CN109816441A - Tactful method for pushing, system and relevant apparatus - Google Patents
Tactful method for pushing, system and relevant apparatus Download PDFInfo
- Publication number
- CN109816441A CN109816441A CN201910035727.6A CN201910035727A CN109816441A CN 109816441 A CN109816441 A CN 109816441A CN 201910035727 A CN201910035727 A CN 201910035727A CN 109816441 A CN109816441 A CN 109816441A
- Authority
- CN
- China
- Prior art keywords
- customer
- portrait
- attribute
- image information
- end article
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
It includes: the image information for obtaining the first customer and the second customer that the embodiment of the present application, which discloses a kind of tactful method for pushing, system and relevant apparatus, method, and determines the first customer according to image information as shopping user, and the second customer is colleague user;Determine that the first attribute portrait of the first customer and mood are drawn a portrait and the second attribute of the second customer is drawn a portrait according to image information;It is obtained and the first highest end article of customer match degree according to the first attribute portrait, the purchasing power scoring that the first customer is obtained according to the first attribute portrait and the second attribute portrait obtains the probability that the first customer buys default commodity according to the second attribute portrait and mood portrait;Shopping guide's Policy model that the probability of end article, purchasing power scoring and the default commodity of purchase is imported to pre-training, obtains shopping guide's strategy;Export shopping guide's strategy.The embodiment of the present application advantageously reduces the difficulty that data are acquired under line, is drawn a portrait in real time to customer, and the accuracy and validity for being directed to customer shopping guide strategy are improved.
Description
Technical field
This application involves field of artificial intelligence, and in particular to a kind of strategy method for pushing, system and relevant apparatus.
Background technique
With the development of artificial intelligence technology, current existing purchase guiding system passes through real-time collecting commodity data on line, disappears
The person of expense buys the data and other related datas of commodity, and the demand to active user predicts, according to prediction result to user
Recommend suitable product.And the difficulty of the purchase guiding system data acquisition under line, cause the prediction error needed to user big,
The foundation that hotel owner effectively executes decision can not be given.
Summary of the invention
The embodiment of the present application provides a kind of tactful method for pushing, system and relevant apparatus, acquires number under line to reduce
According to difficulty, drawn a portrait in real time to customer, improve be directed to customer shopping guide strategy accuracy and validity.
In a first aspect, the embodiment of the present application provides a kind of tactful method for pushing, comprising:
The image information of the first customer and the second customer are obtained, and determines that first customer is according to the image information
Do shopping user, and second customer is colleague user;
The the first attribute portrait and mood portrait and described second of first customer are determined according to the image information
The second attribute of customer is drawn a portrait;
According to first attribute portrait obtain with the highest end article of the first customer match degree, according to described the
One attribute portrait and second attribute portrait obtain the purchasing power scoring of first customer, are drawn a portrait according to second attribute
The probability that first customer buys default commodity is obtained with mood portrait;
The probability of the end article, purchasing power scoring and the purchase default commodity is imported into pre-training
Shopping guide's Policy model obtains shopping guide's strategy;
Export shopping guide's strategy.
Second aspect, the embodiment of the present application provide a kind of tactful supplying system characterized by comprising
Image processing arrangement, for obtaining the image information of the first customer and the second customer, and according to the image information
First customer is determined as shopping user, second customer is colleague user;It is also used to be determined according to the image information
The the first attribute portrait and mood portrait of first customer and the second attribute portrait of second customer;It is also used to root
According to the acquisition of first attribute portrait and the highest end article of the first customer match degree, drawn a portrait according to first attribute
The purchasing power scoring that first customer is obtained with second attribute portrait, according to second attribute portrait and the mood
Portrait obtains the probability that first customer buys default commodity;Be also used to by the end article, the purchasing power scoring and
The probability of the purchase default commodity imports shopping guide's Policy model of pre-training, obtains shopping guide's strategy;It is also used to export institute
State shopping guide's strategy.
The third aspect, the embodiment of the present application provide a kind of tactful driving means, are applied to tactful supplying system, the strategy
Driving means includes processing unit and communication unit, wherein
The processing unit, for obtaining the image information of the first customer and the second customer, institute by the communication unit
It states processing unit and first customer is determined as shopping user according to the image information, second customer is colleague user;
And the first attribute portrait and mood portrait and second customer of first customer is determined according to the image information
The second attribute portrait;And it is obtained and the highest target quotient of the first customer match degree according to first attribute portrait
Product score according to the purchasing power that first attribute portrait and second attribute portrait obtain first customer, according to institute
It states the second attribute portrait and mood portrait obtains the probability that first customer buys default commodity;And by the target
The probability of commodity, purchasing power scoring and the purchase default commodity imports shopping guide's Policy model of pre-training, obtains
Shopping guide's strategy;And shopping guide's strategy is exported by the communication unit.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, wherein above-mentioned computer-readable
Storage medium storage is used for the computer program of electronic data interchange, wherein above-mentioned computer program executes computer such as
Step some or all of described in the embodiment of the present application first aspect either method.
5th aspect, the embodiment of the present application provide a kind of computer program product, wherein above-mentioned computer program product
Non-transient computer readable storage medium including storing computer program, above-mentioned computer program are operable to make to calculate
Machine executes the step some or all of as described in the embodiment of the present application first aspect either method.The computer program product
It can be a software installation packet.
As can be seen that obtaining the image information of the first customer and the second customer first, and according to shadow in the embodiment of the present application
As information determine the first customer for shopping user, the second customer be colleague user;Then, the first customer is determined according to image information
The first attribute portrait and mood portrait and the second customer the second attribute portrait;It is obtained secondly, being drawn a portrait according to the first attribute
With the first highest end article of customer match degree, the purchase of the first customer is obtained according to the first attribute portrait and the second attribute portrait
Power scoring is bought, the probability that the first customer buys default commodity is obtained according to the second attribute portrait and mood portrait;Again, by target
The probability of commodity, purchasing power scoring and the default commodity of purchase imports shopping guide's Policy model of pre-training, obtains shopping guide's strategy;Most
Afterwards, output shopping guide strategy.As it can be seen that tactful supplying system can by acquiring image information, analysis and determine the first customer and
The attribute of two customers is drawn a portrait, and then the scoring of the determining and highest end article of the first customer match degree, purchasing power and purchase
The probability of default commodity reduces eventually by the output of deep learning model for shopping guide's strategy of the first customer and acquires number under line
According to difficulty, drawn a portrait in real time to customer, improve shopping guide's strategy accuracy and validity.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of flow diagram of tactful method for pushing provided by the embodiments of the present application;
Fig. 2 is the flow diagram of another tactful method for pushing provided by the embodiments of the present application;
Fig. 3 is the flow diagram of another tactful method for pushing provided by the embodiments of the present application;
Fig. 4 is a kind of schematic diagram of tactful supplying system provided by the embodiments of the present application;
Fig. 5 is a kind of functional unit composition block diagram of tactful driving means provided by the embodiments of the present application.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall in the protection scope of this application.
The description and claims of this application and term " first " in above-mentioned attached drawing, " second " etc. are for distinguishing
Different objects, are not use to describe a particular order.In addition, term " includes " and " having " and their any deformations, it is intended that
It is to cover and non-exclusive includes.Such as the process, method, system, product or equipment for containing a series of steps or units do not have
It is defined in listed step or unit, but optionally further comprising the step of not listing or unit, or optionally also wrap
Include other step or units intrinsic for these process, methods, product or equipment.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
Referring to Fig. 1, Fig. 1 is that the embodiment of the present application provides a kind of flow diagram of tactful method for pushing, as schemed institute
Show, this strategy method for pushing includes:
S101, obtains the image information of the first customer and the second customer, and determines described first according to the image information
Customer is shopping user, and second customer is colleague user;
Wherein, the image information includes pictorial information and video information.
In the specific implementation, the image information of customer can be captured using optical camera, including the candid photograph based on capture machine
Picture, and video information acquisition is carried out based on camera.According to the pictorial information and video information determination
First customer is shopping user, and second customer is colleague user.
In the specific implementation, the first customer can be used as the same passerby of the second customer in shopping process, i.e., cared for for second
When visitor's analysis shopping guide's strategy, the second customer is shopping user, and the first customer is colleague user.
S102 determines that the first attribute portrait of first customer and mood are drawn a portrait according to the image information, Yi Jisuo
State the second attribute portrait of the second customer;
Wherein, the first attribute portrait and the second attribute portrait include age information, gender information, occupational information, face
Looks information;Height information, weight information, waistline information;Clothes fashion, garment language, clothes pattern etc..
In the specific implementation, determining that the first attribute of first customer is drawn a portrait according to the image information of first customer;
The video in human facial expression information analysis and image information is carried out according to the pictorial information in the image information of first customer
Information carries out motion analysis, determines the mood portrait of first customer;Institute is determined by the image information of second customer
State the second attribute portrait of the second customer.
S103, according to first attribute portrait obtain with the highest end article of the first customer match degree, according to
The first attribute portrait and second attribute portrait obtain the purchasing power scoring of first customer, belong to according to described second
Property portrait and mood portrait obtain the probability that first customer buys default commodity;
S104 imports the probability of the end article, purchasing power scoring and the purchase default commodity pre-
Trained shopping guide's Policy model obtains shopping guide's strategy;
Wherein, shopping guide's strategy includes whether to need shopping guide's follow-up first customer, if recommends shopping place
The type etc. of commodity.
Wherein, shopping guide's Policy model is preparatory trained deep learning model.
In the specific implementation, by the end article, the probability of purchasing power scoring and the purchase default commodity
It as input content, is input in preparatory trained shopping guide's Policy model, shopping guide's Policy model output shopping guide's strategy.
S105 exports shopping guide's strategy.
In the specific implementation, obtaining output shopping guide's strategy such as electronic equipment of the backward businessman staff of shopping guide's strategy.
As can be seen that obtaining the image information of the first customer and the second customer first, and according to shadow in the embodiment of the present application
As information determine the first customer for shopping user, the second customer be colleague user;Then, the first customer is determined according to image information
The first attribute portrait and mood portrait and the second customer the second attribute portrait;It is obtained secondly, being drawn a portrait according to the first attribute
With the first highest end article of customer match degree, the purchase of the first customer is obtained according to the first attribute portrait and the second attribute portrait
Power scoring is bought, the probability that the first customer buys default commodity is obtained according to the second attribute portrait and mood portrait;Again, by target
The probability of commodity, purchasing power scoring and the default commodity of purchase imports shopping guide's Policy model of pre-training, obtains shopping guide's strategy;Most
Afterwards, output shopping guide strategy.As it can be seen that tactful supplying system can by acquiring image information, analysis and determine the first customer and
The attribute of two customers is drawn a portrait, and then the scoring of the determining and highest end article of the first customer match degree, purchasing power and purchase
The probability of default commodity reduces eventually by the output of deep learning model for shopping guide's strategy of the first customer and acquires number under line
According to difficulty, drawn a portrait in real time to customer, improve shopping guide's strategy accuracy and validity.
It is described to determine that the first attribute of first customer is drawn a portrait according to the image information in a possible example
With the second attribute portrait of mood portrait and second customer, comprising: the image information is imported to the attribute of pre-training
Portrait learning model obtains the physiologic information and wearing information of first customer and second customer;Believed according to the physiology
Breath and the wearing information determine the first attribute portrait and second attribute portrait;Institute is obtained by the image information
State the expression information and action message of the first customer;The expression information and the action message are imported to the mood point of pre-training
Class learning model obtains the more class probabilities of mood of first customer;Described is determined according to the more class probabilities of the mood
The mood of one customer is drawn a portrait.
Wherein, the physiologic information includes the information such as age, gender, the colour of skin, posture, and the wearing information includes clothes money
Formula, style, clothes pattern, the information such as clothes and accessories brand.The attribute portrait learning model is preparatory trained depth
Learning model, the mood classification learning model are preparatory trained deep learning model.
In the specific implementation, importing the attribute portrait learning model of pre-training using image information as input content, institute is obtained
The first physiologic information and the first wearing information for stating the first customer, are established according to first physiologic information and the first wearing information
First attribute portrait.It draws a portrait learning model using the image information as the attribute that input content imports pre-training, described in acquisition
The second physiologic information of second customer and the second wearing information establish the according to second physiologic information and the second wearing information
Two attributes portrait.Facial Expression Analysis is carried out by the image information of first customer and motion analysis obtains the first customer's
Expression information and action message imported into preparatory trained mood classification learning using expression information and action message as input
Model, mood classification learning model export the more class probabilities of mood of the first customer, according to the more class probabilities determinations of mood
The mood of first customer is drawn a portrait, and it includes glad, sad, indignation etc. that mood is classified more.
As it can be seen that tactful supplying system can determine the first of first customer based on the image information in this example
Attribute portrait and mood portrait and the second attribute portrait of second customer, are able to carry out real-time portrait, realize and be directed to
The personalized portrait of different customers.
It is described to be obtained with the first customer match degree most according to first attribute portrait in a possible example
High end article is commented according to the purchasing power that first attribute portrait and second attribute portrait obtain first customer
Point, the probability that first customer buys default commodity is obtained according to second attribute portrait and mood portrait, comprising:
First attribute is drawn a portrait and imports the matching degree learning model of pre-training, is obtained and the highest quotient of the first customer match degree
Product;The purchasing power scoring learning model that first attribute portrait and second attribute portrait are imported to pre-training, obtains institute
State the purchasing power scoring of the first customer;Second attribute portrait and mood portrait are imported to the purchase probability of pre-training
Model is practised, the probability of the shopping of first customer is obtained.Wherein, the matching degree learning model is preparatory trained depth
Learning model, for determining and the first highest commodity of customer match degree.
In the specific implementation, regarding the first attribute portrait of first customer as input content, import trained in advance
Matching degree learning model, matching degree learning model exports in shopping place and the first highest end article of customer match degree.
Wherein, the purchasing power scoring learning model is preparatory trained deep learning model, for judging customer's
Purchasing power, and score the purchasing power of customer.
Make in the specific implementation, the second attribute of the first attribute portrait of first customer and second customer is drawn a portrait
The purchasing power scoring learning model of pre-training is imported for input content, the purchasing power scoring learning model output described first cares for
The purchasing power scoring of visitor.
Wherein, the purchase probability learning model is preparatory trained deep learning model, for determining that customer is directed to
The purchase probability of default commodity, the default commodity, which can be, determines that first customer checks by the image information
Commodity.
In the specific implementation, by the second attribute portrait of second customer and the mood portrait of first customer as defeated
Enter the purchase probability learning model that content imports pre-training, the purchase probability learning model exports the shopping of first customer
Probability.
As it can be seen that in this example, since tactful supplying system can be drawn a portrait based on the first attribute of the first customer, mood portrait
It draws a portrait with the second attribute of the second customer, and trained deep learning model in advance, determining and first customer match
It spends highest end article, purchasing power scoring, for the purchase probability of default commodity, is able to reflect the letter of the psychological levels of user
Breath improves the accuracy and validity of shopping guide's strategy.
In a possible example, obtained and the first customer match degree highest according to first attribute portrait
End article after, further includes: according to the end article obtain push content;The push content is sent to shopping field
Advertisement screen and/or first customer electronic equipment.
In the specific implementation, the push content can be sent to the advertisement screen of shopping place, it can also be by the push
The first customer of prepackage APP, Xiang Suoshu that content is sent to the electronic equipment of first customer sends instant communication information etc..
As it can be seen that tactful supplying system can be based on and the highest end article of the first customer match degree in this example
Push content is sent to the first customer and advertisement screen, the first customer is improved to the purchase probability of end article, simplifies shopping guide
Process, understand end article information more easily convenient for customer, improve the shopping experience sense of customer.
In a possible example, the push content includes merchandise news and the position of the end article, institute
Stating merchandise news includes end article title, end article material, end article size and end article pictorial information.
In the concrete realization, the push content can increase or decrease according to the actual situation.
As it can be seen that tactful supplying system can allow users to quickly understand commodity by the content of transmission in this example,
Shopping speed is improved, shopping experience and shopping guide's effect are improved.
In a possible example, the push content is sent to the advertisement screen and/or described first of shopping place
Before the electronic equipment of customer, further includes: the electronic equipment of detection first customer;By described in image information determination
The face information of first customer, the face information is for positioning first customer;Bind the electronic equipment and the people
Face information.
In the concrete realization, the electronic equipment of first customer, such as shopping plaza can be detected by plurality of devices
Gate inhibition, the equipment being mounted on commodity supporter etc..
As it can be seen that in this example, by the way that the electronic equipment of first customer and the face information are bound,
In order to which accurately corresponding push content can be sent for first customer.
In a possible example, the face information of first customer, the people are determined by the image information
Face information is for after positioning first customer, further includes: when the end article for receiving first customer and being directed to
Selection instruction when, generate the navigation routine between first customer and the end article.
In the specific implementation, first customer selects the end article, it can be and click the push content, it can also be with
It is to click described end article etc..
As it can be seen that in this example, the selection instruction for being directed to end article by receiving the first customer generates the first customer to institute
The navigation routine for stating end article enables the first customer fast and accurately to find the Recommendations, improves shopping speed, mentions
Shopping experience and shopping guide's effect are risen.
It is consistent with above-mentioned embodiment shown in FIG. 1, referring to Fig. 2, Fig. 2 is a kind of strategy provided by the embodiments of the present application
The flow diagram of method for pushing, as shown, this strategy method for pushing includes:
S201, tactful supplying system obtain the image information of the first customer and the second customer, and according to the image information
First customer is determined as shopping user, second customer is colleague user;
The attribute portrait learning model that the image information imports pre-training is obtained institute by S202, the strategy supplying system
State the physiologic information and wearing information of the first customer and second customer;
S203, the strategy supplying system determine that first attribute is drawn according to the physiologic information and the wearing information
Picture and second attribute portrait;
S204, the strategy supplying system obtain expression information and the movement of first customer by the image information
Information;
S205, the strategy supplying system classify the mood that the expression information and the action message import pre-training
Learning model obtains the more class probabilities of mood of first customer;
S206, the strategy supplying system determine that the mood of first customer is drawn according to the more class probabilities of the mood
Picture;
S207, the strategy supplying system, which draws a portrait first attribute, imports the matching degree learning model of pre-training, obtains
It takes and the highest commodity of the first customer match degree;First attribute portrait and second attribute portrait are imported into pre- instruction
Experienced purchasing power scoring learning model, obtains the purchasing power scoring of first customer;By second attribute portrait and it is described
Mood portrait imports the purchase probability learning model of pre-training, obtains the probability of the shopping of first customer;
S208, the strategy supplying system are described default by the end article, purchasing power scoring and the purchase
The probability of commodity imports shopping guide's Policy model of pre-training, obtains shopping guide's strategy;
S209, the strategy supplying system export shopping guide's strategy.
As can be seen that obtaining the image information of the first customer and the second customer first, and according to shadow in the embodiment of the present application
As information determine the first customer for shopping user, the second customer be colleague user;Then, the first customer is determined according to image information
The first attribute portrait and mood portrait and the second customer the second attribute portrait;It is obtained secondly, being drawn a portrait according to the first attribute
With the first highest end article of customer match degree, the purchase of the first customer is obtained according to the first attribute portrait and the second attribute portrait
Power scoring is bought, the probability that the first customer buys default commodity is obtained according to the second attribute portrait and mood portrait;Again, by target
The probability of commodity, purchasing power scoring and the default commodity of purchase imports shopping guide's Policy model of pre-training, obtains shopping guide's strategy;Most
Afterwards, output shopping guide strategy.As it can be seen that tactful supplying system can by acquiring image information, analysis and determine the first customer and
The attribute of two customers is drawn a portrait, and then the scoring of the determining and highest end article of the first customer match degree, purchasing power and purchase
The probability of default commodity reduces eventually by the output of deep learning model for shopping guide's strategy of the first customer and acquires number under line
According to difficulty, drawn a portrait in real time to customer, improve shopping guide's strategy accuracy and validity.
In addition, tactful supplying system can be determined based on the image information first customer the first attribute portrait and
Mood portrait and the second attribute portrait of second customer, are able to carry out real-time portrait, realize for different customers'
Personalization portrait.
It is consistent with above-mentioned embodiment shown in FIG. 1, referring to Fig. 3, Fig. 3 is a kind of strategy provided by the embodiments of the present application
The flow diagram of method for pushing, as shown, this strategy method for pushing includes:
S301, tactful supplying system obtain the image information of the first customer and the second customer, and according to the image information
First customer is determined as shopping user, second customer is colleague user;
S302, it is described strategy supplying system according to the image information determine first customer the first attribute portrait and
Mood portrait and the second attribute portrait of second customer;
S303, the strategy supplying system obtain and the first customer match degree highest according to first attribute portrait
End article, commented according to the purchasing power that first attribute portrait and second attribute portrait obtain first customer
Point, the probability that first customer buys default commodity is obtained according to second attribute portrait and mood portrait;
S304, the strategy supplying system obtain push content according to the end article;
The push content is sent to the advertisement screen and/or described the of shopping place by S305, the strategy supplying system
The electronic equipment of one customer;
S306, the strategy supplying system are described default by the end article, purchasing power scoring and the purchase
The probability of commodity imports shopping guide's Policy model of pre-training, obtains shopping guide's strategy;
S307, the strategy supplying system export shopping guide's strategy.
As can be seen that obtaining the image information of the first customer and the second customer first, and according to shadow in the embodiment of the present application
As information determine the first customer for shopping user, the second customer be colleague user;Then, the first customer is determined according to image information
The first attribute portrait and mood portrait and the second customer the second attribute portrait;It is obtained secondly, being drawn a portrait according to the first attribute
With the first highest end article of customer match degree, the purchase of the first customer is obtained according to the first attribute portrait and the second attribute portrait
Power scoring is bought, the probability that the first customer buys default commodity is obtained according to the second attribute portrait and mood portrait;Again, by target
The probability of commodity, purchasing power scoring and the default commodity of purchase imports shopping guide's Policy model of pre-training, obtains shopping guide's strategy;Most
Afterwards, output shopping guide strategy.As it can be seen that tactful supplying system can by acquiring image information, analysis and determine the first customer and
The attribute of two customers is drawn a portrait, and then the scoring of the determining and highest end article of the first customer match degree, purchasing power and purchase
The probability of default commodity reduces eventually by the output of deep learning model for shopping guide's strategy of the first customer and acquires number under line
According to difficulty, drawn a portrait in real time to customer, improve shopping guide's strategy accuracy and validity.
In addition, tactful supplying system can based on the highest end article of the first customer match degree to the first customer
Push content is sent with advertisement screen, the first customer is improved to the purchase probability of end article, simplifies the process of shopping guide, be convenient for
Customer more easily understands end article information, improves the shopping experience sense of customer.
It is consistent with above-mentioned Fig. 1, Fig. 2, embodiment shown in Fig. 3, referring to Fig. 4, Fig. 4 is provided by the embodiments of the present application
A kind of schematic diagram of strategy supplying system 400, as shown, this strategy supplying system 400 includes:
Image processing arrangement 410 is believed for obtaining the image information of the first customer and the second customer, and according to the image
Breath determines that first customer is shopping user, and second customer is colleague user;It is also used to true according to the image information
The the first attribute portrait and mood portrait of fixed first customer and the second attribute portrait of second customer;It is also used to
According to the acquisition of first attribute portrait and the highest end article of the first customer match degree, drawn according to first attribute
Picture and second attribute portrait obtain the purchasing power scoring of first customer, according to second attribute portrait and the feelings
Thread portrait obtains the probability that first customer buys default commodity;It is also used to score the end article, the purchasing power
Shopping guide's Policy model that pre-training is imported with the probability of the purchase default commodity, obtains shopping guide's strategy;It is also used to export
Shopping guide's strategy is to shopping guide's equipment;
Shopping guide's equipment 420, for receiving shopping guide's strategy.
As can be seen that obtaining the image information of the first customer and the second customer first, and according to shadow in the embodiment of the present application
As information determine the first customer for shopping user, the second customer be colleague user;Then, the first customer is determined according to image information
The first attribute portrait and mood portrait and the second customer the second attribute portrait;It is obtained secondly, being drawn a portrait according to the first attribute
With the first highest end article of customer match degree, the purchase of the first customer is obtained according to the first attribute portrait and the second attribute portrait
Power scoring is bought, the probability that the first customer buys default commodity is obtained according to the second attribute portrait and mood portrait;Again, by target
The probability of commodity, purchasing power scoring and the default commodity of purchase imports shopping guide's Policy model of pre-training, obtains shopping guide's strategy;Most
Afterwards, output shopping guide strategy.As it can be seen that tactful supplying system can by acquiring image information, analysis and determine the first customer and
The attribute of two customers is drawn a portrait, and then the scoring of the determining and highest end article of the first customer match degree, purchasing power and purchase
The probability of default commodity reduces eventually by the output of deep learning model for shopping guide's strategy of the first customer and acquires number under line
According to difficulty, drawn a portrait in real time to customer, improve shopping guide's strategy accuracy and validity.
In a possible example, the tactful supplying system 400, further includes:
The image processing arrangement 410 is also used to obtain push content according to the end article, send in the push
Hold;
Detection device 430, for detecting the electronic equipment of first customer;
Intelligent terminal 440, the electronic equipment of advertisement screen and first customer including shopping place, for receiving push
The push content.
It is above-mentioned that mainly the scheme of the embodiment of the present application is described from the angle of method side implementation procedure.It is understood that
, in order to realize the above functions, it comprises execute the corresponding hardware configuration of each function and/or software mould for electronic equipment
Block.Those skilled in the art should be readily appreciated that, in conjunction with each exemplary unit of embodiment description presented herein
And algorithm steps, the application can be realized with the combining form of hardware or hardware and computer software.Some function actually with
Hardware or computer software drive the mode of hardware to execute, the specific application and design constraint item depending on technical solution
Part.Professional technician can specifically realize described function to each using distinct methods, but this reality
Now it is not considered that exceeding scope of the present application.
The embodiment of the present application can carry out the division of functional unit according to above method example to electronic equipment, for example, can
With each functional unit of each function division of correspondence, two or more functions can also be integrated in a processing unit
In.Above-mentioned integrated unit both can take the form of hardware realization, can also realize in the form of software functional units.It needs
It is noted that be schematical, only a kind of logical function partition to the division of unit in the embodiment of the present application, it is practical real
It is current that there may be another division manner.
Fig. 5 is the functional unit composition block diagram of strategy driving means 500 involved in the embodiment of the present application.The strategy pushes away
Device 500 is sent to be applied to tactful supplying system, including processing unit 501 and communication unit 502, wherein
The processing unit 501, for obtaining the image letter of the first customer and the second customer by the communication unit 502
Breath determines first customer according to the image information as shopping user, and second customer is colleague user;And according to
The image information determines that the first attribute portrait of first customer and the second of mood portrait and second customer belongs to
Property portrait;And according to the acquisition of first attribute portrait and the highest end article of the first customer match degree, according to institute
It states the first attribute portrait and second attribute portrait obtains the purchasing power scoring of first customer, according to second attribute
Portrait and mood portrait obtain the probability that first customer buys default commodity;And by the end article, described
The probability of purchasing power scoring and the purchase default commodity imports shopping guide's Policy model of pre-training, obtains shopping guide's strategy;
And shopping guide's strategy is exported by the communication unit 502.
Wherein, the tactful driving means 500 can also include storage unit 503, for storing the program of electronic equipment
Code and data.The processing unit 501 can be processor, and the communication unit 502 can be touching display screen or receipts
Device is sent out, storage unit 503 can be memory.
In the embodiment of the present application, the image information of the first customer and the second customer are obtained first, and true according to image information
Fixed first customer is shopping user, and the second customer is colleague user;Then, determine the first customer according to image information first belongs to
Property portrait and mood portrait and the second customer the second attribute portrait;It is cared for secondly, being obtained according to the first attribute portrait with first
The objective highest end article of matching degree is commented according to the purchasing power that the first attribute portrait and the second attribute portrait obtain the first customer
Point, the probability that the first customer buys default commodity is obtained according to the second attribute portrait and mood portrait;Again, by end article,
Purchasing power scoring and the probability for buying default commodity import shopping guide's Policy model of pre-training, obtain shopping guide's strategy;Finally, output
Shopping guide's strategy.As it can be seen that tactful supplying system analysis and can determine the first customer and the second customer by acquiring image information
Attribute portrait, and then the scoring of the determining and highest end article of the first customer match degree, purchasing power and the default commodity of purchase
Probability, eventually by deep learning model output for the first customer shopping guide strategy, reduce line under acquire data difficulty
Property, it is drawn a portrait in real time to customer, improves the accuracy and validity of shopping guide's strategy.
In a possible example, determine that the first attribute of first customer is drawn according to the image information described
In terms of picture and mood portrait and the second attribute of second customer are drawn a portrait, the processing unit 501 is specifically used for: by institute
The attribute portrait learning model for stating image information importing pre-training obtains the physiology letter of first customer and second customer
Breath and wearing information;The first attribute portrait and second attribute are determined according to the physiologic information and the wearing information
Portrait;The expression information and action message of first customer are obtained by the image information;By the expression information and institute
The mood classification learning model that action message imports pre-training is stated, the more class probabilities of mood of first customer are obtained;According to
The more class probabilities of mood determine the mood portrait of first customer.
In a possible example, obtained and the first customer match degree described according to first attribute portrait
Highest end article obtains the purchasing power of first customer according to first attribute portrait and second attribute portrait
Scoring obtains the probability side that first customer buys default commodity according to second attribute portrait and mood portrait
Face, the processing unit 501 are specifically used for: first attribute being drawn a portrait and imports the matching degree learning model of pre-training, is obtained
With the highest commodity of the first customer match degree;First attribute portrait and second attribute portrait are imported into pre-training
Purchasing power score learning model, obtain the purchasing power scoring of first customer;By second attribute portrait and the feelings
Thread portrait imports the purchase probability learning model of pre-training, obtains the probability of the shopping of first customer.
In a possible example, the processing unit 501 obtains and described the according to first attribute portrait
It after the one highest end article of customer match degree, is also used to: push content is obtained according to the end article;By the push
Content is sent to the advertisement screen of shopping place and/or the electronic equipment of first customer.
In a possible example, the push content is sent to the advertisement of shopping place by the processing unit 501
It before screen and/or the electronic equipment of first customer, is also used to: the electronic equipment of detection first customer;By described
Image information determines the face information of first customer, and the face information is for positioning first customer;Described in binding
Electronic equipment and the face information.
In a possible example, the processing unit 501 determines first customer's by the image information
Face information, the face information is for being also used to: being directed to when receiving first customer after positioning first customer
The end article selection instruction when, generate the navigation routine between first customer and the end article.
The embodiment of the present application also provides a kind of computer storage medium, wherein computer storage medium storage is for electricity
The computer program of subdata exchange, the computer program make computer execute any as recorded in above method embodiment
Some or all of method step, above-mentioned computer include electronic equipment.
The embodiment of the present application also provides a kind of computer program product, and above-mentioned computer program product includes storing calculating
The non-transient computer readable storage medium of machine program, above-mentioned computer program are operable to that computer is made to execute such as above-mentioned side
Some or all of either record method step in method embodiment.The computer program product can be a software installation
Packet, above-mentioned computer includes electronic equipment.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because
According to the application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, related actions and modules not necessarily the application
It is necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed device, it can be by another way
It realizes.For example, the apparatus embodiments described above are merely exemplary, such as the division of said units, it is only a kind of
Logical function partition, there may be another division manner in actual implementation, such as multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be through some interfaces, the indirect coupling or communication connection of device or unit,
It can be electrical or other forms.
Above-mentioned unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If above-mentioned integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer-readable access to memory.Based on this understanding, the technical solution of the application substantially or
Person says that all or part of the part that contributes to existing technology or the technical solution can body in the form of software products
Reveal and, which is stored in a memory, including some instructions are used so that a computer equipment
(can be personal computer, server or network equipment etc.) executes all or part of each embodiment above method of the application
Step.And memory above-mentioned includes: USB flash disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), mobile hard disk, magnetic or disk.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in a computer-readable memory, memory
May include: flash disk, read-only memory (English: Read-Only Memory, referred to as: ROM), random access device (English:
Random Access Memory, referred to as: RAM), disk or CD etc..
The embodiment of the present application is described in detail above, specific case used herein to the principle of the application and
Embodiment is expounded, the description of the example is only used to help understand the method for the present application and its core ideas;
At the same time, for those skilled in the art can in specific embodiments and applications according to the thought of the application
There is change place, in conclusion the contents of this specification should not be construed as limiting the present application.
Claims (11)
1. a kind of strategy method for pushing characterized by comprising
The image information of the first customer and the second customer are obtained, and determines first customer for shopping according to the image information
User, second customer are colleague user;
The first attribute portrait of first customer is determined according to the image information and mood is drawn a portrait and second customer
The second attribute portrait;
According to the acquisition of first attribute portrait and the highest end article of the first customer match degree, belong to according to described first
Property portrait and second attribute portrait obtain the purchasing power scoring of first customer, according to second attribute portrait and institute
It states mood portrait and obtains the probability that first customer buys default commodity;
The probability of the end article, purchasing power scoring and the purchase default commodity is imported to the shopping guide of pre-training
Policy model, output shopping guide's strategy.
2. the method according to claim 1, wherein described determine first customer according to the image information
The first attribute portrait and mood portrait and second customer the second attribute portrait, comprising:
The attribute portrait learning model that the image information imports pre-training is obtained into first customer and second customer
Physiologic information and wearing information;
The first attribute portrait and second attribute portrait are determined according to the physiologic information and the wearing information;
The expression information and action message of first customer are obtained by the image information;
The mood classification learning model that the expression information and the action message are imported to pre-training, obtains first customer
The more class probabilities of mood;
The mood portrait of first customer is determined according to the more class probabilities of the mood.
3. the method according to claim 1, wherein described obtain and described the according to first attribute portrait
The one highest end article of customer match degree obtains described first according to first attribute portrait and second attribute portrait
The purchasing power of customer scores, and obtains first customer according to second attribute portrait and mood portrait and buys default quotient
The probability of product, comprising:
First attribute is drawn a portrait and imports the matching degree learning model of pre-training, is obtained and the first customer match degree highest
Commodity;
The purchasing power scoring learning model that first attribute portrait and second attribute portrait are imported to pre-training, obtains institute
State the purchasing power scoring of the first customer;
The purchase probability learning model that second attribute portrait and mood portrait are imported to pre-training, obtains described first
The probability of the shopping of customer.
4. the method according to claim 1, wherein being obtained and described first according to first attribute portrait
After the highest end article of customer match degree, further includes:
Push content is obtained according to the end article;
The push content is sent to the electronic equipment of the advertisement screen and/or first customer of shopping place.
5. according to the method described in claim 4, it is characterized in that, the push content includes the commodity letter of the end article
Breath and position, the merchandise news include end article title, end article material, end article size and end article figure
Piece information.
6. method according to claim 4 or 5, which is characterized in that the push content is sent to the wide of shopping place
Before announcement screen and/or the electronic equipment of first customer, further includes:
Detect the electronic equipment of first customer;
Determine that the face information of first customer, the face information are cared for for positioning described first by the image information
Visitor;
Bind the electronic equipment and the face information.
7. according to the method described in claim 6, it is characterized in that, determining the people of first customer by the image information
Face information, the face information are used to position after first customer, further includes:
When receiving the selection instruction for the end article that first customer is directed to, generate first customer with it is described
Navigation routine between end article.
8. a kind of strategy supplying system characterized by comprising
Image processing arrangement is determined for obtaining the image information of the first customer and the second customer, and according to the image information
First customer is shopping user, and second customer is colleague user;It is also used to according to image information determination
The the first attribute portrait and mood portrait of first customer and the second attribute portrait of second customer;It is also used to according to institute
The acquisition of the first attribute portrait and the highest end article of the first customer match degree are stated, according to first attribute portrait and institute
The purchasing power scoring that the second attribute portrait obtains first customer is stated, is drawn a portrait according to second attribute portrait and the mood
Obtain the probability that first customer buys default commodity;It is also used to score the end article, the purchasing power and described
The probability for buying the default commodity imports shopping guide's Policy model of pre-training, obtains shopping guide's strategy;It is also used to export described lead
Purchase strategy arrives shopping guide's equipment;
Shopping guide's equipment, for receiving shopping guide's strategy.
9. system according to claim 8, which is characterized in that further include:
The image processing arrangement is also used to obtain push content according to the end article, sends the push content;
Detection device, for detecting the electronic equipment of first customer;
Intelligent terminal, the electronic equipment of advertisement screen and first customer including shopping place push away described in push for receiving
Send content.
10. a kind of strategy driving means, which is characterized in that be applied to tactful supplying system, the strategy driving means includes place
Manage unit and communication unit, wherein
The processing unit, for obtaining the image information of the first customer and the second customer by the communication unit, according to institute
It states image information and determines first customer as shopping user, second customer is colleague user;And according to the image
Information determines that the first attribute portrait of first customer and mood are drawn a portrait and the second attribute of second customer is drawn a portrait;
And according to the acquisition of first attribute portrait and the highest end article of the first customer match degree, belong to according to described first
Property portrait and second attribute portrait obtain the purchasing power scoring of first customer, according to second attribute portrait and institute
It states mood portrait and obtains the probability that first customer buys default commodity;And the end article, the purchasing power are commented
Divide and shopping guide's Policy model of the probability importing pre-training of the purchase default commodity, acquisition shopping guide are tactful;And pass through
The communication unit exports shopping guide's strategy.
11. a kind of computer readable storage medium, which is characterized in that storage is used for the computer program of electronic data interchange,
In, the computer program makes computer execute the method according to claim 1 to 7.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811640296 | 2018-12-29 | ||
CN2018116402968 | 2018-12-29 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109816441A true CN109816441A (en) | 2019-05-28 |
CN109816441B CN109816441B (en) | 2021-05-11 |
Family
ID=66604277
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910035727.6A Active CN109816441B (en) | 2018-12-29 | 2019-01-15 | Policy pushing method, system and related device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109816441B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110223114A (en) * | 2019-05-29 | 2019-09-10 | 恩亿科(北京)数据科技有限公司 | The method and apparatus for managing the characteristic information of user |
CN110751492A (en) * | 2019-10-10 | 2020-02-04 | 深圳市云积分科技有限公司 | High-value crowd identification method and device |
CN110969512A (en) * | 2019-12-02 | 2020-04-07 | 深圳市云积分科技有限公司 | Commodity recommendation method and device based on user purchasing behavior |
CN110992095A (en) * | 2019-12-03 | 2020-04-10 | 深圳市云积分科技有限公司 | Consumer portrait generation method and device |
CN110990446A (en) * | 2019-12-19 | 2020-04-10 | 国网区块链科技(北京)有限公司 | Intelligent investment and customer retrieval method and device based on investor portrait |
CN111080376A (en) * | 2019-12-30 | 2020-04-28 | 深圳市云积分科技有限公司 | Method and device for improving sociability of user based on information sharing |
CN111144996A (en) * | 2019-12-30 | 2020-05-12 | 深圳市云积分科技有限公司 | Shopping social method and device |
CN111813986A (en) * | 2020-07-10 | 2020-10-23 | 重庆中科云从科技有限公司 | Intelligent advertisement pushing method, device, system, medium and electronic terminal |
CN112084862A (en) * | 2020-08-06 | 2020-12-15 | 珠海格力电器股份有限公司 | Gait analysis method and device, storage medium and electronic equipment |
CN112418994A (en) * | 2020-11-26 | 2021-02-26 | 珠海格力电器股份有限公司 | Commodity shopping guide method and device, electronic equipment and storage medium |
CN113055423A (en) * | 2019-12-27 | 2021-06-29 | Oppo广东移动通信有限公司 | Policy pushing method, policy execution method, device, equipment and medium |
CN113643047A (en) * | 2021-08-17 | 2021-11-12 | 中国平安人寿保险股份有限公司 | Recommendation method, device and equipment for virtual reality control strategy and storage medium |
CN113643068A (en) * | 2021-08-18 | 2021-11-12 | 北京小米移动软件有限公司 | Commodity purchase intention determining method and device, storage medium and electronic equipment |
WO2021237414A1 (en) * | 2020-05-25 | 2021-12-02 | 鸿富锦精密工业(武汉)有限公司 | Information pushing method and apparatus, electronic device, and storage medium |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
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 |
CN107424012A (en) * | 2017-07-31 | 2017-12-01 | 京东方科技集团股份有限公司 | A kind of intelligent shopping guide method, intelligent shopping guide equipment |
US20180060907A1 (en) * | 2015-03-20 | 2018-03-01 | Nec Corporation | Sales promotion apparatus, sales promotion system, store system, sales promotion method, and program |
CN108021929A (en) * | 2017-11-16 | 2018-05-11 | 华南理工大学 | Mobile terminal electric business user based on big data, which draws a portrait, to establish and analysis method and system |
CN108022152A (en) * | 2017-11-30 | 2018-05-11 | 北京长城华冠汽车技术开发有限公司 | The automatic commending system of user's commodity and recommendation method based on image recognition |
CN108230086A (en) * | 2017-11-30 | 2018-06-29 | 广东数相智能科技有限公司 | A kind of system, method and the storage medium of commercial articles vending adjustment |
CN108550059A (en) * | 2018-04-28 | 2018-09-18 | 东莞市华睿电子科技有限公司 | A kind of Products Show method based on Identification of Images |
CN108564414A (en) * | 2018-04-23 | 2018-09-21 | 帷幄匠心科技(杭州)有限公司 | Method of Commodity Recommendation based on behavior under line and system |
CN108647811A (en) * | 2018-04-26 | 2018-10-12 | 中国联合网络通信集团有限公司 | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity |
CN108846724A (en) * | 2018-06-06 | 2018-11-20 | 北京京东尚科信息技术有限公司 | Data analysing method and system |
CN108876526A (en) * | 2018-06-06 | 2018-11-23 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device and computer readable storage medium |
CN108961005A (en) * | 2018-07-06 | 2018-12-07 | 北京旷视科技有限公司 | Information-pushing method, device, electronic equipment and medium |
CN108985839A (en) * | 2018-07-10 | 2018-12-11 | 深圳市科脉技术股份有限公司 | Shopping guide method and device in unmanned supermarket based on recognition of face |
CN109034973A (en) * | 2018-07-25 | 2018-12-18 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, system and computer readable storage medium |
-
2019
- 2019-01-15 CN CN201910035727.6A patent/CN109816441B/en active Active
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180060907A1 (en) * | 2015-03-20 | 2018-03-01 | Nec Corporation | Sales promotion apparatus, sales promotion system, store system, sales promotion method, and program |
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 |
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 |
CN107424012A (en) * | 2017-07-31 | 2017-12-01 | 京东方科技集团股份有限公司 | A kind of intelligent shopping guide method, intelligent shopping guide equipment |
CN108021929A (en) * | 2017-11-16 | 2018-05-11 | 华南理工大学 | Mobile terminal electric business user based on big data, which draws a portrait, to establish and analysis method and system |
CN108230086A (en) * | 2017-11-30 | 2018-06-29 | 广东数相智能科技有限公司 | A kind of system, method and the storage medium of commercial articles vending adjustment |
CN108022152A (en) * | 2017-11-30 | 2018-05-11 | 北京长城华冠汽车技术开发有限公司 | The automatic commending system of user's commodity and recommendation method based on image recognition |
CN108564414A (en) * | 2018-04-23 | 2018-09-21 | 帷幄匠心科技(杭州)有限公司 | Method of Commodity Recommendation based on behavior under line and system |
CN108647811A (en) * | 2018-04-26 | 2018-10-12 | 中国联合网络通信集团有限公司 | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity |
CN108550059A (en) * | 2018-04-28 | 2018-09-18 | 东莞市华睿电子科技有限公司 | A kind of Products Show method based on Identification of Images |
CN108846724A (en) * | 2018-06-06 | 2018-11-20 | 北京京东尚科信息技术有限公司 | Data analysing method and system |
CN108876526A (en) * | 2018-06-06 | 2018-11-23 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device and computer readable storage medium |
CN108961005A (en) * | 2018-07-06 | 2018-12-07 | 北京旷视科技有限公司 | Information-pushing method, device, electronic equipment and medium |
CN108985839A (en) * | 2018-07-10 | 2018-12-11 | 深圳市科脉技术股份有限公司 | Shopping guide method and device in unmanned supermarket based on recognition of face |
CN109034973A (en) * | 2018-07-25 | 2018-12-18 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, system and computer readable storage medium |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110223114A (en) * | 2019-05-29 | 2019-09-10 | 恩亿科(北京)数据科技有限公司 | The method and apparatus for managing the characteristic information of user |
CN110751492A (en) * | 2019-10-10 | 2020-02-04 | 深圳市云积分科技有限公司 | High-value crowd identification method and device |
CN110969512A (en) * | 2019-12-02 | 2020-04-07 | 深圳市云积分科技有限公司 | Commodity recommendation method and device based on user purchasing behavior |
CN110969512B (en) * | 2019-12-02 | 2022-11-15 | 深圳市云积分科技有限公司 | Commodity recommendation method and device based on user purchasing behavior |
CN110992095A (en) * | 2019-12-03 | 2020-04-10 | 深圳市云积分科技有限公司 | Consumer portrait generation method and device |
CN110992095B (en) * | 2019-12-03 | 2022-11-11 | 深圳市云积分科技有限公司 | Consumer portrait generation method and device |
CN110990446A (en) * | 2019-12-19 | 2020-04-10 | 国网区块链科技(北京)有限公司 | Intelligent investment and customer retrieval method and device based on investor portrait |
CN113055423A (en) * | 2019-12-27 | 2021-06-29 | Oppo广东移动通信有限公司 | Policy pushing method, policy execution method, device, equipment and medium |
CN111144996A (en) * | 2019-12-30 | 2020-05-12 | 深圳市云积分科技有限公司 | Shopping social method and device |
CN111080376A (en) * | 2019-12-30 | 2020-04-28 | 深圳市云积分科技有限公司 | Method and device for improving sociability of user based on information sharing |
CN111144996B (en) * | 2019-12-30 | 2022-12-23 | 深圳市云积分科技有限公司 | Method and device for social shopping |
WO2021237414A1 (en) * | 2020-05-25 | 2021-12-02 | 鸿富锦精密工业(武汉)有限公司 | Information pushing method and apparatus, electronic device, and storage medium |
CN111813986A (en) * | 2020-07-10 | 2020-10-23 | 重庆中科云从科技有限公司 | Intelligent advertisement pushing method, device, system, medium and electronic terminal |
CN111813986B (en) * | 2020-07-10 | 2023-12-22 | 重庆中科云从科技有限公司 | Intelligent advertisement pushing method, device, system, medium and electronic terminal |
CN112084862A (en) * | 2020-08-06 | 2020-12-15 | 珠海格力电器股份有限公司 | Gait analysis method and device, storage medium and electronic equipment |
CN112418994A (en) * | 2020-11-26 | 2021-02-26 | 珠海格力电器股份有限公司 | Commodity shopping guide method and device, electronic equipment and storage medium |
CN112418994B (en) * | 2020-11-26 | 2024-06-04 | 珠海格力电器股份有限公司 | Commodity shopping guide method and device, electronic equipment and storage medium |
CN113643047A (en) * | 2021-08-17 | 2021-11-12 | 中国平安人寿保险股份有限公司 | Recommendation method, device and equipment for virtual reality control strategy and storage medium |
CN113643047B (en) * | 2021-08-17 | 2024-05-10 | 中国平安人寿保险股份有限公司 | Recommendation method, device, equipment and storage medium of virtual reality control strategy |
CN113643068A (en) * | 2021-08-18 | 2021-11-12 | 北京小米移动软件有限公司 | Commodity purchase intention determining method and device, storage medium and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN109816441B (en) | 2021-05-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109816441A (en) | Tactful method for pushing, system and relevant apparatus | |
CN105224075B (en) | Sensor-based mobile search, correlation technique and system | |
US20180054564A1 (en) | Apparatus and method for providing user's emotional information in electronic device | |
CN105117463B (en) | Information processing method and information processing unit | |
CN106055710A (en) | Video-based commodity recommendation method and device | |
CN111506758B (en) | Method, device, computer equipment and storage medium for determining article name | |
CN107992478A (en) | The method and apparatus for determining focus incident | |
WO2011097517A2 (en) | Image tagging based upon cross domain context | |
CN107609056A (en) | A kind of question and answer processing method and equipment based on picture recognition | |
CN103136321A (en) | Method and device of multimedia information processing and mobile terminal | |
CN109309878A (en) | The generation method and device of barrage | |
CN109086742A (en) | scene recognition method, scene recognition device and mobile terminal | |
CN111026967B (en) | Method, device, equipment and medium for obtaining user interest labels | |
CN109918513A (en) | Image processing method, device, server and storage medium | |
CN108429816A (en) | Method and apparatus for generating information | |
CN109902644A (en) | Face identification method, device, equipment and computer-readable medium | |
CN109215037A (en) | Destination image partition method, device and terminal device | |
CN110209810A (en) | Similar Text recognition methods and device | |
CN110322305A (en) | Data object information providing method, device and electronic equipment | |
CN108898649A (en) | Image processing method and device | |
CN112766406A (en) | Article image processing method and device, computer equipment and storage medium | |
CN110246280B (en) | Human-cargo binding method and device, computer equipment and readable medium | |
CN107423441A (en) | A kind of picture correlating method and its device, electronic equipment | |
CN108932704A (en) | Image processing method, picture processing unit and terminal device | |
CN108898169A (en) | Image processing method, picture processing unit and terminal device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |