WO2017005014A1

WO2017005014A1 - Method and device for searching matched commodities

Info

Publication number: WO2017005014A1
Application number: PCT/CN2016/077392
Authority: WO
Inventors: 周小丽
Original assignee: 中兴通讯股份有限公司
Priority date: 2015-07-09
Filing date: 2016-03-25
Publication date: 2017-01-12
Also published as: CN106339390A

Abstract

Embodiments of the present invention provide a method and device for searching matched commodities. The method comprises: acquiring human body characteristic data about a user; establishing a human body model about the user according to the human body characteristic data; and matching corresponding commodities for the human body model according to the human body characteristic data. The embodiments of the present invention resolve the problem of low efficiency of searching matched commodities during a shopping process in the related art.

Description

Method and device for searching matching products

Technical field

The present application relates to the field of electronic commerce, for example, to a method and apparatus for searching for matching products.

Background technique

With the rise and boom of e-commerce, users are increasingly demanding for the humanization and intelligence of e-shopping. Related online shopping can't give users a sense of reality. Users can't try on clothes personally. They can only choose the model photos and clothing sizes provided by the sellers of the e-commerce platform, so the selected clothes often have a certain discrepancy with themselves. The e-commerce platform provides a mechanism for returning goods (such as seven days no reason to return, etc.), or it is difficult to avoid waste of logistics resources and time.

The online shopping selection process is cumbersome. Usually, the e-commerce platform's shopping process includes that after the user enters the store, the user can see pictures of the goods (such as models tried on) and a small amount of text description on the list page. The user selects among a series of products. After you have your favorite products, you need to click on the corresponding position of the product and then go to the product details page to view the size, color, and the different angles of the model. If you don't fit, you need to exit the product details page and continue to select other products. This has been repeated many times, which inevitably hurts the user's interest and wastes the user's time, so the user is in urgent need of a more humane online shopping experience.

However, there is currently no solution to the problem of the cumbersome shopping process and the inefficiency of searching for matching products during the shopping process in the relevant online shopping platform.

Summary of the invention

The embodiment of the invention provides a method and a device for searching for matching commodities, so as to at least solve the problem that the related products in the related art search for matching products are inefficient.

An embodiment of the present invention provides a method for searching for a matching product, including: acquiring human body feature data of the user; creating a human body model of the user according to the human body feature data; and matching the human body model according to the human body feature data Corresponding goods.

Optionally, the acquiring the human body feature data of the user includes: scanning the user by using a multimedia device to obtain scan data of the user; and performing 3D human body scanning technology and/or biometric identification In other techniques, the scan data is identified to generate human body feature data.

Optionally, the acquiring the human body feature data of the user includes: collecting the user's picture file and/or the parameter information of the user body in the video file; analyzing the parameter information to generate the human body feature by using an image and/or video analysis technology data.

Optionally, the matching the merchandise according to the human body feature data for the human body model comprises: searching for an item matching the human body feature data according to a preset algorithm; and using the 3D mapping technology to The picture is attached to the mannequin.

Optionally, the preset algorithm includes at least one of the following: a content filtering recommendation algorithm, a collaborative filtering recommendation algorithm, and a hybrid recommendation algorithm.

Optionally, after matching the corresponding product to the human body model according to the human body feature data, the method further includes: receiving a first instruction of the user, and switching the human body model according to the first instruction An application scenario; and/or receiving a second instruction of the user, and switching the shape of the mannequin according to the second instruction.

In addition, the embodiment of the present invention further provides an apparatus for searching for a matching product, comprising: an acquiring module, configured to acquire human body feature data of the user; and a creating module, configured to create the human body model of the user according to the human body feature data; The matching module is configured to match the human body model with the corresponding product according to the human body feature data.

Optionally, the acquiring module includes: a scanning unit configured to scan the user by using a multimedia device to obtain scan data of the user; and the first generating unit is configured to pass 3D human body scanning technology and/or biometrics The identification technique identifies the scan data to generate human body feature data.

Optionally, the acquiring module further includes: an acquiring unit, configured to collect parameter information of the user body in the picture file and/or the video file of the user; the second generating unit is configured to analyze by using image and/or video analysis technology The parameter information generates the human body feature data.

Optionally, the matching module includes: a searching unit, configured to search for an item that matches the human body feature data according to a preset algorithm; and the mapping unit is configured to paste the picture of the product in the 3D mapping technology On the human body model.

The embodiment of the invention further provides a computer readable storage medium storing computer executable instructions for performing the above method.

Embodiments of the present invention also provide an apparatus including one or more processors, a memory, and one or more programs, the one or more programs being stored in a memory when executed by one or more processors , perform the above method.

The embodiment of the present invention takes the human body feature data of the user, creates the human body model of the user according to the human body feature data, and obtains a human body model that is proportional to the user, and then uses the obtained human body feature data as the human body model. Matching the corresponding products, achieving the purpose of streamlining the shopping process, accurately matching the products, solving the problem of low efficiency of searching for matching products in the related technology in the related technology, thereby achieving the effect of improving the user shopping experience.

DRAWINGS

1 is a flow chart of a method of searching for matching merchandise in accordance with an embodiment of the present invention;

2 is a structural block diagram of an apparatus for searching for matching merchandise according to an embodiment of the present invention;

3 is a structural block diagram 1 of an apparatus for searching for matching merchandise according to an embodiment of the present invention;

4 is a structural block diagram 2 of an apparatus for searching for matching merchandise according to an embodiment of the present invention;

5 is a structural block diagram 3 of an apparatus for searching for matching merchandise according to an alternative embodiment of the present invention;

6 is a flow chart showing a method of searching for matching merchandise according to an alternative embodiment of the present invention;

FIG. 7 is a schematic flowchart of a method for searching for matching products in an application scenario according to an alternative embodiment of the present invention.

FIG. 8 is a schematic structural diagram of a hardware of a device according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings, which are a part of the embodiments of the present invention, but not all of the embodiments.

The present application will be described in detail below with reference to the drawings in conjunction with the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict.

It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or order.

In this embodiment, a method for searching for a matching product is provided. In the embodiment of the present invention, the method for searching for a matching product may be completed by using an e-commerce platform. Optionally, the e-commerce platform may be installed in a shopping terminal, and the shopping is performed. Terminals include, but are not limited to, mobile terminals (such as cell phones, PADs, etc.) and notebook computers. In addition, the method can be jointly performed by the e-commerce platform and the server, wherein the e-commerce platform sends the acquired human body characteristic data to the server end, and receives the commodity information returned by the server corresponding to the human body feature data.

1 is a flow chart of a method for searching for matching merchandise according to an embodiment of the present invention. As shown in FIG. 1, the method includes:

Step S102, acquiring human body feature data of the user;

In this embodiment, the human body feature data may be, but is not limited to, one or more of the following user body information: the user's height, circumference, shoulder width, skin color, head circumference, wrist size, foot length, and pupil distance. , nose height, hair style, width and height. In different shopping scenarios, the human body data acquired by the e-commerce platform may be different. For example, when the user selects a watch on the Internet, the e-commerce platform may only use information such as the size of the user's wrist and the skin color; and when purchasing the shirt, the e-commerce platform Get information about the user's height, measurements, shoulder width, skin tone, and hairstyle.

Optionally, the human body feature data may be acquired by using an e-commerce platform in real time, or may be obtained from a pre-set database for storing human body characteristic data through an e-commerce platform.

Optionally, if the human body feature data is acquired by real-time acquisition by the e-commerce platform, after the human body feature data is collected in real time, the e-commerce platform may also determine whether the human body characteristic data of the user has been stored in the database, and if the The human body characteristic data of the user is different from the human body characteristic data of the user collected in real time, and the e-commerce platform updates the human body characteristic data of the user in the database.

Step S104, creating a human body model of the user according to the human body feature data;

Optionally, the e-commerce platform performs 3D modeling according to the acquired human body feature data to form a three-dimensional image, thereby creating a human body model. Optionally, in the corresponding shopping scene, the human body model may be in addition to the entire 3D human body model. Other small models, such as the model of the head, the model of the upper limb, and so on. At the same time, in order to achieve the authenticity of shopping and achieve the immersive effect, the human body model can be the size of the user or the body, or a certain proportion.

Step S106, matching the corresponding product to the human body model according to the human body feature data;

According to the obtained human body characteristic data, first, the e-commerce platform can obtain the commodity parameter information corresponding to the human body characteristic data (such as the size of the product, the color of the product, the style of the product, etc.), and then the e-commerce platform obtains the parameter information of the product from the database. Matching items.

For example, when the user purchases the top coat, the e-commerce platform obtains the human body characteristic data: height (170cm), measurements (84cm, 62cm, 86cm), shoulder width (80cm), skin color (white), hairstyle (plate size), electricity. Based on the height, measurements and shoulder width data, the platform initially determines the size of the top as the M code and the style as the self-cultivation. According to the skin color data, the color of the top is determined to be dark. Therefore, the e-commerce platform obtains a top that matches the size, style or color of the above-mentioned top from the database. According to the searched top and top parameter information (the parameter information of the top includes the size of M code, the style is slim and the color is dark), the tops are displayed in order from high to low, which is recommended for the human body model.

The matching degree between the top and the top parameter information may refer to the degree that the top meets the parameter information of the top. The high matching degree of the top may refer to the degree of meeting the parameter information of the top, and the low matching degree of the top may refer to the parameter information of the top. The degree is low. For example, when the top coat simultaneously satisfies the size parameter, the style parameter and the color parameter of the top garment, it is determined that the top garment has the highest matching degree; when the top garment satisfies at least two of the top garment parameters, it is determined that the top garment has a medium matching degree; When only one of the parameters of the top is satisfied, it is determined that the matching degree of the top is the lowest.

According to the embodiment of the present invention, the human body feature data of the user is acquired, the human body model of the user is created according to the human body feature data, and a human body model that is proportional to the user is obtained, and the corresponding human body model is matched according to the acquired human body feature data. The purpose of streamlining the shopping process, accurately matching the products, solving the problem that the related technology searches for matching products in the shopping process is low, and the effect of improving the user shopping experience is achieved.

In an optional implementation manner of this embodiment, the step S102 in the embodiment obtains the human body feature data of the user, which can be implemented as follows:

Among them, the first method includes:

S11. Scan the user through the multimedia device to obtain scan data of the user.

The multimedia device can be a camera and a scanner provided by the shopping terminal, such as a camera and a scanner of a computer and a mobile phone, or a camera or a scanner connected to the shopping terminal, such as a 3D human body sweep. The scanner, the e-commerce platform scans the user through the camera of the shopping terminal or the 3D body scanner to obtain the scan data of the user.

S12. Identify the scan data to generate human body feature data by using a 3D human body scanning technology and/or a biometric recognition technology.

The e-commerce platform can digitally process the scan data of the user obtained by the S11 through the 3D human body scanning technology or the biometric recognition technology, and analyze and obtain the human body feature data, such as the contour data of the user obtained by the contour recognition technology. The scan data may refer to real data of the user, such as the user's real height, measurements, etc.; optionally, the scan data may be digitized to obtain human body feature data suitable for generating a three-dimensional human body model, and the human body feature data may be Scanned data after a certain scaling.

Mode 2 includes:

S21. Collect parameter information of a user body in a picture file and/or a video file of the user;

The picture file and the video file are already stored by the shopping terminal, or the user has uploaded or temporarily uploaded. In this way, in the case that the shopping terminal does not have a multimedia device, the e-commerce platform can also obtain the user's parameter information according to the user's picture file and/or video file.

S22: Analyze parameter information to generate human body feature data by using image and/or video analysis technology.

The image information of the user can be analyzed and digitized by image or video analysis technology to obtain the human body characteristic data of the user.

It should be noted that the first mode and the second mode can be used in combination in the application scenario, and can also be used separately.

In an optional implementation manner of this embodiment, for the step S106 involved in the embodiment, the product corresponding to the human body model matching according to the human body feature data may be implemented by:

S31. Search for an item that matches the human body characteristic data according to a preset algorithm;

In this embodiment, the product parameters (such as product size, style, color, etc.) matching the human body characteristic data are first obtained according to the human body characteristic data, and then the product corresponding to the product parameter information is searched according to the parameter information of the product, and Recommend the searched items to the user in turn.

In the specific search and recommendation process, content filtering recommendation algorithms, such as proximity algorithms, may be employed. (k-Nearest Neighbor, abbreviated as KNN), a preset algorithm such as a collaborative filtering recommendation algorithm and a hybrid recommendation algorithm to achieve matching of human characteristic data and commodity parameters, determining commodities according to commodity parameters, and the e-commerce platform is based on the matching degree Sort the items in order from high to low.

Optionally, a threshold may be set, and the product whose matching degree exceeds the threshold is recommended to the user, and the product whose matching degree is lower than the threshold is analyzed, and the reason for the incomplete matching is obtained for the user to refer to.

S32, the picture of the product is attached to the human body model through the 3D texture technology.

Among them, through the 3D mapping technology, the pictures of the goods are attached to the created mannequin from different angles and directions according to the dimensions of the human body model, thereby realizing an intuitive and comprehensive display.

In an optional implementation manner of this embodiment, after matching the product to the human body model according to the human body feature data, the method may further include:

Step S41: Receive a first instruction of the user and switch an application scenario of the human body model according to the first instruction.

In this embodiment, the application scene of the created human body model can be switched by using the 3D background mapping technology, and the application scene such as the background image, the scene picture, and the effect diagram are used to achieve the try-on effect in different scenarios.

In another optional implementation manner of this embodiment, after the human body model is matched with the product according to the human body feature data, the method further includes:

Step S51, receiving a second instruction of the user and switching the modeling of the human body model according to the second instruction.

In this embodiment, the 3D animation technology can be used to realize the movement and posture of the hand lifting, the lower jaw, the turning body, etc., thereby switching the shape of the human body model, and the user can see the wearing effect under different movements and shapes.

Through the description of the above embodiments, those skilled in the art can clearly understand that the method of the embodiment can be implemented by means of software plus a necessary general hardware platform, and can also be implemented by hardware. Based on the understanding, the technical solution of the embodiment of the present invention may be embodied in the form of a software product stored in a non-volatile storage medium (such as a ROM/RAM, a magnetic disk, an optical disk), including instructions. The method of the embodiment of the present application is executed in such a manner that a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.).

In this embodiment, a matching device based on human body characteristic data is also provided, and the following uses The term "module" can implement a combination of software and/or hardware for a predetermined function. The apparatus described in the following embodiments is optionally implemented in software, but the apparatus may also be implemented in hardware, or a combination of software and hardware.

2 is a structural block diagram of an apparatus for searching for matching merchandise according to an embodiment of the present invention. As shown in FIG. 2, the apparatus includes:

The obtaining module 20 is configured to acquire human body feature data of the user;

In this embodiment, the human body feature data may be, but is not limited to, one or more of the following user body information: the user's height, circumference, shoulder width, skin color, head circumference, wrist size, foot length, and pupil distance. , nose height, hair style, width and height. In different shopping scenarios, the human body feature data acquired by the acquisition module 20 may be different. For example, when the user selects a watch on the Internet, the e-commerce platform may only obtain information such as the size of the user's wrist and the skin color; and when purchasing the shirt, the e-commerce platform acquires User's height, measurements, shoulder width, skin tone and hairstyle.

Optionally, the human body feature data may be acquired by using an e-commerce platform in real time, or may be obtained from a pre-set database for storing human body characteristic data through an e-commerce platform. If the human body feature data is acquired through real-time acquisition, after the human body feature data is collected in real time, it can also be determined whether the human body feature data of the user has been stored in the database, if the human body feature data of the user already exists and is collected in real time. If the human body characteristic data is different, the human body characteristic data of the user in the database is updated.

The creating module 22 is coupled to the acquiring module 20 and configured to create a human body model of the user according to the human body feature data;

The creation module 22 performs 3D modeling according to the human body feature data acquired by the acquisition module 20 to form a three-dimensional stereo image, thereby creating a human body model. Optionally, in a specific shopping scenario, the human body model may be in addition to the entire 3D. Other small models outside the human body model, such as the model of the head, the model of the upper limbs, etc. At the same time, in order to achieve the realism of shopping and achieve the immersive effect, the human body model can be the size of the user or the real person, or In a certain proportion.

The matching module 24 is coupled to the creation module 22 and configured to match the corresponding product to the human body model according to the human body feature data.

According to the human body feature data acquired by the acquisition module 20, first, product parameter information corresponding to the human body feature data (such as the size of the product, the color of the product, the style of the product, etc.) can be obtained, and then the e-commerce platform is The target item that matches the parameter information of the item is obtained in the database.

For example, in the process of purchasing the tops, the human body data obtained by the e-commerce platform are: height (170cm), measurements (84cm, 62cm, 86cm), shoulder width (80cm), skin color (white), hairstyle (plate size), matching The module 24 initially determines the size of the top as the M code and the style as the self-cultivation based on the height, measurements and shoulder width data, and initially determines the color of the top as a dark color based on the skin color data. Therefore, the e-commerce platform obtains the target tops matching the size, style or color of the above-mentioned tops from the database, and displays the target tops in order from high to low according to the matching degree of the target tops and the tops, and the human body model is displayed. recommend. In this embodiment, the acquiring module 20 acquires the human body feature data of the user, and the creating module 22 creates a human body model of the user according to the human body feature data, and obtains a human body model that is proportional to the user, and then the matching module 24 uses the human body characteristic data obtained as the human body. The model matches the corresponding merchandise, realizes the purpose of streamlining the shopping process, accurately matching the merchandise, and solving the problem that the related technology searches for matching products in the shopping process with low efficiency, thereby achieving the effect of improving the user shopping experience.

FIG. 3 is a block diagram of an optional structure of an apparatus for searching for matching merchandise according to an embodiment of the present invention. As shown in FIG. 3, the apparatus further includes: a scanning unit 30, in addition to all the modules shown in FIG. First generating unit 32,

The scanning unit 30 is configured to scan the user by using the multimedia device to obtain scan data of the user.

The multimedia device can be a camera and a scanner provided by the shopping terminal, such as a camera and a scanner of a computer and a mobile phone, or a camera or a scanner connected to the computer end, such as a 3D body scanner, the scanning unit 30 through the camera or 3D. The body scanner scans the user to get the user's scan data.

The first generating unit 32 is coupled to the scanning unit 30 and configured to identify the scan data of the user by using a 3D human body scanning technology and/or a biometric recognition technology to generate human body feature data.

Optionally, for the scan data scanned by the scanning unit 30, the first generating unit 32 may digitally process the result of the 3D human body scan or the biometric recognition by using a 3D human body scanning technology or a biometric recognition technology, and analyze and obtain the human body characteristic data. The contour data of the user's face is obtained by contour recognition technology.

FIG. 4 is a block diagram of an optional structure of an apparatus for searching for matching merchandise according to an embodiment of the present invention. As shown in FIG. 4, the apparatus further includes: an acquisition unit 40, in addition to all the modules shown in FIG. a second generating unit 42;

The collecting unit 40 is configured to collect parameter information of the user's body in the picture file of the user and/or the video file;

Optionally, the picture file and the video file are already stored by the terminal, or the user has uploaded or temporarily uploaded. In this way, the user's parameter information can be obtained from the photo in the case where the shopping terminal does not have a multimedia device.

The second generating unit 42 is coupled to the collecting unit 40 and configured to analyze the parameter information by using image and/or video analysis technology to generate human body feature data.

Optionally, the second generating unit 42 may analyze and digitize the collected parameter information of the user by using a picture or video analysis technology to obtain the human body feature data of the user.

FIG. 5 is a block diagram 3 of an optional structure of an apparatus for searching for matching merchandise according to an embodiment of the present invention. As shown in FIG. 5, the matching module 24 includes: a search unit 50, in addition to all the modules shown in FIG. Mapping unit 52;

The search unit 50 is configured to search for an item that matches the human body feature data according to a preset algorithm;

In this embodiment, the search unit 50 may first obtain the product parameters matching the human body feature data according to the human body feature data, and then search for at least one product according to the product parameters, and sequentially recommend the searched products to the human body model.

In the specific search and recommendation process, content filtering recommendation algorithms, such as proximity algorithm (k-Nearest Neighbor, KNN for short), collaborative filtering recommendation algorithm and hybrid recommendation algorithm, can be used to implement human body characteristic data and commodity parameters. Matching, and sorting the searched products according to the matching degree from high to low. Optionally, a threshold may be set, the products whose matching degree exceeds the threshold is recommended to the user, and the products whose matching degree is lower than the threshold are analyzed. Get the reason for the incomplete match for the user's reference.

The mapping unit 52 is coupled to the search unit 50 and configured to pass the product through the 3D mapping technology. The picture is attached to the mannequin.

Optionally, the mapping unit 52 uses the 3D mapping technology to paste the picture of the product from the different angles and directions to the created mannequin according to the dimensions of the human body model, thereby realizing an intuitive and comprehensive display.

In an optional implementation manner of this embodiment, the device for searching for matching products includes a first switching module 60, in addition to all the modules shown in FIG. 2, and is configured to match the human body model data with the human body model data. Thereafter, the first instruction of the user is received and the application scenario of the human body model is switched according to the first instruction.

In another optional implementation manner of this embodiment, the device for searching for matching products includes a second switching module 70, in addition to all the modules shown in FIG. 2, and is configured to match the human body feature data for the human body model. After the commodity, the second instruction of the user is received and the shape of the human body model is switched according to the second instruction.

In this embodiment, the 3D animation technology can be used to realize the movement and posture of raising the hand, squatting, turning, etc., thereby switching the shape of the human body model, and the user can see the try-on effect of different movements and shapes.

It should be noted that the foregoing modules may be implemented by software or hardware. When the foregoing modules are implemented by hardware, the foregoing modules may be implemented by: the modules are all located in the same processor; or the modules are respectively located in multiple processors. in.

The present solution will be described in detail below in conjunction with the optional embodiments. The acquisition of human trait data is achieved through scanning, contour recognition or image analysis techniques, rather than user input. Through 3D modeling technology, create a “model” that is the same proportion as the user's body shape, instead of choosing from the existing “model” built into the e-commerce platform system. The human body characteristic data is automatically searched for the "wearing" (texture) "model" that best matches the user's clothing, and other similar products are also listed, arranged in order of matching, for the user to select. The user can see how they try on the clothes from a third party's perspective, and can choose different scenes (such as on the street, indoors, parks, etc.) to try on the clothes. Users can raise their hands on the "model". Kneeling, turning, etc., so that the try-on effect can be seen from different angles.

6 is a schematic flowchart of a method for searching for matching merchandise according to an optional application example of the present invention. As shown in FIG. 6, the method includes:

S601: The try-on system in the e-commerce platform is awakened by the user (buyer), that is, the user (buyer) logs into the e-commerce platform through the shopping terminal and enters the try-through system, and then executes S6020 or S6022:

S6020: the try-on system automatically starts the camera of the shopping terminal or the camera or scanner connected to the PC end (such as 3D body scanner), requires the user to scan the whole body or part, obtain the scan data of the user, and then execute S6030;

S6022: The system requires the user to upload a photo or video of the whole body or part of the part, collect the parameter information of the user's body in the photo or video, and then execute S6032;

S6030: The try-through system digitizes the scanned data of the scanned user through 3D human body scanning technology or biometric identification technology (contour recognition);

S6032: The try-through system analyzes the collected parameter information of the user's body through image or video analysis technology to obtain human body characteristic data, and performs digital processing;

S604: The trial-through system searches whether the human body characteristic data of the user already exists in a database (Database, referred to as DB) or detects whether the human body characteristic data of other users in the DB matches the human body characteristic data of the user;

Wherein, the try-on system searches whether the human body feature data of the user already exists in the database, and may include: if the user's human special diagnosis data already exists in the database, when the human body feature data stored in the database and the human body feature acquired in real time When the data is different, the human body characteristic data in the database is updated to the human body characteristic data acquired in real time;

In addition, if the human body feature data of the user does not exist in the database, the human body feature data acquired in real time can be stored in the database, so that the user can select the human body feature data from the database when the next time shopping. .

S605: when the human body feature data does not exist in the DB, save the digitized human body feature data obtained by S6030 or S6032 to the DB of the try-through system;

S606: The try-through system utilizes 3D modeling technology according to the human body characteristic data obtained by S6030 or S6032. Create a three-dimensional model;

S607: The try-through system matches the corresponding target product according to the human body feature data acquired in S604 for the three-dimensional model of the user created in S606;

Optionally, the product matching the user's human body characteristic data is searched by a preset algorithm, and the image of the product is ironed to the user's three-dimensional model through a 3D mapping technology.

The user's human body characteristic data may include information such as the user's height, measurements, shoulder width, skin color, and hairstyle. The try-on system determines the size of the user's suitable product according to the user's height, measurements, shoulder width, and the like, and fits the user. The product size is calculated according to the matching degree (similarity) of all the products in the try-on system, and the products whose matching degree is greater than the preset threshold are determined as the target products, and the target products are arranged in order from the highest to the bottom to form the product list. .

Optionally, the preset algorithm may be limited to any one of the following: a content filtering recommendation algorithm (such as KNN algorithm), a collaborative filtering recommendation algorithm, and a hybrid recommendation algorithm (the content filtering recommendation algorithm may be combined with the collaborative filtering recommendation algorithm) .

S608: When the human body feature data already exists in the DB, the trial wear system passes the previous order result and the comment result (the matching value in the comment) corresponding to the user (user or other user) corresponding to the human body characteristic data in the DB, and cooperates The recommendation algorithm or the hybrid recommendation algorithm is filtered, and the try-through system searches and filters out the target items that match the human body characteristic data, and arranges the target items in order from the highest to the lowest to form a product list.

S609: The try-through system sequentially pastes the picture corresponding to the item in the product list formed by S607 or S608 into the three-dimensional model created by S606 through the 3D texture technology to realize the smart recommendation product;

S610: The try-through system can realize the application scene switching after the 3D model created by S606 through the 3D background mapping technology, so as to facilitate the user to view the try-on effect of the products in different scenes on the three-dimensional model;

S611: The try-on system can change the posture of the three-dimensional model created by the S606 through the 3D animation technology, so that the user can see the try-on effect of the product on the three-dimensional model after the action is added;

S612: If the item recommended by the system intelligently does not meet the user's requirement, the user can select and match the product from the product list, that is, repeat the operations of S610, S611, and S612.

The following is a schematic diagram of a method for searching for matching products in an application scenario according to an alternative embodiment of the present invention, and FIG. 7 is a schematic flowchart of a method for searching for matching products in an application scenario according to an alternative embodiment of the present invention. Show that the method includes:

S701: the buyer logs into the e-commerce platform through a shopping terminal or a PC connected to a camera or a scanner (such as a 3D body scanner);

S702: The buyer selects the favorite merchant shop and clicks the “Try on” button to enter the try-on system;

S703: The try-on system detects whether the shopping terminal has a camera or is connected to the scanner;

S704: When the try-on system detects that the shopping terminal has a camera or a scanner, the try-on system displays on the display screen of the shopping terminal, and the human body characteristic data of the buyer can be obtained by clicking the following button: “scan”, “upload photo/video” ", and shows that you can exit the try-on system by clicking the "Exit System" button;

S705: When the try-on system detects that the shopping terminal has no camera or is not connected to the scanner, the try-on system displays two buttons of “uploading photos/videos” and “exiting the system” on the display screen of the shopping terminal, and simultaneously at the shopping terminal. The display prompts the buyer to scan after the scanner is connected;

S707: When the buyer selects to upload the special feature data by scanning, after the buyer clicks the “scan” button, the shopping terminal enters the scanning phase, and simultaneously displays the “cancel scan” button, and cancels the scanning to exit the scanning phase.

S708: After the buyer scans, the scanning phase ends, the shopping terminal enters the modeling stage, and the human body model is started to be created;

S709: The three-dimensional model of the human body is successfully created, and the display of the shopping terminal displays a three-dimensional human body model with the same body shape as the buyer and wearing the product (the size recommended by the system is recommended to be suitable for the buyer). At the same time, the left side of the human body three-dimensional model shows the parameters (such as size) of the goods worn on the three-dimensional model of the human body, the matching value (such as 98%), the reason for the 2% mismatch (such as the length of the sleeve is 2 cm), and suggestions (such as Recommended to buy).

Optionally, a “Voice Recommendation” button may be set on the display screen of the shopping terminal at the same time. After clicking the button, the above-mentioned product parameters (such as size, style and color) and matching value (such as 98%) are tried on the system. The reason for the mismatch (such as the length of the sleeve is 2 cm) and the suggestion (such as the recommended purchase) are promptly given to the user by voice.

Optionally, the right side of the display screen of the shopping terminal may also be arranged with the matching value from high to low. The list of products, and each item in the item list will show which information of the item is highly suitable for the buyer (such as the color of the product and the buyer's skin suitability).

Optionally, a picture of different application scenes of the three-dimensional model of the human body may be displayed below the display screen of the shopping terminal (the application scene may be indoor, street view, park, etc.);

S710: When the buyer chooses to upload the human body feature data by uploading photos/videos, the buyer selects the “upload photo/video” button, and after the photo/video upload is successful, the try-on system starts to create the human body three-dimensional model, and performs steps. S709;

S711: If the buyer selects the application scene picture below the display screen of the shopping terminal, the background behind the human body three-dimensional model is switched to the selected application scene map;

S712: The buyer can realize the turning, lifting, etc. of the three-dimensional model of the human body by rotating or dragging the arm, so that the three-dimensional model of the human body makes different postures;

S713: If the buyer is satisfied, the order will be placed. If you are not satisfied, you can take off the goods on the 3D model of the human body, re-select other products from the list of products on the right side of the shopping terminal display, and repeat the operations of S711 and S712 until the user is satisfied. Place an order or quit the try-on system;

S714: If the buyer finally does not select a satisfactory product, he may choose to order at the store, or exit the trial-through system of the store and enter another store to re-select, that is, repeat the operations of S702 to S713.

Compared with the current online shopping method, this embodiment provides a more user-friendly, smarter, more concise, and more fun online shopping method for the user, so that the buyer himself can be a "model" and dress himself up. I can enjoy my own wear effect from the perspective of the third party. I can also match different styles of clothing through different application scenarios, and I can try it like in reality, plus the different action effects of the “model”, so that I can purchase the process. I found out whether the goods fit in all aspects. This makes people feel more real and adds to the fun of shopping. In this embodiment, according to the shape characteristics of the buyer, or the previous order result or the comment result of the buyer or other users having the same body shape characteristics as the buyer, the clothing that best matches the buyer is searched through a series of algorithms, and automatically Wearing on the “model”, other parameters will be displayed accordingly, or prompted by the “voice recommendation” function. That is, after the buyer enters the try-on system, he only needs to scan himself or upload his own photos or videos, and then can place an order, which greatly reduces the shopping process and makes the online shopping simple and convenient.

Embodiments of the present invention also provide a storage medium. Optionally, in this embodiment, the foregoing storage medium may be configured to store program code for performing the following steps:

S1, acquiring human body characteristic data of the user;

S2, creating a human body model of the user according to the human body characteristic data;

S3, matching the corresponding human body model with the human body model according to the human body characteristic data.

Optionally, in this embodiment, the foregoing storage medium may include, but is not limited to, a USB flash drive, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, and a magnetic memory. A non-volatile storage medium that can store program code, such as a disc or an optical disc.

For example, the examples in this embodiment may refer to the examples described in the foregoing embodiments and the optional embodiments, and details are not described herein again.

Obviously, those skilled in the art should understand that the above modules or steps can be implemented by a general computing device, which can be concentrated on a single computing device or distributed over a network of multiple computing devices. They may be implemented in program code executable by a computing device, such that they may be stored in a storage device for execution by a computing device, and in some instances, illustrated or described in a different order than those illustrated herein. The steps are either made into integrated circuit modules, or a plurality of modules or steps are made into a single integrated circuit module. The above is only an embodiment of the present invention and is not intended to limit the present invention.

FIG. 8 is a schematic structural diagram of a hardware of a device according to an embodiment of the present invention. As shown in FIG. 8, the device includes:

One or more processors 410, one processor 410 is taken as an example in FIG. 4;

Memory 420;

The device may also include an input device 430 and an output device 440.

The processor 410, the memory 420, the input device 430, and the output device 440 in the device may be connected by a bus or other means, and the bus connection is taken as an example in FIG.

The memory 420 is used as a computer readable storage medium, and can be used to store software programs, computer executable programs, and modules, such as program instructions/modules corresponding to the processing method of high-precision map data in the embodiment of the present invention (for example, FIG. 2 The acquisition module 20, the creation module 22 and the matching module 24) are shown. The processor 410 executes various functional applications and data processing of the server by executing software programs, instructions, and modules stored in the memory 420, that is, a method for processing high-precision map data of the above method embodiments.

The memory 420 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to usage of the terminal device, and the like. Moreover, memory 420 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 420 can optionally include memory remotely located relative to processor 410, which can be connected to the terminal device over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

Input device 430 can be used to receive input digital or character information and to generate key signal inputs related to user settings and function control of the terminal. Output device 440 can include a display device such as a display screen.

The one or more modules are stored in the memory 420, and when executed by the one or more processors 410, perform the following operations:

Obtaining human body characteristic data of the user;

Creating a human body model of the user according to the human body feature data;

The human body model is matched with the corresponding product according to the human body feature data.

Industrial applicability

The e-commerce platform of the embodiment of the invention provides a method for the buyer to search for matching products, and solves the problem that the related products are inefficient in searching for matching products during the shopping process, thereby saving the time for the buyer to search for matching products by electronic shopping, and improving the time. The buyer's e-shopping experience.

Claims

A method of searching for matching items, including:

Obtaining human body characteristic data of the user;

Creating a human body model of the user according to the human body feature data;

The human body model is matched with the corresponding product according to the human body feature data.
The method of claim 1, wherein the obtaining human body feature data of the user comprises:

Scanning the user by using a multimedia device to obtain scan data of the user;

The scan data is identified to generate human body feature data by 3D body scanning technology and/or biometric recognition technology.
The method of claim 1, wherein the obtaining human body feature data of the user comprises:

Collecting parameter information of the user's body in the user's picture file and/or video file;

The parameter information is analyzed by image and/or video analysis techniques to generate the human body feature data.
The method according to claim 1, wherein the matching the corresponding product according to the human body feature data for the human body model comprises:

Searching for an item that matches the human body feature data according to a preset algorithm;

A picture of the product is attached to the mannequin by a 3D mapping technique.
The method according to claim 4, wherein the preset algorithm comprises at least one of the following: a content filtering recommendation algorithm, a collaborative filtering recommendation algorithm, and a hybrid recommendation algorithm.
The method according to claim 1, after the matching the corresponding product to the human body model according to the human body feature data, the method further includes:

Receiving a first instruction of the user, and switching an application scenario of the human body model according to the first instruction; and/or,

Receiving a second instruction of the user, and switching a shape of the human body model according to the second instruction.
A device for searching for matching products, including:

Obtaining a module, configured to obtain human body characteristic data of the user;

Creating a module, configured to create a human body model of the user according to the human body feature data;

The matching module is configured to match the human body model with the corresponding product according to the human body feature data.
The apparatus of claim 7, wherein the obtaining module comprises:

a scanning unit, configured to scan the user by using a multimedia device to obtain scan data of the user;

The first generating unit is configured to identify the scan data to generate human body feature data by using a 3D body scanning technology and/or a biometric recognition technology.
The apparatus of claim 7, wherein the obtaining module comprises:

The collecting unit is configured to collect parameter information of the user body in the picture file of the user and/or the video file;

The second generating unit is configured to analyze the parameter information by image and/or video analysis technology to generate the human body feature data.
The apparatus of claim 7, wherein the matching module comprises:

a search unit configured to search for an item that matches the human body feature data according to a preset algorithm;

The map unit is configured to attach a picture of the product to the mannequin by a 3D mapping technique.
A computer readable storage medium storing computer executable instructions arranged to perform the method of any of claims 1-6.