CN109583970A - Advertisement placement method, device, computer equipment and storage medium - Google Patents
Advertisement placement method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109583970A CN109583970A CN201811536054.4A CN201811536054A CN109583970A CN 109583970 A CN109583970 A CN 109583970A CN 201811536054 A CN201811536054 A CN 201811536054A CN 109583970 A CN109583970 A CN 109583970A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- user
- micro
- preset
- webpage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0263—Targeted advertisements based upon Internet or website rating
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a kind of advertisement placement method, device, computer equipment and storage medium, include the following steps: micro- facial expression image when obtaining user's browse network page；Micro- facial expression image is input in preset Expression Recognition model, interest index of the user to the commodity shown in the Webpage is obtained；Advertisement to be put is determined according to the interest index, and the advertisement is launched in the Webpage browsed to the user.Micro- expression of the user in the browse network page is identified by Expression Recognition model, obtains user to the interest index of the commodity shown in Webpage, and determine advertisement to be put by interest index, and then precisely launched.Since micro- expression can really react the potential psychology of user, obtained interest index is true, accurate, so not only can be improved advertisement dispensing into accuracy, interested commodity can also be provided for user, provided convenience for user.
Description
Technical field
The present embodiments relate to financial field, especially a kind of advertisement placement method, device, computer equipment and storage
Medium.
Background technique
With the development of internet technology, computer becomes people's work, life, learns indispensable tool.Many enterprises
In order to promote the sale of products, the advertisement about product is usually issued in a network so that people buy.
But since the hobby of the network user, age level are inferior multifarious, the demand to commodity is not also identical.
Since enterprise is identical in the advertisement launched on webpage, not only result in that advertisement is many and diverse, and target group are indefinite to cause in this way
Launch not accurate problem, when uninterested advertisement is shown on webpage, can interfere user clear for the network user
Look at webpage information.
Summary of the invention
The embodiment of the present invention provide it is a kind of according to user or sell people ease of Use can insure to client push
Product simultaneously carries out highlighted method to the main points in insurance products.
In order to solve the above technical problems, the technical solution that the embodiment of the invention uses is: providing a kind of wide
Put-on method is accused, is included the following steps:
Obtain micro- facial expression image when user's browse network page；
Micro- facial expression image is input in preset Expression Recognition model, obtains the user to the Webpage
The interest index of the commodity of middle display；
Advertisement to be put is determined according to the interest index, and the advertisement is launched to the network browsed to the user
In the page.
Optionally, micro- facial expression image when acquisition user's browse network page, comprising:
Obtain the instruction that the user enters Webpage；
The facial expression image of the user is shot according to described instruction calling built-in camera；
Normalization is carried out to the facial expression image according to preset processing method, obtains micro- facial expression image.
It is optionally, described that advertisement to be put is determined according to the interest index, comprising:
Judge whether the interest index is greater than preset value；
When the interest index is greater than the preset value, the merchandise news shown in the current network page is obtained；
The advertisement to be put is chosen according to the merchandise news.
It is optionally, described to obtain the merchandise news shown in the current network page, comprising:
Extract the uniform resource locator of the Webpage；
According to the determining Commercial goods labels with the uniform resource locator with mapping relations of preset mapping relations list.
It is optionally, described that the advertisement to be put is chosen according to the merchandise news, comprising:
Determine the type for the commodity that the merchandise news is characterized；
Chosen in advertising resource database according to the type with the advertising resource of the type matching, and will be described
The advertising resource matched is as the advertisement to be put.
Optionally, described that micro- facial expression image is input in preset Expression Recognition model, obtain the user couple
Before the interest index of the commodity shown in the Webpage, further includes:
Obtain the training sample image set of micro- expression；
Preset convolutional neural networks model is trained by the training sample image set, obtains micro- table
Feelings identification model.
It is optionally, described that preset convolutional neural networks model is trained by the training sample image, comprising:
The desired value of the training sample image is obtained by the convolutional neural networks model；
The training sample image is input in the convolutional neural networks model, excitation value is obtained；
Compare whether the distance between the desired value and the excitation value are less than or equal to preset threshold value, and when described
When the distance between desired value and the excitation value are greater than threshold value, iterative cycles iteration updates the convolution by inverse algorithms
Weight in neural network model, until the distance between the desired value and the excitation value are less than or equal to preset first threshold
Value.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of advertisement delivery device, comprising:
Module is obtained, for obtaining micro- facial expression image when user's browse network page；
Processing module obtains the user for micro- facial expression image to be input in preset Expression Recognition model
Interest index to the commodity shown in the Webpage；
Execution module for determining advertisement to be put according to the interest index, and the advertisement is launched to described
In the Webpage of user's browsing.
Optionally, the acquisition module includes:
First acquisition submodule enters the instruction of Webpage for obtaining the user；
First processing submodule, for shooting the facial expression image of the user according to described instruction calling built-in camera；
First implementation sub-module is obtained for carrying out normalization to the facial expression image according to preset processing method
Micro- facial expression image.
Optionally, the processing module includes:
Second processing submodule, for judging whether the interest index is greater than preset value；
Third handles submodule, for obtaining in the current network page when the interest index is greater than the preset value
The merchandise news of display；
Second implementation sub-module, for choosing the advertisement to be put according to the merchandise news.
Optionally, first acquisition submodule includes:
Second acquisition submodule, for extracting the uniform resource locator of the Webpage；
Third implementation sub-module, for determining have with the uniform resource locator according to preset mapping relations list
The Commercial goods labels of mapping relations.
Optionally, the third implementation sub-module includes:
Third acquisition submodule, for determining the type of commodity that the merchandise news is characterized；
The module of 4th execution, for being chosen in advertising resource database according to the type and the type matching
Advertising resource, and using the matched advertising resource as the advertisement to be put.
Optionally, further includes:
4th acquisition submodule, for obtaining the training sample image set of micro- expression；
5th implementation sub-module, for by the training sample image set to preset convolutional neural networks model into
Row training, obtains micro- Expression Recognition model.
Optionally, the 5th implementation sub-module includes:
5th acquisition submodule, for obtaining the expectation of the training sample image by the convolutional neural networks model
Value；
6th implementation sub-module is obtained for the training sample image to be input in the convolutional neural networks model
To excitation value；
7th implementation sub-module, for comparing whether the distance between the desired value and the excitation value are less than or equal to
Preset threshold value, and when the distance between the desired value and the excitation value are greater than threshold value, iterative cycles iteration passes through
Inverse algorithms update the weight in the convolutional neural networks model, until the distance between the desired value and the excitation value are small
In or equal to preset first threshold.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of computer equipment, including memory and processing
Device is stored with computer-readable instruction in the memory, when the computer-readable instruction is executed by the processor, so that
The processor executes the step of advertisement placement method described above.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of storage Jie for being stored with computer-readable instruction
Matter, when the computer-readable instruction is executed by one or more processors, so that one or more processors execute above-mentioned institute
The step of stating advertisement placement method.
The beneficial effect of the embodiment of the present invention is: micro- table by Expression Recognition model to user in the browse network page
Feelings are identified, are obtained user and are determined to the interest index of the commodity shown in Webpage, and by interest index wait throw
The advertisement put, and then precisely launched.Since micro- expression can really react the potential psychology of user, obtained interest index
Really, accurately, so not only can be improved advertisement dispensing into accuracy, interested commodity can also be provided for user, for
It provides convenience at family.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the basic procedure schematic diagram of advertisement placement method of the embodiment of the present invention；
The method of micro- facial expression image when Fig. 2 is a kind of acquisition user's browse network page provided in an embodiment of the present invention
Basic procedure schematic diagram；
Fig. 3 provides a kind of basic procedure of method that advertisement to be put is determined according to interest index for the embodiment of the present invention
Schematic diagram；
Fig. 4 is a kind of basic flow for the method for obtaining the merchandise news shown in the current network page of work of the embodiment of the present invention
Journey schematic diagram；
Fig. 5 is that the embodiment of the present invention also provides a kind of basic procedure of method that advertisement to be put is chosen according to merchandise news
Schematic diagram；
Fig. 6 is a kind of basic procedure schematic diagram of the generation method of Expression Recognition model provided in an embodiment of the present invention；
Fig. 7 be it is provided in an embodiment of the present invention by training sample image set to preset convolutional neural networks model into
The basic procedure schematic diagram of the method for row training；
Fig. 8 is advertisement delivery device of embodiment of the present invention basic structure block diagram；
Fig. 9 is computer equipment of embodiment of the present invention basic structure block diagram.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.
In some processes of the description in description and claims of this specification and above-mentioned attached drawing, contain according to
Multiple operations that particular order occurs, but it should be clearly understood that these operations can not be what appears in this article suitable according to its
Sequence is executed or is executed parallel, and serial number of operation such as 101,102 etc. is only used for distinguishing each different operation, serial number
It itself does not represent and any executes sequence.In addition, these processes may include more or fewer operations, and these operations can
To execute or execute parallel in order.It should be noted that the description such as " first " herein, " second ", is for distinguishing not
Same message, equipment, module etc., does not represent sequencing, does not also limit " first " and " second " and be different type.
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those skilled in the art's every other implementation obtained without creative efforts
Example, shall fall within the protection scope of the present invention.
Embodiment
Those skilled in the art of the present technique are appreciated that " terminal " used herein above, " terminal device " both include wireless communication
The equipment of number receiver, only has the equipment of the wireless signal receiver of non-emissive ability, and including receiving and emitting hardware
Equipment, have on bidirectional communication link, can execute two-way communication reception and emit hardware equipment.This equipment
It may include: honeycomb or other communication equipments, shown with single line display or multi-line display or without multi-line
The honeycomb of device or other communication equipments；PCS (Personal Communications Service, PCS Personal Communications System), can
With combine voice, data processing, fax and/or communication ability；PDA (Personal Digital Assistant, it is personal
Digital assistants), it may include radio frequency receiver, pager, the Internet/intranet access, web browser, notepad, day
It goes through and/or GPS (Global Positioning System, global positioning system) receiver；Conventional laptop and/or palm
Type computer or other equipment, have and/or the conventional laptop including radio frequency receiver and/or palmtop computer or its
His equipment." terminal " used herein above, " terminal device " can be it is portable, can transport, be mounted on the vehicles (aviation,
Sea-freight and/or land) in, or be suitable for and/or be configured in local runtime, and/or with distribution form, operate in the earth
And/or any other position operation in space." terminal " used herein above, " terminal device " can also be communication terminal, on
Network termination, music/video playback terminal, such as can be PDA, MID (Mobile Internet Device, mobile Internet
Equipment) and/or mobile phone with music/video playing function, it is also possible to the equipment such as smart television, set-top box.
Client terminal in present embodiment is above-mentioned terminal.
Specifically, referring to Fig. 1, Fig. 1 is the basic procedure schematic diagram of the present embodiment advertisement placement method.
As shown in Figure 1, advertisement placement method includes the following steps:
Micro- facial expression image when S1100, acquisition user's browse network page；
Micro- expression is psychology noun, the expression usually to flash across, for example, frown, the corners of the mouth raises up, eyeball turns over
Deng.Under normal circumstances, micro- expression duration is extremely short, can accurately reflect the emotional state of user, for example, be sick of, it is curious, shy
Happiness, it is happy etc..
In the embodiment of the present invention, when user opens Webpage, the finger that the front camera of controlling terminal is opened is triggered
It enables, and records the expression video of user's browsing pages by front camera, and extract micro- facial expression image from expression video.
In practical applications, when closing or switching the Webpage currently shown, control front camera is closed, the table so obtained
Feelings video is the expression video that user browses the current network page.
It should be noted that when obtaining micro- facial expression image, by intercepted from expression video include micro- expression image
Normalization is carried out, makes micro- facial expression image that there is same size, contrast, pixel value.
S1200, micro- facial expression image is input in preset Expression Recognition model, obtains user to showing in Webpage
Commodity interest index；
Expression Recognition model is used to determine whether user is interested by identifying micro- expression, for example, micro- expression is mouth
Angle, which raises up, can indicate that user is happy, interested in the content of display, and micro- expression is to curl one's lip to indicate user's agitation, to display
Content lose interest in.Wherein, Expression Recognition model is to be instructed using micro- expression training set to convolutional neural networks model
Model after white silk.
It should be noted that interest index is for indicating user to the commodity interest level shown in Webpage.
S1300, advertisement to be put is determined according to interest index, and advertisement is launched to the Webpage browsed to user
In.
In the embodiment of the present invention, when terminal judges that user refers to the interest of the commodity shown in Webpage by micro- expression
When number is higher, illustrate that user is interested in the commodity in Webpage, the determining advertisement with the goods matching of terminal is used as wait throw
The advertisement put.
In practical applications, advertisement to be put can be the advertisement with the commodity with type, for example, user is in network
Mobile phone is browsed in the page, advertisement to be put can be the mobile phone of other brands；Advertisement to be put is also possible to and the commodity
The advertisement of other commodity with same brand, for example, user browses mobile phone in Webpage, the brand of the mobile phone is XXX,
Then advertisement to be put can be the tablet computer of XXX brand.
In some embodiments, when terminal launches advertisement, terminal obtain user website registration information, when
When logging in the website, advertisement is shown user by terminal in the page of the website.
Above-mentioned advertisement placement method knows micro- expression of the user in the browse network page by Expression Recognition model
Not, user is obtained to the interest index of the commodity shown in Webpage, and advertisement to be put is determined by interest index,
And then it is precisely launched.Since micro- expression can really react the potential psychology of user, obtained interest index is true, quasi-
Really, so not only can be improved advertisement dispensing into accuracy, interested commodity can also be provided for user, provided for user
It is convenient.
In practical applications, the angle as where built-in camera when recording the expression video of user is different, obtains
Expression picture size it is different, therefore, in order to improve the accuracy rate of identification, the embodiment of the present invention provides a kind of acquisition user browsing
The method of micro- facial expression image when Webpage, as shown in Fig. 2, Fig. 2 is that a kind of acquisition user provided in an embodiment of the present invention is clear
Look at Webpage when micro- facial expression image method basic procedure schematic diagram.
As shown in Fig. 2, step S1100 includes:
S1110, the instruction that user enters Webpage is obtained；
The embodiment of the present invention triggers the instruction in the link of user click Webpage, and enters in Webpage.
Wherein, which opens for the camera built in controlling terminal, and grabs the expression of user's browse network page.
S1120, the facial expression image that built-in camera shooting user is called according to instruction；
In practical applications, built-in camera can shoot with user the user out of period that browse to closing and browse net
The expression video of the network page, and according to the facial expression image of each frame in preset timing node interception expression video as user's
Micro- facial expression image.Wherein, in order to ensure that can obtain more accurately information, when preset timing node can be set shorter
Between, such as 0.2s, 0.3s etc..The facial expression image of interception can also further be screened, can't see face for example, deleting
Image.
S1130, normalization is carried out to facial expression image according to preset processing method, obtains micro- facial expression image.
In the embodiment of the present invention, normalization can be carried out to facial expression image by preset image processing software, wherein
Normalization refer to multiple facial expression images are cut, the processing such as pixel equilibrium make ratio shared by facial expression in facial expression image
The identical or contrast of example, gray level are identical.So, it can be ensured that the interest index of Expression Recognition model identification is accurate.
Under normal conditions, interest exponential representation user is to the interested degree of commodity, and interest index is higher, and user is to commodity
Interested degree is bigger, for above-mentioned interest index the embodiment of the invention provides a kind of according to interest index determine it is to be put
Advertisement method, as shown in figure 3, the embodiment of the present invention provides a kind of method for determining advertisement to be put according to interest index
Basic procedure schematic diagram.
As shown in figure 3, step S1200 the following steps are included:
S1210, judge whether interest index is greater than preset value；
S1220, when interest index is greater than preset value, obtain the merchandise news that shows in the current network page；
In the embodiment of the present invention, interested degree can be configured, for example, interested, indifferent to,
It is sick of three kinds, numerical value can also be set to every kind of level of interest including very interested and two kinds indifferent to, specifically,
For example, very interested is 10, interested is 5, and indifferent to is 0, and being sick of is -5.Wherein, the preset value in the embodiment of the present invention
The above level of interest is referred to be configured, for example, in order to precisely launch advertisement, just it is launched when interest index is 10 wide
It accuses, at this point it is possible to which it is 9 or 9.9 that preset value, which is arranged,.It should be noted that above method is merely illustrative, it in practical applications, can
With according to purpose to be achieved is thought referring to the above method, details are not described herein.
S1230, advertisement to be put is chosen according to merchandise news.
Merchandise news is the information for the commodity that user indicates in Webpage, for example, the appearance picture of commodity, the class of commodity
Type, marque etc..In the embodiment of the present invention, when interest index is greater than preset value, that is, determine that user is emerging to the commodity sense
When interesting, terminal chooses relevant to commodity advertisement as advertisement to be put, for example, advertisement relevant to commodity is and commodity
Belong to the advertisement of other commodity of same type, or belong to the advertisement of other commodity with brand with commodity, for example, commodity are
The mobile phone of XX brand, then advertisement to be put can be the mobile phone of YY brand or the computer of XX brand.
The embodiment of the present invention also provides a kind of method of merchandise news for obtaining and showing in the current network page, such as Fig. 4 institute
Show, Fig. 4 is that a kind of basic procedure for the method for obtaining the merchandise news shown in the current network page of work of the embodiment of the present invention shows
It is intended to.
As shown in figure 4, step S1220 the following steps are included:
S1221, the uniform resource locator for extracting Webpage；
S1222, the commodity class according to preset mapping relations list determination with uniform resource locator with mapping relations
Type.
Uniform resource locator is the uniform resource locator of electric business website under normal conditions, and electric business website includes comprehensive
Electric business and lateral electric business, wherein comprehensive electric business is to sell the electric business of all kinds of commodity, and lateral electric business is to sell certain seed type
Commodity electric business, for example, deal exclusively in insurance class product, financing class product, 3C Product class electric business.The embodiment of the present invention
In, the preset mapping relations list of terminal includes the mapping relations of uniform resource locator and Commercial goods labels, passes through mapping relations
List can determine Commercial goods labels.
Commercial goods labels describe the relevant informations such as type, the brand of commodity for indicating merchandise news.
The embodiment of the present invention also provides a kind of method for choosing advertisement to be put according to merchandise news, as shown in figure 5, Fig. 5
A kind of basic procedure schematic diagram of method for choosing advertisement to be put according to merchandise news is also provided for the embodiment of the present invention.
As shown in figure 5, step S1230 includes the following steps:
S1231, the type for determining the commodity that merchandise news is characterized；
Merchandise news includes the type of commodity, brand, extracts the type of commodity in the embodiment of the present invention from merchandise news.
S1232, chosen in advertising resource database according to type with the advertising resource of type matching, and will it is matched extensively
Resource is accused as advertisement to be put.
In the embodiment of the present invention, terminal summarizes selection in advertising resource database according to the type of the commodity got
The advertising resource matched.In practical applications, the type of the commodity publicized in advertising resource database according to advertisement is to each wide
Setting label is accused, will be compared with the label of advertisement with the type of commodity during matched, when the alignment is identical, is determined
The type matching for the commodity that advertising resource and user browse in Webpage.
The embodiment of the present invention provides a kind of generation method of Expression Recognition model, as shown in fig. 6, Fig. 6 is that the present invention is implemented
A kind of basic procedure schematic diagram of the generation method for Expression Recognition model that example provides.
As shown in fig. 6, further including following step before step S1200:
S1201, the training sample image set for obtaining micro- expression；
The training sample image collection of micro- expression is combined into the image collection including a variety of micro- expressions, which is divided into multiple groups, often
One group includes the multiple micro- facial expression images for being marked with same interest index.Assuming that there is two groups, one group is interested micro- expression, example
Such as, the image that multiple corners of the mouths raise up, this kind of micro- expression indicate interested in the content of display, and interest index is set as 10, another
Group is uninterested micro- facial expression image, for example, the movement curled one's lip, expression loses interest in the content of display, and interest index is set
It is set to 0.
It should be noted that preset convolutional neural networks model is CNN convolutional neural networks model or VGG convolutional Neural
Network model.
S1202, preset convolutional neural networks model is trained by training sample image set, obtains micro- expression
Identification model.
The embodiment of the present invention provides a kind of side that training sample image is trained preset convolutional neural networks model
Method, as shown in fig. 7, Fig. 7 be it is provided in an embodiment of the present invention by training sample image set to preset convolutional neural networks
The basic procedure schematic diagram for the method that model is trained.
S12021, the desired value that training sample image is obtained by convolutional neural networks model；
Every group of micro- facial expression image is input in convolutional neural networks model, the output valve of each micro- facial expression image is obtained,
And be ranked up output valve, take median as the desired value of every group of micro- facial expression image.
S12022, training sample image is input in convolutional neural networks model, obtains excitation value；
China of the embodiment of the present invention, every group of micro- expression training sample image is sequentially inputted in neural network model, mind
Feature extraction and classification are carried out to facial image through network model.
Excitation value is the excited data that convolutional neural networks model is exported according to micro- facial expression image of input, in nerve net
Network model is not trained to before convergence, and excitation value is the biggish numerical value of discreteness, when neural network model is trained to convergence
Later, excitation value is metastable data.
S12023, compare whether the distance between desired value and excitation value are less than or equal to preset threshold value, and when expectation
When the distance between value and excitation value are greater than threshold value, iterative cycles iteration updates the convolutional neural networks by inverse algorithms
Weight in model, until the distance between desired value and excitation value are less than or equal to preset first threshold.
By loss function judge neural network model full articulamentum output excitation value and setting desired value whether one
It causes, when result is inconsistent, needs to be adjusted the weight in first passage by back-propagation algorithm.
In some embodiments, loss function by calculate excitation classification value and setting expectation classification value between away from
From (Euclidean distance or space length), whether the expectation classification value to determine excitation classification value and setting is consistent, setting first
Threshold value, when the distance between excitation value and the expectation classification value of setting are less than or equal to first threshold, it is determined that excitation classification
Value is consistent with the desired value of setting, and otherwise, then excitation value and the desired value of setting are inconsistent.
When the desired value of the excitation value of neural network model and setting is inconsistent, need using stochastic gradient descent algorithm
Weight in neural network model is corrected, so that the output result of convolutional neural networks model and classification judge information
Expected result is identical.By several training sample sets (by the photograph in all training sample sets when in some embodiments, training
Piece, which is upset, to be trained, with increase model by interference performance, enhance the stability of output.By training and correction repeatedly,
When the classification of neural network model output category data and each training sample reaches and (is not limited to) 99.5% referring to information comparison,
Training terminates.
The embodiment of the present invention also provides a kind of advertisement delivery device to solve above-mentioned technical problem.Referring specifically to Fig. 8, figure
8 be the present embodiment advertisement delivery device basic structure block diagram.
As shown in figure 8, a kind of advertisement delivery device, comprising: obtain module 2100, processing module 2200 and execution module
2300.Wherein, module 2100 is obtained, for obtaining micro- facial expression image when user's browse network page；Processing module 2200 is used
It is input in preset Expression Recognition model in by micro- facial expression image, obtains the user to showing in the Webpage
Commodity interest index；Execution module 2300, for determining advertisement to be put according to the interest index, and will be described wide
It accuses in the Webpage launched and browsed to the user.
Above-mentioned advertisement delivery device knows micro- expression of the user in the browse network page by Expression Recognition model
Not, user is obtained to the interest index of the commodity shown in Webpage, and advertisement to be put is determined by interest index,
And then it is precisely launched.Since micro- expression can really react the potential psychology of user, obtained interest index is true, quasi-
Really, so not only can be improved advertisement dispensing into accuracy, interested commodity can also be provided for user, provided for user
It is convenient.
In some embodiments, the acquisition module includes: the first acquisition submodule, is entered for obtaining the user
The instruction of Webpage；First processing submodule, for shooting the table of the user according to described instruction calling built-in camera
Feelings image；First implementation sub-module obtains institute for carrying out normalization to the facial expression image according to preset processing method
State micro- facial expression image.
In some embodiments, the processing module includes: second processing submodule, for judging the interest index
Whether preset value is greater than；Third handles submodule, for obtaining current network when the interest index is greater than the preset value
The merchandise news shown in the page；Second implementation sub-module, for choosing the advertisement to be put according to the merchandise news.
In some embodiments, first acquisition submodule includes: the second acquisition submodule, for extracting the net
The uniform resource locator of the network page；Third implementation sub-module, for according to preset mapping relations list determination and the system
One Resource Locator has the Commercial goods labels of mapping relations.
In some embodiments, the third implementation sub-module includes: third acquisition submodule, for determining the quotient
The type for the commodity that product information is characterized；The module of 4th execution, for being selected in advertising resource database according to the type
The advertising resource with the type matching is taken, and using the matched advertising resource as the advertisement to be put.
In some embodiments, advertisement delivery device further include: the 4th acquisition submodule, for obtaining the instruction of micro- expression
Practice sample image set；5th implementation sub-module is used for through the training sample image set to preset convolutional Neural net
Network model is trained, and obtains micro- Expression Recognition model.
In some embodiments, the 5th implementation sub-module includes: the 5th acquisition submodule, for by the convolution
Neural network model obtains the desired value of the training sample image；6th implementation sub-module is used for the training sample figure
As being input in the convolutional neural networks model, excitation value is obtained；7th implementation sub-module, for compare the desired value with
Whether the distance between described excitation value is less than or equal to preset threshold value, and between the desired value and the excitation value
When distance is greater than threshold value, iterative cycles iteration updates the weight in the convolutional neural networks model by inverse algorithms, until
The distance between the desired value and the excitation value are less than or equal to preset first threshold.
In order to solve the above technical problems, the embodiment of the present invention also provides computer equipment.It is this referring specifically to Fig. 9, Fig. 9
Embodiment computer equipment basic structure block diagram.
As shown in figure 9, the schematic diagram of internal structure of computer equipment.As shown in figure 9, the computer equipment includes passing through to be
Processor, non-volatile memory medium, memory and the network interface of bus of uniting connection.Wherein, the computer equipment is non-easy
The property lost storage medium is stored with operating system, database and computer-readable instruction, can be stored with control information sequence in database
Column, when which is executed by processor, may make processor to realize a kind of advertisement placement method.The computer is set
Standby processor supports the operation of entire computer equipment for providing calculating and control ability.The storage of the computer equipment
It can be stored with computer-readable instruction in device, when which is executed by processor, processor may make to execute one
Kind advertisement placement method.The network interface of the computer equipment is used for and terminal connection communication.Those skilled in the art can manage
It solves, structure shown in Fig. 9, only the block diagram of part-structure relevant to application scheme, is not constituted to the application side
The restriction for the computer equipment that case is applied thereon, specific computer equipment may include more more or less than as shown in the figure
Component, perhaps combine certain components or with different component layouts.
Processor obtains module 2100, processing module 2200 and execution module for executing in present embodiment in Fig. 8
2300 particular content, program code and Various types of data needed for memory is stored with the above-mentioned module of execution.Network interface is used for
To the data transmission between user terminal or server.Memory in present embodiment, which is stored in advertisement placement method, to be executed
Program code needed for all submodules and data, server is capable of the program code of invoking server and data execute all sons
The function of module.
Computer equipment identifies micro- expression of the user in the browse network page by Expression Recognition model, obtains
User determines advertisement to be put, Jin Erjin by interest index to the interest indexes of the commodity shown in Webpage
Row is precisely launched.Since micro- expression can really react the potential psychology of user, obtained interest index is true, accurate, so
Not only can be improved advertisement dispensing into accuracy, interested commodity can also be provided for user, provided convenience for user.
The present invention also provides a kind of storage mediums for being stored with computer-readable instruction, and the computer-readable instruction is by one
When a or multiple processors execute, so that one or more processors execute advertisement placement method described in any of the above-described embodiment
Step.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, which can be stored in a computer-readable storage and be situated between
In matter, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, storage medium above-mentioned can be
The non-volatile memory mediums such as magnetic disk, CD, read-only memory (Read-Only Memory, ROM) or random storage note
Recall body (Random Access Memory, RAM) etc..
It should be understood that although each step in the flow chart of attached drawing is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, can execute in the other order.Moreover, at least one in the flow chart of attached drawing
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, execution sequence, which is also not necessarily, successively to be carried out, but can be with other
At least part of the sub-step or stage of step or other steps executes in turn or alternately.
The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of advertisement placement method, which is characterized in that include the following steps:
Obtain micro- facial expression image when user's browse network page；
Micro- facial expression image is input in preset Expression Recognition model, the user is obtained and is shown in the Webpage
The interest index of the commodity shown；
Advertisement to be put is determined according to the interest index, and the advertisement is launched to the Webpage browsed to the user
In.
2. advertisement placement method according to claim 1, which is characterized in that when acquisition user's browse network page
Micro- facial expression image, comprising:
Obtain the instruction that the user enters Webpage；
The facial expression image of the user is shot according to described instruction calling built-in camera；
Normalization is carried out to the facial expression image according to preset processing method, obtains micro- facial expression image.
3. advertisement placement method according to claim 1, which is characterized in that described to be determined according to the interest index wait throw
The advertisement put, comprising:
Judge whether the interest index is greater than preset value；
When the interest index is greater than the preset value, the merchandise news shown in the current network page is obtained；
The advertisement to be put is chosen according to the merchandise news.
4. advertisement placement method according to claim 3, which is characterized in that shown in the acquisition current network page
Merchandise news, comprising:
Extract the uniform resource locator of the Webpage；
According to the determining Commercial goods labels with the uniform resource locator with mapping relations of preset mapping relations list.
5. advertisement placement method according to claim 3, which is characterized in that described according to merchandise news selection
Advertisement to be put, comprising:
Determine the type for the commodity that the merchandise news is characterized；
Chosen in advertising resource database according to the type with the advertising resource of the type matching, and will be described matched
Advertising resource is as the advertisement to be put.
6. according to claim 1 to advertisement placement method described in 5, which is characterized in that described to input micro- facial expression image
Into preset Expression Recognition model, before obtaining the user to the interest index of the commodity shown in the Webpage,
Further include:
Obtain the training sample image set of micro- expression；
Preset convolutional neural networks model is trained by the training sample image set, micro- expression is obtained and knows
Other model.
7. advertisement placement method according to claim 6, which is characterized in that it is described by the training sample image to pre-
If convolutional neural networks model be trained, comprising:
The desired value of the training sample image is obtained by the convolutional neural networks model；
The training sample image is input in the convolutional neural networks model, excitation value is obtained；
It compares whether the distance between the desired value and the excitation value are less than or equal to preset threshold value, and works as the expectation
When the distance between value and the excitation value are greater than threshold value, iterative cycles iteration updates the convolutional Neural by inverse algorithms
Weight in network model, until the distance between the desired value and the excitation value are less than or equal to preset first threshold.
8. a kind of advertisement delivery device characterized by comprising
Module is obtained, for obtaining micro- facial expression image when user's browse network page；
Processing module obtains the user to institute for micro- facial expression image to be input in preset Expression Recognition model
State the interest index of the commodity shown in Webpage；
Execution module for determining advertisement to be put according to the interest index, and the advertisement is launched to the user
In the Webpage of browsing.
9. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, it is described
When computer-readable instruction is executed by the processor, so that the processor executes such as any one of claims 1 to 7 right
It is required that the step of advertisement placement method.
10. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes, so that one or more processors execute the advertisement dispensing side as described in any one of claims 1 to 7 claim
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811536054.4A CN109583970A (en) | 2018-12-14 | 2018-12-14 | Advertisement placement method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811536054.4A CN109583970A (en) | 2018-12-14 | 2018-12-14 | Advertisement placement method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109583970A true CN109583970A (en) | 2019-04-05 |
Family
ID=65928346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811536054.4A Pending CN109583970A (en) | 2018-12-14 | 2018-12-14 | Advertisement placement method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109583970A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245291A (en) * | 2019-05-23 | 2019-09-17 | 广州至真信息科技有限公司 | A kind of display methods of business datum, device, computer equipment and storage medium |
| CN110276633A (en) * | 2019-05-09 | 2019-09-24 | 威比网络科技(上海)有限公司 | Advertisement placement method, system, equipment and storage medium based on online education |
| CN110321477A (en) * | 2019-05-24 | 2019-10-11 | 平安科技（深圳）有限公司 | Information recommendation method, device, terminal and storage medium |
| CN110390098A (en) * | 2019-06-18 | 2019-10-29 | 深圳壹账通智能科技有限公司 | Method, apparatus, equipment and the storage medium of data dispensing side are chosen based on big data |
| CN110533448A (en) * | 2019-06-18 | 2019-12-03 | 平安科技（深圳）有限公司 | Data push method, system and computer equipment based on micro- expression |
| CN110913135A (en) * | 2019-11-26 | 2020-03-24 | 北京达佳互联信息技术有限公司 | Video shooting method and device, electronic equipment and storage medium |
| CN111160953A (en) * | 2019-12-12 | 2020-05-15 | 浙江大华技术股份有限公司 | Method and device for delivering advertisement in application and storage medium |
| CN111639972A (en) * | 2020-05-29 | 2020-09-08 | 中国联合网络通信集团有限公司 | Multimedia data delivery method and device |
| CN112183333A (en) * | 2020-09-27 | 2021-01-05 | 苏州工业职业技术学院 | Human screen interaction method, system and device based on micro-expressions |
| CN112200611A (en) * | 2020-10-12 | 2021-01-08 | 广州欢网科技有限责任公司 | Real-time advertisement putting method and device |
| CN112364241A (en) * | 2020-10-27 | 2021-02-12 | 北京五八信息技术有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN113077295A (en) * | 2021-04-21 | 2021-07-06 | 深圳市东信时代信息技术有限公司 | Advertisement graded delivery method based on user terminal, user terminal and storage medium |
| CN113297499A (en) * | 2021-06-22 | 2021-08-24 | 北京创世路信息技术有限公司 | Information recommendation system, method, computer equipment and storage medium |
| CN113628008A (en) * | 2021-08-11 | 2021-11-09 | 中国工商银行股份有限公司 | Intelligent marketing method, device, equipment and medium |
| CN114187035A (en) * | 2021-11-29 | 2022-03-15 | 北京深演智能科技股份有限公司 | Advertisement putting method, device and system |
| CN115375367A (en) * | 2022-08-26 | 2022-11-22 | 江阴旺达商务贴有限公司 | Advertisement putting identification system and method |
| CN117808536A (en) * | 2024-02-23 | 2024-04-02 | 蓝色火焰科技成都有限公司 | Interactive advertisement evaluation method, system and delivery terminal |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102306360A (en) * | 2011-06-23 | 2012-01-04 | 迈普通信技术股份有限公司 | Feedback method of launching effect of unidirectional video advertising and system |
| CN104484044A (en) * | 2014-12-23 | 2015-04-01 | 上海斐讯数据通信技术有限公司 | Advertisement pushing method and advertisement pushing system |
| CN104573619A (en) * | 2014-07-25 | 2015-04-29 | 北京智膜科技有限公司 | Method and system for analyzing big data of intelligent advertisements based on face identification |
| CN104598869A (en) * | 2014-07-25 | 2015-05-06 | 北京智膜科技有限公司 | Intelligent advertisement pushing method based on human face recognition device |
| CN105825408A (en) * | 2016-05-16 | 2016-08-03 | 刘冰 | Method for advertisement release processing |
| CN106131675A (en) * | 2016-07-19 | 2016-11-16 | 乐视控股（北京）有限公司 | A kind of Method of Commodity Recommendation, Apparatus and system |
| CN106886909A (en) * | 2015-12-15 | 2017-06-23 | 中国电信股份有限公司 | For the method and system of commodity shopping |
| CN206378900U (en) * | 2016-10-24 | 2017-08-04 | 西安文理学院 | A kind of advertisement delivery effect evaluation system based on mobile terminal |
| CN107463876A (en) * | 2017-07-03 | 2017-12-12 | 珠海市魅族科技有限公司 | Information processing method and device, computer installation and storage medium |
| CN107679526A (en) * | 2017-11-14 | 2018-02-09 | 北京科技大学 | A kind of micro- expression recognition method of face |
| CN108182624A (en) * | 2017-12-26 | 2018-06-19 | 努比亚技术有限公司 | Method of Commodity Recommendation, server and computer readable storage medium |
| CN108509893A (en) * | 2018-03-28 | 2018-09-07 | 深圳创维－Rgb电子有限公司 | Video display methods of marking, storage medium and intelligent terminal based on micro- Expression Recognition |
| CN108681805A (en) * | 2018-03-30 | 2018-10-19 | 平安科技（深圳）有限公司 | Task statistical method and device |
| CN108764334A (en) * | 2018-05-28 | 2018-11-06 | 北京达佳互联信息技术有限公司 | Facial image face value judgment method, device, computer equipment and storage medium |
-
2018
- 2018-12-14 CN CN201811536054.4A patent/CN109583970A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102306360A (en) * | 2011-06-23 | 2012-01-04 | 迈普通信技术股份有限公司 | Feedback method of launching effect of unidirectional video advertising and system |
| CN104573619A (en) * | 2014-07-25 | 2015-04-29 | 北京智膜科技有限公司 | Method and system for analyzing big data of intelligent advertisements based on face identification |
| CN104598869A (en) * | 2014-07-25 | 2015-05-06 | 北京智膜科技有限公司 | Intelligent advertisement pushing method based on human face recognition device |
| CN104484044A (en) * | 2014-12-23 | 2015-04-01 | 上海斐讯数据通信技术有限公司 | Advertisement pushing method and advertisement pushing system |
| CN106886909A (en) * | 2015-12-15 | 2017-06-23 | 中国电信股份有限公司 | For the method and system of commodity shopping |
| CN105825408A (en) * | 2016-05-16 | 2016-08-03 | 刘冰 | Method for advertisement release processing |
| CN106131675A (en) * | 2016-07-19 | 2016-11-16 | 乐视控股（北京）有限公司 | A kind of Method of Commodity Recommendation, Apparatus and system |
| CN206378900U (en) * | 2016-10-24 | 2017-08-04 | 西安文理学院 | A kind of advertisement delivery effect evaluation system based on mobile terminal |
| CN107463876A (en) * | 2017-07-03 | 2017-12-12 | 珠海市魅族科技有限公司 | Information processing method and device, computer installation and storage medium |
| CN107679526A (en) * | 2017-11-14 | 2018-02-09 | 北京科技大学 | A kind of micro- expression recognition method of face |
| CN108182624A (en) * | 2017-12-26 | 2018-06-19 | 努比亚技术有限公司 | Method of Commodity Recommendation, server and computer readable storage medium |
| CN108509893A (en) * | 2018-03-28 | 2018-09-07 | 深圳创维－Rgb电子有限公司 | Video display methods of marking, storage medium and intelligent terminal based on micro- Expression Recognition |
| CN108681805A (en) * | 2018-03-30 | 2018-10-19 | 平安科技（深圳）有限公司 | Task statistical method and device |
| CN108764334A (en) * | 2018-05-28 | 2018-11-06 | 北京达佳互联信息技术有限公司 | Facial image face value judgment method, device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 薛天坤: ""基于卷积神经网络的微表情识别"", 《中国新技术新产品》, vol. 1, no. 16, pages 2 - 7 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110276633A (en) * | 2019-05-09 | 2019-09-24 | 威比网络科技(上海)有限公司 | Advertisement placement method, system, equipment and storage medium based on online education |
| CN110245291A (en) * | 2019-05-23 | 2019-09-17 | 广州至真信息科技有限公司 | A kind of display methods of business datum, device, computer equipment and storage medium |
| CN110321477A (en) * | 2019-05-24 | 2019-10-11 | 平安科技（深圳）有限公司 | Information recommendation method, device, terminal and storage medium |
| WO2020238023A1 (en) * | 2019-05-24 | 2020-12-03 | 平安科技（深圳）有限公司 | Information recommendation method and apparatus, and terminal and storage medium |
| CN110390098A (en) * | 2019-06-18 | 2019-10-29 | 深圳壹账通智能科技有限公司 | Method, apparatus, equipment and the storage medium of data dispensing side are chosen based on big data |
| CN110533448A (en) * | 2019-06-18 | 2019-12-03 | 平安科技（深圳）有限公司 | Data push method, system and computer equipment based on micro- expression |
| CN110913135A (en) * | 2019-11-26 | 2020-03-24 | 北京达佳互联信息技术有限公司 | Video shooting method and device, electronic equipment and storage medium |
| CN111160953A (en) * | 2019-12-12 | 2020-05-15 | 浙江大华技术股份有限公司 | Method and device for delivering advertisement in application and storage medium |
| CN111160953B (en) * | 2019-12-12 | 2023-11-03 | 浙江大华技术股份有限公司 | Method, device and storage medium for putting advertisement in application |
| CN111639972A (en) * | 2020-05-29 | 2020-09-08 | 中国联合网络通信集团有限公司 | Multimedia data delivery method and device |
| CN112183333B (en) * | 2020-09-27 | 2021-12-10 | 苏州工业职业技术学院 | Human screen interaction method, system and device based on micro-expressions |
| CN112183333A (en) * | 2020-09-27 | 2021-01-05 | 苏州工业职业技术学院 | Human screen interaction method, system and device based on micro-expressions |
| CN112200611A (en) * | 2020-10-12 | 2021-01-08 | 广州欢网科技有限责任公司 | Real-time advertisement putting method and device |
| CN112364241A (en) * | 2020-10-27 | 2021-02-12 | 北京五八信息技术有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN113077295A (en) * | 2021-04-21 | 2021-07-06 | 深圳市东信时代信息技术有限公司 | Advertisement graded delivery method based on user terminal, user terminal and storage medium |
| CN113077295B (en) * | 2021-04-21 | 2022-02-15 | 深圳市东信时代信息技术有限公司 | Advertisement graded delivery method based on user terminal, user terminal and storage medium |
| CN113297499A (en) * | 2021-06-22 | 2021-08-24 | 北京创世路信息技术有限公司 | Information recommendation system, method, computer equipment and storage medium |
| CN113628008A (en) * | 2021-08-11 | 2021-11-09 | 中国工商银行股份有限公司 | Intelligent marketing method, device, equipment and medium |
| CN114187035A (en) * | 2021-11-29 | 2022-03-15 | 北京深演智能科技股份有限公司 | Advertisement putting method, device and system |
| CN115375367A (en) * | 2022-08-26 | 2022-11-22 | 江阴旺达商务贴有限公司 | Advertisement putting identification system and method |
| CN115375367B (en) * | 2022-08-26 | 2023-04-07 | 江阴旺达商务贴有限公司 | Advertisement putting identification system and method |
| CN117808536A (en) * | 2024-02-23 | 2024-04-02 | 蓝色火焰科技成都有限公司 | Interactive advertisement evaluation method, system and delivery terminal |
| CN117808536B (en) * | 2024-02-23 | 2024-05-14 | 蓝色火焰科技成都有限公司 | Interactive advertisement evaluation method, system and delivery terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583970A (en) | Advertisement placement method, device, computer equipment and storage medium | |
| KR102122373B1 (en) | Method and apparatus for obtaining user portrait | |
| US10824942B1 (en) | Visual similarity and attribute manipulation using deep neural networks | |
| US9875258B1 (en) | Generating search strings and refinements from an image | |
| US20180181569A1 (en) | Visual category representation with diverse ranking | |
| CN103268317B (en) | Image is carried out the system and method for semantic annotations | |
| WO2020019564A1 (en) | Search ranking method and apparatus, electronic device and storage medium | |
| US20080226174A1 (en) | Image Organization | |
| US20210326400A1 (en) | Method and apparatus for processing web content, device, and computer storage medium | |
| CN109359247A (en) | Content delivery method and storage medium, computer equipment | |
| US11238515B1 (en) | Systems and method for visual search with attribute manipulation | |
| CN107368550A (en) | Information acquisition method, device, medium, electronic equipment, server and system | |
| CN107943895A (en) | Information-pushing method and device | |
| CN110413888A (en) | A kind of books recommended method and device | |
| CN107832338A (en) | A kind of method and system for identifying core product word | |
| CN112052297B (en) | Information generation method, apparatus, electronic device and computer readable medium | |
| CN107968743A (en) | The method and apparatus of pushed information | |
| CN113344648B (en) | Advertisement recommendation method and system based on machine learning | |
| CN109360072A (en) | Insurance products recommended method, device, computer equipment and storage medium | |
| CN116383458B (en) | Information pushing method and device | |
| JP2022530725A (en) | Information push methods, devices, equipment and storage media | |
| CN111797622B (en) | Method and device for generating attribute information | |
| CN106294584B (en) | The training method and device of order models | |
| CN116738057A (en) | Information recommendation method, device, computer equipment and storage medium | |
| CN106528753A (en) | Data searching method and apparatus |
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 |