Online marketplace system

Abstract

An online marketplace system is disclosed, including a network interface, a memory, and a processor. The processor is configured to: receive, from a seller via the network interface, an image, the image being an image of an item listed for sale in the online marketplace system; determine that the image has been altered; in response to determining that the image has been altered, perform the following: send, to the seller via the network interface, a request for an unaltered image; or create, in the online marketplace system, a listing for the item including the image, and reduce a ranking of the created listing to change an order of items displayed to a buyer in response to a search request from the buyer.

Description

[0001] This application is a divisional application of the invention patent application filed on December 19, 2016, with application number 201680077470.5 and invention title "Defect Analysis of Images".

[0002] Cross-references to related applications

[0003] This application claims priority and benefit to U.S. Utility Patent Application No. 14 / 986,486, filed December 31, 2015, entitled “FLAW ANALYSIS OF IMAGES,” the entire contents of which are incorporated herein by reference. Technical Field

[0004] This disclosure generally relates to the analysis of defects in images. Background Technology

[0005] E-commerce has become ubiquitous. In addition to physical stores, consumers can purchase goods and services from e-commerce retailers from their computers and / or mobile devices. E-commerce has its drawbacks. In some cases, consumers cannot directly interact with salespeople, which may reduce trust in a potential transaction or purchase. The distance between buyers and sellers, and the anonymity of sellers, may limit a buyer's ability to resolve issues with the product or service after purchase, which may also reduce trust in the engagement.

[0006] Some of these problems can be exacerbated when sellers are not associated with online marketplaces where they list goods or services for sale. For example, in some online marketplaces, sellers are able to list items for sale (or auction) and the marketplace can charge a fee for the service. Once a buyer purchases the goods or services, the seller can deliver them. This distanced relationship between buyer and seller can lead to greater distrust of sellers in online marketplaces and / or e-commerce. Providing e-commerce tools and / or resources that demonstrate seller credibility can increase the likelihood of completing a transaction. Attached Figure Description

[0007] These and other features, aspects and advantages of this disclosure can be better understood when the following detailed description is read in conjunction with the accompanying drawings.

[0008] Figure 1 The following is an example architecture shown according to some embodiments, in which a user can interact with an e-commerce website.

[0009] Figure 2 A block diagram of some components of a server according to some embodiments is shown.

[0010] Figure 3This is a flowchart illustrating an example process of listing items in an online marketplace, according to some embodiments.

[0011] Figure 4 This is a flowchart illustrating an example process for providing defect analysis, defect presentation, and defect-based ranking according to some embodiments.

[0012] Figure 5A , Figure 5B , Figure 5C and Figure 5D Examples of user interfaces for defect marking and / or defect rendering are shown according to some embodiments.

[0013] Figure 6 This is a flowchart of a process for performing defect analysis on an article including a digital display, according to some embodiments. Detailed Implementation

[0014] Systems and methods for determining whether items listed for sale on an online marketplace are defective are disclosed. In some embodiments, a method may receive an image of an item listed for sale on an online marketplace; provide a seller with a user interface that allows the seller to indicate whether the item has one or more defects; provide a user with one or more digital defect highlighting tools via a first user interface; receive defect highlighting of an image via the user interface, the defect highlighting being based on interaction between the user and the defect highlighting tools; and create a listing for the item on the online marketplace, the listing including the image and applying defect highlighting to the image.

[0015] These illustrative embodiments are mentioned not to limit or restrict this disclosure, but to provide examples to aid in understanding it. Further embodiments are discussed in the detailed description, and further description is provided in the detailed description. The advantages offered by one or more of the various embodiments can be further understood by reading this specification or by practicing one or more of the presented embodiments.

[0016] Systems and methods for performing defect analysis on images provided as part of item listings on online marketplaces are disclosed. In some embodiments, presentation to potential buyers may include highlighting or identifying defects within one or more images provided by the seller. In some embodiments, defect analysis may be performed, which may include implicit defect analysis and explicit defect analysis. In some embodiments, the results of defect analysis may be used as part of an item listing ranking system and / or may be used to penalize sellers who fail to report defects in their items.

[0017] Some embodiments can be used to increase buyer satisfaction and / or seller credibility by providing sellers with the opportunity to disclose and / or present defects in their listed items for sale. Additionally, some embodiments may be useful for online marketplaces to encourage sellers to identify and / or present defects to potential sellers, potentially increasing credibility and conversion rates. Such embodiments can help e-commerce and / or online marketplaces overcome many challenges.

[0018] Defects can include scratches, chips, dents, wrinkles, cracks, water damage, stains, chips, bending, discoloration, fading, holes, ink stains, abrasions, etc. A defect can be any damage to an item that makes it less new or places it in a condition that the user perceives as not new.

[0019] In online marketplaces where sellers can sell secondhand items, the success of these marketplaces likely depends at least in part on the level of trust buyers have in sellers. For example, the more open sellers are about listing items for sale, the higher the level of trust buyers have, which may translate into buyers being more likely to purchase items from those sellers. Sellers who provide open and honest descriptions of defects in their listings are more likely to be trusted than those who do not. Defect analysis and / or presentation, as discussed in this literature, can provide avenues for increasing trust between buyers and sellers, potentially leading to higher conversion rates.

[0020] Figure 1 An example architecture 100 is shown, in which a user (either a seller or a buyer, or both) can interact with an e-commerce website. For example, a user can access the e-commerce website using a user device that may include a mobile device 105 or a computer 110. The user device may include, for example, a smartphone, tablet, laptop, desktop computer, smartwatch, or a combination thereof. The user device can be coupled to or connected to network 115 via a wired or wireless connection.

[0021] An e-commerce website may be hosted or maintained by server 120, which may include one or more servers, either locally or widely distributed. In some embodiments, server 120 may be a cloud-based server system, which may include multiple servers located in different locations and connected via a network. The website hosted by server 120 may provide one or more representations of items as listings that can be purchased by users. Images of these items and text describing them may be sent to a user device via network 115 to provide the listings on the website. Users may use a web browser, application, or app on their device to view the images and text. The website may provide a marketplace where users can browse and purchase items listed as listings in the marketplace.

[0022] Network 115 can be any network or network configuration configured for communication between sending and receiving devices. In some embodiments, network 115 may include a conventional type of network, a wired or wireless network, and may have a variety of different configurations. Furthermore, network 115 may include a local area network (LAN), a wide area network (WAN) (e.g., the Internet), or other interconnected data paths through which multiple devices and / or entities can communicate. In some embodiments, network 115 may include a peer-to-peer network. Network 115 may also be coupled to or may include portions of a telecommunications network for transmitting data in various different communication protocols. In some embodiments, network 115 includes... A communication network or cellular communication network for sending and receiving communications and / or data, including via Short Message Service (SMS), Multimedia Messaging Service (MMS), Hypertext Transfer Protocol (HTTP), Direct Data Connection, Wireless Application Protocol (WAP), email, etc. Network 115 may also include a mobile data network, which may include third-generation (3G), fourth-generation (4G), Long Term Evolution (LTE), LTE-A Advanced, LTE Voice (“VoLTE”), or any other mobile data network or combination of mobile data networks. Furthermore, network 115 may include one or more IEEE 802.11 wireless networks.

[0023] Server 120 may store information for item listings. This information may include, for example, text describing the item listed for sale in the item listing, one or more images of the item listed for sale in the item listing, links or buttons for selecting items to purchase, etc. Server 120 may also include a database containing information about all items listed for sale or previously listed for sale in the market. This database may include statistics regarding the probability and / or types of defects that an item, item type, or item category may have.

[0024] Figure 2 A block diagram of some components of a server 120 according to some embodiments described herein is shown. The server 120 can be arranged according to at least one embodiment described herein. The server 120 may include a computing system 205 and a database 230. The computing system 205 may include a communication interface 210, a processor 215, a memory 220, and a data storage 225. One or more communication interfaces 210, processors 215, memory 220, and data storage 225 may be communicatively coupled.

[0025] In some embodiments, the communication interface 210 may be used by the computing system 205 to communicate with... Figure 1The communication interface 210 communicates with the network 115 and / or the mobile device 105. In some embodiments, the communication interface 210 may use any communication protocol, interface, standard, etc., to communicate with the network 115 and / or the mobile device 105. In some embodiments, the communication interface 210 may use a wired or wireless connection to communicate with the network 115 and / or the mobile device 105.

[0026] In some embodiments, processor 215 may include any suitable dedicated or general-purpose computer, computing entity, or processing device comprising various computer hardware or software modules, and may be configured to execute instructions stored on any suitable computer-readable storage medium. For example, processor 215 may include a microprocessor, microcontroller, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or any other digital or analog circuit configured to interpret and / or execute program instructions and / or process data. Although in Figure 2 While shown as a single processor, it should be understood that processor 215 may include any number of processors configured to perform any number of operations described herein, individually or collectively. Additionally, one or more processors may reside on one or more different electronic devices, such as different servers. In some embodiments, processor 215 may interpret and / or execute program instructions stored in memory 220, data storage 225, or both memory 220 and data storage 225, and / or process data stored therein. In some embodiments, processor 215 may retrieve program instructions from data storage 225 and / or database 230 and load the program instructions into memory 220. After the program instructions are loaded into memory 220, processor 215 may execute the program instructions.

[0027] In some embodiments, memory 220 and data storage 225 may include a computer-readable storage medium for carrying or having computer-executable instructions or data structures stored thereon. Such a computer-readable storage medium may be any available medium accessible by a general-purpose computer or a special-purpose computer, such as processor 215. By way of example, and not limitation, these computer-readable storage media may include tangible or non-transitory computer-readable storage media, including random access memory (RAM), read-only memory (ROM), electronically erasable programmable read-only memory (EEPROM), optical disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage or other magnetic storage devices, flash memory devices (e.g., solid-state memory devices), or any other storage medium that may be used to carry or store desired program code in the form of computer-executable instructions or data structures and accessible by a general-purpose or special-purpose computer. Combinations of the above may also be included within the scope of computer-readable storage media. Computer-executable instructions may include, for example, instructions and data configured to cause processor 215 to perform specific operations or groups of operations.

[0028] In some embodiments, database 230 may be communicatively coupled to computing system 205. Database 230 may include one or more other databases, such as serial number database 235, price database 240, user profile database 250, listing database 255, image-defect database 260, filter database 270, and defect profile database 265. Database 230 may also include multiple modules that, when executed by processor 215, enable computing system 205 to perform operations to create listings for mobile device 105 based on metadata received from mobile device 105.

[0029] In some embodiments, database 230 may include a computer-readable storage medium for carrying or having computer-executable instructions or data structures stored thereon. Such a computer-readable storage medium may be any available medium accessible by a general-purpose or special-purpose computer, such as processor 215. By way of example, and not limitation, such a computer-readable storage medium may include tangible or non-transitory computer-readable storage media, including random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), optical disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage or other magnetic storage devices, flash memory devices (e.g., solid-state memory devices), or any other storage medium that may be used to carry or store desired program code in the form of computer-executable instructions or data structures and that is accessible by a general-purpose or special-purpose computer. Combinations of the above may also be included within the scope of computer-readable storage media. Computer-executable instructions may include, for example, instructions and data configured to cause processor 215 to perform specific operations or groups of operations.

[0030] In some embodiments, the user profile database 250 may include a server (such as...) Figure 1 The server 120 interacts with various user-related information. For each user, this information may include, for example, demographic data such as age, gender, ethnicity, and other data, user location, shopping history, purchase history, recently viewed items, recently placed items in the virtual shopping cart but not purchased, preferred delivery options, credit card information, listing information, address, phone number, defect history, etc.

[0031] In some embodiments, the user profile database 250 may also include user listing preferences. User listing preferences may include auction preferences, auction duration preferences, delivery preferences, storefront images, store names, usernames, reviews, ratings, payment preferences, defect display preferences, or some combination thereof.

[0032] In some embodiments, the listing database 255 may include listings of products for sale posted on server 120. The listing database 255 may also include listings of products that have been created but not yet published. The listing database 255 may include descriptions of listed items for sale and / or previously listed items for sale. In some embodiments, the listing database 255 may reference images stored in the image-defect database 260.

[0033] In some embodiments, the image-defect database 260 may include multiple images that have been uploaded for display within item listings. For example, each item listing may be associated with one or more images stored in the image-defect database 260. In some embodiments, the image-defect database 260 may include different versions of images.

[0034] In some embodiments, the image-defect database 260 may include listings or categories of items and the likelihood that an item was defective at the time of listing. For example, the image-defect database 260 may include entries indicating that a particular type of clothing is highly likely to discolor. As another example, the image-defect database 260 may include entries indicating that a particular type of electronic device typically has scratches. As yet another example, the image-defect database 260 may include entries indicating that a particular type of handheld device typically has a defective screen.

[0035] In some embodiments, the defect profile database 265 may include a plurality of digital image filters that may be applied to the image in real time or before being displayed to the user. These digital image filters may include, for example, contrast-enhancing digital image filters, color-inverting digital image filters, spatial domain digital image filters, as well as detection digital image filters, unsharpening digital image filters, Laplacian digital image filters, Gaussian digital image filters, smoothing digital image filters, etc.

[0036] In some embodiments, the filter database 270 may include data indicating the types of digital image filters that can be used for a particular item or item category to highlight typical defects in the item or item category. In some embodiments, one or more digital image filters may be returned from the filter database 270 and applied to one or more images based on the type of defect. In some embodiments, one or more digital image filters may be returned from the filter database 270 and applied to one or more images based on the item type or item category.

[0037] Without departing from the scope of this disclosure, server 120 may be modified, added to, or omitted. For example, computing system 205 and database 230 can be connected via a network (such as... Figure 1 The network 115) is communicatively coupled. Alternatively or additionally, server 120 may include multiple computing systems 205 that can operate to perform one or more processes described in this disclosure.

[0038] Figure 3 This is a flowchart of an example process 300 for listing items on an online marketplace. In some embodiments, one or more steps of process 300 may be performed by... Figure 1 and Figure 2The server 120 is implemented using one or more components. Although illustrated as discrete boxes, the various boxes may be divided into additional boxes, combined into fewer boxes, executed in a different order, or omitted, depending on the desired implementation.

[0039] Process 300 begins at box 305, whereby the seller receives images and / or product listing information from the seller at server 120, for example via a user device (e.g., mobile device 105 or computer 110). The listing information may include a description of the item listed for sale on the online marketplace and / or one or more images of the listed item. The listing information may also include item type, item category, etc.

[0040] At box 310, you can create an item listing. An item listing may include, for example, a title, description, text received from the seller, and / or an image provided by the seller. An item listing may also include, for example, a selling price, a starting price, a current price, a shipping price, and a shipping method. An item listing may include various other elements or characteristics. For example, an item listing may be a webpage or a series of webpages or other digital media that can be presented to buyers through the online marketplace. An item listing may include an item type and / or category, which may be provided by the seller or by the online marketplace based on text received from the seller.

[0041] At box 315, defect analysis can be performed on the images provided by the seller. Defect analysis may include, for example, item-specific or category-specific defect analysis based on a specific item and / or item category. For instance, specific digital image filters can be applied to images based on item type or item category. For example, using item type or item category, server 120 can use defect profile database 265 to identify typical defects. Based on typical defects, digital image filters can be selected from filter database 270 and applied to one or more images of that item.

[0042] As another example, the text provided by the seller can indicate that the item in the listing contains a specific type of defect. Based on the specific type of defect, a digital image filter can be selected from the filter database 270 and applied to one or more images of the item.

[0043] At box 320, item listings can be presented on the online marketplace. Item listings may include one or more original images, one or more digitally filtered images, or a combination thereof. In some embodiments, digitally filtered images may be available but not provided as part of the item listing. In some embodiments, item listings may be made available to multiple users via web pages, applets, mobile apps, or applications. In some embodiments, item listings may be provided using one or more markup languages ​​(e.g., HTML and / or XML).

[0044] At box 325, defect highlighting tools can be provided to sellers via web pages, mini-programs, and / or applications. For example, as part of the defect highlighting tools provided to sellers, sellers may be able to click on links or images and may be provided with digitally filtered images or digitally filtered portions of images. As another example, tools can be provided to users that allow them to highlight, circle, zoom in, point to, or mark one or more portions of an image.

[0045] As another example, a defect highlighting tool can be provided as part of an item listing and can include an original image with a slider that allows the user to slide back and forth. For example, as a user (e.g., a buyer or seller) slides the slider back and forth, a digital image filter can be applied to the image and / or portions of the image. As another example, a digitally filtered image can be displayed instead of a portion or the entire original image. In some embodiments, the slider can increase one or more parameters of the digital filter. For example, if the digital filter is a contrast filter, the slider can be used to increase or decrease the amount of contrast applied to the image. As another example, if the digital filter is an unsharpened digital image filter, the slider can be used to increase or decrease the amount of edge highlighting appearing in the highlighted image by changing parameters in the filter (e.g., a scaling constant, such as a k-scaling constant).

[0046] In some embodiments, the defect highlighting tool may allow the user to select a variety of digital image filters that can be applied to part or the entire original image. For example, a drop-down menu or other menu may be provided to the user, allowing them to select one or more digital filters that can be applied to the image. In response, one or more images may be presented through an item listing, wherein one or more digital filters are applied to an image provided by the seller.

[0047] In some embodiments, at box 325, a defect highlighting tool may be provided to the seller. For example, the seller may be able to modify the item listing to include one or more defect highlights or defect highlighting tools in the item listing.

[0048] In some embodiments, at box 325, a defect highlighting tool may be provided to the buyer. For example, the defect highlighting tool provided to the buyer may allow the buyer to highlight one or more images in an item listing. For example, the aforementioned slider may be provided to allow the buyer to change, modify filters, and / or apply filters to one or more images.

[0049] Figure 4 This is a flowchart of an example process 400 that provides defect analysis, defect presentation, and ranking based on defect analysis. In some embodiments, it can be achieved through... Figure 1 and Figure 2 One or more components of server 120 are used to implement one or more steps of process 400. Although illustrated as discrete boxes, the individual boxes may be divided into additional boxes, combined into fewer boxes, executed in a different order, or omitted, depending on the desired implementation. In some embodiments, only one or more boxes of process 400 may be executed.

[0050] Process 400 begins at box 405, where explicit defect analysis is performed. Explicit defect analysis can include any type of defect identification provided by the seller listing the item for sale on the online marketplace. For example, as part of the listing creation process, sellers may be asked whether the item they are listing on the online marketplace has a defect. If the seller indicates that the item has a defect, a user interface (e.g., provided via a web browser) can be provided to allow the seller to circle, point to, or highlight defects in one or more images of the item for sale on the online marketplace. For example, as... Figure 5B The example shown provides drawing tools that allow sellers to draw out defects in images using circles. As another example, such as... Figure 5C As shown, an ellipse drawing tool can be provided to allow sellers to circle defects in an image. As another example, an arrow tool can be provided to allow sellers to point to defects in an image, such as... Figure 5D As shown in the image. As another example, a text tool could be provided to allow sellers to add text about defects in the image, such as... Figure 5D As shown in the image.

[0051] In some embodiments, explicit defect analysis 405 may provide a user interface that asks the seller whether the item contains defects.

[0052] In some embodiments, the explicit defect analysis 405 may provide a user interface in which the seller can upload additional images. For example, the seller can upload images that have been taken of a specific defect or enlarged images to focus on that defect.

[0053] In some embodiments, the explicit defect analysis 405 may provide a user interface including zoom tools. For example, a seller may use the zoom tools to magnify the area where the defect is located and / or provide a separate image of the magnified area of ​​the defect.

[0054] In some embodiments, explicit defect analysis 405 may provide a user interface including various digital image filter tools. For example, the user interface may allow the seller to apply one or more digital image filters, such as those selected from filter database 270, which can highlight or emphasize defects in an image. For example, images provided by the seller during the online listing process may be provided to the seller in the user interface, and one or more buttons or sliders may also be provided, allowing the seller to turn one or more digital image filters on or off, and / or to increase or decrease the intensity (or other factors) of one or more digital image filters. For example, these digital image filters may include contrast digital image filters, color saturation digital image filters, unsharpening digital image filters, Laplacian digital image filters, Gaussian digital image filters, smoothing digital image filters, etc. These digital image filters may include any digital image filters located in filter database 270.

[0055] At box 410, implicit defect analysis can be performed. In some embodiments, implicit defect analysis can be performed by server 120 in response to information provided by the seller in text and / or image format. In some embodiments, implicit defect analysis can be performed by server 120 without interaction with the seller. In some embodiments, implicit defect analysis 410 can mark an item as defective based on text entered by the seller, the type of the listed item, the item category of the item, or analysis performed on one or more images of the item provided by the seller.

[0056] In some embodiments, if the seller enters text in the item description indicating that the item may be defective, the implicit defect analysis 410 can mark the item as defective. For example, if any words associated with defect or its derivatives appear in the item description, the implicit defect analysis can mark the item as defective. These words may include, for example, “damaged,” “squeaking,” “scratches,” “dents,” “discoloration,” “fading,” “dirty,” “used,” “old,” “stains,” “damage,” “holes,” “water damage,” “fragments,” “defect,” etc.

[0057] In some embodiments, the entire description can be used to limit whether implicit defect analysis is triggered. For example, if the item is a golf club and the description uses the word "chip," it might describe the type of golf club rather than any defects in the club. As another example, if the item is listed as an antique, it can be assumed that it has defects, so implicit defect analysis may not be triggered despite the use of words associated with defects.

[0058] In some embodiments, implicit defect analysis 410 may mark an item as defective based on item type or item category. For example, certain items, item types, or item categories may be more or less defective. For example, defect profile database 265 may include item listings, item types, or item categories that are typically associated with defects. If an item, item type, or item category matches an item listing, item type, or item category in defect profile database 265 that is associated with an item that may be defective, implicit defect analysis may mark that item as defective.

[0059] In some embodiments, if analysis of the image indicates that the image may have been altered or may indicate that the item is defective, implicit defect analysis 410 may mark the item as defective. For example, implicit defect analysis 410 may use digital image filters (e.g., digital image filters from filter database 270) and / or image forensic analysis to determine whether the image has been altered using photo editing software. For example, digital image filtering and / or image forensic analysis may use error level analysis (ELA) tools to determine the amount of difference that occurred during JPEG resaving. Various other techniques may also be used. In some embodiments, implicit defect analysis 410 may determine whether digital image filtering and / or image forensic analysis has been applied to the image to reduce the likelihood that a potential buyer might see a defect.

[0060] As another example, implicit defect analysis 410 can examine the metadata associated with an image to determine whether the image has been modified by photo editing software. The metadata indicates that the image was last saved by a photo editing application, such as Photoshop, Illustrator, Corel Draw, Pixlr, Serif PhotoPlus, Acorn, GIMP, Affinity Photo, Adobe Lightroom, ACDSee, Corel PaintShop, Aperture, DxO Optics, Pixelmator, etc. For example, some images may include XMP metadata that may contain a history field. If the history field indicates that the image has been saved multiple times, the image may have been modified. In some embodiments, implicit defect analysis can check whether the image includes an XMP metadata history field with entries exceeding a threshold. If so, then it can be determined that the image has been modified.

[0061] In some embodiments, the presence of XMP metadata itself can indicate that the image was opened and / or saved by an Adobe product, and can also indicate that the image was created by... Product (e.g., Photoshop) editing. In some embodiments, implicit defect analysis can check whether the image includes XMP metadata. If so, it can be determined that the image has been modified.

[0062] In some embodiments, implicit vulnerability analysis 410 may use online third-party forensic analysis services to determine whether an image has been modified. For example, the image may be uploaded to a webpage performing forensic analysis, such as www.fotoforensics.com, www.imageforensic.org, www.izitru.com, imageedited.com, etc. Implicit vulnerability analysis 410 may determine whether the image has been modified based on the results provided by the third-party webpage.

[0063] In some embodiments, if an image is determined to include known indications of digitally modified image effects, such as if the image includes rainbow patterns, then implicit defect analysis 410 can mark the item as defective. Images can be processed to determine whether they have been digitally modified using any number of techniques, such as error level analysis, principal component analysis, PCA cross product, etc. For example, error level analysis compares the separation between the red and blue channels in an image. Principal component analysis (PCA) identifies an orthogonal coordinate system based on the variance of the data space. PCA cross product can compare various features of the image between a PCA vector and another image vector (such as a vector from the center of a color cloud to a specific color).

[0064] In some embodiments, if the implicit defect analysis 410 can determine that the image has been altered, the marketplace can provide a prompt to request the seller to provide a new image of the item.

[0065] In some embodiments, implicit defect analysis 410 can compare an image of a listed item with one or more images of the same item or item type and determine whether any variations between the two images indicate a defect in the listed item. For example, one or more images of the same item or item type can be extracted from the listing database 255. The comparison between the two images can provide an indication that the listed image contains defects. For example, the two images can be scaled to have the same size and / or background or foreground items can be removed before the comparison. Differences in the value of each pixel can be calculated. Regions where different values ​​above a predetermined threshold are concentrated can indicate the presence of defects in the image of the listed item.

[0066] Figure 5A , Figure 5B , Figure 5C and Figure 5D Examples of user interfaces for defect marking and / or defect rendering, according to some embodiments, are shown. Figure 5A In this example, item 505 is presented to user interface 500 and has a defect 550. In this example, item 505 is an Adirondack chair, and the defect is a scratch on the chair's armrest. The user interface provides the seller with several tools: drawing tool 510, circle tool 515, arrow tool 520, text tool 525, and zoom tool 530. Various other tools may be included. Although in Figure 5A Many tools are shown, but some of these tools may or may not be included in the user interface 500.

[0067] Figure 5B , Figure 5C and Figure 5D Here are two examples where the seller has indicated that there is a defect in the image of the item being listed for sale. Figure 5B The circle 555 is shown, drawn by the seller using drawing tool 510 around defect 550. Figure 5C The circle 560 is shown, drawn by the seller using the circle tool 515 around the defect 550. Figure 5D An arrow 565 pointing to defect 550 and text 570 identifying the defect are shown. Arrow 565 can be drawn using arrow tool 520, and text 570 can be added using text tool 525.

[0068] In some embodiments, implicit defect analysis 410 can use, for example... Figure 6The process 600 shown determines whether a digital display is defective. One or more steps of process 600 may be performed by [unclear - likely a specific method or entity]. Figure 1 and Figure 2 The server 120 shown is implemented using one or more components. Although illustrated as discrete boxes, the various boxes may be divided into additional boxes, combined into fewer boxes, executed in a different order, or omitted, depending on the desired implementation. In some embodiments, only one or a few boxes of process 600 may be executed.

[0069] Process 600 begins at box 605, where it can be determined whether an item includes a digital display. For example, this can be determined based on keywords found in the text, item type, item category, etc. For instance, if the item is a computer, television, mobile phone, tablet computer, etc., it can be assumed that it includes a digital display.

[0070] At box 610, process 600 may provide the seller with sample images to be displayed on the item's digital display. For example, the seller may be directed to a specific webpage or provided with a specific file containing sample images that can be displayed on the item's digital display.

[0071] At box 615, a digital photograph of the sample image can be received from the seller. For example, when a digital display is showing a sample image, the seller can be instructed to take a digital image of the display showing the item. A user interface can be provided to the seller, allowing them to upload a digital photograph of the display showing the sample image. In response, the seller can upload the digital photograph.

[0072] At box 620, a comparison can be made between the digital photograph and the sample image. For example, a pixel-by-pixel or region-by-region comparison can be made between the digital photograph and the sample image. For instance, process 600 can take the average value of the regions in the digital photograph and compare these values ​​with the average value of the corresponding regions in the sample image. If the difference between the regions in the sample image and the regions in the digital photograph exceeds a threshold, the display may be defective in the region corresponding to the comparison.

[0073] In some embodiments, the threshold may be determined based on the average difference between the pixels of the digital photograph and the sample image. For example, the threshold may be greater than the average difference between the pixels of the digital photograph and the sample image.

[0074] In some embodiments, at box 415, the identified defect can be presented or highlighted to buyers (or sellers) in the online marketplace in any of a variety of different ways. For example, one or more additional images may be provided in the online marketplace listings that identify, highlight, or help emphasize the defect. For example, these one or more images may include images uploaded by sellers and modified in such a way as to identify, highlight, or help emphasize the defect. For example, the image may be a scaled-down portion of an image that includes the defect, and the image may have a digital image filter from filter database 270 applied to the image to better display the defect relative to the rest of the image. The image may include one or more lines encircling the defect (see [link to image]). Figure 5B and Figure 5C The image may include one or more lines or arrows pointing to the defect (see...). Figure 5D The image may include text describing the defect, etc.

[0075] In some embodiments, a defect highlighting tool can be provided in conjunction with an image of the item in the user interface. The defect highlighting tool allows the seller to interact with the image to highlight defects within the image. For example, when the user moves the defect tool over a portion of the image in the user interface, a digital image filter can be applied to the image to highlight one or more defects. Alternatively or additionally, as the user moves the defect tool over a portion of the image in the user interface, at least a portion of a second image of the item can be displayed in the user interface. The second image of the item can be an image having a digital image filter applied to it that can highlight defects in the image. The digital image filter can be, for example, a digital image filter selected from a filter database 270. The buyer can be able to select the defect tool, and by interacting with the image, the buyer can be able to view the highlighted defects within the image.

[0076] As another example, a defect highlighting tool may include one or more slider widgets in the user interface. Users can interact with these slider widgets to change the type, amount, and / or position of the digital image filter applied to the image. The digital image filter may be, for example, a digital image filter selected from a filter database 270. For example, as the user moves the slider widget in the user interface, the image may be processed more or less in real time. As another example, the amount of image processing may increase or decrease depending on the position of the slider widget as the user moves it in the user interface. As another example, the processing position in the image may change depending on the position of the slider widget as the user moves it in the user interface.

[0077] In some embodiments, the ranking of item listings in the online marketplace 420 can be altered based on explicit defect analysis 405 and / or implicit defect analysis 410. Ranking indicates the order in which item listings are presented to buyers relative to other item listings in response to a search query. Generally, the more relevant an item is to a search query, the higher its ranking, and the more likely potential buyers are to view and purchase the item. Other factors that may influence ranking may include, for example, the relevance of the item to the search criteria, the amount of text provided by the seller, the item's price, the number of images provided by the seller, the seller's rating, or the ratings of items with the same or similar item types.

[0078] In some embodiments, sellers may be encouraged and / or actively supported to explicitly indicate that an item includes defects and / or provide specific types of defect indications. For example, if a defect is indicated in explicit defect analysis 405, and the seller does not provide any additional images of the item or any defect highlighting on the images, the item will be given a lower ranking compared to sellers who provide additional images of the item and / or apply any defect highlighting to the images of the item. Alternatively or additionally, in response to sellers who do not provide any additional images of the item or do not provide any defect highlighting on the images, the item listing may lose a predetermined number of ranking points, etc.

[0079] In some embodiments, an item listing may receive a predetermined number of ranking points in response to sellers who actually provide any additional images of the item and / or highlight any defects in the images.

[0080] In some embodiments, if an item, item type, or item category is determined to be consistent with an item, item type, and / or category typically associated with a defect, but without a defect identified by the seller in implicit defect analysis 410 and / or explicit defect analysis 405, the item listing may receive an increase in ranking points. Alternatively, in some embodiments, if an item, item type, or item category is determined to be consistent with an item, item type, and / or item category typically associated with a defect, but without a defect identified by the seller in implicit defect analysis 410 and / or explicit defect analysis 405, the item listing may lose ranking points.

[0081] In some embodiments, the increase in ranking can be proportional to the number of defect highlights provided by the seller. For example, if a seller provides multiple defect highlights for one or more images, the item's ranking in a search query can increase by more ranking points compared to when the seller provides a single defect highlight or no defect highlights.

[0082] In some embodiments, if the seller provides one or more images of the defect, the item's ranking in search queries can be increased.

[0083] In some embodiments, if it is determined in implicit defect analysis 410 that an item's image has been altered, the item's ranking may be reduced by a predetermined number of points. Alternatively or additionally, in some embodiments, if it is determined in implicit defect analysis 410 that an item's image has been altered, the item may not be offered for sale on the online marketplace or may be removed from the online marketplace. Alternatively or additionally, in some embodiments, if it is determined that an item's image has been altered, the seller's rating may be reduced by a predetermined number of points. Alternatively or additionally, in some embodiments, items listed for sale on the online marketplace include indications (e.g., text and / or images) indicating that one or more images have been altered by the seller.

[0084] Some embodiments include digital image filters that can be used to determine whether an image contains defects. These digital image filters, or algorithms for applying them, may be stored, for example, in a filter database 270. Any number or type of digital image filters can be applied to an image to determine whether it contains defects or to process the image to highlight all potential defects.

[0085] In some embodiments, a training set of previously published defective items can be used to identify digital image filters that produce digitally filtered images highlighting specific types of defects. Machine learning algorithms (e.g., support vector machines, neural networks, or other supervised learning models) can be used to associate digital image filters with specific defects. In some embodiments, the machine learning algorithm can be applied to item listings (e.g., previously published items) in a listing database 255. For example, the machine learning algorithm can be applied to a set of item listings known to include defects and / or have defects identified in one or more images. The set of item listings may also include indications of the type of defect on the items. The machine learning algorithm can iteratively apply one or more digital image filters to each image in the set of item listings and determine the optimal digital image filter based on user feedback, image analysis, or image comparison. The machine learning algorithm can then associate the optimal digital image filter with an item type and / or with a defect type. For example, the machine learning algorithm can provide a database that associates digital image filters with item types and / or defect types, etc. For example, this database can be expanded or revised over time as more item listings are analyzed. This database can be stored, for example, in filter database 270.

[0086] Some embodiments may include a method for highlighting defects in images on an online e-commerce marketplace. The method may include receiving images of items listed for sale on the online marketplace from a seller via the internet; providing the seller with a first user interface via the internet, allowing the seller to indicate whether the item has one or more defects; in response to a user indicating one or more defects in the item via the first user interface, providing the seller with one or more digital defect highlighting tools via the first user interface; receiving defect highlighting of the image based on the interaction between the seller and the defect highlighting tools via the first user interface; and creating a listing for the item on the online marketplace that includes the image and applies defect highlighting to the image.

[0087] In some embodiments, defect highlighting of an image includes instructions from a user to apply a digital image filter to the image to create a second image; and / or the application of defect highlighting includes displaying the image and providing the buyer with tools to allow the buyer to operate a user interface item, which alternatively displays a portion of the second image in place of the first image.

[0088] In some embodiments, the highlighting tool may include at least one tool selected from the following: lasso tool, line drawing tool, ellipse drawing tool, text tool, arrow tool, zoom tool, and digital image filter application tool.

[0089] In some embodiments, highlighting defects in an image may include highlighting selected from: providing lines around the defects, inserting text into the image, inserting arrows into the image, magnifying a portion of the image, and applying digital image filters to the image.

[0090] In some embodiments, applying a digital image filter to an image may include applying a digital image filter selected from the following: contrast-enhancing digital image filter, color-inverting digital image filter, spatial domain digital image filter, detection digital image filter, unsharpening digital image filter, Laplacian digital image filter, Gaussian digital image filter, and smoothing digital image filter.

[0091] In some embodiments, defect highlighting of the image is provided in a second image that includes the image and the defect highlighting.

[0092] The term “basically” refers to what is called manufacturing tolerance or within 5% or 10% of the value of the manufacturing tolerance.

[0093] This document sets forth numerous specific details to provide a thorough understanding of the claimed subject matter. However, those skilled in the art will understand that the claimed subject matter can be practiced without these specific details. In other instances, methods, apparatus, or systems known to those of ordinary skill in the art have not been described in detail to avoid obscuring the claimed subject matter.

[0094] Some parts are presented based on algorithms or symbolic representations of operations performed on data bits or binary digital signals stored in the memory of a computing system (such as computer memory). These algorithmic descriptions or representations are examples of techniques used by those skilled in the art in the field of data processing to convey the essence of their work to others skilled in the art. An algorithm is a self-consistent sequence of operations or similar processes that leads to a desired result. In this context, the operation or process involves the physical manipulation of physical quantities. Typically, but not necessarily, such quantities can take the form of electrical or magnetic signals that can be stored, transmitted, combined, compared, or otherwise manipulated. Primarily for reasons of common use, it has sometimes proven convenient to refer to such signals as bits, data, values, elements, symbols, characters, items, numbers, numerical values, etc. However, it should be understood that all these and similar terms are associated with appropriate physical quantities and are merely convenient notations. Unless otherwise stated, it should be understood that throughout this specification, the use of terms such as “processing,” “operation,” “calculation,” “determine,” and “identify” refers to the actions or processes of a computing device, such as one or more computers or one or more similar electronic computing devices, which manipulate or convert data of physical, electronic, or magnetic quantities within the memory, registers, or other information storage, transmission, or display devices of the computing platform.

[0095] The one or more systems discussed herein are not limited to any particular hardware architecture or configuration. Computing devices may include any suitable arrangement of components that provides results dependent on one or more inputs. Suitable computing devices include multipurpose microprocessor-based computer systems that access stored software that programs or configures the computing system from a general-purpose computing device to a dedicated computing device for implementing one or more embodiments of this subject matter. The teachings contained herein can be implemented in the software used for programming or configuring the computing device using any suitable programming, scripting, or other type of language or combination of languages.

[0096] Embodiments of the methods disclosed herein can be executed in the operation of such a computing device. The order of the boxes presented in the above examples can be varied; for example, the boxes can be reordered, combined, and / or decomposed into sub-boxes. Some boxes or processes can be executed in parallel.

[0097] The use of “suitable for” or “configured to” in this document implies open and inclusive language, which does not exclude devices suitable for or configured to perform additional tasks or steps. Furthermore, the use of “based on” implies open and inclusive language, because processes, steps, calculations, or other actions “based on” one or more of the stated conditions or values ​​may actually be based on additional conditions or values ​​beyond those stated conditions and values. The headings, lists, and numbers included herein are for ease of interpretation only and are not intended to be restrictive.

[0098] While the subject matter has been described in detail with reference to specific embodiments thereof, it should be recognized that those skilled in the art, upon gaining an understanding of the foregoing, can readily make changes, alterations, and equivalents to these embodiments. Therefore, it should be understood that this disclosure is presented for illustrative purposes and not for limitation, and does not exclude such modifications, alterations, and / or additions to the subject matter, as these will be apparent to those skilled in the art.

[0099] In addition, this disclosure also includes the following embodiments.

[0100] (1). A method for highlighting defects in images of items for sale on an e-commerce online marketplace, the method comprising:

[0101] The system receives images of items listed for sale on the online marketplace and text describing those items from sellers via the internet from one or more servers hosting the online marketplace.

[0102] The one or more servers determine, based on the text, that the item includes a defect, the defect including damage to the item;

[0103] In response to determining that the item includes a defect, the one or more servers create a defect highlighting of the image, which modifies the image to make the defect stand out;

[0104] The one or more servers further create listings for the item on an online marketplace, the listings including the image and highlighting defects in the image; and

[0105] In response to a search query, the listings for the item are displayed by the one or more servers.

[0106] (2). The method according to (1) is characterized in that creating the defect highlighting includes applying a digital image filter to the image.

[0107] (3). The method according to (2) is characterized in that the digital image filter includes digital image filters selected from the following: contrast enhancement digital image filter, color inversion digital image filter, spatial domain digital image filter, detection digital image filter, unsharpening digital image filter, Laplacian digital image filter, Gaussian digital image filter and smoothing digital image filter.

[0108] (4). The method according to (1) is characterized in that:

[0109] Determining an item's defects includes identifying the defect type based on the text; and

[0110] The method also includes determining the defect salience type based on the defect type.

[0111] (5). The method according to (4) is characterized in that determining the defect highlighting type based on the defect type further includes searching for the defect highlighting type in a database that associates the defect highlighting type with the item type.

[0112] (6). The method according to (1) is characterized in that determining that the article includes defects includes determining whether the text includes words selected from the following: scratch, fragment, dent, wrinkle, crack, water damage, stain, discoloration, fading, hole, ink stain and abrasion.

[0113] (7). The method according to (1) is characterized in that:

[0114] Text related to items includes text indicating the type of item;

[0115] Identifying defects in items includes searching the database for one or more specific defect types associated with the item type; and

[0116] Create defect highlighting based on one or more specific defect types.

[0117] (8). The method according to (1) is characterized in that determining that the article includes defects includes determining whether the image is an image that has been altered.

[0118] (9). The method according to (1) is characterized in that creating a listing includes creating an item listing on an online marketplace, the listing including the image and a second image including a defect highlighting of the image.

[0119] (10). One or more non-transitory computer-readable media storing one or more programs configured to cause one or more processors to perform the method as described in (1) when executed.

[0120] (11). A method for determining whether a digital display contains a defect, the method comprising:

[0121] Receive listing information from sellers for items offered for sale on the online marketplace at the server hosting the online marketplace;

[0122] The server determines that the item includes a digital display;

[0123] The server provides sample images to the seller;

[0124] The server receives a digital photograph of the item as a sample image displayed on a digital display.

[0125] The server compares the received digital photographs with sample images to determine the differences between the digital photographs and sample images;

[0126] In response to the difference being greater than a threshold, the server determines that the digital display includes a defect; and

[0127] The digital display, presented by the server, shows listings of items on an online marketplace, including the defects shown, highlighting the defects.

[0128] (12). The method according to (11) is characterized in that providing the seller with sample images includes at least one selected from the following:

[0129] Send sample images to the seller via email; and

[0130] Provides a link to a sample image located on the network.

[0131] (13). The method according to (11) is characterized in that:

[0132] The listing information includes text describing the item; and

[0133] Determining whether an item includes a digital display also includes determining whether the text describing the item contains keywords associated with the item including the digital display.

[0134] (14). The method according to (11) is characterized in that:

[0135] The listing information includes the type of item; and

[0136] Determining the item includes determining whether the item type corresponds to an item type having a digital display.

[0137] (15). The method according to (11) is characterized in that the comparison is performed pixel by pixel or region by region.

[0138] (16). One or more non-transitory computer-readable media storing one or more programs configured to cause one or more processors to perform the method as described in (11) when executed.

[0139] (17). An online marketplace system, comprising:

[0140] Network interface;

[0141] Memory; and

[0142] Processor, the processor being configured to:

[0143] Images are received from sellers via a network interface; the images are of items listed for sale in an online marketplace system.

[0144] It has been determined that the image has been altered; and

[0145] In response to determining that the image has been modified, the following steps are taken:

[0146] Send a request for the unmodified image to the seller via the web interface; or

[0147] Create listings for items with images in the online marketplace system, and lower the ranking of the created listings to change the order in which items are displayed to buyers in response to search requests from buyers.

[0148] (18). The online marketplace system according to (17) is characterized in that the determination that an image has been modified is based on metadata associated with the image.

[0149] (19). The online marketplace system according to (17) is characterized in that the determination that an image has been altered is based on the results of forensic analysis and / or digital image filtering.

[0150] (20). The online marketplace system according to (17), characterized in that determining that the image has been modified further includes:

[0151] Sending images to forensic analysis services via the Internet; and

[0152] Receive forensic analysis from the forensic analysis service.

Claims

1. An online marketplace system, comprising: Network interface; Memory; as well as Processor, the processor being configured to: Images are received from sellers via a network interface; the images are of items listed for sale in an online marketplace system. Determine whether the image has been altered by the seller; as well as In response to determining that the image has been altered by the seller: The item is marked as defective; Send a request for the unmodified image to the seller via the network interface; or The system creates listings for items that include the image in an online marketplace system and lowers the ranking of the created listings to change the order in which items are displayed to buyers in response to search requests from buyers.

2. The online marketplace system according to claim 1, wherein, Determining whether an image has been modified is based on the metadata associated with the image.

3. The online marketplace system according to claim 1, wherein, Determining whether the image has been altered is based on forensic analysis and / or the results of digital image filtering.

4. The online marketplace system according to claim 3, wherein, The digital image filter includes digital image filters selected from the following: contrast enhancement digital image filter, color inversion digital image filter, spatial domain digital image filter, detection digital image filter, unsharpening digital image filter, Laplacian digital image filter, Gaussian digital image filter, and smoothing digital image filter.

5. The online marketplace system according to claim 1, wherein, Determining whether the image has been altered also includes: The image was sent to an forensic analysis service via the Internet; and Receive forensic analysis from the forensic analysis service.

Images