WO2020192691A1 - 基于图像的搜索方法、服务器、终端及介质 - Google Patents

基于图像的搜索方法、服务器、终端及介质 Download PDF

Info

Publication number
WO2020192691A1
WO2020192691A1 PCT/CN2020/081121 CN2020081121W WO2020192691A1 WO 2020192691 A1 WO2020192691 A1 WO 2020192691A1 CN 2020081121 W CN2020081121 W CN 2020081121W WO 2020192691 A1 WO2020192691 A1 WO 2020192691A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
display
attributes
terminal
image
Prior art date
Application number
PCT/CN2020/081121
Other languages
English (en)
French (fr)
Inventor
李耀强
Original Assignee
北京京东尚科信息技术有限公司
北京京东世纪贸易有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京京东尚科信息技术有限公司, 北京京东世纪贸易有限公司 filed Critical 北京京东尚科信息技术有限公司
Priority to EP20776656.9A priority Critical patent/EP3951622A4/en
Priority to US17/598,856 priority patent/US20220197939A1/en
Publication of WO2020192691A1 publication Critical patent/WO2020192691A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G06F16/532—Query formulation, e.g. graphical querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G06F16/538—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures

Definitions

  • the present disclosure relates to the technical field of the Internet, and in particular to an image-based search method, server, terminal and medium.
  • the prior art has at least the following problems:
  • the recall result may include There are many targets similar to image content, so users need to filter out the content they want to browse from a large number of targets.
  • the image search engine recalls the image content of the product image in the index library, it may appear that the recalled similar products include multiple styles, multiple brands, or multiple promotional types of products.
  • Users can only filter out the most desired or worth buying products by browsing. This may require turning several pages or even more than a dozen pages, spending more time and energy, and bringing users a poor user experience, which may eventually Affect the total turnover of the commodity.
  • the present disclosure provides an image-based search method, server, terminal, and medium, thereby at least partially solving one or more problems caused by limitations and defects of related technologies.
  • the first aspect of the present disclosure provides an image-based search method applied to a server.
  • the method includes: extracting a target set from an index library according to the image content in the image to be searched;
  • the attributes of the targets determine the number of targets corresponding to the attributes of each target; according to the number of targets corresponding to the attributes of each target, the display target and the attributes of the display target are sent to the terminal.
  • extracting the target set from the index library includes: searching the index library with the image content in the image to be searched from the index library. Targets with similar image content; extracting the target set from the searched targets based on the principle of similarity.
  • determining the number of targets corresponding to the attribute of each target includes: calculating the number of occurrences of each target attribute in the target set; The number of occurrences of the attributes of the target in the target set determines the number of targets corresponding to the attributes of each target.
  • sending the display target and the attributes of the display target to the terminal includes: according to the number of targets corresponding to the attributes of each target, The attributes of each target are sorted; according to the sorting result, the display target and the attributes of the display target are sent to the terminal.
  • sending the display target and the attributes of the display target to the terminal includes: selecting from the ranking result to the terminal according to the number of display positions of the terminal The target attribute displayed by the terminal; according to the target attribute displayed to the terminal, the target attribute and the display target corresponding to the target attribute are sent to the terminal.
  • the method further includes: in the target set, if a target has multiple types of similar or identical promotional information, generating one type of promotional information based on the multiple types of similar or identical promotional information.
  • the method further includes: The attribute operation is to send the display target corresponding to the attribute of the display target specified by the user to the terminal.
  • the third aspect of the present disclosure provides an image-based search method, which is applied to a terminal, and the method includes: sending an image to be searched to a server, so that the server obtains an index library from the image content in the image to be searched. Extract the target set in the target set, determine the target number corresponding to the attribute of each target according to the attribute of each target in the target set, and send the display target and the display to the terminal according to the target number corresponding to the attribute of each target The attributes of the target; receiving the display target and the attributes of the display target.
  • the method further includes: receiving the attribute of the display target specified by the user, so that the server responds to the user-specified attribute operation of the display target , And send a display target corresponding to the attribute of the display target specified by the user to the terminal; receive a display target corresponding to the attribute of the display target specified by the user.
  • a third aspect of the present disclosure provides an image-based search device, which is applied to a server.
  • the device includes: an extraction module for extracting a target set from an index library according to the image content in the image to be searched; a determination module, It is used to determine the number of targets corresponding to the attributes of each target according to the attributes of each target in the target set; the first sending module is used to send display targets to the terminal according to the number of targets corresponding to the attributes of each target And the attributes of the display target.
  • the above-mentioned extraction module includes: a search module, configured to search for a target similar to the image content from the index library according to the image content in the image to be searched; an extraction sub-module, The target set is extracted from the searched targets based on the principle of similarity.
  • the above-mentioned determination module includes: a calculation module for calculating the number of occurrences of the attributes of each target in the target set; and a determining sub-module for calculating the attributes of each target in the target set The number of occurrences determines the number of targets corresponding to the attributes of each target.
  • the above-mentioned first sending module includes: a sorting module, configured to sort the attributes of each target according to the number of targets corresponding to the attributes of each target; As a result, the display target and the attributes of the display target are sent to the terminal.
  • the above-mentioned first sending submodule includes: a selection module, configured to select the target attribute to be displayed to the terminal from the ranking result according to the number of display positions of the terminal; the first sending submodule The sub-module of is configured to send the target attribute and the display target corresponding to the target attribute to the terminal according to the target attribute displayed to the terminal.
  • the device further includes: a generating module, in the target set, if a target has multiple types of similar or identical promotional information, generate a type of promotional information based on multiple types of similar or identical promotional information .
  • the device further includes: a response module, configured to send a display target corresponding to the attribute of the display target specified by the user to the terminal in response to the user-specified attribute operation of the display target.
  • a response module configured to send a display target corresponding to the attribute of the display target specified by the user to the terminal in response to the user-specified attribute operation of the display target.
  • a fourth aspect of the present disclosure provides a terminal for information search.
  • the terminal includes: an image sending device configured to send an image to be searched to a server, so that the server will Search for the image content in the image to extract the target set from the index library, and determine the number of targets corresponding to the attributes of each target according to the attributes of each target in the target set, and the number of targets corresponding to the attributes of each target Sending the display target and the attributes of the display target to the terminal; a receiving device configured to receive the display target and the attributes of the display target; a display device configured to display the display The attributes of the target and the display target.
  • the terminal further includes: an input device configured to receive the attributes of the display target specified by the user, and send the attributes of the display target specified by the user to the server, so that all The server responds to the user-specified attribute operation of the display target, and sends to the terminal a display target corresponding to the attribute of the display target specified by the user;
  • the receiving device is also configured to receive the display specified by the user The display target corresponding to the attribute of the target; the display device is further configured to display the display target corresponding to the attribute of the display target specified by the user.
  • the terminal further includes an image acquisition device configured as an acquisition device for acquiring an image to be searched.
  • the image acquisition device includes a camera installed on the terminal.
  • the display device and the input device are integrated into a touch-sensitive display device, and the touch-sensitive display device is configured to display the display target and the attributes of the display target, and input the attributes of the display target specified by the user .
  • a fifth aspect of the present disclosure provides a server including: one or more processors, and a storage device.
  • the storage device is used to store one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the image-based search method described in the first aspect above.
  • a sixth aspect of the present disclosure provides a computer-readable medium having executable instructions stored thereon, and when the instructions are executed by a processor, the processor executes the image-based search method described in the first aspect.
  • a seventh aspect of the present disclosure provides a computer program including computer-executable instructions, which are used to implement the image-based search method described in the first aspect when executed.
  • An eighth aspect of the present disclosure provides a terminal including: one or more processors and a storage device.
  • the storage device is used to store one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the image-based search method described in the second aspect above.
  • the terminal includes a camera, and the camera is used to obtain an image to be searched.
  • the terminal further includes a touch-sensitive display configured to display the display target and the attributes of the display target, and input the attributes of the display target specified by the user.
  • a ninth aspect of the present disclosure provides a computer-readable medium having executable instructions stored thereon, and when the instructions are executed by a processor, the processor executes the image-based search method described in the second aspect above.
  • a tenth aspect of the present disclosure provides a computer program including computer-executable instructions, which when executed are used to implement the image-based search method described in the second aspect.
  • the technical solution server can extract a target set from an index library according to the image content in the image to be searched.
  • Each target in the target set has attributes similar to the image content, and according to the target The attributes of each target in the set are determined, the number of targets corresponding to the attributes of each target is determined, and the display target and the attributes of the display target are sent to the terminal according to the number of targets corresponding to the attributes of each target, so that users can quickly , Accurately filter out the target you want to browse, greatly improving the user experience.
  • the terminal can send the image to be searched to the server, so that the server extracts the target set from the index library according to the image content in the image to be searched, and according to each target set
  • the attribute of the target determines the number of targets corresponding to the attribute of each target, and sends the display target and the attribute of the display target to the terminal according to the target number corresponding to the attribute of each target, so that the terminal can receive the display target and
  • the user can quickly and accurately screen out the target he wants to browse, which greatly improves the user experience.
  • FIG. 1 shows a schematic diagram of an exemplary system architecture 100 of an image-based search method or an image-based search device to which an embodiment of the present invention can be applied;
  • Fig. 2 schematically shows a flowchart of an image-based search method applied to a server according to an embodiment of the present disclosure
  • FIG. 3 schematically shows a flowchart of an image-based search method applied to a server according to another embodiment of the present disclosure
  • Fig. 4 schematically shows a flowchart of an image-based search method applied to a server according to another embodiment of the present disclosure
  • Fig. 5 schematically shows a flowchart of an image-based search method applied to a server according to another embodiment of the present disclosure
  • Fig. 6 schematically shows a flowchart of an image-based search method applied to a server according to another embodiment of the present disclosure
  • Fig. 7 schematically shows a flowchart of an image-based search method applied to a terminal according to an embodiment of the present disclosure
  • FIG. 8A schematically shows a schematic diagram of interaction between a terminal and a server according to an embodiment of the present disclosure
  • FIG. 8B schematically shows a schematic diagram of the target and target attributes shown in the related art
  • FIG. 8C schematically shows a schematic diagram of a displayed target and target attributes according to an embodiment of the present disclosure
  • Fig. 9 schematically shows a block diagram of an image-based search device applied to a server according to an embodiment of the present disclosure
  • Fig. 10 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure
  • Fig. 11 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure
  • Fig. 12 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure
  • FIG. 13 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure
  • Fig. 14 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure
  • Fig. 15 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure
  • FIG. 16 schematically shows a block diagram of a terminal for confidence search according to an embodiment of the present disclosure
  • Fig. 17 schematically shows a structural diagram of a server according to an embodiment of the present disclosure.
  • FIG. 18 schematically shows a structural diagram of a terminal according to an embodiment of the present disclosure.
  • FIG. 1 shows a schematic diagram of an exemplary system architecture 100 of an image-based search method or an image-based search device to which an embodiment of the present invention can be applied.
  • the system architecture 100 may include one or more of terminal devices 101, 102, 103, a network 104 and a server 105.
  • the network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105.
  • the network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables.
  • the numbers of terminal devices, networks, and servers in FIG. 1 are merely illustrative. According to implementation needs, there can be any number of terminal devices, networks and servers.
  • the server 105 may be a server cluster composed of multiple servers.
  • the user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages and so on.
  • the terminal devices 101, 102, and 103 may be various electronic devices with display screens, including but not limited to smart phones, tablet computers, portable computers, desktop computers, and so on.
  • the server 105 may be a server that provides various services.
  • the server 105 can obtain the image to be searched from the terminal device 103 (or the terminal device 101 or 102), and then can extract the target set from the index library according to the image content in the image to be searched, and according to the target set
  • the attributes of each target determine the number of targets corresponding to the attributes of each target, and send the display target and the attributes of the display target to the terminal according to the number of targets corresponding to the attributes of each target, so that users can quickly and accurately Filter out the target you want to browse to, greatly improving the user experience.
  • the image-based search method provided by the embodiment of the present invention is generally executed by the server 105, and accordingly, the image-based search device is generally set in the server 105.
  • some terminals may have functions similar to those of a server to execute the method. Therefore, the image-based search method provided by the embodiment of the present invention is not limited to be executed on the server side.
  • Fig. 2 schematically shows a flowchart of an image-based search method applied to a server according to an embodiment of the present disclosure.
  • the image-based search method applied to the server includes steps S110 to S130.
  • step S110 the target set is extracted from the index library according to the image content in the image to be searched.
  • step S120 the number of targets corresponding to the attributes of each target is determined according to the attributes of each target in the target set.
  • step S130 the display target and the attributes of the display target are sent to the terminal according to the number of targets corresponding to the attributes of each target.
  • the method can extract the target set from the index library according to the image content in the image to be searched, and determine the number of targets corresponding to the attribute of each target according to the attribute of each target in the target set, and according to the attribute of each target
  • the corresponding number of targets, the display target and the attributes of the display target are sent to the terminal, so that users can quickly and accurately screen out the targets they want to browse, which greatly improves user experience.
  • the image to be searched is a product image
  • the method of the present disclosure helps users to quickly and accurately screen out the target product from a large number of recalled products, greatly improving the user experience, and ultimately increasing the total transaction volume.
  • the aforementioned image to be searched may include, but is not limited to, product images, person images, animal images, and building images.
  • the above-mentioned image to be searched is a product image
  • the image content of the product image can be a product, a person, an animal, or a building.
  • it can also be the brand of the product, the color of the product, the shape of the product, and the three-level category of the product.
  • the image content of the commodity image may be a commodity.
  • a large number of targets can be searched from the index library according to the image content of the commodity image, and the targets are similar to the image content.
  • the product is a mobile phone
  • a product similar to the mobile phone can be searched from the index library according to the image content.
  • the image content of the image to be searched is the image content of a person image, an animal image, or a building image
  • the corresponding person, animal, and building can be searched from the index library based on the image content.
  • the index database when the image content of the image to be searched is the brand, color, shape, and three-level category of the product, the index database can be searched for products that are similar or identical to the brand according to the brand of the product. aims. According to the color of the product, the index database can be searched for a target similar or the same as the color. According to the shape of the product, a target similar to or the same as the shape can be searched from the index library. According to the three-level category of the commodity, the index database can be searched to have similar or identical targets with the three-level category. In addition, since the implementation process of searching for a target from the index library based on other images to be searched is the same or similar to the implementation process based on the image to be searched as a commodity image, it will not be repeated here.
  • the aforementioned target set may contain content similar to the image content of the image to be searched.
  • the image content of the image to be searched is a commodity, and the content contained in the target set is a commodity similar to the commodity.
  • the image content of the image to be searched is a person, and the content contained in the target set is a person similar to the person.
  • the image content of the image to be searched is an animal, and the content contained in the target set is an animal similar to the animal.
  • the image content of the image to be searched is a building, and the content contained in the target set is a building similar to the building.
  • the above-mentioned target set includes targets having similar image content to the image to be searched.
  • the image to be searched is an image of a product
  • the image content of the product includes the brand of the product, the color of the product, the shape of the product, and the three-level category of the product.
  • the image to be searched is an image of a mobile phone
  • the image content of the mobile phone may be Huawei, white, rectangle, communication equipment, and so on. According to each image content of the mobile phone, it can be sent to the index library to search for mobile phones with similar content to the image, and each search result can be used as the aforementioned mobile phone collection, that is, the target collection.
  • the attributes of each target are obtained by traversing each target in the above-mentioned target set.
  • the above-mentioned target collection is a product collection
  • the attributes of each product can be obtained by traversing each product in the product collection (for example, the attributes can be brand, three-level category, style, etc.). Then determine the number of targets corresponding to the attributes of each target according to the attributes of each target, so that the display target and the attributes of the display target can be sent to the terminal according to the number of targets corresponding to the attributes of each target, so that the user You can quickly and accurately filter out the target you want to browse, greatly improving the user experience.
  • the above method further includes: in response to the user specifying the attribute of the display target, sending to the terminal a display target corresponding to the attribute of the display target specified by the user In this way, the user-specified target can be quickly filtered from the display target in step S130 and the attributes of the display target, which further saves the user time for screening.
  • the attributes of the display target specified by the user may be generated based on the attributes of each target in the target set, so as to realize that the terminal can be recommended and specified by the user in response to the attribute operation of the display target specified by the user.
  • the display target corresponding to the attribute of the display target.
  • Fig. 3 schematically shows a flowchart of an image-based search method applied to a server according to another embodiment of the present disclosure.
  • step S110 may specifically include step S111 and step S112.
  • step S111 according to the image content in the image to be searched, an object similar to the image content is searched from the index library.
  • step S112 the target set is extracted from the searched targets based on the principle of similarity.
  • This method can search for objects similar to the image content from the index library according to the image content in the image to be searched, and then extract the target set from the searched objects based on the principle of similarity. From the targets searched for by searching for each image content in the image, extracting targets that are relatively similar to each image content makes it easier to count the number of targets corresponding to the attributes of each target.
  • the image attribute image content of the commodity image may be a commodity.
  • 58 products that are similar to the product can be searched out from the index database.
  • 20 products can be extracted from 58 products that are similar to the product and used as a product collection. That is, the above-mentioned target set. Determining the target set in this way makes it easier to count the number of targets corresponding to the attributes of each target. Among them, the number of targets extracted from the search results can be specified by the terminal in the request parameters.
  • the image content of the product image may also be the brand of the product, the color of the product, the shape of the product, the three-level category of the product, and so on.
  • the brand of the product 58 objects similar to the brand are searched from the index library, 62 objects with the color similar to the color are searched from the index library according to the color of the product, and from the index library according to the shape of the product Searched for 50 objects with similar shapes, and searched out 200 objects with similar shapes from the index database according to the three-level category of the product.
  • the number of objects in each search result The sum is 370.
  • the principle of similarity it is possible to preliminarily extract objects with relatively similar content from each image content in the image to be searched, and use the extracted results as the target set.
  • 20 targets can be extracted from 58 targets similar to the brand
  • 26 targets are extracted from 62 targets similar to the color
  • 50 targets with the same color can be searched from the index library.
  • 15 objects with similar shapes are extracted
  • 30 objects are extracted from 200 objects with similar three-level categories
  • the extracted results are used as the target set, that is, the target set includes 91 targets, so that subsequent It is easier to count the number of targets corresponding to the attributes of each target.
  • the number of targets extracted from the search results can be specified by the terminal in the request parameters.
  • the image content of the product image may be the brand of the product, the color of the product, the shape of the product, the three-level category of the product, and so on.
  • the brand of the product 58 objects similar to the brand are searched from the index library, 62 objects with the color similar to the color are searched from the index library according to the color of the product, and from the index library according to the shape of the product Searched for 50 objects with similar shapes, and searched out 200 objects with similar shapes from the index database according to the three-level category of the product.
  • the number of objects in each search result The sum is 370.
  • the principle of similarity it is possible to preliminarily extract objects with relatively similar content from each image content in the image to be searched, and use the extracted results as the target set.
  • 20 targets can be extracted from 58 targets similar to the brand
  • 26 targets are extracted from 62 targets similar to the color
  • 50 targets with the same color can be searched from the index library.
  • 15 objects with similar shapes are extracted
  • 30 objects are extracted from 200 objects with similar three-level categories
  • the extracted results are used as the target set, that is, the target set includes 91 targets, so that subsequent It is easier to count the number of targets corresponding to the attributes of each target.
  • the number of targets extracted from the search results can be specified by the terminal in the request parameters.
  • the above method further includes: in the target set, if a target has multiple types of similar or identical promotional information, generating one type of promotional information based on multiple types of similar or identical promotional information.
  • a target has multiple types of similar or identical promotional information
  • generating one type of promotional information based on multiple types of similar or identical promotional information.
  • 26 targets are extracted from 62 targets with similar colors, and among the 26 targets extracted, many targets contain promotional information.
  • the promotion information may be 50% off for purchases of 10 or more, 30% for purchases of 100 or more, and 20% for purchases of 5 or more.
  • the total purchase amount is 100 minus 10
  • the total purchase amount is 1000 minus 100
  • the total purchase is 10,000 minus 500, etc.
  • a kind of promotion information can be generated based on multiple similar or identical promotion information, for example , Aggregate multiple full M minus N into full minus, aggregate multiple full M minus N into full discount, etc., which is convenient for users to watch.
  • Fig. 4 schematically shows a flowchart of an image-based search method applied to a server according to another embodiment of the present disclosure.
  • step S120 may specifically include step S121 and step S122.
  • step S121 the number of occurrences of each target attribute in the target set is calculated.
  • step S122 the number of targets corresponding to the attributes of each target is determined according to the number of occurrences of the attributes of each target in the target set.
  • This method can determine the number of targets corresponding to the attributes of each target according to the number of occurrences of the attributes of each target in the target set, so that the subsequent display target and the number of targets corresponding to the attributes of each target are sent to the terminal.
  • the attributes of the display target are described, so that users can quickly and accurately filter out the target they want to browse, which greatly improves the user experience.
  • the image attribute image content of the commodity image may be a commodity.
  • 58 products that are similar to the product can be searched out from the index database.
  • 20 products can be extracted from 58 products that are similar to the product and used as a product collection.
  • the attribute value can be brand ID, three-level category ID, style ID, etc.
  • the attribute value can be brand ID, three-level category ID, style ID, etc.
  • the number of times that the style ID appears in the product collection, and further, the number of products corresponding to the brand ID, the third-level category ID, and the style ID is determined according to the number of times the brand ID, the third-level category ID, and the style ID appear in the product collection. Specifically, determine whether the brand ID, the third-level category ID, and the style ID have appeared. If they have appeared, add 1 to the number of products corresponding to the attribute ID, otherwise add the attribute ID and set the corresponding number of products to 1. In this way, the number of products corresponding to the brand ID, three-level category ID, and style ID can be quickly determined.
  • the image content of the product image may be the brand of the product, the color of the product, the shape of the product, the three-level category of the product, and so on.
  • the index database can be searched for goals that are similar or the same as the brand. At this time, the attribute value of each goal that is similar or the same as the brand can be obtained, such as the brand ID of the goal. .
  • traversing the search results from the index database according to the brand of the product can calculate the number of times the target's brand ID appears in the search results, and further, according to the number of times the target's brand ID appears in the target set Determine the target quantity corresponding to the brand ID of the target. Specifically, determine whether the brand ID has already appeared, if it does, add 1 to the number of products corresponding to the attribute ID, otherwise add the attribute ID and set the corresponding number of products to 1, which can be quickly determined in this way The number of targets corresponding to the brand ID of the target.
  • Fig. 5 schematically shows a flowchart of an image-based search method applied to a server according to another embodiment of the present disclosure.
  • step S130 may specifically include step S131 and step S132.
  • step S131 the attributes of each target are sorted according to the number of targets corresponding to the attributes of each target.
  • step S132 according to the sorting result, the display target and the attributes of the display target are sent to the terminal.
  • This method can sort the attributes of each target according to the number of targets corresponding to the attributes of each target, and then send the display target and the attributes of the display target to the terminal according to the sorting result, so that the user can Quickly and accurately filter out the target you want to browse, which greatly improves the user experience.
  • the image attribute image content of the commodity image may be a commodity.
  • 58 products that are similar to the product can be searched from the index database.
  • 20 products can be extracted from 58 products that are similar to the product and used as a product collection.
  • the attribute value can be brand ID, three-level category ID, style ID, etc.
  • the number of appearances of the style ID in the product collection, and further, the number of products corresponding to the brand ID, the third-level category ID, and the style ID is determined according to the number of appearances of the brand ID, the third-level category ID, and the style ID in the product collection. Specifically, determine whether the brand ID, the third-level category ID, and the style ID have appeared. If they have appeared, add 1 to the number of products corresponding to the attribute ID, otherwise add the attribute ID and set the corresponding number of products to 1.
  • the number of products corresponding to the brand ID, three-level category ID, and style ID can be quickly determined.
  • the brand ID, the third-level category ID, and the style ID are sorted based on the number of products corresponding to the brand ID, the third-level category ID, and the style ID, and the TopK attributes are taken as the summary result and returned to the terminal.
  • K is determined according to the display situation of the terminal.
  • the image content of the product image may be the brand of the product, the color of the product, the shape of the product, the three-level category of the product, and so on.
  • the index database can be searched for goals that are similar or the same as the brand. At this time, the attribute value of each goal that is similar or the same as the brand can be obtained, such as the brand ID of the goal. .
  • traversing the search results from the index database according to the brand of the product can calculate the number of times the target's brand ID appears in the search results, and further, according to the number of times the target's brand ID appears in the target set Determine the target quantity corresponding to the brand ID of the target. Specifically, it is determined whether the brand ID has already appeared, if it has appeared, the number of products corresponding to the attribute ID is increased by 1, otherwise the attribute ID is added and the corresponding number of products is set to 1. Similarly, according to the above calculation method, the target quantity corresponding to the color ID of the product, the shape ID of the product, and the three-level category ID of the product can also be calculated.
  • the attribute IDs are sorted based on the number of targets corresponding to each attribute ID, and TopK attributes are taken as the summary result and returned to the terminal. Among them, K is determined according to the display situation of the terminal.
  • Fig. 6 schematically shows a flowchart of an image-based search method applied to a server according to another embodiment of the present disclosure.
  • step S132 may specifically include step S132-1 and step S132-2.
  • step S132-1 the target attribute to be displayed to the terminal is selected from the ranking result according to the number of display positions of the terminal.
  • step S132-2 according to the target attribute displayed to the terminal, the target attribute and the display target corresponding to the target attribute are sent to the terminal.
  • the method can select the target attributes displayed to the terminal from the above sorting results according to the number of display positions of the terminal, and the target attributes and display targets determined in this way to be displayed to the terminal are more flexible, and the user experience is further improved.
  • the number of display positions of the aforementioned terminal may be determined by the type of terminal.
  • the terminal is a mobile device (for example, a mobile phone, a tablet computer, etc.), and the terminal is a variety of computers (for example, a laptop, a desktop computer, etc.). Compared with various computers, the number of display positions of mobile devices may be less. some.
  • Fig. 7 schematically shows a flowchart of an image-based search method applied to a terminal according to an embodiment of the present disclosure.
  • the image-based search method applied to the terminal includes step S210 and step S220.
  • step S210 the image to be searched is sent to the server, so that the server extracts the target set from the index library according to the image content in the image to be searched, and determines each target set according to the attribute of each target in the target set.
  • the target quantity corresponding to the attribute of the target, and the display target and the attribute of the display target are sent to the terminal according to the target quantity corresponding to the attribute of each target.
  • step S220 the display target and the attributes of the display target are received.
  • the method can send the image to be searched to the server, so that the server extracts the target set from the index library according to the image content in the image to be searched, and determines the target set according to the attribute of each target in the target set.
  • the number of targets corresponding to the attributes, and the display target and the attributes of the display target are sent to the terminal according to the target number corresponding to the attributes of each target, so that the terminal can receive the display target and the attributes of the display target. Time users can quickly and accurately filter out the target they want to browse, which greatly improves the user experience.
  • the method further includes: receiving the attribute of the display target specified by the user, so that the server responds to the attribute operation of the display target specified by the user, and sends to the terminal The display target corresponding to the attribute of the display target specified by the user; and the display target corresponding to the attribute of the display target specified by the user is received.
  • the method can receive the attribute of the display target specified by the user, so that the server responds to the attribute operation of the display target specified by the user, and sends the display target corresponding to the attribute of the display target specified by the user to the terminal, and then The display target corresponding to the attribute of the display target designated by the user is received, so that the target designated by the user can be quickly screened out, which further saves the user time for screening.
  • the interaction scene between the terminal and the server S1, the user uses the terminal to send a mobile phone image to the server; S2, when the server receives the mobile phone image, it obtains the image content of the mobile phone image (ie, mobile phone) by identifying the mobile phone image; S3 , Search for mobile phones similar to the image content from each index library according to the acquired image content; S4, extract mobile phones that are more similar to the image content from each search result based on the principle of similarity, and use them as a product collection; S5: Obtain the attributes of each mobile phone by traversing the product collection; S6: After the traversal is completed, calculate the number of times each mobile phone’s attributes appear in the product collection; S7, according to the attributes of each mobile phone appear in the product collection The number of times to determine the number of mobile phones corresponding to the attributes of each target; S8, according to the number of mobile phones corresponding to the attributes of each mobile phone, send the display target and the attributes of the display target to the terminal, so that users can quickly and accurately filter out themselves Want to browse to the
  • the terminal receives the user's operation on the attributes of the above display target; S10, in response to the user specifying the attribute operation of the display target, sends to the terminal a display target corresponding to the attribute of the display target specified by the user, so that The display target in step S8 and the attributes of the display target quickly screen out the target specified by the user, which further saves the user time for screening.
  • FIG. 8B and FIG. 8C for the interface changes in displaying commodities and commodity attributes.
  • Figure 8B shows the search results based on a headset image in the related technology.
  • A1 is the product attribute corresponding to the image content
  • A2 is the search result based on a headset image.
  • Figure 8C shows the search result of the present disclosure based on a headset image.
  • A1 is the product attribute corresponding to the image content
  • A2 is the search result based on a headset image.
  • A1 The product attributes and product coverage in A2 are relatively small, and A3 is also displayed in the search results of the present disclosure, so as to realize that multiple full M minus N can be aggregated into full minus, and multiple full M can be discounted by N Summarize into full folds, etc., which is not only convenient for users to watch, but also reduces the requirements for terminal display positions.
  • the terminal can also display other attributes of the product in addition to the three-level categories included in A1, such as the style of the product (for example, simple and modern, Sports, etc.), product brands (for example, Huawei, Huawei, Huawei, LG), etc.
  • the style of the product for example, simple and modern, Sports, etc.
  • product brands for example, Huawei, Huawei, LG
  • users can not only click the product attributes in A1, but also click the product style and product brand.
  • the display target in step S8 and the attributes of the display target quickly screen out the target specified by the user, which further saves the user time for screening.
  • Fig. 9 schematically shows a block diagram of an image-based search device applied to a server according to an embodiment of the present disclosure.
  • the image-based search device 200 includes an extraction module 210, a determination module 220, and a first sending module 230.
  • the extraction module 210 is configured to extract the target set from the index library according to the image content in the image to be searched.
  • the determining module 220 is configured to determine the number of targets corresponding to the attributes of each target according to the attributes of each target in the target set.
  • the first sending module 230 is configured to send the display target and the attributes of the display target to the terminal according to the number of targets corresponding to the attributes of each target.
  • the image-based search device 200 can extract a target set from an index library according to the image content in the image to be searched.
  • Each target in the target set has attributes similar to the image content, and according to each target set in the target set.
  • the attributes of each target are determined, the number of targets corresponding to the attributes of each target is determined, and the display target and the attributes of the display target are sent to the terminal according to the number of targets corresponding to the attributes of each target, so that users can quickly and accurately Filter out the target you want to browse, greatly improving the user experience.
  • the image to be searched is a product image
  • the method of the present disclosure helps users to quickly and accurately screen out the target product from a large number of recalled products, greatly improving the user experience, and ultimately increasing the total transaction volume.
  • the image-based search device 200 is used to implement the image-based search method described in the embodiment of FIG. 2.
  • Fig. 10 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure.
  • the aforementioned extraction module 210 includes a search module 211 and an extraction sub-module 212.
  • the search module 211 is configured to search for objects similar to the image content from the index library according to the image content in the image to be searched.
  • the extraction sub-module 212 extracts the target set from the searched targets based on the principle of similarity.
  • the extraction module 210 can search for objects similar to the image content from the index library according to the image content in the image to be searched, and then extract the object set from the searched objects based on the principle of similarity, so that it can be preliminarily obtained from From the targets searched out according to the content of each image in the image to be searched, the targets that are relatively similar to the content of each image are extracted, making it easier to subsequently count the number of targets corresponding to the attributes of each target.
  • the extraction module 210 is used to implement the image-based search method described in the embodiment of FIG. 3.
  • Fig. 11 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure.
  • the aforementioned determining module 220 includes a calculating module 221 and a determining sub-module 222.
  • the calculation module 221 is configured to calculate the number of occurrences of each target attribute in the target set.
  • the determining sub-module 222 is configured to determine the number of targets corresponding to the attributes of each target according to the number of times the attributes of each target appear in the target set.
  • the determining module 220 can determine the number of targets corresponding to the attributes of each target according to the number of occurrences of the attributes of each target in the target set, so that subsequent display targets are sent to the terminal according to the number of targets corresponding to the attributes of each target. And the attributes of the display target, so that the user can quickly and accurately filter out the target he wants to browse, which greatly improves the user experience.
  • the determining module 220 is used to implement the image-based search method described in the embodiment of FIG. 4.
  • Fig. 12 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure.
  • the above-mentioned first sending module 230 includes a sorting module 231 and a first sending sub-module 232.
  • the sorting module 231 is configured to sort the attributes of each target according to the number of targets corresponding to the attributes of each target.
  • the first sending submodule 232 is configured to send the display target and the attributes of the display target to the terminal according to the sorting result.
  • the first sending module 230 may sort the attributes of each target according to the number of targets corresponding to the attributes of each target, and then send the display target and the attributes of the display target to the terminal according to the sorting result, This allows users to quickly and accurately filter out the targets they want to browse, which greatly improves user experience.
  • the first sending module 230 is used to implement the image-based search method described in the embodiment of FIG. 5.
  • Fig. 13 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure.
  • the aforementioned first sending submodule 232 includes a selection module 232-1 and a submodule 232-2 of the first sending submodule.
  • the selecting module 232-1 is configured to select the target attribute to be displayed to the terminal from the ranking result according to the number of display positions of the terminal.
  • the submodule 232-2 of the first sending submodule is configured to send the target attribute and the display target corresponding to the target attribute to the terminal according to the target attribute displayed to the terminal.
  • the first sending sub-module 232 can select the target attribute to be displayed to the terminal from the above sorting result according to the number of display positions of the terminal, and the target attribute to be displayed to the terminal determined in this way is more flexible, which further improves users. Experience.
  • the first recommendation submodule 232 is used to implement the image-based search method described in the embodiment of FIG. 6.
  • Fig. 14 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure.
  • the image-based search apparatus 300 includes a generation module 310.
  • the generating module 310 in the target set, if a target has multiple types of similar or identical promotional information, generates one type of promotional information based on multiple types of similar or identical promotional information.
  • the image-based search device 200 can generate a kind of promotion information based on a variety of similar or identical promotion information, which is convenient for users to watch.
  • Fig. 15 schematically shows a block diagram of an image-based search device applied to a server according to another embodiment of the present disclosure.
  • the image-based search device 400 includes a response module 410.
  • the response module 410 is configured to send a display target corresponding to the attribute of the display target specified by the user to the terminal in response to the user-specified attribute operation of the display target.
  • the image-based search device 400 can send the display target corresponding to the attribute of the display target specified by the user to the terminal in response to the attribute operation of the display target specified by the user, so that the display target and the display can be sent to the terminal.
  • the user-specified target can be quickly filtered out of the target's attributes, which further saves the user the time spent in screening.
  • the sub-module 232-2 of the first sending sub-module, the generation module 310, and the response module 410 may be combined into one module for implementation, or any one of the modules may be split into multiple modules. Or, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module.
  • the extraction module 210, the search module 211, the extraction sub-module 212, the determination module 220, the calculation module 221, the determination sub-module 222, the first sending module 230, the sorting module 231, the first sending sub-module 232, At least one of the selection module 232-1, the submodule 232-2 of the first sending submodule, the generation module 310, and the response module 410 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), Programmable logic array (PLA), system on chip, system on substrate, system on package, application specific integrated circuit (ASIC), or can be implemented in hardware or firmware such as any other reasonable way to integrate or package the circuit, Or it can be realized by an appropriate combination of software, hardware, and firmware.
  • FPGA field programmable gate array
  • PLA Programmable logic array
  • ASIC application specific integrated circuit
  • At least one of the sub-module 232-2 of the first sending sub-module, the generating module 310, and the response module 410 can be at least partially implemented as a computer program module, and when the program is run by a computer, the function of the corresponding module can be executed .
  • FIG. 16 schematically shows a block diagram of a terminal for information search according to an embodiment of the present disclosure.
  • the terminal 500 for information search includes an image sending device 510, a receiving device 520, and a display device 530.
  • the image sending device 510 is configured to send the image to be searched to the server, so that the server extracts a target set from the index library according to the image content in the image to be searched, and according to the target
  • the attribute of each target in the set determines the number of targets corresponding to the attribute of each target, and sends the display target and the attribute of the display target to the terminal according to the number of targets corresponding to the attribute of each target.
  • the receiving device 520 is configured to receive the display target and the attributes of the display target.
  • the display device 530 is configured to display the display target and the attributes of the display target.
  • the terminal 500 for information search may send the image to be searched to the server, so that the server extracts the target set from the index library according to the image content in the image to be searched, and according to the target set of each target in the target set.
  • the attribute determines the target number corresponding to the attribute of each target, and sends the display target and the attribute of the display target to the terminal according to the target number corresponding to the attribute of each target, so that the terminal can receive the display target and the display target. Display the attributes of the target, at this time users can quickly and accurately filter out the target they want to browse, which greatly improves the user experience.
  • the terminal 500 for information search is used to implement the image-based search method described in the embodiment of FIG. 7.
  • the information search terminal 500 further includes an image acquisition device configured to acquire an image to be searched.
  • the above-mentioned image acquisition device includes a camera installed on the terminal.
  • the information search terminal 500 further includes: an input device configured to receive the attributes of the display target specified by the user, and send the attributes of the display target specified by the user to the The server, so that the server responds to the user-specified attribute operation of the display target, and sends the display target corresponding to the attribute of the user-specified display target to the terminal; the receiving device 520 is also configured to receive and The display target corresponding to the attribute of the display target specified by the user; the display device 530 is further configured to display the display target corresponding to the attribute of the display target specified by the user.
  • the above-mentioned display device 530 and the above-mentioned input device are integrated into a touch-sensitive display device, and the touch-sensitive display device is configured to display the display target and the attributes of the display target, and input the display target specified by the user. Attributes.
  • Fig. 17 schematically shows a schematic diagram of a server of an embodiment of the present disclosure.
  • the server may be the server 105 in FIG. 1.
  • the server can be used to execute the image-based search method applied to the server provided in the above embodiment.
  • the server 600 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 610 (for example, one or more processors) and a memory 620.
  • CPU central processing units
  • One or more storage media 630 for storing application programs 633 or data 632 for example, one or one storage device with a large amount of storage.
  • the memory 620 and the storage medium 630 may be short-term storage or persistent storage.
  • the program stored in the storage medium 630 may include one or more modules (not shown in the figure), and each module may include a series of command operations on the server.
  • the central processing unit 610 may be configured to communicate with the storage medium 630, and execute a series of instruction operations in the storage medium 630 on the server 600.
  • the server 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input and output interfaces 660, and/or one or more operating systems 631, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc. It is configured that one or more central processors 610 can execute operations performed by the server in the above method embodiments.
  • the image to be searched can be received through the wired or wireless network interface 650 or the input/output interface 660, and then the image to be searched can be received through the application 633.
  • the image is processed to obtain the image content in the image to be searched, and the application 633 can extract the target set from the index library according to the image content in the image to be searched, and determine the attribute of each target in the target set.
  • the display target and the attribute of the display target are sent to the terminal according to the target quantity corresponding to the attribute of each target.
  • the index library may be the index library in the aforementioned memory 620 or the aforementioned storage medium.
  • the application program 633 e.g., search engine
  • the application program 633 can search the index library according to the image content in the image to be searched and search for images similar to the image content.
  • the target set is extracted from the searched targets based on the principle of similarity.
  • the application program 633 can calculate the number of times the attributes of each target appear in the target set, and according to the attributes of each target in the target The number of occurrences in the set determines the number of targets corresponding to the attributes of each target.
  • the application 633 can sort the attributes of each target according to the number of targets corresponding to the attributes of each target, and The sorting result sends the display target and the attributes of the display target to the aforementioned terminal.
  • the application program 633 e.g., search engine
  • the application program 633 can select the target attribute to be displayed to the terminal from the ranking result according to the number of display positions of the terminal, and according to The target attribute displayed to the above terminal sends the target attribute and the display target corresponding to the target attribute to the terminal.
  • the application 633 for example, search engine
  • the central processing unit 610 executes the above-mentioned application 633
  • the application 633 can be based on multiple Similar or identical promotional information generates a kind of promotional information.
  • the application 633 (for example, search engine) is executed by the central processing unit 610, the application 633 sends the display target and the display target to the terminal according to the number of targets corresponding to the attributes of each target. After displaying the attributes of the target, the application 633 can also respond to the user-specified attribute operation of the display target, and then send the display target corresponding to the attribute of the display target specified by the user to the aforementioned terminal.
  • the application 633 for example, search engine
  • the application 633 sends the display target and the display target to the terminal according to the number of targets corresponding to the attributes of each target. After displaying the attributes of the target, the application 633 can also respond to the user-specified attribute operation of the display target, and then send the display target corresponding to the attribute of the display target specified by the user to the aforementioned terminal.
  • FIG. 18 is a schematic structural diagram of a terminal in an embodiment of the present disclosure.
  • the terminal can be used to implement the image-based search method applied to the terminal provided in the foregoing embodiment.
  • the terminal device 800 may include a communication unit 110, a memory 120 including one or more computer-readable storage media, an input unit 130, a touch-sensitive display 140, a sensor 150, an audio circuit 160, a wireless communication unit 170, including one or more The above processing core processor 180, power supply 190 and other components.
  • a communication unit 110 may include a communication unit 110, a memory 120 including one or more computer-readable storage media, an input unit 130, a touch-sensitive display 140, a sensor 150, an audio circuit 160, a wireless communication unit 170, including one or more
  • the above processing core processor 180, power supply 190 and other components including one or more
  • FIG. 18 does not constitute a limitation on the terminal device, and may include more or fewer components than shown in the figure, or a combination of certain components, or different component arrangements. among them:
  • the communication unit 110 may be used for receiving and sending signals during information transmission or communication.
  • the communication unit 110 may be an RF (Radio Frequency) circuit, router, modem, or other network communication equipment.
  • RF Radio Frequency
  • the communication unit 110 is an RF circuit, after receiving the downlink information of the base station, it is handed over to one or more processors 180 for processing; in addition, data related to the uplink is sent to the base station.
  • the RF circuit as a communication unit includes but is not limited to an antenna, at least one amplifier, a tuner, one or more oscillators, a subscriber identity module (SIM) card, a transceiver, a coupler, and an LNA (Low Noise Amplifier). Noise amplifier), duplexer, etc.
  • SIM subscriber identity module
  • LNA Low Noise Amplifier
  • the communication unit 110 may also communicate with the network and other devices through wireless communication.
  • Wireless communication can use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication, Global System for Mobile Communications), GPRS (General Packet Radio Service, General Packet Radio Service), CDMA (Code Division Multiple Access, code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service, short message service), etc.
  • the memory 120 may be used to store software programs and modules.
  • the processor 180 executes various functional applications and data processing by running the software programs and modules stored in the memory 120.
  • the memory 120 may mainly include a program storage area and a data storage area.
  • the program storage area may store an operating system, an application program required by at least one function (such as a sound playback function, an image playback function, etc.), etc.;
  • the data (such as audio data, phone book, etc.) created by the use of the terminal device 800, etc.
  • the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • the memory 120 may further include a memory controller to provide the processor 180 and the input unit 130 to access the memory 120.
  • the input unit 130 may be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
  • the input unit 130 may include a touch-sensitive surface 131 and other input devices 132.
  • the touch-sensitive surface 131 also called a touch screen or a touch pad, can collect user touch operations on or near it (for example, the user uses any suitable objects or accessories such as fingers, stylus, etc.) on or on the touch-sensitive surface 131. Operation near the touch-sensitive surface 131), and drive the corresponding connection device according to a preset program.
  • the touch-sensitive surface 131 may include two parts: a touch detection device and a touch controller.
  • the touch detection device detects the user's touch position, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it To the processor 180, and can receive and execute the commands sent by the processor 180.
  • the touch-sensitive surface 131 can be implemented in multiple types such as resistive, capacitive, infrared, and surface acoustic wave.
  • the input unit 130 may also include other input devices 132.
  • the other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackball, mouse, and joystick.
  • the touch-sensitive display 140 may be used to display information input by the user or information provided to the user and various graphical user interfaces of the terminal device 800. These graphical user interfaces may be composed of graphics, text, icons, videos, and any combination thereof.
  • the touch-sensitive display 140 may include a display panel 141.
  • the display panel 141 may be configured in the form of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc.
  • the touch-sensitive surface 131 may cover the display panel 141.
  • the touch-sensitive surface 131 detects a touch operation on or near it, it is transmitted to the processor 180 to determine the type of the touch event, and then the processor 180 responds to the touch event.
  • the type provides corresponding visual output on the display panel 141.
  • the touch-sensitive surface 131 and the display panel 141 are used as two independent components to realize input and input functions, in some embodiments, the touch-sensitive surface 131 and the display panel 141 can be integrated to realize input. And output function.
  • the terminal device 800 may also include at least one sensor 150, such as a light sensor, a motion sensor, and other sensors.
  • the light sensor may include an ambient light sensor and a proximity sensor.
  • the ambient light sensor can adjust the brightness of the display panel 141 according to the brightness of the ambient light.
  • the proximity sensor can close the display panel 141 and/or when the terminal device 800 is moved to the ear. Backlight.
  • the gravity acceleration sensor can detect the magnitude of acceleration in various directions (usually three-axis), and can detect the magnitude and direction of gravity when it is stationary.
  • the terminal device 800 can also be configured with other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc. No longer.
  • the audio circuit 160, the speaker 161, and the microphone 162 can provide an audio interface between the user and the terminal device 800.
  • the audio circuit 160 can transmit the electrical signal converted from the received audio data to the speaker 161, which is converted into a sound signal for output by the speaker 161; on the other hand, the microphone 162 converts the collected sound signal into an electrical signal, and the audio circuit 160 After being received, it is converted into audio data, processed by the audio data output processor 180, and then sent to another terminal device via the RF circuit 110, or the audio data is output to the memory 120 for further processing.
  • the audio circuit 160 may also include an earplug jack to provide communication between a peripheral earphone and the terminal device 800.
  • the terminal device may be equipped with a wireless communication unit 170, which may be a WIFI (Wireless Fidelity, wireless fidelity) module.
  • WIFI Wireless Fidelity, wireless fidelity
  • the terminal device 800 can help users send and receive e-mails, browse web pages, and access streaming media. It provides users with wireless broadband Internet access.
  • the wireless communication unit 170 is shown in FIG. 10, it can be understood that it is not a necessary component of the terminal device 800, and can be omitted as required without changing the essence of the disclosure.
  • the processor 180 is the control center of the terminal device 800, which uses various interfaces and lines to connect various parts of the entire mobile phone, runs or executes software programs and/or modules stored in the memory 120, and calls data stored in the memory 120 , Perform various functions of the terminal device 800 and process data, so as to monitor the mobile phone as a whole.
  • the processor 180 may include one or more processing cores; the processor 180 may integrate an application processor and a modem processor, where the application processor mainly processes the operating system, user interface, and application programs, etc.
  • the adjustment processor mainly deals with wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 180.
  • the terminal device 800 also includes a power source 190 (such as a battery) for supplying power to various components.
  • the power source can be logically connected to the processor 180 through a power management system, so that functions such as charging, discharging, and power management are realized through the power management system.
  • the power supply 190 may also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and any other components.
  • the terminal device 800 may further include a camera 200, and the camera may be used to obtain an image to be searched. Although not shown, the terminal device 800 may also include a Bluetooth module, etc., which will not be repeated here.
  • the terminal device 800 further includes a memory 120 and one or more programs. One or more programs are stored in the memory 120 and are configured to be executed by one or more processors 180. More than one program includes an image-based search method for the application terminal provided by the embodiment of the present disclosure.
  • the user can obtain the image to be searched through the above-mentioned camera 200, and then use the communication unit 110 or the wireless communication unit 170 based on the program.
  • the server 600 searches for the display target and the attributes of the display target based on the searched image
  • the display target sent by the server 600 can also be received through the communication unit 110 or the wireless communication unit 170 based on the program. And display the attributes of the target, and display the display target and the attributes of the display target on the display panel 141 of the touch-sensitive display 140.
  • the program can generate a request based on this operation, and based on the program, the request can be sent to the server 600 through the communication unit 110 or the wireless communication unit 170, and after the server 600 responds to the request, based on the program through the communication unit 110 or wireless communication
  • the unit 170 may also receive the display target corresponding to the attribute of the display target specified by the user, and display the display target corresponding to the attribute of the display target specified by the user on the display panel 141.
  • the mobile terminal described in the present disclosure may be various handheld terminal devices, such as mobile phones, personal digital assistants (PDAs), etc., so the protection scope of the present disclosure should not be limited to a specific type of mobile terminal.
  • PDAs personal digital assistants
  • the method according to the present disclosure can also be implemented as a computer program executed by the central processing unit CPU.
  • the computer program executes the above-mentioned functions defined in the method of the present disclosure.
  • the above method steps and system units can also be implemented using a controller and a computer-readable storage device for storing a computer program that enables the controller to implement the above steps or unit functions.
  • non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash Memory.
  • Volatile memory can include random access memory (RAM), which can act as external cache memory.
  • RAM can be obtained in various forms, such as synchronous RAM (DRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchronous link DRAM (SLDRAM) and direct Rambus RAM (DRRAM).
  • DRAM synchronous RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDR SDRAM double data rate SDRAM
  • ESDRAM enhanced SDRAM
  • SLDRAM Synchronous link DRAM
  • DRRAM direct Rambus RAM
  • the storage devices of the disclosed aspects are intended to include, but are not limited to, these and other suitable types of memory.
  • DSP digital signal processors
  • ASIC dedicated Integrated circuit
  • FPGA field programmable gate array
  • a general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine.
  • the processor may also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration.
  • the steps of the method or algorithm described in combination with the disclosure herein may be directly included in hardware, a software module executed by a processor, or a combination of the two.
  • the software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.
  • An exemplary storage medium is coupled to the processor such that the processor can read information from or write information to the storage medium.
  • the storage medium may be integrated with the processor.
  • the processor and the storage medium may reside in the ASIC.
  • the ASIC can reside in the user terminal.
  • the processor and the storage medium may reside as discrete components in the user terminal.
  • the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions can be stored as one or more instructions or codes on a computer-readable medium or transmitted through the computer-readable medium.
  • Computer-readable media include computer storage media and communication media, including any media that facilitates the transfer of a computer program from one location to another.
  • a storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.
  • the computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, or may be used for carrying or storing instructions in the form of Or any other medium that can be accessed by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. Also, any connection is properly termed a computer-readable medium.
  • coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave to send software from a website, server, or other remote source
  • coaxial cable Cable, fiber optic cable, twisted pair, DSL or wireless technologies such as infrared, radio and microwave are all included in the definition of media.
  • magnetic disks and optical disks include compact disks (CDs), laser disks, optical disks, digital versatile disks (DVD), floppy disks, and Blu-ray disks. Disks generally reproduce data magnetically, while optical disks use lasers to optically reproduce data .
  • the combination of the above content should also be included in the scope of computer-readable media.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Library & Information Science (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本公开提供了一种基于图像的搜索方法，应用于服务器，该方法包括：根据待搜索图像中的图像内容，从索引库中提取目标集合；根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量；根据每个目标的属性所对应的目标数量，向终端发送展示目标和所述展示目标的属性，这样使得用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。 (图2)

Description

基于图像的搜索方法、服务器、终端及介质 技术领域
本公开涉及互联网的技术领域，尤其涉及一种基于图像的搜索方法、服务器、终端及介质。
背景技术
随着智能设备的逐步普及与以深度神经网络为代表的机器学习方法在图像检索领域的应用，图像搜索技术在互联网的应用越来载广泛。尤其在电商领域中，图像搜索技术的兴起成功地解决了传统文字搜索难以解决的问题。例如，当用户难以用文字来描述想要购买的物品时，只需要上传一张物品的图片，搜索引擎就可以基于图像搜索的技术，简便、准确、快速地从海量商品中召回用户想要购买的商品，从而显著地提升用户的购物体验。
但是，在实现本发明的发明构思的过程中，发明人发现现有技术至少存在以下问题：在相关技术中，图像搜索引擎基于图像内容在索引库中进行召回时，在召回的结果中可能包含有许多与图像内容相似的目标，这样需要用户从大量的目标中筛选出自己想要浏览的内容。例如，图像搜索引擎基于商品图像的图像内容在索引库中进行召回时，可能会出现召回的相似商品集中同时包含多种款式、多种品牌或多种促销类型的商品，在这种情况下，用户只能通过浏览的方式来筛选出最想或最值得购买的商品，这样可能需要翻好几页甚至十几页、花费较多的时间与精力，给用户带来较差的用户体验，最终可能影响该商品的成交总额。
发明内容
有鉴于此，本公开提供一种基于图像的搜索方法、服务器、终端及介质，进而至少部分地解决了由于相关技术的限制和缺陷而导致的一个或者多个问题。
本公开的第一个方面提供了一种基于图像的搜索方法，应用于服务器，该方法包括：根据待搜索图像中的图像内容，从索引库中提取目标集合；根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量；根据每个目标的属性所对应的目标数量，向终端发送展示目标和所述展示目标的属性。
根据本公开的实施例，根据所述待搜索图像中的图像内容，从索引库中提取所述目标集合包括：根据所述待搜索图像中的图像内容，从所述索引库中搜索出具有与所述图像内容相似的目标；基于相似度原则从搜索出的目标中提取所述目标集合。
根据本公开的实施例，根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量包括：计算每个目标的属性在所述目标集合中出现次数；根据每个目标的属性在所述目标集合中出现次数，确定每个目标的属性所对应的目标数量。
根据本公开的实施例，根据每个目标的属性所对应的目标数量，向所述终端发送所述 展示目标和所述展示目标的属性包括：根据每个目标的属性所对应的目标数量，对每个目标的属性进行排序；根据排序结果，向所述终端发送所述展示目标和所述展示目标的属性。
根据本公开的实施例，根据所述排序结果，向所述终端发送所述展示目标和所述展示目标的属性包括：根据所述终端的展示位的数量，从所述排序结果中选取向所述终端展示的目标属性；根据向所述终端展示的目标属性，向所述终端发送所述目标属性以及与所述目标属性相对应的展示目标。
根据本公开的实施例，该方法还包括：在所述目标集合中，如果某目标具有多种相似或相同的促销信息时，基于多种相似或相同的促销信息生成一种促销信息。
根据本公开的实施例，在根据每个目标的属性所对应的目标数量，向所述终端发送所述展示目标和所述展示目标的属性之后，该方法还包括：响应于用户指定展示目标的属性操作，向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标。
本公开的第三个方面提供了一种基于图像的搜索方法，应用于终端，该方法包括：向服务器发送待搜索图像，以使得所述服务器根据所述待搜索图像中的图像内容从索引库中提取目标集合，以及根据所述目标集合中每个目标的属性确定每个目标的属性所对应的目标数量，并根据每个目标的属性所对应的目标数量向终端发送展示目标和所述展示目标的属性；接收所述展示目标和所述展示目标的属性。
根据本公开的实施例，在接收所述展示目标和所述展示目标的属性之后，该方法还包括：接收用户指定的展示目标的属性，以使得所述服务器响应于用户指定展示目标的属性操作，并向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标；接收与所述用户指定的展示目标的属性相对应的展示目标。
本公开的第三个方面提供了一种基于图像的搜索装置，应用于服务器，该装置包括：提取模块，用于根据待搜索图像中的图像内容，从索引库中提取目标集合；确定模块，用于根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量；第一发送模块，用于根据每个目标的属性所对应的目标数量，向终端发送展示目标和所述展示目标的属性。
根据本公开的实施例，上述提取模块包括：搜索模块，用于根据所述待搜索图像中的图像内容，从所述索引库中搜索出具有与所述图像内容相似的目标；提取子模块，基于相似度原则从搜索出的目标中提取所述目标集合。
根据本公开的实施例，上述确定模块包括：计算模块，用于计算每个目标的属性在所述目标集合中出现次数；确定子模块，用于根据每个目标的属性在所述目标集合中出现次数，确定每个目标的属性所对应的目标数量。
根据本公开的实施例，上述第一发送模块包括：排序模块，用于根据每个目标的属性所对应的目标数量，对每个目标的属性进行排序；第一发送子模块，用于根据排序结果，向所述终端发送所述展示目标和所述展示目标的属性。
根据本公开的实施例，上述第一发送子模块包括：选取模块，用于根据所述终端的展 示位的数量，从所述排序结果中选取向所述终端展示的目标属性；第一发送子模块的子模块，用于根据向所述终端展示的目标属性，向所述终端发送所述目标属性以及与所述目标属性相对应的展示目标。
根据本公开的实施例，该装置还包括：生成模块，在所述目标集合中，如果某目标具有多种相似或相同的促销信息时，基于多种相似或相同的促销信息生成一种促销信息。
根据本公开的实施例，该装置还包括：响应模块，用于响应于用户指定展示目标的属性操作，向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标。
本公开的第四个方面提供了一种用于信息搜索的终端，该终端包括：图像发送装置，所述图像发送装置被配置为向服务器发送待搜索图像，以使得所述服务器根据所述待搜索图像中的图像内容从索引库中提取目标集合，以及根据所述目标集合中每个目标的属性确定每个目标的属性所对应的目标数量，并根据每个目标的属性所对应的目标数量向终端发送展示目标和所述展示目标的属性；接收装置，所述接收装置被配置为接收所述展示目标和所述展示目标的属性；显示装置，所述显示装置被配置为显示所述展示目标和所述展示目标的属性。
根据本公开的实施例，该终端还包括：输入装置，所述输入装置被配置为接收用户指定的展示目标的属性，并发送所述用户指定的展示目标的属性至所述服务器，以使得所述服务器响应于用户指定展示目标的属性操作，并向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标；所述接收装置还被配置为接收与所述用户指定的展示目标的属性相对应的展示目标；所述显示装置还被配置为显示所述用户指定的展示目标的属性相对应的展示目标。
根据本公开的实施例，该终端还包括图像获取装置，所述图像获取装置被配置为获取待搜索图像的获取装置。
根据本公开的实施例，所述图像获取装置包括安装于所述终端上的摄像头。
根据本公开的实施例，所述显示装置和所述输入装置集成为触敏显示装置，所述触敏显示装置被配置为显示展示目标和展示目标的属性，并输入用户指定的展示目标的属性。
本公开的第五个方面提供了一种服务器，包括：一个或多个处理器，以及存储装置。所述存储装置用于存储一个或多个程序。其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器执行如上第一方面所述的基于图像的搜索方法。
本公开的第六个方面提供了一种计算机可读介质，其上存储有可执行指令，该指令被处理器执行时使处理器执行如上第一方面所述的基于图像的搜索方法。
本公开的第七个方面提供了一种计算机程序，所述计算机程序包括计算机可执行指令，所述指令在被执行时用于实现第一方面所述的基于图像的搜索方法。
本公开的第八个方面提供了一种终端，包括：一个或多个处理器，以及存储装置。所述存储装置用于存储一个或多个程序。其中，当所述一个或多个程序被所述一个或多个处 理器执行时，使得所述一个或多个处理器执行如上第二方面所述的基于图像的搜索方法。
根据本公开的实施例，所述终端包括摄像头，所述摄像头用于获取待搜索图像。
根据本公开的实施例，所述终端还包括触敏显示器，所述触敏显示器用于显示展示目标和展示目标的属性，并输入用户指定的展示目标的属性。
本公开的第九个方面提供了一种计算机可读介质，其上存储有可执行指令，该指令被处理器执行时使处理器执行如上第二方面所述的基于图像的搜索方法。
本公开的第十个方面提供了一种计算机程序，所述计算机程序包括计算机可执行指令，所述指令在被执行时用于实现第二方面所述的基于图像的搜索方法。
本公开提供的应用于服务器的基于图像的搜索方法的有益效果如下：
通过本公开实施例提供的技术方案服务器可以根据待搜索图像中的图像内容，从索引库中提取目标集合，所述目标集合中每个目标具有与所述图像内容相似的属性，根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量，根据每个目标的属性所对应的目标数量，向终端发送展示目标和所述展示目标的属性，这样使得用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。
本公开提供的应用于终端的基于图像的搜索方法的有益效果如下：
通过本公开实施例提供的技术方案终端可以向服务器发送待搜索图像，以使得所述服务器根据所述待搜索图像中的图像内容从索引库中提取目标集合，以及根据所述目标集合中每个目标的属性确定每个目标的属性所对应的目标数量，并根据每个目标的属性所对应的目标数量向终端发送展示目标和所述展示目标的属性，使得终端可以接收到所述展示目标和所述展示目标的属性，此时用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
图1示出了可以应用本发明实施例的基于图像的搜索方法或基于图像的搜索装置的示例性系统架构100的示意图；
图2示意性示出了根据本公开实施例的应用于服务器的基于图像的搜索方法的流程图；
图3示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索方法的流程图；
图4示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索方法的流程图；
图5示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索方法的流程图；
图6示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索方法的流程图；
图7示意性示出了根据本公开实施例的应用于终端的基于图像的搜索方法的流程图；
图8A示意性示出了根据本公开实施例的终端与服务器交互的示意图；
图8B示意性示出了相关技术中展示的目标和目标属性的示意图；
图8C示意性示出了根据本公开实施例的展示的目标和目标属性的示意图；
图9示意性示出了根据本公开实施例的应用于服务器的基于图像的搜索装置的方框图；
图10示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置的方框图；
图11示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置的方框图；
图12示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置的方框图；
图13示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置的方框图；
图14示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置的方框图；
图15示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置的方框图；
图16示意性示出了根据本公开实施例的用于信心搜索的终端的方框图；
图17示意性示出了根据本公开实施例的服务器的结构示意图。
图18示意性示出了根据本公开实施例的终端的结构示意图。
具体实施方式
以下，将参照附图来描述本公开的实施例。但是应该理解，这些描述只是示例性的，而并非要限制本公开的范围。此外，在以下说明中，省略了对公知结构和技术的描述，以避免不必要地混淆本公开的概念。
在此使用的术语仅仅是为了描述具体实施例，而并非意在限制本公开。在此使用的术语“包括”、“包含”等表明了所述特征、步骤、操作和/或部件的存在，但是并不排除存在或添加一个或多个其他特征、步骤、操作或部件。
在此使用的所有术语(包括技术和科学术语)具有本领域技术人员通常所理解的含义，除非另外定义。应注意，这里使用的术语应解释为具有与本说明书的上下文相一致的含义，而不应以理想化或过于刻板的方式来解释。
在使用类似于“A、B和C等中至少一个”这样的表述的情况下，一般来说应该按照 本领域技术人员通常理解该表述的含义来予以解释(例如，“具有A、B和C中至少一个的系统”应包括但不限于单独具有A、单独具有B、单独具有C、具有A和B、具有A和C、具有B和C、和/或具有A、B、C的系统等)。本领域技术人员还应理解，实质上任意表示两个或更多可选项目的转折连词和/或短语，无论是在说明书、权利要求书还是附图中，都应被理解为给出了包括这些项目之一、这些项目任一方、或两个项目的可能性。例如，短语“A或B”应当被理解为包括“A”或“B”、或“A和B”的可能性。
图1示出了可以应用本发明实施例的基于图像的搜索方法或基于图像的搜索装置的示例性系统架构100的示意图。
如图1所示，系统架构100可以包括终端设备101、102、103中的一种或多种，网络104和服务器105。网络104用以在终端设备101、102、103和服务器105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
应该理解，图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备、网络和服务器。比如服务器105可以是多个服务器组成的服务器集群等。
用户可以使用终端设备101、102、103通过网络104与服务器105交互，以接收或发送消息等。终端设备101、102、103可以是具有显示屏的各种电子设备，包括但不限于智能手机、平板电脑、便携式计算机和台式计算机等等。
服务器105可以是提供各种服务的服务器。例如服务器105可以从终端设备103(也可以是终端设备101或102)中获取到待搜索图像，然后可以根据待搜索图像中的图像内容，从索引库中提取目标集合，根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量，根据每个目标的属性所对应的目标数量，向终端发送展示目标和所述展示目标的属性，这样使得用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。
在一些实施例中，本发明实施例所提供的基于图像的搜索方法一般由服务器105执行，相应地，基于图像的搜索装置一般设置于服务器105中。在另一些实施例中，某些终端可以具有与服务器相似的功能从而执行本方法。因此，本发明实施例所提供的基于图像的搜索方法不限定在服务器端执行。
图2示意性示出了根据本公开实施例的应用于服务器的基于图像的搜索方法的流程图。
如图2所示，应用于服务器的基于图像的搜索方法包括步骤S110～步骤S130。
在步骤S110中，根据待搜索图像中的图像内容，从索引库中提取目标集合。
在步骤S120中，根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量。
在步骤S130中，根据每个目标的属性所对应的目标数量，向终端发送展示目标和所 述展示目标的属性。
该方法可以根据待搜索图像中的图像内容，从索引库中提取目标集合，根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量，根据每个目标的属性所对应的目标数量，向终端发送展示目标和所述展示目标的属性，这样使得用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。例如，待搜索图像为商品图像，通过本公开的方法有助于用户从大量的召回商品中快速、准确地筛选出目标商品，极大地提升用户体验，最终使成交总额有较大幅度的增长。
在本公开的一些实施例中，上述待搜索图像可以包括但不限于商品图像、人物图像、动物图像、建筑物图像。例如，上述待搜索图像为商品图像，该商品图像的图像内容可以是商品、人物、动物、建筑物，当然也可以是商品的品牌、商品的颜色、商品的形状、商品的三级类目、人物的身高、人物的性别、人物的年龄、动物的种类、动物的颜色、动物的生活环境、建筑物的形状、建筑物的结构、建筑物的名称等等。
在本公开的一些实施例中，以待搜索图像为商品图像为例，该商品图像的图像内容可以是商品。在本实例中，根据该商品图像的图像内容可以从索引库中搜索出大量的目标，所述目标与图像内容相似。例如，该商品为手机，根据该图像内容可以从索引库中搜索出与该手机相似的商品。另外，当待搜索图像的图像内容为人物图像、动物图像、或者建筑物图像的图像内容时，基于这些图像内容可以从索引库中搜索出与其相对应的人物、动物、建筑物。
在本公开的一些实施例中，当待搜索图像的图像内容为商品的品牌、颜色、形状、三级品类时，可以根据商品的品牌可以从索引库中搜索出具有与该品牌相似或相同的目标。根据商品的颜色可以从索引库中搜索出具有与该颜色相似或相同的目标。根据商品的形状可以从索引库中搜索出具有与该形状相似或相同的目标。根据商品的三级类目可以从索引库中搜索出具有与该三级类目相似或相同的目标。另外，由于根据其他待搜索图像从索引库搜索目标的实施过程与根据待搜索图像为商品图像的实施过程相同或相似，因此在此不再赘述。
在本公开的一些实施例中，上述目标集合中可以包含与待搜索图像的图像内容相似的内容。例如，待搜索图像的图像内容为商品，目标集合中包含的内容为与该商品相似的商品。待搜索图像的图像内容为人物，目标集合中包含的内容为与该人物相似的人物。待搜索图像的图像内容为动物，目标集合中包含的内容为与该动物相似的动物。待搜索图像的图像内容为建筑物，目标集合中包含的内容为与该建筑物相似的建筑物。
在本公开的一些实施例中，上述目标集合中包含具有与待搜索图像的图像内容相似的目标。例如，待搜索图像为商品的图像，该商品的图像内容包括商品的品牌、商品的颜色、商品的形状、商品的三级类目。根该商品的图像内容可以从索引库中搜索出大量具有与该商品的图像内容相似的目标。具体地，待搜索图像为手机的图像，该手机的图像内容可以是华为、白色、长方形、通讯设备等等。根据该手机的每一个图像内容都可以送索引库中 搜索出具有与该图像内容相似的手机，可以将各个搜索结果作为上述手机集合，即目标集合。
在本公开的一些实施例中，通过遍历上述目标集合中每个目标来得到每个目标的属性。例如，上述目标集合为商品集合，通过遍历该商品集合中每个商品可以得到每个商品的属性(例如，属性可以品牌、三级类目、风格等等)。然后根据每个目标的属性来确定每个目标的属性所对应的目标数量，从而可以根据每个目标的属性所对应的目标数量，向终端发送展示目标和所述展示目标的属性，以使得用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。
在本公开的一些实施例中，在上述步骤S130之后，上述方法还包括：响应于用户指定展示目标的属性操作，向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标，这样可以从步骤S130中的展示目标和所述展示目标的属性中快速的筛选出用户指定的目标，进一步地为用户节省了筛选时所用的时间。
在本公开的一些实施例中，上述用户指定展示目标的属性可以是基于上述目标集合中每个目标的属性生成的，从而实现可以响应于用户指定展示目标的属性操作来向终端推荐与用户指定的展示目标的属性相对应的展示目标。
图3示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索方法的流程图。
如图3所示，上述步骤S110具体可以包括步骤S111和步骤S112。
在步骤S111中，根据所述待搜索图像中的图像内容，从所述索引库中搜索出具有与所述图像内容相似的目标。
在步骤S112中，基于相似度原则从搜索出的目标中提取所述目标集合。
该方法可以根据待搜索图像中的图像内容来从索引库中搜索出具有与图像内容相似的目标，然后基于相似度原则从搜索出的目标中提取所述目标集合，这样可以初步的从根据待搜索图像中的各个图像内容搜索出的目标中提取具有与各个图像内容较为相似的目标，使得后续在统计每个目标的属性所对应的目标数量更加简单。
在本公开的一些实施例中，以待搜索图像为商品图像为例，该商品图像的图像属性图像内容可以是商品。例如，根据该商品可以从索引库中搜索出58个与该商品相似的商品，此时可以基于相似度原则可以从58个与该商品相似的商品中提取20个商品，将其作为商品集合，即上述的目标集合。以此方式确定目标集合使得后续在统计每个目标的属性所对应的目标数量更加简单。其中，从搜索结果提取的目标个数可以由终端在请求参数中指定。
在本公开的一些实施例中，以待搜索图像为商品图像为例，该商品图像的图像内容还可以是商品的品牌、商品的颜色、商品的形状、商品的三级类目等等。例如，根据商品的品牌从索引库中搜索出58个具有与该品牌相似的目标，根据商品的颜色从索引库中搜索出62个具有与该颜色相似的目标，根据商品的形状从索引库中搜索出50个具有与该形状相似的目标，根据商品的三级类目从索引库中搜索出200个具有与该三级类目相似的目 标，此时在各个搜索结果中的目标的数量之和为370。在本实施例中，可以基于相似度原则初步的从根据待搜索图像中的各个图像内容搜索出的目标中提取具有与各个图像内容较为相似的目标，将提取的结果作为目标集合。例如，基于相似度原则可以从58个具有与该品牌相似的目标中提取20个目标，从62个具有与该颜色相似的目标中提取26个目标，从索引库中搜索出50个具有与该形状相似的目标中提取15个目标，从200个具有与该三级类目相似的目标中提取30个目标，并将提取的结果作为目标集合，即该目标集合包括91个目标，这样使得后续在统计每个目标的属性所对应的目标数量更加简单。其中，从搜索结果提取的目标个数可以由终端在请求参数中指定。
在本公开的一些实施例中，以待搜索图像为商品图像为例，该商品图像的图像内容可以是商品的品牌、商品的颜色、商品的形状、商品的三级类目等等。例如，根据商品的品牌从索引库中搜索出58个具有与该品牌相似的目标，根据商品的颜色从索引库中搜索出62个具有与该颜色相似的目标，根据商品的形状从索引库中搜索出50个具有与该形状相似的目标，根据商品的三级类目从索引库中搜索出200个具有与该三级类目相似的目标，此时在各个搜索结果中的目标的数量之和为370。在本实施例中，可以基于相似度原则初步的从根据待搜索图像中的各个图像内容搜索出的目标中提取具有与各个图像内容较为相似的目标，将提取的结果作为目标集合。例如，基于相似度原则可以从58个具有与该品牌相似的目标中提取20个目标，从62个具有与该颜色相似的目标中提取26个目标，从索引库中搜索出50个具有与该形状相似的目标中提取15个目标，从200个具有与该三级类目相似的目标中提取30个目标，并将提取的结果作为目标集合，即该目标集合包括91个目标，这样使得后续在统计每个目标的属性所对应的目标数量更加简单。其中，从搜索结果提取的目标个数可以由终端在请求参数中指定。
在本公开的一些实施例中，上述方法还包括：在所述目标集合中，如果某目标具有多种相似或相同的促销信息时，基于多种相似或相同的促销信息生成一种促销信息。例如，从62个具有与该颜色相似的目标中提取26个目标，其中，在提取26个目标中有多个目标含有促销信息。例如，该促销信息可以是购买数量满10个打五折，购买数量满100个打三折，购买数量满5个打八折。或者购买总额满100个减10，购买总额满1000个减100，购买总额满10000个减500等等，在这种情况下，可以基于多种相似或相同的促销信息生成一种促销信息，例如，将多个满M减N汇总成满减、将多个满M打N折汇总成满折等等，这样方便用户观看。
图4示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索方法的流程图。
如图4所示，上述步骤S120具体可以包括步骤S121和步骤S122。
在步骤S121中，计算每个目标的属性在所述目标集合中出现次数。
在步骤S122中，根据每个目标的属性在所述目标集合中出现次数，确定每个目标的属性所对应的目标数量。
该方法可以根据每个目标的属性在目标集合中出现次数来确定每个目标的属性所对应的目标数量，以便于后续根据每个目标的属性所对应的目标数量来向终端发送展示目标和所述展示目标的属性，从而使得用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。
在本公开的一些实施例中，以待搜索图像为商品图像为例，该商品图像的图像属性图像内容可以是商品。例如，根据该商品可以从索引库中搜索出58个与该商品相似的商品，此时可以基于相似度原则可以从58个与该商品相似的商品中提取20个商品，将其作为商品集合，通过遍历该商品集合中每个商品来得到每个商品的属性值(例如，属性值可以品牌ID、三级类目ID、风格ID等等)，并计算出品牌ID、三级类目ID、风格ID在商品集合中出现的次数，进一步地，根据品牌ID、三级类目ID、风格ID在商品集合中出现次数来确定品牌ID、三级类目ID、风格ID所对应的商品数量。具体地，判断品牌ID、三级类目ID、风格ID是否已经出现过，如果出现过，将该属性ID对应的商品数量加1，否则新增该属性ID并将对应的商品数量置为1，以此方式可以快速的确定出品牌ID、三级类目ID、风格ID所对应的商品数量。
在本公开的一些实施例中，以待搜索图像为商品图像为例，该商品图像的图像内容可以是商品的品牌、商品的颜色、商品的形状、商品的三级类目等等。例如，根据商品的品牌可以从索引库中搜索出具有与该品牌相似或相同的目标，此时可以从每个具有与该品牌相似或相同的目标中获取其属性值，例如该目标的品牌ID。在本实例中，遍历根据商品的品牌从索引库中搜索出的结果可以计算出该目标的品牌ID在搜索结果中出现的次数，进一步地，根据该目标的品牌ID在目标集合中出现次数来确定该目标的品牌ID所对应的目标数量。具体地，判断该品牌ID是否已经出现过，如果出现过，将该属性ID对应的商品数量加1，否则新增该属性ID并将对应的商品数量置为1，以此方式可以快速的确定出该目标的品牌ID所对应的目标数量。
图5示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索方法的流程图。
如图5所示，上述步骤S130具体可以包括步骤S131和步骤S132。
在步骤S131中，根据每个目标的属性所对应的目标数量，对每个目标的属性进行排序。
在步骤S132中，根据排序结果，向所述终端发送所述展示目标和所述展示目标的属性。
该方法可以根据每个目标的属性所对应的目标数量来对每个目标的属性进行排序，然后根据排序结果来向所述终端发送所述展示目标和所述展示目标的属性，这样使得用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。
在本公开的一些实施例中，以待搜索图像为商品图像为例，该商品图像的图像属性图像内容可以是商品。例如，根据该商品可以从索引库中搜索出58个与该商品相似的商品， 此时可以基于相似度原则可以从58个与该商品相似的商品中提取20个商品，将其作为商品集合，通过遍历该商品集合中每个商品来得到每个商品的属性值(例如，属性值可以品牌ID、三级类目ID、风格ID等等)，并计算出品牌ID、三级类目ID、风格ID在商品集合中出现的次数，进一步地，根据品牌ID、三级类目ID、风格ID在商品集合中出现次数来确定品牌ID、三级类目ID、风格ID所对应的商品数量。具体地，判断品牌ID、三级类目ID、风格ID是否已经出现过，如果出现过，将该属性ID对应的商品数量加1，否则新增该属性ID并将对应的商品数量置为1，以此方式可以快速的确定出品牌ID、三级类目ID、风格ID所对应的商品数量。当遍历结束后，基于品牌ID、三级类目ID、风格ID对应的商品数量对品牌ID、三级类目ID、风格ID进行排序，并取TopK个属性作为汇总结果返回终端。其中，K根据终端的展示情况而定。
在本公开的一些实施例中，以待搜索图像为商品图像为例，该商品图像的图像内容可以是商品的品牌、商品的颜色、商品的形状、商品的三级类目等等。例如，根据商品的品牌可以从索引库中搜索出具有与该品牌相似或相同的目标，此时可以从每个具有与该品牌相似或相同的目标中获取其属性值，例如该目标的品牌ID。在本实例中，遍历根据商品的品牌从索引库中搜索出的结果可以计算出该目标的品牌ID在搜索结果中出现的次数，进一步地，根据该目标的品牌ID在目标集合中出现次数来确定该目标的品牌ID所对应的目标数量。具体地，判断该品牌ID是否已经出现过，如果出现过，将该属性ID对应的商品数量加1，否则新增该属性ID并将对应的商品数量置为1。同理根据上述计算方法也可以计算出商品的颜色ID、商品的形状ID、商品的三级类目ID所对应的目标数量。当遍历结束后，基于各属性ID对应的目标数量对属性ID进行排序，并取TopK个属性作为汇总结果返回终端。其中，K根据终端的展示情况而定。
图6示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索方法的流程图。
如图6所示，上述步骤S132具体可以包括步骤S132-1和步骤S132-2。
在步骤S132-1中，根据所述终端的展示位的数量，从所述排序结果中选取向所述终端展示的目标属性。
在步骤S132-2中，根据向所述终端展示的目标属性，向所述终端发送所述目标属性以及与所述目标属性相对应的展示目标。
该方法可以根据所述终端的展示位的数量来从上述排序结果中选取向终端展示的目标属性，以此方式确定出的向终端展示的目标属性和展示目标更加灵活，进一步地提高了用户体验。
在本公开的一些实施例中，上述终端的展示位的数量可以由终端的种类来确定。例如，终端为移动设备(例如，手机、平板电脑等等)，终端为各种电脑(例如，笔记本电脑、台式电脑等等)，移动设备相对于各种电脑来说展示位的数量可能会少一些。
图7示意性示出了根据本公开实施例的应用于终端的基于图像的搜索方法的流程图。
如图所示7所示，应用于终端的基于图像的搜索方法包括步骤S210和步骤S220。
在步骤S210中，向服务器发送待搜索图像，以使得所述服务器根据所述待搜索图像中的图像内容从索引库中提取目标集合，以及根据所述目标集合中每个目标的属性确定每个目标的属性所对应的目标数量，并根据每个目标的属性所对应的目标数量向终端发送展示目标和所述展示目标的属性。
在步骤S220中，接收所述展示目标和所述展示目标的属性。
该方法可以向服务器发送待搜索图像，以使得所述服务器根据所述待搜索图像中的图像内容从索引库中提取目标集合，以及根据所述目标集合中每个目标的属性确定每个目标的属性所对应的目标数量，并根据每个目标的属性所对应的目标数量向终端发送展示目标和所述展示目标的属性，使得终端可以接收到所述展示目标和所述展示目标的属性，此时用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。
在本公开的一些实施例中，在上述步骤S220之后，该方法还包括：接收用户指定的展示目标的属性，以使得所述服务器响应于用户指定展示目标的属性操作，并向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标；接收与所述用户指定的展示目标的属性相对应的展示目标。
该方法可以接收用户指定的展示目标的属性，以使得所述服务器响应于用户指定展示目标的属性操作，并向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标，然后接收与所述用户指定的展示目标的属性相对应的展示目标，这样可以快速的筛选出用户指定的目标，进一步地为用户节省了筛选时所用的时间。
下面参考图8A，并通过一个具体的实施例来描述服务器和终端的交互过程。其中，S1和S9由终端执行，S2～S8和S10由服务器执行。
终端与服务器的交互场景：S1，用户使用终端向服务器发送一张手机图像；S2，当服务器接收到该手机图像时，通过识别该手机图像来获取手机图像的图像内容(即，手机)；S3，根据获取到的图像内容从各个索引库搜索与所述图像内容相似的手机；S4，基于相似度原则从各个搜索结果中提取与所述图像内容较为相似的手机，并将其作为商品集合；S5，通过遍历该商品集合来获取每个手机的属性；S6，遍历结束后，计算每个手机的属性在该商品集合中出现的次数；S7，根据每个手机的属性在该商品集合中出现的次数来确定每个目标的属性所对应的手机数量；S8，根据每个手机的属性所对应的手机数量向终端发送展示目标和展示目标的属性，从而使得用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。另外，S9，终端接收用户对上述展示目标的属性的操作；S10，响应于用户指定展示目标的属性操作，向终端发送与所述用户指定的展示目标的属性相对应的展示目标，这样可以从步骤S8中的展示目标和所述展示目标的属性中快速的筛选出用户指定的目标，进一步地为用户节省了筛选时所用的时间。
本公开与相关技术在展示商品和商品的属性的界面变化可以具体参考图8B和图8C。
图8B示出的是相关技术中基于一张耳机图像搜索出的结果，在搜索结果中的A1是 与图像内容对应的商品属性、A2是基于一张耳机图像搜索出的结果，显然A1和A2中的商品属性和商品的覆盖面太广，很难实现快速、准确地筛选出自己想要浏览到的商品。相反地，图8C示出的是本公开基于一张耳机图像搜索出的结果，在搜索结果中的A1是与图像内容对应的商品属性、A2是基于一张耳机图像搜索出的结果，显然A1和A2中的商品属性和商品的覆盖面较小，并且在本公开的搜索结果中还展示了A3，从而实现了可以将多个满M减N汇总成满减、将多个满M打N折汇总成满折等等，这样不仅方便用户观看，还可以减少对终端展示位的要求。
另外，如果用户点击图8C中的筛选控件时，在终端还可以展示出除A1中包含的三级类目之外，还可以展示商品的其他属性，例如，商品的风格(例如，简约现代、运动等等)、商品的品牌(例如，华为、小米、LG)等等，在这种情况下，用户除了可以点击A1中的商品属性，还可以点击商品的风格和商品的品牌，样可以从步骤S8中的展示目标和所述展示目标的属性中快速的筛选出用户指定的目标，进一步地为用户节省了筛选时所用的时间。
图9示意性示出了根据本公开实施例的应用于服务器的基于图像的搜索装置的方框图。
如图9所示，基于图像的搜索装置200包括提取模块210、确定模块220和第一发送模块230。
具体地，提取模块210，用于根据待搜索图像中的图像内容，从索引库中提取目标集合。
确定模块220，用于根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量。
第一发送模块230，用于根据每个目标的属性所对应的目标数量，向终端发送展示目标和所述展示目标的属性。
该基于图像的搜索装置200可以根据待搜索图像中的图像内容，从索引库中提取目标集合，所述目标集合中每个目标具有与所述图像内容相似的属性，根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量，根据每个目标的属性所对应的目标数量，向终端发送展示目标和所述展示目标的属性，这样使得用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。例如，待搜索图像为商品图像，通过本公开的方法有助于用户从大量的召回商品中快速、准确地筛选出目标商品，极大地提升用户体验，最终使成交总额有较大幅度的增长。
根据本公开的实施例，该基于图像的搜索装置200用于实现图2实施例描述的基于图像的搜索方法。
图10示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置的方框图。
如图10所示，上述提取模块210包括搜索模块211和提取子模块212。
具体地，搜索模块211，用于根据所述待搜索图像中的图像内容，从所述索引库中搜索出具有与所述图像内容相似的目标。
提取子模块212，基于相似度原则从搜索出的目标中提取所述目标集合。
该提取模块210可以根据待搜索图像中的图像内容来从索引库中搜索出具有与图像内容相似的目标，然后基于相似度原则从搜索出的目标中提取所述目标集合，这样可以初步的从根据待搜索图像中的各个图像内容搜索出的目标中提取具有与各个图像内容较为相似的目标，使得后续在统计每个目标的属性所对应的目标数量更加简单。
根据本公开的实施例，该提取模块210用于实现图3实施例描述的基于图像的搜索方法。
图11示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置的方框图。
如图11所示，上述确定模块220包括计算模块221和确定子模块222。
具体地，计算模块221，用于计算每个目标的属性在所述目标集合中出现次数。
确定子模块222，用于根据每个目标的属性在所述目标集合中出现次数，确定每个目标的属性所对应的目标数量。
该确定模块220可以根据每个目标的属性在目标集合中出现次数来确定每个目标的属性所对应的目标数量，以便于后续根据每个目标的属性所对应的目标数量来向终端发送展示目标和所述展示目标的属性，从而使得用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。
根据本公开的实施例，该确定模块220用于实现图4实施例描述的基于图像的搜索方法。
图12示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置的方框图。
如图12所示，上述第一发送模块230包括排序模块231和第一发送子模块232。
具体地，排序模块231，用于根据每个目标的属性所对应的目标数量，对每个目标的属性进行排序。
第一发送子模块232，用于根据排序结果，向所述终端发送所述展示目标和所述展示目标的属性。
该第一发送模块230可以根据每个目标的属性所对应的目标数量来对每个目标的属性进行排序，然后根据排序结果来向所述终端发送所述展示目标和所述展示目标的属性，这样使得用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。
根据本公开的实施例，该第一发送模块230用于实现图5实施例描述的基于图像的搜索方法。
图13示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置 的方框图。
如图13所示，上述第一发送子模块232包括选取模块232-1和第一发送子模块的子模块232-2。
具体地，选取模块232-1，用于根据所述终端的展示位的数量，从所述排序结果中选取向所述终端展示的目标属性。
第一发送子模块的子模块232-2，用于根据向所述终端展示的目标属性，向所述终端发送所述目标属性以及与所述目标属性相对应的展示目标。
该第一发送子模块232可以根据所述终端的展示位的数量来从上述排序结果中选取向终端展示的目标属性，以此方式确定出的向终端展示的目标属性更加灵活，进一步地提高了用户体验。
根据本公开的实施例，该第一推荐子模块232用于实现图6实施例描述的基于图像的搜索方法。
图14示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置的方框图。
如图14所示，除了图9实施例描述的提取模块210、确定模块220和第一发送模块230之外，基于图像的搜索装置300包括生成模块310。
具体地，生成模块310，在所述目标集合中，如果某目标具有多种相似或相同的促销信息时，基于多种相似或相同的促销信息生成一种促销信息。
该基于图像的搜索装置200可以基于多种相似或相同的促销信息生成一种促销信息，这样方便用户观看。
图15示意性示出了根据本公开另一个实施例的应用于服务器的基于图像的搜索装置的方框图。
如图15所示，除了图9实施例描述的提取模块210、确定模块220和第一发送模块230之外，基于图像的搜索装置400包括生响应模块410。
具体地，响应模块410，用于响应于用户指定展示目标的属性操作，向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标。
该基于图像的搜索装置400可以响应于用户指定展示目标的属性操作，向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标，这样可以向终端发送展示目标和所述展示目标的属性中快速的筛选出用户指定的目标，进一步地为用户节省了筛选时所用的时间。
可以理解的是，提取模块210、搜索模块211、提取子模块212、确定模块220、计算模块221、确定子模块222、第一发送模块230、排序模块231、第一发送子模块232、选取模块232-1、第一发送子模块的子模块232-2、生成模块310、以及响应模块410可以合并在一个模块中实现，或者其中的任意一个模块可以被拆分成多个模块。或者，这些模块中的一个或多个模块的至少部分功能可以与其他模块的至少部分功能相结合，并在一个模 块中实现。根据本发明的实施例，提取模块210、搜索模块211、提取子模块212、确定模块220、计算模块221、确定子模块222、第一发送模块230、排序模块231、第一发送子模块232、选取模块232-1、第一发送子模块的子模块232-2、生成模块310、以及响应模块410中的至少一个可以至少被部分地实现为硬件电路，例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC)，或可以以对电路进行集成或封装的任何其他的合理方式等硬件或固件来实现，或以软件、硬件以及固件三种实现方式的适当组合来实现。或者，提取模块210、搜索模块211、提取子模块212、确定模块220、计算模块221、确定子模块222、第一发送模块230、排序模块231、第一发送子模块232、选取模块232-1、第一发送子模块的子模块232-2、生成模块310、以及响应模块410中的至少一个可以至少被部分地实现为计算机程序模块，当该程序被计算机运行时，可以执行相应模块的功能。
图16示意性示出了根据本公开实施例的用于信息搜索的终端的方框图。
如图16所示，该用于信息搜索的终端500包括图像发送装置510、接收装置520和显示装置530。
具体地，图像发送装置510，该图像发送装置被配置为向服务器发送待搜索图像，以使得所述服务器根据所述待搜索图像中的图像内容从索引库中提取目标集合，以及根据所述目标集合中每个目标的属性确定每个目标的属性所对应的目标数量，并根据每个目标的属性所对应的目标数量向终端发送展示目标和所述展示目标的属性。
接收装置520，该接收装置被配置为接收所述展示目标和所述展示目标的属性。
显示装置530，该显示装置530被配置为显示所述展示目标和所述展示目标的属性。
该用于信息搜索的终端500可以向服务器发送待搜索图像，以使得所述服务器根据所述待搜索图像中的图像内容从索引库中提取目标集合，以及根据所述目标集合中每个目标的属性确定每个目标的属性所对应的目标数量，并根据每个目标的属性所对应的目标数量向终端发送展示目标和所述展示目标的属性，使得终端可以接收到所述展示目标和所述展示目标的属性，此时用户可以快速、准确地筛选出自己想要浏览到的目标，极大地提升用户体验。
根据本公开的实施例，该用于信息搜索的终端500用于实现图7实施例描述的基于图像的搜索方法。
在本公开的一些实施例中，该信息搜索的终端500还包括图像获取装置，该图像获取装置被配置为获取待搜索图像的获取装置。
在本公开的一些实施例中，上述图像获取装置包括安装于所述终端上的摄像头。
在本公开的一些实施例中，该信息搜索的终端500还包括：输入装置，所述输入装置被配置为接收用户指定的展示目标的属性，并发送所述用户指定的展示目标的属性至所述服务器，以使得所述服务器响应于用户指定展示目标的属性操作，并向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标；上述接收装置520还被配置为接收与所 述用户指定的展示目标的属性相对应的展示目标；上述显示装置530还被配置为显示所述用户指定的展示目标的属性相对应的展示目标。
在本公开的一些实施例中，上述显示装置530和上述输入装置集成为触敏显示装置，所述触敏显示装置被配置为显示展示目标和展示目标的属性，并输入用户指定的展示目标的属性。
图17示意性示出了本公开实施例的服务器的示意图。根据本公开的实施例，所述服务器可以是图1中的服务器105。该服务器可以用于执行上述实施例中提供的应用于服务器的基于图像的搜索方法。
参见图17，该服务器600可因配置或性能不同而产生比较大的差异，可以包括一个或一个以上中央处理器(central processingunits，CPU)610(例如，一个或一个以上处理器)和存储器620，一个或一个以上存储应用程序633或数据632的存储介质630(例如一个或一个以上海量存储设备)。其中，存储器620和存储介质630可以是短暂存储或持久存储。存储在存储介质630的程序可以包括一个或一个以上模块(图示没标出)，每个模块可以包括对服务器中的一系列指令操作。更进一步地，中央处理器610可以设置为与存储介质630通信，在服务器600上执行存储介质630中的一系列指令操作。
服务器600还可以包括一个或一个以上电源640，一个或一个以上有线或无线网络接口650，一个或一个以上输入输出接口660，和/或，一个或一个以上操作系统631，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM等等。经配置可以由一个或者一个以上中央处理器610执行上述方法实施例中应用于服务器所执行的操作。
例如，当上述应用程序633(例如，搜索引擎)被中央处理器610执行时，通过有线或无线网络接口650或输入输出接口660可以接收待搜索图像，然后通过该应用程序633可以对该待搜索图像进行处理以获取待搜索图像中的图像内容，以及通过该应用程序633可以根据待搜索图像中的图像内容从索引库中提取目标集合，根据目标集合中每个目标的属性确定每个目标的属性所对应的目标数量，根据每个目标的属性所对应的目标数量向终端发送展示目标和展示目标的属性。在本实施例中，索引库可以是上述存储器620或上述存储介质中的索引库。
再例如，当上述应用程序633(例如，搜索引擎)被中央处理器610执行时，通过该应用程序633可以根据待搜索图像中的图像内容从上述索引库中搜索出具有与所述图像内容相似的目标，并基于相似度原则从搜索出的目标中提取所述目标集合。
再例如，当上述应用程序633(例如，搜索引擎)被中央处理器610执行时，通过该应用程序633可以计算每个目标的属性在目标集合中出现次数，并根据每个目标的属性在目标集合中出现次数确定每个目标的属性所对应的目标数量。
再例如，当上述应用程序633(例如，搜索引擎)被中央处理器610执行时，通过该应用程序633可以根据每个目标的属性所对应的目标数量对每个目标的属性进行排序，并根据排序结果向上述终端发送展示目标和展示目标的属性。
再例如，当上述应用程序633(例如，搜索引擎)被中央处理器610执行时，通过该应用程序633可以根据上述终端的展示位的数量从上述排序结果中选取向终端展示的目标属性，并根据向上述终端展示的目标属性向该终端发送目标属性以及与目标属性相对应的展示目标。
再例如，当上述应用程序633(例如，搜索引擎)被中央处理器610执行时，在目标集合中，如果某目标具有多种相似或相同的促销信息时，通过该应用程序633可以基于多种相似或相同的促销信息生成一种促销信息。
再例如，当上述应用程序633(例如，搜索引擎)被中央处理器610执行时，在通过该应用程序633根据每个目标的属性所对应的目标数量向上述终端发送所述展示目标和所述展示目标的属性之后，通过该应用程序633还可以响应于用户指定展示目标的属性操作，然后向上述终端发送与用户指定的展示目标的属性相对应的展示目标。
图18是本公开实施例中终端的结构示意图。参见图18，该终端可以用于实施上述实施例中提供的应用于终端的基于图像的搜索方法。
终端设备800可以包括通信单元110、包括有一个或一个以上计算机可读存储介质的存储器120、输入单元130、触敏显示器140、传感器150、音频电路160、无线通信单元170、包括有一个或者一个以上处理核心的处理器180、以及电源190等部件。本领域技术人员可以理解，图18中示出的终端设备结构并不构成对终端设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。其中：
通信单元110可用于收发信息或通话过程中，信号的接收和发送，该通信单元110可以为RF(Radio Frequency，射频)电路、路由器、调制解调器、等网络通信设备。特别地，当通信单元110为RF电路时，将基站的下行信息接收后，交由一个或者一个以上处理器180处理；另外，将涉及上行的数据发送给基站。通常，作为通信单元的RF电路包括但不限于天线、至少一个放大器、调谐器、一个或多个振荡器、用户身份模块(SIM)卡、收发信机、耦合器、LNA(Low Noise Amplifier，低噪声放大器)、双工器等。此外，通信单元110还可以通过无线通信与网络和其他设备通信。无线通信可以使用任一通信标准或协议，包括但不限于GSM(Global System of Mobile communication，全球移动通讯系统)、GPRS(General Packet Radio Service，通用分组无线服务)、CDMA(Code Division Multiple Access，码分多址)、WCDMA(Wideband Code Division Multiple Access，宽带码分多址)、LTE(Long Term Evolution，长期演进)、电子邮件、SMS(Short Messaging Service，短消息服务)等。存储器120可用于存储软件程序以及模块，处理器180通过运行存储在存储器120的软件程序以及模块，从而执行各种功能应用以及数据处理。存储器120可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据终端设备800的使用所创建的数据(比如音频数据、电话本等)等。此外，存储器120可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、 闪存器件、或其他易失性固态存储器件。相应地，存储器120还可以包括存储器控制器，以提供处理器180和输入单元130对存储器120的访问。
输入单元130可用于接收输入的数字或字符信息，以及产生与用户设置以及功能控制有关的键盘、鼠标、操作杆、光学或者轨迹球信号输入。输入单元130可包括触敏表面131以及其他输入设备132。触敏表面131，也称为触摸显示屏或者触控板，可收集用户在其上或附近的触摸操作(比如用户使用手指、触笔等任何适合的物体或附件在触敏表面131上或在触敏表面131附近的操作)，并根据预先设定的程式驱动相应的连接装置。可选的，触敏表面131可包括触摸检测装置和触摸控制器两个部分。其中，触摸检测装置检测用户的触摸方位，并检测触摸操作带来的信号，将信号传送给触摸控制器；触摸控制器从触摸检测装置上接收触摸信息，并将它转换成触点坐标，再送给处理器180，并能接收处理器180发来的命令并加以执行。此外，可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触敏表面131。除了触敏表面131，输入单元130还可以包括其他输入设备132。其他输入设备132可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆等中的一种或多种。
触敏显示器140可用于显示由用户输入的信息或提供给用户的信息以及终端设备800的各种图形用户接口，这些图形用户接口可以由图形、文本、图标、视频和其任意组合来构成。触敏显示器140可包括显示面板141，可选的，可以采用LCD(Liquid Crystal Display，液晶触敏显示器)、OLED(Organic Light-Emitting Diode，有机发光二极管)等形式来配置显示面板141。进一步的，触敏表面131可覆盖显示面板141，当触敏表面131检测到在其上或附近的触摸操作后，传送给处理器180以确定触摸事件的类型，随后处理器180根据触摸事件的类型在显示面板141上提供相应的视觉输出。虽然在图10中，触敏表面131与显示面板141是作为两个独立的部件来实现输入和输入功能，但是在某些实施例中，可以将触敏表面131与显示面板141集成而实现输入和输出功能。
终端设备800还可包括至少一种传感器150，比如光传感器、运动传感器以及其他传感器。光传感器可包括环境光传感器及接近传感器，其中，环境光传感器可根据环境光线的明暗来调节显示面板141的亮度，接近传感器可在终端设备800移动到耳边时，关闭显示面板141和/或背光。作为运动传感器的一种，重力加速度传感器可检测各个方向上(一般为三轴)加速度的大小，静止时可检测出重力的大小及方向，可用于识别手机姿态的应用(比如横竖屏切换、相关游戏、磁力计姿态校准)、振动识别相关功能(比如计步器、敲击)等；至于终端设备800还可配置的陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器，在此不再赘述。
音频电路160、扬声器161，传声器162可提供用户与终端设备800之间的音频接口。音频电路160可将接收到的音频数据转换后的电信号，传输到扬声器161，由扬声器161转换为声音信号输出；另一方面，传声器162将收集的声音信号转换为电信号，由音频电路160接收后转换为音频数据，再将音频数据输出处理器180处理后，经RF电路110以 发送给比如另一终端设备，或者将音频数据输出至存储器120以便进一步处理。音频电路160还可能包括耳塞插孔，以提供外设耳机与终端设备800的通信。
为了实现无线通信，该终端设备上可以配置有无线通信单元170，该无线通信单元170可以为WIFI(Wireless Fidelity，无线保真)模块。WIFI属于短距离无线传输技术，终端设备800通过无线通信单元170可以帮助用户收发电子邮件、浏览网页和访问流式媒体等，它为用户提供了无线的宽带互联网访问。虽然图10中示出了无线通信单元170，但是可以理解的是，其并不属于终端设备800的必须构成，完全可以根据需要在不改变公开的本质的范围内而省略。
处理器180是终端设备800的控制中心，利用各种接口和线路连接整个手机的各个部分，通过运行或执行存储在存储器120内的软件程序和/或模块，以及调用存储在存储器120内的数据，执行终端设备800的各种功能和处理数据，从而对手机进行整体监控。可选的，处理器180可包括一个或多个处理核心；处理器180可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器180中。
终端设备800还包括给各个部件供电的电源190(比如电池)，电源可以通过电源管理系统与处理器180逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。电源190还可以包括一个或一个以上的直流或交流电源、再充电系统、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。
终端设备800还可以包括摄像头200，该摄像头可以用于获取待搜索图像。尽管未示出，该终端设备800还可以包括蓝牙模块等，在此不再赘述。在本实施例中，终端设备800还包括有存储器120，以及一个或者一个以上的程序，其中一个或者一个以上程序存储于存储器120中，且经配置以由一个或者一个以上处理器180执行一个或者一个以上程序包含用于进行本公开实施例提供的应用终端的基于图像的搜索方法。
例如，当上述程序(例如，各支持基于图像搜索目标的应用程序)被处理器180执行时，用户可以通过上述摄像头200来获取待搜索图像，然后基于该程序通过通信单元110或无线通信单元170向服务器600发送该待搜索图像，在服务器600基于该待搜索图像搜索出展示目标和展示目标的属性时，基于该程序通过通信单元110或无线通信单元170还可以接收由服务器600发送的展示目标和展示目标的属性，并在触敏显示器140的显示面板141上展示展示目标和展示目标的属性，在这种情况下，如果用户对显示面板141上的展示目标和展示目标的属性进行操作时，该程序可以基于该次操作生成请求，以及基于该程序通过通信单元110或无线通信单元170可以向服务器600发送该请求，在服务器600响应该请求之后，基于该程序通过通信单元110或无线通信单元170还可以接收到与用户指定的展示目标的属性相对应的展示目标，并在显示面板141上展示与用户指定的展示目标的属性相对应的展示目标。
此外，典型地，本公开所述的移动终端可为各种手持终端设备，例如手机、个人数字 助理(PDA)等，因此本公开的保护范围不应限定为某种特定类型的移动终端。
此外，根据本公开的方法还可以被实现为由中央处理器CPU执行的计算机程序。在该计算机程序被CPU执行时，执行本公开的方法中限定的上述功能。
此外，上述方法步骤以及系统单元也可以利用控制器以及用于存储使得控制器实现上述步骤或单元功能的计算机程序的计算机可读存储设备实现。
此外，应该明白的是，本文所述的计算机可读存储设备(例如，存储器)可以是易失性存储器或非易失性存储器，或者可以包括易失性存储器和非易失性存储器两者。作为例子而非限制性的，非易失性存储器可以包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦写可编程ROM(EEPROM)或快闪存储器。易失性存储器可以包括随机存取存储器(RAM)，该RAM可以充当外部高速缓存存储器。作为例子而非限制性的，RAM可以以多种形式获得，比如同步RAM(DRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据速率SDRAM(DDR SDRAM)、增强SDRAM(ESDRAM)、同步链路DRAM(SLDRAM)以及直接Rambus RAM(DRRAM)。所公开的方面的存储设备意在包括但不限于这些和其它合适类型的存储器。
本领域技术人员还将明白的是，结合这里的公开所描述的各种示例性逻辑块、模块、电路和算法步骤可以被实现为电子硬件、计算机软件或两者的组合。为了清楚地说明硬件和软件的这种可互换性，已经就各种示意性组件、方块、模块、电路和步骤的功能对其进行了一般性的描述。这种功能是被实现为软件还是被实现为硬件取决于具体应用以及施加给整个系统的设计约束。本领域技术人员可以针对每种具体应用以各种方式来实现所述的功能，但是这种实现决定不应被解释为导致脱离本公开的范围。
结合这里的公开所描述的各种示例性逻辑块、模块和电路可以利用被设计成用于执行这里所述功能的下列部件来实现或执行：通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或其它可编程逻辑器件、分立门或晶体管逻辑、分立的硬件组件或者这些部件的任何组合。通用处理器可以是微处理器，但是可替换地，处理器可以是任何传统处理器、控制器、微控制器或状态机。处理器也可以被实现为计算设备的组合，例如，DSP和微处理器的组合、多个微处理器、一个或多个微处理器结合DSP核、或任何其它这种配置。
结合这里的公开所描述的方法或算法的步骤可以直接包含在硬件中、由处理器执行的软件模块中或这两者的组合中。软件模块可以驻留在RAM存储器、快闪存储器、ROM存储器、EPROM存储器、EEPROM存储器、寄存器、硬盘、可移动盘、CD-ROM、或本领域已知的任何其它形式的存储介质中。示例性的存储介质被耦合到处理器，使得处理器能够从该存储介质中读取信息或向该存储介质写入信息。在一个替换方案中，所述存储介质可以与处理器集成在一起。处理器和存储介质可以驻留在ASIC中。ASIC可以驻留在用户终端中。在一个替换方案中，处理器和存储介质可以作为分立组件驻留在用户终端中。
在一个或多个示例性设计中，所述功能可以在硬件、软件、固件或其任意组合中实现。 如果在软件中实现，则可以将所述功能作为一个或多个指令或代码存储在计算机可读介质上或通过计算机可读介质来传送。计算机可读介质包括计算机存储介质和通信介质，该通信介质包括有助于将计算机程序从一个位置传送到另一个位置的任何介质。存储介质可以是能够被通用或专用计算机访问的任何可用介质。作为例子而非限制性的，该计算机可读介质可以包括RAM、ROM、EEPROM、CD-ROM或其它光盘存储设备、磁盘存储设备或其它磁性存储设备，或者是可以用于携带或存储形式为指令或数据结构的所需程序代码并且能够被通用或专用计算机或者通用或专用处理器访问的任何其它介质。此外，任何连接都可以适当地称为计算机可读介质。例如，如果使用同轴线缆、光纤线缆、双绞线、数字用户线路(DSL)或诸如红外线、无线电和微波的无线技术来从网站、服务器或其它远程源发送软件，则上述同轴线缆、光纤线缆、双绞线、DSL或诸如红外先、无线电和微波的无线技术均包括在介质的定义。如这里所使用的，磁盘和光盘包括压缩盘(CD)、激光盘、光盘、数字多功能盘(DVD)、软盘、蓝光盘，其中磁盘通常磁性地再现数据，而光盘利用激光光学地再现数据。上述内容的组合也应当包括在计算机可读介质的范围内。
以上对本公开的实施例进行了描述。但是，这些实施例仅仅是为了说明的目的，而并非为了限制本公开的范围。尽管在以上分别描述了各实施例，但是这并不意味着各个实施例中的措施不能有利地结合使用。本公开的范围由所附权利要求及其等同物限定。不脱离本公开的范围，本领域技术人员可以做出多种替代和修改，这些替代和修改都应落在本公开的范围之内。

Claims (27)

  1. 一种基于图像的搜索方法，应用于服务器，该方法包括：
    根据待搜索图像中的图像内容，从索引库中提取目标集合；
    根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量；
    根据每个目标的属性所对应的目标数量，向终端发送展示目标和所述展示目标的属性。
  2. 根据权利要求1所述的方法，其中，根据所述待搜索图像中的图像内容，从索引库中提取所述目标集合包括：
    根据所述待搜索图像中的图像内容，从所述索引库中搜索出具有与所述图像内容相似的目标；
    基于相似度原则从搜索出的目标中提取所述目标集合。
  3. 根据权利要求1所述的方法，其中，根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量包括：
    计算每个目标的属性在所述目标集合中出现次数；
    根据每个目标的属性在所述目标集合中出现次数，确定每个目标的属性所对应的目标数量。
  4. 根据权利要求1所述的方法，其中，根据每个目标的属性所对应的目标数量，向所述终端发送所述展示目标和所述展示目标的属性包括：
    根据每个目标的属性所对应的目标数量，对每个目标的属性进行排序；
    根据排序结果，向所述终端发送所述展示目标和所述展示目标的属性。
  5. 根据权利要求4所述的方法，其中，根据所述排序结果，向所述终端发送所述展示目标和所述展示目标的属性包括：
    根据所述终端的展示位的数量，从所述排序结果中选取向所述终端展示的目标属性；
    根据向所述终端展示的目标属性，向所述终端发送所述目标属性以及与所述目标属性相对应的展示目标。
  6. 根据权利要求1所述的方法，其中，该方法还包括：
    在所述目标集合中，如果某目标具有多种相似或相同的促销信息时，基于多种相似或相同的促销信息生成一种促销信息。
  7. 根据权利要求1所述的方法，其中，在根据每个目标的属性所对应的目标数量，向所述终端发送所述展示目标和所述展示目标的属性之后，该方法还包括：
    响应于用户指定展示目标的属性操作，向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标。
  8. 一种基于图像的搜索方法，应用于终端，该方法包括：
    向服务器发送待搜索图像，以使得所述服务器根据所述待搜索图像中的图像内容从索引库中提取目标集合，以及根据所述目标集合中每个目标的属性确定每个目标的属性所对 应的目标数量，并根据每个目标的属性所对应的目标数量向终端发送展示目标和所述展示目标的属性；
    接收所述展示目标和所述展示目标的属性。
  9. 根据权利要求8所述的方法，其中，在接收所述展示目标和所述展示目标的属性之后，该方法还包括：
    接收用户指定的展示目标的属性，以使得所述服务器响应于用户指定展示目标的属性操作，并向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标；
    接收与所述用户指定的展示目标的属性相对应的展示目标。
  10. 一种基于图像的搜索装置，应用于服务器，该装置包括：
    提取模块，用于根据待搜索图像中的图像内容，从索引库中提取目标集合，所述目标集合中每个目标具有与所述图像内容相似的属性；
    确定模块，用于根据所述目标集合中每个目标的属性，确定每个目标的属性所对应的目标数量；
    第一发送模块，用于根据每个目标的属性所对应的目标数量，向终端发送展示目标和所述展示目标的属性。
  11. 根据权利要求10所述的装置，其中，所述提取模块包括：
    搜索模块，用于根据所述待搜索图像中的图像内容，从所述索引库中搜索出具有与所述图像内容相似的目标；
    提取子模块，基于相似度原则从搜索出的目标中提取所述目标集合。
  12. 根据权利要求10所述的装置，其中，所述确定模块包括：
    计算模块，用于计算每个目标的属性在所述目标集合中出现次数；
    确定子模块，用于根据每个目标的属性在所述目标集合中出现次数，确定每个目标的属性所对应的目标数量。
  13. 根据权利要求10所述的装置，其中，所述第一发送模块包括：
    排序模块，用于根据每个目标的属性所对应的目标数量，对每个目标的属性进行排序；
    第一发送子模块，用于根据排序结果，向所述终端发送所述展示目标和所述展示目标的属性。
  14. 根据权利要求13所述的装置，其中，所述第一发送子模块包括：
    选取模块，用于根据所述终端的展示位的数量，从所述排序结果中选取向所述终端展示的目标属性；
    第一发送子模块的子模块，用于根据向所述终端展示的目标属性，向所述终端发送所述目标属性以及与所述目标属性相对应的展示目标。
  15. 根据权利要求10所述的装置，其中，该装置还包括：生成模块，在所述目标集合中，如果某目标具有多种相似或相同的促销信息时，基于多种相似或相同的促销信息生成一种促销信息。
  16. 根据权利要求10所述的装置，其中，该装置还包括：响应模块，用于响应于用户指定展示目标的属性操作，向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标。
  17. 一种用于信息搜索的终端，包括：
    图像发送装置，所述图像发送装置被配置为向服务器发送待搜索图像，以使得所述服务器根据所述待搜索图像中的图像内容从索引库中提取目标集合，以及根据所述目标集合中每个目标的属性确定每个目标的属性所对应的目标数量，并根据每个目标的属性所对应的目标数量向终端发送展示目标和所述展示目标的属性；
    接收装置，所述接收装置被配置为接收所述展示目标和所述展示目标的属性；
    显示装置，所述显示装置被配置为显示所述展示目标和所述展示目标的属性。
  18. 根据权利要求17所述的终端，其中，该终端还包括：
    输入装置，所述输入装置被配置为接收用户指定的展示目标的属性，并发送所述用户指定的展示目标的属性至所述服务器，以使得所述服务器响应于用户指定展示目标的属性操作，并向所述终端发送与所述用户指定的展示目标的属性相对应的展示目标；
    所述接收装置还被配置为接收与所述用户指定的展示目标的属性相对应的展示目标；
    所述显示装置还被配置为显示所述用户指定的展示目标的属性相对应的展示目标。
  19. 根据权利要求17或18所述的终端，其中，该终端还包括：
    图像获取装置，所述图像获取装置被配置为获取待搜索图像的获取装置。
  20. 根据权利要求19所述的终端，其中，所述图像获取装置包括安装于所述终端上的摄像头。
  21. 根据权利要求17或18所述的终端，其中，所述显示装置和所述输入装置集成为触敏显示装置，所述触敏显示装置被配置为显示展示目标和展示目标的属性，并输入用户指定的展示目标的属性。
  22. 一种服务器，包括：
    一个或多个处理器；以及
    存储装置，用于存储一个或多个程序；
    其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器执行根据权利要求1～7任意一项所述的方法。
  23. 一种计算机可读介质，其上存储有可执行指令，该指令被处理器执行时使处理器执行根据权利要求1～7任意一项所述的方法。
  24. 一种终端，包括：
    一个或多个处理器；以及
    存储装置，用于存储一个或多个程序；
    其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器执行根据权利要求8～9任意一项所述的方法。
  25. 根据权利要求24所述的终端，其中，所述终端包括摄像头，所述摄像头用于获取待搜索图像。
  26. 根据权利要求24或25所述的终端，其中，所述终端还包括触敏显示器，所述触敏显示器用于显示展示目标和展示目标的属性，并输入用户指定的展示目标的属性。
  27. 一种计算机可读介质，其上存储有可执行指令，该指令被处理器执行时使处理器执行根据权利要求8～9任意一项所述的方法。
PCT/CN2020/081121 2019-03-28 2020-03-25 基于图像的搜索方法、服务器、终端及介质 WO2020192691A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP20776656.9A EP3951622A4 (en) 2019-03-28 2020-03-25 IMAGE-BASED SEARCH PROCESS, SERVER, DEVICE AND MEDIUM
US17/598,856 US20220197939A1 (en) 2019-03-28 2020-03-25 Image-based search method, server, terminal, and medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910242279.7A CN111753181A (zh) 2019-03-28 2019-03-28 基于图像的搜索方法、装置、服务器、客户端及介质
CN201910242279.7 2019-03-28

Publications (1)

Publication Number Publication Date
WO2020192691A1 true WO2020192691A1 (zh) 2020-10-01

Family

ID=72609612

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/081121 WO2020192691A1 (zh) 2019-03-28 2020-03-25 基于图像的搜索方法、服务器、终端及介质

Country Status (4)

Country Link
US (1) US20220197939A1 (zh)
EP (1) EP3951622A4 (zh)
CN (1) CN111753181A (zh)
WO (1) WO2020192691A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112969021B (zh) * 2020-10-30 2022-03-15 上海称意包装设备有限公司 利用内容搜索的继电器控制平台及方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101419612A (zh) * 2007-10-23 2009-04-29 株式会社理光 图像处理设备和图像处理方法
US8352465B1 (en) * 2009-09-03 2013-01-08 Google Inc. Grouping of image search results
CN103345645A (zh) * 2013-06-27 2013-10-09 复旦大学 面向网购平台的商品图像类别预测方法
CN103412937A (zh) * 2013-08-22 2013-11-27 成都数之联科技有限公司 一种基于手持终端的搜索购物方法
CN104142946A (zh) * 2013-05-08 2014-11-12 阿里巴巴集团控股有限公司 一种同款业务对象聚合、搜索的方法和系统
US20170193011A1 (en) * 2015-12-31 2017-07-06 Ebay Inc. Generating structured queries from images
CN107229741A (zh) * 2017-06-20 2017-10-03 百度在线网络技术（北京）有限公司 信息搜索方法、装置、设备以及存储介质

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7933900B2 (en) * 2005-10-23 2011-04-26 Google Inc. Search over structured data
JP5104743B2 (ja) * 2008-12-16 2012-12-19 富士通株式会社 画像検索プログラム、画像検索方法及び記録媒体
US8949252B2 (en) * 2010-03-29 2015-02-03 Ebay Inc. Product category optimization for image similarity searching of image-based listings in a network-based publication system
CN102279851B (zh) * 2010-06-12 2017-05-03 阿里巴巴集团控股有限公司 一种智能导航方法、装置和系统
US8965788B2 (en) * 2011-07-06 2015-02-24 Target Brands, Inc. Search page topology
US10127564B2 (en) * 2011-09-15 2018-11-13 Stephan HEATH System and method for using impressions tracking and analysis, location information, 2D and 3D mapping, mobile mapping, social media, and user behavior and information for generating mobile and internet posted promotions or offers for, and/or sales of, products and/or services
CN103136228A (zh) * 2011-11-25 2013-06-05 阿里巴巴集团控股有限公司 一种图片搜索方法以及图片搜索装置
WO2013152444A1 (en) * 2012-04-09 2013-10-17 R&D Consulting Professionals Inc. Systems and methods for managing a retail network
US8949253B1 (en) * 2012-05-24 2015-02-03 Google Inc. Low-overhead image search result generation
US8843483B2 (en) * 2012-05-29 2014-09-23 International Business Machines Corporation Method and system for interactive search result filter
US8996516B2 (en) * 2013-01-02 2015-03-31 Google Inc. Adjacent search results exploration
US20160098426A1 (en) * 2013-05-16 2016-04-07 Yandex Europe Ag Method and system for presenting image information to a user of a client device
JP6432047B2 (ja) * 2014-08-21 2018-12-05 パナソニックＩｐマネジメント株式会社 コンテンツ認識装置およびコンテンツ認識方法
KR102119868B1 (ko) * 2015-10-20 2020-06-05 전자부품연구원 홍보용 미디어 콘텐츠 제작 시스템 및 그 방법
CN105426462A (zh) * 2015-11-13 2016-03-23 深圳码隆科技有限公司 一种基于图像元素的图像搜索方法和装置
CN107918616A (zh) * 2016-10-09 2018-04-17 阿里巴巴集团控股有限公司 搜索系统、页面显示方法及客户端
US11004131B2 (en) * 2016-10-16 2021-05-11 Ebay Inc. Intelligent online personal assistant with multi-turn dialog based on visual search
CN108399174A (zh) * 2017-02-07 2018-08-14 阿里巴巴集团控股有限公司 对象搜索方法及装置
CN111831844A (zh) * 2019-04-17 2020-10-27 京东方科技集团股份有限公司 图像检索方法、图像检索装置、图像检索设备及介质
JP7431563B2 (ja) * 2019-11-28 2024-02-15 キヤノン株式会社 画像検索装置、画像検索方法、及びプログラム

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101419612A (zh) * 2007-10-23 2009-04-29 株式会社理光 图像处理设备和图像处理方法
US8352465B1 (en) * 2009-09-03 2013-01-08 Google Inc. Grouping of image search results
CN104142946A (zh) * 2013-05-08 2014-11-12 阿里巴巴集团控股有限公司 一种同款业务对象聚合、搜索的方法和系统
CN103345645A (zh) * 2013-06-27 2013-10-09 复旦大学 面向网购平台的商品图像类别预测方法
CN103412937A (zh) * 2013-08-22 2013-11-27 成都数之联科技有限公司 一种基于手持终端的搜索购物方法
US20170193011A1 (en) * 2015-12-31 2017-07-06 Ebay Inc. Generating structured queries from images
CN107229741A (zh) * 2017-06-20 2017-10-03 百度在线网络技术（北京）有限公司 信息搜索方法、装置、设备以及存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3951622A4 *

Also Published As

Publication number Publication date
EP3951622A4 (en) 2023-01-25
EP3951622A1 (en) 2022-02-09
US20220197939A1 (en) 2022-06-23
CN111753181A (zh) 2020-10-09

Similar Documents

Publication Publication Date Title
US11169827B2 (en) Resource loading at application startup using attributes of historical data groups
US9241242B2 (en) Information recommendation method and apparatus
CN108073605B (zh) 一种业务数据的加载、推送、交互信息的生成方法和装置
US20170091335A1 (en) Search method, server and client
CN108334539B (zh) 对象推荐方法、移动终端及计算机可读存储介质
WO2020232615A1 (zh) 信息推荐方法、装置、电子设备以及存储介质
WO2020238951A1 (zh) 网络内容处理方法、装置、设备及计算机存储介质
TW201512865A (zh) 一種網頁數據搜索方法、裝置和系統
WO2016155446A1 (zh) 信息展示方法、信道管理平台及终端
WO2021120875A1 (zh) 搜索方法、装置、终端设备及存储介质
WO2014169715A1 (en) Information recommendation method and apparatus
CN113609392B (zh) 一种内容推荐方法、待推荐内容确定方法和相关装置
US20160189038A1 (en) Techniques for mobile prediction
CN110390569B (zh) 一种内容推广方法、装置及存储介质
CN108492836A (zh) 一种基于语音的搜索方法、移动终端及存储介质
CN113330475B (zh) 信息推荐方法、装置、电子设备以及存储介质
CN111078986B (zh) 数据检索方法、装置及计算机可读存储介质
WO2020221121A1 (zh) 视频查询方法、装置、设备及存储介质
WO2020192691A1 (zh) 基于图像的搜索方法、服务器、终端及介质
CN112925878B (zh) 数据处理方法和装置
CN113190752A (zh) 信息推荐方法、移动终端及存储介质
CN104794139B (zh) 信息检索方法、装置及系统
WO2023173666A1 (zh) 人脸支付方法、装置、电子设备、存储介质、程序和产品
CN111143726A (zh) 一种信息显示方法及移动终端
KR20200026391A (ko) 추천 서비스 제공 방법 및 이를 위한 장치

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20776656

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020776656

Country of ref document: EP

Effective date: 20211028