阅读说明：本技术 一种家庭网络中识别机顶盒的当前用户的方法及设备 (Method and device for identifying current user of set top box in home network ) 是由 王静 于 2019-01-02 设计创作，主要内容包括：本发明实施例提供了一种家庭网络中识别机顶盒的当前用户的方法及设备,其中,所述方法：获取目标家庭的机顶盒的收视行为数据；获取所述目标家庭的家庭网关下挂的用户设备的网络访问行为数据；对所述收视行为数据与各个用户设备的网络访问行为数据进行比对,确定目标用户设备,将所述目标用户设备对应的用户,作为所述机顶盒的当前用户。本发明实施例在不需要视频或音频采集的情况下,也可以尽可能识别机顶盒的当前实际收视用户,从而无需摄像头、麦克风等采集设备,降低了机顶盒设备的自身硬件成本或外设硬件成本,并且本发明实施例还可以丰富基于“用户画像”的大数据分析系统中单个用户数据和用户特征数据,提升用户推荐系统的应用准确性。(The embodiment of the invention provides a method and equipment for identifying a current user of a set top box in a home network, wherein the method comprises the following steps: acquiring viewing behavior data of a set top box of a target family; acquiring network access behavior data of user equipment hung under a home gateway of the target family; and comparing the viewing behavior data with the network access behavior data of each user equipment, determining target user equipment, and taking the user corresponding to the target user equipment as the current user of the set top box. The embodiment of the invention can also identify the current actual viewing user of the set top box as far as possible under the condition of not needing video or audio acquisition, thereby needing no acquisition equipment such as a camera, a microphone and the like, reducing the hardware cost of the set top box equipment or the external hardware cost, enriching single user data and user characteristic data in a big data analysis system based on 'user portrait', and improving the application accuracy of a user recommendation system.)

1. A method for identifying a current user of a set-top box in a home network, comprising:

acquiring viewing behavior data of a set top box of a target family, wherein the viewing behavior data comprises playing duration and/or playing content type and playing time of the set top box playing at this time;

acquiring network access behavior data of user equipment hung under a home gateway of the target family, wherein the network access behavior data comprises active time of network access behavior of the user equipment;

comparing the viewing behavior data with the network access behavior data of each user equipment, determining target user equipment, and taking a user corresponding to the target user equipment as a current user of the set top box;

the coincidence degree of the active time of the network access behavior of the target user equipment and the playing duration of the current playing of the set top box is lowest, or the coincidence degree of the active time of the network access behavior of the target user equipment and the playing time of the preset type content of the set top box is highest.

2. The method of claim 1,

the content types played by the set top box comprise one or more of a program list, a non-episode program and a multi-episode program;

the active time of the network access behavior comprises: the data rate exceeds a first access time of the network access behavior of a preset first threshold, and/or the access rate of the preset website exceeds a second access time of the network access behavior of a preset second threshold.

3. The method as claimed in claim 2, wherein when the number of the user equipments hooked down by the home gateway of the target home is 1, the step of comparing the viewing behavior data with the network access behavior data of each user equipment to determine the target user equipment comprises:

and directly taking the user equipment hung down by the home gateway of the target family as the target user equipment.

4. The method as claimed in claim 3, wherein when the number of the user equipments hooked down by the home gateway of the target home is greater than 1, the step of comparing the viewing behavior data with the network access behavior data of each user equipment to determine the target user equipment comprises:

and solving intersection between the playing duration of the playing of the set top box at this time and the active time of the network access behavior of each user equipment to obtain a coincidence time period, and taking the user equipment corresponding to the minimum coincidence time period as the target user equipment.

5. The method according to claim 4, wherein the step of solving an intersection between the playing duration of the current playing of the set top box and the active time of the network access behavior of each user equipment to obtain a coincidence time period, and using the user equipment corresponding to the minimum coincidence time period as the target user equipment specifically includes:

taking the first access time as the active time, calculating the coincidence time period, and taking the user equipment corresponding to the minimum coincidence time period as the target user equipment;

and if the target user equipment cannot be determined by taking the first access time as the active time, calculating the overlapping time period by taking the second access time as the active time, and taking the user equipment corresponding to the minimum overlapping time period as the target user equipment.

6. The method as claimed in claim 3, wherein when the number of the user equipments hooked down by the home gateway of the target home is greater than 1, the step of comparing the viewing behavior data with the network access behavior data of each user equipment to determine the target user equipment comprises:

determining the playing time of preset type content according to the content type played by the set top box at this time and the playing time of the content, wherein the preset content is non-episode-like programs played among multi-episode-like programs;

and respectively calculating the active time of the network access behavior of each user equipment and the contact ratio of the active time and the playing time of the preset type content, and taking the user equipment corresponding to the highest contact ratio as the target user equipment.

7. The method according to claim 6, wherein the step of respectively calculating the active time of the network access behavior of each ue and the overlap ratio of the playing time of the preset type of content, and using the ue with the highest overlap ratio as the target ue specifically comprises:

taking the first access time as the active time, calculating the contact ratio, and taking the user equipment corresponding to the highest contact ratio as the target user equipment;

and if the target user equipment cannot be determined by taking the first access time as the active time, calculating the contact ratio by taking the second access time as the active time, and taking the user equipment corresponding to the highest contact ratio as the target user equipment.

8. The method according to claim 6 or 7, wherein the step of calculating the overlap of the active time of the network access behavior of each user equipment and the playing time of the preset type of content comprises:

calculating a first absolute value of a difference value between the starting time of the active time of the network access behavior corresponding to the user equipment and the starting time of the playing time of the preset type content, calculating a second absolute value of a difference value between the ending time of the active time of the network access behavior corresponding to the user equipment and the ending time of the playing time of the preset type content, and calculating the first absolute value and the second absolute value to obtain a sum; determining the degree of coincidence according to the sum, wherein the degree of coincidence is inversely related to the sum.

9. A user identification server, comprising:

the system comprises a receiving and sending unit, a playing unit and a playing unit, wherein the receiving and sending unit is used for acquiring viewing behavior data of a set top box of a target family, and the viewing behavior data comprises the playing duration and/or the playing content type and the playing time of the playing of the set top box at this time; acquiring network access behavior data of user equipment hung under a home gateway of the target family, wherein the network access behavior data comprises active time of network access behavior of the user equipment;

the processor is used for comparing the viewing behavior data with the network access behavior data of each user equipment, determining target user equipment and taking a user corresponding to the target user equipment as a current user of the set top box;

the coincidence degree of the active time of the network access behavior of the target user equipment and the playing duration of the current playing of the set top box is lowest, or the coincidence degree of the active time of the network access behavior of the target user equipment and the playing time of the preset type content of the set top box is highest.

10. The user identification server of claim 9,

the content types played by the set top box comprise one or more of a program list, a non-episode program and a multi-episode program;

the active time of the network access behavior comprises: the data rate exceeds a first access time of the network access behavior of a preset first threshold, and/or the access rate of the preset website exceeds a second access time of the network access behavior of a preset second threshold.

11. The user identification server of claim 10,

the processor is further configured to directly use the user equipment hooked up by the home gateway of the target home as the target user equipment when the number of the user equipment hooked up by the home gateway of the target home is 1.

12. The user identification server of claim 11,

the processor is further configured to, when the number of the user equipment hung under the home gateway of the target home is greater than 1, solve an intersection between the playing duration of the current playing of the set top box and the active time of the network access behavior of each user equipment to obtain a coincidence time period, and use the user equipment corresponding to the minimum coincidence time period as the target user equipment.

13. The user identification server of claim 12,

the processor is further configured to calculate the overlapping time period by taking the first access time as the active time, and take the user equipment corresponding to the minimum overlapping time period as the target user equipment; and if the target user equipment cannot be determined by taking the first access time as the active time, calculating the overlapping time period by taking the second access time as the active time, and taking the user equipment corresponding to the minimum overlapping time period as the target user equipment.

14. The user identification server of claim 11,

the processor is further configured to determine a playing time of a preset type of content according to the content type and the playing time of the set top box played this time when the number of the user equipment hung under the home gateway of the target home is greater than 1, where the preset content is a non-episode program played among the multi-episode programs; and respectively calculating the active time of the network access behavior of each user equipment and the contact ratio of the active time and the playing time of the preset type content, and taking the user equipment corresponding to the highest contact ratio as the target user equipment.

15. The user identification server of claim 14,

the processor is further configured to calculate the contact ratio by using the first access time as the active time, and use the ue corresponding to the highest contact ratio as the target ue; and if the target user equipment cannot be determined by taking the first access time as the active time, calculating the contact ratio by taking the second access time as the active time, and taking the user equipment corresponding to the highest contact ratio as the target user equipment.

16. The user identification server according to claim 14 or 15,

the processor is further configured to calculate a first absolute value of a difference between a start time of an active time of the network access behavior corresponding to the user equipment and a start time of the playing time of the preset type of content, calculate a second absolute value of a difference between an end time of the active time of the network access behavior corresponding to the user equipment and an end time of the playing time of the preset type of content, and calculate the first absolute value and the second absolute value to obtain a sum; determining the degree of coincidence according to the sum, wherein the degree of coincidence is inversely related to the sum.

17. A user identification server, comprising: memory, processor and computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the method according to any one of claims 1 to 9.

18. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 9.

Technical Field

The invention relates to the technical field of mobile communication, in particular to a method and equipment for identifying a current user of a set top box in a home network.

Background

With the development of internet televisions, set-top boxes (or smart televisions, the same below) can provide more and more video programs (such as real-time television programs, network-on-demand programs, and the like) for users, and enable the users to select desired video programs according to their preferences at any time through the capability of bidirectional interaction. Meanwhile, in order to recommend videos which the user is interested in quickly and accurately, reduce program searching time of the user and guide the user to watch more videos, a user portrait video program recommendation technology based on big data analysis is often used in the industry to analyze user characteristics and recommend the video program list for the user characteristics, so that the user watching activity of the user internet television is improved.

When a user database is constructed by the technology of 'user portrait' based on big data analysis, firstly, viewing data of each user on a set top box needs to be collected, but because the set top box is a terminal device which is usually placed in the home of the user and is possibly used by multiple people, it is better to know which user in the home of the user currently using the set top box is in a link of collecting the viewing data of the user portrait and a link of recommending a program of a video list for a specific user. For example, the respective viewing behaviors of parents and children in three families may be completely different, and the viewing of a program by a plurality of persons may be different from the viewing of a program by a single user, so that it is necessary to construct a "user profile" according to the difference of the current viewing users.

Disclosure of Invention

The invention provides a method and equipment for identifying a current user of a set top box in a home network, which are used for identifying the current actual viewing user of the set top box under the condition of not increasing hardware cost, thereby laying a key technical foundation for a video program recommendation technology based on user portrait.

To solve the above technical problem, an embodiment of the present invention provides the following solutions:

a method of identifying a current user of a set top box in a home network, comprising:

acquiring viewing behavior data of a set top box of a target family, wherein the viewing behavior data comprises playing duration and/or playing content type and playing time of the set top box playing at this time;

acquiring network access behavior data of user equipment hung under a home gateway of the target family, wherein the network access behavior data comprises active time of network access behavior of the user equipment;

comparing the viewing behavior data with the network access behavior data of each user equipment, determining target user equipment, and taking a user corresponding to the target user equipment as a current user of the set top box;

the coincidence degree of the active time of the network access behavior of the target user equipment and the playing duration of the current playing of the set top box is lowest, or the coincidence degree of the active time of the network access behavior of the target user equipment and the playing time of the preset type content of the set top box is highest.

The embodiment of the invention also provides a user identity recognition server, which comprises:

the system comprises a receiving and sending unit, a playing unit and a playing unit, wherein the receiving and sending unit is used for acquiring viewing behavior data of a set top box of a target family, and the viewing behavior data comprises the playing duration and/or the playing content type and the playing time of the playing of the set top box at this time; acquiring network access behavior data of user equipment hung under a home gateway of the target family, wherein the network access behavior data comprises active time of network access behavior of the user equipment;

the processor is used for comparing the viewing behavior data with the network access behavior data of each user equipment, determining target user equipment and taking a user corresponding to the target user equipment as a current user of the set top box;

the coincidence degree of the active time of the network access behavior of the target user equipment and the playing duration of the current playing of the set top box is lowest, or the coincidence degree of the active time of the network access behavior of the target user equipment and the playing time of the preset type content of the set top box is highest.

The embodiment of the invention also provides another user identity identification server, which comprises: a processor, a memory storing a computer program which, when executed by the processor, performs the method of identifying a current user of a set-top box in a home network as described above.

An embodiment of the present invention further provides a computer-readable storage medium, which includes instructions, and when the instructions are executed on a computer, the instructions cause the computer to execute the method for identifying the current user of the set top box in the home network.

The technical scheme of the embodiment of the invention has the beneficial effects that:

the embodiment of the invention can also identify the current actual audience users of the set top box as much as possible under the condition of not needing video or audio acquisition, thereby needing no acquisition equipment such as a camera, a microphone and the like and reducing the hardware cost of the set top box equipment or the peripheral hardware cost. In addition, the embodiment of the invention can acquire the MAC address of the corresponding user individual equipment or other terminal information of the equipment based on the online behavior data of the user individual equipment in the gateway down-hanging equipment acquired by the home gateway soft probe when matching with the set top box watching user, so that the watching record on the set top box can be combined with the user behavior data of the user video application or other applications on the individual equipment, the single user data and the user characteristic data in the big data analysis system based on the user portrait are enriched, and the application accuracy of the user recommendation system is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.

Fig. 1 is a schematic diagram of an application scenario of the method according to the embodiment of the present invention;

fig. 2 is a schematic flow chart of a method for identifying a current user of a set-top box in a home network according to an embodiment of the present invention;

FIG. 3 illustrates an exemplary diagram of rule 1 provided by an embodiment of the present invention;

FIG. 4 illustrates an exemplary diagram of rule 2 provided by an embodiment of the present invention;

FIG. 5 illustrates an exemplary diagram of rule 3 provided by an embodiment of the present invention;

fig. 6 is a schematic structural diagram of a user identification server according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of a user identification server according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. In the description and in the claims "and/or" means at least one of the connected objects.

The method for identifying the current user of the set top box in the home network provided by the embodiment of the invention monitors the viewing behavior data generated by the user at the set top box, collects the network access behavior data of the internet access behavior of the user equipment hung below the gateway at the home gateway, and comprehensively judges which user equipment in a family corresponds to the current viewing user of the set top box by combining the viewing behavior data and the network access behavior data.

Referring to fig. 1, a schematic view of an application scenario of the method for identifying a current user of a set top box in a home network according to the embodiment of the present invention is shown. As shown in fig. 1, a home network includes a home gateway, to which a plurality of user devices (e.g., a mobile phone 1, a mobile phone 2, a smart watch, etc.) access, and a network (e.g., the internet) is accessed through the home gateway. The user equipment and the home gateway may be connected in a wired or wireless manner, and the user equipment connected to the home gateway is also referred to as the user equipment hung down by the home gateway. The home network also comprises a set-top box, and the set-top box is used for providing internet television programs (including real-time television programs, network on-demand programs and other contents). In the embodiment of the invention, the set-top box can be a device independent of the intelligent television, and at the moment, the set-top box is also connected with the intelligent television. Of course, the set top box may also be integrated in the smart television as a functional module of the smart television, which is not specifically limited in this embodiment of the present invention.

Fig. 1 also includes a user identification server, which may be located in the home network, specifically, may be an independent device in the home network, or may be a functional module integrated in the home gateway, the set-top box, or the smart television. The user identification server is used for identifying the current user of the set top box, namely the user who watches programs through the set top box currently. In fig. 1, the user identification server may also be connected to a user video program recommendation system on the network side, and the user video program recommendation system is further connected to a set top box. User video program recommendation systems are typically located on the network side. Of course, the user video program recommendation system in the embodiment of the present invention may be an independent device in a home network, or may also be a functional module integrated in a home gateway, a set top box, or an intelligent television, at this time, the user video program recommendation system may be connected to a network to obtain a video program from the network, which is not specifically limited in the embodiment of the present invention. In the embodiment of the invention, the user video program recommendation system can receive the identification result of the user identification server and recommend the video program to the set top box according to the identification result.

Referring to fig. 2, a method for identifying a current user of a set top box in a home network according to an embodiment of the present invention includes:

step 21, obtaining the viewing behavior data of the set top box of the target family, wherein the viewing behavior data comprises the playing duration and/or the playing content type and the playing time of the set top box playing this time.

After the set-top box is started, the embodiment of the invention executes the steps 21-23 to determine the current user of the set-top box. The playing of the set top box at this time refers to a playing process started from the last startup of the set top box. The type of content played by the set-top box may generally include one or more of a program guide, an non-episode-like program, and a multi-episode-like program.

Specifically, the program list refers to a page or a menu for displaying program information (such as a program name, a schedule for scheduling the program to be played, and the like), and may also be a menu interface of the set top box (such as a menu at each level of the set top box, a search page including program content, and the like). The non-episode program refers to a program of a single episode (i.e., a non-continuous multi-episode), and may specifically be a program of an advertisement, news, a single-episode movie, or the like. The multi-episode program is a continuous multi-episode program with at least two levels, and the continuous multi-episode program refers to a play order relationship between multi-episode programs, for example, a multi-episode series or a multi-episode movie (e.g., a movie includes 3 levels in the top, middle and bottom). In the embodiment of the invention, the soft probe is arranged at the set top box, and the playing duration after the set top box is started, the type of the played content, the playing time of each content and other information are collected.

Step 22, obtaining network access behavior data of the user equipment hung down from the home gateway of the target home, where the network access behavior data includes active time of the network access behavior of the user equipment.

Here, the user device may be a smartphone, a smart watch, a tablet computer, a notebook computer, or the like, in general. These user equipments are usually strongly correlated with a certain user, i.e. the user who usually uses these user equipments is a certain fixed user. In the embodiment of the invention, the stronger the correlation between the user equipment and the user is, the more accurate the final recognition result is.

In this embodiment of the present invention, the active time of the network access behavior may specifically include: the data rate exceeds a first access time of the network access behavior of a preset first threshold, and/or the access rate of the preset website exceeds a second access time of the network access behavior of a preset second threshold.

The first access time refers to a specific time (e.g., start-stop time) of a network access behavior in which a data rate of the network access exceeds a certain predetermined first threshold, and the second access time refers to a specific time (e.g., start-stop time) of a network access behavior in which an access rate to a preset website exceeds a second threshold. Here, the first and second thresholds may be set according to the history data of the corresponding access behavior, for example, the first threshold may be set according to an average rate of the network access behavior of the user equipment, and may be a certain number (n may be a positive number greater than 1) greater than n times the average rate, for example. For another example, the second threshold is an access rate for a preset website (e.g., a WWW website or an instant messaging server), where the preset website may select a website that is most frequently browsed by the user equipment according to a history of network access of the user equipment. Specifically, the browsing frequency may be parameters such as browsing accumulated time and/or browsing accumulated times, and when multiple parameters are used as the indexes, the parameters may be weighted and summed to obtain a final browsing frequency value. In the embodiment of the present invention, the preset websites corresponding to different user devices may be the same or different.

It should be noted that there is no strict requirement on the execution sequence of the above steps 21 and 22, and any one of the above two steps may be executed first or simultaneously in the embodiment of the present invention.

Step 23, comparing the viewing behavior data with the network access behavior data of each user equipment, determining a target user equipment, and using a user corresponding to the target user equipment as a current user of the set top box;

the coincidence degree of the active time of the network access behavior of the target user equipment and the playing duration of the current playing of the set top box is lowest, or the coincidence degree of the active time of the network access behavior of the target user equipment and the playing time of the preset type content of the set top box is highest.

Here, the current user of the set top box is a user corresponding to the target user equipment, and since the user equipment and the user (i.e. user) thereof usually have a relatively fixed corresponding relationship, as an optimal manner, the device identifier (such as a MAC address, a device serial number, etc.) of the target user equipment may be directly used as the identity identifier of the current user.

Through the above steps, in step 23, the embodiment of the present invention combines the viewing behavior data of the set top box and the network access behavior data of the user equipment, and comprehensively determines which user equipment corresponds to the current viewing user of the set top box in the family, so that the current user of the set top box can be determined more accurately without adding extra hardware in the existing home network, and further, a key technical basis is laid for the video program recommendation technology based on the user portrait.

In step 23, the target ue may be determined according to different rules.

For example, when the number of the user devices hooked down by the home gateway of the target home is 1, in step 23, the user devices hooked down by the home gateway of the target home may be directly used as the target user devices.

For another example, when the number of the user devices hooked under the home gateway of the target home is greater than 1, in step 23, an intersection may be solved between the playing duration of the current playing of the set top box and the active time of the network access behavior of each user device, so as to obtain a coincidence time period, and the user device corresponding to the minimum coincidence time period is used as the target user device.

Here, when the above overlapping time period is solved and the target user equipment is determined, the first access time may be used as the active time, the overlapping time period may be calculated, and the user equipment corresponding to the minimum overlapping time period may be used as the target user equipment. If the first access time is used as the active time, obtaining a plurality of overlapping time periods with the same duration and the smallest duration value, for example, if the durations of the overlapping time periods corresponding to 2 or more user devices are all 0, the target user device cannot be determined according to the first access time, at this time, the second access time may be used as the active time, the overlapping time periods are calculated, and the user device corresponding to the smallest overlapping time period is used as the target user device.

In the implementation mode, the most possible current user of the set top box is found by utilizing the characteristic that the audience users of the set top box generally have less internet surfing behaviors of personal user equipment.

For another example, when the number of the user equipments hung under the home gateway of the target home is greater than 1, in step 23, the playing time of a preset type of content may be determined according to the type of the content played by the set top box this time and the playing time thereof, where the preset content is a non-episode program (such as an advertisement) played among multiple-episode programs; and respectively calculating the active time of the network access behavior of each user equipment and the contact ratio of the active time and the playing time of the preset type content, and taking the user equipment corresponding to the highest contact ratio as the target user equipment.

Similarly, when the contact ratio is solved and the target ue is determined, the contact ratio may be calculated by using the first access time as the active time, and the ue corresponding to the highest contact ratio may be used as the target ue. If the first access time is taken as the active time, a plurality of values are the same, and the highest-value contact ratio is adopted, the target user equipment cannot be determined according to the first access time, at this time, the second access time can be taken as the active time to calculate the contact ratio, and the user equipment corresponding to the highest contact ratio is taken as the target user equipment.

Optionally, as an implementation manner of the overlap ratio calculation, in the embodiment of the present invention, a first absolute value of a difference between a start time of an active time of a network access behavior corresponding to the user equipment and a start time of a play time of the preset type of content may be calculated, a second absolute value of a difference between an end time of the active time of the network access behavior corresponding to the user equipment and an end time of the play time of the preset type of content may be calculated, and the first absolute value and the second absolute value are calculated to obtain a sum; determining the degree of coincidence from the sum, wherein the degree of coincidence is inversely related to the sum, i.e. the greater the sum, the lower the degree of coincidence; conversely, the smaller the sum, the higher the degree of coincidence.

In this implementation, the preset type of content is generally content with a low user viewing desire, for example, a non-episode program (such as an advertisement) that is inserted between multiple-episode programs to be played, and a current user of the set-top box generally uses personal user equipment to surf the internet to play time during the playing process of the non-episode program.

Next, the above method of the embodiment of the present invention is described in more detail by a specific example with reference to fig. 1. The flow steps of this example are as follows:

step S1, after the set-top box is turned on, the user viewing behavior monitoring module in the "soft probe" in the set-top box may set a key viewing behavior mode according to the preset, for example: viewing behavior patterns such as program list viewing behavior, starting to view a certain video program, ending to view a certain video program, entering non-episode programs (such as advertisement time slots between two television episodes) in a multi-episode program and the like, and monitoring whether a certain key viewing behavior pattern occurs in the set top box.

Step S2, when one or more key viewing behavior patterns occur in the set-top box, recording detailed information of the viewing behavior patterns and occurring time information (start time, end time), reporting viewing behavior pattern data (such as key viewing behavior pattern category and time information) to a viewing behavior collection module of the user identity recognition server, and forwarding the viewing behavior collection module to a viewing user recognition module.

Specifically, the detailed information of the viewing behavior pattern may include the following categories:

1) viewing behavior pattern 1, corresponding to program listings viewing: the user browses and views the program list of the set-top box (such as an 'on-screen desktop' system introduced by the program of the set-top box) or searches a certain specific program through the set-top box;

2) viewing behavior mode 2, corresponding to watching non-episode programs, wherein a user watches certain non-episode television programs, possibly movies, news and other programs of a single episode, through a set top box;

3) viewing behavior pattern 3, corresponding to the interrupted viewing of the multi-episode program: the user continuously watches the multi-episode content of a certain multi-episode program through the set-top box, wherein non-episode programs may be interspersed among the multi-episode programs.

Step S3, after receiving the key viewing behavior mode reported by the set-top box, the viewing user identification module at the user identity identification server side acquires the data information of various user internet access behaviors, namely the network access behavior data, of all user equipment (specifically, user individual equipment) in the home network, which is acquired by a soft probe in the home gateway in the home network where the set-top box is located;

1) user-individual device: generally, the set top box is internet access equipment which is only used by a single user, such as a smart phone, a smart watch and the like, and the current set top box user can be distinguished through user individual equipment; the 'watching user identification module' of the user identity identification server side can count how many individual users exist in the user family based on the daily reported data of the home gateway, and can identify the user identity by using the MAC address or other terminal information of the user individual equipment reported by the soft probe of the home gateway.

2) The user internet behavior data pattern, which corresponds to the internet behavior and duration of a specific user device, may specifically include:

2.1) data pattern A: whether the user equipment is at home and the duration interval of network access when the user equipment is at home;

2.2) data pattern B: the user equipment generates a sudden increase event with the internet surfing rate suddenly increasing compared with the average value of the internet surfing rate on the day and a duration interval of the sudden increase event, for example, when the internet surfing rate exceeds 1.2 times of the average value of the internet surfing rate on the day, the user equipment judges that the sudden increase event occurs;

2.3) data mode C: the user equipment generates the condition that the access rate to the preset service website (WWW, WeChat and the like) is suddenly increased compared with the average value of the daily internet access rate and the duration time interval.

Step S4, the "viewing user identification module" at the user identification server combines the viewing behavior pattern data provided by the set-top box probe and the at-home situation and the internet access rate of the user individual device provided by the gateway soft probe, and can determine which (or which) user individual device the current set-top box user may correspond to based on the following rules:

1) rule 1-only a single individual device under the gateway: if the viewing behavior events of the viewing behavior pattern 1 and the viewing behavior pattern 2 occur, when only one individual device is in the home of the user, the set-top box viewing user is the user of the individual device, that is: the individual device behavior pattern of the data from the gateway probe is the data pattern a, and correspondingly, the time matching degree of the two patterns is high (the time interval of the data pattern a covers the time interval of viewing behavior pattern 1+ viewing behavior pattern 2), and a schematic diagram of the rule 1 is shown in fig. 3.

For example, the viewing behavior pattern parameters defining the set-top box probe data are as follows:

t mode N-begin: a start time of the viewing behavior pattern N;

t-mode N-end: the end time of the viewing behavior pattern N;

the parameters of the network access behavior mode of the gateway probe data are defined as follows:

mode A-begin: the starting time of the network online of the individual device hung down by the gateway;

mode A-end: the online end time of the individual device network hung down by the gateway;

rule 1, namely: when 1 to N viewing behaviors are continuous, the starting time of the earliest viewing behavior and the ending time of the last viewing behavior are taken to obtain the viewing behavior mode time duration interval: [ T mode 1-begin, T mode N-end ], intersecting the parameter with the duration of the on-line behavior mode of only one off-hook individual device of the gateway probe in the family,

[ T mode 1-begin, T mode N-end ] & [ X mode 1-begin, X mode N-end ]

And obtaining the terminal with the intersection duration, wherein the probability of the watching user of the current watching behavior of the set top box is the highest. When only one individual device is hung down, the individual device can also be directly used as a watching user of the current watching behavior of the set top box.

2) Rule 2-there are multiple individual devices under the gateway:

a) viewing behavior pattern 1 and viewing behavior pattern 2: if the viewing behavior events of the viewing behavior pattern 1 and the viewing behavior pattern 2 occur, when a plurality of individual devices exist in the user's home, the internet access behavior data pattern B is preferentially adopted for analysis, and it is determined which individual device has a low overlap ratio between the internet access interval and the time interval of the viewing behavior event, and it can be determined that the set-top box viewing user is the individual device user, and a schematic diagram of the rule 2 is shown in fig. 4. And if the data pattern B cannot be distinguished, adopting data pattern C for analysis, wherein the distinguishing modes are the same.

It should be noted that the difference between the data pattern B and the data pattern C is that the access of a specific website is more suitable for the behavior habit of the user in the process of watching a video program, such as the fragmentation time of the user (e.g. the interval time of advertisement, trailer, etc. between two episodes).

Rule 2, namely: when a plurality of individual devices exist, the data of the watching mode is collected: when 1 to N viewing behaviors are continuous, the starting time of the earliest viewing behavior and the ending time of the last viewing behavior are taken to obtain the viewing behavior mode time duration interval: [ T mode 1-begin, T mode N-end ], then collecting the internet behavior mode data of a plurality of terminals: [ T mode B-begin, T mode B-end ], respectively intersecting the parameter with the time duration of the network behavior mode of all the off-hook individual devices of the gateway probe in the family:

[ T mode 1-begin, T mode N-end ] & & (all of the [ T mode B-begin, T mode B-end ] of terminal X),

the terminal with the minimum intersection duration (i.e. the terminal with the minimum occurrence probability of the internet speed sudden increase situation in the viewing behavior) can be obtained, and the probability of the viewing user of the current viewing behavior is the highest.

3) Rule 3: adapted to viewing behavior pattern 3:

if an audience behavioral event of an audience behavioral pattern 3 occurs (non-program videos such as advertisements which are separated between two television episodes appear in the audience behavioral event), when a plurality of individual devices are arranged in a user house, if the coincidence degree of time intervals of the internet surfing behavioral data pattern B of a certain individual device and the non-program video contents (such as head and tail songs, advertisements and the like) separated between two television episodes in the audience behavioral event of the audience behavioral pattern 3 is high, a set top box audience user can be judged to be the individual device user; a schematic diagram of this rule 3 is shown in fig. 5.

Similar to the step a, if the data pattern B can not be distinguished, the data pattern C is adopted for analysis, and the distinguishing mode is the same.

Rule 3 is: when a plurality of individual devices exist, viewing mode data is collected first. For example, in the viewing behavior event of the viewing behavior pattern 3, the non-program video content (such as the beginning and end of a tv episode, advertisement, etc.) in the interval between two tv episodes takes the duration of the non-program video content: [ T mode 1-begin, T mode N-end ]; and then collecting the internet behavior mode data of a plurality of terminals: [ T mode B-begin, T mode B-end ]; then, the duration interval of the watching mode 3 non-program video content and the duration interval of the online behavior mode time of all the off-hook individual devices of the gateway probe in the family are summed according to the following formula:

i T mode 1-begin-T mode B-begin | + | T mode N-end-T mode B-end | + | T

And obtaining a terminal with the minimum sum of the absolute values of the two time differences, namely the terminal with the highest time coincidence degree between the non-program video content and the Internet surfing rate surge condition, wherein the terminal is the terminal with the highest probability of watching users of the current watching behavior.

Step S5, the "viewing user identification module" of the user identification server may also synchronize the identified current set-top box viewing user identifier to the "user video program recommendation system", and the user video program recommendation system may match the current set-top box viewing user behavior (played video program, viewing duration, etc.) with the user identifier, that is, may be used for "user image" big data analysis based on a specific individual user, to improve the function of the video program recommendation system.

It can be seen from the above that, in the embodiments of the present invention, the current actual viewing user of the set-top box can be identified as much as possible without video or audio acquisition, so that acquisition devices such as a camera and a microphone are not required, and the hardware cost of the set-top box device itself or the peripheral hardware cost is reduced. In addition, the embodiment of the invention can acquire the MAC address of the corresponding user individual equipment or other terminal information of the equipment based on the online behavior data of the user individual equipment in the gateway down-hanging equipment acquired by the home gateway soft probe when matching with the set top box watching user, so that the watching record on the set top box can be combined with the user behavior data of the user video application or other applications on the individual equipment, the single user data and the user characteristic data in the big data analysis system based on the user portrait are enriched, and the application accuracy of the user recommendation system is improved.

An apparatus for carrying out the above method is provided further below with reference to the accompanying drawings.

Referring to fig. 6, an embodiment of the present invention further provides a user identification server 60, which includes a transceiver unit 62 and a processor 61. Wherein the content of the first and second substances,

the receiving and sending unit 62 is configured to obtain viewing behavior data of a set top box of a target family, where the viewing behavior data includes a playing duration and/or a playing content type and a playing time of the set top box playing this time; acquiring network access behavior data of user equipment hung under a home gateway of the target family, wherein the network access behavior data comprises active time of network access behavior of the user equipment;

the processor 61 is configured to compare the viewing behavior data with network access behavior data of each user equipment, determine a target user equipment, and use a user corresponding to the target user equipment as a current user of the set top box;

the coincidence degree of the active time of the network access behavior of the target user equipment and the playing duration of the current playing of the set top box is lowest, or the coincidence degree of the active time of the network access behavior of the target user equipment and the playing time of the preset type content of the set top box is highest.

Preferably, the type of the content played by the set top box includes one or more of a program list, a non-episode program and a multi-episode program;

the active time of the network access behavior comprises: the data rate exceeds a first access time of the network access behavior of a preset first threshold, and/or the access rate of the preset website exceeds a second access time of the network access behavior of a preset second threshold.

Preferably, the processor 61 is further configured to, when the number of the user devices hooked down by the home gateway of the target home is 1, directly use the user device hooked down by the home gateway of the target home as the target user device.

Preferably, the processor 61 is further configured to, when the number of the user equipment hung under the home gateway of the target home is greater than 1, solve an intersection between the playing duration of the current playing of the set top box and the active time of the network access behavior of each user equipment to obtain a coincidence time period, and use the user equipment corresponding to the minimum coincidence time period as the target user equipment.

Preferably, the processor 61 is further configured to calculate the overlapping time period by taking the first access time as the active time, and take the user equipment corresponding to the minimum overlapping time period as the target user equipment; and if the target user equipment cannot be determined by taking the first access time as the active time, calculating the overlapping time period by taking the second access time as the active time, and taking the user equipment corresponding to the minimum overlapping time period as the target user equipment.

Preferably, the processor 61 is further configured to determine a playing time of a preset type of content according to the type of content played by the set top box this time and the playing time of the content when the number of the user equipment hung under the home gateway of the target home is greater than 1, where the preset content is a non-episode program played among multiple-episode programs; and respectively calculating the active time of the network access behavior of each user equipment and the contact ratio of the active time and the playing time of the preset type content, and taking the user equipment corresponding to the highest contact ratio as the target user equipment.

Preferably, the processor 61 is further configured to calculate the contact ratio by taking the first access time as the active time, and take the ue corresponding to the highest contact ratio as the target ue; and if the target user equipment cannot be determined by taking the first access time as the active time, calculating the contact ratio by taking the second access time as the active time, and taking the user equipment corresponding to the highest contact ratio as the target user equipment.

Preferably, the processor 61 is further configured to calculate a first absolute value of a difference between a start time of an active time of the network access behavior corresponding to the user equipment and a start time of a playing time of the preset type of content, calculate a second absolute value of a difference between an end time of the active time of the network access behavior corresponding to the user equipment and an end time of the playing time of the preset type of content, and calculate a sum of the first absolute value and the second absolute value; determining the degree of coincidence according to the sum, wherein the degree of coincidence is inversely related to the sum.

Referring to fig. 7, an embodiment of the present invention further provides another user identification server 700, as shown in fig. 7, where the node includes: a processor 701, a transceiver 702, a memory 703 and a bus interface, wherein:

the transceiver 702 is configured to acquire viewing behavior data of a set top box of a target family, where the viewing behavior data includes a playing duration and/or a playing content type and a playing time of the set top box playing this time; acquiring network access behavior data of user equipment hung under a home gateway of the target family, wherein the network access behavior data comprises active time of network access behavior of the user equipment;

the processor 701 is configured to read a program in a memory, and execute the following processes: comparing the viewing behavior data with the network access behavior data of each user equipment, determining target user equipment, and taking a user corresponding to the target user equipment as a current user of the set top box;

the coincidence degree of the active time of the network access behavior of the target user equipment and the playing duration of the current playing of the set top box is lowest, or the coincidence degree of the active time of the network access behavior of the target user equipment and the playing time of the preset type content of the set top box is highest.

In this embodiment of the present invention, the network device 700 further includes: a computer program stored on the memory 703 and executable on the processor 701, the computer program being executable by the processor 701.

In fig. 7, the bus architecture may include any number of interconnected buses and bridges, with one or more processors, represented by processor 701, and various circuits, represented by memory 703, being linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The transceiver 702 may be a number of elements including a transmitter and a receiver that provide a means for communicating with various other apparatus over a transmission medium.

The processor 701 is responsible for managing the bus architecture and general processing, and the memory 703 may store data used by the processor 701 in performing operations.

Optionally, the content type played by the set top box includes one or more of a program list, a non-episode program and a multi-episode program;

the active time of the network access behavior comprises: the data rate exceeds a first access time of the network access behavior of a preset first threshold, and/or the access rate of the preset website exceeds a second access time of the network access behavior of a preset second threshold.

Optionally, the processor is further configured to, when the number of the user equipment hooked down by the home gateway of the target home is 1, directly use the user equipment hooked down by the home gateway of the target home as the target user equipment.

Optionally, the processor is further configured to, when the number of the user equipment hung below the home gateway of the target home is greater than 1, solve an intersection between the playing duration of the current playing of the set top box and the active time of the network access behavior of each user equipment to obtain a coincidence time period, and use the user equipment corresponding to the minimum coincidence time period as the target user equipment.

Optionally, the processor is further configured to calculate the overlapping time period by taking the first access time as the active time, and take the user equipment corresponding to the minimum overlapping time period as the target user equipment; and if the target user equipment cannot be determined by taking the first access time as the active time, calculating the overlapping time period by taking the second access time as the active time, and taking the user equipment corresponding to the minimum overlapping time period as the target user equipment.

Optionally, the processor is further configured to determine a playing time of a preset type of content according to the type of content played by the set top box this time and the playing time of the content when the number of the user equipment hung under the home gateway of the target home is greater than 1, where the preset content is a non-episode program played among multiple-episode programs; and respectively calculating the active time of the network access behavior of each user equipment and the contact ratio of the active time and the playing time of the preset type content, and taking the user equipment corresponding to the highest contact ratio as the target user equipment.

Optionally, the processor is further configured to calculate the contact ratio by taking the first access time as the active time, and take the ue corresponding to the highest contact ratio as the target ue; and if the target user equipment cannot be determined by taking the first access time as the active time, calculating the contact ratio by taking the second access time as the active time, and taking the user equipment corresponding to the highest contact ratio as the target user equipment.

Optionally, the processor is further configured to calculate a first absolute value of a difference between a start time of an active time of the network access behavior corresponding to the user equipment and a start time of the play time of the preset type of content, calculate a second absolute value of a difference between an end time of the active time of the network access behavior corresponding to the user equipment and an end time of the play time of the preset type of content, and calculate the first absolute value and the second absolute value to obtain a sum; determining the degree of coincidence according to the sum, wherein the degree of coincidence is inversely related to the sum.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.