPLE III
Referring to fig. 3, fig. 3 is an electronic device according to an embodiment of the present invention, the electronic device includes:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to execute the method according to the first embodiment.
Example four
The embodiment of the invention also discloses a computer storage medium, wherein a computer program is stored on the storage medium, and the computer program executes the method in the first embodiment when being executed by a processor.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (7)
1. A customer management method based on face recognition is characterized in that: the method comprises the following steps:
s1, receiving a video image of a client entering a monitoring area acquired by a camera;
s2, carrying out face recognition on the client based on the video image, and storing the face recognition result;
s3, analyzing the activity characteristics of the client in the monitoring area based on the video image;
s4, judging whether the client is a potential client or not based on the activity characteristics, if so, turning to S5; otherwise, turning to S1;
s5, creating a client file for the client based on the face recognition result;
the activity features comprise track features and communication features;
analyzing the activity characteristics of the client in the monitoring area based on the video image in step S3 includes: tracking and identifying the client to determine the active position point of the client in the monitoring area so as to obtain the track characteristic; when the business personnel and the client are in the accompanying state, the communication state of the client is identified to obtain communication characteristics;
associating the track feature and the communication feature as the activity feature;
the determining whether the client is a potential client based on the activity characteristics in step S4 includes:
s40, performing cluster analysis on the activity position points in the track characteristics to identify the activity area of the client in the monitoring area, and obtaining a first potential value based on the attribute of the activity area;
s41, obtaining a second potential value based on the alternating current state in the alternating current feature;
s42, calculating a third potential value based on the first potential value and the second potential value; if the third potential value is greater than the threshold value, determining that the customer is a potential customer;
wherein, 1) for the first potential value: giving different first initial sub-values to each monitoring area sub-area in advance, and accumulating the first initial sub-values of the monitoring area sub-areas which are passed by a client to obtain a first potential value; 2) for the second potential value: giving second initial sub-values to the expressions, the actions and the combination of the expressions and the actions in advance according to a certain sequence, and accumulating scores of the expressions and/or the actions of the customer in a specified time period to obtain a second potential value;
clustering position point data of the clients by adopting a clustering algorithm to realize that each position point belongs to a corresponding monitoring area sub-area, and the position point which is positioned in a setting area outside a door of the monitoring area sub-area and has the residence time reaching a first time threshold value belongs to the monitoring area sub-area, but the setting area should discharge an area which is positioned in the door area but can not visually observe the inside of the monitoring area sub-area;
the communication characteristics also comprise a time incidence relation with the track characteristics, and the third potential value is corrected based on the time incidence relation;
s43, analyzing the tracking continuity of the client in the video image;
s44, if the tracking continuity does not satisfy the predetermined condition, making the third potential value γ ═ γ1 *A third potential value; otherwise, let the third potential value be γ2 *A third potential value, wherein γ1<1，γ2>1；
The tracking continuity is the times that the client loses tracking identification, namely cannot be identified, the preset condition is a reasonable threshold corresponding to the times, and if the times that cannot be identified are smaller than the threshold, the preset condition is judged to be met; if the number of times that the identification cannot be carried out is larger than the threshold value, judging that the number of times does not meet the preset condition;
s45, extracting appearance features and wearing features of the client based on the video image, wherein the appearance features comprise face information and height information;
s46, comparing the appearance characteristic and the wearing characteristic with exclusion conditions, wherein the exclusion conditions are determined based on age; if the comparison result is not matched, go to S47;
and S47, sending a confirmation request to the service personnel terminal, and if the feedback of the service personnel terminal is yes, turning to S5.
2. The method of claim 1, wherein: the cameras are distributed cameras arranged in the monitoring area.
3. The method according to claim 1 or 2, characterized in that: after step S5, the method further includes:
and sending the created customer file to the service personnel terminal, generating a service menu based on the customer file if feedback of the service personnel terminal is received within a set time period, and sending the service menu to a specified terminal.
4. The method of claim 3, wherein: the appointed terminals comprise business personnel terminals, monitoring area sub-area terminals and storehouse terminals.
5. A customer management system based on face recognition for implementing the method according to any one of claims 1 to 4, characterized in that: the system comprises a camera and a processing module; wherein,
the camera is used for acquiring a video image of a client entering a monitoring area;
the processing module is used for carrying out face recognition on the client based on the video image and storing the face recognition result; analyzing the activity characteristics of the client in the monitoring area based on the video image; and judging whether the client is a potential client or not based on the activity characteristics, and if so, creating a client file for the client based on the face recognition result.
6. An electronic device, the device comprising:
a memory storing executable program code;
a processor coupled with the memory;
the method is characterized in that: the processor calls the executable program code stored in the memory to perform the method of any of claims 1-4.
7. A computer storage medium having a computer program stored thereon, characterized in that: the computer program, when executed by a processor, performs the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110775052.6A CN113487356B (en) | 2021-07-08 | 2021-07-08 | Customer management method and system based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110775052.6A CN113487356B (en) | 2021-07-08 | 2021-07-08 | Customer management method and system based on face recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113487356A CN113487356A (en) | 2021-10-08 |
| CN113487356B true CN113487356B (en) | 2022-04-05 |
Family
ID=77938123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110775052.6A Active CN113487356B (en) | 2021-07-08 | 2021-07-08 | Customer management method and system based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113487356B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107844990A (en) * | 2017-10-31 | 2018-03-27 | 努比亚技术有限公司 | A kind of approaches to IM and its system, terminal device for intelligent shops |
| CN109858958A (en) * | 2019-01-17 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Aim client orientation method, apparatus, equipment and storage medium based on micro- expression |
| CN109919006A (en) * | 2019-01-23 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Expression detection method, device, electronic device and storage medium |
| CN111178966A (en) * | 2019-12-30 | 2020-05-19 | 武汉零客思唯科技有限公司 | Latent customer behavior analysis method and system based on face recognition |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8725567B2 (en) * | 2006-06-29 | 2014-05-13 | Microsoft Corporation | Targeted advertising in brick-and-mortar establishments |
| 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 |
-
2021
- 2021-07-08 CN CN202110775052.6A patent/CN113487356B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107844990A (en) * | 2017-10-31 | 2018-03-27 | 努比亚技术有限公司 | A kind of approaches to IM and its system, terminal device for intelligent shops |
| CN109858958A (en) * | 2019-01-17 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Aim client orientation method, apparatus, equipment and storage medium based on micro- expression |
| CN109919006A (en) * | 2019-01-23 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Expression detection method, device, electronic device and storage medium |
| CN111178966A (en) * | 2019-12-30 | 2020-05-19 | 武汉零客思唯科技有限公司 | Latent customer behavior analysis method and system based on face recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113487356A (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11409983B2 (en) | Methods and apparatuses for dynamically adding facial images into database, electronic devices and media | |
| US12008880B2 (en) | Utilizing artificial intelligence to detect objects or patient safety events in a patient room | |
| US11151383B2 (en) | Generating visual event detectors | |
| US10959657B2 (en) | Stress management system and stress management method | |
| US20190332872A1 (en) | Information push method, information push device and information push system | |
| US20180060536A1 (en) | Stress management system and stress management method | |
| US9378421B2 (en) | System and method for seat occupancy detection from ceiling mounted camera using robust adaptive threshold criteria | |
| US20140314310A1 (en) | Automatic analysis of rapport | |
| CN109376982B (en) | Target employee selection method and device | |
| CN113688794A (en) | Identity recognition method and device, electronic equipment and computer readable storage medium | |
| KR101785427B1 (en) | Customer management system and method based on features extracted from facial image of customer by neural network | |
| CN110046955A (en) | Marketing method, device, computer equipment and storage medium based on recognition of face | |
| US10388092B1 (en) | Computer vision-based surveillance for services | |
| CN113487356B (en) | Customer management method and system based on face recognition | |
| CN105590306B (en) | Photograph diary | |
| WO2012071677A1 (en) | Method and system for face recognition | |
| US20210383667A1 (en) | Method for computer vision-based assessment of activities of daily living via clothing and effects | |
| Chen et al. | A collaborative framework for ergonomic feedback using smart cameras | |
| JP3540494B2 (en) | Cooperative work adjusting device and cooperative work adjusting method | |
| CN113487357B (en) | Customer file management method and system based on face recognition | |
| WO2024241312A1 (en) | Method of online shopping and system therefor | |
| US10614578B2 (en) | System and method for tracking people, animals and objects using a volumetric representation and artificial intelligence | |
| CN114463700B (en) | Seat status management method, device, equipment and storage medium | |
| CN109325800A (en) | A kind of working method of supermarket's intelligent commodity shelf based on computer vision | |
| Wani et al. | Real Time Smart Mirror System Using Internet on Things |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |