CN109598578A - The method for pushing and device of business object data, storage medium, computer equipment - Google Patents
The method for pushing and device of business object data, storage medium, computer equipment Download PDFInfo
- Publication number
- CN109598578A CN109598578A CN201811332144.1A CN201811332144A CN109598578A CN 109598578 A CN109598578 A CN 109598578A CN 201811332144 A CN201811332144 A CN 201811332144A CN 109598578 A CN109598578 A CN 109598578A
- Authority
- CN
- China
- Prior art keywords
- business object
- target user
- information
- dressing
- personality
- 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
- G06Q30/06—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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses a kind of method for pushing of business object data and device, storage medium, computer equipments, this method comprises: obtaining target user's image information；From target user's image information, dressing characteristic information relevant to target user is extracted；According to dressing characteristic information, the personality scoring of target user is calculated；It is scored according to personality, calculates the matching degree of target user and business object；According to matching degree, to the corresponding data of target user's transmission service object.The application can analyze user's personality in conjunction with the dressing information of user, the matching degree of user and business object are calculated to score according to user's personality, it realizes and personalized business object data is pushed to different users according to matching degree, push effect is more preferable, while also can be avoided salesman and linking up the dislike for causing user with user's chat.
Description
Technical field
This application involves technical field of data processing, particularly with regard to the method for pushing and dress of a kind of business object data
It sets, storage medium, computer equipment.
Background technique
Existing Products Show mode is mostly directly to recommend some best-selling products or mainstay product to customer or complete
The hobby for catering to customer entirely carries out Products Show, or is pushed away according to the purchasing power of the statistics attributive analysis client of user
It recommends, few salesmans can targetedly provide the suggested design of profession according to the style and features of customer individual, and promote
The mode that member generallys use chat understands customer, since the professional standards of salesman are irregular, if in a manner of improperly and objective
The conflict psychology for being likely to result in client is linked up at family, is unfavorable for the accurate recommendation of product, is also consumed a large amount of human resources.
Summary of the invention
In view of this, this application provides a kind of method for pushing of business object data and device, storage medium, computers
Equipment carries out product matching according to the dressing feature of user automatically, improves recommendation accuracy.
According to the one aspect of the application, a kind of method for pushing of business object data is provided, which is characterized in that packet
It includes:
Obtain target user's image information；
From target user's image information, dressing characteristic information relevant to the target user is extracted；
According to the dressing characteristic information, the personality scoring of the target user is calculated；
It is scored according to the personality, calculates the matching degree of the target user and business object；
According to the matching degree, the corresponding data of Xiang Suoshu target user's transmission service object.
According to the another aspect of the application, a kind of driving means of business object data is provided, which is characterized in that packet
It includes:
Target image acquiring unit, for obtaining target user's image information；
Dressing feature extraction unit, for extracting related to the target user from target user's image information
Dressing characteristic information；
Personality scoring computing unit, for calculating the personality scoring of the target user according to the dressing characteristic information；
Business object matching degree computing unit calculates the target user and business pair for scoring according to the personality
The matching degree of elephant；
Business object data push unit, for according to the matching degree, Xiang Suoshu target user's transmission service object pair
The data answered.
According to the application another aspect, a kind of storage medium is provided, computer program, described program are stored thereon with
The method for pushing of above-mentioned business object data is realized when being executed by processor.
According to the application another aspect, a kind of computer equipment is provided, including storage medium, processor and be stored in
On storage medium and the computer program that can run on a processor, the processor realize above-mentioned business when executing described program
The method for pushing of object data.
By above-mentioned technical proposal, a kind of method for pushing and device, storage Jie of business object data provided by the present application
Matter, computer equipment extract the dressing feature of the user from the image information of target user, thus to the personality of user into
Row scoring, and score according to personality and calculate the matching degree of user and business object, thus according to matching degree size to target user
Transmission service object data, with recommendation hot-sale products and main product or salesman in the prior art by chatting with user
The mode for linking up analysis user preferences is compared, and the application can push personalization to different users in conjunction with the dressing information of user
Business object data, push effect is more preferable, while also can be avoided salesman and user and chatting the dislike linked up and cause user.
Above description is only the general introduction of technical scheme, in order to better understand the technological means of the application,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects, features and advantages of the application can
It is clearer and more comprehensible, below the special specific embodiment for lifting the application.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen
Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings:
Fig. 1 shows a kind of flow diagram of the method for pushing of business object data provided by the embodiments of the present application；
Fig. 2 shows the flow diagrams of the method for pushing of another business object data provided by the embodiments of the present application；
Fig. 3 shows a kind of structural schematic diagram of the driving means of business object data provided by the embodiments of the present application；
Fig. 4 shows the structural schematic diagram of the driving means of another business object data provided by the embodiments of the present application.
Specific embodiment
The application is described in detail below with reference to attached drawing and in conjunction with the embodiments.It should be noted that not conflicting
In the case of, the features in the embodiments and the embodiments of the present application can be combined with each other.
A kind of method for pushing of business object data is provided in the present embodiment, as shown in Figure 1, this method comprises:
Step 101, target user's image information is obtained.
Below by taking financial product data are business object as an example, the embodiment of the present application is illustrated, the application can provide
Two kinds of application scenarios: first, target user enters off-line transaction hall, acquires target user by the camera in trading hall
Image information；Second, by the computer terminal (such as smart phone, computer etc.) of target user in terminal photograph album or
The image information of other storage locations acquisition target user.
It should be noted that obtaining the process of target user's image information by camera are as follows: receive camera acquisition
After image information, recognition of face processing is carried out to image information, and the face letter in the face information and database that will identify that
Breath is matched, and after determining target user's identity, the image information of acquisition is determined as target user's image information.
In addition, obtaining the process of target user's image information by terminal device are as follows: the photographic intelligence of receiving terminal apparatus,
The reserved face information for obtaining terminal user, finds out photo relevant to reserved face information as mesh in photographic intelligence
Mark user images information.
Step 102, from target user's image information, dressing characteristic information relevant to target user is extracted.
It may include image background, other staff etc. in the image information of target user, need to extract from image
Dressing characteristic information relevant to target user out, for example, the clothes fashion of user is leisure money, movement money, fashionable dress money, commercial affairs
Money etc..
Step 103, according to dressing characteristic information, the personality scoring of target user is calculated.
The dressing feature of target user can usually reflect the personality preference of user, such as wear the people of commercial money clothes
Usually have rigorous personality, so as to the subsequent personality according to target user score to target user push it is matched with its personality
The information of product.
It should be noted that personality scoring here, is subsequent transmission service object data and calculates, personality scoring
Height do not react the quality of user's personality, differentiation is only made to the personality of user, in a manner of scoring so as to according to property
Lattice scoring situation pushes the product information for being suitble to user.
Step 104, it is scored according to personality, calculates the matching degree of target user and business object.
Specifically, in step 103, it has been described that usually can speculate the personality preference of user by dressing feature,
Similar, the user for being also easy to deduce which kind of personality according to product characteristic is easier to generate interest to the product, therefore, according to mesh
The personality preference for marking user, according to the corresponding personality preference profile of product concluded in advance, calculating target user and product
Matching degree, matching degree is higher, represents the product and is easier to be received by target user.
Step 105, according to matching degree, to the corresponding data of target user's transmission service object.
Corresponding product is arranged according to the sequence of matching degree from big to small, to successively push in sequence to target user
Relevant product information, such as name of product, product library storage, the recent sales situation of product, the recent situation of Profit of product etc.,
To realize that the technical effect according to user preferences push product information, recommendation effect are more preferable, it is easier to be easily accepted by a user.
Alternatively, it is also possible to recommending matching degree to be greater than the corresponding product of product of preset value to target user, or to target
User recommends matching degree ranking in the product of several former.
Technical solution by applying this embodiment, the dressing that the user is extracted from the image information of target user are special
Sign, so that the personality to user scores, and scores according to personality and calculates the matching degree of user and business object, thus according to
Matching degree size to target user's transmission service object data, with recommend in the prior art hot-sale products and main product or
Salesman with user chat link up analysis user preferences by way of compared with, the application can in conjunction with user dressing information to
Different users pushes personalized business object data, and push effect is more preferable, while also can be avoided salesman and chatting with user
It links up the dislike for causing user.
Further, as the refinement and extension of above-described embodiment specific embodiment, in order to completely illustrate the present embodiment
Specific implementation process, provide the method for pushing of another business object data, as shown in Fig. 2, this method comprises:
Step 201, target user's image information is obtained.
The image information of target user is obtained from line or under line, to obtain the dressing of target user from image information
Feature.
Step 202, the sample of users image information and corresponding with sample of users image information that image pattern is concentrated is obtained
Dressing characteristic information.
In this application, the dressing characteristic information of target user is by can be to the mould that dressing characteristic information extracts
What type obtained, therefore, first have to obtain training sample so as to training pattern, training sample include the image information of sample of users with
And the dressing characteristic information of sample of users.
Step 203, image preprocessing is carried out to sample of users image information.
In the above-described embodiments, specifically, image preprocessing process includes but is not limited to one of following operation or combination: with
Machine cuts, rotation, overturning, adjusts brightness and adjustment contrast.
Sample of users image information in training sample needs to carry out image preprocessing, is easy to distinguish to obtain being more clear
Other image, facilitates model training.
Step 204, using deep learning engine to treated sample of users image information and corresponding dressing feature
Information is trained, and obtains deep learning model.
It in the above-described embodiments, can be by the sample of users image information and its corresponding dressing feature letter in training sample
Breath is divided into several groups, obtains multiple training groups and a validation group, utilizes deep learning engine according to multiple training groups respectively
It is trained and obtains multiple deep learning models, then multiple deep learning models are verified respectively using validation group, count
The accuracy of identification of each model is calculated, the highest model of accuracy of identification deep learning model the most final is chosen, naturally it is also possible to
Specify any one in multiple deep learning models as deep learning model, deep learning model is used to utilize target user
Image information identification user dressing characteristic information.
It should be noted that can also only train a deep learning model to save the time.
Step 205, image preprocessing is carried out to target user's image information.
In order to improve the accuracy of identification of deep learning model, needs to pre-process target user's image information, make figure
As being more clear easy discrimination.
Step 206, using deep learning model, to treated, target user's image information is identified, is obtained and target
The dressing characteristic information of user.
It will be input in deep learning model by target user's image information of image preprocessing, pass through deep learning mould
Type identifies image information, extracts target user's dressing characteristic information corresponding with target user's image information.
Step 207, according to default dressing code of points, according to dressing style information, dressing colouring information and match respectively
Adorn the corresponding dressing style scoring of information matches, dressing color score and accessories scoring.
In the above-described embodiments, specifically, dressing characteristic information includes dressing style information, dressing colouring information and matches
Adorn information.
It include dressing style information in the dressing characteristic information of extraction, for example, leisure money, movement money, commercial money etc.,
Colouring information is filled, for example, black, white, camouflage color etc., accessory information, for example, peaked cap, handbag, leisure wrist-watch etc.
Deng according to default dressing code of points, respectively to the dressing style information of target user, dressing colouring information and accessory information
It scores.
For example, the dressing style of target user's first is leisure money, dressing color is navy blue, accessories are leisure wrist-watch, press
According to default dressing code of points, the corresponding dressing style scoring of the money that lies fallow is 0.5 point, and the corresponding dressing color score of navy blue is
0.8 point, the corresponding accessories scoring of leisure wrist-watch is 0.5 point, it is determined that the dressing style information of the target user, dressing color letter
Breath and accessory information are scored respectively 0.5,0.8,0.5.
Step 208, it is weighed according to the scoring of dressing style, dressing color score and accessories scoring and corresponding dressing style
Weight, dressing color weight and accessories weight are weighted and ask to the scoring of dressing style, dressing color score and accessories scoring
It scores with the personality for obtaining target user.
According to default dressing style weight, dressing color weight and accessories weight, to the scoring of dressing style, dressing color
Scoring and accessories scoring are weighted summation, to obtain the personality scoring of target user.
For example, default dressing style weight, dressing color weight and accessories weight, respectively 0.5,0.3,0.2, then on
State personality scoring=0.5*0.5+0.3*0.8+0.2*0.5=0.59 of user's first.
In addition, it is necessary to explanation, above-mentioned dressing style weight, dressing color weight and accessories weight can be according to days
Gas information is made appropriate adjustment, such as rainy weather or winter, and people, which more have a preference for, wears the deeper clothes of color, at this time can be appropriate
Reduce weight of the color score in overall score, increase other weights, for example, by dressing style weight, dressing color weight and
It is 0.5,0.2,0.3 that accessories weight, which adjusts separately,.
Step 209, the personality factor is matched according to personality scoring and pre-set business object-rule for each product；
Specifically, according to pre-set business object-rule, the scoring of business object is obtained；According to personality factor calculation formula,
The personality factor, personality factor calculation formula are calculated using the scoring of business object and personality scoring are as follows:
X=1- | i-j | × k,
Wherein, X is the personality factor, and i is personality scoring, and j is product scoring, and k is predetermined coefficient.
In the above-described embodiments, for each product, the personality factor is to calculate matching degree between product and target user
One of condition.First, in accordance with pre-set product rule, then the corresponding product scoring of matching product is scored according to the personality of user
And product scoring, target user is calculated for the personality factor size of the product.
Specifically, the value range of the personality factor be (0,1], here, utilize target user personality scoring with the production
The absolute value of the scoring of product and the product of predetermined coefficient, to calculate the size of the personality factor, it should be noted that above-mentioned exhausted in order to make
To the product with predetermined coefficient is worth less than 1, determine that predetermined coefficient k's is big by the value range of personality scoring and product scoring
It is small, if not 1 point of full marks that personality scoring and product score, k takes 1；If the full marks of personality scoring and product scoring are equal
It is 10 points, then k takes 0.1；If the full marks non-q, k of personality scoring and product scoring take 1/q.
For example, it is assumed that the full marks of personality scoring and product scoring are all 1 point, the personality scoring of user's first is 0.59, currency
The product scoring of fund A is 0.9, then user's first is 1- to the personality factor of monetary fund A | 0.59-0.9 |=0.61.
Step 210, obtain the historical purchase information of target user, and according to the purchase of historical purchase information analysis of history because
Son.
In the above-described embodiments, specifically, according to pre-set business object classification rule, the classification of business object is obtained；It obtains
Take the historical purchase information of target user；According to historical purchase information, counting user buys the corresponding whole business pair of the category
The number m of elephant and target user buy the total degree n of all categories business object, buy the factor for m/n as history.
According to preset product classification information, using the historical purchase information of target user to target user to the said goods
The history purchase factor calculated, specifically, first, in accordance with pre-set product classifying rules, the type of the said goods is carried out
Matching, and then find out all products identical with the product type；Then according to the historical purchase information of target user, mesh is counted
Mark user buys the number m of the type product and target user buys the total degree n of all products；Finally calculate history purchase
The factor is bought, it is m/n that history, which buys the factor,.
It is determined it should be noted that pre-set business object classification rule can score according to the product of every kind of product, for example,
Product is scored and is divided into classification 1 for 0-0.3 points of product, the product that product scoring is 0.3-0.6 is divided into classification 2, product
The product that scoring is 0.6-0.8 is divided into classification 3, and the product that product scoring is 0.8-1 is divided into classification 4.
For example, the product scoring of monetary fund A is 0.9 point, according to pre-set business object classification rule, monetary fund A belongs to
It is analyzed in classification 4, and then according to the historical purchase information of user's first, the total degree that user's first buys all products is 15 times,
In, the number that purchase belongs to the product of classification 4 is 9 times, then user's first is 9/15=to the history purchase factor of monetary fund A
0.6。
Step 211, according to the inventory information of product, the corresponding inventory's factor of product is obtained.
In the above-described embodiments, specifically, the inventory information of business object is obtained, if determining business pair according to inventory information
As not in stock, then inventory's factor is 0；If determining business object in stock according to inventory information, inventory's factor is 1.
If the product is 0 without enabling inventory's factor to the data that user pushes the product, otherwise without inventory
Inventory's factor is 1.
For example, above-mentioned monetary fund A is by inquiry, in stock, then inventory's factor takes 1.
It should be noted that inventory's factor can also be determined according to specific quantity in stock.For example, quantity in stock be 1000 with
On then think inventory's abundance, inventory's factor is set as 1, and quantity in stock is between 0-100, then it is assumed that low stock, inventory's factor
It is set as 0.1.
Step 212, the product for calculating the personality factor, the history purchase factor and inventory's factor, obtains target user and product
Matching degree.
The matching degree of target user and product is the product of the personality factor, the history purchase factor and inventory's factor.
For example, user's first and the matching degree of monetary fund A=personality factor 0.61* history buy factor 0.6* inventory's factor
1=0.366.
Step 213, according to matching degree, to the corresponding data of target user's transmission service object.
After the matching degree for calculating target user and all over products, recommend corresponding product data to user, to realize use
Family personalized recommendation.
Technical solution by applying this embodiment is calculated using the dressing characteristic information extracted in user images information and is used
The personality at family scores, and default scoring, the historical purchase information of user and the inventories of product of combination product, calculates and uses
The matching degree at family and every kind of business object, to realize according to the size transmission service object data of matching degree to user's
Personalized ventilation system, recommendation effect is more preferable, also avoids directly causing user to dislike with user's progress communication exchange, improve
User experience.
Further, the specific implementation as Fig. 1 method, the embodiment of the present application provide a kind of pushing away for business object data
Device is sent, as shown in figure 3, the device includes: target image acquiring unit 31, dressing feature extraction unit 32, personality scoring meter
Calculate unit 33, product matching degree computing unit 34, business object data push unit 35.
Target image acquiring unit 31, for obtaining target user's image information；
Dressing feature extraction unit 32, for extracting dressing relevant to target user from target user's image information
Characteristic information；
Personality scoring computing unit 33, for calculating the personality scoring of target user according to dressing characteristic information；
Business object matching degree computing unit 34 calculates of target user and business object for scoring according to personality
With degree；
Business object data push unit 35 is used for according to matching degree, to the corresponding number of target user's transmission service object
According to.
In specific application scenarios, as shown in figure 4, dressing feature extraction unit 32, specifically includes: sample image obtains
Unit 321, sample image pretreatment unit 322, model training unit 323, target image pretreatment unit 324, dressing feature
Extract subelement 325.
Sample image acquiring unit 321, for obtaining the sample of users image information and and sample of image pattern concentration
The corresponding dressing characteristic information of user images information；
Sample image pretreatment unit 322, for carrying out image preprocessing to sample of users image information；
Model training unit 323, for using deep learning engine to treated sample of users image information and right
The dressing characteristic information answered is trained, and obtains deep learning model；
Target image pretreatment unit 324, for carrying out image preprocessing to target user's image information；
Dressing feature extraction subelement 325, for using deep learning model to treated target user's image information
It is identified, obtains the dressing characteristic information with target user.
In any of the above-described embodiment, specifically, dressing characteristic information include dressing style information, dressing colouring information with
And accessory information.
The computing unit 33 as shown in figure 4, personality scores, specifically includes: dressing scoring computing unit 331, personality scoring meter
Operator unit 332.
Dressing is scored computing unit 331, for according to default dressing code of points, respectively according to dressing style information,
It fills colouring information and accessory information matches corresponding dressing style scoring, dressing color score and accessories scoring；
Personality score computation subunit 332, for according to dressing style scoring, dressing color score and accessories scoring and
Corresponding dressing style weight, dressing color weight and accessories weight to the scoring of dressing style, dressing color score and are matched
Decorations scoring is weighted the personality scoring that summation obtains target user.
In specific application scenarios, as shown in figure 4, business object matching degree computing unit 34, specifically includes: personality because
Sub- computing unit 341, history purchase factor calculating unit 342, inventory's factor calculating unit 343, business object matching degree calculate
Subelement 344.
Personality factor calculating unit 341 is used for for each business object, according to personality scoring and pre-set business pair
As rule, the personality factor is matched.
In the above-described embodiments, specifically, personality factor calculating unit 341 is specifically used for being advised according to pre-set business object
Then, the scoring of business object is obtained；According to personality factor calculation formula, calculated using the scoring of business object and personality scoring
The personality factor, personality factor calculation formula are as follows:
X=1- | i-j | × k,
Wherein, X is the personality factor, and i is personality scoring, and j is product scoring, and k is predetermined coefficient.
History buys factor calculating unit 342, buys for obtaining the historical purchase information of target user, and according to history
Information analysis history buys the factor.
In the above-described embodiments, specifically, according to pre-set business object classification rule, the classification of business object is obtained；It obtains
Take the historical purchase information of target user；According to historical purchase information, counting user buys the corresponding whole business pair of the category
The number m of elephant and target user buy the total degree n of all categories business object, buy the factor for m/n as history.
Inventory's factor calculating unit 343 obtains the corresponding inventory of business object for the inventory information according to business object
The factor.
In the above-described embodiments, specifically, the inventory information of business object is obtained, if determining business pair according to inventory information
As not in stock, then inventory's factor is 0；If determining business object in stock according to inventory information, inventory's factor is 1.
Business object matching degree computation subunit 344, for calculating the personality factor, the history purchase factor and inventory's factor
Product, obtain the matching degree of target user and business object.
In the above-described embodiments, specifically, image preprocessing process includes but is not limited to one of following operation or combination: with
Machine cuts, rotation, overturning, adjusts brightness and adjustment contrast.
It should be noted that each function involved by a kind of driving means of business object data provided by the embodiments of the present application
Other corresponding descriptions of unit, can be with reference to the corresponding description in Fig. 1 and Fig. 2, and details are not described herein.
Based on above-mentioned method as depicted in figs. 1 and 2, correspondingly, the embodiment of the present application also provides a kind of storage medium,
On be stored with computer program, which realizes above-mentioned business object data as depicted in figs. 1 and 2 when being executed by processor
Method for pushing.
Based on this understanding, the technical solution of the application can be embodied in the form of software products, which produces
Product can store in a non-volatile memory medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), including some instructions
With so that computer equipment (can be personal computer, server or the network equipment an etc.) execution the application is each
Method described in implement scene.
Based on above-mentioned method as shown in Figure 1 and Figure 2 and Fig. 3, virtual bench embodiment shown in Fig. 4, in order to realize
Above-mentioned purpose, the embodiment of the present application also provides a kind of computer equipments, are specifically as follows personal computer, server, network
Equipment etc., the computer equipment include storage medium and processor；Storage medium, for storing computer program；Processor is used
The method for pushing of above-mentioned business object data as depicted in figs. 1 and 2 is realized in execution computer program.
Optionally, which can also include user interface, network interface, camera, radio frequency (Radio
Frequency, RF) circuit, sensor, voicefrequency circuit, WI-FI module etc..User interface may include display screen
(Display), input unit such as keyboard (Keyboard) etc., optional user interface can also connect including USB interface, card reader
Mouthful etc..Network interface optionally may include standard wireline interface and wireless interface (such as blue tooth interface, WI-FI interface).
It will be understood by those skilled in the art that a kind of computer equipment structure provided in this embodiment is not constituted to the meter
The restriction for calculating machine equipment, may include more or fewer components, perhaps combine certain components or different component layouts.
It can also include operating system, network communication module in storage medium.Operating system is management and preservation computer
The program of device hardware and software resource supports the operation of message handling program and other softwares and/or program.Network communication
Module is for realizing the communication between each component in storage medium inside, and between other hardware and softwares in the entity device
Communication.
Through the above description of the embodiments, those skilled in the art can be understood that the application can borrow
It helps software that the mode of necessary general hardware platform is added to realize, hardware realization can also be passed through.Believe from the image of target user
The dressing feature of the user is extracted in breath, so that the personality to user scores, and score according to personality calculate user with
The matching degree of business object and is pushed away in the prior art thus according to matching degree size to target user's transmission service object data
Hot-sale products and main product or salesman are recommended compared in such a way that user chats and links up analysis user preferences, this Shen
Personalized business object data please can be pushed to different users in conjunction with the dressing information of user, push effect is more preferable, together
When also can be avoided salesman and user and chat the dislike linked up and cause user.
It will be appreciated by those skilled in the art that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, module in attached drawing or
Process is not necessarily implemented necessary to the application.It will be appreciated by those skilled in the art that the mould in device in implement scene
Block can according to implement scene describe be distributed in the device of implement scene, can also carry out corresponding change be located at be different from
In one or more devices of this implement scene.The module of above-mentioned implement scene can be merged into a module, can also be into one
Step splits into multiple submodule.
Above-mentioned the application serial number is for illustration only, does not represent the superiority and inferiority of implement scene.Disclosed above is only the application
Several specific implementation scenes, still, the application is not limited to this, and the changes that any person skilled in the art can think of is all
The protection scope of the application should be fallen into.
Claims (10)
1. a kind of method for pushing of business object data characterized by comprising
Obtain target user's image information；
From target user's image information, dressing characteristic information relevant to the target user is extracted；
According to the dressing characteristic information, the personality scoring of the target user is calculated；
It is scored according to the personality, calculates the matching degree of the target user and business object；
According to the matching degree, Xiang Suoshu target user pushes the corresponding data of the business object.
2. the method according to claim 1, wherein described from target user's image information, extract with
The relevant dressing characteristic information of the target user, specifically includes:
Obtain the sample of users image information and dressing corresponding with sample of users image information spy that image pattern is concentrated
Reference breath；
Image preprocessing is carried out to the sample of users image information；
Using deep learning engine, to treated, the sample of users image information and corresponding dressing characteristic information are carried out
Training, obtains deep learning model；
Image preprocessing is carried out to target user's image information；
Using the deep learning model, to treated, target user's image information is identified, is obtained and the target
The dressing characteristic information of user.
3. the method according to claim 1, wherein the dressing characteristic information include dressing style information,
Fill colouring information and accessory information；
It is described according to the dressing characteristic information, calculate the personality scoring of the target user, specifically include:
According to default dressing code of points, according to the dressing style information, the dressing colouring information and described match respectively
Adorn the corresponding dressing style scoring of information matches, dressing color score and accessories scoring；
According to dressing style scoring, the dressing color score and accessories scoring and corresponding dressing style power
Weight, dressing color weight and accessories weight comment dressing style scoring, the dressing color score and the accessories
Divide and is weighted the personality scoring that summation obtains the target user.
4. according to the method in any one of claims 1 to 3, which is characterized in that it is described to be scored according to the personality, it calculates
The matching degree of the target user and business object, specifically include:
The personality factor is matched according to personality scoring and pre-set business object-rule for each business object；
The historical purchase information of the target user is obtained, and the factor is bought according to the historical purchase information analysis of history；
According to the inventory information of the business object, the corresponding inventory's factor of the business object is obtained；
Calculate the personality factor, the history purchase factor and inventory's factor product, obtain the target user with
The matching degree of the business object.
5. according to the method described in claim 4, it is characterized in that, described for each business object, according to the property
Lattice scoring and pre-set business object-rule, match the personality factor, specifically include:
According to the pre-set business object-rule, the scoring of the business object is obtained；
According to personality factor calculation formula, using the scoring of the business object and personality scoring calculate the personality because
Son, the personality factor calculation formula are as follows:
X=1- | i-j | × k,
Wherein, X is the personality factor, and i is personality scoring, and j is business object scoring, and k is predetermined coefficient.
6. according to the method described in claim 4, it is characterized in that, the historical purchase information for obtaining the target user,
And the factor is bought according to the historical purchase information analysis of history, it specifically includes:
According to pre-set business object classification rule, the classification of the business object is obtained；
Obtain the historical purchase information of the target user；
According to the historical purchase information, count the user buy the corresponding whole business objects of the category number m and
The target user buys the total degree n of all categories business object, buys the factor for m/n as the history.
7. according to the method described in claim 4, it is characterized in that, the inventory information according to the business object, obtains
The corresponding inventory's factor of the business object, specifically includes:
Obtain the inventory information of the business object；
If determining the business object not in stock according to the inventory information, inventory's factor is 0；
If determining the business object in stock according to the inventory information, inventory's factor is 1.
8. a kind of driving means of business object data characterized by comprising
Target image acquiring unit, for obtaining target user's image information；
Dressing feature extraction unit is extracted relevant to the target user for from target user's image information
Fill characteristic information；
Personality scoring computing unit, for calculating the personality scoring of the target user according to the dressing characteristic information；
Business object matching degree computing unit calculates the target user and business object for scoring according to the personality
Matching degree；
Business object data push unit, for according to the matching degree, Xiang Suoshu target user's transmission service object to be corresponding
Data.
9. a kind of storage medium, is stored thereon with computer program, which is characterized in that realization when described program is executed by processor
The method for pushing of business object data described in any one of claims 1 to 7.
10. a kind of computer equipment, including storage medium, processor and storage can be run on a storage medium and on a processor
Computer program, which is characterized in that the processor is realized described in any one of claims 1 to 7 when executing described program
Business object data method for pushing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811332144.1A CN109598578A (en) | 2018-11-09 | 2018-11-09 | The method for pushing and device of business object data, storage medium, computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811332144.1A CN109598578A (en) | 2018-11-09 | 2018-11-09 | The method for pushing and device of business object data, storage medium, computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109598578A true CN109598578A (en) | 2019-04-09 |
Family
ID=65958557
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811332144.1A Pending CN109598578A (en) | 2018-11-09 | 2018-11-09 | The method for pushing and device of business object data, storage medium, computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598578A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978672A (en) * | 2019-04-10 | 2019-07-05 | 南京诺博灵信息科技有限公司 | A kind of marketing system and method based on image recognition |
| CN110532461A (en) * | 2019-07-05 | 2019-12-03 | 中国平安财产保险股份有限公司 | Information platform method for pushing, device, computer equipment and storage medium |
| CN110766271A (en) * | 2019-09-10 | 2020-02-07 | 中国平安财产保险股份有限公司 | Customer service agent configuration method and device based on deep learning and computer equipment |
| CN111539376A (en) * | 2020-05-11 | 2020-08-14 | 南京林业大学 | Multi-modal emotion recognition system and method based on video images |
| CN112637295A (en) * | 2020-12-15 | 2021-04-09 | 平安普惠企业管理有限公司 | Business object pushing method, device, equipment and storage medium |
| CN112884399A (en) * | 2021-01-28 | 2021-06-01 | 重庆允成互联网科技有限公司 | Industrial product online marketing method, server and system based on storeroom front-end processor |
| CN115934179A (en) * | 2022-09-26 | 2023-04-07 | 贝壳找房(北京)科技有限公司 | Service function control method and equipment |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103309976A (en) * | 2013-06-13 | 2013-09-18 | 华东师范大学 | Method for improving social recommendation efficiency based on user personality |
| CN103533438A (en) * | 2013-03-19 | 2014-01-22 | Tcl集团股份有限公司 | Clothing push method and system based on intelligent television |
| CN104699770A (en) * | 2015-03-02 | 2015-06-10 | 惠州Tcl移动通信有限公司 | Method and system for analyzing and acquiring character features of user based on mobile terminal |
| CN105117924A (en) * | 2015-07-01 | 2015-12-02 | 向莉妮 | Personalized commodity recommendation system |
| CN105139237A (en) * | 2015-09-25 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Information push method and apparatus |
| CN105279242A (en) * | 2015-09-29 | 2016-01-27 | 浪潮(北京)电子信息产业有限公司 | Personalized recommendation method and system |
| CN105808774A (en) * | 2016-03-28 | 2016-07-27 | 北京小米移动软件有限公司 | Information providing method and device |
| CN106326441A (en) * | 2016-08-26 | 2017-01-11 | 乐视控股（北京）有限公司 | Information recommendation method and device |
| CN106776619A (en) * | 2015-11-20 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for determining the attribute information of destination object |
| CN107123057A (en) * | 2017-03-22 | 2017-09-01 | 阿里巴巴集团控股有限公司 | User recommends method and device |
| CN107169797A (en) * | 2017-05-16 | 2017-09-15 | 京东方科技集团股份有限公司 | Intelligent shopping guide method, system, shared server and intelligent shopping guide robot |
| CN107230104A (en) * | 2017-05-26 | 2017-10-03 | 喻继军 | Commodity diversity based on consuming character adaptively recommends method |
| CN107330706A (en) * | 2017-06-06 | 2017-11-07 | 上海航动科技有限公司 | A kind of electricity battalion's customer service system and commercial operation pattern based on artificial intelligence |
| CN108076128A (en) * | 2016-12-28 | 2018-05-25 | 北京市商汤科技开发有限公司 | User property extracting method, device and electronic equipment |
| CN108304429A (en) * | 2017-05-16 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Information recommendation method, device and computer equipment |
| US10083521B1 (en) * | 2015-12-04 | 2018-09-25 | A9.Com, Inc. | Content recommendation based on color match |
-
2018
- 2018-11-09 CN CN201811332144.1A patent/CN109598578A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103533438A (en) * | 2013-03-19 | 2014-01-22 | Tcl集团股份有限公司 | Clothing push method and system based on intelligent television |
| CN103309976A (en) * | 2013-06-13 | 2013-09-18 | 华东师范大学 | Method for improving social recommendation efficiency based on user personality |
| CN104699770A (en) * | 2015-03-02 | 2015-06-10 | 惠州Tcl移动通信有限公司 | Method and system for analyzing and acquiring character features of user based on mobile terminal |
| CN105117924A (en) * | 2015-07-01 | 2015-12-02 | 向莉妮 | Personalized commodity recommendation system |
| CN105139237A (en) * | 2015-09-25 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Information push method and apparatus |
| CN105279242A (en) * | 2015-09-29 | 2016-01-27 | 浪潮(北京)电子信息产业有限公司 | Personalized recommendation method and system |
| CN106776619A (en) * | 2015-11-20 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for determining the attribute information of destination object |
| US10083521B1 (en) * | 2015-12-04 | 2018-09-25 | A9.Com, Inc. | Content recommendation based on color match |
| CN105808774A (en) * | 2016-03-28 | 2016-07-27 | 北京小米移动软件有限公司 | Information providing method and device |
| CN106326441A (en) * | 2016-08-26 | 2017-01-11 | 乐视控股（北京）有限公司 | Information recommendation method and device |
| CN108076128A (en) * | 2016-12-28 | 2018-05-25 | 北京市商汤科技开发有限公司 | User property extracting method, device and electronic equipment |
| CN107123057A (en) * | 2017-03-22 | 2017-09-01 | 阿里巴巴集团控股有限公司 | User recommends method and device |
| CN107169797A (en) * | 2017-05-16 | 2017-09-15 | 京东方科技集团股份有限公司 | Intelligent shopping guide method, system, shared server and intelligent shopping guide robot |
| CN108304429A (en) * | 2017-05-16 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Information recommendation method, device and computer equipment |
| CN107230104A (en) * | 2017-05-26 | 2017-10-03 | 喻继军 | Commodity diversity based on consuming character adaptively recommends method |
| CN107330706A (en) * | 2017-06-06 | 2017-11-07 | 上海航动科技有限公司 | A kind of electricity battalion's customer service system and commercial operation pattern based on artificial intelligence |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978672A (en) * | 2019-04-10 | 2019-07-05 | 南京诺博灵信息科技有限公司 | A kind of marketing system and method based on image recognition |
| CN110532461A (en) * | 2019-07-05 | 2019-12-03 | 中国平安财产保险股份有限公司 | Information platform method for pushing, device, computer equipment and storage medium |
| CN110532461B (en) * | 2019-07-05 | 2023-06-02 | 中国平安财产保险股份有限公司 | Information platform pushing method and device, computer equipment and storage medium |
| CN110766271A (en) * | 2019-09-10 | 2020-02-07 | 中国平安财产保险股份有限公司 | Customer service agent configuration method and device based on deep learning and computer equipment |
| CN111539376A (en) * | 2020-05-11 | 2020-08-14 | 南京林业大学 | Multi-modal emotion recognition system and method based on video images |
| CN112637295A (en) * | 2020-12-15 | 2021-04-09 | 平安普惠企业管理有限公司 | Business object pushing method, device, equipment and storage medium |
| CN112637295B (en) * | 2020-12-15 | 2023-04-28 | 平安普惠企业管理有限公司 | Service object pushing method, device, equipment and storage medium |
| CN112884399A (en) * | 2021-01-28 | 2021-06-01 | 重庆允成互联网科技有限公司 | Industrial product online marketing method, server and system based on storeroom front-end processor |
| CN112884399B (en) * | 2021-01-28 | 2023-07-25 | 重庆允丰科技有限公司 | Online marketing method, server and system for industrial products based on warehouse front-end processor |
| CN115934179A (en) * | 2022-09-26 | 2023-04-07 | 贝壳找房(北京)科技有限公司 | Service function control method and equipment |
| CN115934179B (en) * | 2022-09-26 | 2023-11-24 | 贝壳找房(北京)科技有限公司 | Service function control method and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598578A (en) | The method for pushing and device of business object data, storage medium, computer equipment | |
| US20180268458A1 (en) | Automated recommendation and virtualization systems and methods for e-commerce | |
| US8718369B1 (en) | Techniques for shape-based search of content | |
| CN108197532A (en) | The method, apparatus and computer installation of recognition of face | |
| CN106055710A (en) | Video-based commodity recommendation method and device | |
| EP2953082A1 (en) | User-state mediated product selection | |
| CN108292425A (en) | Automatically the image capture guided and displaying | |
| US10672055B2 (en) | Method and system for presenting personalized products based on digital signage for electronic commerce | |
| CN105229689A (en) | Article automatic powder adding is added to the method for virtual shopping cart | |
| CN104981830A (en) | Clothing matching system and method | |
| CN104423945B (en) | A kind of information processing method and electronic equipment | |
| CN108509458B (en) | Business object identification method and device | |
| CN107169002A (en) | A kind of personalized interface method for pushing and device recognized based on face | |
| CN110084657A (en) | A kind of method and apparatus for recommending dress ornament | |
| CN111784449A (en) | Data pushing method, data pushing equipment, storage medium and device | |
| CN109858344A (en) | Love and marriage object recommendation method, apparatus, computer equipment and storage medium | |
| CN109947510A (en) | A kind of interface recommended method and device, computer equipment | |
| CN110879993A (en) | Neural network training method, and execution method and device of face recognition task | |
| KR102115364B1 (en) | Electronic business card platform and information sharing method using thereof | |
| CN108920828B (en) | Clothing matching method and system | |
| KR20200085723A (en) | Method and device for recommending facial wear products | |
| CN108596646A (en) | A kind of garment coordination recommendation method of fusion face character analysis | |
| CN113609319A (en) | Commodity searching method, device and equipment | |
| KR20230137861A (en) | Method and apparatus for providing offline purchase service providing convenience of purchase through customized preparation | |
| KR20210127464A (en) | Coodinating and styling methods and systems through deep learning |
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 |