CN110598017A - Self-learning-based commodity detail page generation method - Google Patents
Self-learning-based commodity detail page generation method Download PDFInfo
- Publication number
- CN110598017A CN110598017A CN201910820761.4A CN201910820761A CN110598017A CN 110598017 A CN110598017 A CN 110598017A CN 201910820761 A CN201910820761 A CN 201910820761A CN 110598017 A CN110598017 A CN 110598017A
- Authority
- CN
- China
- Prior art keywords
- image
- detail page
- picture
- commodity
- template
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a self-learning-based commodity detail page generation method, which at least comprises the following steps: s1, providing an image processing model; s2, constructing a detail page template library; s3, constructing a picture library; s4, providing an image or an image set, and extracting the main color of the image or the image set; matching pictures in a picture library by using a posture similarity algorithm aiming at the images, and sequencing the image sets by combining the main body color and the matching degree; s5, matching the image or the image set with a detail page template library according to the category of the image or the image set; s6, matching the picture space occupying frame and the image on the module according to the matched detail page template and the configuration parameters in the S5; s7, cutting the corresponding image according to the cutting rule in the picture occupying frame on the module; and S8, generating a commodity detail page.
Description
Technical Field
The invention belongs to the field of automation of visual layout design, and particularly relates to a commodity detail page generation method based on self-learning.
Background
The E-commerce commodity detail page is subjected to art designing, picture repairing, typesetting, adjusting and cutting, and then the manufactured commodity detail page is uploaded and published to each E-commerce platform. Such a conventional procedure takes several tens of minutes to several hours.
At present, in the prior art, a commodity detail page of an e-commerce platform is generated in a naming matching mode. Firstly naming the picture space occupying frame on the template, then appointing a name for the material picture file, and placing the material picture file with the appointed name on the picture space occupying frame with the same name on the template through a computer program. The method has the following defects: the designer is required to plan the layout of the detail page in the mind in advance, then specify the position of the material diagram on the detail page, and finally name the picture file. The method only fills the named pictures in the detail page template, does not have the function of intelligent typesetting layout, and has limited improvement efficiency.
Chinese patent publication No. CN105068985A, which is an automated design and typesetting method based on artificial intelligence machine. S1, establishing an information mapping docking framework according to fields required by a third-party e-commerce platform; and S2, performing intelligent automatic typesetting according to the product pictures. And S3, forming a final commodity detail page after fine adjustment, checking and confirming, and fully automatically uploading the final commodity detail page to each large third-party e-commerce platform according to the final confirmation of the customer. The specific process of S2 is that the original detail page template submitted by the customer is uploaded to the typesetting system, the typesetting system has the decoding function of analyzing the PSD source file, the PSD source file can be analyzed by the decoding function in the typesetting system and the preset template information provided by the merchant is combined to generate an intelligent template for artificial intelligent identification and automatic editing, then the product picture provided by the customer is uploaded to the intelligent template in the typesetting system, the typesetting system can automatically visually identify the content of the product picture from the aesthetic standard angle, the picture content of the automatically identified product is combined into the commodity display detail page by automatically comparing, placing, cutting and beautifying the picture, and the typesetting system can automatically visually identify the content of the product picture from the aesthetic standard angle by using a DenseNet model and follow the following steps: a. performing aesthetic scoring on the pictures according to aesthetic rules on the third-party E-business platform and detection of real-time images, automatically sequencing the scoring from high to low, and entering the next step; b. identifying objects in the pictures by detecting the pictures meeting the conditions in the last step a through a GPU cluster, scoring each product picture according to the preset information matching degree, and sequencing the picture scores from high to low in sequence; c. automatically cutting and deleting the selected picture after the step b according to the picture requirement of the size of a preset aesthetic template on the intelligent template; d. analyzing the semantics of the E-commerce product field to analyze the specific semantics of the product field and the corresponding relation of the product field; e. the typesetting system can automatically select fields and pictures meeting the requirements of preset pictures and field information, and finally, the fields and the pictures are spliced to corresponding areas on the intelligent template through automatic comparison, placing, cutting and beautifying of the pictures to be combined into a commodity display detail page. The disadvantages are that: when the method is used for processing a certain material packet, only one pre-configured detail page template exists. When the clothing type of the material map does not conform to the preset type on the template, or the components of the material package picture are complex, the final detailed page effect is poor, a large amount of manual adjustment in a detailed page editor is needed, and the efficiency is still low.
Disclosure of Invention
In order to solve the technical problem, the invention provides a self-learning-based commodity detail page generation method, which at least comprises the following steps:
s1, providing an image processing model;
s2, constructing a detail page template library;
s3, constructing a picture library;
s4, providing an image or an image set, and extracting the main color of the image or the image set; matching pictures in a picture library by using a posture similarity algorithm aiming at the images, and sequencing the image sets by combining the main body color and the matching degree;
s5, matching the image or the image set with a detail page template library according to the category of the image or the image set;
s6, matching the picture space occupying frame and the image on the module according to the matched detail page template and the configuration parameters in the S5;
s7, cutting the corresponding image according to the cutting rule in the picture occupying frame on the module;
and S8, generating a commodity detail page.
Preferably, the image processing model is constructed as follows:
s11, collecting commodity images;
s12, classifying the commodity images based on the deep neural network training model;
s13, selecting key points of the commodity image based on the conditional Pose Machines model;
s14, positioning a commodity image target detection frame based on the Faster R-CNN model;
and S15, extracting the main body color of the commodity image and classifying according to the main body color.
Preferably, the construction method of the detail page template library is as follows:
s21, recording the new detail page into a template library;
s22, training a CRF model based on the template element sequence in the template library, and predicting the template element sequence of the image or the image set to obtain a new detail page template.
Preferably, the attitude similarity algorithm is as follows:
s41, detecting a human body or clothing target frame in the image;
s42, selecting a target frame with the largest area in the image, and zooming the target area to 200 pixels in width;
s43, if the difference of the aspect ratio of the target frames of the two images is larger than k, returning a 'dissimilarity' judgment result; wherein k is 0.2;
s44, detecting key points of the human body or the clothes, and defining the number of the key points as m;
s45, normalizing the coordinates X and Y of the key points detected in the selected target frame to be between [0 and 1 ];
s46, fixing the sequence of the key points to form a vector coordinate axis, and taking the X and Y coordinate values of the key points as vector values to obtain a vector v; undetected keypoint markers X and Y are-1; v. ofi,xX coordinate, v, representing the ith keypointi,yY-coordinate representing the ith keypoint;
s47, if at least n homonymous key points exist in the two comparison areas, continuing to calculate; otherwise, returning a 'dissimilar' judgment result; wherein n is 0.9;
s48, constructing a rectangle for each area according to the min (X), the min (Y), the max (X) and the max (Y) of the coordinates of the key points with the same name; if the ratio of the area of the smaller rectangle to the area of the larger rectangle is less than t, returning a 'dissimilarity' judgment result; wherein t is 0.7;
s49, and keypoint vectors v1 and v2 of the two graphs, which define the distance between the keypoints in Euclidean space:
d <0.1 is considered as a diagram with similar postures.
Compared with the prior art, the technical scheme of the application has the beneficial effects that:
according to the method for generating the commodity detail page based on self-learning, the efficiency of editing the detail page can be greatly improved, a large amount of manual adjustment in a detail page editor is not needed, and the labor cost is saved.
For manually making a single detail page in the prior art, the average time consumption is about 20 minutes or more, and for making the single detail page by the method, the average time consumption is about 2 minutes or less, so that the efficiency improvement of more than 10 times is realized. After the merchant user uses the system, the labor input of the art designer for manufacturing the commodity detail page can be greatly reduced, and great economic benefits are generated.
Drawings
FIG. 1 is a flow chart of the method of the present application.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited thereto.
Examples
The embodiment discloses a self-learning-based commodity detail page generation method, which at least comprises the following steps:
s1, providing an image processing model;
the embodiment of the application is directed to a method for generating a detail page of a clothing article.
The clothing classification of the material map, the type of the material map, the clothing target detection frame, the human body key points, the clothing key points and other information are called basic image semantic information.
Defining a clothing classification: short sleeves, long sleeves, windcheaters, shorts, trousers, one-piece dress, skirt, and the like.
Seven large types of material pictures are defined: model picture, hanging picture, flat picture, detail picture, hanging picture and combination picture.
Three shot body segments of the model figure are defined: upper body, lower body and whole body.
Three shooting angles of a model picture, a hanging picture and a floor picture are defined: front, side and back views.
The human body frame and the clothes frame are defined and are approximate minimum surrounding rectangular frames of the main body in the picture.
Defining human body key points: neck, chin, left ear, right ear, left shoulder, right shoulder, left waist, right waist, left knee, right knee, etc
Defining key points of the garment, a left cuff outer angle, a left cuff inner angle, a right cuff outer angle, a right cuff inner angle, a left neckline, a right neckline, a lower neckline, a left lower swing angle, a right lower swing angle, a crotch, a left trouser leg bottom outer angle, a left trouser leg bottom inner angle and the like.
Preferably, the image processing model is constructed as follows:
s11, collecting clothing commodity images;
s12, classifying the clothing commodity images based on a deep neural network training model (Mask R-CNN model);
s13, selecting key points of the clothing commodity image based on the conditional Pose Machines model;
s14, positioning a clothing commodity image target detection frame based on the Faster R-CNN model;
and S15, extracting the main body color of the clothing commodity image and cutting the detail map.
S2, constructing a detail page template library;
the detail page template determines the visual layout characteristics of the detail page, and generally comprises a poster picture module, a model display module, a sub-style comparison module, a detail picture module, a material fabric module, a commodity information module, a commodity index module, a size table module, a size recommendation table module, a collocation recommendation module and the like. The module is composed of a series of elements which are equal in width and are arranged in a non-overlapping mode from top to bottom. The element has a picture placeholder frame and a decorative picture assembly or text thereon. The picture placeholder box may specify a selection strategy, such as to select a particular type of material map, such as "front upper body mannequin picture", "side upper body mannequin picture", "trousers picture", and "neckline detail picture", etc. The picture space occupying frame is attached with cutting parameters, such as the left, right, up and down distance between a figure main body or a clothing main body and the boundary of the picture space occupying frame is appointed, and the rules that the figure is placed in the middle or in the left can also be appointed.
The construction method of the detail page template library comprises the following steps:
s21, recording the new detail page into a template library;
s22, training a CRF model based on the template element sequence in the template library, and predicting the template element sequence of the image or the image set to obtain a new detail page template.
When a user uses the system, a new detail page can be automatically generated, if the user is not satisfied, the detail page can be modified in detail page editing, and the method comprises an increase and decrease module, an increase and decrease picture space occupying frame and a material picture, layout adjustment, character color or size change and the like.
S3, constructing a picture library;
downloading a large amount of high-quality picture data from an e-commerce platform regularly, extracting data such as key points of a human body and key points of clothes, and constructing a picture library.
S4, providing an image or an image set, and extracting the color of the image main body. Matching pictures in a picture library by using a posture similarity algorithm aiming at the images, and then sequencing the image sets by combining the main body color and the matching degree;
the attitude similarity algorithm is as follows:
s41, detecting a human body or clothing target frame in the image;
s42, selecting a target frame with the largest area in the image, and zooming the target area to 200 pixels in width;
s43, if the difference of the aspect ratio of the target frames of the two images is larger than k, returning a 'dissimilarity' judgment result; wherein k is 0.2;
s44, detecting key points of the human body or the clothes, and defining the number of the key points as m;
s45, normalizing the coordinates X and Y of the key points detected in the selected target frame to be between [0 and 1 ];
s46, fixing the sequence of the key points, such as { neck, chin, left ear, right ear, left shoulder, right shoulder, left waist, right waist, left knee and right knee … … }, forming a vector coordinate axis, and taking the X and Y coordinate values of the key points as vector values to obtain a vector v; undetected keypoint markers X and Y are-1; v. ofi,xX coordinate, v, representing the ith keypointi,yY-coordinate representing the ith keypoint;
s47, if at least n homonymous key points exist in the two comparison areas, continuing to calculate; otherwise, returning a 'dissimilar' judgment result; wherein n is 0.9;
s48, for each area, constructing a rectangle according to the min (X), min (Y), max (X) and max (Y) of the coordinates of the key points with the same name. If the ratio of the area of the smaller rectangle to the area of the larger rectangle is less than t, returning a 'dissimilarity' judgment result; wherein t is 0.7;
s49, and keypoint vectors v1 and v2 of the two graphs, which define the distance between the keypoints in Euclidean space:
d <0.1 is considered as a diagram with similar postures.
And S5, matching the image or the image set with the detail page template library according to the category of the image or the image set.
The image or the image set refers to a material packet uploaded by a user, and image semantic information is extracted by using an image processing model;
and searching the detail page template library of the user according to the clothing types of the material images in the material packet to obtain a detail page template list. And selecting the most similar intelligent detail page template according to the similarity between the material packet and the sample diagram in the picture space occupying frame on the detail page template. And if the matched detail page template is configured with a dynamic expansion strategy, using a specified module in the CRF model expansion template to obtain a new detail page template. And if the dynamic extension strategy is not configured, directly using the matched detail page template.
The matching method of the similarity between the material package and the sample diagram in the picture placeholder box on the detail page template comprises the following steps:
(1) the material packet has the attribute of the clothing type, and the template of the corresponding type is retrieved from the template library.
For example, if the current material package belongs to a shirt type, the template list of the shirt in the template library is retrieved. If no shirt template is in the library, the manually configured initial detail page template is selected.
(2) If a plurality of detail page templates are searched in the previous step, the 'sub-style number' attribute of the material package is extracted, if the 'sub-style number' of the detail page templates is the same as that of the detail page templates, the template is selected, and the next step is carried out. And if the attribute of the 'sub style quantity' of none of the detail page templates is the same, directly switching to the next judgment.
(3) If the previous step still matches a plurality of templates, the method takes seven types of the material map: the method comprises the steps of taking a model picture, a hanging picture, a floor map, a detail picture, a hanging picture and a combined picture as components, counting the number of material pictures of each component to form a feature vector, obtaining the feature vector of the sample picture in a picture space occupying frame on a material packet and a detail page template, and matching the detail page template with the maximum feature vector similarity.
(4) If the model display module in the matched detail page template is configured with a dynamic generation strategy, the element sequence of the model display module can be dynamically generated based on the CRF model according to the sorted material map, so as to obtain a new detail page template, and the matching is successful and finished.
S6, matching the picture space occupying frame and the image on the template according to the matched detail page template and the configuration parameters in the S5;
and traversing all modules in the template from top to bottom, and preferentially selecting the highest-aesthetic-degree picture of the specified type from the rest pictures according to the picture selection rule of the picture occupying frame. Pictures that have been used, generally, cannot be reused unless a reuse graph strategy is defined.
Some modules have special drawing selection rules. For example, if there are n sub-patterns in the material map, the sub-pattern comparison module dynamically sets the module to have n image space-occupying frames. It is also desirable that the visual dimensions of the subject in each picture placeholder be equal in size and pose as similar as possible. The key point data of the human body and the clothing can be used for selecting material graphs with similar postures and unifying the visual scale of the main body in the graph.
S7, cutting the corresponding image or image set according to the cutting rule in the image occupying frame on the module;
and S8, generating a commodity detail page.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (4)
1. A self-learning-based commodity detail page generation method is characterized by at least comprising the following steps:
s1, providing an image processing model;
s2, constructing a detail page template library;
s3, constructing a picture library;
s4, providing an image or an image set, and extracting the main color of the image or the image set; matching pictures in a picture library by using a posture similarity algorithm aiming at the images, and sequencing the image sets by combining the main body color and the matching degree;
s5, matching the image or the image set with a detail page template library according to the category of the image or the image set;
s6, matching the picture space occupying frame and the image on the module according to the matched detail page template and the configuration parameters in the S5;
s7, cutting the corresponding image according to the cutting rule in the picture occupying frame on the module;
and S8, generating a commodity detail page.
2. The self-learning based commodity detail page generation method according to claim 1, wherein the image processing model is constructed by the following method:
s11, collecting commodity images;
s12, classifying the commodity images based on the deep neural network training model;
s13, selecting key points of the commodity image based on the conditional Pose Machines model;
s14, positioning a commodity image target detection frame based on the Faster R-CNN model;
and S15, extracting the main body color of the commodity image and classifying according to the main body color.
3. The self-learning based commodity detail page generation method according to claim 1, wherein the detail page template library is constructed by the following method:
s21, recording the new detail page into a template library;
s22, training a CRF model based on the template element sequence in the template library, and predicting the template element sequence of the image or the image set to obtain a new detail page template.
4. The self-learning based merchandise detail page generation method of claim 1 wherein the attitude similarity algorithm is as follows:
s41, detecting a human body or clothing target frame in the image;
s42, selecting a target frame with the largest area in the image, and zooming the target area to 200 pixels in width;
s43, if the difference of the aspect ratio of the target frames of the two images is larger than k, returning a 'dissimilarity' judgment result; wherein k is 0.2;
s44, detecting key points of the human body or the clothes, and defining the number of the key points as m;
s45, normalizing the coordinates X and Y of the key points detected in the selected target frame to be between [0 and 1 ];
s46, fixing key pointsSequentially forming a vector coordinate axis, and taking the X and Y coordinate values of the key points as vector values to obtain a vector v; undetected keypoint markers X and Y are-1; v. ofi,xX coordinate, v, representing the ith keypointi,yY-coordinate representing the ith keypoint;
s47, if at least n homonymous key points exist in the two comparison areas, continuing to calculate; otherwise, returning a 'dissimilar' judgment result; wherein n is 0.9;
s48, constructing a rectangle for each area according to the min (X), the min (Y), the max (X) and the max (Y) of the coordinates of the key points with the same name; if the ratio of the area of the smaller rectangle to the area of the larger rectangle is less than t, returning a 'dissimilarity' judgment result; wherein t is 0.7;
s49, and keypoint vectors v1 and v2 of the two graphs, which define the distance between the keypoints in Euclidean space:
d <0.1 is considered as a diagram with similar postures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910820761.4A CN110598017B (en) | 2019-08-29 | 2019-08-29 | Self-learning-based commodity detail page generation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910820761.4A CN110598017B (en) | 2019-08-29 | 2019-08-29 | Self-learning-based commodity detail page generation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110598017A true CN110598017A (en) | 2019-12-20 |
| CN110598017B CN110598017B (en) | 2020-08-14 |
Family
ID=68856829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910820761.4A Active CN110598017B (en) | 2019-08-29 | 2019-08-29 | Self-learning-based commodity detail page generation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110598017B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111353532A (en) * | 2020-02-26 | 2020-06-30 | 北京三快在线科技有限公司 | Image generation method and device, computer-readable storage medium and electronic device |
| CN111489419A (en) * | 2020-06-28 | 2020-08-04 | 广州筷子信息科技有限公司 | Poster generation method and system |
| CN113485703A (en) * | 2021-06-21 | 2021-10-08 | 上海百秋电子商务有限公司 | Online interactive commodity detail page editing method and system |
| CN113610601A (en) * | 2021-08-08 | 2021-11-05 | 北京极睿科技有限责任公司 | Method and device for updating commodity detail page content, electronic equipment and storage medium |
| CN114419194A (en) * | 2021-09-29 | 2022-04-29 | 阿里巴巴（中国）有限公司 | Method for generating collocation image and electronic equipment |
| CN115525281A (en) * | 2022-10-12 | 2022-12-27 | 广州宏天软件股份有限公司 | Form interactive graph display and selection method |
| CN117314546A (en) * | 2023-03-14 | 2023-12-29 | 广东南粤分享汇控股有限公司 | E-commerce product analysis method, system, medium and computer based on artificial intelligence |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104111933A (en) * | 2013-04-17 | 2014-10-22 | 阿里巴巴集团控股有限公司 | Method and device for acquiring business object label and building training model |
| CN104408155A (en) * | 2014-12-04 | 2015-03-11 | 北京京东尚科信息技术有限公司 | Method and device for generating webpage codes, and system |
| CN104573131A (en) * | 2015-02-15 | 2015-04-29 | 北京京东尚科信息技术有限公司 | Method for generating commodity detail page data and terminal device |
| CN104616158A (en) * | 2015-02-13 | 2015-05-13 | 北京京东尚科信息技术有限公司 | Product detail page generation method and device |
| CN105931096A (en) * | 2016-04-14 | 2016-09-07 | 杭州艺豆网络科技有限公司 | Commodity detail page making method |
| CN106157106A (en) * | 2015-04-23 | 2016-11-23 | 阿里巴巴集团控股有限公司 | The methods of exhibiting of merchandise news and device |
| CN106547928A (en) * | 2016-12-27 | 2017-03-29 | 浪潮软件集团有限公司 | E-commerce industry commodity detail page decoration method |
| CN106649695A (en) * | 2016-12-19 | 2017-05-10 | 天脉聚源(北京)传媒科技有限公司 | Commodity page generation method and device |
| CN107609193A (en) * | 2017-10-16 | 2018-01-19 | 杭州时间线信息科技有限公司 | The intelligent automatic processing method and system of picture in a kind of suitable commodity details page |
| CN107622134A (en) * | 2017-10-16 | 2018-01-23 | 杭州时间线信息科技有限公司 | The Automated Design typesetting formula details page preparation method that a kind of visual identity and artificial intelligence are combined |
| CN107665238A (en) * | 2017-08-24 | 2018-02-06 | 北京搜狗科技发展有限公司 | Image processing method and device, the device for picture processing |
| CN109542441A (en) * | 2018-11-29 | 2019-03-29 | 方正璞华软件（武汉）股份有限公司 | A kind of commodity page customization method, device and equipment |
| CN109658479A (en) * | 2018-11-26 | 2019-04-19 | 河南大瑞物联网科技有限公司 | A kind of auxiliary automatic design method for the electric business platform buyer's guide page |
-
2019
- 2019-08-29 CN CN201910820761.4A patent/CN110598017B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104111933A (en) * | 2013-04-17 | 2014-10-22 | 阿里巴巴集团控股有限公司 | Method and device for acquiring business object label and building training model |
| CN104408155A (en) * | 2014-12-04 | 2015-03-11 | 北京京东尚科信息技术有限公司 | Method and device for generating webpage codes, and system |
| CN104616158A (en) * | 2015-02-13 | 2015-05-13 | 北京京东尚科信息技术有限公司 | Product detail page generation method and device |
| CN104573131A (en) * | 2015-02-15 | 2015-04-29 | 北京京东尚科信息技术有限公司 | Method for generating commodity detail page data and terminal device |
| CN106157106A (en) * | 2015-04-23 | 2016-11-23 | 阿里巴巴集团控股有限公司 | The methods of exhibiting of merchandise news and device |
| CN105931096A (en) * | 2016-04-14 | 2016-09-07 | 杭州艺豆网络科技有限公司 | Commodity detail page making method |
| CN106649695A (en) * | 2016-12-19 | 2017-05-10 | 天脉聚源(北京)传媒科技有限公司 | Commodity page generation method and device |
| CN106547928A (en) * | 2016-12-27 | 2017-03-29 | 浪潮软件集团有限公司 | E-commerce industry commodity detail page decoration method |
| CN107665238A (en) * | 2017-08-24 | 2018-02-06 | 北京搜狗科技发展有限公司 | Image processing method and device, the device for picture processing |
| CN107609193A (en) * | 2017-10-16 | 2018-01-19 | 杭州时间线信息科技有限公司 | The intelligent automatic processing method and system of picture in a kind of suitable commodity details page |
| CN107622134A (en) * | 2017-10-16 | 2018-01-23 | 杭州时间线信息科技有限公司 | The Automated Design typesetting formula details page preparation method that a kind of visual identity and artificial intelligence are combined |
| CN109658479A (en) * | 2018-11-26 | 2019-04-19 | 河南大瑞物联网科技有限公司 | A kind of auxiliary automatic design method for the electric business platform buyer's guide page |
| CN109542441A (en) * | 2018-11-29 | 2019-03-29 | 方正璞华软件（武汉）股份有限公司 | A kind of commodity page customization method, device and equipment |
Non-Patent Citations (2)
| Title |
|---|
| 张威: ""基于内容的服装检索系统的设计与实现"", 《万方》 * |
| 罗梦研: ""基于卷积神经网络的女装图像分类算法研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111353532A (en) * | 2020-02-26 | 2020-06-30 | 北京三快在线科技有限公司 | Image generation method and device, computer-readable storage medium and electronic device |
| CN111489419A (en) * | 2020-06-28 | 2020-08-04 | 广州筷子信息科技有限公司 | Poster generation method and system |
| CN113485703A (en) * | 2021-06-21 | 2021-10-08 | 上海百秋电子商务有限公司 | Online interactive commodity detail page editing method and system |
| CN113610601A (en) * | 2021-08-08 | 2021-11-05 | 北京极睿科技有限责任公司 | Method and device for updating commodity detail page content, electronic equipment and storage medium |
| CN114419194A (en) * | 2021-09-29 | 2022-04-29 | 阿里巴巴（中国）有限公司 | Method for generating collocation image and electronic equipment |
| CN115525281A (en) * | 2022-10-12 | 2022-12-27 | 广州宏天软件股份有限公司 | Form interactive graph display and selection method |
| CN115525281B (en) * | 2022-10-12 | 2023-06-27 | 广州宏天软件股份有限公司 | Form interactive graph display and selection method |
| CN117314546A (en) * | 2023-03-14 | 2023-12-29 | 广东南粤分享汇控股有限公司 | E-commerce product analysis method, system, medium and computer based on artificial intelligence |
| CN117314546B (en) * | 2023-03-14 | 2024-07-09 | 广东南粤分享汇控股有限公司 | E-commerce product analysis method, system, medium and computer based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110598017B (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110598017B (en) | Self-learning-based commodity detail page generation method | |
| EP3908943B1 (en) | Method, apparatus, electronic device and computer readable storage medium for image searching | |
| US11321769B2 (en) | System and method for automatically generating three-dimensional virtual garment model using product description | |
| CN106709568B (en) | The object detection and semantic segmentation method of RGB-D image based on deep layer convolutional network | |
| US9940749B2 (en) | Method and system for generating three-dimensional garment model | |
| CN109670591B (en) | Neural network training method and image matching method and device | |
| US8983142B1 (en) | Programmatic silhouette attribute determination | |
| CN110335277A (en) | Image processing method, device, computer readable storage medium and computer equipment | |
| TWI559242B (en) | Visual clothing retrieval | |
| US11270476B2 (en) | Method and system for providing photorealistic changes for digital image | |
| CN109583481B (en) | Fine-grained clothing attribute identification method based on convolutional neural network | |
| Cychnerski et al. | Clothes detection and classification using convolutional neural networks | |
| CN109614925A (en) | Dress ornament attribute recognition approach and device, electronic equipment, storage medium | |
| CN104021381B (en) | Human movement recognition method based on multistage characteristics | |
| CN109711266A (en) | Dress ornament attribute tags recognition methods based on neural network model sophisticated category | |
| CN109766822A (en) | Gesture identification method neural network based and system | |
| CN107870992A (en) | Editable image of clothing searching method based on multichannel topic model | |
| CN110647906A (en) | Clothing target detection method based on fast R-CNN method | |
| CN108596098A (en) | Analytic method, system, equipment and the storage medium of human part | |
| CN105117399A (en) | Image search method and device | |
| CN110196917A (en) | Personalized LOGO format method for customizing, system and storage medium | |
| Miura et al. | SNAPPER: fashion coordinate image retrieval system | |
| Dwina et al. | Skin segmentation based on improved thresholding method | |
| KR102475004B1 (en) | Method for mentality analysis based on object analysis on picture and apparuatus for performing the method | |
| CN111159456A (en) | Multi-scale clothing retrieval method and system based on deep learning and traditional features |
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 |