CN110458644A - A kind of information processing method and relevant device - Google Patents
A kind of information processing method and relevant device Download PDFInfo
- Publication number
- CN110458644A CN110458644A CN201910604331.9A CN201910604331A CN110458644A CN 110458644 A CN110458644 A CN 110458644A CN 201910604331 A CN201910604331 A CN 201910604331A CN 110458644 A CN110458644 A CN 110458644A
- Authority
- CN
- China
- Prior art keywords
- target user
- information
- image
- target
- service product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to technical field of biometric identification, a kind of information processing method and relevant device are specifically disclosed, this method comprises: obtaining the identity information of target user；Based on the customer data base pre-established, the determining and matched action trail of identity information, it specifically includes: such as the image information that identity information is target user, region detection is carried out to image information according to algorithm of target detection, determine the target area in image information comprising face, face-image in target area is formed into input data, input data is input to preparatory trained neural network model, obtain the character pair vector of face-image, feature vector and the template vector in user library data are compared, obtained and the matched action trail of target user；According to action trail determination and the matched service product of target user, service product is sent to default terminal, to recommend service product to target user.The application, which is conducive to improve, recommends success rate.
Description
Technical field
This application involves technical field of biometric identification, and in particular to a kind of information processing method and relevant device.
Background technique
As the improvement of people's living standards, economic structure is perfect, more and more Xian Xia banks occur, moreover, often
It has the client of many people's transacting business in the banking hall, and bank clerk can only be visitor according to the demand of client
Corresponding business is handled at family, and the potential demand of each client can not be known for bank clerk.For example, hall, bank fund
Sales force can not determine which client has the intention of purchase fund, push away to carry out fund product to these potential customers
It recommends, for another example, credit card business personnel can not know which portions of client needs to handle credit card, to can not carry out to these users
The recommendation of credit card.
When carrying out Products Show in the prior art, to customer resources using low, specific aim is low.
Summary of the invention
The embodiment of the present application provides a kind of information processing method and relevant device, to carry out business by information matches
Products Show, to improve the success rate of Products Show.
In a first aspect, the embodiment of the present application provides a kind of information processing method, comprising:
Obtain the identity information of target user；
Based on the customer data base pre-established, the determining and matched action trail of the identity information is specifically included: such as
Identity information is the image information of the target user, carries out region detection to described image information according to algorithm of target detection,
It determines the target area in described image information comprising face, the face-image in the target area is formed into input data,
The input data is input to preparatory trained neural network model, obtains the character pair vector of the face-image,
Described eigenvector and the template vector in the user library data are compared, obtained and the matched behavior rail of the target user
Mark；
According to action trail determination and the matched service product of the target user, the industry is sent to default terminal
Business product, to recommend the service product to the target user.
Second aspect, the embodiment of the present application provide a kind of information processing unit, comprising:
Acquiring unit, for obtaining the identity information of target user；
Matching unit, for based on the customer data base pre-established, the determining and matched behavior rail of the identity information
Mark is specifically used for: if identity information is the image information of the target user, according to algorithm of target detection to described image information
Region detection is carried out, the target area in described image information comprising face is determined, by the face-image in the target area
Input data is formed, the input data is input to preparatory trained neural network model, obtains the face-image
Character pair vector compares described eigenvector and the template vector in the user library data, obtains using with the target
The matched action trail in family；
Determination unit, for determining with the matched service product of the target user according to the action trail, to default
Terminal sends the service product, to recommend the service product to the target user.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, including processor, memory, communication interface and
One or more programs, wherein one or more of programs are stored in the memory, and are configured by described
It manages device to execute, described program is included the steps that for executing the instruction in method as described in relation to the first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, the computer-readable storage medium
Matter is stored with computer program, and the computer program makes the method for computer execution as described in relation to the first aspect.
Implement the embodiment of the present application, has the following beneficial effects:
As can be seen that obtaining user information in embodiments herein, behavior rail corresponding with user information is searched
Mark determines matched service product according to action trail, so that progress is targetedly business recommended, improves business recommended effect
Rate and success rate.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is some embodiments of the present application, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of flow diagram of information processing method provided by the embodiments of the present application；
Figure 1A is a kind of schematic diagram for forming input data provided by the embodiments of the present application；
Fig. 2 is the flow diagram of another information processing method provided by the embodiments of the present application；
Fig. 3 is the flow diagram of another information processing method provided by the embodiments of the present application；
Fig. 4 is a kind of structural schematic diagram of information processing unit provided by the embodiments of the present application；
Fig. 5 is that a kind of functional unit of information processing unit provided by the embodiments of the present application forms block diagram.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on this Shen
Please in embodiment, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall in the protection scope of this application.
The description and claims of this application and term " first ", " second ", " third " and " in the attached drawing
Four " etc. are not use to describe a particular order for distinguishing different objects.In addition, term " includes " and " having " and it
Any deformation, it is intended that cover and non-exclusive include.Such as it contains the process, method of a series of steps or units, be
System, product or equipment are not limited to listed step or unit, but optionally further comprising the step of not listing or list
Member, or optionally further comprising other step or units intrinsic for these process, methods, product or equipment.
Referenced herein " embodiment " is it is meant that the special characteristic, result or the characteristic that describe can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
Information processing unit, target terminal and default terminal in the application may include smart phone (such as Android
Mobile phone, iOS mobile phone, Windows Phone mobile phone etc.), tablet computer, palm PC, laptop, mobile internet device
MID (Mobile Internet Devices, referred to as: MID) or wearable device etc., above-mentioned electronic equipment is only citing, rather than
Above-mentioned electronic equipment for convenience of description, is known as using by exhaustion including but not limited to above-mentioned electronic equipment in following example
Family equipment UE (User equipment, referred to as: UE).Certainly in practical applications, above-mentioned user equipment is also not necessarily limited to above-mentioned change
Existing form, such as can also include: intelligent vehicle mounted terminal, computer equipment etc..
Refering to fig. 1, Fig. 1 is a kind of information processing method provided by the embodiments of the present application, and this method is applied to information processing
Device, this method include the content as shown in step S101~S103:
Step S101, the identity information of target user is obtained.
Wherein, target user is the user in bank's transacting business.
Optionally, as the identity information be MAC address, obtain the realization of the identity information of target user
Process can be with are as follows: intercepts any frame data that the target terminal is sent by the wifi probe of predeterminated position, parses the frame
The information of MAC layer and physical layer in data, obtains the MAC Address of target terminal, wherein the target terminal is target user
Terminal.Specifically, wifi probe can be pre-set near bank queuing machine, when target user leads in bank queuing machine
When taking queue number, the MAC Address of the target terminal is obtained by the wifi probe, it certainly, can also be preparatory by the wifi probe
Other positions are set to, to obtain the MAC Address of target terminal, the application does not do unique restriction, for example, may also be disposed on bank
Inlet.
Optionally, such as the image information that the identity information is target user, the realization of the identity information of target user is obtained
Process can be with are as follows: the image information of the target user is obtained by the camera of predeterminated position, wherein the predeterminated position is taken the photograph
As head can be the camera at the camera or bank queuing machine of bank monitoring system.
In a possible example, after the identity information for obtaining target user, the method also includes: record currently obtains
The first moment of the identity information of the target user is taken, acquisition last time obtains the second moment of the identity information of the target user,
The time difference for determining the first moment and the second moment ignores the identity information if the time difference is less than time threshold.It can see
Out, it in book example, is avoided by time difference judgement frequently to target user's frequent progress Products Show, to reduce target use
The dislike degree at family.
Wherein, which can be 1 hour, 1 day, 2 days or other values.
Step S102, based on the customer data base pre-established, the determining and matched action trail of the identity information, tool
Body includes: the image information such as identity information for the target user, is carried out according to algorithm of target detection to described image information
Region detection determines the target area in described image information comprising face, the face-image in the target area is formed
The input data is input to preparatory trained neural network model, obtains the correspondence of the face-image by input data
Feature vector compares described eigenvector and the template vector in the user library data, obtains and the target user
The action trail matched.
Wherein, algorithm of target detection includes but is not limited to following a kind of: R-CNN, Fast R-CNN, SPP, YOLO, SSD
Deng.
In a possible example, by the target area face-image composition input data input data it
Before, the method also includes: pretreatment operation is carried out to face-image, is obtained corresponding with the size that the neural network model is set
Face-image, so that the input data of subsequent composition meets the structure of the neural network model, wherein the pretreatment operation packet
It includes: cutting, expansion, scaling, etc..
Optionally, the realization process of the above-mentioned face-image composition input data by the target area can be with are as follows: obtains
Take the picture element matrix of the face-image in the target area；The picture element matrix is less than to the pixel value zero setting of first threshold；
The convolution kernel size for obtaining the neural network model, it is according to the convolution kernel size that the zero of the picture element matrix after zero setting is tight
Adjacent is arranged in same row or with a line composition input data, composition zero region corresponding with the convolution kernel size；It will
The picture element matrix arranged is labeled as input data.
Specifically, for neural network model, calculating process is generally convolution algorithm, such as obtains and convolution kernel
It is not being lost then when the convolution kernel in input data and neural network model is carried out convolution algorithm in corresponding zero region
When computational accuracy, without participating in operation, the speed of recognition of face is improved.
Wherein, which can be 2,5,10 or other values.
Optionally, which is adjusted according to the loss precision that the neural network model allows.
The process of composition input data is described in detail with reference to Figure 1A.
As shown in Figure 1A, the matrix on the left side is the picture element matrix of the face-image, the i.e. picture element matrix of 6*6, wherein grey
Part is that the pixel of pixel value zero obtains intermediate pixel matrix as shown in Figure 1A after partial pixel value zero setting, such as should
The convolution kernel of neural network model, can be adjacent by the zero in the picture element matrix on the left side according to convolution kernel size having a size of 3*3
It is arranged in upper left corner area, forms the zero region of a 3*3, obtains right pixels matrix shown in figure 1A, i.e. input data,
Therefore when the input data and convolution kernel carry out convolution, since the pixel value in the zero region of the 3*3 is zero, then without into
Row convolution algorithm directly obtains convolution results 0, saves operation time, improves recognition of face speed.
In a possible example, such as identity information is MAC Address, based on the customer data base pre-established, really
The fixed and matched action trail of the identity information, specifically includes: by the MAC in the MAC Address and the user library data
Address set is compared, obtain with the matched destination-mac address of the MAC Address, by the corresponding behavior of the destination-mac address
Action trail of the track as the target user.
Step S103, according to action trail determination and the matched service product of the target user, to default terminal
The service product is sent, to recommend the service product to the target user.
Optionally, the personal information of target user, proprietary information and transacting business as described in the action trail includes,
It can be with according to the determining realization process with the matched service product of the target user of the action trail are as follows: according to the property
Information determines that the target user can transacting business collection；According to the information of transacting business and it is described can transacting business collection it is true
The non-transacting business collection of the fixed target user, that is, obtain this can transacting business collection and transacting business difference set, by the difference set
As the services sets to be handled；Using the non-transacting business collection as the services sets to be handled of the target user；According to described
Personal information determine it is described have wait handling target user described in service set handle at least one of qualification and wait for transacting business；It will
At least one described service marker to be handled be and the matched service product of the target user.
Wherein, the proprietary information include deposit information, can Mortgage assets information etc.；
Wherein, personal information includes name, occupation, age, gender etc..
For example, as the deposit information of the target user is corresponding can transacting business information collection are as follows: it is commercially available to exist at present
Fund or stock are sold, credit card is handled, handles deposit, loan, if the information of transacting business of the target user includes loan industry
Business, fixed deposit business and credit card are opened an account, if the target user meets the limitation of age condition purchase fund, for example, should
Age of user was 25 one full year of life, it is determined that the corresponding target user to transacting business is to buy fund on sale or stock, then will
The fund or stock on sale as with the matched service product of the target user.
Optionally, which is the terminal device of business personnel corresponding with the service product, is sent out to default terminal
Send the realization process of the service product can be with are as follows: the number of calling out the numbers that the target user gets in queue machine to be obtained, on duty by turns
When to the target user；The vocational window where the number of calling out the numbers is obtained, the identity information of the target user, the business are produced
Product and the vocational window are sent to the terminal device, so that the business personnel is that the target user pushes away in the vocational window
Recommend the service product.
As can be seen that in embodiments herein, obtain the identity information in the personnel of bank's transacting business, search with
The corresponding action trail of user information determines matched service product according to action trail, improves the utilization to bank's resource
Rate；It is targetedly business recommended according to action trail progress, it solves the problems, such as blindly to recommend service product in the prior art, mention
High business recommended efficiency and success rate.
In a possible example, the method also includes:
When such as the quantity of at least one service product being multiple, determine in the multiple service product each service product with
The degree of association of transacting business；Priority ranking is carried out to the multiple service product according to the sequence of the degree of association, is arranged
Sequence result；Corresponding default terminal successively is sent by the multiple service product according to the ranking results.It can be seen that In
In this example, when being matched to multiple service products, priority ranking is carried out to service product and is mentioned with carrying out specific aim recommendation
Height recommends success rate.
Optionally, it determines the multiple to each reality to transacting business and the degree of association of transacting business in transacting business
Existing process can be with are as follows: obtain to transacting business and the respective type of service of transacting business, according to type of service determination each to
The degree of association of transacting business and transacting business determines the corresponding degree of association highest of the identical industry service product of type of service,
The settable degree of association is 1.
For example, what such as services sets to be handled included is purchase stock to transacting business, handles credit card, handles society
Card etc. is protected, transacting business includes purchase fund, it is determined that purchase stock is identical as the type of service of fund, and (i.e. financing produces
Product), determine both degree of association highest, preferentially to fund office manager push the target user have purchase fund qualification and
Intention improves the recommendation success rate to service product so that fund office manager preferentially recommends fund product to the target user.
In a possible example, after determining the service product, the method also includes:
Obtain the product type of the service product；When the product type is financial product, used according to the target
The assets information at family determines the amount of money to be put into or the additional amount of money to the financial product；It is described to send the industry to default terminal
Business product include: to the default terminal send the business produce and the corresponding amount of money to be put into of the service product or
The additional amount of money described in person.
In a possible example, the method also includes:
After determining the service product, family corresponding with the target user is obtained from user library database and is drawn
Picture determines that whether the family member of the target user had a service product business handles money according to family portrait
Lattice indicate the business personnel of the default terminal to the target if so, family portrait is sent to the default terminal
The family member of user and/or the target user recommend the service product, to increase recommendation channel, improve recommend at
Power.
In a possible example, after sending the service product to default terminal, the method also includes: to
When the target user recommends the service product, micro- facial expression image of the target user is obtained；To the face-image into
The micro- Expression analysis of row, obtains the emotional information of the target user, determines the target user to institute according to the emotional information
The level of interest of service product is stated, such as the level of interest is less than second threshold, sends to the default terminal preset
Prompt information, the prompt information recommend the service product for prompting to terminate to the target user.In this example, lead to
Micro- Expression analysis is crossed, obtains the emotional information of target user in real time, terminates Products Show in time, target user is reduced and product is pushed away
The dislike degree recommended avoids blindly recommending, improves Products Show efficiency and success rate.
Optionally, in above-mentioned possible example, micro- Expression analysis is carried out to micro- facial expression image, obtains the target
The realization process of the emotional information of user can be with are as follows: micro- facial expression image is carried out RGB channel decomposition, is obtained and the RGB
Corresponding three gray level images in channel；By the gray value of each gray level image in three gray level images from [0,255] two-value
Change the input data that tri- channels RGB are obtained to [0,1]；Convolution algorithm is carried out to the input data in each channel respectively,
Obtain the feature vector in each channel；The mean value for determining the feature vector of the RGB channel, using the mean value as micro- table
Described eigenvector is input to softmax classifier, it is corresponding to obtain the target user by the corresponding feature vector of feelings image
Emotional information.Micro- Expression Recognition is carried out by multichannel, improves the precision of micro- Expression Recognition.
Optionally, in above-mentioned possible example, micro- Expression analysis is carried out to micro- facial expression image, obtains the target
The realization process of the emotional information of user can be with are as follows: is mentioned using histograms of oriented gradients to micro- facial expression image feature
It takes, obtains M characteristic point；Multidimensional expression space is established to micro- facial expression image according to preset intrinsic dimensionality, is obtained described
N number of basic facial expression point in multidimensional expression space；Each spy in the M characteristic point is determined according to N number of basic facial expression point
Potential energy of the sign point in the multidimensional expression space；It is true according to potential energy of each characteristic point in the multidimensional expression space
The corresponding expression information of fixed each characteristic point is matched to obtain with template potential energy the corresponding expression information of each characteristic point；
The corresponding expression information of each characteristic point of synthesis, obtains the emotional information of the target user；Wherein, each basic facial expression point exists
A corresponding basic coordinates, each characteristic point corresponding feature in the multidimensional expression space in the multidimensional expression space
Coordinate.Micro- Expression Recognition is carried out by the more tiny granularity of characteristic point in this example, further increases micro- Expression Recognition
Precision.
Wherein, potential energy of each characteristic point in the multidimensional expression space is determined by following formula:
Wherein, j is j-th of characteristic point in the M characteristic point,For i-th in N number of basic facial expression point
Basic facial expression point, α are preset attenuation coefficient,Between j-th of characteristic point and i-th of basic facial expression point
Euclidean distance,Potential energy for j-th of characteristic point relative to i-th of basic facial expression point, E (s) are institute
State the potential energy of j-th of characteristic point, 1≤j≤M, 1≤i≤N.
In a possible example, the method also includes:
The face-image for acquiring the target user in real time obtains at least one first image, according to it is described at least one
It is business recommended that first image determines whether that business personnel carries out to the target user, if so, determination has business personnel to institute
State target user carry out it is business recommended, if not, determine do not carry out it is business recommended, and in real time to the collected face-image in exit
Identification is carried out, as described in being detected in exit when the face-image of target user, the face of the target user is schemed
As and be associated storage with the matched service product of the target user, so as to next time detect it is described mark user face
When image, directly carry out it is business recommended, without carrying out business matching, to improve recommendation efficiency.
In above-mentioned possible example, determine whether business personnel to the mesh according at least one described first image
Mark user carries out business recommended realization process can be with are as follows: carries out Face datection at least one described first image, determines institute
State the first image that two faces are included at least at least one first image；To first figure for including at least two faces
As carrying out identification, determine in first image including at least two faces whether the face figure comprising business personnel
Picture, according to it is described whether comprising business personnel face-image determine whether business personnel to the target user carry out business
Recommend.
Referring to Fig.2, Fig. 2 is the flow diagram of another information processing method provided by the embodiments of the present application, this method
Applied to information processing unit, this method includes the content as shown in step S201~S203:
Step S201, the identity information of target user is obtained.
Step S202, based on the customer data base pre-established, the determining and matched action trail of the identity information, tool
Body includes: the image information such as identity information for the target user, is carried out according to algorithm of target detection to described image information
Region detection determines the target area in described image information comprising face, the face-image in the target area is formed
The input data is input to preparatory trained neural network model, obtains the correspondence of the face-image by input data
Feature vector compares described eigenvector and the template vector in the user library data, obtains and the target user
The action trail matched.
Step S203, according to action trail determination and the matched service product of the target user, to default terminal
The service product is sent, to recommend the service product to the target user.
Step S204, when recommending the service product to the target user, micro- expression of the target user is obtained
Image.
Step S205, micro- Expression analysis is carried out to micro- facial expression image, obtains the emotional information of the target user, root
The target user is determined to the level of interest of the service product according to the emotional information, and such as level of interest is less than
Second threshold sends preset prompt information to the default terminal.
It should be noted that the specific implementation process of each step of method shown in Fig. 2 can be found in side described in above-mentioned Fig. 1
The specific implementation process of method, no longer describes herein.
As can be seen that in embodiments herein, obtain the identity information in the personnel of bank's transacting business, search with
The corresponding action trail of user information determines matched service product according to action trail, improves the utilization to bank's resource
Rate；It is targetedly business recommended according to action trail progress, it solves the problems, such as blindly to recommend service product in the prior art, mention
High business recommended efficiency and success rate；Moreover, being carried out when carrying out Products Show to target user to the target user
Micro- Expression analysis terminates Products Show, avoids invalid Products Show in user's dislike, is improving Products Show efficiency
When, reduce the dislike degree of user, promotes user experience.
Refering to Fig. 3, Fig. 3 is the flow diagram of another information processing method provided by the embodiments of the present application, this method
Applied to information processing unit, this method includes the content as shown in step S301~S306:
Step S301, the identity information of target user is obtained.
Step S302, based on the customer data base pre-established, the determining and matched action trail of the identity information, tool
Body includes: the image information such as identity information for the target user, is carried out according to algorithm of target detection to described image information
Region detection determines the target area in described image information comprising face, the face-image in the target area is formed
The input data is input to preparatory trained neural network model, obtains the correspondence of the face-image by input data
Feature vector compares described eigenvector and the template vector in the user library data, obtains and the target user
The action trail matched.
Step S303, according to action trail determination and the matched service product of the target user.
Step S304, family's portrait corresponding with the target user is obtained from user library database, according to the family
Race's portrait determines that whether the family member of the target user had a service product business handles qualification, if so, to pre-
If terminal sends the service product and family portrait, with to the family of the target user and/or the target user
Member recommends the service product.
Step S305, recommending the service product to the family member of the target user and/or the target user
When, obtain micro- facial expression image of the target user.
Step S306, micro- Expression analysis is carried out to micro- facial expression image, obtains the emotional information of the target user, root
The target user is determined to the level of interest of the service product according to the emotional information, and such as level of interest is less than
Second threshold sends preset prompt information to the default terminal.
It should be noted that the specific implementation process of each step of method shown in Fig. 3 can be found in side described in above-mentioned Fig. 1
The specific implementation process of method, no longer describes herein.
As can be seen that in embodiments herein, obtain the identity information in the personnel of bank's transacting business, search with
The corresponding action trail of user information determines matched service product according to action trail, improves the utilization to bank's resource
Rate；It is targetedly business recommended according to action trail progress, it solves the problems, such as blindly to recommend service product in the prior art, mention
High business recommended efficiency and success rate；Moreover, obtaining family's portrait of the target user, it is determined whether to family member
The recommendation for carrying out the service product increases the mode of Products Show, improves and recommends success rate；In addition, to target user and/
Or the family member of target user carries out micro- Expression analysis to the target user, in user's dislike, eventually when carrying out Products Show
Only Products Show avoids invalid Products Show, when improving Products Show efficiency, reduces the dislike degree of user,
Promote user experience.
It is consistent with above-mentioned Fig. 1, Fig. 2, embodiment shown in Fig. 3, referring to Fig. 4, Fig. 4 is provided by the embodiments of the present application
A kind of structural schematic diagram of information processing unit 400, as shown in figure 4, information processing unit 400 includes processor, memory, leads to
Believe interface and one or more programs, wherein said one or multiple programs are different from said one or multiple application programs,
And said one or multiple programs are stored in above-mentioned memory, and are configured to be executed by above-mentioned processor, above procedure
Including the instruction for executing following steps:
Obtain the identity information of target user；
Based on the customer data base pre-established, the determining and matched action trail of the identity information is specifically included: such as
Identity information is the image information of the target user, carries out region detection to described image information according to algorithm of target detection,
It determines the target area in described image information comprising face, the face-image in the target area is formed into input data,
The input data is input to preparatory trained neural network model, obtains the character pair vector of the face-image,
Described eigenvector and the template vector in the user library data are compared, obtained and the matched behavior rail of the target user
Mark；
According to action trail determination and the matched service product of the target user, the industry is sent to default terminal
Business product, to recommend the service product to the target user.
In a possible example, obtain target user identity information in terms of, above procedure be specifically used for execute with
The instruction of lower step: if identity information is MAC address, it is whole that target is intercepted by the wifi probe of predeterminated position
Any one frame data sent are held, the information of the MAC layer and physical layer in the frame data is parsed, obtains the target terminal
MAC Address, wherein the target terminal is the terminal of target user；If identity information is the image information of the target user,
The image information of the target user is obtained by the camera of predeterminated position.
In a possible example, in terms of the face-image in the target area is formed input data, above-mentioned journey
Sequence is specifically used for executing the instruction of following steps: obtaining the picture element matrix of the face-image in the target area；By the picture
It is less than the pixel value zero setting of first threshold in prime matrix；The convolution kernel size for obtaining the neural network model, according to the volume
Product core size forms input data, composition by the zero arranged adjacent in the picture element matrix after zero setting in same row or with a line
Zero region corresponding with the convolution kernel size；The picture element matrix arranged is labeled as input data.
In a possible example, as described in the action trail includes the personal information of target user, proprietary information and
Transacting business, in terms of the determining and matched service product of the target user according to the action trail, above procedure tool
Body is used to execute the instruction of following steps: determining that the target user can transacting business collection according to the proprietary information；According to institute
State the business handled and it is described can transacting business collection determine the non-transacting business collection of the target user；It is not handled described
Services sets are as target user services sets to be handled；Wait handle described in service set according to personal information determination
Target user, which has, to handle at least one of qualification and waits for transacting business；By at least one described service marker to be handled be with it is described
The matched service product of target user.
In a possible example, above procedure is also used to execute the instruction of following steps: obtaining the service product
Product type；When the product type is financial product, determined according to the assets information of the target user to the finance
The amount of money to be put into of product or the additional amount of money；
In terms of default terminal sends the service product, above procedure is specifically used for executing the instruction of following steps:
The business production and the corresponding amount of money to be put into of the service product or the addition are sent to the default terminal
The amount of money.
In a possible example, above procedure is also used to execute the instruction of following steps: pushing away to the target user
When recommending the service product, micro- facial expression image of the target user is obtained；Micro- Expression analysis is carried out to micro- facial expression image,
The emotional information of the target user is obtained, sense of the target user to the service product is determined according to the emotional information
Levels of interest, such as level of interest are less than second threshold, send preset prompt information to the default terminal, described to mention
Show information for prompt terminate to the target user recommendation service product.
In a possible example, micro- Expression analysis is being carried out to micro- facial expression image, is obtaining the target user's
In terms of emotional information, above procedure is specifically used for executing the instruction of following steps: micro- facial expression image is carried out RGB channel point
Solution, obtains three gray level images corresponding with the RGB channel；By the gray scale of each gray level image in three gray level images
Value obtains the input data in tri- channels RGB from [0,255] binaryzation to [0,1]；Respectively to the input number in each channel
According to convolution algorithm is carried out, the feature vector in each channel is obtained；Determine the mean value of the feature vector of the RGB channel, it will be described
Described eigenvector is input to softmax classifier, obtains institute by mean value as the corresponding feature vector of the micro- facial expression image
State the corresponding emotional information of target user.
A kind of possible function of information processing unit 500 involved in above-described embodiment is shown refering to Fig. 5, Fig. 5
Unit composition block diagram, electronic equipment 500 include: acquiring unit 510, matching unit 520 and determination unit 530, in which:
Acquiring unit 510, for obtaining the identity information of target user；
Matching unit 520, for based on the customer data base pre-established, the determining and matched behavior of the identity information
Track specifically includes: such as the image information that identity information is the target user, being believed according to algorithm of target detection described image
Breath carries out region detection, determines the target area in described image information comprising face, and the face in the target area is schemed
As composition input data, the input data is input to preparatory trained neural network model, obtains the face-image
Character pair vector, described eigenvector and the template vector in the user library data are compared, obtained and the target
The matched action trail of user；
Determination unit 530, for determining with the matched service product of the target user according to the action trail, to pre-
If terminal sends the service product, to recommend the service product to the target user.
In a possible example, in terms of the identity information for obtaining target user, acquiring unit 510 is specifically used for: such as
Identity information is MAC address, intercepts any one of target terminal transmission by the wifi probe of predeterminated position
Frame data parse the information of the MAC layer and physical layer in the frame data, obtain the MAC Address of the target terminal, wherein
The target terminal is the terminal of target user；Such as the image information that identity information is the target user, pass through predeterminated position
Camera obtain the image information of the target user.
In a possible example, in terms of the face-image in the target area is formed input data, matching is single
Member 520, is specifically used for: obtaining the picture element matrix of the face-image in the target area；By in the picture element matrix less than
The pixel value zero setting of one threshold value；The convolution kernel size for obtaining the neural network model, according to the convolution kernel size by zero setting
Zero arranged adjacent in picture element matrix afterwards forms input data, composition and the convolution kernel ruler in same row or with a line
Very little corresponding zero region；The picture element matrix arranged is labeled as input data.
In a possible example, as described in the action trail includes the personal information of target user, proprietary information and
Transacting business, in terms of the determining and matched service product of the target user according to the action trail, determination unit
530, it is specifically used for: determines that the target user can transacting business collection according to the proprietary information；According to the industry handled
Business and it is described can transacting business collection determine the non-transacting business collection of the target user；By the non-transacting business collection as institute
State target user's services sets to be handled；Have according to personal information determination wait handle target user described in service set
At least one for handling qualification waits for transacting business；It is to be matched with the target user by least one described service marker to be handled
Service product.
In a possible example, determination unit 530 is also used to obtain the product type of the service product；
When the product type is financial product, is determined according to the assets information of the target user and the finance is produced
The amount of money to be put into of product or the additional amount of money；In terms of default terminal sends the service product, determination unit 530 is specific to use
In: the business, which is sent, to the default terminal produces and the corresponding amount of money to be put into of the service product or described chase after
Add the amount of money.
In a possible example, information processing unit 500 further include: prompt unit 540；
Prompt unit 540, for obtaining the target user's when recommending the service product to the target user
Micro- facial expression image；Micro- Expression analysis is carried out to micro- facial expression image, the emotional information of the target user is obtained, according to described
Emotional information determines the target user to the level of interest of the service product, and such as level of interest is less than the second threshold
Value sends preset prompt information to the default terminal, and the prompt information is pushed away for prompting to terminate to the target user
Recommend the service product.
In a possible example, micro- Expression analysis is being carried out to micro- facial expression image, is obtaining the target user's
In terms of emotional information, prompt unit 540 is specifically used for: will micro- facial expression image progress RGB channel decomposition, obtain with it is described
Corresponding three gray level images of RGB channel；By the gray value of each gray level image in three gray level images from [0,255] two
Value obtains the input data in tri- channels RGB to [0,1]；Convolution fortune is carried out to the input data in each channel respectively
It calculates, obtains the feature vector in each channel；The mean value for determining the feature vector of the RGB channel, using the mean value as described in
The corresponding feature vector of micro- facial expression image, is input to softmax classifier for described eigenvector, obtains the target user couple
The emotional information answered.
The embodiment of the present application also provides a kind of computer storage medium, and the computer-readable recording medium storage has calculating
Machine program, the computer program are executed by processor to realize at any information as recorded in above method embodiment
Some or all of reason method step.
The embodiment of the present application also provides a kind of computer program product, and the computer program product includes storing calculating
The non-transient computer readable storage medium of machine program, the computer program are operable to that computer is made to execute such as above-mentioned side
Some or all of any information processing method recorded in method embodiment step.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because
According to the application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, embodiment described in this description belongs to alternative embodiment, related actions and modules not necessarily the application
It is necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed device, it can be by another way
It realizes.For example, the apparatus embodiments described above are merely exemplary, such as the division of the unit, it is only a kind of
Logical function partition, there may be another division manner in actual implementation, such as multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be through some interfaces, the indirect coupling or communication connection of device or unit,
It can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also be realized in the form of software program module.
If the integrated unit is realized in the form of software program module and sells or use as independent product
When, it can store in a computer-readable access to memory.Based on this understanding, the technical solution of the application substantially or
Person says that all or part of the part that contributes to existing technology or the technical solution can body in the form of software products
Reveal and, which is stored in a memory, including some instructions are used so that a computer equipment
(can be personal computer, server or network equipment etc.) executes all or part of each embodiment the method for the application
Step.And memory above-mentioned includes: USB flash disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), mobile hard disk, magnetic or disk.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in a computer-readable memory, memory
May include: flash disk, read-only memory (English: Read-Only Memory, referred to as: ROM), random access device (English:
Random Access Memory, referred to as: RAM), disk or CD etc..
The embodiment of the present application is described in detail above, specific case used herein to the principle of the application and
Embodiment is expounded, the description of the example is only used to help understand the method for the present application and its core ideas；
At the same time, for those skilled in the art can in specific embodiments and applications according to the thought of the application
There is change place, in conclusion the contents of this specification should not be construed as limiting the present application.
Claims (10)
1. a kind of information processing method characterized by comprising
Obtain the identity information of target user；
Based on the customer data base pre-established, the determining and matched action trail of the identity information is specifically included: such as identity
Information is the image information of the target user, carries out region detection to described image information according to algorithm of target detection, determines
Include the target area of face in described image information, the face-image in the target area is formed into input data, by institute
It states input data and is input to preparatory trained neural network model, the character pair vector of the face-image is obtained, by institute
It states feature vector to compare with the template vector in the user library data, obtain and the matched action trail of the target user；
According to action trail determination and the matched service product of the target user, the business is sent to default terminal and is produced
Product, to recommend the service product to the target user.
2. the method according to claim 1, wherein the identity information for obtaining target user, comprising:
If identity information is MAC address, intercept what target terminal was sent by the wifi probe of predeterminated position
Any one frame data parse the information of the MAC layer and physical layer in the frame data, obtain the MAC Address of the target terminal,
Wherein, the target terminal is the terminal of target user；
Such as the image information that identity information is the target user, obtain the target user's by the camera of predeterminated position
Image information.
3. method according to claim 1 or 2, which is characterized in that the face-image group by the target area
At input data, comprising:
Obtain the picture element matrix of the face-image in the target area；
The pixel value zero setting of first threshold will be less than in the picture element matrix；
The convolution kernel size for obtaining the neural network model, will be in the picture element matrix after zero setting according to the convolution kernel size
Zero arranged adjacent forms input data in same row or with a line, forms zero area corresponding with the convolution kernel size
Domain；
The picture element matrix arranged is labeled as input data.
4. method according to claim 1-3, which is characterized in that if the action trail includes that the target is used
The personal information at family, proprietary information and transacting business, described determined according to the action trail match with the target user
Service product, comprising:
Determine that the target user can transacting business collection according to the proprietary information；
According to the business handled and it is described can transacting business collection determine the non-transacting business collection of the target user；
Using the non-transacting business collection as target user services sets to be handled；
According to the personal information determine described in wait handle target user described in service set have handle qualification at least one
To transacting business；
It is and the matched service product of the target user by least one described service marker to be handled.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
Obtain the product type of the service product；
When the product type is financial product, determined according to the assets information of the target user to the financial product
The amount of money to be put into or the additional amount of money；
It is described that send the service product to default terminal include: to send the business to the default terminal to produce and the industry
The corresponding amount of money to be put into of business product or the additional amount of money.
6. the method according to claim 1, wherein the method also includes:
When recommending the service product to the target user, micro- facial expression image of the target user is obtained；
Micro- Expression analysis is carried out to micro- facial expression image, the emotional information of the target user is obtained, is believed according to the mood
Breath determines the target user to the level of interest of the service product, and such as level of interest is less than second threshold, to
The default terminal sends preset prompt information, and the prompt information is terminated for prompting to described in target user recommendation
Service product.
7. according to the method described in claim 6, it is characterized in that, described carry out micro- Expression analysis to the micro- facial expression image,
Obtain the emotional information of the target user, comprising:
Micro- facial expression image is subjected to RGB channel decomposition, obtains three gray level images corresponding with the RGB channel；
By the gray value of each gray level image in three gray level images from [0,255] binaryzation to [0,1], obtain described
The input data in tri- channels RGB；
Convolution algorithm is carried out to the input data in each channel respectively, obtains the feature vector in each channel；
The mean value for determining the feature vector of the RGB channel, using the mean value as the corresponding feature of the micro- facial expression image to
Amount, is input to softmax classifier for described eigenvector, obtains the corresponding emotional information of the target user.
8. a kind of information processing unit characterized by comprising
Acquiring unit, for obtaining the identity information of target user；
Matching unit, for based on the customer data base pre-established, the determining and matched action trail of the identity information, tool
Body is used for: such as the image information that identity information is the target user, being carried out according to algorithm of target detection to described image information
Region detection determines the target area in described image information comprising face, the face-image in the target area is formed
The input data is input to preparatory trained neural network model, obtains the correspondence of the face-image by input data
Feature vector compares described eigenvector and the template vector in the user library data, obtains and the target user
The action trail matched；
Determination unit is used for according to action trail determination and the matched service product of the target user, to default terminal
The service product is sent, to recommend the service product to the target user.
9. a kind of electronic equipment, which is characterized in that including processor, memory, communication interface and one or more program,
In, one or more of programs are stored in the memory, and are configured to be executed by the processor, described program
Include the steps that requiring the instruction in any one of 1-7 method for perform claim.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, the computer program are executed by processor to realize the method according to claim 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910604331.9A CN110458644A (en) | 2019-07-05 | 2019-07-05 | A kind of information processing method and relevant device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910604331.9A CN110458644A (en) | 2019-07-05 | 2019-07-05 | A kind of information processing method and relevant device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110458644A true CN110458644A (en) | 2019-11-15 |
Family
ID=68482206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910604331.9A Pending CN110458644A (en) | 2019-07-05 | 2019-07-05 | A kind of information processing method and relevant device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110458644A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111753745A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | User experience processing method and device for self-service business handling equipment |
| CN113076533A (en) * | 2020-01-03 | 2021-07-06 | 中国移动通信集团广东有限公司 | Service processing method and device |
| CN113723374A (en) * | 2021-11-02 | 2021-11-30 | 广州通达汽车电气股份有限公司 | Alarm method and related device for identifying user contradiction based on video |
| US20210398133A1 (en) * | 2019-05-31 | 2021-12-23 | Boe Technology Group Co., Ltd. | User identity recognition method and device, electronic device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108230162A (en) * | 2017-12-29 | 2018-06-29 | 泰康保险集团股份有限公司 | Method, apparatus, storage medium and the electronic equipment that insurance service is recommended |
| CN109409220A (en) * | 2018-09-19 | 2019-03-01 | 平安科技（深圳）有限公司 | Business bootstrap technique, device and storage medium based on recognition of face |
| CN109685611A (en) * | 2018-12-15 | 2019-04-26 | 深圳壹账通智能科技有限公司 | A kind of Products Show method, apparatus, computer equipment and storage medium |
| CN109767261A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium |
| CN109829784A (en) * | 2019-01-17 | 2019-05-31 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, equipment and storage medium based on micro- expression |
-
2019
- 2019-07-05 CN CN201910604331.9A patent/CN110458644A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108230162A (en) * | 2017-12-29 | 2018-06-29 | 泰康保险集团股份有限公司 | Method, apparatus, storage medium and the electronic equipment that insurance service is recommended |
| CN109409220A (en) * | 2018-09-19 | 2019-03-01 | 平安科技（深圳）有限公司 | Business bootstrap technique, device and storage medium based on recognition of face |
| CN109685611A (en) * | 2018-12-15 | 2019-04-26 | 深圳壹账通智能科技有限公司 | A kind of Products Show method, apparatus, computer equipment and storage medium |
| CN109767261A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium |
| CN109829784A (en) * | 2019-01-17 | 2019-05-31 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, equipment and storage medium based on micro- expression |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210398133A1 (en) * | 2019-05-31 | 2021-12-23 | Boe Technology Group Co., Ltd. | User identity recognition method and device, electronic device and storage medium |
| CN113076533A (en) * | 2020-01-03 | 2021-07-06 | 中国移动通信集团广东有限公司 | Service processing method and device |
| CN113076533B (en) * | 2020-01-03 | 2023-09-05 | 中国移动通信集团广东有限公司 | Service processing method and device |
| CN111753745A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | User experience processing method and device for self-service business handling equipment |
| CN113723374A (en) * | 2021-11-02 | 2021-11-30 | 广州通达汽车电气股份有限公司 | Alarm method and related device for identifying user contradiction based on video |
| CN113723374B (en) * | 2021-11-02 | 2022-02-15 | 广州通达汽车电气股份有限公司 | Alarm method and related device for identifying user contradiction based on video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110458644A (en) | A kind of information processing method and relevant device | |
| TWI706333B (en) | Fraud transaction identification method, device, server and storage medium | |
| CN108197532A (en) | The method, apparatus and computer installation of recognition of face | |
| CN112417096B (en) | Question-answer pair matching method, device, electronic equipment and storage medium | |
| CN107545241A (en) | Neural network model is trained and biopsy method, device and storage medium | |
| CN108763277A (en) | A kind of data analysing method, computer readable storage medium and terminal device | |
| CN110111136B (en) | Video data processing method, video data processing device, computer equipment and storage medium | |
| CN110502694A (en) | Lawyer's recommended method and relevant device based on big data analysis | |
| CN112995414B (en) | Behavior quality inspection method, device, equipment and storage medium based on voice call | |
| CN110276243A (en) | Score mapping method, face comparison method, device, equipment and storage medium | |
| CN110046648A (en) | The method and device of business classification is carried out based at least one business disaggregated model | |
| CN116467525A (en) | Recommendation method, device, equipment and storage medium of business products | |
| CN115018608A (en) | Risk prediction method and device and computer equipment | |
| CN112001760B (en) | Potential user mining method and device, electronic equipment and storage medium | |
| CN111429232A (en) | Product recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN112528140A (en) | Information recommendation method, device, equipment, system and storage medium | |
| CN113011968B (en) | Account state detection method and device, storage medium and electronic equipment | |
| CN115689648B (en) | User information processing method and system applied to directional delivery | |
| TWI676145B (en) | Online review method and system | |
| CN117437002A (en) | Service carding method, device, computer equipment and storage medium | |
| CN117237088A (en) | Loan auditing method, device and storage medium based on face recognition | |
| CN117709801A (en) | Client data processing method, device, computer equipment and storage medium | |
| CN117391330A (en) | Financial business handling sequence determining method, device and computer equipment | |
| CN116483501A (en) | Method and device for displaying software application, electronic equipment and storage medium | |
| CN116542779A (en) | Product recommendation method, device, equipment and storage medium based on artificial intelligence |
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 |