CN108124197B - Method and device for identifying terminal access behavior - Google Patents

Method and device for identifying terminal access behavior Download PDF

Info

Publication number
CN108124197B
CN108124197B CN201711365115.0A CN201711365115A CN108124197B CN 108124197 B CN108124197 B CN 108124197B CN 201711365115 A CN201711365115 A CN 201711365115A CN 108124197 B CN108124197 B CN 108124197B
Authority
CN
China
Prior art keywords
access behavior
behavior data
time
sliding
window
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201711365115.0A
Other languages
Chinese (zh)
Other versions
CN108124197A (en
Inventor
陶志强
王劲
吴英华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Planning and Designing Institute of Telecommunications Co Ltd
Original Assignee
Guangdong Planning and Designing Institute of Telecommunications Co Ltd
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 Guangdong Planning and Designing Institute of Telecommunications Co Ltd filed Critical Guangdong Planning and Designing Institute of Telecommunications Co Ltd
Priority to CN201711365115.0A priority Critical patent/CN108124197B/en
Publication of CN108124197A publication Critical patent/CN108124197A/en
Application granted granted Critical
Publication of CN108124197B publication Critical patent/CN108124197B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H04N21/25808—Management of client data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H04N21/25866—Management of end-user data
    • H04N21/25891—Management of end-user data being end-user preferences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44213—Monitoring of end-user related data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/4508—Management of client data or end-user data

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computer Graphics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Social Psychology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The invention relates to a method and a device for identifying terminal access behaviors, and belongs to the technical field of internet. The method comprises the following steps: acquiring current access behavior data and corresponding historical access behavior data of a terminal; the access behavior data comprises access behavior data of the terminal from online to current moment; constructing a sliding window according to the current access behavior data, and sliding the sliding window in the historical access behavior data to obtain a historical window corresponding to the historical access behavior data; respectively calculating the matching degree of the sliding window and each historical window, and determining target historical access behavior data matched with the current access behavior data according to the matching degree; and identifying the access behavior data according to the target historical access behavior data. According to the technical scheme, the problem of huge calculation amount of terminal access behavior identification is solved, the terminal behavior can be accurately identified, and accurate terminal access behavior data can be obtained through a small amount of calculation amount.

Description

Method and device for identifying terminal access behavior
Technical Field
The invention relates to the technical field of internet, in particular to a method and a device for identifying terminal access behaviors, a computer readable storage medium and computer equipment.
Background
The current DHCP server (DHCP server) mainly uses a static method for leasing an IP address, and the lease time of a terminal is generally 1-2 hours. In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: after the terminal obtains the IP address, the DHCP server does not release the address within the validity period of the address lease, but the behavior of the terminal is different, and the terminal may be offline when the validity period of the address lease is over. Therefore, it is very necessary to identify the terminal behavior, but the history data of the terminal is huge, which results in a huge amount of calculation for identifying the terminal behavior. Therefore, it is necessary to find an accurate identification method of the access behavior of the terminal.
Disclosure of Invention
Based on the method and the device, the terminal access behavior can be accurately identified, and the access behavior data of the terminal can be accurately obtained through a small amount of calculation.
The content of the embodiment of the invention is as follows:
a method for identifying terminal access behaviors comprises the following steps: acquiring current access behavior data and corresponding historical access behavior data of a terminal; the access behavior data comprises access behavior data of the terminal from online to current moment; constructing a sliding window according to the current access behavior data, and sliding the sliding window in the historical access behavior data to obtain a historical window corresponding to the historical access behavior data; respectively calculating the matching degree of the sliding window and each historical window, and determining target historical access behavior data matched with the current access behavior data according to the matching degree; and identifying the access behavior data according to the target historical access behavior data.
In one embodiment, after the step of constructing a sliding window according to the current access behavior data, the method further includes: and acquiring a preset longitudinal time sliding range and a preset transverse time sliding range, and forming a specific time sliding range of the sliding window by the longitudinal time sliding range and the transverse time sliding range.
In one embodiment, three different specific time sliding ranges of the sliding window are formed by the longitudinal time sliding range and the transverse time sliding range; the step of sliding the sliding window in the historical access behavior data includes: sliding the sliding window in historical access behavior data within a first specific time sliding range; the longitudinal time sliding range in the first specific time sliding range is a plurality of months before the current time, the transverse time sliding range is the time range in the set day of each month, and the set day and the time range are determined according to the current time.
In one embodiment, the step of sliding the sliding window in the historical access behavior data includes: sliding the sliding window in the historical access behavior data within a second specific time sliding range; the longitudinal time sliding range in the second specific time sliding range is a plurality of weeks before the current time, the transverse time sliding range is a first set time range of each day, and the first set time range is determined according to the current time.
In one embodiment, the step of sliding the sliding window in the historical access behavior data includes: sliding the sliding window in the historical access behavior data within a sliding range of a third specific time; the longitudinal time sliding range in the third specific time sliding range is a plurality of days before the current time, the transverse time sliding range is a second set time range of each day, and the second set time range is determined according to the current time.
In one embodiment, the step of calculating the matching degree between the sliding window and each history window respectively includes: calculating a first matching degree of the sliding window and each history window in a first specific time sliding range, and judging whether a first matching degree meeting a preset condition exists or not; if not, calculating a second matching degree of the sliding window and each history window in a second specific time sliding range, and judging whether a second matching degree meeting a preset condition exists or not; if not, calculating a third matching degree of the sliding window and each history window in a third specific time sliding range, and judging whether a third matching degree meeting preset conditions exists.
In one embodiment, the step of determining the target historical access behavior data matched with the current access behavior data according to the matching degree includes: and if the matching degree corresponding to a certain history window meets a preset condition, acquiring the history access behavior data corresponding to the history window to obtain the target history access behavior data matched with the current access behavior data.
In one embodiment, the target historical access behavior data includes an online time and an offline time of the terminal, a playing content when the network television is played, and a starting time of the playing content.
In one embodiment, the step of identifying the current access behavior data according to the target historical access behavior data includes: and identifying the access behavior data according to the online time, the offline time, the playing content, the starting time and the playing duration in the target historical access behavior data.
Correspondingly, an embodiment of the present invention provides an apparatus for identifying a terminal access behavior, including: the behavior data acquisition module is used for acquiring the current access behavior data of the terminal and the corresponding historical access behavior data; the access behavior data comprises access behavior data of the terminal from online to current moment; the window sliding module is used for constructing a sliding window according to the current access behavior data and sliding the sliding window in the historical access behavior data to obtain a historical window corresponding to the historical access behavior data; the target behavior data acquisition module is used for respectively calculating the matching degree of the sliding window and each historical window and determining target historical access behavior data matched with the current access behavior data according to the matching degree; and the terminal behavior identification module is used for identifying the access behavior data according to the target historical access behavior data.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method described above, the computer program being stored thereby.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method described above when executing the program.
According to the technical scheme, historical access behavior data of the terminal and the access behavior data after the terminal is online at this time are obtained, and the matching degree of the access behavior data at this time and the historical access behavior data is calculated. And determining target historical access behavior data matched with the current access behavior data according to the matching degree, and identifying the current access behavior data according to the target historical access behavior data. The terminal behavior is accurately identified through the target historical access behavior data which is highly matched with the current behavior data of the terminal, and the access behavior data of the terminal can be accurately obtained through a small amount of calculation.
Drawings
FIG. 1 is a diagram illustrating the actual system processing performance of an operator DHCP server in one embodiment;
FIG. 2 is a schematic flow chart diagram illustrating a method for identifying access behavior of a terminal in one embodiment;
FIG. 3 is a diagram of a sliding window and historical access behavior data in one embodiment;
fig. 4 is a schematic structural diagram of an apparatus for recognizing an access behavior of a terminal in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the invention takes the terminal access behavior identification of the network television as an example, but the terminal access behavior identification method and device of the invention can also be applied to other scenes of terminal access behavior identification.
At present, DHCP address allocation mainly adopts a broadcast mode, and is easy to bring instantaneous peak bandwidth influence on network capacity. In addition, the DHCP server mainly uses a static method for the lease of the IP address, and the lease time of the tv address is generally 1-2 hours. The user behaviors of the television are different, and the processing performance of the DHCP server system has larger peak-to-average difference. In addition, as shown in fig. 1, fig. 1 shows the actual system processing performance of a DHCPServer of a certain operator, and it can be seen that the tv viewing behavior of a user has periodicity. According to actual observation, users generally watch television in cycles of weeks or days.
An embodiment of the present invention provides a method for identifying a terminal access behavior, and as shown in fig. 2, is a schematic flowchart of the method for identifying a terminal access behavior of an embodiment. In this embodiment, a server is taken as an example for explanation, and the method for identifying a terminal access behavior provided in this embodiment mainly includes steps S110 to S140, which are explained in detail as follows:
s110, acquiring current access behavior data of the terminal and corresponding historical access behavior data; the access behavior data comprises access behavior data of the terminal from online to current time.
In this step, the terminal performs a series of operations after getting online, and the terminal obtains corresponding access behavior data according to the operations. At a certain moment (namely the current moment), the terminal sends access behavior data from the online terminal to the server. Meanwhile, the server is provided with a historical access behavior database, and after receiving the access behavior data sent by the terminal, the server acquires the historical access behavior data of the terminal from the historical access behavior database of the server. Optionally, the historical access behavior database is configured to store behavior data of television and video access performed by a user through a terminal, and the server stores the access behavior data into the historical access behavior database after receiving the access behavior data sent by the terminal each time.
Optionally, the terminal may be an electronic device used by a user, such as a television, a computer, a mobile phone, or other devices that need to access a network. Specifically, the terminal is a network television.
Optionally, the access behavior data (including the current access behavior data and the historical access behavior data) may be all access behaviors performed after the terminal is online, and may be behaviors of watching a network television, a video, and the like, and may also be behaviors of listening to music, browsing a web page, and the like. Specifically, the access behavior data is related to the network television played by the terminal, and includes: the playing content C, the starting time Ts and the playing duration Int of the playing content C and the like. The historical access behavior data is related access behavior data in a historical online process before the terminal is online at this time.
Optionally, the terminal may obtain the access behavior data at intervals, and specifically, the terminal obtains the access behavior data generated by the user through the network television at intervals of 1 minute.
S120, a sliding window is constructed according to the current access behavior data, and the sliding window slides in the historical access behavior data to obtain a historical window corresponding to the historical access behavior data.
Optionally, the sliding window is consistent with the current access behavior data, and the sliding process of the sliding window is equivalent to sliding the current access behavior data in the historical access behavior data as a whole. The history window is history access behavior data which are selected one by one in the sliding process of the sliding window.
In the step, a sliding window is constructed, historical access behavior data are selected one by one through sliding of the sliding window, and the matching degree of the current access behavior data and the corresponding multiple historical access behavior data is calculated.
S130, respectively calculating the matching degree of the sliding window and each historical window, and determining target historical access behavior data matched with the current access behavior data according to the matching degree.
The step of calculating the matching degree between the sliding window and each history window comprises the following steps: constructing a sliding window matrix according to the playing content contained in the sliding window, the starting time and the playing duration of the playing content; constructing a history window matrix according to the playing content C contained in the history window, the starting time Ts and the playing duration Int of the playing content C; and calculating a correlation coefficient of the sliding window matrix and the historical window matrix to obtain the matching degree of the sliding window and the corresponding historical window.
The matching degree of the sliding window and each historical window is calculated, target historical access behavior data matched with the current access behavior data are determined according to the matching degree of the current access behavior data and the historical access behavior data of the terminal, and the current access behavior data of the terminal are consistent with the target historical access behavior data.
And S140, identifying the current access behavior data according to the target historical access behavior data.
The access behavior data of this time is consistent with or related to the data type and format of the target historical access behavior data, and the target historical access behavior data is matched with the access behavior data of this time from the terminal being on line to the current moment, so that the access behavior data of this time after the current moment can be considered to be consistent with the historical access behavior data. And identifying the access behavior data of the access behavior data after the current moment according to the target historical access behavior data.
In this embodiment, target historical access behavior data matched with the current access behavior data is determined according to the matching degree between the current access behavior data and the historical access behavior data, and the current access behavior data is identified according to the target historical access behavior data. The terminal behavior can be accurately identified, and the access behavior data of the terminal can be accurately obtained through a small amount of calculation.
In an embodiment, after the step of constructing a sliding window according to the current access behavior data, the method further includes: and acquiring a preset longitudinal time sliding range and a preset transverse time sliding range, and forming a specific time sliding range of the sliding window by the longitudinal time sliding range and the transverse time sliding range.
Wherein, the longitudinal time sliding range refers to longitudinal time, such as: past month, week, etc.; the lateral time sliding range refers to lateral time, such as: 8:00 to 12:00 a day. The vertical time-sliding range and the horizontal time-sliding range constitute a time range (specific time-sliding range) when the sliding window slides in the historical access behavior data. Fig. 3 is a schematic diagram of a sliding window, and as shown in fig. 3, the sliding window (Slide Windows) slides in the past 4 weeks of historical access behavior data. For example, if the vertical time slip range is one month (10 months 1 to 10 months 31 days), and the horizontal time slip range is 8:00 to 12:00 per day, the specific time slip range is 8:00 to 12:00 per day in the past month. Thus, the sliding window slides from 8:00 to 12:00 on day 1 of 10 months, then from 8:00 to 12:00, … … on day 2 of 10 months, and from 8:00 to 12:00 on day 31 of 10 months, and the sliding ends.
The embodiment determines the sliding time range of the sliding window, determines the historical access behavior data corresponding to the current access behavior data in the relevant time, and can effectively reduce the calculation amount of the process of determining the target historical access behavior data.
In one embodiment, three different specific time sliding ranges of the sliding window are formed by the longitudinal time sliding range and the transverse time sliding range; the step of sliding the sliding window in the historical access behavior data includes: sliding the sliding window in historical access behavior data within a first specific time sliding range; the longitudinal time sliding range in the first specific time sliding range is a plurality of months before the current time, the transverse time sliding range is the time range in the set day of each month, and the set day and the time range are determined according to the current time.
Optionally, the set day may be a working day or a double holiday (monday, sunday, etc.) on which the current time is located, or may refer to a day belonging to a certain double holiday, and the set day may be all double holidays, or may be other set days; the time range may be a period of time before or after the current time.
The first specific time-sliding range is exemplified as follows: the current time is 12 months, 15 days and 10:00, the friday can be within a longitudinal time sliding range of 8 months, 14 days and 12 months, 14 days, and the transverse time sliding range can be half an hour before and after the historical time corresponding to the current time in each friday, namely 9: 30-10: 30 of each friday. Therefore, the first specific time slip ranges from 9:30 to 10:30 for every friday in 8 months and 14 days to 12 months and 14 days.
The present embodiment causes the sliding window to slide in the past several months so as to determine the matching relationship between the historical access behavior data and the present access behavior data in the past several months.
In one embodiment, three different specific time sliding ranges of the sliding window are formed by the longitudinal time sliding range and the transverse time sliding range; the step of sliding the sliding window in the historical access behavior data includes: sliding the sliding window in the historical access behavior data within a second specific time sliding range; the longitudinal time sliding range in the second specific time sliding range is a plurality of weeks before the current time, the transverse time sliding range is a first set time range of each day, and the first set time range is determined according to the current time.
Optionally, the first set time range may be a period of time before and after the current time, or a period of time before/after the current time, or may be other times.
The second specific time-sliding range is exemplified as follows: the current time is 12 months, 15 days and 10:00, the longitudinal time sliding range can be 12 months, 8 days to 12 months and 14 days, and the transverse time sliding range can be about half an hour before and after the historical time corresponding to the current time, namely 9:30 to 10: 30. Therefore, the second specific time slip range is 9:30 to 10:30 per day in the range of 12 months and 8 days to 12 months and 14 days.
The present embodiment causes the sliding window to slide in the past several months so as to determine the matching relationship between the historical access behavior data and the present access behavior data in the past several weeks.
In one embodiment, three different specific time sliding ranges of the sliding window are formed by the longitudinal time sliding range and the transverse time sliding range; the step of sliding the sliding window in the historical access behavior data includes: sliding the sliding window in the historical access behavior data within a sliding range of a third specific time; the longitudinal time sliding range in the third specific time sliding range is a plurality of days before the current time, the transverse time sliding range is a second set time range of each day, and the second set time range is determined according to the current time.
Alternatively, the second set time range may be a set time, may be a time before and after the current time, or a time before/after the current time, or may be other times.
The third specific time sliding range is exemplified as follows: the current time is 12 months and 15 days at 10:00, the longitudinal time sliding range can be 12 months and 12 days to 12 months and 14 days, and the transverse time sliding range can be 8:00 to 22:00 every day. Therefore, the third specific time slip range is 8:00 to 22:00 per day in 12 months to 12 months and 14 days.
The present embodiment causes the sliding window to slide in the past several months so as to determine the matching relationship between the historical access behavior data and the present access behavior data in the past several days.
In an embodiment, the step of calculating the matching degree between the sliding window and each history window respectively includes: calculating a first matching degree of the sliding window and each history window in a first specific time sliding range, and judging whether a first matching degree meeting a preset condition exists or not; if not, calculating a second matching degree of the sliding window and each history window in a second specific time sliding range, and judging whether a second matching degree meeting a preset condition exists or not; if not, calculating a third matching degree of the sliding window and each history window in a third specific time sliding range, and judging whether a third matching degree meeting preset conditions exists.
The condition that meets the preset condition may be that the matching degree corresponding to the target historical access behavior data is greater than, equal to, or less than a preset threshold, or may be another condition. Specifically, the condition that the preset condition is met is that the matching degree is more than or equal to 0.7. Of course, the threshold may be other values.
Alternatively, the enormous amount of computation is required to avoid the sliding window Win _ i from traversing all the samples of the historical access behavior data H. In the embodiment, a set of layered capturing algorithm of target historical access behavior data is designed by utilizing the characteristic that a user watches videos and a television has periodicity (as shown in fig. 1). The process of determining the target historical access behavior data can be divided into: the method comprises four parts of monthly calculation, weekly calculation, daily calculation and default links. The specific process is as follows:
and (4) monthly calculation: first, let Win _ i during the last 4 weeks, Ts on the same daynowHistory corresponding to the time of terminal online within half an hourSliding in access behavior data. The process calculates 4 x 1 to 4 hours of data in 1 minute steps. If there is some matching degree max (| R)i| R is not less than 0.7, and max (| R) is obtained according to the matching degreei|) determine target historical access behavior data. If there is no matching degree of 0.7 or more, "week calculation" is performed.
Week calculation: let Win _ i during past 1 week, Ts per daynowAnd sliding in corresponding historical access behavior data within the previous half hour and the next half hour. The correlation coefficient is calculated in the same manner as above, and the process needs to calculate the data amount in 7 × 1 — 7 hours. If there is some matching degree max (| R)i| R is not less than 0.7, and max (| R) is obtained according to the matching degreei|) determine target historical access behavior data. If the matching degree is not more than or equal to 0.7, the day calculation is carried out.
Day calculation: and enabling Win _ i to slide in historical access behavior data corresponding to 8 am to 12 pm in the latest 1 day, wherein the calculation process of the correlation coefficient is the same as that of the historical access behavior data, and the calculation process needs 16 hours of data. If there is some matching degree max (| R)i| R is not less than 0.7, and max (| R) is obtained according to the matching degreei|) determine target historical access behavior data. If the matching degree is not more than or equal to 0.7, entering a default link.
A default link: max (| R) obtained after three times of matching in month, week and dayiAll |) is less than 0.7, which indicates that the current access behavior data of the terminal does not have strong correlation with the historical access behavior data. The access behavior data of the terminal at this time is not identified through the target historical access behavior data.
In the embodiment, when linear matching is performed, three stages of month, week and day calculation are performed successively, and in the three stages, if any one stage can achieve a better matching effect, calculation is terminated, otherwise, a default link is entered. And after target historical access behavior data corresponding to the access behavior data of the terminal after the terminal is on line at this time are found, identifying the access behavior data of the terminal at this time through the target historical access behavior data. And capturing the similar behaviors of the terminal through the maximum linear matching so as to predict the subsequent access behavior data of the terminal. The method can accurately estimate the terminal behavior and determine the basis for data distribution and the like of the terminal.
In an embodiment, the step of determining, according to the matching degree, target historical access behavior data that matches the current access behavior data includes: and if the matching degree corresponding to a certain history window meets a preset condition, acquiring the history access behavior data corresponding to the history window to obtain the target history access behavior data matched with the current access behavior data.
In the course of carrying out monthly calculation, weekly calculation and daily calculation, if a certain matching degree max (| R) can be foundi| R) is more than or equal to 0.7, which shows that the access behavior data of the terminal has stronger repeatability and correlation with the historical access behavior data of a certain past day, then max (| R)iAnd | the corresponding historical access behavior data Win _ max (Tsmax) is determined as the target historical access behavior data.
In the embodiment, when the matching degree meeting the requirement is found, the historical access behavior data corresponding to the matching degree meeting the requirement is determined as the target historical access behavior data, and the target historical access behavior data is considered to be consistent with the access behavior data after the terminal is online at this time.
In an embodiment, the target historical access behavior data includes an online time and an offline time of the terminal, a playing content when the network television is played, and a starting time of the playing content.
The target historical access behavior data comprises an online time Ts of the terminalnowThe off-line time, the playing content C, the start time Ts and the playing duration Int of the playing content C. The current access behavior data and all historical access behavior data of the terminal also include the playing content C, and the start time Ts and the playing duration Int of the playing content C.
The embodiment determines the access behavior data as the related data of the network television, and can accurately determine the video playing behavior of the terminal so as to analyze the relation between the historical access behavior data and the access behavior data and further determine the target historical access behavior data.
In an embodiment, the step of identifying the current access behavior data according to the target historical access behavior data includes: and identifying the access behavior data according to the online time, the offline time, the playing content, the starting time and the playing duration in the target historical access behavior data.
Optionally, the terminal sends an address continuation request to the server at the current time, where the access behavior data of this time is contained in an Option 60 field of the address continuation request sent by the terminal, the Option 60 field in the DHCP request message may be self-defined, the Option 60 field is defined in this embodiment, and the related access behavior data is contained in the Option 60 field of the address continuation request sent by the terminal. The server of this embodiment may be provided with a memory for storing the terminal access behavior data of the user over a period of time. If the terminal access behavior data of 4 weeks is stored and the access behavior data is acquired every 1 minute, the duration of the stored access behavior data is 4 × 7 × 24 × 60 — 40320 minutes in total.
The detailed definition of the Option 60 field may be:
1) ts (start time, unit: time of day): the user plays the starting time of a certain television content through the terminal. The start time was cycled over 24 hours. According to actual requirements, the starting time is accurate to minutes. The DHCP request message uses 2 bytes, which can uniquely indicate the starting time of the user viewing a certain broadcast content in the past 4 weeks.
2) C (playback content, unit: a string of codes): in this embodiment, the playing content is encoded in a manner of "class, 1Byte) -affiliated series (series, 1Byte) -set (episode, 1 Byte)" by using the ID number of the video content watched by the user. Such as:
live broadcast: news simulcast is "news live broadcast-central 1 set-news simulcast program" is 00000001, 00000001, 00000001;
on demand: nominal 1 st set of people is "scenario film on demand-Hua number district-nominal 1 st set of people" 00000100, 00000001, 0000001.
3) Int (viewing duration, unit: minutes): the time a user continuously browses a certain content. One content time is generally not more than 4 hours, and is thus represented by 1 Byte.
Optionally, Ts, C, and Int in the message may also be stored by other byte numbers to store more data or less data.
The specific design of the Option 60 field is as shown in tables 1 and 2:
TABLE 1 DHCP Option 60 field design
Figure BDA0001512716950000111
Table 2 DHCP Option 60 field format description
Field name Length of Content providing method and apparatus
Code 8 60, fixed value
Length 8 Length of the entire message (Byte)
Enterprise Code 16 Enterprise code
Field type 32 Extended Attribute, fixed value 32, custom
Field Length 8 Length of extension field
TS_n Value - 1Byte, custom
C_n Value - 3Byte, custom
Int_n Value - 1Byte, custom
As shown in table 1, the DHCP Option 60 may store access behavior data (Ts1, C1, Int1, Ts2, C2, Int2, Ts3, C3, Int3, … …, Tsn, Cn, Intn) of a plurality of terminals.
In this embodiment, the online time, the offline time, the playing content, the start time, and the playing duration in the target historical access behavior data are used, so that the online time, the offline time, the playing content, the start time, and the playing duration of the terminal can be determined, and relevant parameters such as the IP address continuation time of the terminal after the current time can be adjusted accordingly.
The present embodiment identifies the access behavior data of this time according to the playing content in the target historical access behavior data, and the start time and the playing duration of the playing content. The access behavior data of the network television played by the terminal at this time can be effectively identified through the relevant data of the network television played by the terminal.
Optionally, the access behavior data of this time is identified, and the server returns the access behavior data of this time obtained by identification to the corresponding terminal.
In order to better understand the above method, an application example of the identification method of the terminal access behavior of the present invention is described in detail below.
And acquiring the access behavior data of the terminal from online to the current moment and the corresponding historical access behavior. And constructing a sliding window Win _ i according to the current access behavior data, and sliding the sliding window in the historical access behavior data to obtain a historical window corresponding to the historical access behavior data.
Respectively calculating the matching degree of the sliding window and each historical window, and the specific process is as follows:
1. according to the definition of the fields, the server acquires the past 4 weeks of data of the terminal from a historical access behavior database to obtain historical access behavior data H, and a historical window matrix is constructed:
Figure BDA0001512716950000121
the history window matrix is a 40321 row and 3 column matrix (40321 minutes exist in 4 weeks by taking minutes as a unit, so the rows of the history window matrix are 40321 rows), and the time (online time) when a user starts up at a certain time is recorded as Tsnow. And filling the collected Ts and the corresponding C, Int into the matrix, completing Ts, C and Int which are not watched by the user with 0, and storing the collected data into a historical access behavior database. A diagram of the terminal historical access behavior data is shown in fig. 3 (where Dt represents time). As shown in fig. 3, the playing duration Int1 of the terminal playing content C1 is 30min, Ts1 is the starting time of playing content C1; the playing duration Int1 of the playing content C2 is 18min, and Ts2 is the starting time of the playing content C2; the playing duration Intn of the playing content Cn is j min, and Tsn is the starting time of the playing content Cn.
2. After the user is on line, the terminal system acquires the access behavior data corresponding to the behavior of the terminal since the terminal is on line, and obtains the access behavior data X of the terminal. After normalization processing, the following results are obtained:
Figure BDA0001512716950000131
wherein, T is the default lease time distributed for the terminal by the server when the terminal is on line, the terminal sends the address renewal request to the server when 0.5T, therefore, the access behavior data of the terminal is the terminal from TsnowTo Tsnow+0.5TAccess behavior data in between. Thus, the matrix is a (0.5T +1) row 3 column matrix. The collected Ts and its corresponding C, Int are filled into the matrix, the user does not see Ts of the video, C, Int is completed with 0.
3. Obtaining a matrix corresponding to the sliding window according to the access behavior data X, and obtaining the following result after normalization processing:
Figure BDA0001512716950000132
wherein, Win _ i(0.5T+1)×3(Tsi) Representing a sliding window, TsiThe sliding window is slid at a certain moment in the sliding process.
4. Let Win _ i(0.5T+1)×3(Tsi) Slide in historical access behavior data H, and calculate Win _ i(0.5T+1)×3(Tsi) And X(0.5T+1)×3(Tsnow) Correlation coefficient of (d):
Ri＝Corrcoef(Win_i(0.5T+1)×3(Tsi),X(0.5T+1)×3(Tsnow))，
wherein R isiRepresenting the correlation coefficient of a certain history window and a sliding window, | RiLess than or equal to 1. A sliding window is illustrated in fig. 3, where Win _ end represents the time when the sliding window ends and Win _ start represents the time when the sliding window begins, and as illustrated in fig. 3, the sliding window slides in the past 4 weeks of historical access behavior data.
And determining the target historical access behavior data matched with the current access behavior data according to the matching degree. The calculation process for determining the target historical access behavior data and the terminal offline time corresponding to the target historical access behavior data can be divided into the following steps: the method comprises four parts of monthly calculation, weekly calculation, daily calculation and default links. The specific process is as follows:
and (4) monthly calculation: first, Win _ i Ts the same day in the past 4 weeksnowAnd sliding in corresponding historical access behavior data within the previous half hour and the next half hour. The process calculates 4 x 1 to 4 hours of data in 1 minute steps. If a certain matching degree max (| R) can be foundi| R) is more than or equal to 0.7, which shows that the access behavior data of the terminal has stronger repeatability and correlation with the historical access behavior data of a certain past day, then max (| R)iAnd | the corresponding historical access behavior data Win _ max (Tsmax) is determined as the target historical access behavior data. The target historical access behavior data max (| R)i|) the difference between the down time (history time) immediately following the terminal and the request time (current time when the terminal initiates the address renewal request) is determined as the address renewal time New lease time of the terminal, and the calculation is finished. If there is no matching degree of 0.7 or more, "week calculation" is performed.
Week calculation: ts daily during 1 week of Win _ inowAnd sliding in corresponding historical access behavior data within the previous half hour and the next half hour. The correlation coefficient is calculated in the same manner as above, and the process needs to calculate the data amount in 7 × 1 — 7 hours. If a certain matching degree max (| R) can be foundiIf | is not less than 0.7, then compare with max (| R)i|) the corresponding historical access behavior data is determined as target access behavior data, the difference value between the down time immediately following the terminal in the target historical access behavior data and the current time is calculated, the difference value is determined as the address continuation time NewLeaseTime of the terminal, and the calculation is finished. If the matching degree is not more than or equal to 0.7, the day calculation is carried out.
Day calculation: win _ i slides historical access behavior data corresponding to 8 am to 12 pm in the latest 1 day, and the calculation process of the correlation coefficient is the same as the above, and the process needs 16 hours of data calculation. If a certain matching degree max (| R) can be foundiIf |) is not less than 0.7, determining the address continuation time of the terminal according to the matching degree, wherein the determination process of the address continuation time of the terminal is the same as the above. If the matching degree is not more than or equal to 0.7, entering a default link.
A default link: if the matching is performed three times in the month, week and dayMax (| R) obtained afteriAll |) is less than 0.7, which indicates that the current access behavior data of the terminal does not have strong correlation with the historical access behavior data. The server does not modify the LeaseTime, and the user still adopts the default address renewal time LeaseTime.
The step of determining the address renewal time of the terminal is a process of identifying the access behavior of the terminal according to the target historical access behavior data.
It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present invention is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present invention.
Based on the same idea as the identification method of the terminal access behavior in the above embodiment, the present invention further provides a device for identifying the terminal access behavior, which can be used to execute the identification method of the terminal access behavior. For convenience of explanation, the schematic structural diagram of the embodiment of the apparatus for identifying the access behavior of the terminal only shows a part related to the embodiment of the present invention, and those skilled in the art will understand that the illustrated structure does not constitute a limitation to the apparatus, and may include more or less components than those illustrated, or combine some components, or arrange different components.
As shown in fig. 4, the means for identifying the terminal access behavior includes a behavior data acquiring module 410, a window sliding module 420, a target behavior data acquiring module 430, and a terminal behavior identifying module 440.
A behavior data obtaining module 410, configured to obtain current access behavior data of the terminal and corresponding historical access behavior data; the access behavior data comprises access behavior data of the terminal from online to current time.
And the window sliding module 420 is configured to construct a sliding window according to the current access behavior data, and slide the sliding window in the historical access behavior data to obtain a historical window corresponding to the historical access behavior data.
And a target behavior data obtaining module 430, configured to calculate matching degrees between the sliding window and each historical window, and determine, according to the matching degrees, target historical access behavior data that matches the current access behavior data.
And a terminal behavior identification module 440, configured to identify the current access behavior data according to the target historical access behavior data.
In an embodiment, the apparatus for identifying an access behavior of a terminal further includes a sliding range determining module, configured to obtain a preset longitudinal time sliding range and a preset transverse time sliding range, where the longitudinal time sliding range and the transverse time sliding range form a specific time sliding range of the sliding window.
In an embodiment, the mobile terminal further comprises a specific sliding range determining module, configured to form three different specific time sliding ranges of the sliding window by the longitudinal time sliding range and the transverse time sliding range; the window sliding module 420 comprises a first sliding submodule, which is used for enabling the sliding window to slide in the historical access behavior data within a first specific time sliding range; the longitudinal time sliding range in the first specific time sliding range is a plurality of months before the current time, the transverse time sliding range is the time range in the set day of each month, and the set day and the time range are determined according to the current time.
In an embodiment, the mobile terminal further comprises a specific sliding range determining module, configured to form three different specific time sliding ranges of the sliding window by the longitudinal time sliding range and the transverse time sliding range; the window sliding module 420 comprises a second sliding submodule, which is used for enabling the sliding window to slide in the historical access behavior data within a second specific time sliding range; the longitudinal time sliding range in the second specific time sliding range is a plurality of weeks before the current time, the transverse time sliding range is a first set time range of each day, and the first set time range is determined according to the current time.
In an embodiment, the mobile terminal further comprises a specific sliding range determining module, configured to form three different specific time sliding ranges of the sliding window by the longitudinal time sliding range and the transverse time sliding range; the window sliding module 420 comprises a third sliding submodule, configured to enable the sliding window to slide in the historical access behavior data within a third specific time sliding range; the longitudinal time sliding range in the third specific time sliding range is a plurality of days before the current time, the transverse time sliding range is a second set time range of each day, and the second set time range is determined according to the current time.
In an embodiment, the window sliding module 420 further includes: the first matching degree calculation operator module is used for calculating the first matching degree of the sliding window and each historical window in a first specific time sliding range and judging whether the first matching degree meeting the preset condition exists or not; the second matching degree calculation operator module is used for calculating second matching degrees of the sliding window and each historical window in a second specific time sliding range and judging whether the second matching degrees meeting preset conditions exist or not; and the third matching degree calculation operator module is used for calculating the third matching degree of the sliding window and each historical window in a third specific time sliding range and judging whether a third matching degree meeting preset conditions exists or not.
In an embodiment, the target behavior data obtaining module 430 is configured to, if the matching degree corresponding to a certain history window meets a preset condition, obtain historical access behavior data corresponding to the history window, and obtain target historical access behavior data matched with the current access behavior data.
In an embodiment, the target historical access behavior data includes an online time and an offline time of the terminal, a playing content when the network television is played, and a starting time of the playing content.
In an embodiment, the terminal behavior identification module 440 is configured to identify the current access behavior data according to the online time, the offline time, the playing content, the starting time, and the playing duration in the target historical access behavior data.
It should be noted that, the identification apparatus of the terminal access behavior of the present invention corresponds to the identification method of the terminal access behavior of the present invention one to one, and the technical features and the beneficial effects described in the above embodiments of the identification method of the terminal access behavior are all applicable to the embodiments of the identification apparatus of the terminal access behavior, and specific contents may refer to the descriptions in the embodiments of the method of the present invention, which are not described herein again, and thus are stated herein.
In addition, in the above-mentioned exemplary embodiment of the identification apparatus of the terminal access behavior, the logical division of each program module is only an example, and in practical applications, the above-mentioned function distribution may be performed by different program modules according to needs, for example, due to the configuration requirements of corresponding hardware or the convenience of implementation of software, that is, the internal structure of the identification apparatus of the terminal access behavior is divided into different program modules to perform all or part of the above-described functions.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium and sold or used as a stand-alone product. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It should be noted that the terms "first \ second \ third" related to the embodiments of the present invention are merely used for distinguishing similar objects, and do not represent a specific ordering for the objects, and it should be understood that "first \ second \ third" may exchange a specific order or sequence order if allowed. It should be understood that the terms first, second, and third, as used herein, are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or otherwise described herein.
The terms "comprises" and "comprising," and any variations thereof, of embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or (module) elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-described examples merely represent several embodiments of the present invention and should not be construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A method for identifying terminal access behaviors is characterized by comprising the following steps:
acquiring current access behavior data and corresponding historical access behavior data of a terminal; the access behavior data comprises access behavior data of the terminal from online to current moment;
constructing a sliding window according to the current access behavior data, and sliding the sliding window in the historical access behavior data to obtain a historical window corresponding to the historical access behavior data;
respectively calculating the matching degree of the sliding window and each historical window, and determining target historical access behavior data matched with the current access behavior data according to the matching degree;
identifying the current access behavior data according to the target historical access behavior data;
after the step of constructing a sliding window according to the access behavior data of this time, the method further comprises the following steps:
acquiring a preset longitudinal time sliding range and a preset transverse time sliding range, and forming a specific time sliding range of the sliding window by the longitudinal time sliding range and the transverse time sliding range;
the step of sliding the sliding window in the historical access behavior data includes:
sliding the sliding window in historical access behavior data within a first specific time sliding range; the longitudinal time sliding range in the first specific time sliding range is a plurality of months before the current time, the transverse time sliding range is the time range in the set day of each month, and the set day and the time range are determined according to the current time.
2. The method according to claim 1, wherein the vertical time sliding range and the horizontal time sliding range constitute three different specific time sliding ranges of the sliding window;
the step of sliding the sliding window in the historical access behavior data includes:
sliding the sliding window in the historical access behavior data within a second specific time sliding range; the longitudinal time sliding range in the second specific time sliding range is a plurality of weeks before the current time, the transverse time sliding range is a first set time range of each day, and the first set time range is determined according to the current time.
3. The method for identifying access behavior of a terminal according to claim 2, wherein the step of sliding the sliding window in the historical access behavior data comprises:
sliding the sliding window in the historical access behavior data within a sliding range of a third specific time; the longitudinal time sliding range in the third specific time sliding range is a plurality of days before the current time, the transverse time sliding range is a second set time range of each day, and the second set time range is determined according to the current time.
4. The method for identifying access behaviors of a terminal according to claim 3, wherein the step of calculating the matching degree between the sliding window and each history window respectively comprises:
calculating a first matching degree of the sliding window and each history window in a first specific time sliding range, and judging whether a first matching degree meeting a preset condition exists or not;
if not, calculating a second matching degree of the sliding window and each history window in a second specific time sliding range, and judging whether a second matching degree meeting a preset condition exists or not;
if not, calculating a third matching degree of the sliding window and each history window in a third specific time sliding range, and judging whether a third matching degree meeting preset conditions exists.
5. The method for identifying the terminal access behavior according to claim 4, wherein the step of determining the target historical access behavior data matched with the current access behavior data according to the matching degree comprises the following steps:
and if the matching degree corresponding to a certain history window meets a preset condition, acquiring the history access behavior data corresponding to the history window to obtain the target history access behavior data matched with the current access behavior data.
6. The method according to claim 1, wherein the target historical access behavior data includes an online time and an offline time of the terminal, a playing content when the network television is played, and a starting time of the playing content.
7. The method for identifying the access behavior of the terminal according to claim 6, wherein the step of identifying the access behavior data of this time according to the target historical access behavior data comprises:
and identifying the access behavior data according to the online time, the offline time, the playing content, the starting time and the playing duration in the target historical access behavior data.
8. An apparatus for recognizing access behavior of a terminal, comprising:
the behavior data acquisition module is used for acquiring the current access behavior data of the terminal and the corresponding historical access behavior data; the access behavior data comprises access behavior data of the terminal from online to current moment;
the window sliding module is used for constructing a sliding window according to the current access behavior data and sliding the sliding window in the historical access behavior data to obtain a historical window corresponding to the historical access behavior data;
the target behavior data acquisition module is used for respectively calculating the matching degree of the sliding window and each historical window and determining target historical access behavior data matched with the current access behavior data according to the matching degree;
the terminal behavior identification module is used for identifying the current access behavior data according to the target historical access behavior data;
the device for identifying the terminal access behavior further comprises a sliding range determining module, wherein the sliding range determining module is used for acquiring a preset longitudinal time sliding range and a preset transverse time sliding range, and the longitudinal time sliding range and the transverse time sliding range form a specific time sliding range of the sliding window;
the window sliding module comprises a first sliding submodule and a second sliding submodule, wherein the first sliding submodule is used for enabling the sliding window to slide in historical access behavior data within a first specific time sliding range; the longitudinal time sliding range in the first specific time sliding range is a plurality of months before the current time, the transverse time sliding range is the time range in the set day of each month, and the set day and the time range are determined according to the current time.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for identifying an access behavior of a terminal according to any one of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method for identifying access behavior of a terminal according to any one of claims 1 to 7 when executing the program.
CN201711365115.0A 2017-12-18 2017-12-18 Method and device for identifying terminal access behavior Active CN108124197B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711365115.0A CN108124197B (en) 2017-12-18 2017-12-18 Method and device for identifying terminal access behavior

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711365115.0A CN108124197B (en) 2017-12-18 2017-12-18 Method and device for identifying terminal access behavior

Publications (2)

Publication Number Publication Date
CN108124197A CN108124197A (en) 2018-06-05
CN108124197B true CN108124197B (en) 2020-09-18

Family

ID=62230169

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711365115.0A Active CN108124197B (en) 2017-12-18 2017-12-18 Method and device for identifying terminal access behavior

Country Status (1)

Country Link
CN (1) CN108124197B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110661902B (en) * 2019-09-26 2022-06-03 浪潮商用机器有限公司 Method for monitoring client renewal

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005222111A (en) * 2004-02-03 2005-08-18 Yamaha Corp Portable terminal for av equipment, av equipment and server device
CN102325062A (en) * 2011-09-20 2012-01-18 北京神州绿盟信息安全科技股份有限公司 Abnormal login detecting method and device
CN102752288A (en) * 2012-06-06 2012-10-24 华为技术有限公司 Method and device for identifying network access action
CN103064853A (en) * 2011-10-20 2013-04-24 北京百度网讯科技有限公司 Search suggestion generation method, device and system
CN104468249A (en) * 2013-09-17 2015-03-25 深圳市腾讯计算机系统有限公司 Method and device for detecting abnormal account number
CN107169499A (en) * 2016-03-07 2017-09-15 阿里巴巴集团控股有限公司 A kind of Risk Identification Method and device
CN107194515A (en) * 2017-05-27 2017-09-22 冯小平 Determine user's current behavior and the method and apparatus for predicting user view
CN107241697A (en) * 2017-06-30 2017-10-10 北京奇虎科技有限公司 User behavior for mobile terminal determines method, device and mobile terminal

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005222111A (en) * 2004-02-03 2005-08-18 Yamaha Corp Portable terminal for av equipment, av equipment and server device
CN102325062A (en) * 2011-09-20 2012-01-18 北京神州绿盟信息安全科技股份有限公司 Abnormal login detecting method and device
CN103064853A (en) * 2011-10-20 2013-04-24 北京百度网讯科技有限公司 Search suggestion generation method, device and system
CN102752288A (en) * 2012-06-06 2012-10-24 华为技术有限公司 Method and device for identifying network access action
CN104468249A (en) * 2013-09-17 2015-03-25 深圳市腾讯计算机系统有限公司 Method and device for detecting abnormal account number
CN107169499A (en) * 2016-03-07 2017-09-15 阿里巴巴集团控股有限公司 A kind of Risk Identification Method and device
CN107194515A (en) * 2017-05-27 2017-09-22 冯小平 Determine user's current behavior and the method and apparatus for predicting user view
CN107241697A (en) * 2017-06-30 2017-10-10 北京奇虎科技有限公司 User behavior for mobile terminal determines method, device and mobile terminal

Also Published As

Publication number Publication date
CN108124197A (en) 2018-06-05

Similar Documents

Publication Publication Date Title
CN110134829B (en) Video positioning method and device, storage medium and electronic device
CN101365102B (en) Audience rating statistical method and system based on video content recognition
CN105163142B (en) A kind of user preference determines method, video recommendation method and system
CN104378662B (en) The system and method that a kind of smart television judges the effective viewed programs of user
WO2018187274A1 (en) System and method for determining tv tune-in attribution
WO2004019527A1 (en) Method of content identification, device, and software
KR20170027648A (en) Method and apparatus for synchronous putting of real-time mobile advertisement based on audio fingerprint
CN108197336B (en) Video searching method and device
WO2017161744A1 (en) Video recommendation method and apparatus
CN111327965A (en) Video slicing speed-multiplying playing method, system and storage medium
US11212570B2 (en) Viewing data
JP6792694B1 (en) Equipment, methods and programs for evaluating the effects of TVCM
CN106303591B (en) A kind of video recommendation method and device
CN107222762A (en) A kind of method and apparatus of recommendation of the channels
CN108124197B (en) Method and device for identifying terminal access behavior
US10171326B2 (en) Method and apparatus for estimating a maximum time interval error in a data transmission network
CN113808037A (en) Image optimization method and device
US20180189276A1 (en) System to build advertisement database from unreliable sources
CN110121088A (en) A kind of customer attribute information determines method, apparatus and electronic equipment
CN107864234B (en) Method and device for acquiring address continuation time
CN104935967B (en) The interest recognition methods of video terminal user a kind of and device
CN110996142A (en) Video recall method and device, electronic equipment and storage medium
CN104301759B (en) The acquisition methods and acquisition device of rating duration
CN104410874A (en) A method, a device, and a system for detecting video viscosity information
CN106454398A (en) Video processing method and terminal

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant