CN108960563A - A kind of ranking method and its equipment in shop - Google Patents
A kind of ranking method and its equipment in shop Download PDFInfo
- Publication number
- CN108960563A CN108960563A CN201810495240.1A CN201810495240A CN108960563A CN 108960563 A CN108960563 A CN 108960563A CN 201810495240 A CN201810495240 A CN 201810495240A CN 108960563 A CN108960563 A CN 108960563A
- Authority
- CN
- China
- Prior art keywords
- shop
- grading
- item
- target
- value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000000284 extract Substances 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 43
- 238000013528 artificial neural network Methods 0.000 claims description 29
- 230000001815 facial effect Effects 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003466 anti-cipated effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 210000000746 body region Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 239000002537 cosmetic Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention is suitable for technical field of data processing, provides the ranking method and its equipment in a kind of shop, comprising: obtains the object images of all objects into target shop within the grading period；Each object image is imported into object properties respectively and extracts model, determines the object properties of each object；Based on the industry type in target shop, the ratings attributes item for grading to target shop is chosen from object properties, and determine the rating weight of the desirable each attribute value of each ratings attributes item；The object number of each attribute value is counted according to all object properties；The rating weight of each attribute value and object number are imported into grading computation model, obtain the shop grade in target shop.The present invention is not necessarily to artificial collection in worksite data, or arranges user's remote monitor shop, improves the efficiency and cost of labor of grading.
Description
Technical field
The invention belongs to technical field of data processing more particularly to the ranking methods and its equipment in a kind of shop.
Background technique
With economic continuous development, and the difficulty for opening up shop reduces, and the quantity in small miniature shop is continuously increased.And
The starting fund of most of storekeeper is to bank or other financial institution loans often by acquiring in the type shop,
And in order to determine the loan repayment capacity of this part storekeeper, bank and financial institution need to grade to the shop after loan,
Adjustment is refunded tactful at any time.
Existing shop rank method needs to carry out on-site inspection by user shop, determines the quotient based on observation situation
The grading in shop, or graded at a distance for example, by the mode of telephone interview or real-time network video monitoring.However it is above-mentioned
The ranking method in shop needs that more cost of labor is spent to carry out on-site inspection or long-range monitoring, at high cost and efficiency of grading
It is lower.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of ranking method in shop and its equipment, to solve existing sound
Frequency plays control technology, can not meet simultaneously and temporarily skip certain audio files and can be reduced user's operation again, and control efficiency is lower,
The poor problem of usage experience.
The first aspect of the embodiment of the present invention provides a kind of ranking method in shop, comprising:
Obtain the object images of all objects into target shop within the grading period；
Each object images are imported into object properties respectively and extract model, determine the object category of each object
Property；
Based on the industry type in the target shop, chosen from the object properties for being carried out to the target shop
The ratings attributes item of grading, and determine the rating weight of the desirable each attribute value of each ratings attributes item；
The object number of each attribute value is counted according to all object properties；
The rating weight of each attribute value and object number are imported into grading computation model, obtain the target
The shop grade in shop；The grading computation model specifically:
Wherein, Lv is shop grade；aijFor the rating weight of j-th of attribute value in i-th ratings attributes item；Qij
For the object number of j-th of attribute value in i-th ratings attributes item；M is the item number of the ratings attributes item；niFor
The number of the desirable attribute value of i-th ratings attributes item；QAlwaysIt is total of the object obtained in the grading period
Number.
The second aspect of the embodiment of the present invention provides a kind of grading equipment in shop, including memory, processor and
The computer program that can be run in the memory and on the processor is stored, the processor executes the computer
It is performed the steps of when program
Obtain the object images of all objects into target shop within the grading period；
Each object images are imported into object properties respectively and extract model, determine the object category of each object
Property；
Based on the industry type in the target shop, chosen from the object properties for being carried out to the target shop
The ratings attributes item of grading, and determine the rating weight of the desirable each attribute value of each ratings attributes item；
The object number of each attribute value is counted according to all object properties；
The rating weight of each attribute value and object number are imported into grading computation model, obtain the target
The shop grade in shop；The grading computation model specifically:
Wherein, Lv is shop grade；aijFor the rating weight of j-th of attribute value in i-th ratings attributes item；Qij
For the object number of j-th of attribute value in i-th ratings attributes item；M is the item number of the ratings attributes item；niFor
The number of the desirable attribute value of i-th ratings attributes item；QAlwaysIt is total of the object obtained in the grading period
Number.
The third aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and the computer program performs the steps of when being executed by processor
Obtain the object images of all objects into target shop within the grading period；
Each object images are imported into object properties respectively and extract model, determine the object category of each object
Property；
Based on the industry type in the target shop, chosen from the object properties for being carried out to the target shop
The ratings attributes item of grading, and determine the rating weight of the desirable each attribute value of each ratings attributes item；
The object number of each attribute value is counted according to all object properties；
The rating weight of each attribute value and object number are imported into grading computation model, obtain the target
The shop grade in shop；The grading computation model specifically:
Wherein, Lv is shop grade；aijFor the rating weight of j-th of attribute value in i-th ratings attributes item；Qij
For the object number of j-th of attribute value in i-th ratings attributes item；M is the item number of the ratings attributes item；niFor
The number of the desirable attribute value of i-th ratings attributes item；QAlwaysIt is total of the object obtained in the grading period
Number.
The ranking method and its equipment for implementing a kind of shop provided in an embodiment of the present invention have the advantages that
The embodiment of the present invention is determined each by obtaining all object images into target store object within the grading period
The object properties of a object can be estimated into the purchasing power of the customer in the target shop and purchase by object properties and be anticipated
To, and according to the industry type in the target shop, extracted from object properties with the sector type degree of correlation is biggish can be with
Corresponding to each attribute value that ratings attributes item and the ratings attributes item for grading to the target shop can use
Rating weight, statistics object number corresponding to each attribute value within the grading period, so that the target shop be calculated
Shop grade.Compared with existing shop ranking method, artificial collection in worksite data are not necessarily to, or arrange user's remote monitor
The shop improves the efficiency and cost of labor of grading.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is a kind of implementation flow chart of the ranking method in shop that first embodiment of the invention provides；
Fig. 2 is a kind of ranking method specific implementation flow chart in shop that second embodiment of the invention provides；
Fig. 3 is a kind of ranking method S101 specific implementation flow chart in shop that third embodiment of the invention provides；
Fig. 4 is a kind of ranking method specific implementation flow chart in shop that fourth embodiment of the invention provides；
Fig. 5 is a kind of structural block diagram of the grading equipment in shop that one embodiment of the invention provides；
Fig. 6 be another embodiment of the present invention provides a kind of shop grading equipment schematic diagram.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
The embodiment of the present invention is determined each by obtaining all object images into target store object within the grading period
The object properties of a object can be estimated into the purchasing power of the customer in the target shop and purchase by object properties and be anticipated
To, and according to the industry type in the target shop, extracted from object properties with the sector type degree of correlation is biggish can be with
Corresponding to each attribute value that ratings attributes item and the ratings attributes item for grading to the target shop can use
Rating weight, statistics object number corresponding to each attribute value within the grading period, so that the target shop be calculated
Shop grade solves the ranking method in existing shop, needs that more cost of labor is spent to carry out on-site inspection or long-range
Monitoring, problem at high cost and lower efficiency of grading.
In embodiments of the present invention, the executing subject of process is the grading equipment in shop.The grading equipment in the shop includes
But it is not limited to: the terminal devices such as laptop, computer, server.It is emphasized that the grading equipment setting in the shop
There is a distributed camera shooting terminal, which is set at target shop, enters the shop for obtaining
The object images of object.Fig. 1 shows the implementation flow chart of the ranking method in the shop of first embodiment of the invention offer, is described in detail
It is as follows:
In S101, the object images of all objects into target shop within the grading period are obtained.
In the present embodiment, the grading equipment in shop is preset with shop grading process, comments when detecting that current time reaches
The grade period can then carry out grading operation to target shop, realize the loan repayment capacity for periodically determining the target shop.Specifically,
The grading equipment in shop is provided with multiple grading nodes based on the debit date in target shop and loaning bill duration, should whenever reaching
When grading node, then the object images of the object into the target shop can be obtained, until acquisition duration meets the grading period
Duration just stops acquisition, and is graded based on all object images acquired in this period to shop.
It should be noted that the grading equipment in shop passes through wireless network with the distributed camera shooting terminal for being set to target shop
Network is communicatively coupled.When distributed camera shooting terminal, which detects the presence of object, enters the target shop, then a width pair can be shot
As image, and the object images are fed back to the grading equipment in shop by wireless network.Wherein, distributed camera shooting terminal detection
The mode for entering target shop with the presence or absence of object can be with are as follows: and whether detection shooting picture fringe region has found facial image,
If detecting in fringe region there are facial image, the facial image is tracked, when the facial image reaches in camera picture
Between region when, then obtain current picture, and the picture is sent to the grading equipment in shop.It is new when having by the above method
When object enters camera picture, distributed camera shooting terminal is available to arrive relatively clear object images, to improve subsequent
The accuracy rate of Object identifying.
Optionally, in the present embodiment, distributed camera shooting terminal can be placed in the entrance in target shop, and be arranged
There is an infrared sensor, detects whether that object passes through the entrance in the target shop by the infrared sensor.If detecting
There is object by the entrance, then obtain the object images of the object, unites to realize to the object for entering target shop
Meter, the purpose acquired.Preferably due to will necessarily be further out the target shop into target store object, i.e., it can be in a timing
Between in section infrared sensor can collect the object images of same target twice, in this case, in order to avoid computing repeatedly, quotient
The grading equipment in shop, can be to the face information of each object image after receiving the object images that distributed camera shooting terminal returns
It is identified, selection includes the object images of identical face as an object images group in preset time range, and only
It is recorded as an object, is not repeated to record.Certainly, if outside preset time range, occur pair comprising identical face again
As image, then it can be identified as the object and enter target shop twice, be identified as two person-times.For example, a certain user understands mesh daily
Shops for goods is marked, and preset time range is one, then distributed camera shooting terminal collects the use within one day
All object images at family then only can be identified as one person-time, that is, be only used as an object；And another day collects the user again
Object images, then be identified as another pair as.
Optionally, in the present embodiment, the grading equipment in shop can then execute at once after getting object images
The operation of S102；It can also be unified that all object images acquired in the period are carried out pair after the completion of grading the period
As attributes extraction.
In S102, each object images are imported into object properties respectively and extract model, it is each described right to determine
The object properties of elephant.
In the present embodiment, object images contain the facial information and/or posture information of the object, therefore pass through face
Information and posture information can determine the object properties of the user, which includes but is not limited to: the gender of the object,
Age, hair style, occupation, height, weight and purchasing power.Therefore, in order to determine the object properties of the object, the grading in shop is set
The standby object properties that can be directed respectively into collected each object image are extracted in model, to determine the object category of each object
Property.
In the present embodiment, which, which extracts model, to be image recognition algorithm, pass through the human body area to object
Area image is positioned, to obtain the apparel characteristic of the object, sex character and age characteristics, then passes through above three
Characteristic value determines the object properties of the object.
It should be noted that the format of each object properties is identical, the i.e. obtained object of each object image zooming-out
The attribute item number that attribute includes is consistent, if part attribute item can not be extracted to obtain in an object image, by the attribute item
Curriculum offering be sky.
In S103, based on the industry type in the target shop, choose from the object properties for the mesh
The ratings attributes item that mark shop is graded, and determine the grading power of the desirable each attribute value of each ratings attributes item
Weight.
In the present embodiment, its corresponding target object of different types of shop is all different.Such as selling makeup
The shop of product, target object are mainly women, and the age is 25 more than one full year of life；And for automobile parts sale shop,
Target object is mainly male, and is worn clothes based on shirt or Western-style clothes.It can be seen that for different industry types, for right
As the attribute item of the concern of attribute is different, thus when determining whether each user can carry out purchase product in shop, institute
The attribute item of selection also can accordingly change.And since the probability that the object is bought in target shop is bigger, then target quotient
The turnover in shop also will be higher, so that the grading in its shop also can be higher, therefore while grading to target shop is of interest
Ratings attributes item will be consistent with the attribute item of target shop user of interest, therefore according to the industry type in target shop, really
The fixed ratings attributes item for grading to the target shop.
It continues with above-mentioned example to be illustrated, for selling the shop of cosmetics, concern is primarily with the objects
Gender and age, therefore " gender " and " age " is for the ratings attributes item to the target shop in object properties.
And in " gender " this ratings attributes, desirable attribute value be " male " and " women ", and different attribute values its correspondence
Rating weight be also different.Such as the object of " women " more maximum probability buys the commodity in the target shop, therefore its is right
The weighted value answered is larger；And the probability that the object of " male " buys the commodity in the target shop is then lower, thus its corresponding power
Weight values are less.It can be seen that the grading equipment in shop is having chosen except ratings attributes item, it is also necessary to be taken to the ratings attributes item
Institute is for rating weight when parameters value.
In the present embodiment, the mapping table of industry type and ratings attributes is stored in the grading equipment in shop, it should
The attribute item and each attribute item that each industry type object of interest is had recorded in mapping table take different parameters value
When corresponding rating weight.Equipment of grading, can be from the mapping table really by the industry type in acquisition target shop
Determine ratings attributes item and the rating weight of parameters value corresponding to the sector type.
Optionally, the grading equipment in shop can determine the target shop according to the type of target store sales product
Industry type.Wherein, if a certain shop type of selling product is more, corresponding multiple industry types then choose multiple industry classes
Sold in type product quantity and comprising the most industry type of type of merchandize, industry class as the target shop
Type.
In S104, the object number of each attribute value is counted according to all object properties.
In the present embodiment, the grading equipment in shop can be according to the object category of the object of all acquisitions within the grading period
Property, the object number of each attribute value is counted respectively.It should be noted that all properties in same ratings attributes item
The sum of object number of value, the total number of the object as acquired in the grading period.For example, being for ratings attributes item
" gender ", then desirable attribute value is " male " and " women " two attribute values, and is counted within the grading period, and gender is
The object number and gender of " male " are the object number of " women ".And " male " object number and " women " object person
The sum of number is necessarily equal to the total number of the object acquired in the grading period.As a same reason, for other ratings attributes items
The object number of each attribute value can be counted by the similar above method.
In S105, the rating weight of each attribute value and object number are imported into grading computation model, obtained
To the shop grade in the target shop；The grading computation model specifically:
Wherein, Lv is shop grade；aijFor the rating weight of j-th of attribute value in i-th ratings attributes item；Qij
For the object number of j-th of attribute value in i-th ratings attributes item；M is the item number of the ratings attributes item；niFor
The number of the desirable attribute value of i-th ratings attributes item；QAlwaysIt is total of the object obtained in the grading period
Number.
In the present embodiment, the grading equipment in shop can by the rating weight of each attribute value in each ratings attributes item with
And object number is imported into grading computation model, calculates shop grade of the target shop within this grading period.It needs
Illustrate,For the corresponding subitem score value of i-th of ratings attributes item, therefore all m gradings are belonged to
The subitem score value of property item adds up, then the shop grade of the available target shop entirety.
It should be noted that belonging to the sum of rating weight of each attribute value of same ratings attributes item is 1.Such as
" gender " this ratings attributes item is respectively " male " and " women " comprising two attribute values, corresponding 0.2 and
0.8 rating weight, and the sum of rating weight of two attribute values is 1.
In order to make it easy to understand, following calculating process for illustrating shop grade by an example.One in a certain grading period
The object images for having got 10 objects altogether have determined the object properties of each object based on 10 object images, and therefrom
The rating weight for extracting different attribute value in ratings attributes related to the industry type in target shop and each ratings attributes is
Convenient for comparing, show that the object number of each attribute value that this statistics obtains and grading are weighed below by way of the form of table
Weight.Ginseng is shown in Table 1, and the object number and rating weight of each attribute value are imported into grading computation model, calculating process
It is as follows:
Lv=(0.3*5+0.7*5)+(0.2*1+0.6*9+0.2*0)+(0.2*3+0.7*4+0.1*3)=15.9
I.e. this shop grade being calculated is 15.9.What by the shop, grade can be evaluated whether the shop manages shape
Condition.
Table 1
Above as can be seen that a kind of ranking method in shop provided in an embodiment of the present invention is by obtaining within the grading period
All object images into target store object, determine the object properties of each object, by object properties can estimate into
Enter the purchasing power and purchase intention of the customer in the target shop, and according to the industry type in the target shop, from object
Extraction and the biggish ratings attributes item that can be used for grading to the target shop of the sector type degree of correlation in attribute, with
And rating weight corresponding to the desirable each attribute value of the ratings attributes item, statistics each attribute value institute within the grading period are right
The object number answered, so that the shop grade in the target shop be calculated.Compared with existing shop ranking method, it is not necessarily to people
Work collection in worksite data, or user's remote monitor shop is arranged, improve the efficiency and cost of labor of grading.
Fig. 2 shows a kind of specific implementation flow charts of the ranking method in shop of second embodiment of the invention offer.Ginseng
As shown in Figure 2, relative to embodiment described in Fig. 1, described according to institute in a kind of ranking method in shop provided in this embodiment
It states object images and identifies that the object properties of each object further include before S201~S203, specific details are as follows:
In S201, the training image and training object properties of multiple trained objects are obtained.
In the present embodiment, it is specially more attribute combination learning DeepMAR neural networks that object properties, which extract model, in order to
The accuracy for improving DeepMAR neural network output object properties, needs to input training data to the neural network
Practise training.Therefore, in S201, terminal device can obtain the training image and training object properties of trained object.Wherein, training
The number of user is multiple, it is preferable that the number of the training user should be greater than 1000, to improve the DeepMAR nerve net
The identification accuracy of network.
In the present embodiment, the grading equipment in shop can carry out image acquisition to multiple objects, and input above-mentioned object
Object properties, the grading equipment in certain shop can acquire the object images of the object when object carries out typing operation, and
And be associated the object images and the object information of the object typing, to be stored in database in the grading equipment in shop
Typing user, used trained object when can be used as this to DeepMAR neural metwork training.In S201, grading
Equipment is using the training image of training object as the input reference of DeepMAR neural network, the training object of training user
Output reference value of the attribute as DeepMAR neural network instructs DeepMAR neural network by above-mentioned two parameter
Practice.
It should be noted that the format of the training object properties of each trained object be it is identical, i.e., wrapped in object properties
The item number of the property parameters item contained is identical.If the problem of object images of any trained object are due to shooting angle can not solve
Part property parameters item is precipitated, then the property parameters item is sky, is trained to ensure that DeepMAR neural network
When, the parameter of each channel output is meant that fixed, improves the accuracy of DeepMAR neural network.
In S202, the training image and the trained object properties are based on, more attribute combination learning DeepMAR are adjusted
Learning parameter in neural network, so that the learning parameter meets the following conditions:
Wherein, θ*For the learning parameter adjusted；Pic is the training image；I is the trained object properties；
I1,I2,I3,…,InFor the parameter value for every attribute item that the trained object properties include；N is the number of the attribute item；p
(I1,I2,I3,…,In|Pic；It θ) is to imported into the training image of the trained object when the value of the learning parameter is θ
The DeepMAR neural network, output result are the probability value of the training object properties of the training user；maxθ∑(Pic,I)logp
(I1,I2,I3,…,n|Pic；The value of learning parameter when θ) being maximized for the probability value.
In the present embodiment, DeepMAR neural network has N number of output channel, and each output channel corresponds to object properties
In include every property parameters item, such as include in object properties: 6 age, gender, occupation, height, weight, hair style use
Family parameter then can then be provided with 6 output channels in DeepMAR neural network, according to each property parameters item in object properties
In number, for the fixed corresponding input channel of each property parameters item, to guarantee the use of each input channel input
Family parameter is identical.The input channel of the DeepMAR neural network is one, the as input channel of object images.Certainly,
If same target gets multiple object images in preset time range, image number of this input can be multiple,
To improve the accuracy rate of identification.
It in the present embodiment, include multiple nervous layers in DeepMAR neural network, each nervous layer is provided with corresponding
Parameter is practised, can adapt to different input types and output type by adjusting the parameter value of learning parameter.When learning parameter is set
When being set to a certain parameter value, the object images of multiple trained objects are input to the DeepMAR neural network, by corresponding output one
The object properties of output can be compared with training object properties for the object properties of each object, grading equipment, determine this
Whether output is correct, and the output based on multiple trained objects is as a result, obtain output knot when the learning parameter takes the parameter value
The correct probability value of fruit.Grading equipment can adjust the learning parameter, so that the probability value is maximized, then it represents that the DeepMAR
Neural network is adjusted to be finished.
In S203, based on the DeepMAR neural network after regularized learning algorithm parameter, generates the object properties and extract
Model.
In the present embodiment, the DeepMAR neural network after terminal device will have adjusted learning parameter is as object properties
Model is extracted, the accuracy rate that object properties extract model identification is improved.
In embodiments of the present invention, DeepMAR neural network is trained by training object, is choosing output result just
Parameter value of the corresponding learning parameter as learning parameter in DeepMAR neural network when true probability value maximum, to improve
The accuracy of candidate protocol identification realizes the purpose precisely pushed.
Fig. 3 shows the specific implementation flow of the ranking method S101 in shop of third embodiment of the invention offer a kind of
Figure.It is shown in Figure 3, relative to embodiment described in Fig. 1, include in a kind of ranking method S101 in shop provided in this embodiment
S1011 and S1013, specific details are as follows:
Further, as another embodiment of the present invention, it is described obtain it is all into target shop within the grading period
The object images of object, comprising:
In S1011, the acquisition when detecting that object enters the target shop that distributed camera shooting terminal is sent is received
Ambient image.
In the present embodiment, distributed camera shooting terminal can acquire target quotient when detecting that object enters target shop
The ambient image in shop, specifically, the ambient image can be the StoreFront image in the target shop.It, can be with by the ambient image
Identification obtains multiple customers in the target shop, and the object images of each customer are extracted from the ambient image.
In the present embodiment, range sensor has can be set in the entrance in target shop, if detect get away from
When mutating from value, then identification has object to enter target shop, at this point, range sensor can send an image capture instruction
Current goal shop can be obtained after distributed camera shooting terminal receives the image capture instruction to distributed camera shooting terminal
Then ambient image executes the relevant operation of S1022.
In S1012, the facial image for including in the ambient image is identified.
In the present embodiment, grading equipment determines the facial image for including in the ambient image by face recognition algorithms,
If the number of the facial image identified can be multiple there are the face of multiple objects in the ambient image.
In the present embodiment, grading equipment can be numbered for each facial image in ambient image, be each face figure
As one buffer zone of creation, for storing object images corresponding to the facial image.Optionally, grading equipment is determining
After each facial image, mostly all face figures for having stored facial image and this acquisition can will be collected in preset time range
As being compared, determine the facial image of this acquisition whether have it is corresponding stored facial image, if so, this acquisition is not
The object images of the facial image are stored again, but ignore the facial image, thus the case where reducing repetition storage
Occur, improve the availability of memory space and reduces unnecessary identification operation.
In S1013, according to the facial image, interception includes the image of the objective subject from the ambient image
As object images.
In the present embodiment, grading equipment can be based on the facial image, and it is corresponding that the facial image is positioned from ambient image
Approximate region where the main body of object obtains the region being connected with the facial image outer profile by outline identification algorithm, from
And the image of the facial image corresponding objects main body is sketched the contours of, and identify the subject image as object images.
Optionally, before S1013, grading equipment can be pre-processed ambient image, such as by sharpening, filtering
Scheduling algorithm carries out denoising to ambient image, can also overturn scheduling algorithm by greyscale transformation, pixel color value and first determine object
The profile of body region is intercepting the image of corresponding region based on the profile as object images from primal environment image.
In embodiments of the present invention, the ambient image that grading equipment is fed back by obtaining distributed camera shooting terminal, so as to
Enough object images for once obtaining multiple objects improve object properties extraction to reduce the number of image zooming-out operation
Efficiency.
Fig. 4 shows a kind of specific implementation flow chart of the ranking method in shop of fourth embodiment of the invention offer.Ginseng
As shown in Figure 4, relative to embodiment described in FIG. 1 to FIG. 3, a kind of ranking method in shop provided in this embodiment it is described will be each
The rating weight and object number of a attribute value imported into grading computation model, obtain the shop etc. in the target shop
After grade, further includes: S401~S404, specific details are as follows:
In S401, the shop grade is compared with grading range.
In the present embodiment, the shop grade being calculated can be compared by grading equipment with preset grading range,
If the shop grade drops into grading range, then it represents that the management state in the target shop meets expected expectation, has corresponding
Loan repayment capacity, therefore current refund strategy can be kept not to change, in this case, grading equipment can wait next time
The arrival in grading period, carries out grading operation to the target shop again.
In the present embodiment, the shop grade that period acquires if this is graded is lower than the lower limit value of the grading range,
Then execute the relevant operation of S402 and S403；If shop grade is higher than the upper limit value of grading range, the correlation of S404 is executed
Operation.
In S402, if the shop grade in the target shop executes announcement lower than the lower limit value of preset grading range
Alert operation, and reduce the credit grade in the target shop.
In the present embodiment, grading equipment is lower than the lower limit value of grading range in the shop grade that target shop has been determined,
It then indicates that the management state in the target shop is poor, may not have corresponding loan repayment capacity, it is therefore desirable to target quotient
Shop executes alarm operation, to prompt the storekeeper in the target shop to need to refund on schedule.Wherein, which includes but unlimited
In: alarm email or alarm message are sent to user, the hotel owner of corresponding responsible person Yu target shop can also be arranged certainly
Telephonic communication is carried out, to further determine that the management state of current shop.
In the present embodiment, since grading equipment determines that the management state in the target shop is poor, may not have refund
Ability, therefore, in this case, grading equipment can reduce the credit grade in the target shop, to limit the loan in the target shop
Money permission.
In S403, the trading account of the management user in the target shop is obtained, and the trading account is identified as
Adventure account.
In the present embodiment, grading equipment in addition to the target shop is carried out loan limitation operation and alarm operation other than,
The trading account that the management user in the target shop can also be obtained, avoiding management user from passing through private channel is the target shop
Loan operation is carried out, the more investment risks of bank or financial institution are increased, therefore can identify that such trading account is risk
Account.
In embodiments of the present invention, by shop target shop of the grading lower than preset range lower limit value and the target
The management user in shop carries out transaction limits, causes unnecessary economic loss so as to avoid bank or other financial institutions.
Further, as another embodiment of the present invention, described by the rating weight of each attribute value and right
As number imported into grading computation model, after obtaining the shop grade in the target shop, further includes:
In S404, if upper limit value of the shop grade in the target shop higher than the grading range, described in raising
The trading privilege in target shop；The trading privilege includes loan limit.
In the present embodiment, grading equipment is higher than the upper limit value of grading range in the shop grade that target shop has been determined,
Then indicate that the management state in the target shop is more excellent, can be improved the trading privilege in target shop at this time, allow target trade company into
The loan requests of one step, and trading privilege is directly proportional to loan limit, i.e., and trading privilege is higher, then the amount of money that can be provided a loan is got over
It is more.
In embodiments of the present invention, for business circumstance preferably target shop, its trading privilege is improved, so as to increase
Add the amount received of bank and other financial institutions in loan transaction and other trading items, increases the benefit of enterprise.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Fig. 5 shows a kind of structural block diagram of the grading equipment in shop of one embodiment of the invention offer, which comments
The each unit that grade equipment includes is used to execute each step in the corresponding embodiment of Fig. 1.Referring specifically to corresponding to Fig. 1 and Fig. 1
Embodiment in associated description.For ease of description, only the parts related to this embodiment are shown.
Referring to Fig. 5, the grading equipment in the shop includes:
Object images acquiring unit 51, for obtaining the object diagram of all objects into target shop within the grading period
Picture；
Object properties extraction unit 52 extracts model for each object images to be imported into object properties respectively,
Determine the object properties of each object；
Grading parameter acquiring unit 53 is selected from the object properties for the industry type based on the target shop
It takes in the ratings attributes item graded to the target shop, and determines that each ratings attributes item can use each
The rating weight of attribute value；
Object number statistic unit 54, for counting the object person of each attribute value according to all object properties
Number；
Shop level de-termination unit 55, for the rating weight of each attribute value and object number to imported into and comment
Grade computation model, obtains the shop grade in the target shop；The grading computation model specifically:
Wherein, Lv is shop grade；aijFor the rating weight of j-th of attribute value in i-th ratings attributes item；Qij
For the object number of j-th of attribute value in i-th ratings attributes item；M is the item number of the ratings attributes item；niFor
The number of the desirable attribute value of i-th ratings attributes item；QAlwaysIt is total of the object obtained in the grading period
Number.
Optionally, the grading equipment in shop further include:
Training object acquisition unit, for obtaining the training image and training object properties of multiple trained objects；
Learning parameter adjustment unit adjusts more attribute connection for being based on the training image and the trained object properties
The learning parameter in study DeepMAR neural network is closed, so that the learning parameter meets the following conditions:
Wherein, θ*For the learning parameter adjusted；Pic is the training image；I is the trained object properties；
I1,I2,I3,…,InFor the parameter value for every attribute item that the trained object properties include；N is the number of the attribute item；p
(I1,I2,I3,…,In|Pic；It θ) is to imported into the training image of the trained object when the value of the learning parameter is θ
The DeepMAR neural network, output result are the probability value of the training object properties of the training user；maxθ∑(Pic,I)logp
(I1,I2,I3,…,In|Pic；The value of learning parameter when θ) being maximized for the probability value；
Object properties extract model generation unit, for based on the DeepMAR neural network after regularized learning algorithm parameter,
It generates the object properties and extracts model.
Optionally, object images acquiring unit 51 includes:
Ambient image acquiring unit is detecting that object enters the target for receiving that distributed camera shooting terminal sends
The ambient image acquired when shop；
Facial image recognition unit, the facial image for including in the ambient image for identification；
Object images interception unit, for according to the facial image, interception to be comprising described right from the ambient image
As the image of main body is as object images.
Optionally, the grading equipment in shop further include:
Alarm operation execution unit, if the shop grade for the target shop is lower than the lower limit of preset grading range
Value, then execute alarm operation, and reduce the credit grade in the target shop；
Adventure account recognition unit, the trading account of the management user for obtaining the target shop, and by the friendship
Easy account is identified as adventure account.
Optionally, the grading equipment in shop further include:
Trading privilege adjustment unit, if the shop grade for the target shop is higher than the upper limit of the grading range
Value, then improve the trading privilege in the target shop；The trading privilege includes loan limit.
Therefore, the grading equipment in shop provided in an embodiment of the present invention is equally not necessarily to artificial collection in worksite data, Huo Zhean
User's remote monitor shop is arranged, the efficiency and cost of labor of grading are improved.
Fig. 6 be another embodiment of the present invention provides a kind of shop grading equipment schematic diagram.As shown in fig. 6, the reality
The grading equipment 6 for applying the shop of example includes: processor 60, memory 61 and is stored in the memory 61 and can be described
The computer program 62 run on processor 60, such as the grading program in shop.The processor 60 executes the computer journey
The step in the ranking method embodiment in above-mentioned each shop, such as S101 shown in FIG. 1 to S105 are realized when sequence 62.Alternatively,
The processor 60 realizes the function of each unit in above-mentioned each Installation practice, such as Fig. 5 when executing the computer program 62
Shown 51 to 55 function of module.
Illustratively, the computer program 62 can be divided into one or more units, one or more of
Unit is stored in the memory 61, and is executed by the processor 60, to complete the present invention.One or more of lists
Member can be the series of computation machine program instruction section that can complete specific function, and the instruction segment is for describing the computer journey
Implementation procedure of the sequence 62 in the grading equipment 6 in the shop.For example, the computer program 62 can be divided into object diagram
As acquiring unit, object properties extraction unit, grading parameter acquiring unit, object number statistic unit and shop grade determine
Unit, each unit concrete function are as described above.
The grading equipment 6 in the shop can be the meter such as desktop PC, notebook, palm PC and cloud server
Calculate equipment.The grading equipment in the shop may include, but be not limited only to, processor 60, memory 61.Those skilled in the art can
To understand, Fig. 6 is only the example of the grading equipment 6 in shop, does not constitute the restriction of the grading equipment 6 to shop, can wrap
It includes than illustrating more or fewer components, perhaps combines certain components or different components, such as the grading in the shop is set
Standby can also include input-output equipment, network access equipment, bus etc..
Alleged processor 60 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 61 can be the internal storage unit of the grading equipment 6 in the shop, such as the grading in shop is set
Standby 6 hard disk or memory.The memory 61 is also possible to the External memory equipment of the grading equipment 6 in the shop, such as institute
State the plug-in type hard disk being equipped in the grading equipment 6 in shop, intelligent memory card (Smart Media Card, SMC), secure digital
(Secure Digital, SD) card, flash card (Flash Card) etc..Further, the memory 61 can also both include
The internal storage unit of the grading equipment 6 in the shop also includes External memory equipment.The memory 61 is described for storing
Other programs and data needed for the grading equipment in computer program and the shop.The memory 61 can be also used for temporarily
When store the data that has exported or will export.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into 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 realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..Computer-readable Jie
Matter may include: can carry the computer program code any entity or device, recording medium, USB flash disk, mobile hard disk,
Magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as does not include electric carrier signal and electricity according to legislation and patent practice, computer-readable medium in certain jurisdictions
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of ranking method in shop characterized by comprising
Obtain the object images of all objects into target shop within the grading period；
Each object images are imported into object properties respectively and extract model, determine the object properties of each object；
Based on the industry type in the target shop, choose from the object properties for grading to the target shop
Ratings attributes item, and determine the rating weight of the desirable each attribute value of each ratings attributes item；
The object number of each attribute value is counted according to all object properties；
The rating weight of each attribute value and object number are imported into grading computation model, obtain the target shop
Shop grade；The grading computation model specifically:
Wherein, Lv is shop grade；aijFor the rating weight of j-th of attribute value in i-th ratings attributes item；QijIt is i-th
The object number of j-th of attribute value in the item ratings attributes item；M is the item number of the ratings attributes item；niIt is i-th
The number of the desirable attribute value of the ratings attributes item；QAlwaysTotal number for the object obtained in the grading period.
2. ranking method according to claim 1, which is characterized in that identify each institute according to the object images described
Before the object properties for stating object, further includes:
Obtain the training image and training object properties of multiple trained objects；
Based on the training image and the trained object properties, adjust in more attribute combination learning DeepMAR neural networks
Learning parameter, so that the learning parameter meets the following conditions:
Wherein, θ * is the learning parameter adjusted；Pic is the training image；I is the trained object properties；I1, I2,
I3..., InFor the parameter value for every attribute item that the trained object properties include；N is the number of the attribute item；p(I1,
I2, I3..., In|Pic；It θ) is that the training image of the trained object is imported into institute when the value of the learning parameter is θ
DeepMAR neural network is stated, output result is the probability value of the training object properties of the training user；maxθ∑(Pic, I)logp
(I1, I2, I3..., In|Pic；The value of learning parameter when θ) being maximized for the probability value；
Based on the DeepMAR neural network after regularized learning algorithm parameter, generates the object properties and extract model.
3. ranking method according to claim 1, which is characterized in that the acquisition is all within the grading period to enter target
The object images of the object in shop, comprising:
Receive the ambient image acquired when detecting that object enters the target shop that distributed camera shooting terminal is sent；
Identify the facial image for including in the ambient image；
According to the facial image, image of the interception comprising the objective subject is as object images from the ambient image.
4. ranking method according to claim 1-3, which is characterized in that described by each attribute value
Rating weight and object number imported into grading computation model, after obtaining the shop grade in the target shop, further includes:
If the shop grade in the target shop executes alarm operation, and reduce lower than the lower limit value of preset grading range
The credit grade in the target shop；
The trading account of the management user in the target shop is obtained, and the trading account is identified as adventure account.
5. ranking method according to claim 4, which is characterized in that in the rating weight by each attribute value
And object number imported into grading computation model, after obtaining the shop grade in the target shop, further includes:
If the shop grade in the target shop is higher than the upper limit value of the grading range, the transaction in the target shop is improved
Permission；The trading privilege includes loan limit.
6. a kind of grading equipment in shop, which is characterized in that the grading equipment in the shop includes memory, processor and deposits
The computer program that can be run in the memory and on the processor is stored up, the processor executes the computer journey
Following steps are realized when sequence:
Obtain the object images of all objects into target shop within the grading period；
Each object images are imported into object properties respectively and extract model, determine the object properties of each object；
Based on the industry type in the target shop, choose from the object properties for grading to the target shop
Ratings attributes item, and determine the rating weight of the desirable each attribute value of each ratings attributes item；
The object number of each attribute value is counted according to all object properties；
The rating weight of each attribute value and object number are imported into grading computation model, obtain the target shop
Shop grade；The grading computation model specifically:
Wherein, Lv is shop grade；aijFor the rating weight of j-th of attribute value in i-th ratings attributes item；QijIt is i-th
The object number of j-th of attribute value in the item ratings attributes item；M is the item number of the ratings attributes item；niIt is i-th
The number of the desirable attribute value of the ratings attributes item；QAlwaysTotal number for the object obtained in the grading period.
7. the grading equipment in shop according to claim 6, it is characterised in that identified described according to the object images
Before the object properties of each object, the processor also realizes following steps when executing the computer program:
Obtain the training image and training object properties of multiple trained objects；
Based on the training image and the trained object properties, adjust in more attribute combination learning DeepMAR neural networks
Learning parameter, so that the learning parameter meets the following conditions:
Wherein, θ*For the learning parameter adjusted；Pic is the training image；I is the trained object properties；I1, I2,
I3..., InFor the parameter value for every attribute item that the trained object properties include；N is the number of the attribute item；p(I1,
I2, I3..., In|Pic；It θ) is that the training image of the trained object is imported into institute when the value of the learning parameter is θ
DeepMAR neural network is stated, output result is the probability value of the training object properties of the training user；maxθ∑(Pic, I)logp
(I1, I2, I3..., In|Pic；The value of learning parameter when θ) being maximized for the probability value；
Based on the DeepMAR neural network after regularized learning algorithm parameter, generates the object properties and extract model.
8. the grading equipment in shop according to claim 6, which is characterized in that it is described obtain grading the period in it is all into
Enter the object images of the object in target shop, comprising:
Receive the ambient image acquired when detecting that object enters the target shop that distributed camera shooting terminal is sent；
Identify the facial image for including in the ambient image；
According to the facial image, image of the interception comprising the objective subject is as object images from the ambient image.
9. according to the grading equipment in the described in any item shops claim 6-8, which is characterized in that described by each category
The rating weight and object number of property value imported into grading computation model, after obtaining the shop grade in the target shop,
The processor also realizes following steps when executing the computer program:
If the shop grade in the target shop executes alarm operation, and reduce lower than the lower limit value of preset grading range
The credit grade in the target shop；
The trading account of the management user in the target shop is obtained, and the trading account is identified as adventure account.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 5 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810495240.1A CN108960563A (en) | 2018-05-22 | 2018-05-22 | A kind of ranking method and its equipment in shop |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810495240.1A CN108960563A (en) | 2018-05-22 | 2018-05-22 | A kind of ranking method and its equipment in shop |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108960563A true CN108960563A (en) | 2018-12-07 |
Family
ID=64499814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810495240.1A Pending CN108960563A (en) | 2018-05-22 | 2018-05-22 | A kind of ranking method and its equipment in shop |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108960563A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156941A (en) * | 2016-06-06 | 2016-11-23 | 腾讯科技（深圳）有限公司 | A kind of user credit scoring optimization method and device |
| CN107679103A (en) * | 2017-09-08 | 2018-02-09 | 口碑(上海)信息技术有限公司 | For entity attributes analysis method and system |
| CN107705155A (en) * | 2017-10-11 | 2018-02-16 | 北京三快在线科技有限公司 | A kind of consuming capacity Forecasting Methodology, device, electronic equipment and readable storage medium storing program for executing |
-
2018
- 2018-05-22 CN CN201810495240.1A patent/CN108960563A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156941A (en) * | 2016-06-06 | 2016-11-23 | 腾讯科技（深圳）有限公司 | A kind of user credit scoring optimization method and device |
| CN107679103A (en) * | 2017-09-08 | 2018-02-09 | 口碑(上海)信息技术有限公司 | For entity attributes analysis method and system |
| CN107705155A (en) * | 2017-10-11 | 2018-02-16 | 北京三快在线科技有限公司 | A kind of consuming capacity Forecasting Methodology, device, electronic equipment and readable storage medium storing program for executing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220198568A1 (en) | Systems and methods for providing customized financial advice | |
| CN111861174B (en) | Credit assessment method for user portrait | |
| US20210264448A1 (en) | Privacy preserving ai derived simulated world | |
| CN110827138B (en) | Push information determining method and device | |
| US20110238550A1 (en) | Systems and methods for predicting financial behaviors | |
| WO2022073519A1 (en) | Method, apparatus and device for applying for account in virtual bank, and computer storage medium | |
| CN106815754A (en) | The charging method and air control system server of a kind of risk control system | |
| CN110020149A (en) | Labeling processing method, device, terminal device and the medium of user information | |
| CN108572988A (en) | A kind of house property assessment data creation method and device | |
| CN107392614A (en) | The implementation method and device of off-line transaction | |
| KR20190122555A (en) | Pay utilization system and method based on interest data between users | |
| CN112767046B (en) | Method and device for constructing non-standardized service product | |
| CN108960563A (en) | A kind of ranking method and its equipment in shop | |
| CN112351389A (en) | Tracking method, device, terminal, medium and system for person track in commercial place | |
| KR102354982B1 (en) | Method and apparatus for providing clothing platform service based on big data | |
| CN113191570A (en) | Fund planning recommendation method, device and equipment based on deep learning | |
| CN113283979A (en) | Loan credit evaluation method and device for loan applicant and storage medium | |
| Koski et al. | Data markets in making: the role of technology giants | |
| CN117787961B (en) | Payment ticket business integrated management method and system | |
| CN109118292A (en) | The method, device and equipment of information processing | |
| US11250955B2 (en) | Systems and methods for health evaluation and monitoring | |
| US11488184B2 (en) | Systems, methods, and apparatuses for forecasting merchant performance | |
| CN113313597B (en) | Product combination recommendation method, device and system, storage medium and electronic device | |
| Nah et al. | HCI in Business, Government and Organizations. eCommerce and Consumer Behavior: 6th International Conference, HCIBGO 2019, Held as Part of the 21st HCI International Conference, HCII 2019, Orlando, FL, USA, July 26-31, 2019, Proceedings, Part I | |
| Nalini et al. | Gauging acuity of online shoppers towards digital payments apps–Fisher analysis of variance |
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 | ||
| AD01 | Patent right deemed abandoned | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20231208 |