CN106713255A - Use information management method and system - Google Patents
Use information management method and system Download PDFInfo
- Publication number
- CN106713255A CN106713255A CN201510797129.4A CN201510797129A CN106713255A CN 106713255 A CN106713255 A CN 106713255A CN 201510797129 A CN201510797129 A CN 201510797129A CN 106713255 A CN106713255 A CN 106713255A
- Authority
- CN
- China
- Prior art keywords
- user
- characteristic value
- identity
- user information
- information database
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/1066—Session management
- H04L65/1073—Registration or de-registration
Abstract
The present invention relates to a user information management method. The method comprises the steps of receiving a human face image of a user sent by a terminal; identifying a feature value of the human face image by using a deep learning-based human face identification method; inquiring whether a user information database stores an identifier corresponding to the feature value; if the user information database stores the identifier corresponding to the feature value, inquiring a user information record associated with the identifier in the user information database; and sending the user information record to the terminal to display. The present invention further provides a user information management method. According to the method, the human face image of the user is acquired and is identified by using the deep learning-based human face identification method, so that the user is identified at a high accuracy rate, the user information is tracked and managed, and the method is high in reliability and low in costs.
Description
Technical field
The present invention relates to intelligent management field, more particularly to a kind of user information management method and system.
Background technology
To the management of consumer's authentication be in traditional user management, such as service industry by periodically to
Entity vip card piece is provided at family, and user relies on corresponding vip card, in specified market, restaurant, body-building shop
Deng consuming at businessman, various VIP rights can be enjoyed, such as discount, integration accumulation, pay, this mode
By numerous businessmans as a Main Means for cultivating loyal user, its range of application constantly expands, a lot
User can hold three to four vip cards according to oneself hobby.Equally, vip card there is also multiple types in itself
The group of type, such as regular member card, stored value card, coupons, accumulating card, or all kinds card
Close, and as the intensification species of application is more enriched.
But, as a large amount of distribution of entity vip card are used, its shortcoming is also gradually displayed.
From the user point of view, it is the very troublesome thing of part to manage multiple vip cards.In order to consumption when can
VIP rights are enjoyed at any time, it is standby that user need to carry with various vip cards, its storage, take all extremely not
Just.Meanwhile, entity card is easily lost, is stolen or damages, and the vip card of magnetic stripe card form is easy because of magnetic strip information
It is damaged and may causes to cancel, handling again will also expends the time and money of user.
From the point of view of hair fastener square degree, the vip card for using at present has magnetic stripe card, IC-card, metal card, hard paper
Card etc., but it is no matter any, and a large amount of distribution of vip card will inevitably result from considerable making with hair
Send cost.Meanwhile, if subscriber card is lost, mending card will virtually increase the operating cost of card issuer, and use
If family cannot with oneself take card because of inconvenience, or the benefit card cycle is more long, then influence the consumption enthusiasm of user.
And with the development of society, the popularity rate such as mobile phone, MSN is very high, thus
Engender using the mode of mobile phone and MSN account user bound identity to improve vip card
Application management, realize virtual electronic vip card manage, but this need user provide identity information, movement
The security informations such as telephone number, MSN account, user's heart may be reluctant to provide, and
Businessman provides user information management the careless slightly leakage for being all easily caused user's associated privacy information, from
And cause the dislike of user, also, it is subject to malicious exploitation after the information such as the telephone number of user is known by other people
If, loss can be brought to businessman and user.
The content of the invention
Based on this, it is necessary to high cost for user information management method in the prior art, in-convenience in use
With unsafe problem, there is provided a kind of low cost, user information management method easy to use and safe and be
System.
A kind of user information management method, including:
The facial image of the user that receiving terminal sends;
Using the face identification method based on deep learning, the characteristic value of the facial image is recognized;
Whether there is identity corresponding with the characteristic value in searching user's information database;
When there is identity corresponding with the characteristic value in inquiring the User Information Database, look into
To ask in the User Information Database and be mutually related user profile with the identity and record;
User profile record is sent into the terminal to be shown.
A kind of customer information control system, including:
Image receiver module, the facial image of the user sent for receiving terminal;
Face recognition module, for using the face identification method based on deep learning, recognizing the face figure
The characteristic value of picture;
Identification module, it is corresponding with the characteristic value for whether there is in searching user's information database
Identity;
Enquiry module, it is corresponding with the characteristic value for existing in the User Information Database is inquired
During identity, the user profile that is mutually related with the identity in the User Information Database is inquired about
Record;
Sending module, is shown for user profile record to be sent into the terminal.
Above-mentioned user information management method and system, by obtaining the facial image of user and being based on deep learning
Recognition of face, the characteristic value of automatic identification user's facial image, according to the spy of user in user profile data
Value indicative and the unique corresponding identity of its identity such that it is able to realize the identity of automatic identification user and inquire about
With display and the identity be mutually related user profile record, by understand user profile record realize
Management to user, this kind of method safety reliability, the individual privacy of user is not related to, and save entity
The puzzlements such as the cost and carrying inconvenience of card, also save the cost of card making;Based on deep learning
Recognition of face can high-accuracy identifying user face characteristic, face characteristic is not susceptible to ambient influnence, reliable
Property is high, and anti-counterfeiting performance is good.
Brief description of the drawings
Fig. 1 is the system architecture diagram of user information management method in one embodiment of the invention;
Fig. 2 is the schematic internal view of server in one embodiment of the invention;
The flow chart of the user information management method that Fig. 3 is provided by one embodiment of the invention;
The flow chart of the user information management method that Fig. 4 is provided by second embodiment of the invention;
The flow chart of the user information management method that Fig. 5 is provided by third embodiment of the invention;
The flow chart of the user information management method that Fig. 6 is provided by fourth embodiment of the invention;
The structural representation of the customer information control system that Fig. 7 is provided by another embodiment of the present invention;
The structural representation of the customer information control system that Fig. 8 is provided by second embodiment of the invention.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, below in conjunction with accompanying drawing and reality
Example is applied, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only
It is used to explain the present invention, is not intended to limit the present invention.
Unless otherwise defined, all of technologies and scientific terms used here by the article with belong to technology of the invention
The implication that the technical staff in field is generally understood that is identical.The art for being used in the description of the invention herein
Language is intended merely to describe the purpose of specific embodiment, it is not intended that in the limitation present invention.It is used herein
Term " and/or " include the arbitrary and all of combination of one or more related Listed Items.
The user information management method that the embodiment of the present invention is provided can be applied in the system shown in Fig. 1, such as
Shown in Fig. 1, terminal 100 is communicated by network with server 200, and terminal 100 is obtained including image
Module and display module, described image acquisition module are used to shoot the facial image of user, and are sent to service
Device, the facial image of the user that 200 receiving terminal of server 100 sends, using the people based on deep learning
Face recognition method, recognizes the characteristic value of the facial image, whether there is in searching user's information database with
The corresponding identity of the characteristic value, exists and the feature in the User Information Database is inquired
When being worth corresponding identity, inquire about and be mutually related with the identity in the User Information Database
User profile is recorded, and user profile record is sent into the terminal 100 is shown.
In one embodiment, the internal structure of the server 200 in Fig. 1 is as shown in Fig. 2 the server
200 include the processor, storage medium, internal memory and the network interface that are connected by system bus.Wherein, the clothes
The be engaged in storage medium of device 200 is stored with operating system, database and a kind of Management System for Clients Information, data
Storehouse is used for data storage, such as stores User Information Database.The processor of the server 200 is used to provide
Calculate and control ability, support the operation of whole access server.Storage is saved as in the server 200 to be situated between
The operation of the customer information control system in matter provides environment.The network interface of the server 200 be used for it is outer
The terminal in portion is communicated by network connection, such as the facial image of the user that receiving terminal 200 sends and user
Registration request etc..
As shown in figure 3, in one embodiment, there is provided a kind of user information management method, the method can be answered
In for server as shown in Figure 1, following steps are specifically included:
Step 201, the facial image of the user that receiving terminal 200 sends.
In the present embodiment, terminal 200 includes shooting the image collection module of facial image, and terminal 200 can be with
Position by the facial image of software application interface transmission user, or by sensing the face of user
Sent after automatically snapping the facial image of user.Wherein, the face figure of user is sent by software application interface
Seem that the user's identification button or other specific function buttons startup image provided by software application interface are provided
Acquisition module shoots the facial image of user and sends.Automatically snapped by the position for sensing the face of user and used
Family refers to the face alignment image collection module that user is determined whether by infrared sensing, is obtained with starting image
Modulus block shoots the facial image of user and sends.
Step 203, using the face identification method based on deep learning, recognizes the characteristic value of the facial image.
The basic thought of deep learning refers to the learning process of the brain that people is simulated by neutral net, with energy
The multilayer abstract mechanism of human brain is enough used for reference to realize to real-world object or data (such as image, voice and text
Deng) abstract expression, integration characteristics are extracted and grader is under a learning framework, the extraction process of feature
In as far as possible reduce human intervention.
Deep learning model is made up of the neuron of multilayer, and every layer of neuron receives lower one layer of nerve
The input of unit, by the non-linear relation between input and output, by the combinations of features of low layer into higher
Abstract mark, to find the distributed nature of observation data.Taking out for multilayer is formed by study from bottom to top
As mark, and multi-level feature learning is an automatic unmanned process intervened.According to the nerve for learning
The sample data of input is mapped to various levels of feature by network structure, system, using grader or
Classification and Identification is carried out to the output unit of top layer with algorithm.
According to the basic thought of deep learning, using the face identification method based on deep learning in the present embodiment
Including setting up nerve network system model by autocoding (AutoEncoder), the neutral net set up
System model includes input layer, output layer and some hidden layers, has connection between only adjacent node layer, together
It is mutually connectionless between one layer and cross-layer node.Each layer of neutral net is instructed using input facial image
Practice, after one group of original input facial image is given, during by nerve network system including n-layer, lead to
The parameter crossed in adjustment nerve network system model so that any one layer of input and output is equal, and most
Whole system output is equal with input, i.e. system output is still input facial image, so as to obtain input face
The a series of level characteristics of image, that is, obtain the characteristic value of input facial image.Wherein, to neutral net
The process that system model is trained is trained to training including preceding with backward.Forward direction training process is for from bottom to top
Unsupervised learning, i.e., since bottom, the training of past top layer in layer, in training process, training is learned
Acquistion, using n-1 layers of output as the input of n-th layer, trains n-th layer, thus to after the (n-1)th layer parameter
Respectively obtain the parameter of each layer;Backward training process is top-down supervised learning, i.e. training error from top
Transmission downwards, so as to the parameter to each layer of nerve network system model is finely adjusted.
As other optional embodiment, can also use dilute using the face identification method based on deep learning
Dredge coding (Sparse Coding) or limited Boltzmann machine (Restrict Boltzmann Machine, RBM)
Set up nerve network system model.Wherein sparse coding refers to plus limitation on the basis of autocoding
(Regularity) output equal limitation and, must be input into loosen, at the same using in linear algebra base it is general
Read, i.e. O=W1*B1+W2*B2+ ...+Wn*Bn, wherein, O is output, and I is input, and Bi is base,
Wi is coefficient, formula is optimized by solving Min | I-O |, in the hope of base Bi and coefficient Wi, by these bases
, used as another approximate expression being input into, along with the limitation of L1, wherein L1 is main for Bi and coefficient Wi
It is that major part is 0 in constraining the node in each layer, only a small number of is not 0, obtains Min | I-O |+u*
(|W1|+|W2|+…+|Wn|).In the nerve network system model set up using sparse coding, by face figure
As being input into, such that it is able to automatically learn to being hidden in face image data potential basic function conduct
Characteristic value.
The nerve network system model set up using limited Boltzmann machine can be considered including visual layers, that is, be input into
The bigraph (bipartite graph) of data Layer (v) and hidden layer (h), without connection between each layer of node, it is assumed that all of node
All it is two-valued variable node, and assumes that full probability distribution p (v, h) meets ANALOGY OF BOLTZMANN DISTRIBUTION, as input v
Afterwards, hidden layer h can be obtained by p (h | v), and after obtaining hidden layer h, by p (v | h) and can weight
Structure input data layer, by adjusting parameter so that if the input layer and former input layer one that are obtained from hidden layer
Sample, then the hidden layer for obtaining is exactly another expression of input data layer, can be made so as to obtain hidden layer
To be input into the characteristic value of layer data.Therefore using the recognizable face figure of the input of facial image as input data layer
The characteristic value of picture.The number of plies of the hidden layer of limited Boltzmann machine is increased, depth Boltzmann can be obtained
Machine, so that the characteristic value accuracy of identification of facial image is higher.
In the present embodiment, using the face identification method based on deep learning, nerve is set up by deep learning
Network system model, can automatically learn the other method for expressing of face image data, that can dock
The facial image of the user that the terminal for receiving sends is identified, to extract corresponding characteristic value.Wherein, it is deep
Degree study can also be realized using other deep learning methods in the prior art.
Step 205, whether there is identity corresponding with the characteristic value in searching user's information database.
In the present embodiment, identity is being capable of the unique corresponding numbering for identifying user identity.User believes
Be stored with breath database user facial image characteristic value and identity mapping relations.By identification
After going out the characteristic value of facial image, by the characteristic value one of the facial image in characteristic value and user data information storehouse
One contrast, is matched by being inquired in User Information Database with the characteristic value of the facial image of user
Facial image and determine the identity of user.Used as another optional embodiment, identity can also
Be other can the unique corresponding information for identifying user identity, such as information such as name, sex and ages
Combination etc..
, there is identity mark corresponding with the characteristic value in the User Information Database is inquired in step 207
During knowledge, the user profile record that is mutually related with the identity in the User Information Database is inquired about.
Wherein, user profile is recorded and determined by the purpose of user management, such as the user management of businessman of service industry
Final purpose be to obtain more loyal users, it is therefore desirable to it is more to understand old users and identification and attract newly
User, corresponding user profile record includes consuming relative recording and user basic information.The basic letter of user
Ceasing includes the personal information of user, such as the classification of address name, sex, address, age and user, such as
Honored guest user, domestic consumer or other special users that different businessmans need to carry out user according to oneself management
Deng classification etc..Consumption relative recording includes history consumer record, cumulative consumption number in user's different time sections
Volume, application give the information such as the record of commodity, the record of purchase commodity sales promotion.
User profile record is corresponding with identity, is stored in User Information Database, the user profile
The content of record can be set by the different regulatory requirements to user.
Step 209, is sent to the user profile record terminal and is shown.
User profile is recorded and shown in terminal 100, is easy to understand from terminal 100 and judge the body of user
Part and/or behavioural habits etc., realize the management to user.Subscriber information management with businessman of service industry is
Example, in the business activity of service industry, by issuing commodity sales promotion or giving particular commodity more to get
User be the means often used, in such business activity, for businessman, it is desirable to same
User will not repeat to get commodity sales promotion or give commodity, and it is desired to ensure that more users can be by neck
Get commodity sales promotion or give commodity and reach advertisement function, and for a user, then may think to the greatest extent
May more than get commodity sales promotion or give commodity.In a preferred embodiment, the user profile record
Including getting promotional item or giving the record of commodity, identification is carried out by the facial image of user and is inquired
User profile is recorded, such that it is able to learn that whether user got promotional item or give commodity, effectively prevented
The repetition of user is claimed, and be can guarantee that again if being strictly that the user not claimed just can claim.
In the present embodiment, the management method of user profile passes through the facial image of user in real and based on deep
Spend the recognition of face of study, the identity of automatic identification user such that it is able to it should be understood that the letter of user
Breath record when can inquire about, such as service industry businessman inquiry consumption user history consumption relative recording or
Whether it is the information record such as VIP user or new user, realizes the efficient management to user profile, this kind of side
Method is safe and reliable, the individual privacy of user is not related to, and save the entity card for representing user identity
The puzzlements such as the cost and carrying inconvenience of piece;Recognition of face based on deep learning can realize the knowledge of high-accuracy
The face characteristic of other user, prevents the leak being identified using photo, face characteristic to be not susceptible to environment shadow
Ring, reliability is high, and anti-counterfeiting performance is good.
In one embodiment, step 203, using the face identification method based on deep learning, identification is described
The characteristic value of facial image includes:The API of recognition of face open platform is called, is opened by the recognition of face
Platform carries out recognition of face and extracts the characteristic value of the facial image.Wherein, open platform refers to software system
System makes the outside program can be with by disclose its application programming interface (API) or function (function)
Increase the function or the resource using the software systems of the software systems, without changing the software systems
Source code.Recognition of face open platform is to refer to realize recognition of face based on facial image and extract face figure
The open platform of the characteristic value of picture.The knowledge of facial image is realized by way of calling recognition of face open platform
Not, the deep learning module of itself can be saved, cost is significantly reduced, and give full play to open flat
The relative independentability of platform perfect in shape and function so that the precision of its identification can be carried with the gradual perfection of open platform
Rise.
In another embodiment, Fig. 4 is referred to, whether is deposited in step 205, searching user's information database
After identity corresponding with the characteristic value, including:
Step 2061, does not exist body corresponding with the characteristic value in the User Information Database is inquired
During part mark, identity corresponding with the characteristic value is set up;
Step 2062, stores the characteristic value is corresponding with the corresponding identity to the user profile
Database.
When not existing identity corresponding with the characteristic value in inquiring User Information Database, visually
For the user be new user, by setting up identity corresponding with the characteristic value, by the characteristic value with
The corresponding identity correspondence is stored to the User Information Database, to improve user profile number in real time
According to storehouse.When long-term renewal during script has been stored in User Information Database causes to recognize
Corresponding characteristic value and identity can also be re-established and store, automatically to update user profile data
Storehouse.
Further, Fig. 4 is referred to, the facial image of the user sent in step 201, receiving terminal 100
Before, it is further comprising the steps of:
Step 102, receives the user's registration request that the terminal 100 sends.
Terminal 100 initiates user's registration by software application interface asks, and can be by soft specifically
The new user button of registration or other buttons that part application interface is provided initiate user's registration request.Terminal 100
User's registration is sent to server 200 to ask, to enter into user's registration flow.User's registration flow includes
Three below step.
Step 104, receives the facial image of the user that the terminal 100 sends.
Step 106, using the face identification method based on deep learning, recognizes the characteristic value of the facial image.
Step 108, sets up identity corresponding with the characteristic value, and the characteristic value is corresponding with described
Identity correspondence is stored to the User Information Database.
In the present embodiment, step 104,106 respectively with step 201,203 identical.Wherein, step 104
In, the facial image that terminal 100 sends user can also be the initiation user provided by software application interface
Registration request and start image collection module shoot user facial image and be sent to server 200.It is new when having
During user, user's registration is sent by terminal 100 and is asked, server 200 receives the transmission of terminal 100
When user's registration is asked, then receive the facial image of the user of the transmission of the terminal 100 and use based on deep
The face identification method of study is spent, is recognized after the characteristic value of the facial image, set up automatically and the spy
Log-on message is stored to complete by the corresponding identity of value indicative to form the log-on message of new user
The registration of new user, forms initial User Information Database, convenient follow-up identification and tracking to the user
Management.
As another optional embodiment, the facial image of a part of user in initial User Information Database
Characteristic value can be from the human face data of the opening of existing recognition of face open platform with corresponding identity
Imported in storehouse, just can be realized thus for this certain customers also can be by the user management without registration
System is identified and tracing management.
In one embodiment, Fig. 4 is referred to, whether is deposited in step 205, searching user's information database
After identity corresponding with the characteristic value, also include:
, there is identity mark corresponding with the characteristic value in the User Information Database is inquired in step 206
During knowledge, this information record of user to the User Information Database is stored.
When there is identity corresponding with the characteristic value in inquiring the User Information Database, deposit
This information record of the user to User Information Database is stored up, it is real in order to be inquired about when needing
Now to the lasting tracing management of old user.
As shown in figure 5, in one embodiment, there is provided a kind of customer information control system, the system bag
Include image-receptive mould, 10, face recognition module 20, identification module 30, enquiry module 40 and transmission mould
Block 50,
Wherein, image receiver module 10 is used for the facial image of the user that receiving terminal sends.
Face recognition module 20 is used to, using the face identification method based on deep learning, recognize the face figure
The characteristic value of picture.
Identification module 30 is used in searching user's information database with the presence or absence of corresponding with the characteristic value
Identity.
Enquiry module 40 is used in the User Information Database is inquired in the presence of corresponding with the characteristic value
The user profile note that is mutually related with the identity in the User Information Database is inquired about during identity
Record.
Sending module 50 is shown for user profile record to be sent into the terminal.
In one embodiment, as shown in fig. 6, the customer information control system also sets up module including mark
60 and memory module 70,
Wherein, mark set up module 60 for when inquire in the User Information Database in the absence of with it is described
During the corresponding identity of characteristic value, identity corresponding with the characteristic value is set up.
Memory module 70 is used to store the characteristic value is corresponding with the corresponding identity to the user
Information database.
Further, as shown in fig. 7, in one embodiment, the customer information control system includes user
Register device and customer identification device.The customer identification device includes the image-receptive in embodiment illustrated in fig. 5
Module 10, face recognition module 20, identification module 30, enquiry module 40 and sending module 50 or
Image receiver module 10, face recognition module 20, identification module 30 in embodiment illustrated in fig. 6, look into
Ask module 40, sending module 50, mark and set up module 60 and memory module 70.The user's registration device bag
Include request receiving module 801, mark and set up module 802 and memory module 803.
Wherein, request receiving module 801 is used to receive the user's registration request of the transmission of the terminal 100.
Mark sets up module 802 for recognizing the characteristic value of the facial image in the face recognition module 20
Afterwards, identity corresponding with the characteristic value is set up.
Memory module 803 is used to store the characteristic value is corresponding with the corresponding identity to the use
Family information database.
Mark in the user's registration device set up module 802 and memory module 803 can respectively with Fig. 6 institutes
Show that the mark in customer identification device sets up module 60 and memory module 70 is equal modules, or divides
It is not independent.The function of customer identification device is realization under the normal operation state of terminal 100 in the present embodiment
Function, and the new user's registration that the function of user's registration device is provided by the software application interface of terminal 100
The user's registration that button is initiated is asked and started;As an alternative embodiment, the user's identification dress
Putting can also include that request receiving module is used for the user's identification request that receiving terminal 100 sends, and accordingly should
The function of customer identification device is initiated by the user's identification button that the software application interface of terminal 100 provides
User's identification is asked and started.
In another embodiment, Fig. 6 is referred to, face recognition module 20 includes API Calls unit 22, API
Call unit 22 is used to call the API of recognition of face open platform, is entered by the recognition of face open platform
Row recognition of face simultaneously extracts the characteristic value of the facial image.Recognition of face open platform is referred to based on people
Face image realizes recognition of face and extracts the open platform of the characteristic value of facial image.By calling recognition of face
The mode of open platform realizes the identification of facial image, can save the deep learning module of itself, greatly
Cost is reduced, and gives full play to the relative independentability of open platform perfect in shape and function so that the essence of its identification
Degree can be lifted with the gradual perfection of open platform.
In one embodiment, as shown in figure 8, the customer information control system also includes memory module 90, use
In when there is identity corresponding with the characteristic value in inquiring the User Information Database, store
This information record of the user is to the User Information Database.When inquiring the user profile data
When there is identity corresponding with the characteristic value in storehouse, this information record of user to use is stored
Family information database, in order to be inquired about when needing, realizes the tracing management to old user.As one
In optional embodiment, the memory module 90 is identical molds with the memory module 70 in embodiment illustrated in fig. 6
Block, for when in inquiring the User Information Database exist identity corresponding with the characteristic value when,
To be used for respectively by the characteristic value it is corresponding with the corresponding identity store to User Information Database and
User this information record is stored to User Information Database.
One of ordinary skill in the art will appreciate that all or part of flow in realizing above-described embodiment method,
Computer program be can be by instruct the hardware of correlation to complete, described program can be stored in a calculating
In machine read/write memory medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.
Wherein, described storage medium can for magnetic disc, CD, read-only memory (Read-Only Memory,
) or random access memory (Random Access Memory, RAM) etc. ROM.
Embodiment described above only expresses several embodiments of the invention, and its description is more specific and detailed,
But can not therefore be construed as limiting the scope of the patent.It should be pointed out that for this area
For those of ordinary skill, without departing from the inventive concept of the premise, some deformations can also be made and changed
Enter, these belong to protection scope of the present invention.
Claims (10)
1. a kind of user information management method, including:
The facial image of the user that receiving terminal sends;
Using the face identification method based on deep learning, the characteristic value of the facial image is recognized;
Whether there is identity corresponding with the characteristic value in searching user's information database;
When there is identity corresponding with the characteristic value in inquiring the User Information Database,
Inquire about the user profile record that is mutually related with the identity in the User Information Database;
User profile record is sent into the terminal to be shown.
2. user information management method according to claim 1, it is characterised in that methods described is also wrapped
Include:
Do not exist identity corresponding with the characteristic value in the User Information Database is inquired
When, set up identity corresponding with the characteristic value;
Store the characteristic value is corresponding with the corresponding identity to the User Information Database.
3. user information management method according to claim 1, it is characterised in that received eventually described
It is further comprising the steps of before the step of holding the facial image of the user for sending:
Receive the user's registration request that the terminal sends;
Receive the facial image of the user that the terminal sends;
Using the face identification method based on deep learning, the characteristic value of the facial image is recognized;
Identity corresponding with the characteristic value is set up, by the characteristic value and the corresponding identity mark
Know correspondence to store to the User Information Database.
4. the user information management method according to claim 1 or 2 or 3, it is characterised in that described
Include using the face identification method based on deep learning, the step of the characteristic value for recognizing the facial image:
The API of recognition of face open platform is called, recognition of face is carried out simultaneously by the recognition of face open platform
Extract the characteristic value of the facial image.
5. user information management method according to claim 1, it is characterised in that the inquiry user
After the step of whether there is identity corresponding with the characteristic value in information database, also include:When
Inquire when there is identity corresponding with the characteristic value in the User Information Database, storage is described
This information record of user is to the User Information Database.
6. a kind of customer information control system, including:
Image receiver module, the facial image of the user sent for receiving terminal;
Face recognition module, for using the face identification method based on deep learning, recognizing the face
The characteristic value of image;
Identification module, it is corresponding with the characteristic value for whether there is in searching user's information database
Identity;
Enquiry module, it is corresponding with the characteristic value for existing in the User Information Database is inquired
Identity when, inquire about the user that is mutually related with the identity in the User Information Database
Information record;
Sending module, is shown for user profile record to be sent into the terminal.
7. customer information control system according to claim 6, it is characterised in that also include:
Mark sets up module, for not existing and the feature in the User Information Database is inquired
When being worth corresponding identity, identity corresponding with the characteristic value is set up;
Memory module, for storing the characteristic value is corresponding with the corresponding identity to the use
Family information database.
8. customer information control system according to claim 6, it is characterised in that:The system is also wrapped
Include:
Request receiving module, for receiving the user's registration request that the terminal sends;
Mark sets up module, for after the characteristic value that the face recognition module recognizes the facial image,
Set up identity corresponding with the characteristic value;
Memory module, for storing the characteristic value is corresponding with the corresponding identity to the user
Information database.
9. the user information management method according to claim 6 or 7 or 8, it is characterised in that:It is described
Face recognition module includes API Calls unit, the API for calling recognition of face open platform, by institute
Stating recognition of face open platform carries out recognition of face and extracts the characteristic value of the facial image.
10. user information management method according to claim 6, it is characterised in that:The system is also
It is corresponding with the characteristic value for existing in the User Information Database is inquired including memory module
During identity, this information record of user to the User Information Database is stored.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510797129.4A CN106713255B (en) | 2015-11-17 | 2015-11-17 | User information management method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510797129.4A CN106713255B (en) | 2015-11-17 | 2015-11-17 | User information management method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106713255A true CN106713255A (en) | 2017-05-24 |
CN106713255B CN106713255B (en) | 2020-07-24 |
Family
ID=58933552
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510797129.4A Active CN106713255B (en) | 2015-11-17 | 2015-11-17 | User information management method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106713255B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107705398A (en) * | 2017-09-07 | 2018-02-16 | 平安科技(深圳)有限公司 | service providing method, device, storage medium and computing device |
CN108133533A (en) * | 2018-02-23 | 2018-06-08 | 王志强 | A kind of synthesis door meets management system |
CN108776791A (en) * | 2018-06-07 | 2018-11-09 | 中国平安人寿保险股份有限公司 | Client identity identifies method of calibration, device, computer equipment and storage medium |
CN108924258A (en) * | 2018-08-14 | 2018-11-30 | 深圳壹账通智能科技有限公司 | Background information method for pushing, device, computer equipment and storage medium |
CN109858219A (en) * | 2018-12-22 | 2019-06-07 | 深圳市珍爱捷云信息技术有限公司 | User registering method, device, electronic equipment and computer readable storage medium |
CN109902531A (en) * | 2017-12-07 | 2019-06-18 | 北京京东金融科技控股有限公司 | User management method, device, medium and electronic equipment |
CN110245964A (en) * | 2019-06-14 | 2019-09-17 | 北京市商汤科技开发有限公司 | Information-pushing method and device and storage medium |
CN111368101A (en) * | 2020-03-05 | 2020-07-03 | 腾讯科技(深圳)有限公司 | Multimedia resource information display method, device, equipment and storage medium |
CN111881759A (en) * | 2020-06-30 | 2020-11-03 | 青岛海尔科技有限公司 | Identity category identification method and device and storage medium |
CN112580010A (en) * | 2020-12-23 | 2021-03-30 | 四川虹微技术有限公司 | Biological feature sharing method and device, electronic equipment and storage medium |
CN114969151A (en) * | 2022-05-12 | 2022-08-30 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Energy consumption data mining system based on neural network |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110188712A1 (en) * | 2010-02-04 | 2011-08-04 | Electronics And Telecommunications Research Institute | Method and apparatus for determining fake image |
CN102592116A (en) * | 2011-12-27 | 2012-07-18 | Tcl集团股份有限公司 | Cloud computing application method, system and terminal equipment, and cloud computing platform |
CN104102927A (en) * | 2013-04-01 | 2014-10-15 | 三星电子株式会社 | Display apparatus for performing user certification and method thereof |
CN104270253A (en) * | 2014-10-21 | 2015-01-07 | 中国建设银行股份有限公司 | Method, devices and system for user identity authentication |
CN104463123A (en) * | 2014-12-11 | 2015-03-25 | 南威软件股份有限公司 | B/S-based face recognition method and system |
CN104573679A (en) * | 2015-02-08 | 2015-04-29 | 天津艾思科尔科技有限公司 | Deep learning-based face recognition system in monitoring scene |
CN104573619A (en) * | 2014-07-25 | 2015-04-29 | 北京智膜科技有限公司 | Method and system for analyzing big data of intelligent advertisements based on face identification |
CN104899579A (en) * | 2015-06-29 | 2015-09-09 | 小米科技有限责任公司 | Face recognition method and face recognition device |
-
2015
- 2015-11-17 CN CN201510797129.4A patent/CN106713255B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110188712A1 (en) * | 2010-02-04 | 2011-08-04 | Electronics And Telecommunications Research Institute | Method and apparatus for determining fake image |
CN102592116A (en) * | 2011-12-27 | 2012-07-18 | Tcl集团股份有限公司 | Cloud computing application method, system and terminal equipment, and cloud computing platform |
CN104102927A (en) * | 2013-04-01 | 2014-10-15 | 三星电子株式会社 | Display apparatus for performing user certification and method thereof |
CN104573619A (en) * | 2014-07-25 | 2015-04-29 | 北京智膜科技有限公司 | Method and system for analyzing big data of intelligent advertisements based on face identification |
CN104270253A (en) * | 2014-10-21 | 2015-01-07 | 中国建设银行股份有限公司 | Method, devices and system for user identity authentication |
CN104463123A (en) * | 2014-12-11 | 2015-03-25 | 南威软件股份有限公司 | B/S-based face recognition method and system |
CN104573679A (en) * | 2015-02-08 | 2015-04-29 | 天津艾思科尔科技有限公司 | Deep learning-based face recognition system in monitoring scene |
CN104899579A (en) * | 2015-06-29 | 2015-09-09 | 小米科技有限责任公司 | Face recognition method and face recognition device |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107705398A (en) * | 2017-09-07 | 2018-02-16 | 平安科技(深圳)有限公司 | service providing method, device, storage medium and computing device |
CN109902531B (en) * | 2017-12-07 | 2021-10-01 | 北京京东金融科技控股有限公司 | User management method, device, medium and electronic equipment |
CN109902531A (en) * | 2017-12-07 | 2019-06-18 | 北京京东金融科技控股有限公司 | User management method, device, medium and electronic equipment |
CN108133533A (en) * | 2018-02-23 | 2018-06-08 | 王志强 | A kind of synthesis door meets management system |
CN108776791A (en) * | 2018-06-07 | 2018-11-09 | 中国平安人寿保险股份有限公司 | Client identity identifies method of calibration, device, computer equipment and storage medium |
CN108924258A (en) * | 2018-08-14 | 2018-11-30 | 深圳壹账通智能科技有限公司 | Background information method for pushing, device, computer equipment and storage medium |
CN108924258B (en) * | 2018-08-14 | 2022-07-08 | 深圳壹账通智能科技有限公司 | Background information pushing method and device, computer equipment and storage medium |
CN109858219A (en) * | 2018-12-22 | 2019-06-07 | 深圳市珍爱捷云信息技术有限公司 | User registering method, device, electronic equipment and computer readable storage medium |
CN110245964A (en) * | 2019-06-14 | 2019-09-17 | 北京市商汤科技开发有限公司 | Information-pushing method and device and storage medium |
CN111368101B (en) * | 2020-03-05 | 2021-06-18 | 腾讯科技(深圳)有限公司 | Multimedia resource information display method, device, equipment and storage medium |
CN111368101A (en) * | 2020-03-05 | 2020-07-03 | 腾讯科技(深圳)有限公司 | Multimedia resource information display method, device, equipment and storage medium |
CN111881759A (en) * | 2020-06-30 | 2020-11-03 | 青岛海尔科技有限公司 | Identity category identification method and device and storage medium |
CN112580010A (en) * | 2020-12-23 | 2021-03-30 | 四川虹微技术有限公司 | Biological feature sharing method and device, electronic equipment and storage medium |
CN112580010B (en) * | 2020-12-23 | 2024-01-30 | 四川虹微技术有限公司 | Biological feature sharing method and device, electronic equipment and storage medium |
CN114969151A (en) * | 2022-05-12 | 2022-08-30 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Energy consumption data mining system based on neural network |
Also Published As
Publication number | Publication date |
---|---|
CN106713255B (en) | 2020-07-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106713255A (en) | Use information management method and system | |
US11341515B2 (en) | Systems and methods for sensor data analysis through machine learning | |
Baran et al. | Customer Relationship Management: the foundation of contemporary marketing strategy | |
US9361623B2 (en) | Preferred customer marketing delivery based on biometric data for a customer | |
CN111784455A (en) | Article recommendation method and recommendation equipment | |
US20100082403A1 (en) | Advocate rank network & engine | |
CN107301578A (en) | Obtain and recognize the method and its device of customer information | |
CN106055710A (en) | Video-based commodity recommendation method and device | |
CN110163715A (en) | Information recommendation method, device, equipment and system | |
WO2021185281A1 (en) | Shelf interaction method and shelf | |
US20220101420A1 (en) | Computer-implemented methods and system for customized interactive image collection based on customer data | |
CN104852892B (en) | A kind of autonomous login method of novel Internet of Things web station system | |
US20180018729A1 (en) | Systems, methods, and computer program products for intelligently processing and manipulating a subject image according to consumer data | |
US20210233152A1 (en) | System and Method for Fashion Recommendations | |
CN111008335B (en) | Information processing method, device, equipment and storage medium | |
CN104575339A (en) | Media information pushing method based on face detection interface | |
CN107392614A (en) | The implementation method and device of off-line transaction | |
CN108564364A (en) | A kind of rural culture big data credit investigation system precisely drawn a portrait based on block chain technology and user | |
US20210390567A1 (en) | System and method for content recognition and data categorization | |
US11244382B1 (en) | Computer-implemented method and system for auto-generation of multi-merchant interactive image collection | |
Gregorczuk | Retail analytics: Smart-stores saving bricks-and-mortar retail or a privacy problem? | |
US11526925B2 (en) | System and method for fashion recommendations | |
CN113672816B (en) | Account feature information generation method and device, storage medium and electronic equipment | |
US20230106289A1 (en) | Favorite merchants selection in transaction based authentication | |
KR102275255B1 (en) | System of goods transaction brokerage for business opening and closing |
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 |