WO2017197826A1 - 图像特征关系的匹配方法、装置和系统 - Google Patents
图像特征关系的匹配方法、装置和系统 Download PDFInfo
- Publication number
- WO2017197826A1 WO2017197826A1 PCT/CN2016/101059 CN2016101059W WO2017197826A1 WO 2017197826 A1 WO2017197826 A1 WO 2017197826A1 CN 2016101059 W CN2016101059 W CN 2016101059W WO 2017197826 A1 WO2017197826 A1 WO 2017197826A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- features
- server
- images
- image features
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/40—Business processes related to social networking or social networking services
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Definitions
- the present invention belongs to the field of Internet technologies, and in particular, to a method, device and system for matching relationship of image features.
- the user usually matches the potential friends according to the personal information input by the user, the friend information and the background preset logic, and recommends the potential friends to the user.
- this recommendation method only recommends the user according to the text information matching rule preset by the background server, so the recommendation success rate of the dating object is very low, and the user pays little attention to the dating objects automatically pushed by the background server.
- the embodiments of the present invention provide a method, a device, and a system for matching relationship of image features, which are used to solve the problem that the success rate of automatically recommending potential friends in the prior art is low. Problems.
- Embodiments of the present invention also provide an electronic device, a non-transitory computer storage medium, and a computer program product.
- the present invention discloses a relationship matching method for image features, comprising: acquiring a sample image and identifying an image feature of the sample image; performing statistical analysis on the relationship between the image features of the sample image to obtain an image feature An association rule between; identifying an image feature of the first image when receiving the first image uploaded by the client; and pushing one or more associated with the image feature of the first image according to the association rule
- the second image is displayed to the client.
- the present invention also discloses a relationship matching method for image features, comprising: uploading a first image to a server, so that the server identifies an image feature of the first image; and receiving the server according to an association rule Pushing one or more second images associated with the image features of the first image, the association rules being obtained by statistical analysis of the association relationship between the image features of the sample images by the server; The one or more second images are displayed.
- the present invention also discloses a relationship matching device for image features, comprising: a first identification module for acquiring a sample image and identifying an image feature of the sample image; and an analysis module for the image of the sample image
- the association relationship between the features is statistically analyzed to obtain an association rule between the image features
- the second identification module is configured to identify the image feature of the first image when receiving the first image uploaded by the client
- a pushing module configured to push, according to the association rule, one or more second images associated with image features of the first image to the client for presentation.
- the present invention also discloses a relationship matching device for image features, comprising: an uploading module, configured to upload a first image to a server, so that the server identifies an image feature of the first image; a receiving module, configured to receive one or more second images that are associated with image features of the first image that are pushed by the server according to an association rule, where the association rule is an image feature of the sample image by the server
- the correlation relationship is obtained by performing statistical analysis;
- the display module is configured to display the one or more second images.
- the present invention also discloses a relationship matching system for image features, including a terminal device and a server; the server acquires a sample image and identifies an image feature of the sample image, and associates the image features of the sample image Performing statistical analysis on the relationship to obtain an association rule between the image features; the terminal device uploads the first image to the server, the server identifies the image feature of the first image, and pushes and compares the image according to the association rule One or more second images associated with image features of an image to the terminal device, the terminal device presenting the one or more second images.
- the embodiment of the present invention further provides a non-transitory computer storage medium storing computer executable instructions for performing a relationship matching method of any of the above image features of the present application.
- An embodiment of the present invention provides an electronic device, including: at least one processor;
- the at least one processor communicatively coupled to the memory; wherein
- the memory stores instructions executable by the one processor, the instructions being executed by the at least one processor to enable the at least one processor to:
- An embodiment of the present invention provides an electronic device, including: at least one processor;
- the at least one processor communicatively coupled to the memory; wherein
- the memory stores instructions executable by the one processor, the instructions being executed by the at least one processor to enable the at least one processor to:
- association rule Receiving, according to an association rule, the image feature of the first image that is pushed by the server And one or more second images, wherein the association rule is obtained by statistical analysis of an association relationship between image features of the sample image by the server;
- the one or more second images are displayed.
- Embodiments of the present invention also provide a computer program product, the computer program product comprising a computing program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer When the computer is caused to perform the relationship matching method of any of the above image features of the present application.
- the method, device, and system for matching relationship of image features provided by the embodiments of the present invention analyze the association rules between image features, and the images matched according to the association rules are closer to the realistic friend needs of the user. Thereby improving the success rate of pushing friends.
- FIG. 1 is a schematic structural diagram of a relationship matching system for image features according to an embodiment of the present invention
- FIG. 2 is a flowchart of a method for matching relationship of image features according to an embodiment of the present invention
- FIG. 3 is a flowchart of a method for matching relationship of image features according to an embodiment of the present invention.
- FIG. 4 is a block diagram of a relationship matching device for image features according to an embodiment of the present invention.
- FIG. 5 is a block diagram of a relationship matching device for image features according to an embodiment of the present invention.
- FIG. 6 is a block diagram of an electronic device according to an embodiment of the present invention.
- FIG. 7 is a block diagram of an electronic device according to an embodiment of the present invention.
- the embodiment of the invention identifies the image features of the sample image, determines the association relationship between the image features according to the association relationship between the sample images, and performs statistical analysis on the association relationship between the image features to obtain an association rule between the image features, and obtains the obtained rules.
- the more the association relationship between the image features the more accurate the association rule is.
- a plurality of second images are pushed to the client for display, and the pushing of the images is performed based on the internal rules obtained by analyzing the association relationship of the image features, so that the user has a certain social representation and is more consistent with
- the realistic friend demand makes the pushed image more likely to attract the attention of the user, thereby improving the recommendability of the dating object automatically pushed by the dating platform and the efficiency of the user searching for the dating object through the dating platform.
- FIG. 1 is a schematic structural diagram of a relationship matching system for image features according to an embodiment of the present invention, which is suitable for a terminal device 10 server 11.
- the terminal device 10 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.
- the server 11 is a back-end server of a website or an application that provides a network dating service for network users.
- the user accesses a website or an application that provides a network dating service through the terminal device 10, and performs data interaction with the background server 11 of the website or application.
- the user registers the user account on the website or the application, and the login service operation is completed locally in the terminal device 10 through the user account to use the network dating service.
- the server 11 can acquire sample images in various ways.
- the sample image includes an image of the user's own image and one or more ideal target friends of the user.
- the operator of the website or application can submit the image of the person and the image of the ideal target friend by the volunteer by recruiting the volunteers offline, and the server 11 images the person, the image of the ideal target, and the image of the person.
- the association relationship with the image of the ideal target friend object is saved.
- sample images can be collected by online testing. For a user account that has registered and uploaded his own image, after the user account logs in to the website or application, pushes a plurality of images to him and selects an image from which he can be an ideal target friend. After receiving the selected image of the user account, the server 11 saves the image uploaded by the user account, the selected image, and the association relationship between the uploaded image and the selected image.
- the image feature of the image of the personal image and the ideal target friend object can be realized by the existing image feature and the face recognition technology.
- the recognized image feature may be an overall feature of the image, such as dignified, pure, mature, small meat, etc., which can reflect the overall impression of the person in the image; or may be a local feature of the image, for example, short hair, single eyelid
- the awl face and the like which can reflect the local features of the characters in the image; the above-mentioned overall features and local features can also be included.
- the relationship between the image feature of the person image and the image feature of the ideal target friend object is established according to the relationship between the image of the person and the image of the ideal target friend object.
- the association rule is the rule that best explains the relationship between image features, and can be obtained by a data depth mining algorithm, such as Apriori algorithm, Eclat algorithm, and the like.
- Apriori algorithm e.g., Apriori algorithm
- Eclat algorithm e.g., Eclat algorithm
- the server 11 After the new user of the network dating platform uploads the personal image to the server 11 through the terminal device 10, the server 11 first performs image feature recognition on the uploaded personal image. The association rules obtained by the analysis are then matched to the image features associated with the image features of the image of the person. The images of the other users having the associated image features are retrieved, and the retrieved images of other users are finally pushed to the terminal device 10. In the web page or application opened by the terminal device 10, the image pushed by the server 11 is displayed.
- the pushed image is obtained according to the association rules of the data depth mining, and is closer to the user's realistic friend demand, and is more interesting to the user, thereby improving the success rate of pushing the dating object.
- the association rule between the image features may be an association rule between the overall features or an association rule between the local features; or may be an association rule between the combination of the overall feature and the local feature.
- the overall feature and the local feature of the image are identified, and the overall feature and the local feature are used as a combination of image features to establish an association between the user image and the image feature combination of the ideal target friend object.
- the relationship is then statistically analyzed for the association between various combinations of image features to obtain association rules between various combinations of image features.
- the pushed image can be matched according to the association rules between various combinations of image features. In this way, the analysis of the image features and the resulting association rules will be more refined, so that the pushed image can be more interested in the user, further improving the recommendation success rate of the dating object.
- the recommendation service for the dating object provided by the user of the dating platform is that the user has uploaded the image of the person. Users who have not uploaded their own images cannot use the above method to recommend friends.
- the user who has uploaded the image of the user may be further divided, that is, among the users who have uploaded the image of the user, only the permission level of the user account of the user reaches the preset threshold, and the recommendation of the friend of the friend is provided. service.
- the server 11 determines whether the weight level of the user account is greater than or equal to a preset threshold.
- the weight of the user account When the weight of the user account is greater than or equal to the preset threshold, one or more images associated with the image features of the image of the user are pushed to the terminal device 10 according to the association rule; when the weight level of the user account is less than When the threshold is preset, a prompt message for raising the privilege level is sent to the terminal device 10. Alternatively, when the privilege level of the user account is greater than or equal to the preset threshold but the user account does not upload the user image, the prompt message for uploading the image of the person is sent to the terminal device 10.
- the operator of the website or application will spend a lot of manpower and financial resources to collect the sample image and find the association rules between the image features of the sample image, so the recommendation service of the above-mentioned dating object is provided to the user whose permission level reaches the preset threshold, Help reduce the operating costs of dating sites or apps.
- the embodiment of the present invention provides a relationship matching method for image features on the server 11 side. As shown in FIG. 2, the method includes the following steps.
- the first image is a user's own image
- the second image is an image that is matched according to an association rule and an image feature of the first image.
- the second image matched according to the association rule is closer to the user's realistic friend demand, thereby improving the success rate of pushing the friend object.
- the relationship matching method of the image features further includes the following steps.
- the receiving client returns an image selected from the plurality of third images, and establishes an association relationship between the image features of the first image and the image features of the selected image.
- the third image is a selectable image that is pushed for the user who has uploaded the image of the person.
- the online dating platform Through the online dating platform, more sample images are collected to improve the representation of association rules and make them more suitable for the user's friends.
- step S23 further comprises the following steps.
- step S231. Determine whether the permission level of the client is greater than or equal to a preset threshold. When the privilege level of the client is greater than or equal to the preset threshold, step S232 is performed; when the privilege level of the client is less than the preset threshold, step S233 is performed.
- Providing the image matching service of the dating object to the user with higher priority level helps to reduce the operating cost of the dating platform.
- step S21 further comprises the following steps.
- the combination of image features includes global features and local features, which make the image features more detailed, and thus the correlation rules obtained by the analysis are more refined, which becomes the association rule between the combination of image features, so that the second image pushed can be more capable. Arouse the interest of users.
- An embodiment of the present invention provides a method for matching relationship of image features on the terminal device 10 side. As shown in FIG. 3, the method includes the following steps.
- the receiving server sends one or more second images that are associated with the image features of the first image according to the association rule.
- the association rule is obtained by statistical analysis of the relationship between the image features of the sample images by the server. ;
- the user After uploading the image of the person, the user will receive the image of other users pushed according to the association rule of the image feature, and the pushed image will be close to the reality of the friend's demand, and has higher attraction to the user.
- the relationship matching method of the image features further includes the following steps.
- the user who has uploaded the image of the person can also participate in the online collection of the sample image, select the image of interest from the image provided by the server and feed it back to the server, and continue the statistical analysis by the server to improve the representation of the association rule of the image feature. Sex.
- FIG. 4 is a schematic diagram of an image feature matching device according to an embodiment of the present invention.
- a first identification module 110 configured to acquire a sample image and identify an image feature of the sample image
- the analyzing module 111 is configured to perform statistical analysis on the relationship between the image features of the sample image to obtain an association rule between the image features;
- the second identification module 112 is configured to identify an image feature of the first image when receiving the first image uploaded by the client;
- the first pushing module 113 is configured to push the one or more second images associated with the image features of the first image to the client for display according to the association rule.
- the relationship matching device of the image feature further includes:
- a second pushing module configured to push a plurality of third images to the client, where the plurality of third images respectively have different image features
- the first receiving module is configured to receive, by the client, an image selected from the plurality of third images, and establish an association relationship between the image features of the first image and the image features of the selected image.
- the first pushing module 113 further includes:
- the determining sub-module is configured to determine whether the permission level of the client is greater than or equal to a preset threshold
- a pushing submodule configured to: when the privilege level of the client is greater than or equal to the preset threshold, push the one or more second images associated with the image features of the first image to the client according to the association rule;
- the sending submodule is configured to send a prompt message of the elevated privilege level to the client when the privilege level of the client is less than a preset threshold.
- the analyzing module 111 further includes:
- the analysis sub-module is configured to perform statistical analysis on the association relationship between various combinations of image features, and obtain association rules between various combinations of image features.
- FIG. 5 is a schematic diagram of an image feature matching device according to an embodiment of the present invention, which is located on the side of the terminal device 10, and includes:
- the uploading module 100 is configured to upload a first image to a server, so that the server identifies an image feature of the first image;
- the second receiving module 101 is configured to receive, by the server, one or more second images that are associated with image features of the first image that are pushed according to an association rule, where the association rule is performed by the server on the sample image.
- the display module 102 is configured to display the one or more second images.
- the relationship matching device of the image feature further includes:
- a third receiving module configured to receive a plurality of third images pushed by the server
- a sending module configured to send the image selected from the plurality of third images to the server according to the selected operation, so that the server establishes an association relationship between the image features of the first image and the image features of the selected image.
- each of the foregoing functional modules may be implemented by a hardware processor.
- FIG. 6 is a block diagram of an electronic device according to an embodiment of the present disclosure, and the device may include:
- One or more processors 601 and memory 602, one processor 601 is taken as an example in FIG.
- the electronic device may also include an input device 603 and an output device 604.
- the processor 601, the memory 602, the input device 603, and the output device 604 can be connected by a bus or other means.
- the memory 602 is used as a non-transitory computer readable storage medium, and can be used for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions corresponding to the relationship matching method of image features in the embodiment of the present invention. / module.
- the processor 601 executes various functional applications and data processing of the server by running non-transitory software programs, instructions, and modules stored in the memory 602, that is, a method for matching the image features of the above method embodiments.
- the memory 602 may include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created by the use of the relationship matching device according to the image feature, and the like. .
- memory 602 can include high speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device.
- the memory 602 can optionally include a memory remotely located relative to the processor 601, which can be connected via a network Connect to the processing device of the list item operation. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
- the input device 603 can receive input digital or character information, and generate key signal inputs related to user settings and function control of the relationship matching device of the image features.
- Output device 604 can include a display device such as a display screen.
- the one or more modules are stored in the memory 602, and when executed by the one or more processors 601, perform a relationship matching method of image features in any of the above method embodiments.
- FIG. 7 is a block diagram of an electronic device according to an embodiment of the present disclosure, and the device may include:
- processors 701 and a memory 702 are exemplified by a processor 701 in FIG.
- the relationship matching electronic device of the image feature may further include: an input device 703 and an output device 704.
- the processor 701, the memory 702, the input device 703, and the output device 704 can be connected by a bus or other means.
- the memory 702 is used as a non-transitory computer readable storage medium, and can be used for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions corresponding to the relationship matching method of image features in the embodiment of the present invention. / module.
- the processor 701 executes various functional applications and data processing of the server by running non-transitory software programs, instructions, and modules stored in the memory 702, that is, a method for matching the image features of the above method embodiments.
- the memory 702 may include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created by the use of the relationship matching device according to the image feature, and the like. .
- memory 702 can include high speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device.
- memory 702 can optionally include memory remotely located relative to processor 701 that can be connected to the processing device of the list item operation over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
- the input device 703 can receive input numeric or character information, and generate key signal inputs related to user settings and function control of the relationship matching device of the image features.
- Output device 704 can include a display device such as a display screen.
- the one or more modules are stored in the memory 702, and when executed by the one or more processors 701, perform a relationship matching method of image features in any of the above method embodiments.
- the above product can perform the method provided by the embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
- the above product can perform the method provided by the embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
- the electronic device of the embodiment of the invention exists in various forms, including but not limited to:
- Mobile communication devices These devices are characterized by mobile communication functions and are mainly aimed at providing voice and data communication.
- Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.
- Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has mobile Internet access.
- Such terminals include: PDAs, MIDs, and UMPC devices, such as the iPad.
- Portable entertainment devices These devices can display and play multimedia content. Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, and smart toys and portable car navigation devices.
- the server consists of a processor, a hard disk, a memory, a system bus, etc.
- the server is similar to a general-purpose computer architecture, but because of the need to provide highly reliable services, processing power and stability High reliability in terms of reliability, security, scalability, and manageability.
- an embodiment of the present invention further provides a computer readable storage medium, where the program for executing the method of the foregoing embodiment is stored.
- the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without deliberate labor.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Transfer Between Computers (AREA)
Abstract
一种图像特征的关系匹配方法、装置和系统，包括：获取样本图像并识别样本图像的图像特征(S20)；对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则(S21)；当接收到客户端上传的第一图像时，识别所述第一图像的图像特征(S22)；根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述客户端进行展示(S23)。根据关联规则匹配到的第二图像更贴近该用户的现实交友需求，从而提升了推送交友对象的成功率。
Description
交叉引用
本申请引用于2016年05月17日递交的名称为“图像特征关系的匹配方法、装置和系统”的第201610326124.8号中国专利申请，其通过引用被全部并入本申请。
本发明属于互联网技术领域，具体地说，涉及一种图像特征的关系匹配方法、装置和系统。
随着互联网的快速发展，很多互联网公司都已积累了TB量级的数据。数据随着互联网技术的发展，网络上出现了很多互联网交友平台。多数交友平台依靠网络交友功能来获得流量，提高用户的黏着度。随着更多应用功能的开发，网络交友的服务形式也越来越丰富，网络交友的方式变的更加具体，更具有针对性。
在当前的网络交友平台中，通常会根据用户输入的个人资料、交友条件等文字信息以及后台预设逻辑为用户匹配潜在的交友对象，并将这些潜在交友对象推荐给用户。
但这种推荐方式只是根据后台服务器预设的文字信息匹配规则为用户进行推荐，因此交友对象的推荐成功率很低，用户几乎很少关注这些由后台服务器自动推送的交友对象。
发明内容
有鉴于此，本发明实施例提供了一种图像特征的关系匹配方法、装置和系统，用以解决现有技术中自动为用户推荐潜在交友对象的成功率很低的技
术问题。
本发明实施例还提供一种电子设备、一种非暂态计算机存储介质以及一种计算机程序产品。
为了解决上述技术问题，本发明公开了一种图像特征的关系匹配方法，包括：获取样本图像并识别样本图像的图像特征；对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则；当接收到客户端上传的第一图像时，识别所述第一图像的图像特征；根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述客户端进行展示。
为了解决上述技术问题，本发明还公开了一种图像特征的关系匹配方法，包括：上传第一图像至服务器，以便所述服务器识别所述第一图像的图像特征；接收所述服务器根据关联规则推送的与所述第一图像的图像特征相关联的一个或多个第二图像，所述关联规则是由所述服务器对样本图像的图像特征之间的关联关系进行统计分析而得出的；展示所述一个或多个第二图像。
为了解决上述技术问题，本发明还公开了一种图像特征的关系匹配装置，包括：第一识别模块，用于获取样本图像并识别样本图像的图像特征；分析模块，用于对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则；第二识别模块，用于当接收到客户端上传的第一图像时，识别所述第一图像的图像特征；第一推送模块，用于根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述客户端进行展示。
为了解决上述技术问题，本发明还公开了一种图像特征的关系匹配装置，包括：上传模块，用于上传第一图像至服务器，以便所述服务器识别所述第一图像的图像特征；第二接收模块，用于接收所述服务器根据关联规则推送的与所述第一图像的图像特征相关联的一个或多个第二图像，所述关联规则是由所述服务器对样本图像的图像特征之间的关联关系进行统计分析而得出的；展示模块，用于展示所述一个或多个第二图像。
为了解决上述技术问题，本发明还公开了一种图像特征的关系匹配系统，包括终端设备和服务器；所述服务器获取样本图像并识别样本图像的图像特征，对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则；所述终端设备上传第一图像至所述服务器，所述服务器识别所述第一图像的图像特征，根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述终端设备，所述终端设备展示所述一个或多个第二图像。
本发明实施例还提供一种非暂态计算机存储介质，存储有计算机可执行指令，所述计算机可执行指令用于执行本申请上述任一项图像特征的关系匹配方法。
本发明实施例提供一种电子设备，包括：至少一个处理器；以及，
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一个处理器执行的指令，所述指令被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：
获取样本图像并识别样本图像的图像特征；
对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则；
当接收到客户端上传的第一图像时，识别所述第一图像的图像特征；
根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述客户端进行展示。
本发明实施例提供一种电子设备，包括：至少一个处理器；以及，
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一个处理器执行的指令，所述指令被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：
上传第一图像至服务器，以便所述服务器识别所述第一图像的图像特征；
接收所述服务器根据关联规则推送的与所述第一图像的图像特征相关
联的一个或多个第二图像，所述关联规则是由所述服务器对样本图像的图像特征之间的关联关系进行统计分析而得出的；
展示所述一个或多个第二图像。
本发明实施例还提供了一种计算机程序产品，所述计算机程序产品包括存储在非暂态计算机可读存储介质上的计算程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行本申请上述任一项图像特征的关系匹配方法。
与现有技术相比，本发明实施例提供的图像特征的关系匹配方法、装置和系统，分析出图像特征之间的关联规则，根据关联规则匹配到的图像更贴近该用户的现实交友需求，从而提升了推送交友对象的成功率。
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本发明实施例的图像特征的关系匹配系统的架构示意图；
图2是本发明实施例提供的一种图像特征的关系匹配方法的流程图；
图3是本发明实施例提供的一种图像特征的关系匹配方法的流程图；
图4是本发明实施例提供的一种图像特征的关系匹配装置的框图；
图5是本发明实施例提供的一种图像特征的关系匹配装置的框图；
图6为本发明实施例提供的一种电子设备的框图；
图7为本发明实施例提供的一种电子设备的框图。
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
本发明实施例识别样本图像的图像特征，根据样本图像之间的关联关系确定图像特征之间的关联关系，对图像特征之间的关联关系进行统计分析得到图像特征之间的关联规则，获得的图像特征之间的关联关系越多，分析得出的关联规则就越准确，当接收到客户端上传的第一图像时，即可根据关联规则匹配出与第一图像的图像特征相关联的一个或多个第二图像并推送至客户端进行展示，图像的推送是基于对图像特征的关联关系进行分析得出的内在规则来进行的，因此对用户而言具有一定的社会代表性，更符合现实的交友需求，使推送的图像更容易引起用户的关注，从而提升了交友平台为用户自动推送的交友对象的可推荐性以及用户通过交友平台寻找交友对象的效率。
图1是本发明实施例提供的图像特征的关系匹配系统的架构示意图，适包括终端设备10服务器11。终端设备10可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。服务器11是为网络用户提供网络交友服务的网站或应用程序的后台服务器。
用户通过终端设备10访问提供网络交友服务的网站或者应用程序，并与该网站或应用程序的后台服务器11进行数据交互。用户在该网站或应用程序注册用户帐号，通过该用户帐号在终端设备10本地完成登录操作即可使用该网络交友服务。
服务器11可通过各种方式获取样本图像。样本图像包括用户本人图像和该用户的一个或多个理想目标交友对象的图像。网站或应用程序的运营者可通过线下招募志愿者的方式，由志愿者提交本人图像和理想目标交友对象的图像，服务器11将本人图像、理想目标交友对象的图像以及该本人图像
与理想目标交友对象的图像之间关联关系进行保存。此外，还可以通过线上测试的方式收集样本图像。对于已经注册并上传了本人图像的用户帐号，在该用户帐号登录网站或应用程序后，向其推送多个图像并让其从中选出可以做为理想目标交友对象的图像。服务器11接收到该用户帐号的选定的图像后，将该用户帐号上传的图像、选定的图像以及该上传的图像与选定的图像之间的关联关系进行保存。
服务器11获取到样本图像后，对其中本人图像和理想目标交友对象的图像进行图像特征的识别，可通过现有的图像特征以及人脸识别技术来实现。识别出的图像特征可以是该图像的总体特征，例如端庄、清纯、成熟、小鲜肉等能够反映图像中的人物的总体印象的特征；也可以是该图像的局部特征，例如，短发、单眼皮、锥子脸等能够体现图像中的人物的局部特点的特征；还可以同时包括上述总体特征和局部特征。
识别出图像特征后，根据本人图像与理想目标交友对象的图像之间的关联关系，建立本人图像的图像特征与理想目标交友对象的图像特征之间的关联关系。
通过上述方式取得所有样本图像的图像特征的关联关系后，对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则。该关联规则是最能解释图像特征之间关系的规则，可通过数据深度挖掘算法获得，例如Apriori算法、Eclat算法等。服务器11获取到的样本图像越多，分析得到关联规则就越具有广泛的社会代表性，就越贴近现实中的交友需求。因此，通过尽可能多的样本图像来挖掘图像特征之间的关联规则对本发明实施例而言是非常重要的。
当网络交友平台的新用户通过终端设备10上传本人图像至服务器11之后，服务器11首先对上传的本人图像进行图像特征的识别。再利用分析得到的关联规则，匹配到与本人图像的图像特征关联的图像特征。再检索出具有该关联的图像特征的由其他用户的图像，最终将检索到的其他用户的图像推送至终端设备10。在终端设备10打开的网页或应用程序中，将服务器11推送的图像进行展示。
推送的图像是根据数据深度挖掘等到的关联规则匹配得到的，更贴近该用户的现实交友需求，更能使用户感兴趣，从而提升了推送交友对象的成功率。
而对于图像特征之间的关联规则，可以是整体特征之间的关联规则或者局部特征之间的关联规则；还可以是整体特征与局部特征的组合之间的关联规则。在识别图像特征时，识别出该图像的整体特征和局部特征，将该整体特征和局部特征做为一种图像特征的组合，在用户图像和理想目标交友对象的图像特征的组合之间建立关联关系，再对图像特征的各种组合之间的关联关系进行统计分析，得到图像特征的各种组合之间的关联规则。从而可以根据图像特征的各种组合之间的关联规则匹配出推送的图像。这样，对图像特征的分析以及得到的关联规则会更加精细，从而使推送的图像更能够引起用户的兴趣，进一步提升了交友对象的推荐成功率。
上述为交友平台的用户提供的交友对象的推荐服务，前提条件是该用户已经上传了本人图像。对没有上传本人图像的用户则无法利用上述方法为其推荐交友对象。此外，还可以对已上传本人图像的用户做进一步的划分，即在已上传本人图像的用户当中，只有该用户的用户帐号的权限等级达到预设门限时，才为其提供上述交友对象的推荐服务。服务器11在对上传的本人图像进行特征识别后，判断该用户帐号的权项等级是否大于或等于预设门限。当该用户帐号的权项等级大于或等于预设门限时，根据关联规则推送与本人图像的图像特征相关联的一个或多个图像至终端设备10进行展示；当该用户帐号的权项等级小于预设门限时，发送提升权限级别的提示消息至终端设备10。或者，当用户帐号的权限等级大于或等于预设门限但该用户帐号没有上传本人图像时，发送上传本人图像的提示消息至终端设备10。网站或应用程序的运营者会花费大量人力、财力去收集样本图像并寻找样本图像的图像特征之间的关联规则，因此将上述交友对象的推荐服务提供给权限等级达到预设门限的用户，有助于降低交友网站或应用程序的运营成本。
基于以上内容，本发明实施例在服务器11一侧提供了一种图像特征的关系匹配方法，如图2所示，该方法包括以下步骤。
S20，获取样本图像并识别样本图像的图像特征；
S21，对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则；
S22，当接收到客户端上传的第一图像时，识别第一图像的图像特征；
S23，根据关联规则推送与第一图像的图像特征相关联的一个或多个第二图像至客户端进行展示。
其中，第一图像是用户的本人图像，第二图像是根据关联规则以及第一图像的图像特征匹配到的图像。根据关联规则匹配到的第二图像更贴近该用户的现实交友需求，从而提升了推送交友对象的成功率。
在一个实施例中，该图像特征的关系匹配方法进一步包括以下步骤。
S24，推送多个第三图像至客户端，多个第三图像分别具有不同的图像特征；
S25，接收客户端返回从多个第三图像中选定的图像，并建立第一图像的图像特征与选定的图像的图像特征之间的关联关系。
在线上采集样本图像时，第三图像是为已上传本人图像的用户推送的可选择图像。通过该网络交友平台，收集更多的样本图像，来提高关联规则代表性，使其更贴合用户的交友需求。
在一个实施例中，该步骤S23进一步包括以下步骤。
S231，判断客户端的权限级别是否大于或等于预设门限。当客户端的权限级别大于或等于预设门限时，执行步骤S232；当客户端的权限级别小于预设门限时，执行步骤S233。
S232，根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述客户端进行展示；
S233，发送提升权限级别的提示消息至所述客户端。
将交友对象的图像匹配服务提供给权项等级更高的用户，有助于降低交友平台的运营成本。
在一个实施例中，该步骤S21进一步包括以下步骤。
S211，对图像特征的各种组合之间的关联关系进行统计分析，得到图像特征的各种组合之间的关联规则。
图像特征的组合包括整体特征和局部特征，使图像特征进行更加细致的识别，进而使分析得到的关联规则也更加精细，成为图像特征的组合之间的关联规则，使推送的第二图像更能够引起用户的兴趣。
本发明实施例在终端设备10一侧提供了一种图像特征的关系匹配方法，如图3所示，该方法包括以下步骤。
S30，上传第一图像至服务器，以便服务器识别第一图像的图像特征；
S31，接收服务器根据关联规则推送的与第一图像的图像特征相关联的一个或多个第二图像，关联规则是由服务器对样本图像的图像特征之间的关联关系进行统计分析而得出的；
S32，展示一个或多个第二图像。
用户在上传本人图像后，会接收到根据图像特征的关联规则推送的其他用户的图像，推送的图像会很贴近现实的交友需求，对用户具有更高的吸引力。
在一个实施例中，该图像特征的关系匹配方法进一步包括以下步骤。
S33，接收服务器推送的多个第三图像；
S34，根据选定操作将从多个第三图像中选定的图像发送至服务器，以便服务器建立第一图像的图像特征与选定的图像的图像特征之间的关联关系。
已上传本人图像的用户还可以参与样本图像的线上采集，从服务器提供的图像中选出自己感兴趣的图像并反馈给服务器，由服务器继续进行统计分析，以提高图像特征的关联规则的代表性。
以下为本发明的装置实施例，用于执行本发明的上述方法实施例。
图4是本发明实施例提供的一种图像特征的关系匹配装置，位于服务器11一侧，包括：
第一识别模块110，用于获取样本图像并识别样本图像的图像特征；
分析模块111，用于对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则；
第二识别模块112，用于当接收到客户端上传的第一图像时，识别第一图像的图像特征；
第一推送模块113，用于根据关联规则推送与第一图像的图像特征相关联的一个或多个第二图像至客户端进行展示。
在一个实施例中，该图像特征的关系匹配装置进一步包括：
第二推送模块，用于推送多个第三图像至所述客户端，多个第三图像分别具有不同的图像特征；
第一接收模块，用于接收客户端返回从多个第三图像中选定的图像，并建立第一图像的图像特征与选定的图像的图像特征之间的关联关系。
在一个实施例中，该第一推送模块113进一步包括：
判断子模块，用于判断客户端的权限级别是否大于或等于预设门限；
推送子模块，用于当客户端的权限级别大于或等于预设门限时，根据关联规则推送与第一图像的图像特征相关联的一个或多个第二图像至客户端进行展示；
发送子模块，用于当客户端的权限级别小于预设门限时，发送提升权限级别的提示消息至所述客户端。
在一个实施例中，该分析模块111进一步包括：
分析子模块，用于对图像特征的各种组合之间的关联关系进行统计分析，得到图像特征的各种组合之间的关联规则。
图5是本发明实施例提供的一种图像特征的关系匹配装置，位于终端设备10一侧，包括：
上传模块100，用于上传第一图像至服务器，以便所述服务器识别所述第一图像的图像特征；
第二接收模块101，用于接收所述服务器根据关联规则推送的与所述第一图像的图像特征相关联的一个或多个第二图像，所述关联规则是由所述服务器对样本图像的图像特征之间的关联关系进行统计分析而得出的；
展示模块102，用于展示所述一个或多个第二图像。
在一个实施例中，该图像特征的关系匹配装置进一步包括：
第三接收模块，用于接收服务器推送的多个第三图像；
发送模块，用于根据选定操作将从多个第三图像中选定的图像发送至服务器，以便服务器建立第一图像的图像特征与选定的图像的图像特征之间的关联关系。
此外，本发明实施例中可以通过硬件处理器(hardware processor)来实现上述各个功能模块。
图6为本发明实施例提供的一种电子设备的框图，该设备可以包括：
一个或多个处理器601以及存储器602，图6中以一个处理器601为例。
电子设备还可以包括：输入装置603和输出装置604。
处理器601、存储器602、输入装置603和输出装置604可以通过总线或者其他方式连接。
存储器602作为一种非暂态计算机可读存储介质，可用于存储非暂态软件程序、非暂态计算机可执行程序以及模块，如本发明实施例中的图像特征的关系匹配方法对应的程序指令/模块。处理器601通过运行存储在存储器602中的非暂态软件程序、指令以及模块，从而执行服务器的各种功能应用以及数据处理，即实现上述方法实施例图像特征的关系匹配方法。
存储器602可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据图像特征的关系匹配装置的使用所创建的数据等。此外，存储器602可以包括高速随机存取存储器，还可以包括非暂态存储器，例如至少一个磁盘存储器件、闪存器件、或其他非暂态固态存储器件。在一些实施例中，存储器602可选包括相对于处理器601远程设置的存储器，这些远程存储器可以通过网络连
接至列表项操作的处理装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置603可接收输入的数字或字符信息，以及产生与图像特征的关系匹配装置的用户设置以及功能控制有关的键信号输入。输出装置604可包括显示屏等显示设备。
所述一个或者多个模块存储在所述存储器602中，当被所述一个或者多个处理器601执行时，执行上述任意方法实施例中的图像特征的关系匹配方法。
图7为本发明实施例提供的一种电子设备的框图，该设备可以包括：
一个或多个处理器701以及存储器702，图7中以一个处理器701为例。
图像特征的关系匹配电子设备还可以包括：输入装置703和输出装置704。
处理器701、存储器702、输入装置703和输出装置704可以通过总线或者其他方式连接。
存储器702作为一种非暂态计算机可读存储介质，可用于存储非暂态软件程序、非暂态计算机可执行程序以及模块，如本发明实施例中的图像特征的关系匹配方法对应的程序指令/模块。处理器701通过运行存储在存储器702中的非暂态软件程序、指令以及模块，从而执行服务器的各种功能应用以及数据处理，即实现上述方法实施例图像特征的关系匹配方法。
存储器702可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据图像特征的关系匹配装置的使用所创建的数据等。此外，存储器702可以包括高速随机存取存储器，还可以包括非暂态存储器，例如至少一个磁盘存储器件、闪存器件、或其他非暂态固态存储器件。在一些实施例中，存储器702可选包括相对于处理器701远程设置的存储器，这些远程存储器可以通过网络连接至列表项操作的处理装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置703可接收输入的数字或字符信息，以及产生与图像特征的关系匹配装置的用户设置以及功能控制有关的键信号输入。输出装置704可包括显示屏等显示设备。
所述一个或者多个模块存储在所述存储器702中，当被所述一个或者多个处理器701执行时，执行上述任意方法实施例中的图像特征的关系匹配方法。
上述产品可执行本发明实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本发明实施例所提供的方法。
本发明实施例的电子设备以多种形式存在，包括但不限于:
(1)移动通信设备：这类设备的特点是具备移动通信功能，并且以提供话音、数据通信为主要目标。这类终端包括:智能手机(例如iPhone)、多媒体手机、功能性手机，以及低端手机等。
(2)超移动个人计算机设备:这类设备属于个人计算机的范畴，有计算和处理功能，一般也具备移动上网特性。这类终端包括：PDA、MID和UMPC设备等，例如iPad。
(3)便携式娱乐设备：这类设备可以显示和播放多媒体内容。该类设备包括：音频、视频播放器(例如iPod)，掌上游戏机，电子书，以及智能玩具和便携式车载导航设备。
(4)服务器：提供计算服务的设备，服务器的构成包括处理器、硬盘、内存、系统总线等，服务器和通用的计算机架构类似，但是由于需要提供高可靠的服务，因此在处理能力、稳定性、可靠性、安全性、可扩展性、可管理性等方面要求较高。
(5)其他具有数据交互功能的电子装置。
相应地，本发明实施例还提供一种计算机可读存储介质，所述计算机可读存储介质中存储有用于执行上述实施例方法的程序。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。
Claims (19)
- 一种图像特征的关系匹配方法，其特征在于，包括：获取样本图像并识别样本图像的图像特征；对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则；当接收到客户端上传的第一图像时，识别所述第一图像的图像特征；根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述客户端进行展示。
- 根据权利要求1所述的方法，其特征在于，所述方法还包括：推送多个第三图像至所述客户端，所述多个第三图像分别具有不同的图像特征；接收所述客户端返回从所述多个第三图像中选定的图像，并建立所述第一图像的图像特征与所述选定的图像的图像特征之间的关联关系。
- 根据权利要求1所述的方法，其特征在于，所述根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述客户端进行展示包括：判断所述客户端的权限级别是否大于或等于预设门限；当所述客户端的权限级别大于或等于预设门限时，根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述客户端进行展示；当所述客户端的权限级别小于预设门限时，发送提升权限级别的提示消息至所述客户端。
- 根据权利要求1所述的方法，其特征在于，所述对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则包括：对图像特征的各种组合之间的关联关系进行统计分析，得到图像特征的各种组合之间的关联规则。
- 一种图像特征的关系匹配方法，其特征在于，包括：上传第一图像至服务器，以便所述服务器识别所述第一图像的图像特征；接收所述服务器根据关联规则推送的与所述第一图像的图像特征相关联的一个或多个第二图像，所述关联规则是由所述服务器对样本图像的图像特征之间的关联关系进行统计分析而得出的；展示所述一个或多个第二图像。
- 根据权利要求5所述的方法，其特征在于，所述方法还包括：接收所述服务器推送的多个第三图像；根据选定操作将从所述多个第三图像中选定的图像发送至所述服务器，以便所述服务器建立所述第一图像的图像特征与所述选定的图像的图像特征之间的关联关系。
- 一种图像特征的关系匹配装置，其特征在于，包括：第一识别模块，用于获取样本图像并识别样本图像的图像特征；分析模块，用于对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则；第二识别模块，用于当接收到客户端上传的第一图像时，识别所述第一图像的图像特征；第一推送模块，用于根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述客户端进行展示。
- 根据权利要求7所述的装置，其特征在于，所述装置还包括：第二推送模块，用于推送多个第三图像至所述客户端，所述多个第三图像分别具有不同的图像特征；第一接收模块，用于接收所述客户端返回从所述多个第三图像中选定的图像，并建立所述第一图像的图像特征与所述选定的图像的图像特征之间的关联关系。
- 根据权利要求7所述的装置，其特征在于，所述第一推送模块包括：判断子模块，用于判断所述客户端的权限级别是否大于或等于预设门限；推送子模块，用于当所述客户端的权限级别大于或等于预设门限时，根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述客户端进行展示；发送子模块，用于当所述客户端的权限级别小于预设门限时，发送提升权限级别的提示消息至所述客户端。
- 根据权利要求7所述的装置，其特征在于，所述分析模块包括：分析子模块，用于对图像特征的各种组合之间的关联关系进行统计分析，得到图像特征的各种组合之间的关联规则。
- 一种图像特征的关系匹配装置，其特征在于，包括：上传模块，用于上传第一图像至服务器，以便所述服务器识别所述第一图像的图像特征；第二接收模块，用于接收所述服务器根据关联规则推送的与所述第一图像的图像特征相关联的一个或多个第二图像，所述关联规则是由所述服务器对样本图像的图像特征之间的关联关系进行统计分析而得出的；展示模块，用于展示所述一个或多个第二图像。
- 根据权利要求11所述的装置，其特征在于，所述装置还包括：第三接收模块，用于接收所述服务器推送的多个第三图像；发送模块，用于根据选定操作将从所述多个第三图像中选定的图像发送至所述服务器，以便所述服务器建立所述第一图像的图像特征与所述选定的图像的图像特征之间的关联关系。
- 一种图像特征的关系匹配系统，其特征在于，包括终端设备和服务器；所述服务器获取样本图像并识别样本图像的图像特征，对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则；所述终端设备上传第一图像至所述服务器，所述服务器识别所述第一图像的图像 特征，根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述终端设备，所述终端设备展示所述一个或多个第二图像。
- 一种电子设备，其特征在于，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：获取样本图像并识别样本图像的图像特征；对样本图像的图像特征之间的关联关系进行统计分析，得到图像特征之间的关联规则；当接收到客户端上传的第一图像时，识别所述第一图像的图像特征；根据所述关联规则推送与所述第一图像的图像特征相关联的一个或多个第二图像至所述客户端进行展示。
- 一种电子设备，其特征在于，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：上传第一图像至服务器，以便所述服务器识别所述第一图像的图像特征；接收所述服务器根据关联规则推送的与所述第一图像的图像特征相关联的一个或多个第二图像，所述关联规则是由所述服务器对样本图像的图像特征之间的关联关系进行统计分析而得出的；展示所述一个或多个第二图像。
- 一种非暂态计算机可读存储介质，其特征在于，所述非暂态计算机可读存储介质存储计算机指令，所述计算机指令用于使所述计算机 执行权利要求1-4任一所述方法。
- 一种非暂态计算机可读存储介质，其特征在于，所述非暂态计算机可读存储介质存储计算机指令，所述计算机指令用于使所述计算机执行权利要求5-6任一所述方法。
- 一种计算机程序产品，所述计算机程序产品包括存储在非暂态计算机可读存储介质上的计算程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行权利要求1-4任一所述方法。
- 一种计算机程序产品，所述计算机程序产品包括存储在非暂态计算机可读存储介质上的计算程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行权利要求5-6任一所述方法。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610326124.8A CN106021455A (zh) | 2016-05-17 | 2016-05-17 | 图像特征关系的匹配方法、装置和系统 |
| CN201610326124.8 | 2016-05-17 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017197826A1 true WO2017197826A1 (zh) | 2017-11-23 |
Family
ID=57098548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2016/101059 Ceased WO2017197826A1 (zh) | 2016-05-17 | 2016-09-30 | 图像特征关系的匹配方法、装置和系统 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106021455A (zh) |
| WO (1) | WO2017197826A1 (zh) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538606A (zh) * | 2021-08-17 | 2021-10-22 | 数坤(北京)网络科技股份有限公司 | 图像关联方法、联动显示方法及相关产品 |
| US11209442B2 (en) | 2017-12-22 | 2021-12-28 | Google Llc | Image selection suggestions |
| CN114219590A (zh) * | 2022-02-23 | 2022-03-22 | 广亚铝业有限公司 | 一种基于服务器与客户端app的门窗信息服务系统及方法 |
| US11775139B2 (en) | 2017-12-22 | 2023-10-03 | Google Llc | Image selection suggestions |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570123B (zh) * | 2016-11-02 | 2020-07-24 | 中国科学院深圳先进技术研究院 | 基于邻接对象关联规则的遥感图像检索方法及系统 |
| CN107680662A (zh) * | 2017-09-11 | 2018-02-09 | 广州市锐狮网络科技有限公司 | 基于Hadoop云大数据处理的数据库营销系统及方法 |
| CN108154165B (zh) * | 2017-11-20 | 2021-12-07 | 华南师范大学 | 基于大数据与深度学习的婚恋对象匹配数据处理方法、装置、计算机设备和存储介质 |
| CN113038199B (zh) * | 2019-12-24 | 2022-04-05 | 腾讯科技（深圳）有限公司 | 权限变更方法、装置、计算机设备和计算机可读存储介质 |
| CN112163168A (zh) * | 2020-09-15 | 2021-01-01 | 济南雪景网络技术有限公司 | 一种基于计算机视觉的匹配交友方法 |
| CN117321586A (zh) * | 2022-04-29 | 2023-12-29 | 北京小米移动软件有限公司 | 图像处理方法及装置 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030031361A1 (en) * | 2001-08-08 | 2003-02-13 | Amir Said | Predominant color identification in digital images |
| CN103678323A (zh) * | 2012-09-03 | 2014-03-26 | 上海唐里信息技术有限公司 | Sns网络中好友推荐方法与系统 |
| CN104794275A (zh) * | 2015-04-16 | 2015-07-22 | 北京联合大学 | 一种移动终端的人脸与发型匹配模型 |
| CN105389548A (zh) * | 2015-10-23 | 2016-03-09 | 南京邮电大学 | 基于人脸识别的婚恋评价系统和方法 |
-
2016
- 2016-05-17 CN CN201610326124.8A patent/CN106021455A/zh active Pending
- 2016-09-30 WO PCT/CN2016/101059 patent/WO2017197826A1/zh not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030031361A1 (en) * | 2001-08-08 | 2003-02-13 | Amir Said | Predominant color identification in digital images |
| CN103678323A (zh) * | 2012-09-03 | 2014-03-26 | 上海唐里信息技术有限公司 | Sns网络中好友推荐方法与系统 |
| CN104794275A (zh) * | 2015-04-16 | 2015-07-22 | 北京联合大学 | 一种移动终端的人脸与发型匹配模型 |
| CN105389548A (zh) * | 2015-10-23 | 2016-03-09 | 南京邮电大学 | 基于人脸识别的婚恋评价系统和方法 |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11209442B2 (en) | 2017-12-22 | 2021-12-28 | Google Llc | Image selection suggestions |
| US11775139B2 (en) | 2017-12-22 | 2023-10-03 | Google Llc | Image selection suggestions |
| CN113538606A (zh) * | 2021-08-17 | 2021-10-22 | 数坤(北京)网络科技股份有限公司 | 图像关联方法、联动显示方法及相关产品 |
| CN114219590A (zh) * | 2022-02-23 | 2022-03-22 | 广亚铝业有限公司 | 一种基于服务器与客户端app的门窗信息服务系统及方法 |
| CN114219590B (zh) * | 2022-02-23 | 2022-06-17 | 广亚铝业有限公司 | 一种基于服务器与客户端app的门窗信息服务系统及方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106021455A (zh) | 2016-10-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017197826A1 (zh) | 图像特征关系的匹配方法、装置和系统 | |
| CN108446410B (zh) | 信息推荐方法、装置、系统、设备及可读存储介质 | |
| CN109155136B (zh) | 从视频自动检测和渲染精彩场面的计算机化系统和方法 | |
| US10142279B2 (en) | Method and system for presenting a listing of message logs | |
| US9911223B2 (en) | Automatic video segment selection method and apparatus | |
| US9817557B2 (en) | Interactive audience communication for events | |
| CN112104642B (zh) | 一种异常账号确定方法和相关装置 | |
| WO2017181612A1 (zh) | 个性化视频推荐方法及装置 | |
| WO2017181613A1 (zh) | 搜索响应方法、装置及系统 | |
| JP2017153078A (ja) | 人工知能学習方法、人工知能学習システムおよび返答中継方法 | |
| CN104317804B (zh) | 发布投票信息的方法和装置 | |
| US20180302761A1 (en) | Recommendation System for Multi-party Communication Sessions | |
| CN103455411B (zh) | 日志分类模型的建立、行为日志分类方法及装置 | |
| US10719890B1 (en) | Machine learning system and method for clustering | |
| CN102158541B (zh) | 一种共享信息的获取方法、装置、移动终端及服务器 | |
| CN107967333A (zh) | 语音搜索方法、语音搜索装置及电子设备 | |
| US20220405862A1 (en) | System for users to increase and monetize livestream audience engagement | |
| CN113626624B (zh) | 一种资源识别方法和相关装置 | |
| CN108932646A (zh) | 基于运营商的用户标签验证方法、装置和电子设备 | |
| US20170278130A1 (en) | Method and Electronic Device for Matching Advertisement Data | |
| US10593222B1 (en) | Video filming and discovery system | |
| CN112016001A (zh) | 好友推荐方法、设备及计算机可读介质 | |
| CN114969493B (zh) | 一种内容推荐方法和相关装置 | |
| CN111125544B (zh) | 用户推荐方法及装置 | |
| CN110719324A (zh) | 信息推送方法和设备 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16902206 Country of ref document: EP Kind code of ref document: A1 |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 16902206 Country of ref document: EP Kind code of ref document: A1 |