WO2019056501A1 - 个性化Wi-Fi热点推送方法、装置及存储介质 - Google Patents

个性化Wi-Fi热点推送方法、装置及存储介质 Download PDF

Info

Publication number
WO2019056501A1
WO2019056501A1 PCT/CN2017/108798 CN2017108798W WO2019056501A1 WO 2019056501 A1 WO2019056501 A1 WO 2019056501A1 CN 2017108798 W CN2017108798 W CN 2017108798W WO 2019056501 A1 WO2019056501 A1 WO 2019056501A1
Authority
WO
WIPO (PCT)
Prior art keywords
hotspots
user
hotspot
historical
ranked
Prior art date
Application number
PCT/CN2017/108798
Other languages
English (en)
French (fr)
Inventor
金新
王建明
肖京
Original Assignee
平安科技(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 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2019056501A1 publication Critical patent/WO2019056501A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W48/00Access restriction; Network selection; Access point selection
    • H04W48/08Access restriction or access information delivery, e.g. discovery data delivery
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W48/00Access restriction; Network selection; Access point selection
    • H04W48/16Discovering, processing access restriction or access information

Definitions

  • the present application relates to the field of computer technologies, and in particular, to a personalized Wi-Fi hotspot pushing method, an electronic device, and a computer readable storage medium.
  • the scanned wireless Wi-Fi hotspot is displayed in the wireless local area network interface, and the user can manually connect the scanned Wi-Fi hotspot. If there is a connected Wi-Fi in the scanned hot spot Hotspots, the system can automatically connect to the Wi-Fi hotspot.
  • Wi-Fi hotspots usually have a connection password to prevent the network and ensure communication security. In the Wi-Fi hotspot connection process, a password is required for a Wi-Fi hotspot with a password.
  • Wi-Fi hotspots there may be free Wi-Fi hotspots in the scanned Wi-Fi hotspot list, such as: operator Wi-Fi hotspot (China Mobile, China Telecom, China Unicom), public Wi-Fi, merchant Wi -Fi hotspots, etc. Users can choose to connect to the free Wi-Fi hotspots that are scanned.
  • the Wi-Fi hotspots that cause the connection are usually not optimal, which affects the user's online experience.
  • Wi-Fi hotspots and users' attributes are incomplete and difficult to collect, how to use limited data, mine and construct features, and intelligently select the best Wi-Fi hotspots for different users is a very valuable and urgent treatment. solved problem.
  • the present application provides a personalized Wi-Fi hotspot pushing method, an electronic device, and a computer readable storage medium, the main purpose of which is to push an optimal Wi-Fi hotspot to a user by using Wi-Fi hotspots and historical data of the user.
  • a personalized Wi-Fi hotspot pushing method for pushing an optimal Wi-Fi hotspot to a user by using Wi-Fi hotspots and historical data of the user.
  • the present application provides an electronic device, including: a memory, a processor, and a personalized Wi-Fi hotspot pushing program stored on the memory, where the pushing program is executed by the processor as follows step:
  • Receiving step receiving multiple available Wi-Fi hotspots scanned by the client;
  • a scoring step scoring each of the plurality of Wi-Fi hotspots according to historical data of the plurality of Wi-Fi hotspots in the first preset time period by using a predetermined random forest model;
  • the determining step determining the user feature according to the predetermined user image data
  • a sorting step sorting the plurality of Wi-Fi hotspots according to signal strength, score, and user characteristics of the plurality of Wi-Fi hotspots;
  • Push step Recommend the user to the highest ranked Wi-Fi hotspot for users to connect.
  • the step of scoring further comprises:
  • a Wi-Fi hotspot with no historical data among the plurality of Wi-Fi hotspots is given a default score or an average score assigned to other Wi-Fi hotspots.
  • the sorting step comprises:
  • Two or more Wi-Fi hotspots with historical users that match the current user characteristics are sorted according to the score of the Wi-Fi hotspot, and the Wi-Fi hotspots with high scores are ranked first.
  • the pushing step further comprises:
  • the present application further provides a personalized Wi-Fi hotspot pushing method, where the method includes:
  • Receiving step receiving multiple available Wi-Fi hotspots scanned by the client;
  • a scoring step scoring each of the plurality of Wi-Fi hotspots according to historical data of the plurality of Wi-Fi hotspots in the first preset time period by using a predetermined random forest model;
  • the determining step determining the user feature according to the predetermined user image data
  • a sorting step sorting the plurality of Wi-Fi hotspots according to signal strength, score, and user characteristics of the plurality of Wi-Fi hotspots;
  • Push step Recommend the user to the highest ranked Wi-Fi hotspot for users to connect.
  • the step of scoring further comprises:
  • a Wi-Fi hotspot with no historical data among the plurality of Wi-Fi hotspots is given a default score or an average score assigned to other Wi-Fi hotspots.
  • the sorting step comprises:
  • Two or more Wi-Fi hotspots with historical users that match the current user characteristics are sorted according to the score of the Wi-Fi hotspot, and the Wi-Fi hotspots with high scores are ranked first.
  • the pushing step further comprises:
  • the present application further provides a computer readable storage medium, A personalized Wi-Fi hotspot push program is stored on the computer readable storage medium, the push program being executed by the processor to implement the steps of the personalized Wi-Fi hotspot push method as described above.
  • the personalized Wi-Fi hotspot pushing method, the electronic device and the computer readable storage medium proposed by the present application calculate the probability that the Wi-Fi hotspot may be successfully connected in the future by obtaining the Wi-Fi hotspot and the user attribute, and determine the user characteristics, and then sequentially The Wi-Fi hotspots are sorted according to the Wi-Fi hotspot signal strength, user characteristics, and scoring scores. Finally, the user is recommended to sort the Wi-Fi hotspots for the user to refer to, which effectively improves the user's online experience.
  • FIG. 1 is a schematic diagram of a preferred embodiment of an electronic device of the present application.
  • FIG. 2 is a block diagram of a personalized Wi-Fi hotspot push procedure in FIG. 1;
  • FIG. 3 is a flowchart of a first embodiment of a personalized Wi-Fi hotspot pushing method according to the present application
  • FIG. 4 is a schematic diagram of a refinement process of the step S50 of the personalized Wi-Fi hotspot pushing method of the present application.
  • the application provides an electronic device 1 .
  • FIG. 1 it is a schematic diagram of a preferred embodiment of the electronic device 1 of the present application.
  • the electronic device 1 includes a memory 11, a processor 12, a network interface 13, and a communication bus 14.
  • the communication bus 14 is used to implement connection communication between these components.
  • the network interface 13 may include a standard wired interface, a wireless interface (such as a WI-FI interface). Usually used to connect to the client (not shown in Figure 1).
  • the electronic device 1 can connect to the database through the network interface 13, and perform data transmission with the database.
  • the database includes recent Wi-Fi hotspots collected by the client and historical data of the users.
  • the client can be a terminal device with a wireless LAN configuration such as a notebook, a tablet, a smart phone, or an e-book reader.
  • the memory 11 includes at least one type of readable storage medium.
  • the at least one type of readable storage medium may be a non-volatile storage medium such as a flash memory, a hard disk, a multimedia card, a card type memory, or the like.
  • the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1.
  • the readable storage medium may also be an external storage device of the electronic device 1, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SMC). , Secure Digital (SD) card, Flash Card, etc.
  • SMC smart memory card
  • SD Secure Digital
  • the readable storage medium of the memory 11 is generally used for storage and installation in the The personalized Wi-Fi hotspot push program of the electronic device 1, the model file of the pre-built and trained random forest model, and the pre-built user image data.
  • the memory 11 can also be used to temporarily store data that has been output or is about to be output.
  • the processor 12 may be a Central Processing Unit (CPU), microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as performing personalized Wi. -Fi hotspot push program, etc.
  • CPU Central Processing Unit
  • microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as performing personalized Wi. -Fi hotspot push program, etc.
  • FIG 1 shows only the electronic device 1 with the components 11-14 and the personalized Wi-Fi hotspot push program 10, but it should be understood that not all of the illustrated components are required to be implemented, alternative implementations may be more or more Less components.
  • the electronic device 1 may further include a user interface
  • the user interface may include a display, an input unit such as a keyboard, and the optional user interface may further include a standard wired interface and a wireless interface.
  • the electronic device 1 may further include a display, and in some embodiments, an LED display, a liquid crystal display, a touch liquid crystal display, and an Organic Light-Emitting Diode (OLED) touch device.
  • the display is used to display information processed in the electronic device and a user interface for displaying visualizations.
  • the electronic device 1 may further include a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a Wi-Fi module, and the like, and details are not described herein.
  • RF radio frequency
  • a memory Wi-Fi hotspot pushing program 10 is included in the memory 11 as a computer storage medium, and the processor 12 executes the personalized Wi-Fi hotspot pushing program 10 stored in the memory 11. The following steps are implemented:
  • Receiving step receiving multiple available Wi-Fi hotspots scanned by the client;
  • a scoring step scoring each of the plurality of Wi-Fi hotspots according to historical data of the plurality of Wi-Fi hotspots in the first preset time period by using a predetermined random forest model;
  • the determining step determining the user feature according to the predetermined user image data
  • a sorting step sorting the plurality of Wi-Fi hotspots according to signal strength, score, and user characteristics of the plurality of Wi-Fi hotspots;
  • Push step Recommend the user to the highest ranked Wi-Fi hotspot for users to connect.
  • the client version of the personalized Wi-Fi hotspot pushing program (hereinafter referred to as APP) is installed on the client used by each user, and the client connects to the Wi-Fi hotspot operation through the APP.
  • APP personalized Wi-Fi hotspot pushing program
  • the APP scans a plurality of Wi-Fi hotspots available at the current location through the client, and the APP sends the scanned multiple Wi-Fi hotspots to the electronic device 1 for electronic Device 1 scores multiple Wi-Fi hotspots.
  • the model file of the predetermined random forest model is called from the memory 11, and the plurality of Wi-Fi hotspots are retrieved from the database at the first
  • the historical data within a preset time one week is input into the model to obtain a score of the plurality of Wi-Fi hotspots, that is, a probability that the plurality of Wi-Fi hotspots may be successfully connected in the future.
  • the predetermined random forest model is trained by the following steps: collecting historical data of Wi-Fi hotspots visited by each user in the last three months, including: the name of the Wi-Fi, The access time is long, the operation status (connection success, connection failure, login success, login failure, etc.), frequency of access, availability by the operator, etc.
  • the historical data is uploaded to the log server, and the key historical data is extracted through the Extract-Transform-Load (ETL), such as Wi-Fi identification, time, location, connection operation, Internet access duration, connection success times, and connection.
  • ETL Extract-Transform-Load
  • Wi-Fi hotspots of the plurality of Wi-Fi hotspots have no historical data, then the random forest model cannot score the Wi-Fi hotspot for this type of Wi -Fi hotspots, take the default default rating or take the average of several other Wi-Fi hotspot scores and assign them to this type of Wi-Fi hotspot.
  • the score is taken as a score. Assume that the default default score is 8 points, and the average of other Wi-Fi hotspot scores is 8.5 points, then 8.5 is used as the score of Wi-Fi hotspots without historical data; otherwise, if there are other Wi-Fi hotspots The average of the scores is 7.5, and the score of 8 is the Wi-Fi hotspot without historical data.
  • the predetermined user image data is called from the memory 11, and the user characteristics are determined based on historical data such as the user's operation behavior and the Wi-Fi hotspot frequency in the user image data. If the user frequently uses the Wi-Fi hotspot and the connection time of the Wi-Fi hotspot is long, the user is determined to be a heavy user; otherwise, if the user only occasionally connects to the Wi-Fi hotspot and uses it, the user does not Belong to heavy users. If the user frequently switches the Wi-Fi hotspot to connect frequently in a short time, it is determined that the user belongs to the impatient user; otherwise, it is not an impetuous user. Of course, if the user's specific historical data cannot be obtained, the user characteristics cannot be judged.
  • the predetermined user portrait data is constructed according to historical data, and the user portrait data includes: a mobile phone brand, a model, an online time length, an age group, an education degree, a gender, a location of connecting a Wi-Fi hotspot, and a location of the Wi-Fi hotspot. Frequency and other operational behaviors, etc., used to determine user characteristics.
  • the method includes: sorting according to the current signal strength interval of the multiple Wi-Fi hotspots; for the same signal strength interval Two or more Wi-Fi hotspots, determining whether there is a historical user who has the current user characteristics among the historical users connected to the two or more Wi-Fi hotspots, there will be a historical user's Wi that conforms to the current user characteristics.
  • -Fi hotspots are ranked first; and, for two or more Wi-Fi hotspots with historical users that match the current user characteristics, sorted according to the score of the Wi-Fi hotspot, the score will be high Wi-Fi hotspots are on the front.
  • the signal strength distributions of the six Wi-Fi hotspots are as follows, Wi-Fi hotspot A, Wi-Fi hotspot C, and Wi-Fi hotspots.
  • the signal strength interval of E is the same, both between -35dbm and -60dbm.
  • the signal strength interval of Wi-Fi hotspot B and Wi-Fi hotspot D is the same, both between -60dbm and -85dbm, Wi-Fi hotspot F
  • the signal strength interval is between -85dbm and -110dbm.
  • the ratings of the six Wi-Fi hotspots are: 8.9, 9.2, 8.9, 9.3, 9.0, 9.5.
  • the sorting result is divided into two parts according to a preset signal strength threshold (for example, -85dbm), and the six Wi-Fi hotspots are divided into two parts. Some of them are Wi-Fi hotspot A, Wi-Fi hotspot C and Wi-Fi hotspot E, and the other are Wi-Fi hotspot B, Wi-Fi hotspot D and Wi-Fi hotspot F.
  • a preset signal strength threshold for example, -85dbm
  • the two parts of the Wi-Fi hotspot are sorted separately. If the current user's feature is determined to be an urgent user, then for the Wi-Fi hotspots A, C, and E, the history of connecting the Wi-Fi hotspots A, C, and E is determined. Among the users, is there an urgent user? If the Wi-Fi hotspots C and E have urgent historical users, the Wi-Fi hotspots C and E are placed in front of the Wi-Fi hotspot A. For Wi-Fi hotspots B and D, determine whether there are urgent users in the historical users connected to Wi-Fi hotspots B and D. If there are no urgent historical users in Wi-Fi hotspots B and D, then Wi-Fi hotspots B, D sorting unchanged.
  • Wi-Fi hotspots C, E and Wi-Fi hotspots B and D they are sorted according to their scores.
  • Wi-Fi hotspot E is in front of Wi-Fi hotspot C
  • Wi-Fi hotspot D is in Wi-Fi.
  • Fi hot spot B front is in Wi-Fi.
  • the final ranking results of the six Wi-Fi hotspots are: E, C, A, D, B, F.
  • the above embodiment proposes the electronic device 1 to collect Wi-Fi hotspots and user historical data through the client APP and score Wi-Fi hotspots, and then use multiple standards to sort Wi-Fi hotspots, considering Wi-Fi hotspots. Signal strength and scoring, but also consider whether the Wi-Fi hotspot meets the user.
  • the characteristics of the Wi-Fi hotspots that meet the user's characteristics are recommended for the customer, so that the user can refer to the connection operation, which effectively improves the user's online experience.
  • the personalized Wi-Fi hotspot pushing program 10 may also be divided into one or more modules, one or more modules being stored in the memory 11 and processed by one or more The device 12 is executed to complete the application.
  • a module as referred to in this application refers to a series of computer program instructions that are capable of performing a particular function.
  • FIG. 2 it is a schematic diagram of a module of the personalized Wi-Fi hotspot pushing program in FIG.
  • the personalized Wi-Fi hotspot pushing program 10 can be divided into: a receiving module 110, a scoring module 120, a judging module 130, a sorting module 140, and a pushing module 150.
  • the functions or operational steps implemented by the modules 110-150 are similar to the above, and will not be described in detail herein.
  • the receiving module 110 is configured to receive multiple available Wi-Fi hotspots scanned by the client;
  • the scoring module 120 uses a predetermined random forest model to score each Wi-Fi hotspot of the plurality of Wi-Fi hotspots according to historical data of the plurality of Wi-Fi hotspots in the first preset time;
  • the determining module 130 is configured to determine a user feature according to the predetermined user image data
  • the sorting module 140 is configured to sort according to the signal strength, the score, the user feature, and the like of the multiple Wi-Fi hotspots;
  • the pushing module 150 is configured to recommend the most ranked Wi-Fi hotspot to the user for the user to perform the connecting operation.
  • the present application also provides a personalized Wi-Fi hotspot push method.
  • FIG. 2 it is a flowchart of a first embodiment of a personalized Wi-Fi hotspot pushing method according to the present application. The method can be performed by a device that can be implemented by software and/or hardware.
  • the personalized Wi-Fi hotspot pushing method includes: step S10, step S20, step S30, step S40, and step S50.
  • Step S10 Receive multiple available Wi-Fi hotspots scanned by the client. For example, when a user wants to connect to a Wi-Fi hotspot, the APP scans a plurality of Wi-Fi hotspots available at the current location through the client, and the APP sends the scanned multiple Wi-Fi hotspots to the electronic device for the electronic device. Score multiple Wi-Fi hotspots.
  • Step S20 using a predetermined random forest model, scoring each of the plurality of Wi-Fi hotspots according to historical data of the plurality of Wi-Fi hotspots in the first preset time.
  • the predetermined random forest model model file is called from the memory, and the historical data of the plurality of Wi-Fi hotspots within one month is retrieved from the database. And inputting the model to obtain the scores of the plurality of Wi-Fi hotspots, that is, the probability that the plurality of Wi-Fi hotspots may be connected successfully in the future.
  • the predetermined random forest model is trained by the following steps: collecting historical data of Wi-Fi hotspots visited by each user in the last three months, including: the name of the Wi-Fi, and the time of being accessed , operation status (connection success, connection failure, login success, login failure, etc.), frequency of access, operator Provide and so on.
  • step S20 further includes: taking a default score of the Wi-Fi hotspot without historical data among the plurality of Wi-Fi hotspots or taking an average of other multiple Wi-Fi hotspot scores. There is a case where one of the plurality of Wi-Fi hotspots has no historical data, and the random forest model cannot score the Wi-Fi hotspot for this type of Wi-Fi hotspot. Take the default default rating or take the average of several other Wi-Fi hotspot scores and assign them to this type of Wi-Fi hotspot.
  • the score is taken as the score. Assume that the default default score is 8 points, and the average of other Wi-Fi hotspot scores is 8.5 points, then 8.5 is used as the score of Wi-Fi hotspots without historical data; otherwise, if there are other Wi-Fi hotspots The average of the scores is 7.5, and the score of 8 is the Wi-Fi hotspot without historical data.
  • Step S30 determining user characteristics based on predetermined user image data.
  • the predetermined user image data is called from the memory, and the user characteristics are determined according to the user's operation behavior in the user image data, and the historical data such as the Wi-Fi hotspot frequency. If the user frequently uses the Wi-Fi hotspot and the connection time of the Wi-Fi hotspot is long, the user is determined to be a heavy user; otherwise, if the user only occasionally connects to the Wi-Fi hotspot and uses it, the user does not Belong to heavy users. If the user frequently switches the Wi-Fi hotspot to connect frequently in a short time, it is determined that the user belongs to the impatient user; otherwise, it is not an impetuous user.
  • the predetermined user portrait data is constructed according to historical data, and the user portrait data includes: a mobile phone brand, a model, an online time length, an age group, an education degree, a gender, a location of connecting a Wi-Fi hotspot, and a location of the Wi-Fi hotspot. Frequency and other operational behaviors, etc., used to determine user characteristics.
  • Step S40 Sort the plurality of Wi-Fi hotspots according to signal strength, score, and user characteristics of the plurality of Wi-Fi hotspots.
  • the strengths of the multiple Wi-Fi hotspots sent by the client APP are different, and the scores of the Wi-Fi hotspots are also different, and the characteristics of the historical users of each Wi-Fi hotspot are also different.
  • the data is sorted according to the signal strength of the Wi-Fi hotspot, the characteristics of the historical user and the current user, and the rating.
  • step S50 the user is recommended to sort the most advanced Wi-Fi hotspots for the user to perform the connection operation. After sorting the plurality of Wi-Fi hotspots, displaying the sorting result on the client APP display interface, and recommending the most ranked Wi-Fi hotspot to the user for the user to refer to for the connection operation.
  • the personalized Wi-Fi hotspot pushing method proposed in this embodiment collects Wi-Fi hotspots and historical data of users, scores Wi-Fi hotspots, determines user characteristics, and selects the optimal Wi-Fi characteristics. Fi hotspots recommend users to connect operations, which effectively improves the user's online experience.
  • step S50 includes the following refinement steps:
  • Step S51 sorting according to current signal strength intervals of the multiple Wi-Fi hotspots
  • Step S52 For two or more Wi-Fi hotspots in the same signal strength interval, determine whether there is a historical user who has the current user feature among the historical users connected to the two or more Wi-Fi hotspots. Wi-Fi hotspots with historical users that match the current user characteristics are ranked first; and
  • step S53 two or more Wi-Fi hotspots with historical users that meet the current user characteristics are sorted according to the scores of the Wi-Fi hotspots, and the Wi-Fi hotspots with high scores are ranked first.
  • the signal strength distributions of the six Wi-Fi hotspots are as follows, Wi-Fi hotspot A, Wi-Fi hotspot C, and Wi-Fi hotspots.
  • the signal strength interval of E is the same, both between -35dbm and -60dbm.
  • the signal strength interval of Wi-Fi hotspot B and Wi-Fi hotspot D is the same, both between -60dbm and -85dbm, Wi-Fi hotspot F
  • the signal strength interval is between -85dbm and -110dbm.
  • the ratings of the six Wi-Fi hotspots are: 8.9, 9.2, 8.9, 9.3, 9.0, 9.5.
  • the sorting result is divided into two parts according to a preset signal strength threshold (for example, -85dbm), and the six Wi-Fi hotspots are divided into two parts. Some of them are Wi-Fi hotspot A, Wi-Fi hotspot C and Wi-Fi hotspot E, and the other are Wi-Fi hotspot B, Wi-Fi hotspot D and Wi-Fi hotspot F.
  • a preset signal strength threshold for example, -85dbm
  • the two parts of the Wi-Fi hotspot are sorted separately. If the current user's feature is determined to be an urgent user, then for the Wi-Fi hotspots A, C, and E, the history of connecting the Wi-Fi hotspots A, C, and E is determined. Among the users, is there an urgent user? If the Wi-Fi hotspots C and E have urgent historical users, the Wi-Fi hotspots C and E are placed in front of the Wi-Fi hotspot A. For Wi-Fi hotspots B and D, determine whether there are urgent users in the historical users connected to Wi-Fi hotspots B and D. If there are no urgent historical users in Wi-Fi hotspots B and D, then Wi-Fi hotspots B, D sorting unchanged.
  • Wi-Fi hotspots C, E and Wi-Fi hotspots B and D they are sorted according to their scores.
  • Wi-Fi hotspot E is in front of Wi-Fi hotspot C
  • Wi-Fi hotspot D is in Wi-Fi.
  • Fi hot spot B front is in Wi-Fi.
  • the personalized Wi-Fi hotspot pushing method proposed in this embodiment uses a plurality of standards to sort the Wi-Fi hotspots, and considers the Wi-Fi hotspot signal strength and the score, and also considers whether the Wi-Fi hotspot meets the user.
  • the characteristics of the Wi-Fi hotspot are recommended for the customer to meet the user's characteristics, so that the user can refer to the connection operation, which effectively improves the user's online experience.
  • the embodiment of the present application further provides a computer readable storage medium, where the personalized Wi-Fi hotspot pushing program is stored, where the personalized Wi-Fi hotspot pushing program is executed by the processor.
  • Receiving step receiving multiple available Wi-Fi hotspots scanned by the client;
  • a scoring step scoring each of the plurality of Wi-Fi hotspots according to historical data of the plurality of Wi-Fi hotspots in the first preset time period by using a predetermined random forest model;
  • the determining step determining the user feature according to the predetermined user image data
  • a sorting step sorting the plurality of Wi-Fi hotspots according to signal strength, score, and user characteristics of the plurality of Wi-Fi hotspots;
  • Push step Recommend the user to the highest ranked Wi-Fi hotspot for users to connect.
  • the step of scoring further includes:
  • a Wi-Fi hotspot with no historical data among the plurality of Wi-Fi hotspots is given a default score or an average score assigned to other Wi-Fi hotspots.
  • the sorting step includes:
  • Two or more Wi-Fi hotspots with historical users that match the current user characteristics are sorted according to the score of the Wi-Fi hotspot, and the Wi-Fi hotspots with high scores are ranked first.
  • the pushing step further includes:
  • the specific implementation manner of the computer readable storage medium of the present application is substantially the same as the specific implementation manner of the above-mentioned personalized Wi-Fi hotspot pushing method, and details are not described herein again.
  • a disk including a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in the various embodiments of the present application.
  • a terminal device which may be a mobile phone, a computer, a server, or a network device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • User Interface Of Digital Computer (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Telephone Function (AREA)

Abstract

本申请提出一种个性化Wi-Fi热点推送方法,该方法包括:接收客户端扫描到的可用的多个Wi-Fi热点;利用预先确定的随机森林模型,根据所述多个Wi-Fi热点在第一预设时间内的历史数据对该多个Wi-Fi热点中的每个Wi-Fi热点进行评分;根据预先确定的用户画像数据判断用户特征;根据所述多个Wi-Fi热点的信号强度、评分及用户特征对该多个Wi-Fi热点进行排序;及,向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作。本申请还提出一种电子装置及计算机可读存储介质。本申请利用Wi-Fi热点和用户的历史数据,向用户推送最优的Wi-Fi热点以供用户进行连接操作,提升用户上网体验

Description

个性化Wi-Fi热点推送方法、装置及存储介质
优先权申明
本申请基于巴黎公约申明享有2017年9月22日递交的申请号为CN201710868602.2、名称为“个性化Wi-Fi热点推送方法、装置及存储介质”的中国专利申请的优先权,该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请涉及计算机技术领域,尤其涉及一种个性化Wi-Fi热点推送方法、电子装置及计算机可读存储介质。
背景技术
当移动终端启动无线局域网功能时,无线局域网界面中会显示扫描出的Wi-Fi热点,用户可对扫描出Wi-Fi热点进行手动连接,若扫描出的热点中存在曾连接过的Wi-Fi热点,则系统可对该Wi-Fi热点自动进行连接。Wi-Fi热点通常设有连接密码,可防止蹭网和确保通信安全。在Wi-Fi热点连接过程中,对于设有密码的Wi-Fi热点,需输入密码。
根据移动终端的位置,扫描出的Wi-Fi热点列表中,可存在免费Wi-Fi热点,如:运营商Wi-Fi热点(中国移动、中国电信、中国联通)、公共Wi-Fi、商家Wi-Fi热点等。用户对于扫描出的免费Wi-Fi热点,通常随意选择进行连接,随意选择导致连接的Wi-Fi热点通常不是最优的,影响用户上网体验。
由于Wi-Fi热点和用户的属性不全且较难收集到,如何利用有限的数据,挖掘和构造特征,智能的为不同用户挑选出最好用的Wi-Fi热点,是一个非常有价值且亟待解决的问题。
发明内容
本申请提供一种个性化Wi-Fi热点推送方法、电子装置及计算机可读存储介质,其主要目的在于,利用Wi-Fi热点和用户的历史数据,向用户推送最优的Wi-Fi热点以供用户进行连接操作,提升用户上网体验。
为实现上述目的,本申请提供一种电子装置,该电子装置包括:存储器、处理器,所述存储器上存储有个性化Wi-Fi热点推送程序,该推送程序被所述处理器执行时实现如下步骤:
接收步骤:接收客户端扫描到的可用的多个Wi-Fi热点;
评分步骤:利用预先确定的随机森林模型,根据所述多个Wi-Fi热点在第一预设时间内的历史数据对该多个Wi-Fi热点中的每个Wi-Fi热点进行评分;
判断步骤:根据预先确定的用户画像数据判断用户特征;
排序步骤:根据所述多个Wi-Fi热点的信号强度、评分及用户特征对该多个Wi-Fi热点进行排序;及
推送步骤:向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作。
优选地,所述评分步骤还包括:
对所述多个Wi-Fi热点中没有历史数据的Wi-Fi热点赋予一个默认评分或赋予其它多个Wi-Fi热点的平均分。
优选地,所述排序步骤包括:
根据所述多个Wi-Fi热点当前的信号强度区间进行排序;
对于同一个信号强度区间的两个或多个Wi-Fi热点,判断连接过所述两个或多个Wi-Fi热点的历史用户中,是否有符当前用户特征的历史用户,将有符合当前用户特征的历史用户的Wi-Fi热点排在前面;及
对有符合当前用户特征的历史用户的两个或多个Wi-Fi热点,根据Wi-Fi热点的评分进行排序,将评分高的Wi-Fi热点排在前面。
优选地,所述推送步骤还包括:
若在第二预设时间内用户无法连接排序最靠前的Wi-Fi热点,继续向用户推荐剩下的多个Wi-Fi热点中排序靠前的Wi-Fi热点。
此外,为实现上述目的,本申请还提供一种个性化Wi-Fi热点推送方法,该方法包括:
接收步骤:接收客户端扫描到的可用的多个Wi-Fi热点;
评分步骤:利用预先确定的随机森林模型,根据所述多个Wi-Fi热点在第一预设时间内的历史数据对该多个Wi-Fi热点中的每个Wi-Fi热点进行评分;
判断步骤:根据预先确定的用户画像数据判断用户特征;
排序步骤:根据所述多个Wi-Fi热点的信号强度、评分及用户特征对该多个Wi-Fi热点进行排序;及
推送步骤:向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作。
优选地,所述评分步骤还包括:
对所述多个Wi-Fi热点中没有历史数据的Wi-Fi热点赋予一个默认评分或赋予其它多个Wi-Fi热点的平均分。
优选地,所述排序步骤包括:
根据所述多个Wi-Fi热点当前的信号强度区间进行排序;
对于同一个信号强度区间的两个或多个Wi-Fi热点,判断连接过所述两个或多个Wi-Fi热点的历史用户中,是否有符当前用户特征的历史用户,将有符合当前用户特征的历史用户的Wi-Fi热点排在前面;及
对有符合当前用户特征的历史用户的两个或多个Wi-Fi热点,根据Wi-Fi热点的评分进行排序,将评分高的Wi-Fi热点排在前面。
优选地,所述推送步骤还包括:
若在第二预设时间内用户无法连接排序最靠前的Wi-Fi热点,继续向用户推荐剩下的多个Wi-Fi热点中排序靠前的Wi-Fi热点。
此外,为实现上述目的,本申请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上存储有个性化Wi-Fi热点推送程序,该推送程序被处理器执行时实现如上所述的个性化Wi-Fi热点推送方法的步骤。
本申请提出的个性化Wi-Fi热点推送方法、电子装置及计算机可读存储介质,通过获取Wi-Fi热点及用户属性,计算Wi-Fi热点未来可能连接成功的概率,判断用户特征,然后依次根据Wi-Fi热点信号强度、用户特征及评分分值对Wi-Fi热点进行排序,最后向用户推荐排序靠前的Wi-Fi热点供用户参考进行连接操作,有效提升了用户上网体验。
附图说明
图1为本申请电子装置较佳实施例的示意图;
图2为图1中个性化Wi-Fi热点推送程序的模块示意图;
图3为本申请个性化Wi-Fi热点推送方法第一实施例的流程图;
图4为本申请个性化Wi-Fi热点推送方法步骤S50的细化流程示意图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请提供一种电子装置1。参照图1所示,为本申请电子装置1较佳实施例的示意图。
在本实施例中,该电子装置1包括存储器11、处理器12,网络接口13及通信总线14。其中,通信总线14用于实现这些组件之间的连接通信。
网络接口13可以包括标准的有线接口、无线接口(如WI-FI接口)。通常用于连接客户端(图1中未标出)。在本实施例中,电子装置1可以通过网络接口13连接数据库,与数据库进行数据传送。数据库中包括通过客户端收集的近期Wi-Fi热点及用户的历史数据。
客户端可以为笔记本、平板电脑、智能手机、电子书阅读器等具有无线局域网配置的终端设备。
存储器11包括至少一种类型的可读存储介质。所述至少一种类型的可读存储介质可为如闪存、硬盘、多媒体卡、卡型存储器等的非易失性存储介质。在一些实施例中,所述可读存储介质可以是所述电子装置1的内部存储单元,例如该电子装置1的硬盘。在另一些实施例中,所述可读存储介质也可以是所述电子装置1的外部存储设备,例如所述电子装置1上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。
在本实施例中,所述存储器11的可读存储介质通常用于存储安装于所述 电子装置1的个性化Wi-Fi热点推送程序、预先构建并训练好的随机森林模型的模型文件及预先构建的用户画像数据等。所述存储器11还可以用于暂时地存储已经输出或者将要输出的数据。
处理器12在一些实施例中可以是一中央处理器(Central Processing Unit,CPU),微处理器或其他数据处理芯片,用于运行存储器11中存储的程序代码或处理数据,例如执行个性化Wi-Fi热点推送程序等。
图1仅示出了具有组件11-14以及个性化Wi-Fi热点推送程序10的电子装置1,但是应理解的是,并不要求实施所有示出的组件,可以替代的实施更多或者更少的组件。
可选的,该电子装置1还可以包括用户接口,用户接口可以包括显示器(Display)、输入单元比如键盘(Keyboard),可选的用户接口还可以包括标准的有线接口、无线接口。
可选地,该电子装置1还可以包括显示器,在一些实施例中可以是LED显示器、液晶显示器、触控式液晶显示器以及有机发光二极管(Organic Light-Emitting Diode,OLED)触摸器等。显示器用于显示在电子装置中处理的信息以及用于显示可视化的用户界面。
可选地,该电子装置1还可以包括摄像头、射频(Radio Frequency,RF)电路,传感器、音频电路、Wi-Fi模块等等,在此不再赘述。
在图1所示的装置实施例中,作为一种计算机存储介质的存储器11中包括个性化Wi-Fi热点推送程序10,处理器12执行存储器11中存储的个性化Wi-Fi热点推送程序10时实现以下步骤:
接收步骤:接收客户端扫描到的可用的多个Wi-Fi热点;
评分步骤:利用预先确定的随机森林模型,根据所述多个Wi-Fi热点在第一预设时间内的历史数据对该多个Wi-Fi热点中的每个Wi-Fi热点进行评分;
判断步骤:根据预先确定的用户画像数据判断用户特征;
排序步骤:根据所述多个Wi-Fi热点的信号强度、评分及用户特征对该多个Wi-Fi热点进行排序;及
推送步骤:向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作。
在本实施例中,各用户使用的客户端上均安装有个性Wi-Fi热点推送程序的客户端版本(之后简称APP),客户端通过该APP进行连接Wi-Fi热点操作。
例如,当用户想要连接Wi-Fi热点时,该APP通过客户端扫描在当前位置可用的多个Wi-Fi热点,APP将扫描到的多个Wi-Fi热点发送至电子装置1,供电子装置1对多个Wi-Fi热点进行评分。
当电子装置1接收到客户端APP发送的多个Wi-Fi热点后,从存储器11中调用预先确定的随机森林模型的模型文件,从数据库中调取所述多个Wi-Fi热点在第一预设时间(一周)内的历史数据并将其输入模型,得到所述多个Wi-Fi热点的评分,也就是所述多个Wi-Fi热点在未来可能连接成功的概率。其中,所述预先确定的随机森林模型通过以下步骤训练得到:通过该APP收集各用户在最近三个月访问的Wi-Fi热点的历史数据,包括:Wi-Fi的名称、 被访问时间及时长、操作状态(连接成功、连接失败、登陆成功、登陆失败等)、被访问频次、是否运营商提供等。将历史数据上传到日志服务器,并经过数据仓库技术(Extract-Transform-Load,简称ETL)抽取出关键历史数据,如Wi-Fi标识、时间、位置、连接操作、上网时长、连接成功次数、连接失败次数、重试次数、登陆成功次数、登陆失败次数等;针对关键数据,进行分析,从时间维度、运营商/共享热点维度、连接/登陆/重试/上网时长统计等方面构造模型特征,确定模型label;按月、天统计用户使用Wi-Fi热点的频率和数据量,确定时间长度为最近三个月、最近一个月、最近一周的维度,再加上“运营商/共享热点”、“连接/登陆/重试/上网时长”维度组合成一系列特征,如最近三个月运营商的连接成功率、最近一周共享热点的重试次数等。然后以最近三个月的关键历史数据作为训练集,对随机森林模型进行训练,且每天对模型进行更新。
存在一种情况,所述多个Wi-Fi热点中,有一个或多个Wi-Fi热点没有历史数据,那么所述随机森林模型无法对该输Wi-Fi热点进行评分,对于这一类Wi-Fi热点,取预设的默认评分或者取其它多个Wi-Fi热点评分的平均值,赋值给这一类Wi-Fi热点。
进一步地,当这一类Wi-Fi热点的默认评分与其它多个Wi-Fi热点评分的平均值不一致时,取分值高的作为评分。假设预设的默认评分为8分,其它多个Wi-Fi热点评分的平均值为8.5分,则以8.5作为没有历史数据的Wi-Fi热点的评分;反之,若其它多个Wi-Fi热点评分的平均值为7.5分,则以8作为没有历史数据的Wi-Fi热点的评分。
从存储器11中调用预先确定的用户画像数据,依据用户画像数据中用户的操作行为、连接Wi-Fi热点频率等历史数据判断用户特征。若用户经常使用Wi-Fi热点,且每次连接Wi-Fi热点的上网时长较长,则判定该用户属于重度使用者;反之,若用户只是偶尔连接Wi-Fi热点并使用,则该用户不属于重度使用者。若用户经常在短时间内频繁切换Wi-Fi热点进行连接,则判定该用户属于急躁型用户;反之,则不属于急躁型用户。当然,若无法获得用户具体的历史数据,则无法对用户特征进行判断。需要说明的是,所述预先确定的用户画像数据根据历史数据构建得到,用户画像数据包括:用户使用的手机品牌、型号、上网时长、年龄段、学历、性别、连接Wi-Fi热点的位置、频率及其它操作行为等,用于判断用户特征。
客户端APP发送的所述多个Wi-Fi热点信号强度各不相同,各Wi-Fi热点的评分也各有差异,且每个Wi-Fi热点的历史用户的特征也不同。依次根据Wi-Fi热点的信号强度、历史用户及当前用户的特征及评分情况进行排序,具体包括:根据所述多个Wi-Fi热点当前的信号强度区间进行排序;对于同一个信号强度区间的两个或多个Wi-Fi热点,判断连接过所述两个或多个Wi-Fi热点的历史用户中,是否有符当前用户特征的历史用户,将有符合当前用户特征的历史用户的Wi-Fi热点排在前面;及,对有符合当前用户特征的历史用户的两个或多个Wi-Fi热点,根据Wi-Fi热点的评分进行排序,将评分高的 Wi-Fi热点排在前面。
以6个Wi-Fi热点A、B、C、D、E、F为例,这六个Wi-Fi热点的信号强度分布如下,Wi-Fi热点A、Wi-Fi热点C和Wi-Fi热点E的信号强度区间相同,都在-35dbm~-60dbm之间,Wi-Fi热点B和Wi-Fi热点D的信号强度区间相同,都在-60dbm~-85dbm之间,Wi-Fi热点F的信号强度区间在-85dbm~-110dbm之间。6个Wi-Fi热点的评分情况依次为:8.9、9.2、8.9、9.3、9.0、9.5。
那么,对于这6个Wi-Fi热点进行排序,首先按照各Wi-Fi热点的信号强度进行排序,将信号强度强的排在前面,信号强度若的排在后面。具体地,为了提高计算效率,按照预设的信号强度阈值(如-85dbm)对排序结果进行二分处理,将6个Wi-Fi热点分成两部分。一部分为Wi-Fi热点A、Wi-Fi热点C及Wi-Fi热点E,另一部分是Wi-Fi热点B、Wi-Fi热点D及Wi-Fi热点F。
分别对两部分的Wi-Fi热点进行排序,若当前用户的特征判定为急躁型用户,那么,对于Wi-Fi热点A、C、E,判断连接过Wi-Fi热点A、C、E的历史用户中,是否有急躁型用户,若Wi-Fi热点C、E均有急躁型的历史用户,则将Wi-Fi热点C、E排在Wi-Fi热点A的前面。对于Wi-Fi热点B、D,判断连接过Wi-Fi热点B、D历史用户中,是否有急躁型用户,若Wi-Fi热点B、D均没有急躁型的历史用户,则Wi-Fi热点B、D排序不变。
对于Wi-Fi热点C、E及Wi-Fi热点B、D,依次按照其评分分值进行排序,故Wi-Fi热点E排在Wi-Fi热点C前面,Wi-Fi热点D排在Wi-Fi热点B前面。
最后,将两部分Wi-Fi热点的排序结果结合起来,则6个Wi-Fi热点的最终排序结果为:E、C、A、D、B、F。
当然,若当前用户的特征为:既是急躁型用户,也是重度使用者,那么在排序的第二个步骤中,就要同时考虑连接过Wi-Fi热点的历史用户,既有急躁型用户,也有重度使用者。自然最终排序结果也会相应改变,这里不再赘述。
进一步地,对所述多个Wi-Fi热点进行排序后,在客户端APP显示界面上显示排序结果,并向用户推荐排序最靠前的Wi-Fi热点,供用户参考进行连接操作。
可以理解的是,为了使用户能尽快使用网络,若在第二预设时间内用户无法连接排序最靠前的Wi-Fi热点,继续向用户推荐剩下的多个Wi-Fi热点中排序靠前的Wi-Fi热点。若用户对推荐的Wi-Fi热点进行连接操作,但在连接操作后的第二预设时间(5s)后,仍无法连接,那么继续向用户推荐排序靠前的Wi-Fi热点,供用户参考进行连接操作。
上述实施例提出电子装置1,通过客户端APP收集Wi-Fi热点及用户的历史数据并对Wi-Fi热点进行评分,然后采用多个标准对Wi-Fi热点进行排序,在考虑Wi-Fi热点信号强度和评分的同时,还考虑到Wi-Fi热点是否符合用户 的特征,最终为客户推荐最优的、符合用户特征需求的Wi-Fi热点,以供用户参考进行连接操作,有效提升了用户的上网体验。
可选地,在其他的实施例中,个性化Wi-Fi热点推送程序10还可以被分割为一个或者多个模块,一个或者多个模块被存储于存储器11中,并由一个或多个处理器12所执行,以完成本申请。本申请所称的模块是指能够完成特定功能的一系列计算机程序指令段。参照图2所示,为图1中个性化Wi-Fi热点推送程序的模块示意图。在本实施例中,个性化Wi-Fi热点推送程序10可以被分割为:接收模块110、评分模块120、判断模块130、排序模块140及推送模块150。所述模块110-150所实现的功能或操作步骤均与上文类似,此处不再详述。
接收模块110,用于接收客户端扫描到的可用的多个Wi-Fi热点;
评分模块120,利用预先确定的随机森林模型,根据所述多个Wi-Fi热点在第一预设时间内的历史数据对该多个Wi-Fi热点中的每个Wi-Fi热点进行评分;
判断模块130,用于根据预先确定的用户画像数据判断用户特征;
排序模块140,用于根据所述多个Wi-Fi热点的信号强度、评分及用户特征等情况进行排序;及
推送模块150,用于向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作。
此外,本申请还提供一种个性化Wi-Fi热点推送方法。参照图2所示,为本申请个性化Wi-Fi热点推送方法第一实施例的流程图。该方法可以由一个装置执行,该装置可以由软件和/或硬件实现。
在本实施例中,个性化Wi-Fi热点推送方法包括:步骤S10、步骤S20、步骤S30、步骤S40及步骤S50。
步骤S10,接收客户端扫描到的可用的多个Wi-Fi热点。例如,当用户想要连接Wi-Fi热点时,该APP通过客户端扫描在当前位置可用的多个Wi-Fi热点,APP将扫描到的多个Wi-Fi热点发送至电子装置,供电子装置对多个Wi-Fi热点进行评分。
步骤S20,利用预先确定的随机森林模型,根据所述多个Wi-Fi热点在第一预设时间内的历史数据对该多个Wi-Fi热点中的每个Wi-Fi热点进行评分。当电子装置接收到客户端APP发送的多个Wi-Fi热点后,从存储器中调用预先确定的随机森林模型模型文件,从数据库中调取所述多个Wi-Fi热点一个月内的历史数据并将其输入模型,得到所述多个Wi-Fi热点的评分,也就是所述多个Wi-Fi热点在未来可能连接成功的概率。其中,所述预先确定的随机森林模型通过以下步骤训练得到:通过该APP收集各用户在最近三个月访问的Wi-Fi热点的历史数据,包括:Wi-Fi的名称、被访问时间及时长、操作状态(连接成功、连接失败、登陆成功、登陆失败等)、被访问频次、是否运营商 提供等。将历史数据上传到日志服务器,并经过数据仓库技术(ETL)抽取出关键历史数据,如Wi-Fi标识、时间、位置、连接操作、上网时长、连接成功次数、连接失败次数、重试次数、登陆成功次数、登陆失败次数等;针对关键数据,进行分析,从时间维度、运营商/共享热点维度、连接/登陆/重试/上网时长统计等方面构造模型特征,确定模型label;按月、天统计用户使用Wi-Fi热点的频率和数据量,确定时间长度为最近三个月、最近一个月、最近一周的维度,再加上“运营商/共享热点”、“连接/登陆/重试/上网时长”维度组合成一系列特征,如最近三个月运营商的连接成功率、最近一周共享热点的重试次数等。然后以最近三个月的关键历史数据作为训练集,对随机森林模型进行训练,且每天对模型进行更新。
具体地,步骤S20还包括:对所述多个Wi-Fi热点中没有历史数据的Wi-Fi热点取默认评分或取其它多个Wi-Fi热点评分的平均值。存在一种情况,所述多个Wi-Fi热点中,有一个Wi-Fi热点没有历史数据,那么所述随机森林模型无法对该输Wi-Fi热点进行评分,对于这一类Wi-Fi热点,取预设的默认评分或者取其它多个Wi-Fi热点评分的平均值,赋值给这一类Wi-Fi热点。
进一步地,当默认评分与其它多个Wi-Fi热点评分的平均值不一致时,取分值高的作为评分。假设预设的默认评分为8分,其它多个Wi-Fi热点评分的平均值为8.5分,则以8.5作为没有历史数据的Wi-Fi热点的评分;反之,若其它多个Wi-Fi热点评分的平均值为7.5分,则以8作为没有历史数据的Wi-Fi热点的评分。
步骤S30,根据预先确定的用户画像数据判断用户特征。从存储器中调用预先确定的用户画像数据,依据用户画像数据中用户的操作行为、连接Wi-Fi热点频率等历史数据判断用户特征。若用户经常使用Wi-Fi热点,且每次连接Wi-Fi热点的上网时长较长,则判定该用户属于重度使用者;反之,若用户只是偶尔连接Wi-Fi热点并使用,则该用户不属于重度使用者。若用户经常在短时间内频繁切换Wi-Fi热点进行连接,则判定该用户属于急躁型用户;反之,则不属于急躁型用户。当然,若无法获得用户具体的历史数据,则无法对用户特征进行判断。需要说明的是,所述预先确定的用户画像数据根据历史数据构建得到,用户画像数据包括:用户使用的手机品牌、型号、上网时长、年龄段、学历、性别、连接Wi-Fi热点的位置、频率及其它操作行为等,用于判断用户特征。
步骤S40,根据所述多个Wi-Fi热点的信号强度、评分及用户特征对该多个Wi-Fi热点进行排序。客户端APP发送的所述多个Wi-Fi热点信号强度各不相同,各Wi-Fi热点的评分也各有差异,且每个Wi-Fi热点的历史用户的特征也不同。依次根据Wi-Fi热点的信号强度、历史用户及当前用户的特征及评分情况进行排序。
步骤S50,向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作。对所述多个Wi-Fi热点进行排序后,在客户端APP显示界面上显示排序结果,并向用户推荐排序最靠前的Wi-Fi热点,供用户参考进行连接操作。
可以理解的是,为了使用户能尽快使用网络,若在第二预设时间内用户无法连接排序最靠前的Wi-Fi热点,继续向用户推荐剩下的多个Wi-Fi热点中排序靠前的Wi-Fi热点。若用户对推荐的Wi-Fi热点进行连接操作,但在连接操作后的第二预设时间(5s)后,仍无法连接,那么继续向用户推荐排序靠前的Wi-Fi热点,供用户参考进行连接操作。
本实施例提出的个性化Wi-Fi热点推送方法,通过收集Wi-Fi热点及用户的历史数据,对Wi-Fi热点进行评分,判断用户特征,挑选最优的、且符合用户特征的Wi-Fi热点推荐给用户进行连接操作,有效提高了用户上网体验。
基于第一实施例提出本申请个性化Wi-Fi热点推送方法的第二实施例。参照图3所示,在本实施例中,步骤S50包括以下细化步骤:
步骤S51,根据所述多个Wi-Fi热点当前的信号强度区间进行排序;
步骤S52,对于同一个信号强度区间的两个或多个Wi-Fi热点,判断连接过所述两个或多个Wi-Fi热点的历史用户中,是否有符当前用户特征的历史用户,将有符合当前用户特征的历史用户的Wi-Fi热点排在前面;及
步骤S53,对有符合当前用户特征的历史用户的两个或多个Wi-Fi热点,根据Wi-Fi热点的评分进行排序,将评分高的Wi-Fi热点排在前面。
以6个Wi-Fi热点A、B、C、D、E、F为例,这六个Wi-Fi热点的信号强度分布如下,Wi-Fi热点A、Wi-Fi热点C和Wi-Fi热点E的信号强度区间相同,都在-35dbm~-60dbm之间,Wi-Fi热点B和Wi-Fi热点D的信号强度区间相同,都在-60dbm~-85dbm之间,Wi-Fi热点F的信号强度区间在-85dbm~-110dbm之间。6个Wi-Fi热点的评分情况依次为:8.9、9.2、8.9、9.3、9.0、9.5。
那么,对于这6个Wi-Fi热点进行排序,首先按照各Wi-Fi热点的信号强度进行排序,将信号强度强的排在前面,信号强度若的排在后面。具体地,为了提高计算效率,按照预设的信号强度阈值(如-85dbm)对排序结果进行二分处理,将6个Wi-Fi热点分成两部分。一部分为Wi-Fi热点A、Wi-Fi热点C及Wi-Fi热点E,另一部分是Wi-Fi热点B、Wi-Fi热点D及Wi-Fi热点F。
分别对两部分的Wi-Fi热点进行排序,若当前用户的特征判定为急躁型用户,那么,对于Wi-Fi热点A、C、E,判断连接过Wi-Fi热点A、C、E的历史用户中,是否有急躁型用户,若Wi-Fi热点C、E均有急躁型的历史用户,则将Wi-Fi热点C、E排在Wi-Fi热点A的前面。对于Wi-Fi热点B、D,判断连接过Wi-Fi热点B、D历史用户中,是否有急躁型用户,若Wi-Fi热点B、D均没有急躁型的历史用户,则Wi-Fi热点B、D排序不变。
对于Wi-Fi热点C、E及Wi-Fi热点B、D,依次按照其评分分值进行排序,故Wi-Fi热点E排在Wi-Fi热点C前面,Wi-Fi热点D排在Wi-Fi热点B前面。
最后,将两部分Wi-Fi热点的排序结果结合起来,则6个Wi-Fi热点的最 终排序结果为:E、C、A、D、B、F。
当然,若当前用户的特征为:既是急躁型用户,也是重度使用者,那么在排序的第二个步骤中,就要同时考虑连接过Wi-Fi热点的历史用户,既有急躁型用户,也有重度使用者。自然最终排序结果也会相应改变,这里不再赘述。
本实施例提出的个性化Wi-Fi热点推送方法,通过采用多个标准对Wi-Fi热点进行排序,在考虑Wi-Fi热点信号强度和评分的同时,还考虑到Wi-Fi热点是否符合用户的特征,最终为客户推荐最优的、且符合用户特征需求的Wi-Fi热点,以供用户参考进行连接操作,有效提升了用户的上网体验。
此外,本申请实施例还提出一种计算机可读存储介质,所述计算机可读存储介质上存储有个性化Wi-Fi热点推送程序,所述个性化Wi-Fi热点推送程序被处理器执行时实现如下操作:
接收步骤:接收客户端扫描到的可用的多个Wi-Fi热点;
评分步骤:利用预先确定的随机森林模型,根据所述多个Wi-Fi热点在第一预设时间内的历史数据对该多个Wi-Fi热点中的每个Wi-Fi热点进行评分;
判断步骤:根据预先确定的用户画像数据判断用户特征;
排序步骤:根据所述多个Wi-Fi热点的信号强度、评分及用户特征对该多个Wi-Fi热点进行排序;及
推送步骤:向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作。
可选地,所述评分步骤还包括:
对所述多个Wi-Fi热点中没有历史数据的Wi-Fi热点赋予一个默认评分或赋予其它多个Wi-Fi热点的平均分。
可选地,所述排序步骤包括:
根据所述多个Wi-Fi热点当前的信号强度区间进行排序;
对于同一个信号强度区间的两个或多个Wi-Fi热点,判断连接过所述两个或多个Wi-Fi热点的历史用户中,是否有符当前用户特征的历史用户,将有符合当前用户特征的历史用户的Wi-Fi热点排在前面;及
对有符合当前用户特征的历史用户的两个或多个Wi-Fi热点,根据Wi-Fi热点的评分进行排序,将评分高的Wi-Fi热点排在前面。
可选地,所述推送步骤还包括:
若在第二预设时间内用户无法连接排序最靠前的Wi-Fi热点,继续向用户推荐剩下的多个Wi-Fi热点中排序靠前的Wi-Fi热点。
本申请之计算机可读存储介质的具体实施方式与上述个性化Wi-Fi热点推送方法的具体实施方式大致相同,在此不再赘述。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、装置、物品或者方法不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括 为这种过程、装置、物品或者方法所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、装置、物品或者方法中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。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上述实施例方法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,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请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如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种个性化Wi-Fi热点推送方法,其特征在于,所述方法包括:
    接收步骤:接收客户端扫描到的可用的多个Wi-Fi热点;
    评分步骤:利用预先确定的随机森林模型,根据所述多个Wi-Fi热点在第一预设时间内的历史数据对该多个Wi-Fi热点中的每个Wi-Fi热点进行评分;
    判断步骤:根据预先确定的用户画像数据判断用户特征;
    排序步骤:根据所述多个Wi-Fi热点的信号强度、评分及用户特征对该多个Wi-Fi热点进行排序;及
    推送步骤:向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作。
  2. 根据权利要求1所述的个性化Wi-Fi热点推送方法,其特征在于,所述评分步骤还包括:
    对所述多个Wi-Fi热点中没有历史数据的Wi-Fi热点赋予一个默认评分或赋予其它多个Wi-Fi热点的平均分。
  3. 根据权利要求2所述的个性化Wi-Fi热点推送方法,其特征在于,所述排序步骤包括:
    根据所述多个Wi-Fi热点当前的信号强度区间进行排序;
    对于同一个信号强度区间的两个或多个Wi-Fi热点,判断连接过所述两个或多个Wi-Fi热点的历史用户中,是否有符当前用户特征的历史用户,将有符合当前用户特征的历史用户的Wi-Fi热点排在前面;及
    对有符合当前用户特征的历史用户的两个或多个Wi-Fi热点,根据Wi-Fi热点的评分进行排序,将评分高的Wi-Fi热点排在前面。
  4. 根据权利要3所述的个性化Wi-Fi热点推送方法,其特征在于,所述推送步骤还包括:
    若在第二预设时间内用户无法连接排序最靠前的Wi-Fi热点,继续向用户推荐剩下的多个Wi-Fi热点中排序靠前的Wi-Fi热点。
  5. 根据权利要求1所述的个性化Wi-Fi热点推送方法,其特征在于:
    所述历史数据包括:Wi-Fi的名称、被访问时间及时长、操作状态、被访问频次、是否运营商提供;
    所述用户画像数据包括:用户使用的手机品牌、型号、上网时长、年龄段、学历、性别、连接Wi-Fi热点的频率及操作行为。
  6. 一种电子装置,其特征在于,该电子装置包括:存储器、处理器,所述存储器上存储有个性化Wi-Fi热点推送程序,该推送程序被所述处理器执行时实现如下步骤:
    接收步骤:接收客户端扫描到的可用的多个Wi-Fi热点;
    评分步骤:利用预先确定的随机森林模型,根据所述多个Wi-Fi热点在第一预设时间内的历史数据对该多个Wi-Fi热点中的每个Wi-Fi热点进行评分;
    判断步骤:根据预先确定的用户画像数据判断用户特征;
    排序步骤:根据所述多个Wi-Fi热点的信号强度、评分及用户特征对该多个Wi-Fi热点进行排序;及
    推送步骤:向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作。
  7. 根据权利要求6所述的电子装置,其特征在于,所述评分步骤还包括:
    对所述多个Wi-Fi热点中没有历史数据的Wi-Fi热点赋予一个默认评分或赋予其它多个Wi-Fi热点的平均分。
  8. 根据权利要求7所述的电子装置,其特征在于,所述排序步骤包括:
    根据所述多个Wi-Fi热点当前的信号强度区间进行排序;
    对于同一个信号强度区间的两个或多个Wi-Fi热点,判断连接过所述两个或多个Wi-Fi热点的历史用户中,是否有符当前用户特征的历史用户,将有符合当前用户特征的历史用户的Wi-Fi热点排在前面;及
    对有符合当前用户特征的历史用户的两个或多个Wi-Fi热点,根据Wi-Fi热点的评分进行排序,将评分高的Wi-Fi热点排在前面。
  9. 根据权利要求8所述的电子装置,其特征在于,所述推送步骤还包括:
    若在第二预设时间内用户无法连接排序最靠前的Wi-Fi热点,继续向用户推荐剩下的多个Wi-Fi热点中排序靠前的Wi-Fi热点。
  10. 根据权利要求6所述的电子装置,其特征在于:
    所述历史数据包括:Wi-Fi的名称、被访问时间及时长、操作状态、被访问频次、是否运营商提供;
    所述用户画像数据包括:用户使用的手机品牌、型号、上网时长、年龄段、学历、性别、连接Wi-Fi热点的频率及操作行为。
  11. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质上存储有个性化Wi-Fi热点推送程序,该推送程序被处理器执行时实现如下步骤:
    接收步骤:接收客户端扫描到的可用的多个Wi-Fi热点;
    评分步骤:利用预先确定的随机森林模型,根据所述多个Wi-Fi热点在第一预设时间内的历史数据对该多个Wi-Fi热点中的每个Wi-Fi热点进行评分;
    判断步骤:根据预先确定的用户画像数据判断用户特征;
    排序步骤:根据所述多个Wi-Fi热点的信号强度、评分及用户特征对该多个Wi-Fi热点进行排序;及
    推送步骤:向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作。
  12. 根据权利要求11所述的计算机可读存储介质,其特征在于,所述评分步骤还包括:
    对所述多个Wi-Fi热点中没有历史数据的Wi-Fi热点赋予一个默认评分或赋予其它多个Wi-Fi热点的平均分。
  13. 根据权利要求12所述的计算机可读存储介质,其特征在于,所述排序步骤包括:
    根据所述多个Wi-Fi热点当前的信号强度区间进行排序;
    对于同一个信号强度区间的两个或多个Wi-Fi热点,判断连接过所述两个或多个Wi-Fi热点的历史用户中,是否有符当前用户特征的历史用户,将有符合当前用户特征的历史用户的Wi-Fi热点排在前面;及
    对有符合当前用户特征的历史用户的两个或多个Wi-Fi热点,根据Wi-Fi热点的评分进行排序,将评分高的Wi-Fi热点排在前面。
  14. 根据权利要求13所述的计算机可读存储介质,其特征在于,所述推送步骤还包括:
    若在第二预设时间内用户无法连接排序最靠前的Wi-Fi热点,继续向用户推荐剩下的多个Wi-Fi热点中排序靠前的Wi-Fi热点。
  15. 根据权利要求11所述的计算机可读存储介质,其特征在于:
    所述历史数据包括:Wi-Fi的名称、被访问时间及时长、操作状态、被访问频次、是否运营商提供;
    所述用户画像数据包括:用户使用的手机品牌、型号、上网时长、年龄段、学历、性别、连接Wi-Fi热点的频率及操作行为。
  16. 一种个性化Wi-Fi热点推送程序,其特征在于,该推送程序包括:
    接收模块,用于接收客户端扫描到的可用的多个Wi-Fi热点;
    评分模块,利用预先确定的随机森林模型,根据所述多个Wi-Fi热点在第一预设时间内的历史数据对该多个Wi-Fi热点中的每个Wi-Fi热点进行评分;
    判断模块,用于根据预先确定的用户画像数据判断用户特征;
    排序模块,用于根据所述多个Wi-Fi热点的信号强度、评分及用户特征等情况进行排序;及
    推送模块,用于向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作。
  17. 根据权利要求16所述的个性化Wi-Fi热点推送程序,其特征在于,所述评分模块还用于:
    对所述多个Wi-Fi热点中没有历史数据的Wi-Fi热点赋予一个默认评分或赋予其它多个Wi-Fi热点的平均分。
  18. 根据权利要求17所述的个性化Wi-Fi热点推送程序,其特征在于,所述“根据所述多个Wi-Fi热点的信号强度、评分及用户特征等情况进行排序”的步骤包括:
    根据所述多个Wi-Fi热点当前的信号强度区间进行排序;
    对于同一个信号强度区间的两个或多个Wi-Fi热点,判断连接过所述两个或多个Wi-Fi热点的历史用户中,是否有符当前用户特征的历史用户,将有符合当前用户特征的历史用户的Wi-Fi热点排在前面;及
    对有符合当前用户特征的历史用户的两个或多个Wi-Fi热点,根据Wi-Fi热点的评分进行排序,将评分高的Wi-Fi热点排在前面。
  19. 根据权利要求18所述的个性化Wi-Fi热点推送程序,其特征在于,所述“向用户推荐排序最靠前的Wi-Fi热点供用户进行连接操作”的步骤还包括:
    若在第二预设时间内用户无法连接排序最靠前的Wi-Fi热点,继续向用户推荐剩下的多个Wi-Fi热点中排序靠前的Wi-Fi热点。
  20. 根据权利要求16所述的个性化Wi-Fi热点推送程序,其特征在于:
    所述历史数据包括:Wi-Fi的名称、被访问时间及时长、操作状态、被访问频次、是否运营商提供;
    所述用户画像数据包括:用户使用的手机品牌、型号、上网时长、年龄段、学历、性别、连接Wi-Fi热点的频率及操作行为。
PCT/CN2017/108798 2017-09-22 2017-10-31 个性化Wi-Fi热点推送方法、装置及存储介质 WO2019056501A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710868602.2A CN107734594B (zh) 2017-09-22 2017-09-22 个性化wifi热点推送方法、装置及存储介质
CN201710868602.2 2017-09-22

Publications (1)

Publication Number Publication Date
WO2019056501A1 true WO2019056501A1 (zh) 2019-03-28

Family

ID=61206393

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/108798 WO2019056501A1 (zh) 2017-09-22 2017-10-31 个性化Wi-Fi热点推送方法、装置及存储介质

Country Status (2)

Country Link
CN (1) CN107734594B (zh)
WO (1) WO2019056501A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108810916B (zh) * 2018-04-17 2022-08-12 深圳平安通信科技有限公司 Wi-Fi热点推荐方法、装置及存储介质
CN109413663B (zh) * 2018-09-29 2021-11-16 联想(北京)有限公司 一种信息处理方法和设备
CN110798389B (zh) * 2019-11-08 2021-05-18 美的集团股份有限公司 智能家居设备的配网方法、系统及电子设备、存储介质
CN111010716B (zh) * 2019-12-11 2022-02-01 Oppo广东移动通信有限公司 网络控制方法、装置、存储介质及电子设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140071895A1 (en) * 2008-12-12 2014-03-13 Ryan H. Bane Network Selection Based On Customizing Crowdsourced Connection Quality Data
CN103686941A (zh) * 2013-11-29 2014-03-26 宇龙计算机通信科技(深圳)有限公司 一种显示wifi名称的方法及系统
CN104768156A (zh) * 2015-04-30 2015-07-08 北京奇虎科技有限公司 WiFi连接的方法及装置
CN106488539A (zh) * 2015-09-02 2017-03-08 腾讯科技(深圳)有限公司 终端中WiFi资源的处理方法和系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8213922B2 (en) * 2005-12-08 2012-07-03 At&T Intellectual Property I, Lp Method for scanning services with a multimode communication device
CN103037469B (zh) * 2011-10-08 2016-03-30 中国移动通信集团公司 接入网选择方法、用户设备、系统和选网策略单元
CN106488493B (zh) * 2015-08-24 2020-06-02 阿里巴巴集团控股有限公司 识别用户的网络热点类型的方法和装置及电子设备
CN106874522A (zh) * 2017-03-29 2017-06-20 珠海习悦信息技术有限公司 信息推荐方法、装置、存储介质及处理器

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140071895A1 (en) * 2008-12-12 2014-03-13 Ryan H. Bane Network Selection Based On Customizing Crowdsourced Connection Quality Data
CN103686941A (zh) * 2013-11-29 2014-03-26 宇龙计算机通信科技(深圳)有限公司 一种显示wifi名称的方法及系统
CN104768156A (zh) * 2015-04-30 2015-07-08 北京奇虎科技有限公司 WiFi连接的方法及装置
CN106488539A (zh) * 2015-09-02 2017-03-08 腾讯科技(深圳)有限公司 终端中WiFi资源的处理方法和系统

Also Published As

Publication number Publication date
CN107734594A (zh) 2018-02-23
CN107734594B (zh) 2020-12-04

Similar Documents

Publication Publication Date Title
US9978093B2 (en) Method and system for pushing mobile application
WO2020073534A1 (zh) 基于重聚类的推送方法、装置、计算机设备及存储介质
WO2019056501A1 (zh) 个性化Wi-Fi热点推送方法、装置及存储介质
WO2019061993A1 (zh) wifi热点连接方法、装置及存储介质
US20160321745A1 (en) Account binding processing method, apparatus and system
US20160210632A1 (en) Secured payment method and relevant device and system
US20140095308A1 (en) Advertisement distribution apparatus and advertisement distribution method
CN110351115A (zh) 降低网络访问时延的方法、装置、计算机设备及存储介质
CN110515951B (zh) 一种bom标准化方法、系统及电子设备和存储介质
CN109492152B (zh) 推送定制内容的方法、装置、计算机设备及存储介质
CN107809740B (zh) Wi-Fi热点部署优化方法、服务器及存储介质
US9246925B2 (en) Method and system for third-party service platform login
CN104092596B (zh) 一种音乐用户群组的管理方法、装置及系统
WO2021175303A1 (zh) 一种自动生成数据采集模块的方法和系统
CN109194689B (zh) 异常行为识别方法、装置、服务器及存储介质
US20160308795A1 (en) Method, system and apparatus for configuing a chatbot
US20170169062A1 (en) Method and electronic device for recommending video
US10097724B2 (en) System, control method, and recording medium
CN110602049A (zh) 数据传输方法、服务器及存储介质
WO2019080419A1 (zh) 标准知识库的构建方法、电子装置及存储介质
US11895115B2 (en) Match limits for dating application
US11120488B2 (en) System and method for automated network trading platform
CN107908525A (zh) 告警处理方法、设备及可读存储介质
WO2017067398A1 (zh) 一种基于用户填写验证码来进行图片识别的方法及装置
US10846773B2 (en) Information processing device, information processing method, program, and storage medium

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: 17925835

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 28/09/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 17925835

Country of ref document: EP

Kind code of ref document: A1