WO2015051657A1 - 一种用户搜索方法及装置 - Google Patents

一种用户搜索方法及装置 Download PDF

Info

Publication number
WO2015051657A1
WO2015051657A1 PCT/CN2014/081936 CN2014081936W WO2015051657A1 WO 2015051657 A1 WO2015051657 A1 WO 2015051657A1 CN 2014081936 W CN2014081936 W CN 2014081936W WO 2015051657 A1 WO2015051657 A1 WO 2015051657A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
avatar
pending
score
registered
Prior art date
Application number
PCT/CN2014/081936
Other languages
English (en)
French (fr)
Inventor
谢东
Original Assignee
腾讯科技(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 腾讯科技(深圳)有限公司 filed Critical 腾讯科技(深圳)有限公司
Publication of WO2015051657A1 publication Critical patent/WO2015051657A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions

Definitions

  • the embodiments of the present invention relate to the field of network communication technologies, and in particular, to a user search method and apparatus.
  • the embodiment of the invention provides a user search method and device, which can improve the search efficiency of the target user and facilitate the relationship chain expansion in the communication application.
  • a user search method includes the following steps: a computing device receives a user search request sent by a client of a communication application, and obtains a search condition from the user search request; the computing device searches for a search condition from the user database to match the search condition At least one pending user, and obtaining an avatar score of each pending user; the computing device selects at least one target user from the at least one pending user according to the avatar score of the pending user, and selects the selected target user Return to this client.
  • a user search device comprising: a receiving module, configured to receive a user search request sent by a client of a communication application, obtain a search condition from the user search request; and a search module, configured to search for a search condition from the user database Matching at least one pending user, and obtaining an avatar score of each of the pending users; a screening module, configured to filter at least one target user from the at least one pending user according to the avatar score of the pending user, and filter the selected The target user is returned to the client.
  • the user search method and device provided by the embodiment of the present invention, after searching for a pending user that matches the search condition, the target user is filtered out from the pending user according to the avatar score of the pending user, and the target user is returned to the client, thereby improving
  • the search efficiency of the target user is beneficial to the relationship chain expansion in the communication application.
  • FIG. 1 is a schematic structural diagram of a server according to an embodiment of the present disclosure
  • 2 is a schematic diagram of an environment when a user search method is applied according to an embodiment of the present invention
  • FIG. 3 is a flowchart of a user search method according to an embodiment of the present invention
  • FIG. 4 is a flowchart of a method for establishing a user database according to an embodiment of the present invention
  • FIG. 5 is a schematic diagram of a facial feature of a face in an avatar according to an embodiment of the present invention
  • FIG. 6 is a schematic diagram of a user search device according to an embodiment of the present invention
  • FIG. 6B is a schematic structural diagram of a user search apparatus according to an embodiment of the present invention
  • FIG. 6C is a schematic structural diagram of a user search apparatus according to an embodiment of the present invention
  • FIG. 7A is a hardware diagram of a user search apparatus according to an embodiment of the present invention
  • FIG. 7B is a schematic structural diagram of hardware of a user search apparatus according to an embodiment of the present invention.
  • FIG. 1 is a schematic structural diagram of a computing device according to an embodiment of the present invention.
  • the computing device can be, for example, a server.
  • server 1 includes one or more
  • server 1 (only one is shown) memory 11, processor 12, memory controller 13, peripheral interface 14, communication module 15, input unit 16, and display unit 17. These components communicate with one another via one or more communication bus/signal lines. It will be understood by those skilled in the art that the structure shown in FIG. 1 is only illustrative, and The structure of the server 1 is not limited. For example, server 1 may also include more or fewer components than shown in FIG. 1, or have a different configuration than that shown in FIG. The components shown in Figure 1 can be implemented in hardware or a combination of hardware and software.
  • the memory 11 can be used to store machine readable instructions and instruction modules, such as user search methods and apparatus corresponding to machine readable instructions/modules in embodiments of the present invention.
  • the processor 12 implements the user search method and apparatus provided by the embodiments of the present invention by executing the machine-readable instructions and the instruction module stored in the memory 11 to perform various function applications and data processing.
  • Memory 11 may include high speed random access memory, and may also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory. In some examples, memory 11 may further include memory remotely located relative to processor 12, which may be connected to server 1 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof. Access to the memory 11 by the processor 12 and other possible components can be performed under the control of the memory controller 13.
  • Peripheral interface 14 couples various input/output devices to processor 12 and memory 11.
  • the processor 12 runs various software, instructions, and various functions of the server 1 and performs data processing in the memory 11.
  • the communication module 15 is for communicating with a communication network or other device.
  • the communication module 15 may be, for example, a network card.
  • the network card acts as an interface between the computer and the transmission medium in the local area network, and is used to implement physical connection and electrical signal matching with the local area network transmission medium, thereby establishing a local area network and connecting to the Internet (Internet), and various networks such as a local area network and a metropolitan area network. , WAN communication.
  • the network card may include various existing circuit components for performing the above functions, such as a processor and a memory (including ROM and RAM) and the like.
  • the input unit 16 can be used to receive input character information, and generate and user settings And keyboard, mouse, joystick, optical or trackball signal input related to function control.
  • the input unit 16 may include a button 161 and a touch surface 162.
  • the button 161 may include, for example, a character button for inputting a character, and a control button for triggering a control function. Examples of control buttons include a "return to main screen" button, a power on/off button, a camera button, and the like.
  • the touch surface 162 can collect touch operations on or near the user (such as the operation of the user using a finger, a stylus, or the like on any suitable object or accessory on or near the touch surface 162), and according to the The set program drives the corresponding connection device.
  • the touch surface 162 may include two portions of a touch detection device and a touch controller. Wherein, the touch detection device detects the touch orientation of the user, and detects a signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts the touch information into contact coordinates, and sends the touch information
  • the processor 12 is provided and can receive commands from the processor 12 and execute them.
  • the touch surface 162 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves.
  • the input unit 16 can also include other input devices.
  • Other input devices described above include, but are not limited to, one or more of a physical keyboard, a trackball, a mouse, a joystick, and the like.
  • the display unit 17 is for displaying information input by the user, information provided to the user, and various graphical user interfaces of the server 1. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof.
  • display unit 17 includes a display panel 171.
  • the display panel 171 can be, for example, a liquid crystal display (LCD), an organic light-emitting diode display (OLED) display panel, an electric device, or an electro-phoretic display (EPD).
  • the touch surface 162 can be disposed on the display panel 171 to be integrated with the display panel 171.
  • a ring of a user search method is applied.
  • the server 1 may include one or more servers.
  • the server 1 may also be a virtual cloud computing module.
  • Specific examples of the terminal 3 include, but are not limited to, a desktop computer, a portable computer, a smart phone, a tablet, a PDA (Personal Digital Assistant), or the like.
  • the network 2 can be any network connection method, such as the Internet (Internet), the mobile Internet (such as 2G, 3G networks provided by the telecom operators), the local area network (wired or wireless), and the like.
  • an embodiment of the present invention provides a user search method, where the user search method includes the following steps:
  • Step S1 a computing device, such as the foregoing server 1, receives a user search request sent by a client of the communication application, and obtains a search condition from the user search request;
  • Step S2 The computing device searches for at least one pending user that matches the search condition from the user database, and obtains an avatar score of each pending user.
  • Step S3 The computing device selects at least one target user from the at least one pending user according to the avatar score of the pending user, and returns the filtered target user to the client.
  • a search for a pending user that matches the search criteria is found. Then, the target user is filtered out from the pending users according to the avatar score of the pending user, and the target user is returned to the client, thereby improving the search efficiency of the target user and facilitating the relationship chain expansion in the communication application.
  • the communication application described in the step S1 includes an instant messaging application and a social application
  • the instant messaging application includes, for example, QQ, WeChat, and the like
  • the social application includes, for example, a QQ space, a friend network, a microblog, and the like.
  • the communication application is installed in the server 1 and the client of the communication application is installed and operates in the terminal 3.
  • the method may further include the process of the current login user of the client of the communication application logging in to the communication application, including: the current login user inputting a login account to the client of the communication application, according to
  • the login account may include a pre-applied user name and password; the client of the communication application sends the login account to the server 1 to verify its validity; when the server 1 verifies that the login account is valid, the current login user
  • the communication application is successfully logged in so that user search operations can be performed in the client of the communication application, such as entering search conditions, clicking search options, and the like.
  • the client of the communication application issues the user search request to the server 1 based on the user search operation of the currently logged-in user.
  • the user search request includes a search condition including, for example, a gender of the desired target user, a city, an age, an institution, a work unit, and the like. Then, the user search request is received in step S1, and the search condition is obtained from the user search request.
  • a pending user that matches the search condition is searched from the user database.
  • the user database is used to record the personal data of all registered users of the communication application, such as gender, avatar, city, age, college, work unit, and the like. Therefore, the pending user is also a registered user of the communication application.
  • the registered user is a user who is directed to the communication application to apply for registration and obtain a valid login account. Apply to the communication application When registering, the profile described will be uploaded. Therefore, the personal data of all registered users of the communication application are saved in the user database. In addition, the avatar score of each registered user is also recorded in the user database.
  • the establishment process of the user database includes the following steps:
  • Step Sl l preset a set of scoring standards, used to score the avatar of each registered user.
  • the scoring criteria include criteria for scoring facial features of a face.
  • the facial features of the face include, for example, the size of the facial features, the ratio of facial features to the face, the distance between the eyes, the distance between the eyes and the nose, the distance between the eyes and the eyebrows, and the like.
  • This scoring standard can be set based on a large number of samples.
  • Standard data for facial features as well as standard data for individual facial features corresponding to male avatars.
  • the standard data for the distance between the eyes of a female avatar is d
  • the standard for the distance between the eyes of a male avatar is D.
  • the standard data for a facial feature corresponds to a full score for the facial feature, for example 10 points.
  • the criteria for scoring the facial features of the face are set. For example, if the standard data of the distance between the eyes of the female avatar is d, corresponding to a perfect score of 10, if the distance between the eyes is one unit distance or one unit distance larger than the standard data d, for example, d/100, then The full score of 10 is reduced by 0.5.
  • Step S12 scoring the avatar of each registered user of the communication application according to the scoring standard.
  • a face and a facial feature in an avatar of each registered user of the communication application may be identified by a facial recognition technology, and each face is counted.
  • the data corresponding to the feature For example, as shown in FIG. 5, the size of the eye, the size of the nose, the size of the mouth, and the distance between the eyes, the nose, and the mouth (including the distance between the eyes and the nose, the eye and the eye) can be separately calculated in units of pixels. The distance between the mouth, and the distance between the nose and the mouth).
  • the avatar uploaded by the registered user may be his real avatar, or may be a virtual avatar such as a star photo or a cartoon. Therefore, if the face is not recognized by the face recognition technology, the avatar is considered to be a virtual avatar, and the avatar is directly divided into 0.
  • the facial features of the faces of each registered user's avatar are respectively scored, and finally registered.
  • the scores of the facial features of the face in the user's avatar are summed to obtain the avatar score of the registered user. For example, if there are six facial features of a face in a registered user's avatar, the eye size, the nose size, the mouth size, and the distance between the eyes, the nose, and the mouth.
  • the facial feature score of the eye size is 8
  • the facial feature score of the nose size is 7
  • the facial feature score of the mouth size is 9
  • the facial feature score of the distance between the eyes and the nose is 10, the eyes and the mouth.
  • the step of scoring the avatar of each registered user of the communication application according to the scoring standard is implemented in an embodiment of the present invention in the following manner. Whenever a user is successfully registered, the avatar uploaded by the registered user is obtained, and then the face and the facial features in the avatar of the registered user are identified by facial recognition technology, and the data corresponding to each facial feature is counted. Then, according to the scoring standard and the data corresponding to each facial feature, the facial features of the face of the registered user are respectively scored, and finally the scores of the facial features of the face of the registered user's avatar are obtained. And, get the avatar score of the registered user.
  • the user may be prompted to upload the real avatar to the user to be registered. If the user to be registered wishes to be searched as "beauty" or "handsome", then the real avatar should be uploaded.
  • a prompt may be sent to the registered user to prompt the registered user. Update your avatar. If the registered user wants to be searched as "beauty” or "handsome", they can upload a well-dressed or designed photo as an avatar.
  • Step S13 The obtained personal data of each registered user and their avatar score are saved in the user database.
  • the user database can be saved in the memory 11.
  • Step S2 When searching for a pending user that matches the search condition from the user database, the avatar score of each pending user may also be obtained from the user database. If the search condition includes a gender setting, the pending users are all male or all female. If the gender setting is not included in the search condition, the pending user may have both a male and a female.
  • the to-be-determined users may be sorted according to the avatar score from high to low, and then the predetermined number of pending users ranked in front are filtered out as the target user, for example, before screening. Fifteen pending users are targeted users. The target user's avatar score is higher than that of other pending users, so the target user is more likely to be "handsome” or "beauty". Then, if the filtered target user is returned to the client, the current logged-in user of the client does not need to check the personal data of the pending user, and the target user who is more likely to be "handsome" or "beauty” can be obtained.
  • the target user in order to facilitate the current login user to view, the first time is sent.
  • the target user may first sort the avatar score according to the avatar score, and then return the sorted target user to the client for display.
  • the user search method of the embodiment sorts the pending users according to the avatar score from high to low after searching for the pending users that match the search condition, and the specified number is ranked in front.
  • the pending user is selected as the target user to return to the client, so that the current logged-in user of the client can be provided with a target user who is more likely to be "handsome” or "beauty", and the search efficiency of the target user can be improved, and Conducive to the expansion of the relationship chain in communication applications.
  • the user search method provided by the above embodiment after searching for a pending user that matches the search condition, the pending users are sorted according to the avatar score from highest to lowest, and the predetermined number of pending users are arranged in front.
  • the target user is more likely to be “handsome” or “beauty”.
  • the avatar score of the pending user to be searched is generally not high, the target user with a higher avatar score selected from the pending users may still not belong to the generally considered “handsome” or “beauty.” " , can only be regarded as a relatively better part of the pending user.
  • the embodiment of the present invention provides a user search method, and the steps S1 and S2 of the method are the same as the user search method provided in the foregoing embodiment, and details are not described herein again.
  • the method provided by the embodiment of the present invention is compared with the user search method of the foregoing embodiment, and the step S3 includes:
  • the first preset threshold may be a threshold value of a "beauty" or "handsome” avatar score obtained by a large number of sample statistics, for example, 80 points. If a registered user's avatar score exceeds the first preset threshold, the registered user is considered The user belongs to "beauty" or "handsome”. Therefore, in step S3, the pending user whose avatar score exceeds the first preset threshold may be selected as the target user, and the filtered target user is returned to the client.
  • the target user with the highest avatar score is found in the first time.
  • the target user may also be sorted according to the avatar score, and then the sorted target user is returned. Display to the client.
  • the user search method in this embodiment after searching for a pending user that matches the search condition, only selects the pending user whose avatar score exceeds the first preset threshold as the target user, thereby avoiding the avatar.
  • the target users whose avatar scores are relatively high are screened.
  • the target users searched for are more able to meet the search needs of the currently logged in users. If the pending user's avatar score does not exceed the first preset threshold, the target user is not returned to the client, thereby prompting the current logged-in user of the client to expand the search condition to search for the target user.
  • an embodiment of the present invention provides a user search apparatus 100, which is applicable to the foregoing server 1.
  • the user search device 100 includes a receiving module 101, a search module 102, and a selection module 103.
  • the receiving module 101 is configured to receive a user search request sent by a client of the communication application, and obtain a search condition from the user search request.
  • the search module 102 is configured to search for at least one pending user that matches the search condition from the user database, and obtain an avatar score of each pending user.
  • the screening module 103 is configured to filter at least one target user from the at least one pending user according to the avatar score of the pending user, and return the filtered target user to the client.
  • the screening module 103 may sort the pending users according to the avatar score from highest to lowest, and then filter the predetermined number of pending users that are listed in the front as the target user returns to the client. .
  • the selection module 103 may filter the pending users whose avatar score exceeds the first preset threshold as the target user returns to the client.
  • the screening module 103 may further sort the target users according to the avatar score, and then return the sorted target users to the client, so that the current logged-in user of the client can view.
  • the user search device 100 may further include a scoring module 104, as shown in FIG. 6B.
  • the scoring module 104 is configured to preset a set of scoring standards, score the avatar of each registered user of the communication application according to the scoring standard, and save the personal data of each registered user and its avatar score in the user database.
  • the scoring criteria include criteria for scoring facial features of a human face.
  • the scoring module 104 may identify a face and a facial feature in an avatar of each registered user of the communication application by using a facial recognition technology, and face the face of each registered user's avatar according to the scoring standard Feature scores to get the avatar score for each registered user.
  • the user search device 100 may further include a prompting module 105, as shown in FIG. 6C.
  • the prompting module 105 is configured to prompt the user to be registered to upload a real avatar when receiving the registration request of the user to be registered for the communication application.
  • the prompting module 105 is further configured to prompt the registered user to update the avatar when the avatar score of one of the registered users of the communication application is lower than the second preset threshold.
  • the user search method provided by the foregoing embodiment of the present invention may be further referred to, and is not repeated here.
  • modules in the foregoing embodiments of the present invention may be integrated into one or may be separately deployed; may be combined into one module, or may be further split into multiple sub-modules.
  • FIG. 7A is a hardware structural diagram of a user search apparatus 100 according to an embodiment of the present invention.
  • the user search device can include a port 71, a data processing unit 72, a processor 73, and a memory 74.
  • the data processing unit 72 forwards the data received from the port 71 to the processor 73 for processing, and forwards the data received from the processor 73 to the port 71 for forwarding.
  • the memory 74 stores a machine readable instruction module that is executable by the processor 73.
  • the machine readable instruction module includes: a receiving module 101a, a searching module 102a, and a selecting module 103a.
  • the receiving module 101a is configured to receive a user search request sent by a client of the communication application, and obtain a search condition from the user search request.
  • the searching module 102a is configured to search for at least one pending user that matches the search condition from the user database, and obtain an avatar score of each pending user.
  • the screening module 103a is configured to filter at least one target user from the at least one pending user according to the avatar score of the pending user, and return the filtered target user to the client.
  • the machine readable instruction module may further comprise a scoring module
  • the hardware structure diagram of the user search apparatus provided by the embodiment of the present invention may be as shown in FIG. 7B.
  • the modules in the foregoing embodiments of the present invention may be integrated into one or may be separately deployed; may be combined into one module, or may be further split into multiple sub-modules.
  • the user search device 100 of the present embodiment searches for the target user to be returned to the client according to the pending user's avatar score after searching for the pending user that matches the search condition, thereby It can improve the search efficiency of target users and facilitate the relationship chain expansion in communication applications.
  • Hardware modules or units in various embodiments of the invention may be implemented mechanically or electronically.
  • a hardware module can include specially designed permanent circuits or logic devices (such as dedicated processors such as FPGAs or ASICs) for performing specific operations.
  • the hardware modules may also include programmable logic devices or circuits (e.g., including general purpose processors or other programmable processors) that are temporarily configured by software for performing particular operations.
  • programmable logic devices or circuits e.g., including general purpose processors or other programmable processors
  • the hardware modules may also include programmable logic devices or circuits (e.g., including general purpose processors or other programmable processors) that are temporarily configured by software for performing particular operations.
  • programmable logic devices or circuits e.g., including general purpose processors or other programmable processors
  • temporarily configured circuits such as software configuration
  • the present invention can be implemented by means of software plus a necessary general hardware platform, that is, through the machine.
  • the readable instructions are used to instruct the associated hardware to implement, and of course hardware, but in many cases the former is a better implementation.
  • the technical solution of the present invention which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium, including a plurality of instructions for making a
  • the terminal device (which may be a cell phone, a personal computer, a server, or a network device, etc.) performs the methods described in various embodiments of the present invention.
  • the storage medium may be a magnetic disk, a optical disk, a read-only memory (ROM), or a random access memory (RAM).

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Library & Information Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

根据本发明实施例,一计算设备接收通讯应用的客户端发送的用户搜索请求,从所述用户搜索请求中获取搜索条件。所述计算设备从用户数据库中搜索出与所述搜索条件匹配的至少一个待定用户,并获取每个待定用户的头像得分。所述计算设备根据所述待定用户的头像得分从所述至少一个待定用户中筛选出至少一个目标用户,将筛选出的目标用户返回至所述客户端。

Description

一种用户搜索方法及装置 相关文件
本申请要求于 2013 年 10 月 12 日提交中国专利局、 申请号为 201310475633.3 , 发明名称为"一种用户搜索方法及装置"的中国专利申 请的优先权, 其全部内容通过引用结合在本申请中。
技术领域
本发明实施例涉及网络通讯技术领域, 特别涉及一种用户搜索方法 及装置。
发明背景 随着计算机技术和网络技术的发展, 各类通讯应用, 例如即时通讯 类应用、 社交类应用等已经逐步融入到了人们的日常生活中。 在通讯应 用中,用户搜索是一项基本功能。人们可以通过号码或昵称来搜索用户, 也可以按照地理位置来搜索用户, 例如搜索位于附近的用户等。 通常人 们在通过搜索功能搜索到符合搜索条件的陌生用户后, 会先查看该用户 的个人资料, 例如头像、 性别、 所在城市等, 并根据该个人资料进一步 考虑是否将该用户添加为联系人。 发明内容
本发明实施例提供一种用户搜索方法及装置,可以提高目标用户 的搜索效率, 并有利于通讯应用中的关系链拓展。
一种用户搜索方法, 包括以下步骤: 一计算设备接收通讯应用的 客户端发送的用户搜索请求, 从该用户搜索请求中获取搜索条件; 所 述计算设备从用户数据库中搜索出与该搜索条件匹配的至少一个待 定用户, 并获取每个待定用户的头像得分; 所述计算设备根据所述待 定用户的头像得分从所述至少一个待定用户中筛选出至少一个目标 用户, 将所筛选出的目标用户返回至该客户端。
一种用户搜索装置, 包括: 接收模块, 用于接收通讯应用的客户 端发送的用户搜索请求, 从该用户搜索请求中获取搜索条件; 搜索模 块,用于从用户数据库中搜索出与该搜索条件匹配的至少一个待定用 户, 并获取每个待定用户的头像得分; 筛选模块, 用于根据所述待定 用户的头像得分从所述至少一个待定用户中筛选出至少一个目标用 户, 将所筛选出的目标用户返回至该客户端。
本发明实施例提供的用户搜索方法及装置, 在搜索到与搜索条 件匹配的待定用户后,根据所述待定用户的头像得分从所述待定用户 中筛选出目标用户返回给客户端, 从而可以提高目标用户的搜索效 率, 并有利于通讯应用中的关系链拓展。
附图简要说明
以下附图为本发明技术方案的一些实施例, 本发明实施例并不局限 于图中示出的特征。 以下附图中, 相似的标号表示相似的元素:
图 1为本发明实施例提供的一种服务器的结构示意图; 图 2为本发明实施例提供的用户搜索方法应用时的环境示意图; 图 3为本发明实施例提供的用户搜索方法的流程图;
图 4为本发明实施例提供的用户数据库的建立方法的流程图; 图 5为本发明实施例提供的头像中人脸的面部特征示意图; 图 6 A为本发明实施例提供的用户搜索装置的结构示意图; 图 6B为本发明实施例提供的用户搜索装置的结构示意图; 图 6 C为本发明实施例提供的用户搜索装置的结构示意图; 图 7A为本发明实施例提供的用户搜索装置的硬件结构示意图; 图 7B为本发明实施例提供的用户搜索装置的硬件结构示意图。
实施本发明的方式 为了描述上的简洁和直观, 下文通过描述若干代表性的实施例来对 本发明的方案进行阐述。 实施例中大量的细节仅用于帮助理解本发明的 方案。 但是很明显, 本发明的技术方案实现时可以不局限于这些细节。 为了避免不必要地模糊了本发明的方案, 一些实施例没有进行细致地描 述, 而是仅给出了框架。 下文中, "包括" 是指 "包括但不限于", "根 据 ... ... " 是指 "至少根据 ... ..., 但不限于仅根据 ... ... "。 由于汉语的语 言习惯, 下文中没有特别指出一个成分的数量时, 意味着该成分可以是 一个也可以是多个, 或可理解为至少一个。
图 1示出了本发明实施例提供的一种计算设备的结构示意图。该 计算设备例如可以是服务器。 如图 1所示, 服务器 1包括一个或多个
(图中仅示出一个)存储器 11、 处理器 12、 存储控制器 13、 外设接 口 14、 通信模块 15、 输入单元 16及显示单元 17。 这些组件通过一 条或多条通讯总线 /信号线相互通讯。 本领域普通技术人员可以理解, 图 1所示的结构仅为示意, 其并 不对服务器 1的结构造成限定。 例如, 服务器 1还可包括比图 1所示 更多或者更少的组件, 或者具有与图 1所示不同的配置。 图 1所示的 各组件可以釆用硬件或软硬件组合实现。
存储器 11可用于存储机器可读指令以及指令模块, 如本发明实 施例中的用户搜索方法及装置对应的机器可读指令 /模块。 处理器 12 通过运行存储在存储器 11 内的机器可读指令以及指令模块, 从而执 行各种功能应用以及数据处理, 实现本发明实施例提供的用户搜索方 法及装置。
存储器 11可包括高速随机存储器, 还可包括非易失性存储器, 如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。 在一些实例中,存储器 11可进一步包括相对于处理器 12远程设置的 存储器, 这些远程设置的存储器可以通过网络连接至服务器 1。 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。处理器 12以及其他可能的组件对存储器 11的访问可在存 储控制器 13的控制下进行。
外设接口 14将各种输入 /输出装置耦合至处理器 12 以及存储器 11。 处理器 12运行存储器 11内的各种软件、 指令以及执行服务器 1 的各种功能以及进行数据处理。
通信模块 15用于与通信网络或者其他设备进行通信。 具体地, 通信模块 15例如可以是网卡。 网卡作为局域网中连接计算机和传输 介质的接口,用于实现与局域网传输介质之间的物理连接与电信号匹 配, 从而建立局域网并连接到因特网 (Internet ), 与各种网络如局域 网、 城域网、 广域网进行通信。 网卡可包括各种现有的用于执行上述 功能的电路元件, 例如处理器和存储器 (包括 ROM和 RAM ) 等。
输入单元 16可用于接收输入的字符信息, 以及产生与用户设置 以及功能控制有关的键盘、 鼠标、操作杆、光学或者轨迹球信号输入。 根据本发明实施例, 输入单元 16可包括按键 161以及触控表面 162。 按键 161例如可包括用于输入字符的字符按键,以及用于触发控制功 能的控制按键。 控制按键的实例包括 "返回主屏" 按键、 开机 /关机 按键、 拍照键等等。 触控表面 162可收集用户在其上或附近的触摸操 作 (比如用户使用手指、 触笔等任何适合的物体或附件在触控表面 162上或在触控表面 162附近的操作) , 并根据预先设定的程序驱动 相应的连接装置。 根据本发明实施例, 触控表面 162可包括触摸检测 装置和触摸控制器两个部分。 其中, 触摸检测装置检测用户的触摸方 位, 并检测触摸操作带来的信号, 将信号传送给触摸控制器; 触摸控 制器从触摸检测装置上接收触摸信息, 并将它转换成触点坐标, 再送 给处理器 12, 并能接收处理器 12发来的命令并加以执行。 根据本发 明实施例, 可以釆用电阻式、 电容式、 红外线以及表面声波等多种类 型实现触控表面 162。 除了触控表面 162, 输入单元 16还可以包括其 他输入设备。 上述的其他输入设备包括但不限于物理键盘、 轨迹球、 鼠标、 操作杆等中的一种或多种。
显示单元 17用于显示由用户输入的信息、 提供给用户的信息以 及服务器 1的各种图形用户接口。 这些图形用户接口可以由图形、 文 本、 图标、 视频和其任意组合来构成。 在一个实施例中, 显示单元 17包括一个显示面板 171。该显示面板 171例如可为一个液晶显示面 板 (Liquid Crystal Display, LCD)、 有机发光二极管 ( Organic Light-Emitting Diode Display , OLED ) 显示面板、 电;永显示面板 ( Electro-Phoretic Display, EPD ) 等。 根据本发明实施例, 触控表面 162可设置于显示面板 171上从而与显示面板 171构成一个整体。
参阅图 2所示,为本发明实施例提供的用户搜索方法应用时的环 境示意图。 在本实施例中, 该用户搜索方法应用于上述服务器 1中, 该服务器 1可以通过网络 2与终端 3进行网络通信。该服务器 1可以 包括一台或多台服务器, 当然该服务器 1也可以是虚拟云计算模组。 该终端 3的具体实例包括但并不限于台式计算机、 便携式计算机、 智 能手机、 平板电脑、 PDA ( Personal Digital Assistant, 个人数字助理) 或者其他类似的运算装置。 该网络 2可为任意的网络连接方式, 例如 互联网(Internet )、移动互联网(如电信运营商提供的 2G、 3G网络)、 局域网 (有线或者无线) 等。
在一个实施例中, 当人们通过搜索功能搜索到符合搜索条件的众多 陌生用户后, 若人们只是想从中找到长相更加符合一般审美标准的用 户, 如通常说的 "美女" 或 "帅哥", 并将其添加为联系人, 则需要逐 一查看这些用户的个人资料并进行排查, 使得目标用户的搜索效率较 低, 不利用通讯应用的关系链拓展。 参阅图 3所示, 本发明实施例提供一种用户搜索方法, 该用户搜 索方法包括以下步骤:
步骤 S l, 一计算设备, 如前述的服务器 1, 接收通讯应用的客户 端发送的用户搜索请求, 从该用户搜索请求中获取搜索条件;
步骤 S2, 该计算设备从用户数据库中搜索出与该搜索条件匹配 的至少一个待定用户, 并获取每个待定用户的头像得分;
步骤 S3, 该计算设备根据所述待定用户的头像得分从所述至少 一个待定用户中筛选出至少一个目标用户,将所筛选出的目标用户返 回至该客户端。
按照上述的用户搜索方法,在搜索到与搜索条件匹配的待定用户 后,根据所述待定用户的头像得分从所述待定用户中筛选出目标用户 返回给客户端, 从而可以提高目标用户的搜索效率, 并有利于通讯应 用中的关系链拓展。
在一些实施例中, 上述方法的各步骤的实现细节如下。
步骤 S 1所述的通讯应用包括即时通讯类应用和社交类应用, 该 即时通讯类应用例如包括 QQ、 微信等, 该社交类应用例如包括 QQ 空间、 朋友网、 微博等。 根据本发明实施例, 该通讯应用被架设在上 述服务器 1中, 而所述通讯应用的客户端则安装并运行于所述终端 3 中。 根据本发明实施例, 在步骤 S 1之前该方法还可包括该通讯应用 的客户端的当前登录用户登录该通讯应用的过程, 包括: 该当前登录 用户向该通讯应用的客户端输入登录账号, 根据本发明实施例, 该登 录账号可以包括预先申请的用户名及密码;通讯应用的客户端将该登 录账号送至服务器 1验证其有效性; 当服务器 1验证该登录账号有效 时, 该当前登录用户成功登录该通讯应用, 从而可以在该通讯应用的 客户端中执行用户搜索操作, 例如输入搜索条件、 点击搜索选项等。
根据本发明实施例,通讯应用的客户端根据当前登录用户的该用 户搜索操作向服务器 1发出所述用户搜索请求。该用户搜索请求中包 括搜索条件, 该搜索条件例如包括所需目标用户的性别、 所在城市、 年龄、 院校、 工作单位等。 然后, 在步骤 S 1中接收该用户搜索请求, 并从该用户搜索请求中获取该搜索条件。
在步骤 S2中, 从用户数据库中搜索出与该搜索条件匹配的待定 用户。所述用户数据库用于记录通讯应用的所有已注册用户的个人资 料, 例如性别、 头像、 所在城市、 年龄、 院校、 工作单位等。 因此, 该待定用户也属于通讯应用的已注册用户。该已注册用户是指向通讯 应用申请注册并获得有效的登录账号的用户。在用户向通讯应用申请 注册时, 将会上传所述的个人资料。 因此, 所述通讯应用的所有已注 册用户的个人资料都会保存在所述用户数据库中。 此外, 该用户数据 库中还记录有每个已注册用户的头像得分。
根据本发明实施例, 参阅图 4所示, 该用户数据库的建立过程, 包括如下步骤:
步骤 Sl l, 预设一套打分标准, 用于为每个已注册用户的头像打 分。 该打分标准包括针对人脸的面部特征打分的标准。 该人脸的面部 特征例如包括五官的大小、 五官跟面部的比例、 目艮睛之间的距离、 眼 睛和鼻子之间的距离、 眼睛和眉毛的距离等。 该打分标准可以根据大 量的样本设定。
例如, 先收集大量被人们普遍认为属于 "美女" 的女性头像, 以 及属于 "帅哥" 的男性头像, 然后对所收集的女性头像及男性头像的 面部特征分别进行平均统计,得到女性头像对应的各个面部特征的标 准数据, 以及男性头像对应的各个面部特征的标准数据。 例如, 女性 头像的眼睛之间距离的标准数据为 d, 男性头像的眼睛之间距离的标 准数据为 D。 一个面部特征的标准数据对应该面部特征的分值为满 分, 例如 10分。
然后, 根据得到的女性头像对应的各个面部特征的标准数据, 以 及男性头像对应的各个面部特征的标准数据,设定针对人脸的面部特 征打分的标准。 例如, 若女性头像的眼睛之间距离的标准数据为 d, 对应满分 10, 则若眼睛之间的距离每比该标准数据 d小一个单位距 离或大一个单位距离, 例如 d/100, 则从该满分 10中减去 0.5分。
步骤 S12, 根据该打分标准对所述通讯应用的每个已注册用户的 头像打分。 根据本发明实施例, 可以通过面部识别技术识别所述通讯 应用的每个已注册用户的头像中的人脸及其面部特征,并统计出各面 部特征对应的数据。 例如图 5所示, 可以以像素为单位分别计算所识 别的人脸中眼睛大小、 鼻子大小、 嘴大小, 以及眼睛、 鼻子、 嘴巴之 间的距离 (包括眼睛与鼻子之间的距离, 眼睛与嘴巴之间的距离, 以 及鼻子与嘴巴之间的距离)等。 当然, 该已注册用户所上传的头像可 能是自己的真实头像, 也可能为明星照、 卡通画等虚拟头像。 因此, 若通过面部识别技术无法识别出该头像中存在人脸,则认为该头像为 虚拟头像, 直接为该头像打分为 0。
然后,根据该打分标准和统计出的每个已注册用户的头像中的人 脸的各面部特征对应的数据,对每个已注册用户的头像中人脸的面部 特征分别打分,最后将已注册用户的头像中人脸的各面部特征的得分 求和, 得到已注册用户的头像得分。 例如, 若某个已注册用户的头像 中人脸的面部特征包括 6个,分别为眼睛大小、鼻子大小、嘴巴大小, 以及眼睛、 鼻子、 嘴巴之间的距离等。 根据该打分标准, 该眼睛大小 的面部特征得分为 8, 鼻子大小的面部特征得分为 7, 嘴巴大小的面 部特征得分为 9, 眼睛与鼻子之间距离的面部特征得分为 10, 眼睛与 嘴巴之间距离的面部特征得分为 6, 鼻子与嘴巴之间距离的面部特征 得分为 5, 则该已注册用户的头像得分为 (8+7+9+10+6+5 = ) 45分。
上述根据该打分标准对所述通讯应用的每个已注册用户的头像 打分的步骤, 在本发明一个实施例中可按照下述方式实现。 每当一个 用户注册成功时, 就获取该已注册用户所上传的头像, 然后通过面部 识别技术识别该已注册用户的头像中的人脸及其面部特征,并统计出 各面部特征对应的数据。 然后, 根据该打分标准和统计出的各面部特 征对应的数据对该已注册用户的头像中人脸的面部特征分别打分,最 后将该已注册用户的头像中人脸的各面部特征的得分求和,得到该已 注册用户的头像得分。 此外, 为了加强趣味性和互动性, 提高参与度, 当接收到待注册 用户的对该通讯应用的注册请求时, 还可以向该待注册用户下发提 示, 提示待注册用户上传其真实头像。 若待注册用户希望自己被当作 "美女" 或 "帅哥" 被搜索出来, 则应当上传真实头像。 根据本发明 实施例, 当所述通讯应用的某一个已注册用户的头像得分低于一个预 设阔值, 例如 40分时, 则还可以向该已注册用户下发提示, 提示该 已注册用户更新头像。若该已注册用户希望自己被当作"美女"或"帅 哥"被搜索出来, 则可以上传一张经过精心打扮或设计的照片作为头 像。
步骤 S 13, 将得到的每个已注册用户的个人资料及其头像得分保 存在所述用户数据库中。该用户数据库可以保存在所述存储器 11中。 步骤 S2在从该用户数据库中搜索出与所述搜索条件匹配的待定用户 时, 还可以从该用户数据库中获取每个待定用户的头像得分。 若该搜 索条件中包括性别设定, 则该待定用户全部为男性或全部为女性。 若 该搜索条件中不包括性别设定, 则该待定用户中可以既有男性, 也有 女性。
在步骤 S3, 根据本发明实施例, 可以将所述待定用户按照头像 得分从高到低的顺序进行排序,然后将排在前面的指定数量的待定用 户筛选出来作为所述目标用户,例如筛选出前十五个待定用户作为目 标用户。所筛选出来的目标用户的头像得分相较于其它待定用户的头 像得分较高, 因此所述的目标用户更可能为 "帅哥" 或 "美女" 。 然 后, 将所筛选出的目标用户返回至该客户端, 则该客户端的当前登录 用户不需要再通过排查待定用户的个人资料, 就能得到更可能为 "帅 哥" 或 "美女" 的目标用户。
根据本发明实施例, 为了便于该当前登录用户查看, 第一时间发 现头像得分最高的目标用户, 步骤 S3中还可以先将所述目标用户按 照头像得分进行排序,然后将排序后的目标用户返回至该客户端进行 显示。
综上所述, 本实施例的用户搜索方法, 在搜索到与搜索条件匹配 的待定用户后,将所述待定用户按照头像得分从高到低的顺序进行排 序,并将排在前面的指定数量的待定用户 选出来作为所述目标用户 返回至客户端,从而可以为该客户端的当前登录用户提供更有可能是 "帅哥" 或 "美女" 的目标用户, 可以提高目标用户的搜索效率, 并 有利于通讯应用中的关系链拓展。 根据上述实施例提供的用户搜索方法,在搜索到与搜索条件匹配 的待定用户后,将所述待定用户按照头像得分从高到低的顺序进行排 序, 并将排在前面的指定数量的待定用户筛选出来作为目标用户, 这 样, 该目标用户更有可能是 "帅哥" 或 "美女" 。 根据本发明另一实 施例, 若搜索得到的待定用户的头像得分普遍都不高, 则从待定用户 中筛选出的头像得分较高的目标用户可能依然不属于普遍认为的 "帅 哥" 或 "美女" , 只能算待定用户中长相相对较佳的一部分。
有鉴于此, 本发明实施例提供一种用户搜索方法, 该方法的步骤 S 1和 S2与前述实施例提供的用户搜索方法相同, 在此不再赘述。 本 发明实施例提供的方法相较于前述实施例的用户搜索方法,所述步骤 S3包括:
将头像得分超过第一预设阔值的待定用户 选出来作为所述目 标用户。 根据本发明实施例, 该第一预设阔值可以是经过大量样本统 计得到的认为属于 "美女" 或 "帅哥" 头像得分临界值, 例如 80分。 若某一已注册用户的头像得分超过该第一预设阔值,则认为该已注册 用户属于 "美女" 或 "帅哥" 。 因此, 步骤 S3中可以将头像得分超 过第一预设阔值的待定用户筛选出来作为所述目标用户,并将所筛选 出的目标用户返回至该客户端。
根据本发明实施例, 为了便于该当前登录用户查看, 第一时间发 现头像得分最高的目标用户, 步骤 S3中也可以先将所述目标用户按 照头像得分进行排序,然后将排序后的目标用户返回至该客户端进行 显示。
综上所述, 本实施例的用户搜索方法, 由于在搜索到与搜索条件 匹配的待定用户后,只将头像得分超过第一预设阔值的待定用户筛选 出来作为目标用户,避免了在头像得分普遍不高的待定用户中筛选头 像得分相对较高的目标用户的情况。所搜索出的目标用户更加能满足 当前登录用户的搜索需求。若待定用户的头像得分都未超过该第一预 设阔值, 则不返回目标用户至客户端, 从而提示客户端的当前登录用 户扩展搜索条件以便于搜索出目标用户。 参阅图 6A所示, 本发明实施例提供一种用户搜索装置 100, 该 用户搜索装置 100可应用于前述服务器 1中。 如图 6A所示, 该用户 搜索装置 100包括接收模块 101、 搜索模块 102和 选模块 103。
接收模块 101用于接收通讯应用的客户端发送的用户搜索请求, 从该用户搜索请求中获取搜索条件。
搜索模块 102 用于从用户数据库中搜索出与该搜索条件匹配的 至少一个待定用户, 并获取每个待定用户的头像得分。
筛选模块 103 用于根据所述待定用户的头像得分从所述至少一 个待定用户中筛选出至少一个目标用户,将所筛选出的目标用户返回 至该客户端。 在一个实施例中, 筛选模块 103可以将所述待定用户按照头像得 分从高到低的顺序进行排序,然后将排在前面的指定数量的待定用户 筛选出来作为所述目标用户返回至该客户端。
在另一个实施例中, 选模块 103可以将头像得分超过第一预设 阔值的待定用户筛选出来作为所述目标用户返回至该客户端。
在一个实施例中, 筛选模块 103还可以将所述目标用户按照头像 得分进行排序, 然后将排序后的目标用户返回至该客户端, 方便该客 户端的当前登录用户查看。
根据本发明实施例,该用户搜索装置 100还可包括打分模块 104, 如图 6B所示。
打分模块 104用于预设一套打分标准,根据该打分标准对通讯应 用的每个已注册用户的头像打分,并将每个已注册用户的个人资料及 其头像得分保存在所述用户数据库中。所述打分标准包括针对人脸的 面部特征打分的标准。
所述打分模块 104 可以通过面部识别技术识别所述通讯应用的 每个已注册用户的头像中的人脸及其面部特征,并根据该打分标准对 每个已注册用户的头像中人脸的面部特征打分,从而得到每个已注册 用户的头像得分。
根据本发明实施例,该用户搜索装置 100还可包括提示模块 105, 如图 6C所示。
提示模块 105 用于当接收到待注册用户对该通讯应用的注册请 求时, 提示该待注册用户上传真实头像。
根据本发明实施例,所述提示模块 105还用于当所述通讯应用的 某一个已注册用户的头像得分低于第二预设阔值时,提示该已注册用 户更新头像。 对于以上各模块的具体工作过程,可进一步参考本发明前述实施 例提供的用户搜索方法, 在此不再重复。
上述本发明实施例中的模块可以集成于一体, 也可以分离部署; 可以合并为一个模块, 也可以进一步拆分成多个子模块。
上述本发明实施例中的各个模块可以由软件实现(例如存储在计 算机可读取介质中的由处理器执行的机器可读指令), 也可以由硬件 实现 (例如专用集成电路 ( Application Specific Integrated Circuit, ASIC ) 的处理器) , 或者由软件和硬件的结合实现, 本发明实施例 不作具体限定。 图 7A是本发明实施例提供的用户搜索装置 100的硬件结构图。 如图 7A所示, 该用户搜索装置可包括端口 71, 数据处理单元 72, 处理器 73, 以及存储器 74。 其中, 所述数据处理单元 72将从所述端 口 71接收的数据转发至所述处理器 73进行处理, 以及, 将从所述处 理器 73接收的数据转发至所述端口 71进行转发。 所述存储器 74存 储有机器可读指令模块, 所述机器可读指令模块可被所述处理器 73 执行。 其中, 所述机器可读指令模块包括: 接收模块 101a、 搜索模 块 102a和 选模块 103a。
接收模块 101a 用于接收通讯应用的客户端发送的用户搜索请 求, 从该用户搜索请求中获取搜索条件。
搜索模块 102a用于从用户数据库中搜索出与该搜索条件匹配的 至少一个待定用户, 并获取每个待定用户的头像得分。
筛选模块 103a用于根据所述待定用户的头像得分从所述至少一 个待定用户中筛选出至少一个目标用户,将所筛选出的目标用户返回 至该客户端。 根据本发明实施例, 所述机器可读指令模块还可包括打分模块
104a和提示模块 105a。
上述本发明实施例各模块的详细功能可参照前述方法实施例及 装置实施例中的接收模块 101、 搜索模块 102、 选模块 103、 打分 模块 104和提示模块 105的相关描述, 本发明实施例在此不再赘述。
基于以上描述,本发明实施例提供的用户搜索装置的硬件结构图 可:^图 7B所示。
上述本发明实施例中的模块可以集成于一体, 也可以分离部署; 可以合并为一个模块, 也可以进一步拆分成多个子模块。 综上所述, 本实施例的用户搜索装置 100, 在搜索到与搜索条件 匹配的待定用户后,根据所述待定用户的头像得分从所述待定用户中 筛选出目标用户返回给客户端, 从而可以提高目标用户的搜索效率, 并有利于通讯应用中的关系链拓展。 本发明各实施方式中的硬件模块或单元可以以机械方式或电子 方式实现。 例如, 一个硬件模块可以包括专门设计的永久性电路或逻 辑器件 (如专用处理器, 如 FPGA或 ASIC ) 用于完成特定的操作。 硬件模块也可以包括由软件临时配置的可编程逻辑器件或电路(如包 括通用处理器或其它可编程处理器)用于执行特定操作。 至于具体釆 用机械方式, 或是釆用专用的永久性电路, 或是釆用临时配置的电路 (如由软件进行配置)来实现硬件模块, 可以根据成本和时间上的考 虑来决定。
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 到本发明可借助软件加必需的通用硬件平台的方式来实现,即通过机 器可读指令来指令相关的硬件来实现, 当然也可以通过硬件, 但很多 情况下前者是更佳的实施方式。 基于这样的理解, 本发明的技术方案 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, 该计算机软件产品存储在一个存储介质中, 包括若干指令用 以使得一台终端设备(可以是手机, 个人计算机, 服务器, 或者网络 设备等)执行本发明各个实施例所述的方法。
本领域普通技术人员可以理解实现上述实施例方法中的全部或 部分流程, 是可以通过计算机程序来指令相关的硬件来完成, 所述的 程序可存储于一计算机可读取存储介质中, 该程序在执行时, 可包括 如上述各方法的实施例的流程。 其中, 所述的存储介质可为磁碟、 光 盘、 只读存储记忆体 (Read-Only Memory, ROM ) 或随机存储记忆 体 ( Random Access Memory, RAM ) 等。
需要说明的是,上述各流程和各结构图中不是所有的步骤和模块 都是必须的, 可以根据实际的需要忽略某些步骤或模块。 各步骤的执 行顺序不是固定的, 可以根据需要进行调整。 本领域技术人员可以理 解实施例中的装置中的模块可以按照实施例描述进行分布于实施例 的装置中,也可以进行相应变化位于不同于本实施例的一个或多个装 置中。 上述实施例的模块可以合并为一个模块, 也可以进一步拆分成 多个子模块。各模块的划分仅仅是为了便于描述而釆用的功能上的划 分, 实际实现时, 一个模块可以由多个模块实现, 多个模块的功能也 可以由同一个模块实现, 这些模块可以位于同一个设备中, 也可以位 于不同的设备中。
以上所述为本发明的实施例, 并不用以限制本发明, 凡在本发明 的精神和原则之内, 所作的任何修改、 等同替换、 改进等, 均应包含 在本发明的保护范围之内。 综上所述, 权利要求的范围不应局限于以 上描述的例子中的实施方式,而应当将说明书作为一个整体并给予最 宽泛的解释。

Claims

权利要求书
1. 一种用户搜索方法, 其特征在于, 该方法包括:
一计算设备接收通讯应用的客户端发送的用户搜索请求,从所述 用户搜索请求中获取搜索条件;
所述计算设备从用户数据库中搜索出与所述搜索条件匹配的至 少一个待定用户, 并获取每个待定用户的头像得分;
所述计算设备根据所述待定用户的头像得分从所述至少一个待 定用户中筛选出至少一个目标用户,将筛选出的目标用户返回至所述 客户端。
2. 如权利要求 1所述的用户搜索方法, 其特征在于, 还包括: 预设一套打分标准;
根据所述打分标准对所述通讯应用的每个已注册用户的头像打 分;
将所述每个已注册用户的个人资料及其头像得分保存在所述用 户数据库中。
3. 如权利要求 2 所述的用户搜索方法, 其特征在于, 所述打分 标准包括针对人脸的面部特征打分的标准。
4. 如权利要求 3 所述的用户搜索方法, 其特征在于, 所述根据 所述打分标准对所述通讯应用的每个已注册用户的头像打分的步骤 包括:
识别所述通讯应用的每个已注册用户的头像中的人脸及所述人 脸的面部特征;
根据所述打分标准对所述每个已注册用户的头像中人脸的面部 特征打分, 得到所述每个已注册用户的头像得分。
5. 如权利要求 1 所述的用户搜索方法, 其特征在于, 所述根据 所述待定用户的头像得分从所述至少一个待定用户中筛选出至少一 个目标用户的步骤包括:
将所述待定用户按照头像得分从高到低的顺序进行排序; 将排在前面的指定数量的待定用户筛选出来作为所述目标用户。
6. 如权利要求 1 所述的用户搜索方法, 其特征在于, 所述根据 所述待定用户的头像得分从所述至少一个待定用户中筛选出至少一 个目标用户的步骤包括:
将头像得分超过第一预设阔值的待定用户 选出来作为所述目 标用户。
7. 如权利要求 5或 6所述的用户搜索方法, 其特征在于, 所述 将筛选出的目标用户返回至所述客户端的步骤包括:
将所述目标用户按照头像得分进行排序;
将排序后的目标用户返回至所述客户端。
8. 如权利要求 1所述的用户搜索方法, 其特征在于, 还包括: 当接收到待注册用户对该通讯应用的注册请求时,提示该待注册 用户上传真实头像。
9. 如权利要求 1所述的用户搜索方法, 其特征在于, 还包括: 当所述通讯应用的某一个已注册用户的头像得分低于预设阔值 时, 提示该已注册用户更新头像。
10. 一种用户搜索装置, 其特征在于, 该装置包括:
接收模块, 用于接收通讯应用的客户端发送的用户搜索请求, 从 所述用户搜索请求中获取搜索条件;
搜索模块,用于从用户数据库中搜索出与所述搜索条件匹配的至 少一个待定用户, 并获取每个待定用户的头像得分;
筛选模块,用于根据所述待定用户的头像得分从所述至少一个待 定用户中筛选出至少一个目标用户,将筛选出的目标用户返回至所述 客户端。
11. 如权利要求 10 所述的用户搜索装置, 其特征在于, 还包括 打分模块, 用于:
预设一套打分标准;
根据所述打分标准对所述通讯应用的每个已注册用户的头像打 分;
将所述每个已注册用户的个人资料及其头像得分保存在所述用 户数据库中。
12. 如权利要求 11 所述的用户搜索装置, 其特征在于, 所述打 分标准包括针对人脸的面部特征打分的标准。
13. 如权利要求 12 所述的用户搜索装置, 其特征在于, 所述打 分模块还用于:
识别所述通讯应用的每个已注册用户的头像中的人脸及所述人 脸的面部特征;
根据所述打分标准对所述每个已注册用户的头像中人脸的面部 特征打分, 得到所述每个已注册用户的头像得分。
14. 如权利要求 10 所述的用户搜索装置, 其特征在于, 所述筛 选模块还用于:
将所述待定用户按照头像得分从高到低的顺序进行排序; 将排在前面的指定数量的待定用户筛选出来作为所述目标用户。
15. 如权利要求 10 所述的用户搜索装置, 其特征在于, 所述筛 选模块还用于:
将头像得分超过第一预设阔值的待定用户 选出来作为所述目 标用户。
16. 如权利要求 14或 15所述的用户搜索装置, 其特征在于, 所 述筛选模块还用于:
将所述目标用户按照头像得分进行排序;
将排序后的目标用户返回至所述客户端。
17. 如权利要求 10 所述的用户搜索装置, 其特征在于, 还包括 提示模块, 用于:
当接收到待注册用户对该通讯应用的注册请求时,提示该待注册 用户上传真实头像。
18. 如权利要求 10 所述的用户搜索装置, 其特征在于, 还包括 提示模块, 用于:
当所述通讯应用的某一个已注册用户的头像得分低于预设阔值 时, 提示该已注册用户更新头像。
PCT/CN2014/081936 2013-10-12 2014-07-10 一种用户搜索方法及装置 WO2015051657A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201310475633.3A CN104572654A (zh) 2013-10-12 2013-10-12 一种用户搜索方法及装置
CN201310475633.3 2013-10-12

Publications (1)

Publication Number Publication Date
WO2015051657A1 true WO2015051657A1 (zh) 2015-04-16

Family

ID=52812502

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/081936 WO2015051657A1 (zh) 2013-10-12 2014-07-10 一种用户搜索方法及装置

Country Status (2)

Country Link
CN (1) CN104572654A (zh)
WO (1) WO2015051657A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109246218A (zh) * 2018-09-14 2019-01-18 贵州微讯云信息技术服务有限公司 一种基于微信公众平台的公众号及资讯分类搜索系统及搜索方法
CN111767840A (zh) * 2020-06-29 2020-10-13 北京百度网讯科技有限公司 用于验证图像的方法、装置、电子设备及计算机可读存储介质

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107020248B (zh) * 2016-02-02 2019-02-15 济南兰光机电技术有限公司 一种包装检测方法的自动筛选方法及系统
WO2018072151A1 (zh) * 2016-10-19 2018-04-26 深圳市大疆创新科技有限公司 控制方法、控制装置及电子装置
CN106778925B (zh) * 2016-11-03 2021-10-08 五邑大学 一种人脸识别的姿态超完备人脸自动注册方法及其装置
CN107391382B (zh) * 2017-08-08 2020-11-20 北京云测信息技术有限公司 一种目标搜索方法和装置
CN108985881A (zh) * 2018-06-22 2018-12-11 平安科技(深圳)有限公司 合租室友推荐方法、装置及计算机可读存储介质、服务器
RU2739873C2 (ru) * 2019-02-07 2020-12-29 Акционерное общество "Лаборатория Касперского" Способ поиска пользователей, соответствующих требованиям

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100169376A1 (en) * 2008-12-29 2010-07-01 Yahoo! Inc. Visual search engine for personal dating
CN101847144A (zh) * 2009-03-27 2010-09-29 上海薇艾信息科技有限公司 一种网络交友中的肖像处理方法
CN102035891A (zh) * 2010-12-17 2011-04-27 百度在线网络技术(北京)有限公司 一种网络交友平台中推荐好友的方法和装置
CN103020276A (zh) * 2012-12-27 2013-04-03 新浪网技术(中国)有限公司 一种社交对象搜索方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100169376A1 (en) * 2008-12-29 2010-07-01 Yahoo! Inc. Visual search engine for personal dating
CN101847144A (zh) * 2009-03-27 2010-09-29 上海薇艾信息科技有限公司 一种网络交友中的肖像处理方法
CN102035891A (zh) * 2010-12-17 2011-04-27 百度在线网络技术(北京)有限公司 一种网络交友平台中推荐好友的方法和装置
CN103020276A (zh) * 2012-12-27 2013-04-03 新浪网技术(中国)有限公司 一种社交对象搜索方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109246218A (zh) * 2018-09-14 2019-01-18 贵州微讯云信息技术服务有限公司 一种基于微信公众平台的公众号及资讯分类搜索系统及搜索方法
CN111767840A (zh) * 2020-06-29 2020-10-13 北京百度网讯科技有限公司 用于验证图像的方法、装置、电子设备及计算机可读存储介质

Also Published As

Publication number Publication date
CN104572654A (zh) 2015-04-29

Similar Documents

Publication Publication Date Title
WO2015051657A1 (zh) 一种用户搜索方法及装置
JP6431119B2 (ja) 携帯式端末設備における摺接操作による入力補助制御のシステム及び方法
US10068130B2 (en) Methods and devices for querying and obtaining user identification
CN104685494B (zh) 文本辨识驱动的功能
WO2018192406A1 (zh) 身份验证方法及装置、存储介质
US11290447B2 (en) Face verification method and device
WO2016155331A1 (zh) 一种基于穿戴设备的信息传递方法及相关设备
US10769253B2 (en) Method and device for realizing verification code
JP6986187B2 (ja) 人物識別方法、装置、電子デバイス、記憶媒体、及びプログラム
US8799798B2 (en) Method and system for handwriting-based launch of an application
US20170177728A1 (en) Mention suggestion, and information processing methods and systems
JP2015522877A (ja) 画像認識のための適応閾値処理
WO2015165283A1 (en) Photo check-in method, apparatus, and system
WO2019153860A1 (zh) 信息交互方法和装置、存储介质及电子装置
TW201303752A (zh) 基於擴增實境與雲端計算之應用程式執行方法與系統
CN110555171B (zh) 一种信息处理方法、装置、存储介质及系统
WO2016085696A1 (en) Tab based browser content sharing
WO2015003606A1 (en) Method and apparatus for recognizing pornographic image
CN102833182A (zh) 即时通信中进行人脸识别的方法、客户端及系统
WO2022000959A1 (zh) 人机验证方法、装置、设备及存储介质
CN104123344B (zh) 基于搜索结果来生成待提醒事项的方法和装置
US20190096130A1 (en) Virtual mobile terminal implementing system in mixed reality and control method thereof
CN106777071B (zh) 一种图像识别获取参考信息的方法和装置
WO2020114123A1 (zh) 指纹解锁方法及相关装置
US9465534B2 (en) Method for automatic computerized process control, and computerized system implementing the same

Legal Events

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

Ref document number: 14852426

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 14852426

Country of ref document: EP

Kind code of ref document: A1