WO2023050732A1 - 对象推荐方法和装置 - Google Patents
对象推荐方法和装置 Download PDFInfo
- Publication number
- WO2023050732A1 WO2023050732A1 PCT/CN2022/081122 CN2022081122W WO2023050732A1 WO 2023050732 A1 WO2023050732 A1 WO 2023050732A1 CN 2022081122 W CN2022081122 W CN 2022081122W WO 2023050732 A1 WO2023050732 A1 WO 2023050732A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- feature
- retrieval
- images
- object images
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000004590 computer program Methods 0.000 claims description 21
- 238000013473 artificial intelligence Methods 0.000 abstract description 9
- 238000004891 communication Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000013459 approach Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000010267 cellular communication Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06F16/53—Querying
- G06F16/535—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/55—Clustering; Classification
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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 field of computer technology, in particular to recommendation technology based on artificial intelligence, and in particular to an object recommendation method, device, electronic equipment, computer-readable storage medium and computer program product.
- Artificial intelligence is a discipline that studies the use of computers to simulate certain human thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level.
- Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, and machine learning/depth Learning, big data processing technology, knowledge map technology and other major directions.
- the object recommendation technology based on artificial intelligence realizes recommending objects to users according to the characteristics of the objects and the user's preference for objects.
- the present disclosure provides an object recommendation method, device, electronic equipment, computer readable storage medium and computer program product.
- an object recommendation method including: identifying a target user's search image containing a search object to obtain the search features of the search object; based on the search features, from including multiple acquiring at least one retrieval feature image from the first database of feature images; and acquiring a set of target object images from a second database including a plurality of object images based on the at least one retrieval feature image to recommend to the target user .
- an object recommendation device including: an image recognition unit configured to recognize a retrieval image of a retrieval object from a target user to obtain retrieval features of the retrieval object; and
- the first retrieval unit is configured to obtain at least one retrieval feature image from the first database including a plurality of feature images based on the retrieval feature;
- the second retrieval unit is configured to obtain at least one retrieval feature image based on the at least one retrieval feature image, acquiring a target object image set from a second database including a plurality of object images, to recommend to the target user.
- an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores information executable by the at least one processor. instructions, the instructions are executed by the at least one processor, so that the at least one processor implements the method according to the above.
- a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to implement the above method.
- a computer program product comprising a computer program, wherein said computer program, when executed by a processor, implements the method according to the above.
- the retrieval feature of the retrieval object is obtained (for example, when the retrieval object is a mobile phone, the retrieval feature can be a mobile phone classification), from including multiple features
- the feature image corresponding to the retrieval object is obtained from the first image database, and then the feature image is matched with the object image database to obtain a target object image set for recommendation to the target user. Since the feature images in the first database have high definition and good shooting angles, they can better reflect the features of the retrieved objects, so that the object images obtained based on the feature images are more accurate, that is, the target objects recommended to users are more accurate.
- FIG. 1 shows a schematic diagram of an exemplary system in which various methods described herein may be implemented according to an embodiment of the present disclosure
- FIG. 2 shows a flowchart of an object recommendation method according to an embodiment of the present disclosure
- FIG. 3 shows a flowchart of a process of acquiring at least one retrieval feature image from a first database including multiple feature images based on retrieval features in an object recommendation method according to an embodiment of the present disclosure
- FIG. 4 shows a flowchart of a process of obtaining at least one retrieval feature image from at least one first feature image in an object recommendation method according to an embodiment of the present disclosure
- FIG. 5 shows a flowchart of a process of acquiring a target object image set from a second database including a plurality of object images based on at least one retrieval feature image in an object recommendation method according to an embodiment of the present disclosure
- FIG. 6 shows a flow chart of the process of acquiring the target object image set based on one or more first object images in the object recommendation method according to an embodiment of the present disclosure
- FIG. 7 shows a flow chart of a process of acquiring a target object image set based on image information corresponding to at least one feature image and one or more first object images in an object recommendation method according to an embodiment of the present disclosure
- Fig. 8 shows a structural block diagram of an object recommendation device according to an embodiment of the present disclosure.
- FIG. 9 shows a structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure.
- first, second, etc. to describe various elements is not intended to limit the positional relationship, temporal relationship or importance relationship of these elements, and such terms are only used for Distinguishes one element from another.
- first element and the second element may refer to the same instance of the element, and in some cases, they may also refer to different instances based on contextual description.
- FIG. 1 shows a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented according to an embodiment of the present disclosure.
- the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks coupling the one or more client devices to the server 120 110.
- Client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.
- the server 120 may run one or more services or software applications enabling the execution of the object recommendation method.
- server 120 may also provide other services or software applications that may include non-virtualized environments and virtualized environments.
- these services may be provided as web-based services or cloud services, such as under a software-as-a-service (SaaS) model to users of client devices 101, 102, 103, 104, 105, and/or 106 .
- SaaS software-as-a-service
- server 120 may include one or more components that implement the functions performed by server 120 . These components may include software components, hardware components or combinations thereof executable by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and/or 106 may in turn utilize one or more client application programs to interact with server 120 to utilize the services provided by these components. It should be understood that various different system configurations are possible, which may differ from system 100 . Accordingly, FIG. 1 is one example of a system for implementing the various methods described herein, and is not intended to be limiting.
- a user may use client devices 101, 102, 103, 104, 105, and/or 106 to view recommended objects.
- a client device may provide an interface that enables a user of the client device to interact with the client device. The client device can also output information to the user via the interface.
- FIG. 1 depicts only six client devices, those skilled in the art will understand that the present disclosure can support any number of client devices.
- Client devices 101, 102, 103, 104, 105, and/or 106 may include various types of computing devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptops), workstation computers, wearable devices, Smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors or other sensing devices, etc.
- These computer devices can run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems , such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android.
- Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), and the like.
- Wearable devices may include head-mounted displays (such as smart glasses) and other devices.
- Gaming systems may include various handheld gaming devices, Internet-enabled gaming devices, and the like.
- a client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (eg, email applications), Short Message Service (SMS) applications, and may use a variety of communication protocols.
- communication applications eg, email applications
- SMS Short Message Service
- Network 110 can be any type of network known to those skilled in the art that can support data communications using any of a number of available protocols, including but not limited to TCP/IP, SNA, IPX, and the like.
- the one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, Public switched telephone network (PSTN), infrared network, wireless network (eg Bluetooth, WIFI) and/or any combination of these and/or other networks.
- LAN local area network
- Ethernet-based network a token ring
- WAN wide area network
- VPN virtual private network
- PSTN Public switched telephone network
- WIFI wireless network
- Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, midrange servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination .
- Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (eg, one or more flexible pools of logical storage devices that may be virtualized to maintain the server's virtual storage devices).
- server 120 may run one or more services or software applications that provide the functionality described below.
- Computing units in server 120 may run one or more operating systems including any of the operating systems described above as well as any commercially available server operating systems.
- Server 120 may also run any of a variety of additional server applications and/or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, and the like.
- server 120 may include one or more applications to analyze and consolidate data feeds and/or event updates received from users of client devices 101 , 102 , 103 , 104 , 105 , and 106 .
- Server 120 may also include one or more applications to display data feeds and/or real-time events via one or more display devices of client devices 101 , 102 , 103 , 104 , 105 , and 106 .
- the server 120 may be a server of a distributed system, or a server combined with blockchain.
- the server 120 can also be a cloud server, or an intelligent cloud computing server or an intelligent cloud host with artificial intelligence technology.
- Cloud server is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability existing in traditional physical host and virtual private server (VPS, Virtual Private Server) services.
- System 100 may also include one or more databases 130 .
- these databases may be used to store data and other information.
- databases 130 may be used to store information such as audio files and object files.
- Data repository 130 may reside in various locations.
- the data store used by server 120 may be local to server 120, or may be remote from server 120 and may communicate with server 120 via a network-based or dedicated connection.
- Data repository 130 can be of different types.
- the data store used by server 120 may be a database, such as a relational database.
- One or more of these databases may store, update and retrieve the database and data from the database in response to commands.
- databases 130 may also be used by applications to store application data.
- Databases used by applications can be different types of databases such as key-value stores, object stores or regular stores backed by a file system.
- the system 100 of FIG. 1 may be configured and operated in various ways to enable application of the various methods and apparatuses described in accordance with this disclosure.
- an object recommendation method 200 includes:
- Step S210 Identify the target user's search image containing the search object to obtain the search features of the search object;
- Step S220 Obtain at least one retrieval feature image from a first database including a plurality of feature images based on the retrieval feature;
- Step S230 Obtain a target object image set from a second database including a plurality of object images based on the at least one retrieved feature image, to recommend to the target user.
- the retrieval feature of the retrieval object is obtained (for example, when the retrieval object is a mobile phone, the retrieval feature can be a mobile phone classification), from including multiple features
- the feature image corresponding to the retrieval object is obtained from the first image database, and then the feature image is matched with the object image database to obtain a target object image set for recommendation to the target user. Since the feature images in the first database have high definition and good shooting angles, they can better reflect the characteristics of the retrieved object, so that the object image obtained based on the feature image is more accurate, that is, the target object recommended to the user is accurate.
- the target object image is directly obtained from the object image database according to the retrieved image of the target user to recommend to the target user, and the target object image recommended to the target user It is one or more images similar to the retrieved image, and it can only recommend an object matching the retrieved object if the user's image is accurate.
- the recommended object is often inaccurate, which cannot meet the user's needs; nor can it recommend more abundant objects related to the retrieval object to the user based on the retrieval image.
- the current retrieval image of the target user is a photo of a mobile phone screen taken under low-light conditions
- the recommended object image may be a mobile phone with various mobile phone screens.
- the characteristic image corresponding to the mobile phone brand can be obtained from the first database, and the characteristic image is clear , and an image that can reflect the real situation of the mobile phone brand, so that the object image obtained from the second database according to the characteristic image can be accurate, and thus the mobile phone recommended to the user can be accurate.
- the first database is used as an intermediate database for object recommendation and search, and it acts as a bridge, through which the search object and the object image database corresponding to the object recommendation are connected, so that the objects from the object image database The obtained target object images in the target object image set for recommending to target users are more abundant and accurate.
- the first database is a network image database corresponding to webpage search
- the second database is an object image database corresponding to object search, wherein the number of the plurality of object images is less than the number of The number of feature images.
- the first database as a network image database and the second database as an object image database
- the network image database corresponds to webpage search (such as a webpage database of a search engine)
- the object image database corresponds to an object search (such as an e-commerce platform commodity database)
- the richness of corresponding network images in the network image database is far greater than the richness of object images in the object image database.
- the images in the first database are rich, the retrieved feature images are more abundant and accurate. Therefore, the object image obtained based on the retrieved feature image can be more abundant and accurate.
- the method according to the present disclosure may be used for product recommendation, item recommendation, similar item recommendation, etc., without limitation here.
- the objects may be objects, plants, animals, etc., which are not limited here.
- the retrieved image may be an image uploaded by the user after shooting with a mobile phone, or any image uploaded by the user from the client.
- a trained neural network is used to identify the retrieval image of the target user, so as to obtain retrieval features of the retrieval object.
- the trained neural network is obtained by using multiple classified images for training.
- each feature image in the plurality of feature images corresponds to one classification feature in the plurality of classification features
- the search feature includes the first one corresponding to the search object in the plurality of classification features A categorical feature.
- obtaining at least one feature image from a first database including a plurality of feature images includes:
- Step S310 Obtain at least one first feature image corresponding to the first classification feature among the plurality of feature images.
- Step S320 Obtain the at least one retrieval feature image from the at least one first feature image.
- the processing By classifying a plurality of feature images in the first database, and obtaining at least one first feature image corresponding to the classification feature based on the classification feature of the retrieval object, and obtaining the retrieval feature image from the at least one first feature image, the processing
- the amount of data is small.
- the classification features include, for example, multiple classifications respectively corresponding to mobile phones, clothing, food and so on.
- the classification feature also includes multi-level subcategories corresponding to the mobile phone classification of mobile phones, for example, multiple first subcategories corresponding to mobile phone brands, each of the multiple first subcategories A second subcategory corresponding to cell phone models in a first subcategory and so on.
- At least one feature image acquired from the first image database may be the feature image with the highest definition corresponding to the first category, so that the object image obtained based on the feature image is more accurate .
- the feature image of the retrieval object obtained in step S310 may be the clearest image among the multiple large-screen mobile phone images obtained. The image is clearer and the image of the object obtained based on it is more accurate.
- At least one feature image acquired from the first image database may be a plurality of images corresponding to the first category, so that the object images obtained based on the plurality of feature images are more abundant.
- the feature image of the retrieval object acquired in step S310 may be a plurality of images obtained from the official website of brand A, because the images on the official website of brand A Often the shooting angle is better and the images are richer, based on which the object images obtained are more accurate and at the same time, more abundant A-brand mobile phones can be obtained.
- obtaining the at least one retrieval feature image from the at least one first feature image includes:
- Step S410 Obtain a first similarity between each of the at least one first feature image and the retrieved image.
- Step S420 Obtain the at least one retrieval feature image, wherein the first similarity corresponding to each retrieval feature image in the at least one retrieval feature image is greater than a first threshold.
- a feature image whose similarity with the retrieval image is greater than the first threshold is obtained as the retrieval feature image, except that the retrieval feature image is consistent with the category corresponding to the retrieval object.
- the object image acquired based on the retrieval feature image is more accurate.
- acquiring a target object image set from a second database including a plurality of object images includes:
- Step S510 Obtain a second similarity between each of the at least one search feature image and each of the plurality of object images
- Step S520 Obtain one or more first object images from the plurality of object images, wherein, for each first object image in the one or more first object images, the first object image corresponds to a maximum value in at least one second similarity is greater than a second threshold;
- Step S530 Obtain the target object image set based on the one or more first object images.
- a target object image set is obtained by acquiring one or more second object images among the plurality of object images, and obtaining the target object image set from the one or more first object images. Since the second similarity corresponding to each of the one or more first object images and the retrieval feature image is relatively high (the maximum value of at least one second similarity corresponding to the first object image is greater than the first second threshold), which has a higher matching degree with the retrieved image, so the image set of the target object obtained based on it is more accurate, and thus more in line with user needs.
- the object image corresponding to at least one second similarity with the largest average value among the plurality of object images may also be used as the first object image, and a target object image set is obtained based on it to recommend to the target user.
- obtaining the target object image set includes:
- Step S610 Obtain image information corresponding to each retrieval feature image in the at least one retrieval feature image, wherein the image information includes at least one of the following items: the image feature information of the corresponding retrieval feature image and the corresponding Descriptive information related to the retrieved feature image; and
- Step S620 Acquire the target object image set based on the image information corresponding to the at least one feature image and the one or more first object images.
- the target object image is obtained, because the image feature information and description information of the retrieval feature image include more information related to the retrieval object, such as brand logo (logo) , color, etc., the object in the target object image obtained based on the image information is more in line with the user's needs.
- the first database is a network image database
- obtaining the image information corresponding to each of the at least one retrieval feature image includes: for each of the at least one retrieval feature image, obtaining the retrieval The title of the webpage corresponding to the feature image, keywords in the webpage, or keywords corresponding to user requests, and the like.
- obtaining the image information corresponding to each of the at least one retrieval feature image includes: for each of the at least one retrieval feature image, obtaining image features in the retrieval feature image, for example retrieve the pixel values of an object and more.
- each object image of the plurality of object images corresponds to an object of the plurality of objects
- each object of the plurality of objects corresponds to one or more of the plurality of object labels object label
- step S620 based on the image information corresponding to the at least one feature image and the one or more first object images, obtaining the target object image set includes:
- Step S710 Obtain at least one object label among the plurality of object labels based on the image information corresponding to the at least one retrieval feature image;
- Step S720 Obtain at least one second object image from the plurality of object images, wherein the object corresponding to each second object image in the at least one second object image corresponds to the at least one object label;
- Step S730 Obtain the target object image set based on the at least one second object image and the one or more first object images.
- the object label of the corresponding object is obtained by retrieving the image information of the feature image. Since the object label describes the object more accurately, for example, the object label includes brand, model, size, etc., the target object obtained based on the object label is more accurate.
- the set of target object images includes one or more third object images of the one or more first object images, wherein for each of the one or more third object images A third object image, the third object image at least corresponds to the object corresponding to the object image in the at least one second object image.
- a third object image corresponding to the same object as the second object image is obtained from one or more first object images similar to the retrieved feature image as the target object image, so that the target object image is more accurate.
- obtaining the set of target object images further includes: obtaining user preference information, from the at least one second object image based on the user preference A target image set is obtained from the object image and the one or more first object images.
- User preferences include user preferences for search accuracy and search breadth.
- user preferences are preferences for search accuracy so that the target object image set includes the above-mentioned third object image
- user preferences are preferences for search breadth that make the target
- the set of object images includes the aforementioned at least one second object image and one or more first object images.
- the device 800 includes: an image recognition unit 810 configured to recognize a retrieval image of a retrieval object from a target user, so as to obtain the The retrieval feature of the retrieval object; and the first retrieval unit 820 is configured to obtain at least one retrieval feature image from the first database including a plurality of feature images based on the retrieval feature; the second retrieval unit 830 is configured to It is configured to acquire a target object image set from a second database including a plurality of object images based on the at least one retrieval feature image, to recommend to the target user.
- each feature image in the plurality of feature images corresponds to a classification feature in a plurality of classification features
- the retrieval feature includes a classification feature corresponding to the retrieval object in the plurality of classification features A first classification feature
- the first retrieval unit includes: a first retrieval subunit configured to obtain at least one first feature image corresponding to the first classification feature among the plurality of feature images; And a first obtaining unit configured to obtain the at least one retrieval feature image from the at least one first feature image.
- the first acquiring unit includes: a first similarity acquiring unit configured to acquire the relationship between each first feature image in the at least one first feature image and the search image first similarity; and a first acquisition subunit configured to acquire the at least one retrieval feature image, wherein the first similarity corresponding to each retrieval feature image in the at least one retrieval feature image is greater than the first threshold.
- the second retrieval unit includes: a second similarity acquisition unit configured to acquire each of the at least one retrieval feature image and each of the plurality of object images A second degree of similarity between an object image; a second acquisition unit configured to acquire one or more first object images from the plurality of object images, wherein, for the one or more first object For each first object image in the image, the maximum value of the at least one second similarity corresponding to the first object image is greater than the second threshold; and the third acquisition unit is configured to be based on the one or more first An object image, acquiring the target object image set.
- the third acquisition unit includes: a third acquisition subunit configured to acquire image information corresponding to each retrieval feature image in the at least one retrieval feature image, wherein the image information includes At least one of the following items: image feature information of the corresponding retrieval feature image and descriptive information related to the corresponding retrieval feature image; and a fourth acquisition unit configured to be based on the image corresponding to the at least one feature image information and the one or more first object images to obtain the set of target object images.
- each object image of the plurality of object images corresponds to an object of the plurality of objects, and each object of the plurality of objects corresponds to one or more of the plurality of object labels An object tag
- the fourth acquiring unit includes: a fifth acquiring unit configured to acquire at least one object tag among the plurality of object tags based on the image information corresponding to the at least one retrieval feature image; A sixth acquiring unit configured to acquire at least one second object image from the plurality of object images, wherein the object corresponding to each second object image in the at least one second object image is the same as the at least one second object image An object tag corresponds; and a target acquisition unit configured to acquire the set of target object images based on the at least one second object image and the one or more first object images.
- the set of target object images includes one or more third object images of the one or more first object images, wherein for each of the one or more third object images A third object image, the third object image at least corresponds to the object corresponding to the object image in the at least one second object image.
- the first database is a network image database corresponding to webpage search
- the second database is an object image database corresponding to object search, wherein the number of the plurality of object images is less than the number of The number of feature images.
- an electronic device including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program, and the computer program is executed by The at least one processor implements the method according to the above when executed.
- a non-transitory computer-readable storage medium storing a computer program, wherein the computer program implements the above method when executed by a processor.
- a computer program product including a computer program, wherein the computer program implements the method according to the above when executed by a processor.
- an electronic device a readable storage medium, and a computer program product are also provided.
- Electronic device is intended to mean various forms of digital electronic computing equipment, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
- Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices.
- the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
- the device 900 includes a computing unit 901 that can execute according to a computer program stored in a read-only memory (ROM) 902 or loaded from a storage unit 908 into a random-access memory (RAM) 903. Various appropriate actions and treatments. In the RAM 903, various programs and data necessary for the operation of the device 900 can also be stored.
- the computing unit 901, ROM 902, and RAM 903 are connected to each other through a bus 904.
- An input/output (I/O) interface 905 is also connected to the bus 904 .
- the input unit 906 may be any type of device capable of inputting information to the device 900, the input unit 906 may receive input digital or character information, and generate key signal input related to user settings and/or function control of the electronic device, and may Including but not limited to mouse, keyboard, touch screen, trackpad, trackball, joystick, microphone and/or remote control.
- the output unit 907 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, an object/audio output terminal, a vibrator, and/or a printer.
- the storage unit 908 may include, but is not limited to, a magnetic disk and an optical disk.
- the communication unit 909 allows the device 900 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver and/or a chipset , such as a BluetoothTM device, a 1302.11 device, a WiFi device, a WiMax device, a cellular communication device, and/or the like.
- the computing unit 901 may be various general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of computing units 901 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc.
- the calculation unit 901 executes various methods and processes described above, such as the method 200 .
- method 200 may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 908 .
- part or all of the computer program may be loaded and/or installed on the device 900 via the ROM 902 and/or the communication unit 909.
- a computer program is loaded into RAM 903 and executed by computing unit 901, one or more steps of method 200 described above may be performed.
- the computing unit 901 may be configured to execute the method 200 in any other suitable manner (for example, by means of firmware).
- Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof.
- FPGAs field programmable gate arrays
- ASICs application specific integrated circuits
- ASSPs application specific standard products
- SOC system of systems
- CPLD load programmable logic device
- computer hardware firmware, software, and/or combinations thereof.
- programmable processor can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.
- Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented.
- the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
- a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
- a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
- a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
- machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
- RAM random access memory
- ROM read only memory
- EPROM or flash memory erasable programmable read only memory
- CD-ROM compact disk read only memory
- magnetic storage or any suitable combination of the foregoing.
- the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer.
- a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
- a keyboard and pointing device eg, a mouse or a trackball
- Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
- the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
- the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.
- a computer system may include clients and servers.
- Clients and servers are generally remote from each other and typically interact through a communication network.
- the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
- the server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.
- steps may be reordered, added or deleted using the various forms of flow shown above.
- each step described in the present disclosure may be executed in parallel, sequentially or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
提供了一种对象推荐方法和装置,涉及计算机技术领域,尤其涉及基于人工智能的推荐技术领域。该方法包括:对目标用户的包含检索对象的检索图像进行识别,以获得检索对象的检索特征(S210);基于检索特征,从包括多个特征图像的第一数据库中,获取至少一个检索特征图像(S220);以及基于至少一个检索特征图像,从包括多个对象图像的第二数据库中,获取目标对象图像集,以推荐给所述目标用户(S230)。
Description
相关申请的交叉引用
本申请要求于2021年9月28日提交的中国专利申请202111143903.1的优先权,其全部内容通过引用整体结合在本申请中。
本公开涉及计算机技术领域,尤其涉及基于人工智能的推荐技术,具体涉及一种对象推荐方法、装置、电子设备、计算机可读存储介质和计算机程序产品。
人工智能是研究使计算机来模拟人的某些思维过程和智能行为(如学习、推理、思考、规划等)的学科,既有硬件层面的技术也有软件层面的技术。人工智能硬件技术一般包括如传感器、专用人工智能芯片、云计算、分布式存储、大数据处理等技术:人工智能软件技术主要包括计算机视觉技术、语音识别技术、自然语言处理技术以及机器学习/深度学习、大数据处理技术、知识图谱技术等几大方向。
基于人工智能的推荐技术,已经渗透到各个领域。其中,基于人工智能的对象推荐技术,根据对象的特征结合用户对对象的偏好,实现向用户推荐对象。
在此部分中描述的方法不一定是之前已经设想到或采用的方法。除非另有指明,否则不应假定此部分中描述的任何方法仅因其包括在此部分中就被认为是现有技术。类似地,除非另有指明,否则此部分中提及的问题不应认为在任何现有技术中已被公认。
发明内容
本公开提供了一种对象推荐方法、装置、电子设备、计算机可读存储介质和计算机程序产品。
根据本公开的一方面,提供了一种对象推荐方法,包括:对目标用户的包含检索对象的检索图像进行识别,以获得所述检索对象的检索特征;基于所述检索特征,从包括多个特征图像的第一数据库中,获取至少一个检索特征图像;以及基于所述至少一个检索特征图像,从包括多个对象图像的第二数据库中,获取目标对象图像集,以推荐给所述目标用户。
根据本公开的另一方面,提供了一种对象推荐装置,包括:图像识别单元,被配置用于对来自目标用户的检索对象的检索图像进行识别,以获得所述检索对象的检索特征;以及第一检索单元,被配置用于基于所述检索特征,从包括多个特征图像的第一数据库中,获取至少一个检索特征图像;第二检索单元,被配置用于基于所述至少一个检索特征图像,从包括多个对象图像的第二数据库中,获取目标对象图像集,以推荐给所述目标用户。
根据本公开的另一方面,提供了一种电子设备,包括:至少一个处理器;以及与所述至少一个处理器通信连接的存储器;其中所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器实现根据上述的方法。
根据本公开的另一方面,提供了一种存储有计算机指令的非瞬时计算机可读存储介质,其中,所述计算机指令用于使所述计算机实现根据上述的方法。
根据本公开的另一方面,提供了一种计算机程序产品包括计算机程序,其中,所述计算机程序在被处理器执行时实现根据上述的方法。
根据本公开的一个或多个实施例,通过对包含检索对象的检索图像进行识别,获得检索对象的检索特征(例如,检索对象为手机时,检索特征可以是手机分类),从包括多个特征图像的第一数据库中获取对应于检索对象的特征图像,再通过特征图像与对象图像数据库进行匹配,获取目标对象图像集,以推荐给目标用户。由于第一数据库中的特征图像清晰度高、拍摄角度好,更能体现检索对象的特征,从而使基于特征图像获得的对象图像更准确,即给用户推荐的目标对象更加准确。
应当理解,本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征,也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。
附图示例性地示出了实施例并且构成说明书的一部分,与说明书的文字描述一起用于讲解实施例的示例性实施方式。所示出的实施例仅出于例示的目的,并不限制权利要求的范围。在所有附图中,相同的附图标记指代类似但不一定相同的要素。
图1示出了根据本公开的实施例的可以在其中实施本文描述的各种方法的示例性系统的示意图;
图2示出了根据本公开的实施例的对象推荐方法的流程图;
图3示出了根据本公开的实施例的对象推荐方法中基于检索特征从包括多个特征图像的第一数据库中获取至少一个检索特征图像的过程的流程图;
图4示出了根据本公开的实施例的对象推荐方法中从至少一个第一特征图像中获取至少一个检索特征图像的过程的流程图;
图5示出了根据本公开的实施例的对象推荐方法中基于至少一个检索特征图像从包括多个对象图像的第二数据库中获取目标对象图像集的过程的流程图;
图6示出了根据本公开的实施例的对象推荐方法中基于一个或多个第一对象图像获取所述目标对象图像集的过程的流程图;
图7示出了根据本公开的实施例的对象推荐方法中基于至少一个特征图像对应的图像信息和一个或多个第一对象图像获取目标对象图像集的过程的流程图;
图8示出了根据本公开的实施例的对象推荐装置的结构框图;以及
图9示出了能够用于实现本公开的实施例的示例性电子设备的结构框图。
以下结合附图对本公开的示范性实施例做出说明,其中包括本公开实施例的各种细节以助于理解,应当将它们认为仅仅是示范性的。因此,本领域普通技术人员应当认识到,可以对这里描述的实施例做出各种改变和修改,而不会背离本公开的范围。同样,为了清楚和简明,以下的描述中省略了对公知功能和结构的描述。
在本公开中,除非另有说明,否则使用术语“第一”、“第二”等来描述各种要素不意图限定这些要素的位置关系、时序关系或重要性关系,这种术语只是用于将一个元件与另一元件区分开。在一些示例中,第一要素和第二要素可以指向该要素的同一实例,而在某些情况下,基于上下文的描述,它们也可以指代不同实例。
在本公开中对各种所述示例的描述中所使用的术语只是为了描述特定示例的目的,而并非旨在进行限制。除非上下文另外明确地表明,如果不特意限定要素的数量,则该要素可以是一个也可以是多个。此外,本公开中所使用的术语“和/或”涵盖所列出的项目中的任何一个以及全部可能的组合方式。
下面将结合附图详细描述本公开的实施例。
图1示出了根据本公开的实施例可以将本文描述的各种方法和装置在其中实施的示例性系统100的示意图。参考图1,该系统100包括一个或多个客户端设备101、102、103、104、105和106、服务器120以及将一个或多个客户端设备耦接到服务器120的一 个或多个通信网络110。客户端设备101、102、103、104、105和106可以被配置为执行一个或多个应用程序。
在本公开的实施例中,服务器120可以运行使得能够执行对象推荐方法的一个或多个服务或软件应用。
在某些实施例中,服务器120还可以提供可以包括非虚拟环境和虚拟环境的其他服务或软件应用。在某些实施例中,这些服务可以作为基于web的服务或云服务提供,例如在软件即服务(SaaS)模型下提供给客户端设备101、102、103、104、105和/或106的用户。
在图1所示的配置中,服务器120可以包括实现由服务器120执行的功能的一个或多个组件。这些组件可以包括可由一个或多个处理器执行的软件组件、硬件组件或其组合。操作客户端设备101、102、103、104、105和/或106的用户可以依次利用一个或多个客户端应用程序来与服务器120进行交互以利用这些组件提供的服务。应当理解,各种不同的系统配置是可能的,其可以与系统100不同。因此,图1是用于实施本文所描述的各种方法的系统的一个示例,并且不旨在进行限制。
用户可以使用客户端设备101、102、103、104、105和/或106来观看推荐的对象。客户端设备可以提供使客户端设备的用户能够与客户端设备进行交互的接口。客户端设备还可以经由该接口向用户输出信息。尽管图1仅描绘了六种客户端设备,但是本领域技术人员将能够理解,本公开可以支持任何数量的客户端设备。
客户端设备101、102、103、104、105和/或106可以包括各种类型的计算机设备,例如便携式手持设备、通用计算机(诸如个人计算机和膝上型计算机)、工作站计算机、可穿戴设备、智能屏设备、自助服务终端设备、服务机器人、游戏系统、瘦客户端、各种消息收发设备、传感器或其他感测设备等。这些计算机设备可以运行各种类型和版本的软件应用程序和操作系统,例如MICROSOFT Windows、APPLE iOS、类UNIX操作系统、Linux或类Linux操作系统(例如GOOGLE Chrome OS);或包括各种移动操作系统,例如MICROSOFT Windows Mobile OS、iOS、Windows Phone、Android。便携式手持设备可以包括蜂窝电话、智能电话、平板电脑、个人数字助理(PDA)等。可穿戴设备可以包括头戴式显示器(诸如智能眼镜)和其他设备。游戏系统可以包括各种手持式游戏设备、支持互联网的游戏设备等。客户端设备能够执行各种不同的应用程序,例如各种与Internet相关的应用程序、通信应用程序(例如电子邮件应用程序)、短消息服务(SMS)应用程序,并且可以使用各种通信协议。
网络110可以是本领域技术人员熟知的任何类型的网络,其可以使用多种可用协议中的任何一种(包括但不限于TCP/IP、SNA、IPX等)来支持数据通信。仅作为示例,一个或多个网络110可以是局域网(LAN)、基于以太网的网络、令牌环、广域网(WAN)、因特网、虚拟网络、虚拟专用网络(VPN)、内部网、外部网、公共交换电话网(PSTN)、红外网络、无线网络(例如蓝牙、WIFI)和/或这些和/或其他网络的任意组合。
服务器120可以包括一个或多个通用计算机、专用服务器计算机(例如PC(个人计算机)服务器、UNIX服务器、中端服务器)、刀片式服务器、大型计算机、服务器群集或任何其他适当的布置和/或组合。服务器120可以包括运行虚拟操作系统的一个或多个虚拟机,或者涉及虚拟化的其他计算架构(例如可以被虚拟化以维护服务器的虚拟存储设备的逻辑存储设备的一个或多个灵活池)。在各种实施例中,服务器120可以运行提供下文所描述的功能的一个或多个服务或软件应用。
服务器120中的计算单元可以运行包括上述任何操作系统以及任何商业上可用的服务器操作系统的一个或多个操作系统。服务器120还可以运行各种附加服务器应用程序和/或中间层应用程序中的任何一个,包括HTTP服务器、FTP服务器、CGI服务器、JAVA服务器、数据库服务器等。
在一些实施方式中,服务器120可以包括一个或多个应用程序,以分析和合并从客户端设备101、102、103、104、105和106的用户接收的数据馈送和/或事件更新。服务器120还可以包括一个或多个应用程序,以经由客户端设备101、102、103、104、105和106的一个或多个显示设备来显示数据馈送和/或实时事件。
在一些实施方式中,服务器120可以为分布式系统的服务器,或者是结合了区块链的服务器。服务器120也可以是云服务器,或者是带人工智能技术的智能云计算服务器或智能云主机。云服务器是云计算服务体系中的一项主机产品,以解决传统物理主机与虚拟专用服务器(VPS,Virtual Private Server)服务中存在的管理难度大、业务扩展性弱的缺陷。
系统100还可以包括一个或多个数据库130。在某些实施例中,这些数据库可以用于存储数据和其他信息。例如,数据库130中的一个或多个可用于存储诸如音频文件和对象文件的信息。数据存储库130可以驻留在各种位置。例如,由服务器120使用的数据存储库可以在服务器120本地,或者可以远离服务器120且可以经由基于网络或专用的连接与服务器120通信。数据存储库130可以是不同的类型。在某些实施例中,由服务 器120使用的数据存储库可以是数据库,例如关系数据库。这些数据库中的一个或多个可以响应于命令而存储、更新和检索到数据库以及来自数据库的数据。
在某些实施例中,数据库130中的一个或多个还可以由应用程序使用来存储应用程序数据。由应用程序使用的数据库可以是不同类型的数据库,例如键值存储库,对象存储库或由文件系统支持的常规存储库。
图1的系统100可以以各种方式配置和操作,以使得能够应用根据本公开所描述的各种方法和装置。
参看图2,根据本公开的一些实施例的一种对象推荐方法200包括:
步骤S210:对目标用户的包含检索对象的检索图像进行识别,以获得所述检索对象的检索特征;
步骤S220:基于所述检索特征,从包括多个特征图像的第一数据库中,获取至少一个检索特征图像;以及
步骤S230:基于所述至少一个检索特征图像,从包括多个对象图像的第二数据库中,获取目标对象图像集,以推荐给所述目标用户。
根据本公开的一个或多个实施例,通过对包含检索对象的检索图像进行识别,获得检索对象的检索特征(例如,检索对象为手机时,检索特征可以是手机分类),从包括多个特征图像的第一数据库中获取对应于检索对象的特征图像,再通过特征图像与对象图像数据库进行匹配,获取目标对象图像集,以推荐给目标用户。由于第一数据库中的特征图像清晰度高、拍摄角度好,更能体现检索对象的特征,从而使基于特征图像获得的对象图像更准确,即给用户推荐的目标对象跟家准确。
在相关技术中,在基于目标用户的检索图像为用户推荐对象的过程中,根据目标用户的检索图像直接从对象图像数据库中获取目标对象图像以推荐给目标用户,推荐给目标用户的目标对象图像是与检索图像相似的一个或多个图像,其仅仅能在用户图像准确的情况下,推荐与检索对象匹配的对象。当用户的检索图像不清晰时,推荐的对象往往不准确,而不能满足用户的需求;也不能根据检索图像给用户推荐与检索对象相关的更加丰富的对象。
例如,在物品推荐中,目标用户的当前检索图像是在光线不足的条件下拍摄的手机屏的照片,推荐的对象图像可能是含有各种手机屏的手机。在根据本公开的实施例中,可以通过识别该检索图像中的检索对象为哪一种手机品牌的手机,从而从第一数据库中获得对应于该手机品牌的特征图像,该特征图像是清晰的、且能反应该手机品牌的真实 情况的图像,从而能够使根据该特征图像从第二数据库中获得的对象图像准确,进而使给用户推荐的手机准确。
根据本公开的实施例,第一数据库作为对象推荐和搜索的中间数据库,其起到桥梁的作用,通过该桥梁将检索对象和与对象推荐对应的对象图像数据库连接起来,使从对象图像数据库中获得的用以推荐给目标用户的目标对象图像集中的目标对象图像更加丰富和准确。
在一些实施例中,所述第一数据库为对应于网页搜索的网络图像数据库,所述第二数据库为对应于对象搜索的对象图像数据库,其中,所述多个对象图像的数量小于所述多个特征图像的数量。
通过将第一数据库设置成网络图像数据库,第二数据库设置为对象图像数据库,由于网络图像数据库对应于网页搜索(例如搜索引擎的网页数据库),而对象图像数据库对应于对象搜索(例如电商平台的商品数据库),使网络图像数据库中对应的网路图像的丰富程度远远大于对象图像数据库中的对象图像的丰富程度。由于第一数据库中的图像丰富,使获得检索特征图像更加丰富和准确。从而使基于检索特征图像获得的对象图像能够更加丰富和准确。
在一些实施例中,根据本公开的方法可以用于商品推荐、物品推荐、相似物推荐等等,在此不作限制。
在一些实施例中,对象可以是物品、植物、动物等等,在此并不限定。
在一些实施例中,检索图像可以是用户采用手机拍摄后上传图像,也可以用户从客户端上传的任何图像。
在一些实施例中,在步骤S210中,采用经训练的神经网络对目标用户的检索图像进行识别,以获得检索对象的检索特征。其中,经训练的神经网络采用多个已分类图像进行训练而获得。
在一些实施例中,述多个特征图像中的每一个特征图像对应于多个分类特征中的一个分类特征,所述检索特征包括所述多个分类特征中的与所述检索对象对应的第一分类特征。如图3所示、基于所述检索特征,从包括多个特征图像的第一数据库中,获取至少一个特征图像包括:
步骤S310:获取所述多个特征图像中对应于所述第一分类特征的至少一个第一特征图像;以及
步骤S320:从所述至少一个第一特征图像中,获取所述至少一个检索特征图像。
通过将第一数据库中的多个特征图像进行分类,并基于检索对象的分类特征获得对应于该分类特征的至少一个第一特征图像,从至少一个第一特征图像中获取检索特征图像,使处理的数据量少。
在一些实施例中,分类特征例如包括分别对应于手机、服饰、食品等的多个分类。在另一些实施实施例中,分类特征还包括对应于手机的手机分类中所包括的多级子分类,例如对应于手机品牌的多个第一子分类、在多个第一子分类中的每一个第一子分类中的对应于手机型号的第二子分类等等。
在一些实施例中,在步骤S310中,从第一图像数据库中,获取的至少一个特征图像可以是对应于第一分类的清晰度最高的特征图像,使基于该特征图像获得的对象图像更加准确。例如,对于检索对象的检索特征为检索对象的种类,大屏手机,在步骤S310中获取的检索对象的特征图像可以是获得的多个大屏手机图像中的最清晰的图像,由于图像较检索图像更为清晰,基于其获得的对象图像更加准确。
在一个实施例中,在步骤S310中,从第一图像数据库中,获取的至少一个特征图像可以是对应于第一分类的多个图像,使基于该多个特征图像获得的对象图像更加丰富。例如,对于检索对象的检索特征为检索对象的品牌,A品牌,在步骤S310中获取的检索对象的特征图像可以是从A品牌的官网上获得的多个图像,由于A品牌的官网上的图像往往拍摄角度更好、图像更为丰富,基于其获得的对象图像更加准确的同时还能获得更丰富的A品牌的手机。
在一些实施例中,如图4所示,从所述至少一个第一特征图像中,获取所述至少一个检索特征图像包括:
步骤S410:获取所述至少一个第一特征图像中的每一个第一特征图像与所述检索图像之间的第一相似度;以及
步骤S420:获取所述至少一个检索特征图像,其中,所述至少一个检索特征图像中的每一个检索特征图像对应的第一相似度大于第一阈值。
通过从与检索对象对应的第一分类对应的至少一个第一特征图像中,获取与检索图像相似度大于第一阈值的特征图像作为检索特征图像,该检索特征图像除了与检索对象对应的分类一致以外,还与检索图像相似,使基于检索特征图像获取的对象图像更加准确。
在一些实施例中,如图5所示,基于所述至少一个检索特征图像,从包括多个对象图像的第二数据库中,获取目标对象图像集包括:
步骤S510:获取所述至少一个检索特征图像中的每一个检索特征图像与所述多个对象图像中的每一个对象图像之间的第二相似度;
步骤S520:从所述多个对象图像中获取一个或多个第一对象图像,其中,对于所述一个或多个第一对象图像中的每一个第一对象图像,该第一对象图像对应的至少一个第二相似度中的最大值大于第二阈值;以及
步骤S530:基于所述一个或多个第一对象图像,获取所述目标对象图像集。
通过获取多个对象图像中的一个或多个第二对象图像,并从该一个或多个第一对象图像中获取目标对象图像集。由于该一个或多个第一对象图像中的每一个第一对象图像与检索特征图像对应的第二相似度较高(该第一对象图像对应的至少一个第二相似度中的最大值大于第二阈值),其与检索图像的匹配度更高,因此基于其获得的目标对象图像集更加准确,从而更符合用户需求。
在另一些实施例中,还可以将多个对象图像中对应的至少一个第二相似度的平均值最大的对象图像作为第一对象图像,并基于其获得目标对象图像集以推荐给目标用户。
在一些实施例中,如图6所示,基于所述一个或多个第一对象图像,获取所述目标对象图像集包括:
步骤S610:获取所述至少一个检索特征图像中的每一个检索特征图像对应的图像信息,其中所述图像信息包括下列各项中的至少一项:对应的检索特征图像的图像特征信息和与对应的检索特征图像相关的描述信息;以及
步骤S620:基于所述至少一个特征图像对应的图像信息和所述一个或多个第一对象图像,获取所述目标对象图像集。
基于检索特征图像的图像特征信息和与检索特征图像相关的描述信息,获取目标对象图像,由于检索特征图像的图像特征信息和描述信息包括更多与检索对象相关的信息,比如品牌标识(logo),颜色等等,基于该图像信息获得的目标对象图像中的对象更加符合用户需求。
在一些实施例中,第一数据库为网络图像数据库,获取至少一个检索特征图像中的每一个检索特征图像对应的图像信息包括:对于至少一个检索特征图像中的每一个检索特征图像,获取该检索特征图像对应的网页的标题、网页中的关键字或者用户请求对应的关键字等等。
在一些实施例中,获取至少一个检索特征图像中的每一个检索特征图像对应的图像信息包括:对于至少一个检索特征图像中的每一个检索特征图像,获取该检索特征图像中的图像特征,例如检索对象的像素值等等。
在一些实施例中,所述多个对象图像的每一个对象图像对应于多个对象中的一个对象,以及所述多个对象中的每一个对象对应于多个对象标签中的一个或多个对象标签,并且其中,如图7所示,步骤S620、基于所述至少一个特征图像对应的图像信息和所述一个或多个第一对象图像,获取所述目标对象图像集包括:
步骤S710:基于所述至少一个检索特征图像对应的图像信息,获取所述多个对象标签中的至少一个对象标签;
步骤S720:从所述多个对象图像中获取至少一个第二对象图像,其中,所述至少一个第二对象图像中的每一个第二对象图像对应的对象与所述至少一个对象标签对应;以及
步骤S730:基于所述至少一个第二对象图像和所述一个或多个第一对象图像,获取所述目标对象图像集。
通过检索特征图像的图像信息获取对应的对象的对象标签,由于该对象标签对对象的描述更加准确,例如对象标签包括品牌、型号、尺寸等,使基于该对象标签获得的目标对象更加准确。
在一些实施例中,所述目标对象图像集包括所述一个或多个第一对象图像中的一个或多个第三对象图像,其中,对于所述一个或多个第三对象图像中的每一个第三对象图像,该第三对象图像至少与所述至少一个第二对象图像中的一个对象图像对应的对象对应。
从与检索特征图像相似的一个或多个第一对象图像中获取与第二对象图像对应的对象相同的第三对象图像作为目标对象图像,使目标对象图像更加准确。
在一些实施例中,基于所述至少一个第二对象图像和所述一个或多个第一对象图像,获取所述目标对象图像集还包括:获取用户偏好信息,基于用户偏好从至少一个第二对象图像和一个或多个第一对象图像中获取目标图像集。
用户偏好包括用户对于搜索准确度的偏好和搜索广泛性的偏好,例如用户偏好为对搜索准确度的偏好使目标对象图像集包括上述第三对象图像;用户偏好为对搜索广泛性的偏好使目标对象图像集包括上述至少一个第二对象图像和一个或多个第一对象图像。
本公开的技术方案中,所涉及的用户个人信息的收集、存储、使用、加工、传输、提供和公开等处理,均符合相关法律法规的规定,且不违背公序良俗。
根据本公开的另一方面,还提供一种对象推荐装置,参看图8,该装置800包括:图像识别单元810,被配置用于对来自目标用户的检索对象的检索图像进行识别,以获得所述检索对象的检索特征;以及第一检索单元820,被配置用于基于所述检索特征,从包括多个特征图像的第一数据库中,获取至少一个检索特征图像;第二检索单元830,被配置用于基于所述至少一个检索特征图像,从包括多个对象图像的第二数据库中,获取目标对象图像集,以推荐给所述目标用户。
在一些实施例中,所述多个特征图像中的每一个特征图像对应于多个分类特征中的一个分类特征,所述检索特征包括所述多个分类特征中的与所述检索对象对应的第一分类特征,并且其中,所述第一检索单元包括:第一检索子单元,被配置用于获取所述多个特征图像中对应于所述第一分类特征的至少一个第一特征图像;以及第一获取单元,被配置用于从所述至少一个第一特征图像中,获取所述至少一个检索特征图像。
在一些实施例中,所述第一获取单元包括:第一相似度获取单元,被配置用于获取所述至少一个第一特征图像中的每一个第一特征图像与所述检索图像之间的第一相似度;以及第一获取子单元,被配置用于获取所述至少一个检索特征图像,其中,所述至少一个检索特征图像中的每一个检索特征图像对应的第一相似度大于第一阈值。
在一些实施例中,所述第二检索单元包括:第二相似度获取单元,被配置用于获取所述至少一个检索特征图像中的每一个检索特征图像与所述多个对象图像中的每一个对象图像之间的第二相似度;第二获取单元,被配置用于从所述多个对象图像中获取一个或多个第一对象图像,其中,对于所述一个或多个第一对象图像中的每一个第一对象图像,该第一对象图像对应的至少一个第二相似度中的最大值大于第二阈值;以及第三获取单元,被配置用于基于所述一个或多个第一对象图像,获取所述目标对象图像集。
在一些实施例中,所述第三获取单元包括:第三获取子单元,被配置用于获取所述至少一个检索特征图像中的每一个检索特征图像对应的图像信息,其中所述图像信息包括下列各项中的至少一项:对应的检索特征图像的图像特征信息和与对应的检索特征图像相关的描述信息;以及第四获取单元,被配置用于基于所述至少一个特征图像对应的图像信息和所述一个或多个第一对象图像,获取所述目标对象图像集。
在一些实施例中,所述多个对象图像的每一个对象图像对应于多个对象中的一个对象,以及所述多个对象中的每一个对象对应于多个对象标签中的一个或多个对象标签, 并且其中,所述第四获取单元包括:第五获取单元,被配置用于基于所述至少一个检索特征图像对应的图像信息,获取所述多个对象标签中的至少一个对象标签;第六获取单元,被配置用于从所述多个对象图像中获取至少一个第二对象图像,其中,所述至少一个第二对象图像中的每一个第二对象图像对应的对象与所述至少一个对象标签对应;以及目标获取单元,被配置用于基于所述至少一个第二对象图像和所述一个或多个第一对象图像,获取所述目标对象图像集。
在一些实施例中,所述目标对象图像集包括所述一个或多个第一对象图像中的一个或多个第三对象图像,其中,对于所述一个或多个第三对象图像中的每一个第三对象图像,该第三对象图像至少与所述至少一个第二对象图像中的一个对象图像对应的对象对应。
在一些实施例中,所述第一数据库为对应于网页搜索的网络图像数据库,所述第二数据库为对应于对象搜索的对象图像数据库,其中,所述多个对象图像的数量小于所述多个特征图像的数量。
根据本公开的另一方面,还提供一种电子设备,包括:至少一个处理器;以及与所述至少一个处理器通信连接的存储器;其中所述存储器存储有计算机程序,所述计算机程序在被所述至少一个处理器执行时实现根据上述的方法。
根据本公开的另一方面,还提供一种存储有计算机程序的非瞬时计算机可读存储介质,其中,所述计算机程序在被处理器执行时实现根据上述的方法。
根据本公开的另一方面,还提供了一种计算机程序产品,包括计算机程序,其中,所述计算机程序在被处理器执行时实现根据上述的方法。
根据本公开的实施例,还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。
参考图9,现将描述可以作为本公开的服务器或客户端的电子设备900的结构框图,其是可以应用于本公开的各方面的硬件设备的示例。电子设备旨在表示各种形式的数字电子的计算机设备,诸如,膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置,诸如,个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例,并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图9所示,设备900包括计算单元901,其可以根据存储在只读存储器(ROM)902中的计算机程序或者从存储单元908加载到随机访问存储器(RAM)903中的计算机程序,来执行各种适当的动作和处理。在RAM 903中,还可存储设备900操作所需的各种程序和数据。计算单元901、ROM 902以及RAM 903通过总线904彼此相连。输入/输出(I/O)接口905也连接至总线904。
设备900中的多个部件连接至I/O接口905,包括:输入单元906、输出单元907、存储单元908以及通信单元909。输入单元906可以是能向设备900输入信息的任何类型的设备,输入单元906可以接收输入的数字或字符信息,以及产生与电子设备的用户设置和/或功能控制有关的键信号输入,并且可以包括但不限于鼠标、键盘、触摸屏、轨迹板、轨迹球、操作杆、麦克风和/或遥控器。输出单元907可以是能呈现信息的任何类型的设备,并且可以包括但不限于显示器、扬声器、对象/音频输出终端、振动器和/或打印机。存储单元908可以包括但不限于磁盘、光盘。通信单元909允许设备900通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据,并且可以包括但不限于调制解调器、网卡、红外通信设备、无线通信收发机和/或芯片组,例如蓝牙TM设备、1302.11设备、WiFi设备、WiMax设备、蜂窝通信设备和/或类似物。
计算单元901可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元901的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元901执行上文所描述的各个方法和处理,例如方法200。例如,在一些实施例中,方法200可被实现为计算机软件程序,其被有形地包含于机器可读介质,例如存储单元908。在一些实施例中,计算机程序的部分或者全部可以经由ROM 902和/或通信单元909而被载入和/或安装到设备900上。当计算机程序加载到RAM 903并由计算单元901执行时,可以执行上文描述的方法200的一个或多个步骤。备选地,在其他实施例中,计算单元901可以通过其他任何适当的方式(例如,借助于固件)而被配置为执行方法200。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括:实施在一个或者多个计算机程序中,该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/ 或解释,该可编程处理器可以是专用或者通用可编程处理器,可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令,并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器,使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行,作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中,机器可读介质可以是有形的介质,其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备,或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互,可以在计算机上实施此处描述的系统和技术,该计算机具有:用于向用户显示信息的显示装置(例如,CRT(阴极射线管)或者LCD(液晶显示器)监视器);以及键盘和指向装置(例如,鼠标或者轨迹球),用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互;例如,提供给用户的反馈可以是任何形式的传感反馈(例如,视觉反馈、听觉反馈、或者触觉反馈);并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如,作为数据服务器)、或者包括中间件部件的计算系统(例如,应用服务器)、或者包括前端部件的计算系统(例如,具有图形用户界面或者网络浏览器的用户计算机,用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如,通信网络)来将系统的部件相互连接。通信网络的示例包括:局域网(LAN)、广域网(WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器,也可以为分布式系统的服务器,或者是结合了区块链的服务器。
应该理解,可以使用上面所示的各种形式的流程,重新排序、增加或删除步骤。例如,本公开中记载的各步骤可以并行地执行、也可以顺序地或以不同的次序执行,只要能够实现本公开公开的技术方案所期望的结果,本文在此不进行限制。
虽然已经参照附图描述了本公开的实施例或示例,但应理解,上述的方法、系统和设备仅仅是示例性的实施例或示例,本发明的范围并不由这些实施例或示例限制,而是仅由授权后的权利要求书及其等同范围来限定。实施例或示例中的各种要素可以被省略或者可由其等同要素替代。此外,可以通过不同于本公开中描述的次序来执行各步骤。进一步地,可以以各种方式组合实施例或示例中的各种要素。重要的是随着技术的演进,在此描述的很多要素可以由本公开之后出现的等同要素进行替换。
Claims (19)
- 一种对象推荐方法,包括:对目标用户的包含检索对象的检索图像进行识别,以获得所述检索对象的检索特征;基于所述检索特征,从包括多个特征图像的第一数据库中,获取至少一个检索特征图像;以及基于所述至少一个检索特征图像,从包括多个对象图像的第二数据库中,获取目标对象图像集,以推荐给所述目标用户。
- 根据权利要求1所述的方法,其中,所述多个特征图像中的每一个特征图像对应于多个分类特征中的一个分类特征,所述检索特征包括所述多个分类特征中的与所述检索对象对应的第一分类特征,并且其中,所述基于所述检索特征,从包括多个特征图像的第一数据库中,获取至少一个特征图像包括:获取所述多个特征图像中对应于所述第一分类特征的至少一个第一特征图像;以及从所述至少一个第一特征图像中,获取所述至少一个检索特征图像。
- 根据权利要求2所述的方法,其中,所述从所述至少一个第一特征图像中,获取所述至少一个检索特征图像包括:获取所述至少一个第一特征图像中的每一个第一特征图像与所述检索图像之间的第一相似度;以及获取所述至少一个检索特征图像,其中,所述至少一个检索特征图像中的每一个检索特征图像对应的第一相似度大于第一阈值。
- 根据权利要求1-3中任一项所述的方法,其中,所述基于所述至少一个检索特征图像,从包括多个对象图像的第二数据库中,获取目标对象图像集包括:获取所述至少一个检索特征图像中的每一个检索特征图像与所述多个对象图像中的每一个对象图像之间的第二相似度;从所述多个对象图像中获取一个或多个第一对象图像,其中,对于所述一个或多个第一对象图像中的每一个第一对象图像,该第一对象图像对应的至少一个第二相似度中的最大值大于第二阈值;以及基于所述一个或多个第一对象图像,获取所述目标对象图像集。
- 根据权利要求4所述的方法,其中,所述基于所述一个或多个第一对象图像,获取所述目标对象图像集包括:获取所述至少一个检索特征图像中的每一个检索特征图像对应的图像信息,其中所述图像信息包括下列各项中的至少一项:对应的检索特征图像的图像特征信息和与对应的检索特征图像相关的描述信息;以及基于所述至少一个特征图像对应的图像信息和所述一个或多个第一对象图像,获取所述目标对象图像集。
- 根据权利要求5所述的方法,其中,所述多个对象图像的每一个对象图像对应于多个对象中的一个对象,以及所述多个对象中的每一个对象对应于多个对象标签中的一个或多个对象标签,并且其中,所述基于所述至少一个特征图像对应的一个或多个图像信息和所述一个或多个第一对象图像,获取所述目标对象图像集包括:基于所述至少一个检索特征图像对应的图像信息,获取所述多个对象标签中的至少一个对象标签;从所述多个对象图像中获取至少一个第二对象图像,其中,所述至少一个第二对象图像中的每一个第二对象图像对应的对象与所述至少一个对象标签对应;以及基于所述至少一个第二对象图像和所述一个或多个第一对象图像,获取所述目标对象图像集。
- 根据权利要求6所述的方法,其中,所述目标对象图像集包括所述一个或多个第一对象图像中的一个或多个第三对象图像,其中,对于所述一个或多个第三对象图像中的每一个第三对象图像,该第三对象图像至少与所述至少一个第二对象图像中的一个第二对象图像对应的对象对应。
- 根据权利要求1-7中任一项所述的方法,其中,所述第一数据库为对应于网页搜索的网络图像数据库,所述第二数据库为对应于对象搜索的对象图像数据库,其中,所述多个对象图像的数量小于所述多个特征图像的数量。
- 一种对象推荐装置,包括:图像识别单元,被配置用于对目标用户的包含检索对象的检索图像进行识别,以获得所述检索对象的检索特征;以及第一检索单元,被配置用于基于所述检索特征,从包括多个特征图像的第一数据库中,获取至少一个检索特征图像;第二检索单元,被配置用于基于所述至少一个检索特征图像,从包括多个对象图像的第二数据库中,获取目标对象图像集,以推荐给所述目标用户。
- 根据权利要求9所述的装置,所述多个特征图像中的每一个特征图像对应于多个分类特征中的一个分类特征,所述检索特征包括所述多个分类特征中的与所述检索对象对应的第一分类特征,并且其中,所述第一检索单元包括:第一检索子单元,被配置用于获取所述多个特征图像中对应于所述第一分类特征的至少一个第一特征图像;以及第一获取单元,被配置用于从所述至少一个第一特征图像中,获取所述至少一个检索特征图像。
- 根据权利要求10所述的装置,其中,所述第一获取单元包括:第一相似度获取单元,被配置用于获取所述至少一个第一特征图像中的每一个第一特征图像与所述检索图像之间的第一相似度;以及第一获取子单元,被配置用于获取所述至少一个检索特征图像,其中,所述至少一个检索特征图像中的每一个检索特征图像对应的第一相似度大于第一阈值。
- 根据权利要求9-11中任一项所述的装置,其中,所述第二检索单元包括:第二相似度获取单元,被配置用于获取所述至少一个检索特征图像中的每一个检索特征图像与所述多个对象图像中的每一个对象图像之间的第二相似度;第二获取单元,被配置用于从所述多个对象图像中获取一个或多个第一对象图像,其中,对于所述一个或多个第一对象图像中的每一个第一对象图像,该第一对象图像对应的至少一个第二相似度中的最大值大于第二阈值;以及第三获取单元,被配置用于基于所述一个或多个第一对象图像,获取所述目标对象图像集。
- 根据权利要求12所述的装置,其中,所述第三获取单元包括:第三获取子单元,被配置用于获取所述至少一个检索特征图像中的每一个检索特征图像对应的图像信息,其中所述图像信息包括下列各项中的至少一项:对应的检索特征图像的图像特征信息和与对应的检索特征图像相关的描述信息;以及第四获取单元,被配置用于基于所述至少一个特征图像对应的图像信息和所述一个或多个第一对象图像,获取所述目标对象图像集。
- 根据权利要求13所述的装置,其中,所述多个对象图像的每一个对象图像对应于多个对象中的一个对象,以及所述多个对象中的每一个对象对应于多个对象标签中的一个或多个对象标签,并且其中,所述第四获取单元包括:第五获取单元,被配置用于基于所述至少一个检索特征图像对应的图像信息,获取所述多个对象标签中的至少一个对象标签;第六获取单元,被配置用于从所述多个对象图像中获取至少一个第二对象图像,其中,所述至少一个第二对象图像中的每一个第二对象图像对应的对象与所述至少一个对象标签对应;以及目标获取单元,被配置用于基于所述至少一个第二对象图像和所述一个或多个第一对象图像,获取所述目标对象图像集。
- 根据权利要求14所述的装置,其中,所述目标对象图像集包括所述一个或多个第一对象图像中的一个或多个第三对象图像,其中,对于所述一个或多个第三对象图像中的每一个第三对象图像,该第三对象图像至少与所述至少一个第二对象图像中的一个第二对象图像对应的对象对应。
- 根据权利要求9-15中任一项所述的装置,其中,所述第一数据库为对应于网页搜索的网络图像数据库,所述第二数据库为对应于对象搜索的对象图像数据库,其中,所述多个对象图像的数量小于所述多个特征图像的数量。
- 一种电子设备,包括:至少一个处理器;以及与所述至少一个处理器通信连接的存储器;其中所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行权利要求1-8中任意一项所述的方法。
- 一种存储有计算机指令的非瞬时计算机可读存储介质,其中,所述计算机指令用于使所述计算机执行根据权利要求1-8中任一项所述的方法。
- 一种计算机程序产品,包括计算机程序,其中,所述计算机程序在被处理器执行时实现权利要求1-8中任一项所述的方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP22822250.1A EP4184349A4 (en) | 2021-09-28 | 2022-03-16 | METHOD AND DEVICE FOR OBJECT RECOMMENDATION |
JP2022581447A JP2023547299A (ja) | 2021-09-28 | 2022-03-16 | オブジェクト推薦方法及び装置 |
US18/003,116 US12079268B2 (en) | 2021-09-28 | 2022-03-16 | Object recommendation |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111143903.1A CN113868453B (zh) | 2021-09-28 | 2021-09-28 | 对象推荐方法和装置 |
CN202111143903.1 | 2021-09-28 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023050732A1 true WO2023050732A1 (zh) | 2023-04-06 |
Family
ID=78991779
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/081122 WO2023050732A1 (zh) | 2021-09-28 | 2022-03-16 | 对象推荐方法和装置 |
Country Status (5)
Country | Link |
---|---|
US (1) | US12079268B2 (zh) |
EP (1) | EP4184349A4 (zh) |
JP (1) | JP2023547299A (zh) |
CN (1) | CN113868453B (zh) |
WO (1) | WO2023050732A1 (zh) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113868453B (zh) * | 2021-09-28 | 2024-02-27 | 北京百度网讯科技有限公司 | 对象推荐方法和装置 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105320703A (zh) * | 2014-08-05 | 2016-02-10 | 北京大学 | 相似车辆检索中的查询扩展方法及装置 |
CN106202362A (zh) * | 2016-07-07 | 2016-12-07 | Tcl集团股份有限公司 | 图像推荐方法和图像推荐装置 |
CN110110110A (zh) * | 2018-02-02 | 2019-08-09 | 杭州海康威视数字技术股份有限公司 | 一种以图搜图方法、装置、电子设备及存储介质 |
CN113868453A (zh) * | 2021-09-28 | 2021-12-31 | 北京百度网讯科技有限公司 | 对象推荐方法和装置 |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2518641A4 (en) * | 2009-12-24 | 2013-07-24 | Nikon Corp | RESEARCH MANAGEMENT SYSTEM, RESEARCH MANAGEMENT METHOD, AND RESEARCH MANAGEMENT PROGRAM |
CN105117399B (zh) * | 2015-07-03 | 2020-01-03 | 深圳码隆科技有限公司 | 一种图像搜索方法和装置 |
US10861129B2 (en) * | 2016-03-08 | 2020-12-08 | Nant Holdings Ip, Llc | Image feature combination for image-based object recognition |
CN110020185A (zh) * | 2017-12-29 | 2019-07-16 | 国民技术股份有限公司 | 智能搜索方法、终端及服务器 |
CN109992685A (zh) * | 2017-12-29 | 2019-07-09 | 杭州海康威视系统技术有限公司 | 一种检索图片的方法及装置 |
JP6947085B2 (ja) * | 2018-03-09 | 2021-10-13 | オムロン株式会社 | 電子機器及びその制御方法 |
US11127074B2 (en) | 2018-03-20 | 2021-09-21 | A9.Com, Inc. | Recommendations based on object detected in an image |
EP3769267B1 (en) * | 2018-03-23 | 2024-04-24 | Motorola Solutions, Inc. | Method and system for interfacing with a user to facilitate an image search for an object-of-interest |
US11182408B2 (en) * | 2019-05-21 | 2021-11-23 | Microsoft Technology Licensing, Llc | Generating and applying an object-level relational index for images |
JP2020013594A (ja) * | 2019-09-03 | 2020-01-23 | 株式会社メルカリ | 情報処理方法、プログラム、及び情報処理装置 |
CN112507153B (zh) * | 2021-01-29 | 2021-05-07 | 上海众旦信息科技有限公司 | 用于图像检索的方法、计算设备和计算机存储介质 |
CN113190701A (zh) * | 2021-05-07 | 2021-07-30 | 北京百度网讯科技有限公司 | 图像检索方法、装置、设备、存储介质以及计算机程序产品 |
-
2021
- 2021-09-28 CN CN202111143903.1A patent/CN113868453B/zh active Active
-
2022
- 2022-03-16 EP EP22822250.1A patent/EP4184349A4/en active Pending
- 2022-03-16 JP JP2022581447A patent/JP2023547299A/ja active Pending
- 2022-03-16 WO PCT/CN2022/081122 patent/WO2023050732A1/zh active Application Filing
- 2022-03-16 US US18/003,116 patent/US12079268B2/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105320703A (zh) * | 2014-08-05 | 2016-02-10 | 北京大学 | 相似车辆检索中的查询扩展方法及装置 |
CN106202362A (zh) * | 2016-07-07 | 2016-12-07 | Tcl集团股份有限公司 | 图像推荐方法和图像推荐装置 |
CN110110110A (zh) * | 2018-02-02 | 2019-08-09 | 杭州海康威视数字技术股份有限公司 | 一种以图搜图方法、装置、电子设备及存储介质 |
CN113868453A (zh) * | 2021-09-28 | 2021-12-31 | 北京百度网讯科技有限公司 | 对象推荐方法和装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP4184349A4 * |
Also Published As
Publication number | Publication date |
---|---|
US12079268B2 (en) | 2024-09-03 |
EP4184349A1 (en) | 2023-05-24 |
CN113868453A (zh) | 2021-12-31 |
CN113868453B (zh) | 2024-02-27 |
EP4184349A4 (en) | 2023-12-13 |
JP2023547299A (ja) | 2023-11-10 |
US20230350940A1 (en) | 2023-11-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20230005284A1 (en) | Method for training image-text matching model, computing device, and storage medium | |
WO2023020005A1 (zh) | 神经网络模型的训练方法、图像检索方法、设备和介质 | |
WO2023019948A1 (zh) | 多模态信息库的检索方法、管理方法、装置、设备和介质 | |
US20230052389A1 (en) | Human-object interaction detection | |
US20230047628A1 (en) | Human-object interaction detection | |
WO2023142406A1 (zh) | 排序方法、排序模型的训练方法、装置、电子设备及介质 | |
CN112836072A (zh) | 信息展示方法及装置、电子设备和介质 | |
WO2023245938A1 (zh) | 对象推荐方法和装置 | |
JP7518927B2 (ja) | ソーティング方法、ソーティングモデルのトレーニング方法、装置、電子機器及び記憶媒体 | |
WO2023050732A1 (zh) | 对象推荐方法和装置 | |
CN115168545A (zh) | 群组搜索方法、装置、电子设备及介质 | |
WO2024027125A1 (zh) | 对象推荐方法、装置、电子设备和存储介质 | |
WO2023240833A1 (zh) | 信息推荐方法及装置、电子设备和介质 | |
US11599594B2 (en) | Method, apparatus, electronic device and storage medium for data processing | |
CN114445190A (zh) | 商品推荐方法和装置 | |
CN113536120A (zh) | 基于用户行为的兴趣点召回和装置 | |
US20230044508A1 (en) | Data labeling processing | |
CN115809364B (zh) | 对象推荐方法和模型训练方法 | |
US11790014B2 (en) | System and method of determining content similarity by comparing semantic entity attributes | |
CN113722523B (zh) | 对象推荐方法和装置 | |
US20230186664A1 (en) | Method for text recognition | |
CN115564992A (zh) | 图像分类方法和图像分类模型的训练方法 | |
CN114581188A (zh) | 用于对象推荐的神经网络模型的训练方法及装置 | |
CN118643118A (zh) | 基于大语言模型的信息检索方法、装置、设备和介质 | |
CN115630228A (zh) | 对象推荐方法和对象推荐模型的训练方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 2022581447 Country of ref document: JP |
|
ENP | Entry into the national phase |
Ref document number: 2022822250 Country of ref document: EP Effective date: 20221221 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |