Object Recommendation Method and Apparatus

Abstract

The present disclosure provides a method and apparatus for recommending an object, which relates to the computer technology field, in particular to the recommendation technology field based on artificial intelligence. As an implementation, the method and apparatus include: obtaining search features of the search object by performing identification on a search image including a search object of a target user; obtaining at least one search feature image from a first database including a plurality of feature images based on the search features; and obtaining a set of target object images from a second database including a plurality of object images based on the at least one search feature image, and recommending the set of target object images to the target user.

Description

Technical Field

[0001] This application claims the priority of Chinese Patent Application No. 202111143903.1, filed on September 28, 2021, the entire content of which is incorporated herein by reference. This disclosure relates to the field of computer technologies, particularly to recommendation technologies based on artificial intelligence. Specifically, it relates to an object recommendation method, apparatus, electronic device, computer-readable storage medium, and computer program product.

Background Art

[0002] Artificial intelligence is a subject that studies how to simulate some human thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.) on a computer. There are both hardware technologies and software technologies. 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 several major directions such as computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, and knowledge graph technology.

[0003] Recommendation technologies based on artificial intelligence have already penetrated into various fields. Here, the object recommendation technology based on artificial intelligence realizes the recommendation of objects to users according to the preferences of users for objects based on the characteristics of the objects.

[0004] The methods described in this part are not necessarily the methods previously assumed or adopted. Unless otherwise specified, none of the methods described in this part should be considered as prior art just because they are included in this part. Similarly, unless otherwise specified, the problems mentioned in this part should not be considered as those approved by the prior art.

Summary of the Invention

[0005] This disclosure provides object recommendation methods, apparatus, electronic devices, computer-readable storage media, and computer program products. According to one aspect of this disclosure, an object recommendation method is provided. This method includes obtaining search features of a search object by identifying the target user with respect to a search image that includes the search object; obtaining at least one search feature image from a first database containing a plurality of feature images based on the search features; and obtaining a target object image set from a second database containing a plurality of object images based on the at least one search feature image and recommending it to the target user.

[0006] Another aspect of this disclosure provides an object recommendation device. The device includes an image recognition unit configured to obtain search features of a search object by performing identification on search images of search objects from a target user; a first search unit configured to obtain at least one search feature image from a first database containing a plurality of feature images based on the search features; and a second search unit configured to obtain a target object image set from a second database containing a plurality of object images based on the at least one search feature image and recommend it to the target user.

[0007] Another aspect of the present disclosure provides an electronic device comprising at least one processor and a memory communicated to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the above method.

[0008] Another aspect of the present disclosure provides a non-temporary computer-readable storage medium in which computer instructions for causing the computer to implement the above method are stored. According to another aspect of this disclosure, a computer program product is provided which includes a computer program that, when executed by a processor, accomplishes the above-described method.

[0009] According to one or more embodiments of this disclosure, by performing identification on a search image containing a search object, search features of the search object (for example, if the search object is a mobile phone, the search features may be mobile phone classification) are obtained, a feature image corresponding to the search object is retrieved from a first database containing multiple feature images, and further matching is performed with an object image database using the feature image to obtain a target object image set and recommend it to the target user. Because the feature images in the first database have high clarity, good shooting angles, and can better reflect the features of the search object, the object images obtained based on the feature images are more accurate, i.e., the target objects recommended to the user are more accurate. Image set It is more accurate.

[0010] It should be understood that the content described in this section is not intended to identify the essential or important features of the embodiments of this disclosure, nor is it intended to limit the scope of protection of this disclosure. Other features of this disclosure will be readily apparent from the following specification. [Brief explanation of the drawing]

[0011] The drawings illustrate embodiments and constitute part of the specification, and are used to illustrate exemplary embodiments of the embodiments together with the textual description of the specification. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to elements that are similar but not necessarily the same. [Figure 1] A schematic diagram of an exemplary system capable of carrying out the various methods described herein, according to the embodiments of this disclosure, is shown. [Figure 2] A flowchart of an object recommendation method according to an embodiment of this disclosure is shown. [Figure 3] The flowchart shows the process of obtaining at least one search feature image from a first database containing multiple feature images based on search features in an object recommendation method according to an embodiment of the present disclosure. [Figure 4] A flowchart illustrating the process of obtaining at least one search feature image from at least one first feature image in an object recommendation method according to an embodiment of this disclosure is shown. [Figure 5] The flowchart shows the process of obtaining a target object image set from a second database containing multiple object images based on at least one search feature image in an object recommendation method according to an embodiment of the present disclosure. [Figure 6] A flowchart illustrating the process of acquiring a target object image set based on one or more first object images in an object recommendation method according to an embodiment of the present disclosure is shown. [Figure 7] A flowchart illustrating the process of obtaining 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 is shown. [Figure 8] A structural block diagram of an object recommendation device according to an embodiment of this disclosure is shown. [Figure 9] An exemplary structural block diagram of an electronic device that can be used to implement embodiments of the present disclosure is shown. [Modes for carrying out the invention]

[0012] Illustrative embodiments of the present disclosure are described below with reference to drawings, and various details of the embodiments of the present disclosure are included for the sake of clarity, but these should be considered as illustrative only. Accordingly, as will be apparent to those skilled in the art, various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, descriptions of known functions and structures are omitted in the following description.

[0013] In this disclosure, unless otherwise specified, the use of terms such as “first,” “second,” etc., to describe various elements is not intended to limit the spatial, timing, or importance relationships of these elements. Such terms are used solely to distinguish one element from another. In some examples, the first element and the second element may refer to the same example of an element, or, in some cases, different examples based on the contextual description.

[0014] The terminology used in describing the various examples in this disclosure is intended solely to illustrate specific examples and is not intended to limit them. Unless otherwise explicitly indicated in the context, elements may be one or more, unless the number of elements is specifically limited. The term "and / or" as used in this disclosure covers any of the listed items and all possible combinations thereof.

[0015] The embodiments of this disclosure will be described in detail below with reference to the drawings. Figure 1 shows a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein can be implemented according to embodiments of the present disclosure. Referring to Figure 1, 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 110 that connect one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105 and 106 can be configured to run one or more applications.

[0016] In embodiments of this disclosure, the server 120 operates to execute one or more object recommendation services or software applications. In some embodiments, the server 120 may also provide other services or software applications, which may include non-virtual and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, for example, to users of client devices 101, 102, 103, 104, 105 and / or 106 in a Software as a Service (SaaS) model.

[0017] In the configuration shown in Figure 1, the server 120 may include one or more assemblies that implement the functions performed by the server 120. These assemblies may include software assemblies, hardware assemblies, or a combination thereof that can run on one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 can interact with the server 120 using one or more client applications to utilize the services provided by these assemblies. It should be understood that various different system configurations are possible and may differ from system 100. Therefore, Figure 1 is an example of a system for implementing the various methods described herein and is not intended to be limiting.

[0018] A user can view the recommended objects using client devices 101, 102, 103, 104, 105, and / or 106. The client device can provide an interface for a user of the client device to interact with the client device. The client device can also output information to the user via this interface. Although only six client devices are illustrated in FIG. 1, as will be understood by those skilled in the art, the present disclosure can support any number of client devices.

[0019] Client devices 101, 102, 103, 104, 105 and / or 106 may include various types of computer devices such as portable handheld devices, general-purpose computers (e.g., personal computers and laptops), workstation computers, wearable devices, smartscreen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors, or other sensing devices. These computer devices may run various types and versions of software applications and operating systems such as MICROSOFT Windows, APPLE iOS, UNIX® operating systems, Linux® or Linux® operating systems (e.g., GOOGLE Chrome OS), or include various mobile operating systems such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, and Android. Portable handheld devices may include mobile phones, intelligent phones, tablets, and personal digital assistants (PDAs). Wearable devices may include head-mounted displays (e.g., smart glasses) and other devices. Game systems may include various handheld game devices, internet-enabled game devices, and the like. The client device can run various applications, such as Internet-related applications, communication applications (e.g., email applications), and short message service (SMS) applications, and can use various communication protocols.

[0020] Network 110 may be any type of network known to those skilled in the art, and it can use any one of a plurality of available protocols (including but not limited to TCP / IP, SNA, IPX, etc.) to support data communication. By way of example, 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, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth (registered trademark), WIFI), and / or any combination of these and other networks.

[0021] Server 120 may include one or more general-purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX (registered trademark) servers, midrange servers), blade servers, mainframe computers, server clusters, or other suitable configurations and / or combinations. Server 120 may include one or more virtual machines that execute a virtual operating system, or other computing architectures related to virtualization (e.g., one or more flexible pools of virtualized logical storage devices to maintain the virtual storage of the server). In various embodiments, server 120 can execute one or more services or software applications that provide the functions described below.

[0022] The computing unit in server 120 can execute one or more operating systems including any of the above-described operating systems and any commercial server operating systems. Server 120 can also execute any one of various additional server applications and / or middleware applications, such as an HTTP server, an FTP server, a CGI server, a JAVA (registered trademark) server, a database server, etc.

[0023] In some embodiments, the server 120 may include one or more applications for analyzing and integrating data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. The server 120 may also include one or more applications for displaying data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0024] In some embodiments, server 120 may be a server in a distributed system or a server incorporating blockchain. Server 120 may be a cloud server, or an intelligent cloud computing server or intelligent cloud host equipped with artificial intelligence technology. A cloud server is a host product in a cloud computing service system and solves the problems of high management difficulty and low business scalability that exist in conventional physical hosts and virtual private server (VPS) services.

[0025] System 100 may include one or more databases 130. In some embodiments, these databases can be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and object files. The databases 130 can be located in various locations. For example, the database used by server 120 may be located locally with server 120, or it may be located away from server 120 and communicate with server 120 via a network or a dedicated connection. The databases 130 may be of various types. In some embodiments, the database used by server 120 may be a relational database or other type of database. One or more of these databases can store, update, and retrieve data from the databases in response to commands.

[0026] In some embodiments, one or more of the databases 130 may be used by an application to store application data. The database used by the application may be of various types, such as a key-value repository, an object repository, or a general-purpose repository supported by the file system.

[0027] The system 100 in Figure 1 can be configured and operated in various ways so that the various methods and apparatus described in this disclosure can be applied. Referring to Figure 2, the object recommendation method 200 according to some embodiments of this disclosure is: Step S210 involves obtaining the search characteristics of the search object by identifying the search image containing the search object for the target user, Step S220: Based on the aforementioned search features, obtain at least one search feature image from a first database containing multiple feature images. The method includes step S230, which involves obtaining a target object image set from a second database containing multiple object images based on the aforementioned at least one search feature image, and recommending it to the target user.

[0028] According to one or more embodiments of this disclosure, by performing identification on a search image containing a search object, search features of the search object (for example, if the search object is a mobile phone, the search features may be mobile phone classification) are obtained, a feature image corresponding to the search object is retrieved from a first database containing multiple feature images, and further matching is performed with an object image database using the feature image to obtain a target object image set and recommend it to the target user. Because the feature images in the first database have high clarity, good shooting angles, and can better reflect the features of the search object, the object images obtained based on the feature images are more accurate, that is, the target objects recommended to the user are more accurate.

[0029] In related technologies, in the process of recommending objects to a user based on the target user's search image, target object images are directly retrieved from an object image database based on the target user's search image and recommended to the target user. The target object images recommended to the target user are one or more images similar to the search image, and it is only possible to recommend objects that match the search object if the user image is accurate. If the user's search image is unclear, the recommended objects are often inaccurate and fail to meet the user's needs, and it is also impossible to recommend a wider range of objects related to the search object based on the search image.

[0030] For example, in recommending items, the target user's current search image might be a photograph of a mobile phone screen taken under low-light conditions, and the recommended object image could be a mobile phone containing various mobile phone screens. In the embodiments of this disclosure, by identifying which mobile phone brand the search object in the search image is, a feature image corresponding to the mobile phone brand can be obtained from a first database. This feature image is clear and reflects the real situation of the mobile phone brand, thereby making the object image obtained from a second database based on the feature image more accurate, and further making the mobile phone recommended to the user more accurate.

[0031] According to embodiments of the present disclosure, the first database acts as a bridge between object recommendation and search, connecting the search objects with the object image database corresponding to object recommendation, thereby enriching and increasing the accuracy of target object images in the target object image set for recommendation to target users obtained from the object image database.

[0032] In some embodiments, the first database is a network image database corresponding to web search, and the second database is an object image database corresponding to object search, where the number of object images is smaller than the number of feature images.

[0033] The first database is configured as a network image database, and the second database is configured as an object image database. Since the network image database supports web search (e.g., a search engine's web database) and the object image database supports object search (e.g., a product database on an e-commerce platform), 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. Because the first database has a richer collection of images, the resulting search feature images are richer and more accurate. This allows for richer and more accurate object images based on the search feature images.

[0034] In some embodiments, the method according to this disclosure can be used for product recommendations, article recommendations, similar product recommendations, and the like, but is not limited thereto. In some embodiments, the object may be an article, a plant, an animal, etc., and is not limited thereto.

[0035] In some embodiments, the search image may be an image taken and uploaded by the user using their mobile phone, or it may be any image uploaded by the user from a client.

[0036] In some embodiments, in step S210, the search features of the search object are obtained by employing a trained neural network to perform classification on the search image of the target user. Here, the trained neural network is obtained by employing and training multiple classified images.

[0037] In some embodiments, each of the multiple feature images corresponds to one of the multiple classification features, and the search feature includes a first classification feature corresponding to the search object among the multiple classification features. As shown in Figure 3, based on the search feature, at least one search feature image is obtained from a first database containing multiple feature images. Step S310: Obtain at least one first feature image from among the plurality of feature images that corresponds to the first classification feature, The process includes step S320, which involves obtaining at least one search feature image from at least one first feature image.

[0038] The amount of data to be processed is reduced by classifying multiple feature images in the first database, obtaining at least one first feature image corresponding to the classification features of the search object based on those classification features, and then obtaining a search feature image from at least one first feature image.

[0039] In some embodiments, the classification features include multiple classifications corresponding to, for example, mobile phones, clothing, food, etc. In some embodiments, the classification features further include multiple levels of subclassifications within the mobile phone classification corresponding to mobile phones, for example, multiple first subclassifications corresponding to mobile phone brands, and second subclassifications corresponding to mobile phone models within each of the multiple first subclassifications.

[0040] In some embodiments, in step S310, at least one feature image obtained from the first image database may be the feature image with the highest clarity corresponding to the first classification, thereby making the object image obtained based on the feature image more accurate. For example, if the search feature of the search object is the type of search object, a large-screen mobile phone, the feature image of the search object obtained in step S310 may be the clearest image among the obtained large-screen mobile phone images, and since the image is clearer than the search image, the object image obtained based on it is more accurate.

[0041] In one embodiment, in step S310, the at least one feature image obtained from the first image database may be multiple images corresponding to the first classification, thereby enriching the object image obtained based on the multiple feature images. For example, if the search feature of the search object is the brand of the search object, brand A, the feature image of the search object obtained in step S310 may be multiple images obtained from the official website of brand A. Images on the official website of brand A often have better shooting angles and more images, so the object image obtained based on them is more accurate and a richer collection of brand A mobile phones can be obtained.

[0042] In some embodiments, as shown in Figure 4, obtaining the at least one search feature image from the at least one first feature image is possible. Step S410: Obtain a first similarity between each of the first feature images from the at least one first feature image and the search image. The process includes step S420 of obtaining at least one search feature image, wherein the first similarity corresponding to each of the at least one search feature images is greater than a first threshold.

[0043] From at least one first feature image corresponding to a first classification corresponding to a search object, a feature image whose similarity to the search image is greater than a first threshold is obtained and used as the search feature image. This search feature image not only matches the classification corresponding to the search object, but also resembles the search image, thereby making the object image obtained based on the search feature image more accurate.

[0044] In some embodiments, as shown in Figure 5, a target object image set is obtained from a second database containing multiple object images based on at least one search feature image. Step S510: Obtain a second similarity between each of the search feature images from the at least one search feature image and each of the object images from the plurality of object images. Step S520 involves obtaining one or more first object images from the aforementioned plurality of object images, and determining for each of the one or more first object images that the maximum value of at least one second similarity corresponding to the first object image is greater than the second threshold. The process includes step S530, which involves obtaining the target object image set based on one or more first object images.

[0045] One or more second object images are obtained from multiple object images, and a target object image set is obtained from the one or more first object images. The second similarity of each of the one or more first object images corresponding to the search feature image is high (the maximum value of at least one second similarity corresponding to the first object image is greater than the second threshold), and the degree of matching with the search image is higher, so the target object image set obtained based on this is more accurate and better suits the user's needs.

[0046] In some embodiments, among multiple object images, the object image with the highest average value of at least one corresponding second similarity may be designated as the first object image, and a target object image set may be obtained and recommended to the target user based on this.

[0047] In some embodiments, as shown in Figure 6, the target object image set is obtained based on the one or more first object images. Step S610 involves obtaining image information corresponding to each of the at least one search feature images, wherein the image information includes at least one of the image feature information of the corresponding search feature image and descriptive information related to the corresponding search feature image. The at least one of the above search The process includes step S620, which involves obtaining the target object image set based on image information corresponding to the feature image and the one or more first object images.

[0048] Based on the image feature information of the search feature image and the descriptive information associated with the search feature image, a target object image is obtained. Since the image feature information and descriptive information of the search feature image include more information related to the search object, such as brand markers (logo) and color, the object in the target object image obtained based on this image information is better suited to the user's needs.

[0049] In some embodiments, the first database is a network image database, and obtaining image information corresponding to each of the at least one search feature images includes obtaining, for each of the at least one search feature images, the title of the web page corresponding to the search feature image, keywords on the web page, or keywords corresponding to user requests.

[0050] In some embodiments, obtaining image information corresponding to each search feature image among at least one search feature image includes obtaining image features in the search feature image, such as the pixel values ​​of the search object, for each search feature image among at least one search feature image.

[0051] In some embodiments, each of the object images among the plurality of object images corresponds to one of the plurality of objects, each of the plurality of objects corresponds to one or more of the object labels among the plurality of object labels, and here, as shown in Figure 7, at least one search Step S620, which acquires the target object image set based on the image information corresponding to the feature image and the one or more first object images, Step S710: Based on image information corresponding to the at least one search feature image, obtain at least one object label from the plurality of object labels. Step S720 involves obtaining at least one second object image from the plurality of object images, and determining that each of the at least one second object images corresponds to an object corresponding to the at least one object label. The process includes step S730, which involves obtaining the target object image set based on the at least one second object image and the one or more first object images.

[0052] The object label of the corresponding object is obtained from the image information of the search feature image, and the description of the object by the object label is more accurate, for example, the object label includes brand, model, size, etc., and the target object obtained based on the object label is Image set It is more accurate.

[0053] In some embodiments, the target object image set includes one or more third object images from the one or more first object images, wherein each of the one or more third object images corresponds to an object corresponding to at least one of the at least one second object images.

[0054] The target object image is made more accurate by obtaining a third object image similar to the object corresponding to the second object image from one or more first object images that are similar to the search feature image, and using this as the target object image.

[0055] In some embodiments, obtaining the target object image set based on the at least one second object image and the one or more first object images further includes obtaining user preference information and obtaining the target image set from the at least one second object image and the one or more first object images based on the user preference.

[0056] User preferences include the user's preference for search accuracy and search coverage. For example, if the user preference is for search accuracy, the target object image set includes the third object image. If the user preference is for search coverage, the target object image set includes at least one second object image and one or more first object images.

[0057] In the proposed technology described herein, all processing of relevant user personal information, including collection, storage, use, processing, transmission, provision, and disclosure, complies with the provisions of relevant laws and regulations and does not violate public order and morals. Another aspect of the present disclosure further provides an object recommendation device. Referring to Figure 8, the device 800 includes an image recognition unit 810 configured to obtain search features of a search object by performing identification on a search image of the search object from a target user; a first search unit 820 configured to obtain at least one search feature image from a first database containing a plurality of feature images based on the search features; and a second search unit 830 configured to obtain a target object image set from a second database containing a plurality of object images based on the at least one search feature image and recommend it to the target user.

[0058] In some embodiments, each of the plurality of feature images corresponds to one of the plurality of classification features, the search feature includes a first classification feature among the plurality of classification features that corresponds to the search object, and the first search unit includes a first search subunit configured to acquire at least one first feature image from the plurality of feature images that corresponds to the first classification feature, and a first acquisition unit configured to acquire at least one search feature image from the at least one first feature image.

[0059] In some embodiments, the first acquisition unit includes a first similarity acquisition unit configured to acquire a first similarity between each of the at least one first feature images and the search image, and a first acquisition subunit configured to acquire the at least one search feature image, wherein the first similarity corresponding to each of the at least one search feature image is greater than a first threshold.

[0060] In some embodiments, the second search unit includes a second similarity acquisition unit configured to acquire a second similarity between each of the at least one search feature images and each of the plurality of object images; a second acquisition unit configured to acquire one or more first object images from the plurality of object images, wherein for each of the one or more first object images, the maximum value of at least one second similarity corresponding to the first object image is greater than a second threshold; and a third acquisition unit configured to acquire the target object image set based on the one or more first object images.

[0061] In some embodiments, the third acquisition unit is a third acquisition subunit configured to acquire image information corresponding to each of the at least one search feature images, wherein the image information includes at least one of the image feature information of the corresponding search feature image and descriptive information related to the corresponding search feature image, and the at least one search It includes a fourth acquisition unit configured to acquire the target object image set based on image information corresponding to a feature image and the one or more first object images.

[0062] In some embodiments, each of the plurality of object images corresponds to one of the plurality of objects, each of the plurality of objects corresponds to one or more of the plurality of object labels, and the fourth acquisition unit includes a fifth acquisition unit configured to acquire at least one of the plurality of object labels based on image information corresponding to the at least one search feature image, a sixth acquisition unit configured to acquire at least one second object image from the plurality of object images, wherein each of the at least one second object image corresponds to the at least one object label, and a target acquisition unit configured to acquire the target object image set based on the at least one second object image and the one or more first object images.

[0063] In some embodiments, the target object image set includes one or more third object images from the one or more first object images, wherein each of the one or more third object images corresponds to an object corresponding to at least one of the at least one second object images.

[0064] In some embodiments, the first database is a network image database corresponding to web search, and the second database is an object image database corresponding to object search, where the number of object images is smaller than the number of feature images.

[0065] Another aspect of the present disclosure further provides an electronic device, which includes at least one processor and a memory communicated to the at least one processor, wherein the memory stores a computer program, and when the computer program is executed by the at least one processor, the above method is realized.

[0066] Another aspect of this disclosure further provides a non-temporary computer-readable storage medium on which a computer program is stored, thereby achieving the above method when the computer program is executed by a processor.

[0067] Another aspect of this disclosure further provides a computer program product including a computer program, wherein the above method is achieved when the computer program is executed by a processor.

[0068] Embodiments of this disclosure further provide electronic devices, readable storage media, and computer program products. Referring to Figure 9, a structural block diagram of an electronic device 900, which can be used as a server or client of the Disclosure, is described here, as an example of a hardware device applicable to various aspects of the Disclosure. The electronic device represents various forms of digital electronic computer equipment, such as laptop computers, desktop computers, stages, personal digital assistants, servers, blade servers, large computers, and other suitable computers. The electronic device may further represent various forms of mobile devices, such as personal digital processing, mobile phones, smartphones, wearable devices, and other similar computing devices. The components, their connections, and their functions shown herein are illustrative and do not limit the implementation of the Disclosure as described and / or claimed herein.

[0069] As shown in Figure 9, the device 900 includes a computing unit 901, which can perform various appropriate operations and processes by computer programs stored in read-only memory (ROM) 902 or by computer programs loaded from storage unit 908 into random access memory (RAM) 903. The RAM 903 can also store various programs and data necessary for the operation of the device 900. The computing unit 901, ROM 902, and RAM 903 are connected to each other by a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0070] Multiple components in the device 900 are connected to the I / O interface 905 and include an input unit 906, an output unit 907, a storage unit 908, and a communication unit 909. The input unit 906 may be any type of device capable of inputting information into the device 900, and may receive input numeric or character information and generate key signal inputs related to user settings and / or function control of the calculator, and may include, but is not limited to, a mouse, keyboard, touchscreen, trackboard, trackball, operating lever, 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, speaker, object / audio output terminal, vibrator, and / or printer. The storage unit 908 may include, but is not limited to, a magnetic disk or an optical disk. The communication unit 909 enables the device 900 to exchange information / data with other devices via computer networks, such as the Internet, and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, 1302.11 devices, WiFi devices, WiMAX devices, cellular communication devices, and / or similar devices.

[0071] The computing unit 901 may be a variety of general-purpose and / or dedicated processing assemblies having processing and computing capabilities. Some examples of the computing unit 901 may include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units for executing machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs each of the methods and processes described above, for example, method 200. For example, in some embodiments, method 200 may be implemented as a computer software program and tangibly contained in a machine-readable medium, for example, in a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed in the device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of method 200 described above can be performed. Alternatively, in another embodiment, the computing unit 901 may be configured to perform method 200 in any other suitable manner (for example, by firmware).

[0072] Various embodiments of the systems and technologies described 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-a-chip (SOCs), load-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may be implemented in one or more computer programs, which may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, which may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to this storage system, at least one input device, and at least one output device.

[0073] Program code for implementing the methods of this 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 device, so that when the program code is executed by the processor or controller, it performs the functions / operations specified in the flowchart and / or block diagrams. The program code may be executed entirely by machine, partially by machine, partially by machine and partially by remote machine as a standalone software package, or entirely by remote machine or server.

[0074] In the context of this disclosure, machine-readable media may be tangible media that contain or store programs used in or used in conjunction with instruction execution systems, apparatus, or devices. Machine-readable media may be machine-readable signal media or machine-readable storage media. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any appropriate combination thereof. More specific examples of machine-readable storage media include one or more leaded electrical connections, portable computer disks, hard disks, random-access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any appropriate combination thereof.

[0075] To provide user interaction, the computer may implement the systems and technologies described herein, which include a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitoring monitor), and a keyboard and pointing device (e.g., a mouse or trackball), through which the user may input to the computer. Other types of devices may further provide user interaction. For example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback), and input from the user may be received in any form (including sound input, voice input, or tactile input).

[0076] The systems and technologies described herein may be implemented in computing systems including backstage components (e.g., as data servers), computing systems including middleware components (e.g., application servers), computing systems including front-end components (e.g., user computers with graphical user interfaces or web browsers, through which users can interact with embodiments of these systems and technologies), or computing systems consisting of any combination of these backstage components, middleware components, or front-end components. The components of the system may be interconnected by digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local networks (LANs), wide area networks (WANs), and the internet.

[0077] A computer system may include a client and a server. The client and server are generally geographically distant from each other and typically interact via a communication network. The client-server relationship is created by running computer programs on corresponding computers that have a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server combined with a blockchain.

[0078] It should be understood that the steps may be reordered, added, or deleted using the various forms of flows described above. For example, each step described in this disclosure may be performed in parallel, sequentially, or in a different order, as long as the technical proposal disclosed herein achieves the desired result.

[0079] While embodiments or examples of this disclosure have been described with reference to the drawings, it should be understood that the above-described methods, systems, and apparatus are merely illustrative embodiments or examples, and the scope of the invention is not limited by these embodiments or examples, but is limited only by the authorized claims and their equivalents. Various elements of the embodiments or examples may be omitted or replaced by their equivalent elements. Furthermore, each step may be performed in an order different from the order described herein. In addition, various elements of the embodiments or examples may be combined in various ways. Importantly, as the technology advances, many of the elements described herein can be replaced by equivalent elements appearing later in this disclosure.

Claims

1. Object recommendation method, The method involves using a trained neural network to identify a search image containing the search object for the target user, thereby obtaining the search features of the search object, wherein the trained neural network was trained using multiple classified images, and the search features of the search object are the type of the search object. Based on the aforementioned search features, at least one search feature image is obtained from a first database containing multiple feature images. This includes obtaining a target object image set from a second database containing multiple object images based on the at least one search feature image and recommending it to the target user. Each of the aforementioned feature images corresponds to one of the aforementioned classification features, and the search feature includes a first classification feature corresponding to the search object among the aforementioned classification features, and hereby, based on the search feature, obtaining at least one search feature image from a first database containing the aforementioned feature images is: Obtaining at least one first feature image from among the plurality of feature images that corresponds to the first classification feature, This includes obtaining at least one search feature image from at least one first feature image, Obtaining the at least one search feature image from the at least one first feature image is, Obtaining a first similarity between each of the first feature images among the at least one first feature image and the search image, An object recommendation method comprising obtaining at least one search feature image, wherein a first similarity score corresponding to each of the at least one search feature image is greater than a first threshold.

2. Obtaining a target object image set from a second database containing multiple object images based on the aforementioned at least one search feature image is: Obtaining a second similarity between each of the search feature images among the at least one search feature image and each of the object images among the plurality of object images, Obtain one or more first object images from the aforementioned plurality of object images, and for each of the one or more first object images, the maximum value of at least one second similarity score corresponding to the first object image is greater than the second threshold. The method according to claim 1, further comprising obtaining the target object image set based on the one or more first object images.

3. Obtaining the target object image set based on the one or more first object images described above is: The image information corresponding to each of the at least one search feature images is obtained, and the image information includes at least one of the image feature information of the corresponding search feature image and descriptive information related to the corresponding search feature image. The method according to claim 2, comprising obtaining the target object image set based on image information corresponding to at least one search feature image and the one or more first object images.

4. Each of the object images among the plurality of object images corresponds to one of the plurality of objects, each of the plurality of objects corresponds to one or more object labels among the plurality of object labels, and hereby, obtaining the target object image set based on one or more image information corresponding to the at least one search feature image and the one or more first object images is, Based on the image information corresponding to the at least one search feature image, obtain at least one object label from the plurality of object labels, Obtain at least one second object image from the plurality of object images, and ensure that each of the at least one second object images corresponds to an object corresponding to at least one object label. The method according to claim 3, further comprising obtaining the target object image set based on the at least one second object image and the one or more first object images.

5. The method according to claim 4, wherein the target object image set includes one or more third object images from the one or more first object images, wherein for each third object image from the one or more third object images, the third object image corresponds to an object corresponding to at least one second object image from the at least one second object image.

6. Object recommendation device, An image recognition unit configured to obtain search features of a search object by using a trained neural network to identify a search image containing a search object for a target user, wherein the trained neural network is trained using multiple classified images, and the search features of the search object are the type of the search object. A first search unit is configured to obtain at least one search feature image from a first database containing multiple feature images based on the aforementioned search features, A second search unit configured to retrieve a target object image set from a second database containing multiple object images based on the at least one search feature image and recommend it to the target user, Each of the aforementioned feature images corresponds to one of the aforementioned classification features, and the search feature includes a first classification feature corresponding to the search object among the aforementioned classification features, and here the first search unit is A first search subunit is configured to acquire at least one first feature image from among the plurality of feature images that corresponds to the first classification feature, The system includes a first acquisition unit configured to acquire at least one search feature image from at least one first feature image, The first acquisition unit is, A first similarity acquisition unit configured to acquire a first similarity between each of the first feature images among the at least one first feature image and the search image, An object recommendation device comprising a first acquisition subunit configured to acquire at least one search feature image, wherein a first similarity corresponding to each of the at least one search feature image is greater than a first threshold.

7. The second search unit is, A second similarity acquisition unit configured to acquire a second similarity between each of the search feature images among the at least one search feature image and each of the object images among the plurality of object images, A second acquisition unit configured to acquire one or more first object images from the aforementioned plurality of object images, wherein for each of the one or more first object images, the maximum value of at least one second similarity corresponding to the first object image is greater than a second threshold, The apparatus according to claim 6, further comprising a third acquisition unit configured to acquire the target object image set based on the one or more first object images.

8. The third acquisition unit is A third acquisition subunit configured to acquire image information corresponding to each of the at least one search feature images, wherein the image information includes at least one of the image feature information of the corresponding search feature image and descriptive information related to the corresponding search feature image. The apparatus according to claim 7, further comprising a fourth acquisition unit configured to acquire the target object image set based on image information corresponding to at least one search feature image and the one or more first object images.

9. Each of the object images among the plurality of object images corresponds to one of the plurality of objects, and each of the plurality of objects corresponds to one or more object labels among the plurality of object labels, and here the fourth acquisition unit is A fifth acquisition unit configured to acquire at least one object label from among the plurality of object labels based on image information corresponding to at least one search feature image, A sixth acquisition unit configured to acquire at least one second object image from the plurality of object images, wherein each of the at least one second object images corresponds to an object corresponding to the at least one object label of the sixth acquisition unit, The apparatus according to claim 8, further comprising a target acquisition unit configured to acquire the target object image set based on the at least one second object image and the one or more first object images.

10. The apparatus according to claim 9, wherein the target object image set includes one or more third object images from the one or more first object images, wherein for each third object image from the one or more third object images, the third object image corresponds to an object corresponding to at least one second object image from the at least one second object image.

11. It is an electronic device, At least one processor, The memory is communicated to at least one of the aforementioned processors, and here, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to cause the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-temporary computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the method described in any one of claims 1 to 5.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 5.

Images