CN112435083A - Article recommendation method based on brain wave recognition and electronic equipment - Google Patents
Article recommendation method based on brain wave recognition and electronic equipment Download PDFInfo
- Publication number
- CN112435083A CN112435083A CN201910792565.0A CN201910792565A CN112435083A CN 112435083 A CN112435083 A CN 112435083A CN 201910792565 A CN201910792565 A CN 201910792565A CN 112435083 A CN112435083 A CN 112435083A
- Authority
- CN
- China
- Prior art keywords
- image
- user
- brain wave
- viewed
- item
- 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
- 210000004556 brain Anatomy 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000012549 training Methods 0.000 claims description 20
- 230000002194 synthesizing effect Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004883 computer application Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000010189 synthetic method Methods 0.000 description 2
- 230000003042 antagnostic effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 239000004570 mortar (masonry) Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Neurology (AREA)
- Human Computer Interaction (AREA)
- Neurosurgery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Dermatology (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of computer application, in particular to an article recommendation method and electronic equipment based on brain wave recognition.
Description
Technical Field
The invention relates to the technical field of computer application, in particular to an article recommendation method based on brain wave identification and electronic equipment.
Background
In the new internet service environment, users not only are passive recipients of information consumption, but also influence information services from multi-aspect multi-level interaction. With the increasing living standard of people, proper clothes, lap and the like become more important. At present, a lot of existing clothes wearing software in the market is recommended mainly according to gender, season and style, most clothes are provided with purchasing links, and the software is mainly used for selling profits. However, when the direct purchase of clothes is not premised, for example, people want to select favorite clothes or need to customize the clothes, it is difficult to meet the needs of users.
Disclosure of Invention
The invention provides an article recommendation method and electronic equipment based on brain wave recognition, which are used for obtaining the satisfaction degree of a user to an image to be checked by analyzing a brain wave image when the user watches the image to be checked, so that articles are recommended to the user according to the preference of the user to meet the requirements of the user.
In order to solve the above technical problems, the embodiments of the present invention provide the following technical solutions:
an item recommendation method based on brain wave recognition, the method comprising:
the method comprises the steps of obtaining brain wave signals when a user views images to be viewed, wherein the images to be viewed comprise article images, the images to be viewed comprise a plurality of images, and different images to be viewed comprise different article images;
analyzing the brain wave signals aiming at each brain wave signal to obtain the satisfaction degree of a user on the image to be checked corresponding to the brain wave signals;
training a first generation countermeasure network based on the image to be viewed and user satisfaction with the image to be viewed;
and generating a recommendation image comprising an image of the item to be recommended by adopting the first generation countermeasure network, and displaying the recommendation image.
Optionally, in the article recommendation method based on brain wave recognition, before the step of obtaining the brain wave signal of the user viewing each image to be viewed is performed, the method further includes:
and obtaining a user image when the user wears different articles, and taking the user image as an image to be viewed.
Optionally, in the article recommendation method based on brain wave recognition, before the step of obtaining the brain wave signal of the user viewing each image to be viewed is performed, the method further includes:
obtaining a body image and a plurality of item images of a user;
and synthesizing the body image and the article image by adopting a second generation countermeasure network to obtain a user image when the article corresponding to the article image is worn on the user, and taking the user image as an image to be viewed.
Optionally, in the article recommendation method based on brain wave recognition above, before performing the step of obtaining the body image of the user and the plurality of article images, the method further includes:
acquiring a training sample set, wherein the training sample set comprises a body sample image, an object sample image and a user target image;
training a second generation countermeasure network according to the body sample image, the object sample image and the user target image, wherein the second generation countermeasure network comprises a feature detector and an image generator which are in mutual countermeasure, and the feature detector and the image generator are used for synthesizing the body sample image and the object sample image into the user image.
Optionally, in the method for recommending an item based on brain wave recognition, training the first generation countermeasure network based on the image to be checked and the satisfaction degree of the image to be checked includes:
acquiring an image to be viewed with satisfaction greater than a first threshold value in the image to be viewed as a target image to be viewed;
and training a first generation countermeasure network according to the target images to be checked and the satisfaction corresponding to each target image to be checked.
Optionally, in the method for recommending an article based on brain wave recognition, the step of analyzing the brain wave signal to obtain the satisfaction of the user on the image to be viewed corresponding to the brain wave signal includes:
analyzing the brain wave signals to obtain the style satisfaction and the color satisfaction of the user to the object images in the images to be checked corresponding to the brain wave signals;
obtaining a first weight value of style satisfaction degree of the item image and a second weight value of color satisfaction degree of the item image;
and obtaining the satisfaction degree of the user to the image to be checked according to the style satisfaction degree of the item image, the color satisfaction degree of the item image, the first weight value and the second weight value.
Optionally, in the method for recommending an item based on brain wave recognition, the step of generating a recommendation image including an image of the item to be recommended by using the first generation countermeasure network includes:
and generating a recommendation image which has satisfaction degree greater than a second threshold value and comprises an image of an item to be recommended by adopting the first generation countermeasure network.
Optionally, in the article recommendation method based on brain wave recognition, after performing the step of generating a recommendation image including an image of an article to be recommended using the first generation countermeasure network, the method further includes:
acquiring target brain wave data when a user watches the recommended image;
and correcting the recommended image according to the target brain wave data to obtain a corrected recommended image.
Optionally, in the article recommendation method based on brain wave recognition, the article image is a clothing image or an accessory image.
The invention also provides an electronic device, which comprises a memory and a processor, wherein the memory is stored with a computer program, and the computer program is executed by the processor to execute the article recommendation method based on brain wave recognition.
Compared with the prior art, the article recommendation method based on brain wave recognition and the electronic equipment provided by the invention at least have the following beneficial effects:
according to the article recommendation method and the electronic equipment based on the brain wave recognition, the degree of satisfaction of a user on an image to be checked corresponding to the brain wave signal is obtained by analyzing the brain wave signal when the user checks the image to be checked, the image to be checked comprises the article image, a first generation countermeasure network is trained on the basis of the image to be checked and the degree of satisfaction of the user on the image to be checked, a recommended image comprising the article image to be recommended is generated by adopting the first generation countermeasure network and displayed, clothes are recommended according to the preference of the user, and the requirement that the user selects or customizes the clothes according to the requirement of the user is met.
Drawings
The invention will be described in more detail hereinafter on the basis of embodiments and with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating an article recommendation method based on brain wave identification according to an embodiment of the present invention.
Fig. 2 is another flowchart of an article recommendation method based on brain wave recognition according to an embodiment of the present invention.
Fig. 3 is a schematic flowchart of step S120 in fig. 1.
Fig. 4 is a schematic flowchart of step S130 in fig. 1.
Fig. 5 is another flowchart of an article recommendation method based on brain wave identification according to an embodiment of the present invention.
In the drawings, like parts are designated with like reference numerals, and the drawings are not drawn to scale.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the following detailed description of the embodiments of the present invention will be made with reference to the accompanying drawings and the embodiments, so that how to apply technical means to solve the technical problems and achieve the corresponding technical effects can be fully understood and implemented. The embodiments and the features of the embodiments can be combined without conflict, and the technical solutions formed are all within the scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
Referring to fig. 1, an embodiment of the present invention provides an image recommendation method based on brain wave recognition, which is applicable to an electronic device, such as but not limited to a computer, a mobile phone, or a television, and when the method is applied to the electronic device, steps S110 to S140 are performed:
step S110: and acquiring brain wave signals when a user views an image to be viewed.
The images to be checked comprise article images, the number of the images to be checked is multiple, and the article images included in different images to be checked are different.
The article image may be, but not limited to, a clothing image or an ornament image, for example, the article image may be a garment, a skirt, trousers, or shoes, and may be an ornament such as a hat, an ear stud, a hair clip, or a necklace, which is not specifically limited herein, and may be set according to actual requirements.
It can be understood that the objects corresponding to the object images included in the images to be viewed should belong to the same type, that is, have the same attribute, and for example, the objects may belong to a relatively small category such as a hat, a garment, a skirt, trousers, an earring, or a necklace, or may belong to a relatively large category such as an accessory or a garment, and the categories are set according to actual requirements, and are not limited specifically herein.
The image to be viewed may include a body image of the user and an article image, or may only include an article image, which is not specifically limited herein and may be set according to actual requirements.
Optionally, in this embodiment, the image to be viewed includes a body image of the user and an item image, and before the step of S110 is performed, the method further includes: and acquiring an image to be checked.
The mode of acquiring the image to be viewed may be as follows: the method comprises the steps of acquiring an image acquired by an image acquisition device when a user wears an article, taking the image as an image to be checked, acquiring a body image and an article image of the user, synthesizing the article image and the body image of the user to obtain the user image, taking the user image as the image to be checked, acquiring body features and a clothes image of the user, synthesizing the image to be checked according to the body features and the clothes image, setting according to actual requirements, and omitting specific details.
When the user tries on clothes at the brick-and-mortar store to make the identification recommendation based on the tried-on clothes, before performing step S110, the method further includes: and obtaining a user image when the user wears different articles, and taking the user image as an image to be viewed.
Specifically, the step of obtaining the user image when the user wears different articles and taking the user image as the image to be checked may specifically be receiving the user image when the user wears different articles and collected by the image collecting device, and taking the user image as the image to be checked. It can be understood that the image to be viewed by the user may be the image acquired by the image acquisition device, or the image when the user looks at the user wearing the article displayed in the mirror, and it can be understood that when the user looks at the image in the mirror, the image to be viewed acquired by the image acquisition device should be consistent with the image displayed in the mirror.
When the image to be viewed is synthesized from the body image of the user and the article image, the article image may be an article image required by any user, or an article image corresponding to an article recommended by a designer according to a purchase record of the article image or based on posture information and the like in the body image of the user, and is not particularly limited herein. The synthetic method may be a synthetic method using a generated countermeasure network or an image synthesis algorithm, which is not specifically limited herein and may be set according to actual requirements.
Specifically, referring to fig. 2, before executing step S110, the method further includes steps S210 to S240:
step S210: a training sample set is obtained.
Wherein the training sample set comprises a body sample image, an object sample image and a user target image.
It is to be understood that the body sample image is an image of a body of a user, the object sample image is an image of a different color and/or style of clothing accessories, and the target image of the user is an image of the user wearing the article, and the image includes the object sample image.
Step S220: training a second generative confrontation network from the body sample image, object sample image, and user target image.
Wherein the second generation countermeasure network comprises a feature detector and an image generator which are in countermeasure with each other, and the feature detector and the image generator are used for synthesizing the body sample image and the object sample image into the user image.
Step S230: a body image of a user and a plurality of item images are obtained.
The article image may be an image of an article designed and/or matched by a user sending a body image of the user to a professional clothing matching expert such as a clothing store owner and a big data "expert system" model so as to match similarity between the physical characteristics of the user and the purchase record of the user and similar user requirements, or an image of any article that the user needs to try to wear.
Step S240: and synthesizing the body image and the article image by adopting a second generation countermeasure network to obtain a user image when the article corresponding to the article image is worn on the user, and taking the user image as an image to be viewed.
By adopting the second generation countermeasure network for synthesis, the authenticity and the reliability of the obtained image to be checked are effectively ensured, so that the image of the user to be checked is consistent with the image of the real user wearing the article, and the user can conveniently obtain more real and accurate electroencephalogram data according to the image to be checked.
Step S120: and analyzing the brain wave signals aiming at each brain wave signal to obtain the satisfaction degree of the user on the image to be checked corresponding to the brain wave signals.
The method for identifying the brain wave signal to obtain the satisfaction degree of the user on the image to be checked corresponding to the brain wave signal may be: the satisfaction degree of the user on the image to be checked corresponding to the brain wave signal is obtained according to the pre-stored corresponding relation between the brain wave signals of different frequency bands and different satisfaction degrees, or the satisfaction degree corresponding to the brain wave signals is obtained by adopting a neural network algorithm for brain wave signal identification, wherein the neural network algorithm can be used for generating an antagonistic network, is not specifically limited, and can be set according to actual requirements.
In general, the satisfaction of the user on the article generally includes satisfaction on the style of the article and satisfaction on the color of the article, and in order to ensure the reliability of the obtained satisfaction, referring to fig. 3, in this embodiment, the step S120 includes steps S121 to S123.
Step S121: and analyzing the brain wave signals to obtain the style satisfaction and the color satisfaction of the user on the object image in the image to be checked corresponding to the brain wave signals.
Step S122: obtaining a first weight value of style satisfaction of the item image and a second weight value of color satisfaction of the item image.
The first weight value and the second weight value may be obtained by user input or calculation according to a Loss function, and when the Loss function is obtained by calculation, for example, a Loss function Loss may be set, where predict is w1Sface + w2 seg, Sface is an expression parameter value, seg is a psychological state parameter value, w1 is a weight coefficient of style satisfaction, and w2 is a weight coefficient of color satisfaction, and by obtaining the actual satisfaction prediction of the user, the actual satisfaction is directly obtained through data finally obtained after an experimenter fills a real self-assessment table; according to the actual satisfaction, coefficients w1 and w2 corresponding to the minimum Loss function Loss value are obtained, and initial values of w1 and w2 are obtained; covering the obtained initial values of w1 and w2 with the original values of w1 and w2 respectively, and updating the Loss function Loss; performing iterative update processing on the updated Loss function Loss through a random gradient descent algorithm, and continuously updating the Loss function Loss in an iterative manner until the minimized Loss function Loss is obtained; and obtaining coefficients w1 and w2 corresponding to the minimum value of the minimized Loss function Loss to obtain final values w1 and w2, wherein the final value w1 is used as a final weight coefficient of the style satisfaction degree, and the final value w2 is used as a final weight coefficient of the color satisfaction degree.
Step S123: and obtaining the satisfaction degree of the user to the image to be checked according to the style satisfaction degree of the item image, the color satisfaction degree of the item image, the first weight value and the second weight value.
In step S123, the satisfaction of the user with the image to be viewed may be obtained according to a sum of a product of the style satisfaction of the item image and the first weight and a product of the color satisfaction of the item image and the second weight.
Step S130: training a first generation countermeasure network based on the image to be viewed and user satisfaction with the image to be viewed.
The first generation countermeasure network may be generated by training based on all images to be viewed and corresponding satisfaction degrees, or generated by training based on images to be viewed whose satisfaction degrees are greater than a first preset threshold value in all images to be viewed, where no specific limitation is made and the generation is set according to actual requirements.
Referring to fig. 4, optionally, in the present embodiment, the step S130 includes a step S132 and a step S134.
Step S132: and acquiring the image to be checked with the satisfaction degree greater than a first threshold value in the image to be checked as a target image to be checked.
And the size of the first threshold is not specifically limited again, and the first threshold can be set according to actual requirements. It can be understood that the above manner may be that the color satisfaction and the style satisfaction in the acquired image to be viewed are respectively greater than a first threshold, or that the satisfaction of the image to be viewed is greater than a first threshold.
Step S134: and training a first generation countermeasure network according to the target images to be checked and the satisfaction corresponding to each target image to be checked.
Through the arrangement, the image generated by the first generation countermeasure network is adopted as the image with higher user satisfaction, and the reliability of the generated image can be improved.
Step S140: and generating a recommendation image comprising an image of the item to be recommended by adopting the first generation countermeasure network, and displaying the recommendation image.
It can be understood that, when the first generation countermeasure network generates the recommended image, the satisfaction degree corresponding to the recommended image can also be obtained.
In order to make the recommended image generated by using the first generation countermeasure network be an image with high user satisfaction, in this embodiment, the step S140 may specifically be: and generating a recommendation image which has satisfaction degree greater than a second threshold value and comprises an image of an item to be recommended by adopting the first generation countermeasure network.
The size of the second threshold may be greater than the first threshold, and is not specifically limited herein, and may be set according to actual requirements.
Referring to fig. 5, in order to adjust the recommended image when the user is not satisfied with the recommended image, in this embodiment, after step S140 is executed, the method further includes:
step S310: and acquiring target brain wave data when the user watches the recommended image.
Step S320: and correcting the recommended image according to the target brain wave data to obtain a corrected recommended image.
Wherein, the step S320 may specifically be: analyzing the target brain wave data to obtain the color satisfaction degree and style satisfaction degree of the user to the recommended image, and adjusting the color and/or style of the recommended image according to the color satisfaction degree and/or the style satisfaction degree when the satisfaction degree is smaller than a second threshold value, so that the adjusted object image meets the requirements and preferences of the user.
It is understood that the above-mentioned correction of the recommended image may be performed in a loop manner, for example, after step S320 is performed, the corrected recommended image is taken as a new recommended image, and steps S310-S320 are returned to be performed until the analyzed degree of satisfaction of the user on the recommended image is greater than the second threshold. Through the arrangement, the object with higher customer satisfaction can be recommended to the user.
On the basis, the invention further provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the information sharing method based on image recognition is executed.
The memory and the processor are electrically connected to each other directly or indirectly to enable data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines.
The Memory may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The processor may be an integrated circuit chip having signal processing capabilities. The Processor may also be a general-purpose Processor, such as a Central Processing Unit (CPU), a Network Processor (NP), a microprocessor, etc.; but may also be a Digital Signal Processor (DSP)), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components; the processor may also be any conventional processor that may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention.
The electronic device may be, but is not limited to, a mobile phone, a computer, a television, or a tablet computer, and is not specifically limited herein, and may be set according to actual requirements.
Since the electronic device can execute the article recommendation method based on brain wave recognition, the electronic device has the same or corresponding technical features and can achieve the same or corresponding technical effects as the information sharing method based on image recognition, and details are not repeated here.
In summary, the information sharing method and the electronic device based on image recognition provided by the present invention obtain the brain wave signal when the user views the image to be viewed, wherein the image to be checked comprises a plurality of object images, different images to be checked comprise different object images, and for each brain wave signal, analyzing the brain wave signal to obtain the satisfaction degree of a user on an image to be checked corresponding to the brain wave signal, training a first generation countermeasure network based on the image to be checked and the satisfaction degree of the user on the image to be checked, generating a recommendation image including an image of an item to be recommended by using the first generation countermeasure network and displaying the recommendation image, the clothes are recommended according to the preference of the user, so that the requirement that the user selects or customizes the clothes according to the requirement of the user is met. Furthermore, the target electroencephalogram data when the user watches the recommended image is obtained, and the recommended image is corrected according to the target electroencephalogram data to obtain the corrected recommended image, so that the satisfaction degree of the user on the obtained corrected recommended image is further higher, and the requirements of the user are further met.
In the embodiments provided in the present invention, it should be understood that the disclosed system and method can be implemented in other ways. The system and method embodiments described above are merely illustrative.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Although the embodiments of the present invention have been described above, the above descriptions are only for the convenience of understanding the present invention, and are not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. An article recommendation method based on brain wave recognition, the method comprising:
the method comprises the steps of obtaining brain wave signals when a user views images to be viewed, wherein the images to be viewed comprise article images, the images to be viewed comprise a plurality of images, and different images to be viewed comprise different article images;
analyzing the brain wave signals aiming at each brain wave signal to obtain the satisfaction degree of a user on the image to be checked corresponding to the brain wave signals;
training a first generation countermeasure network based on the image to be viewed and user satisfaction with the image to be viewed;
and generating a recommendation image comprising an image of the item to be recommended by adopting the first generation countermeasure network, and displaying the recommendation image.
2. The brain wave recognition-based item recommendation method according to claim 1, wherein before the step of obtaining the brain wave signal of the user viewing each image to be viewed is performed, the method further comprises:
and obtaining a user image when the user wears different articles, and taking the user image as an image to be viewed.
3. The brain wave recognition-based item recommendation method according to claim 1, wherein before the step of obtaining the brain wave signal of the user viewing each image to be viewed is performed, the method further comprises:
obtaining a body image and a plurality of item images of a user;
and synthesizing the body image and the article image by adopting a second generation countermeasure network to obtain a user image when the article corresponding to the article image is worn on the user, and taking the user image as an image to be viewed.
4. The brain wave recognition-based item recommendation method according to claim 3, wherein before performing the step of obtaining the body image of the user and the plurality of item images, the method further comprises:
acquiring a training sample set, wherein the training sample set comprises a body sample image, an object sample image and a user target image;
training a second generation countermeasure network according to the body sample image, the object sample image and the user target image, wherein the second generation countermeasure network comprises a feature detector and an image generator which are in mutual countermeasure, and the feature detector and the image generator are used for synthesizing the body sample image and the object sample image into the user image.
5. The brain wave recognition-based item recommendation method according to claim 1, wherein training the first generation countermeasure network based on the image to be viewed and the satisfaction of the image to be viewed includes:
acquiring an image to be viewed with satisfaction greater than a first threshold value in the image to be viewed as a target image to be viewed;
and training a first generation countermeasure network according to the target images to be checked and the satisfaction corresponding to each target image to be checked.
6. The brain wave recognition-based item recommendation method according to claim 1, wherein the step of analyzing the brain wave signal to obtain the user's satisfaction with the image to be viewed corresponding to the brain wave signal comprises:
analyzing the brain wave signals to obtain the style satisfaction and the color satisfaction of the user to the object images in the images to be checked corresponding to the brain wave signals;
obtaining a first weight value of style satisfaction degree of the item image and a second weight value of color satisfaction degree of the item image;
and obtaining the satisfaction degree of the user to the image to be checked according to the style satisfaction degree of the item image, the color satisfaction degree of the item image, the first weight value and the second weight value.
7. The brain wave recognition-based item recommendation method according to claim 1, wherein the step of generating a recommendation image including an image of an item to be recommended using the first generation countermeasure network includes:
and generating a recommendation image which has satisfaction degree greater than a second threshold value and comprises an image of an item to be recommended by adopting the first generation countermeasure network.
8. The brain wave recognition-based item recommendation method according to claim 1, wherein after performing the step of generating a recommendation image including an image of an item to be recommended using the first generation countermeasure network, the method further comprises:
acquiring target brain wave data when a user watches the recommended image;
and correcting the recommended image according to the target brain wave data to obtain a corrected recommended image.
9. The brain wave identification-based item recommendation method according to claim 1, wherein the item image is a clothing image or an accessory image.
10. An electronic device, characterized by comprising a memory and a processor, wherein the memory stores a computer program, and the computer program is executed by the processor to execute the brain wave identification-based item recommendation method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910792565.0A CN112435083A (en) | 2019-08-26 | 2019-08-26 | Article recommendation method based on brain wave recognition and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910792565.0A CN112435083A (en) | 2019-08-26 | 2019-08-26 | Article recommendation method based on brain wave recognition and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112435083A true CN112435083A (en) | 2021-03-02 |
Family
ID=74690247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910792565.0A Pending CN112435083A (en) | 2019-08-26 | 2019-08-26 | Article recommendation method based on brain wave recognition and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112435083A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073284A (en) * | 2017-12-15 | 2018-05-25 | 南京信息工程大学 | Purchase system based on brain wave identification mood |
| CN108829855A (en) * | 2018-06-21 | 2018-11-16 | 山东大学 | It is worn based on the clothing that condition generates confrontation network and takes recommended method, system and medium |
| CN109509056A (en) * | 2018-10-16 | 2019-03-22 | 平安科技（深圳）有限公司 | Method of Commodity Recommendation, electronic device and storage medium based on confrontation network |
| CN109657156A (en) * | 2019-01-22 | 2019-04-19 | 杭州师范大学 | A kind of personalized recommendation method generating confrontation network based on circulation |
| WO2019153972A1 (en) * | 2018-02-11 | 2019-08-15 | Oppo广东移动通信有限公司 | Information pushing method and related product |
-
2019
- 2019-08-26 CN CN201910792565.0A patent/CN112435083A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073284A (en) * | 2017-12-15 | 2018-05-25 | 南京信息工程大学 | Purchase system based on brain wave identification mood |
| WO2019153972A1 (en) * | 2018-02-11 | 2019-08-15 | Oppo广东移动通信有限公司 | Information pushing method and related product |
| CN108829855A (en) * | 2018-06-21 | 2018-11-16 | 山东大学 | It is worn based on the clothing that condition generates confrontation network and takes recommended method, system and medium |
| CN109509056A (en) * | 2018-10-16 | 2019-03-22 | 平安科技（深圳）有限公司 | Method of Commodity Recommendation, electronic device and storage medium based on confrontation network |
| CN109657156A (en) * | 2019-01-22 | 2019-04-19 | 杭州师范大学 | A kind of personalized recommendation method generating confrontation network based on circulation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110021061B (en) | Collocation model construction method, clothing recommendation method, device, medium and terminal | |
| CN111681070B (en) | Online commodity purchasing method, purchasing device, storage device and purchasing equipment | |
| US20140032359A1 (en) | System and method for providing intelligent recommendations | |
| US20160065843A1 (en) | Method and apparatus for creating photo-taking template database and for providing photo-taking recommendation information | |
| CN106462862A (en) | Method and system for improving size-based product recommendations using aggregated review data | |
| US20110295711A1 (en) | Apparel Fit Advisory Service | |
| CN111311373B (en) | Personalized clothing customizing method and device based on consumer social network | |
| CN109242593B (en) | Case reasoning-based clothing recommendation method and device and storage medium | |
| CN105374057A (en) | Virtual try-on apparatus and virtual try-on method | |
| KR102295459B1 (en) | A method of providing a fashion item recommendation service to a user using a date | |
| US20160343054A1 (en) | Image acquisition and feature extraction apparatus, method of feature extraction and feature identification, and method for creating and providing advertisement content | |
| KR20100026981A (en) | Real identification system of clothing and body trinket wearing system and method | |
| JP6916095B2 (en) | Server and product provision system | |
| KR20220169663A (en) | System and method for operating a service platform that recommends fashion coordination based on artificial intelligence | |
| CN112435083A (en) | Article recommendation method based on brain wave recognition and electronic equipment | |
| JP2018173704A (en) | Information provision system, information provision method, and program | |
| KR102200038B1 (en) | A method of providing a fashion item recommendation service to a user using a date | |
| KR102179916B1 (en) | Coordination providing system using data collected from smart mirror | |
| KR20090077032A (en) | Method for recommending style coordinate using wireless recognition | |
| KR20090003507A (en) | System and method for recommending style coordinate goods using wireless recognition and program recording medium | |
| CN113393304A (en) | Garment customization method and device | |
| CN108596702A (en) | A kind of display methods of arranging effect, system and terminal device | |
| CN115526675A (en) | Clothing recommendation method and equipment | |
| KR20090074720A (en) | Program recording medium | |
| US20200193502A1 (en) | Recommendation engine for clothing selection and wardrobe management |
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 |