WO2023005445A1 - 用户分析方法、系统及存储介质和终端设备 - Google Patents

用户分析方法、系统及存储介质和终端设备 Download PDF

Info

Publication number
WO2023005445A1
WO2023005445A1 PCT/CN2022/097938 CN2022097938W WO2023005445A1 WO 2023005445 A1 WO2023005445 A1 WO 2023005445A1 CN 2022097938 W CN2022097938 W CN 2022097938W WO 2023005445 A1 WO2023005445 A1 WO 2023005445A1
Authority
WO
WIPO (PCT)
Prior art keywords
multimedia
data
user
channel
access data
Prior art date
Application number
PCT/CN2022/097938
Other languages
English (en)
French (fr)
Inventor
张潇
Original Assignee
深圳Tcl新技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳Tcl新技术有限公司 filed Critical 深圳Tcl新技术有限公司
Publication of WO2023005445A1 publication Critical patent/WO2023005445A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43Querying
    • G06F16/435Filtering based on additional data, e.g. user or group profiles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/45Clustering; Classification

Definitions

  • the invention relates to the technical field of information processing, in particular to a user analysis method, system, storage medium and terminal equipment.
  • the smart home project is a project that household companies focus on. People's happiness often comes from the warmth of home. How to make smart homes better serve family members and make people more comfortable has become the core goal.
  • Various smart home applications are inseparable from user usage data. These user usage data can truly reflect people's preferences when using smart homes, and based on user usage data, more intelligent homes can be realized, such as automatic adjustment of water heaters, family The air conditioner that adjusts the temperature near home and the refrigerator that adjusts according to the food, etc.
  • smart TV has become an important smart home in the family, and many smart home technologies in the home are based on smart TV. Visitors outside the door, so as to control whether the door lock is opened, etc., and analyze user emotions based on the user's viewing data on smart TVs, and then adjust the temperature change of the air conditioner according to user emotions, etc. In this way, the analysis of user usage data in smart TVs is more important .
  • Embodiments of the present invention provide a user analysis method, system, storage medium, and terminal device, which implement analysis on multiple shared users corresponding to one user ID.
  • an embodiment of the present invention provides a user analysis method, including:
  • the user identification to be analyzed corresponds to a plurality of shared users
  • any group of data includes at least one piece of multimedia access data
  • the information of the shared user corresponding to the multimedia access data in any set of data is determined according to the second dimension feature and the preset policy.
  • Embodiments of the present invention provide a user analysis system on the one hand, including:
  • a data acquisition unit the user acquires a plurality of pieces of multimedia access data within a preset time period of the user identification to be analyzed, and the user identification to be analyzed corresponds to a plurality of shared users;
  • a grouping unit configured to divide the multiple pieces of multimedia access data into multiple groups of data according to the first dimension feature, any group of data includes at least one piece of multimedia access data;
  • the shared user unit is configured to determine the information of the shared user corresponding to the multimedia access data in any set of data according to the second dimension feature and the preset strategy.
  • Another aspect of the embodiments of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores a plurality of computer programs, and the computer programs are suitable for being loaded and executed by a processor as described in one aspect of the embodiments of the present invention The user analysis method described above.
  • Another aspect of the embodiment of the present invention also provides a terminal device, including a processor and a memory;
  • the memory is used to store a plurality of computer programs, the computer programs are used to be loaded by the processor and execute the user analysis method according to one aspect of the embodiment of the present invention; the processor is used to implement the multiple computer programs Individual computer programs within the Program.
  • the user analysis system will obtain the multimedia access data of the user identification to be analyzed within a period of time, and divide the multimedia access data into multiple groups of data based on the first dimension feature, and then analyze each group of data to obtain Information about the shared user corresponding to the multimedia access data in any set of data.
  • multiple shared users corresponding to a user ID are distinguished, making the application of user data more accurate; and in this analysis process, the multimedia access data is divided into multiple groups for analysis separately, and because each group of data The amount of data is less, so that the amount of analysis and calculation for each set of data is also relatively small, thus simplifying the entire user analysis process.
  • FIG. 1 is a schematic diagram of a user analysis method provided by an embodiment of the present invention
  • Fig. 2 is a flowchart of a user analysis method provided by an embodiment of the present invention.
  • Fig. 3 is a flowchart of a user analysis method provided in an application embodiment of the present invention.
  • Fig. 4 is a schematic diagram of a distributed system to which a user analysis method is applied in another application embodiment of the present invention.
  • Fig. 5 is a schematic diagram of a block structure in another application embodiment of the present invention.
  • Fig. 6 is a schematic diagram of a logical structure of a user analysis system provided by an application embodiment of the present invention.
  • Fig. 7 is a schematic diagram of a logical structure of a terminal device provided by an application embodiment of the present invention.
  • the embodiment of the present invention provides a user analysis method, which can be mainly applied to analyze the multimedia access data corresponding to the user ID when multiple shared users log in to the multimedia server through a user ID and access multimedia resources, so as to distinguish different Shared users, to achieve the analysis of shared users.
  • the user analysis system can implement user analysis through the following steps:
  • the user identification to be analyzed corresponds to a plurality of shared users
  • n groups of data are taken as an example in the figure, and any group of data includes at least one piece of multimedia access data;
  • the information of the shared user corresponding to the multimedia access data in any set of data is determined according to the second dimension feature and the preset policy.
  • the above-mentioned user analysis system can be applied to a smart device, and the smart device analyzes the shared users of the current smart device.
  • the smart device is any terminal device that can support multimedia display, such as a smart device.
  • the user analysis system can be applied to a multimedia server, and the multimedia server analyzes each shared user who uses each smart device.
  • the multimedia access data is divided into multiple groups for analysis separately, and because each group of data The amount of data is less, so that the amount of analysis and calculation for each set of data is also relatively small, thus simplifying the entire user analysis process.
  • the embodiment of the present invention provides a user analysis method, which is mainly the method executed by the user analysis system.
  • the flow chart is shown in Figure 2, including:
  • Step 101 acquiring multiple pieces of multimedia access data within a preset time period of the user ID to be analyzed, where the user ID to be analyzed corresponds to multiple shared users.
  • the user can operate the smart device, log in to a multimedia server (such as a video server, etc.) using a user ID, and access multimedia resources in the multimedia server through the smart device. Every time a user accesses a multimedia resource through a smart device, the smart device will initiate a multimedia resource access request to the multimedia server, which will generate a piece of multimedia access data and store it in the local smart device, or upload the multimedia access data to the multimedia server to store. Among them, when the user passes, log in to a multimedia server (such as a video server, etc.) using a user ID, and access multimedia resources in the multimedia server through the smart device. Every time a user accesses a multimedia resource through a smart device, the smart device will initiate a multimedia resource access request to the multimedia server, which will generate a piece of multimedia access data and store it in the local smart device, or upload the multimedia access data to the multimedia server to store. Among them, when the user passes,
  • the user analysis system can initiate the process of this embodiment according to a certain period, and directly extract the multimedia access data corresponding to any user identifier stored in the smart device or the multimedia server within a preset time period.
  • the preset time period here can be one day, three days or one week, and the multimedia access data in different preset time periods can be obtained for different user identifications, and the preset time period of each user identification can also be based on the actual The application changes dynamically. For example, when the number of pieces of multimedia access data obtained within the preset time period is less than the preset number, it is necessary to change the preset time period, specifically extend the duration of the preset time period.
  • Each piece of multimedia access data above may specifically include: access start time, end access time, and attribute information of the multimedia resource, such as the channel to which the multimedia resource belongs, the title of the multimedia resource, and other information.
  • a channel refers to a type of multimedia resource obtained after classifying all multimedia resources in the multimedia server according to certain rules, which is a multimedia resource of a channel.
  • a channel of a video resource may include a movie channel, a TV series channel, Children's Channel and Documentary Channel, etc.
  • multiple users can use one user ID to log in to the multimedia server and access multimedia resources. These users can be called shared users. For example, multiple members of a family use a smart TV and use one user ID to access video resources. In this embodiment, it is necessary to analyze the multimedia access data corresponding to a user identifier to obtain the shared user corresponding to the user identifier, and determine the attribute information of each shared user.
  • Step 102 Divide multiple pieces of multimedia access data into multiple groups of data according to the first dimension feature, any group of data includes at least one piece of multimedia access data.
  • the first dimension feature refers to a parameter of a dimension involved in multiple pieces of multimedia access data.
  • the user analysis system can divide multiple pieces of multimedia access data into multiple groups of data according to the access time experienced in a single access to multimedia resources. , wherein the access duration experienced by a single access to the multimedia resource can be obtained according to the start access time and end access time in the multimedia access data.
  • multiple ranges of the access duration experienced in a single access to multimedia resources can be determined, and when the access duration obtained according to a piece of multimedia access data belongs to a certain range, the piece of multimedia access data is divided into a corresponding group of data In this way, the division of multimedia access data is realized.
  • Step 103 Determine the shared user information corresponding to the multimedia access data in any set of data according to the second dimension feature and the preset strategy.
  • the second dimension feature refers to another dimension parameter involved in multiple pieces of multimedia access data, which is different from the above-mentioned first dimension feature.
  • the user analysis system determines the shared user information corresponding to the multimedia access data in any set of data according to the channel to which the multimedia resource belongs and the preset policy.
  • the preset strategy is set in the user analysis system in advance, mainly to determine the strategy of sharing user information according to the second dimension characteristics.
  • it may specifically include but not Limited to the following situations:
  • Each piece of multimedia access data corresponds to a multimedia resource, and then the channel to which the multimedia resource belongs can be obtained. In this way, for any set of data, corresponding at least one channel to which the multimedia resource belongs can be obtained.
  • the interval time is less than or equal to the preset time, it is determined that the two pieces of multimedia access data are generated based on a shared user, and the channel attribute of the shared user is: the multimedia resource corresponding to the piece of multimedia access data with the earlier access time belongs to channel.
  • the channels to which the corresponding multimedia resources belong are channel 1, channel 2, ..., channel n.
  • the n channels are all the same and are all channel A, then the multimedia access data in the set of data are all generated based on the same shared user, and the channel attribute of the shared user is channel A.
  • the corresponding access times are a, b, and c respectively, and the highest number of accesses is c. If the highest number of accesses c is less than the preset times, it is determined that the multimedia access data in the group of data are all generated based on the same shared user, and the channel attribute of the shared user is the channel C corresponding to the highest number of visits c; if the highest number of visits c is greater than or equal to the preset number of times, when The interval time between two adjacent multimedia access data in the n pieces of multimedia access data is greater than the preset time, and these two multimedia access data correspond to channel A and channel C respectively, then it is determined that these two multimedia access data are respectively based on different Generated by the sharing user, the channel attributes of the two sharing users are channel A and channel C respectively.
  • the above steps 101 to 103 are to determine the information of the shared user corresponding to any user identifier for the multimedia access data within a preset time period.
  • the multimedia access data respectively determines the shared user information, and the multimedia access data within at least one preset time period, and further counts the multi-dimensional multimedia access characteristics corresponding to the user identification, that is, the habit of accessing multimedia. Specifically, it may include but not limited to the following dimensions:
  • shared users For the dimension of shared users, count the time period when each shared user accesses multimedia resources and the channel to which the multimedia resources are accessed during the corresponding time period. For example, shared user 1 frequently visits documentary channels from 11:00 pm to 1:00 am;
  • the shared users and corresponding channels accessing the multimedia resources are counted in each time period.
  • the user analysis system can first obtain the current access status according to the multimedia access request.
  • the current access status is mainly used to indicate the currently initiated
  • the state of the multimedia access request such as the time of the multimedia access request and the information of the multimedia resources to be accessed; then according to the multi-dimensional multimedia access characteristics and current access status corresponding to the user identification to be analyzed obtained in the above-mentioned embodiment, Recommend corresponding multimedia resources.
  • the user analysis system recommends corresponding multimedia resources:
  • the current access status can be matched with the multimedia access features first, and the features associated with the features matching the current access status in the multimedia access features can be determined, and then the multimedia resources corresponding to the determined associated features can be used as the ones to be recommended Multimedia resources, and then realize the recommendation of multimedia resources.
  • a user initiates a multimedia access request through a user ID on a smart device.
  • the time of the multimedia access request is 12 o'clock in the evening, and the multimedia resource requested to be accessed is a certain movie resource in a movie channel.
  • the multimedia access features corresponding to the identification include: shared user 1 often visits documentary channels from 11:00 pm to 1:00 am, and shared user 2 often visits comedy movies and horror movies in movie channels.
  • the movie resource in the current access state belongs to the comedy movies of the movie channel, and its related features include sharing user 2 and horror movies, so horror movies can be recommended to the smart device.
  • the user analysis system will obtain the multimedia access data of the user identifier to be analyzed within a period of time, and divide the multimedia access data into multiple groups of data based on the first dimension feature, and then conduct The information of the shared user corresponding to the multimedia access data in any set of data is obtained through analysis.
  • multiple shared users corresponding to a user ID are distinguished, making the application of user data more accurate; and in this analysis process, the multimedia access data is divided into multiple groups for analysis separately, and because each group of data The amount of data is less, so that the amount of analysis and calculation for each set of data is also relatively small, thus simplifying the entire user analysis process.
  • the smart device is specifically a smart TV.
  • Recommend multimedia data specifically, as shown in Figure 3, the method of this embodiment may include the following steps:
  • Step 201 when the user operates the smart TV and uses a user ID to log in to the multimedia server and access the multimedia server, during this process, the multimedia server will record the multimedia access data, specifically, when the smart device initiates a multimedia resource request to the multimedia server When a multimedia access request is made, the multimedia server will record a piece of multimedia access data, and the multimedia access data corresponds to a user identifier, and may include access start time, end access time, and attributes of multimedia resources.
  • the multimedia server acquires multiple pieces of multimedia access data corresponding to any user identifier within a preset time period according to a certain period.
  • a user ID can correspond to a smart TV in a family.
  • Step 203 the multimedia server divides multiple pieces of multimedia access data into multiple groups of data according to the first dimensional feature of the access duration experienced in a single access to multimedia resources, for example, divides multimedia access data with an access duration of about 1 hour into one group , the multimedia access data whose access duration is about 2 hours is divided into another group. Then, the following steps 204 to 211 are respectively performed for any set of data.
  • Step 204 the multimedia server determines the channels to which the multimedia resources correspond to each piece of multimedia access data in any set of data, and judges whether the channels to which these multimedia resources belong are the same, if they are the same, then perform step 205; if not, then perform step 206 .
  • Step 205 determine that each piece of multimedia access data in any set of data corresponds to a shared user, and the channel attribute of the shared user is the same channel.
  • Step 206 counting the number of visits of each channel for a plurality of different channels involved in the channel of the multimedia resource corresponding to the multimedia access data in any set of data, respectively counting the number of visits of each channel, wherein one piece of multimedia access data corresponds to one visit, and judging the highest visit among them Whether the number of times is less than the preset number of times (for example, 3 times), if less, execute step 207; if not, execute step 208.
  • the preset number of times for example, 3 times
  • step 207 it is determined that the multimedia access data in any set of data corresponds to a shared user, and the channel attribute of the shared user is the channel corresponding to the highest number of visits.
  • Step 208 for any two adjacent multimedia access data in any set of data, and these two multimedia access data respectively correspond to two channels to which different multimedia resources belong, determine the relationship between the two adjacent multimedia access data Whether the interval time is greater than the preset time, if greater, execute step 209; if less than or equal to, execute step 210.
  • Step 209 determine that two adjacent pieces of multimedia access data respectively correspond to two shared users, and their channel attributes are respectively: the channels to which the multimedia resources respectively correspond to these two pieces of multimedia access data belong.
  • Step 210 determine that two adjacent pieces of multimedia access data correspond to a shared user, and its channel attribute is: the channel to which the multimedia resource corresponding to the piece of multimedia access data with the earlier access time belongs.
  • step 211 it is judged that all the group data have been processed, if yes, then end the process, if not, return to step 204 .
  • the above steps are to analyze multiple pieces of multimedia access data of a user ID in a preset time period, and obtain the information of the shared user corresponding to the user ID.
  • the multimedia server can combine multiple The shared user information obtained by each piece of access data within a preset time period, and the multimedia access data within each preset time period are counted to obtain the multimedia access characteristics related to the user identifier, and then the multimedia access characteristics can be applied to In various scenarios, such as data recommendation scenarios and other applications.
  • the user analysis system in the embodiment of the present invention is mainly a distributed system 100, which may include a client 300 and multiple nodes 200 (access Any form of computing equipment in the network, such as a server, a user terminal), and the client 300 and the node 200 are connected in the form of network communication.
  • FIG 4 is an optional structural diagram of the distributed system 100 applied to the block chain system provided by the embodiment of the present invention, consisting of multiple nodes 200 (accessed in the network Computing devices of any form, such as servers, user terminals) and client 300 are formed, and a point-to-point (P2P, Peer To Peer) network
  • the P2P protocol is an application layer protocol running on the Transmission Control Protocol (TCP, Transmission Control Protocol) protocol.
  • TCP Transmission Control Protocol
  • any machine such as a server or a terminal can join to become a node, and the node includes a hardware layer, an intermediate layer, an operating system layer, and an application layer.
  • Routing the basic function of nodes, is used to support communication between nodes.
  • nodes can also have the following functions:
  • the business implemented by the application includes the code to realize the user analysis function, and the user analysis function mainly includes:
  • the user identifier to be analyzed corresponds to multiple shared users; dividing the multiple pieces of multimedia access data into multiple groups of data according to the first dimension feature, any A set of data includes at least one piece of multimedia access data; and the information of the shared user corresponding to the multimedia access data in any set of data is determined according to the second dimension feature and the preset strategy.
  • Blockchain including a series of blocks (Blocks) that follow each other in chronological order. Once a new block is added to the blockchain, it will not be removed again. The blockchain system is recorded in the block. The record data submitted by the middle node.
  • each block includes the hash value of the transaction records stored in this block (the hash value of this block), and The hash value of the previous block, each block is connected by hash value to form a blockchain.
  • the block may also include information such as a time stamp when the block was generated.
  • Blockchain (Blockchain), essentially a decentralized database, is a series of data blocks associated with each other using cryptographic methods. Each data block contains relevant information to verify the validity of its information. (anti-counterfeiting) and generate the next block.
  • the embodiment of the present invention also provides a user analysis system, the structural diagram of which is shown in Figure 6, which may specifically include:
  • the data acquisition unit 10 the user acquires a plurality of pieces of multimedia access data within a preset time period of the user identification to be analyzed, and the user identification to be analyzed corresponds to a plurality of shared users;
  • the grouping unit 11 is used to divide the multiple pieces of multimedia access data acquired by the data acquisition unit 10 into multiple groups of data according to the first dimension feature, and any group of data includes at least one piece of multimedia access data;
  • the shared user unit 12 is configured to determine the shared user information corresponding to the multimedia access data in any set of data obtained by the grouping unit 11 according to the second dimension feature and the preset strategy.
  • the above-mentioned grouping unit 11 is specifically used to divide the multiple pieces of multimedia access data into multiple groups of data according to the access time experienced by a single access to multimedia resources;
  • the shared user unit 12 is specifically used to The channel to which it belongs and the preset policy determine the shared user information corresponding to the multimedia access data in any set of data.
  • the shared user unit 12 is specifically configured to determine that the multimedia access data in any set of data corresponds to a shared user when at least one piece of multimedia access data in any set of data corresponds to the same channel as the multimedia resource, so The channel attribute of a shared user is the same channel.
  • the channel to which the multimedia resource belongs to at least one piece of multimedia access data in the any set of data includes multiple different channels, count the number of visits of the channel to which the multimedia resource belongs in the any set of data; when the highest number of visits is less than the preset Times, determine that the multimedia access data in any set of data corresponds to a shared user, and the channel attribute of the shared user is the channel corresponding to the highest number of visits.
  • the highest number of access times is greater than or equal to the preset number of times, determine the time interval between two adjacent pieces of multimedia access data among at least one piece of multimedia access data in any set of data;
  • the multimedia access data corresponds to the channel to which the first multimedia resource belongs and the channel to which the second multimedia resource belongs; when the interval time is greater than the preset time, it is determined that the multimedia access data corresponding to the channel to which the first multimedia resource belongs.
  • the first shared user the channel attribute of the first shared user is the channel to which the first multimedia resource belongs; it is determined that the multimedia access data corresponding to the channel to which the second multimedia resource belongs corresponds to the second shared user, and the second shared user
  • the channel attribute of the shared user is the channel to which the second multimedia resource belongs.
  • the user analysis system of this embodiment may also include:
  • the statistics unit 13 is used for sharing user information determined based on the multimedia access data in at least one preset time period obtained by the above shared user unit 12, and the multimedia access data in the at least one preset time period , collecting statistics on multimedia access characteristics of multiple dimensions corresponding to the user identifier.
  • the statistical unit 13 is specifically used to count the time period of each shared user's access to multimedia resources and the channel to which the multimedia resources accessed in the corresponding time period belong to the dimension of the shared user; The time period of access and the corresponding sharing users; for the dimension of time period, the sharing users and corresponding channels accessing multimedia resources in each time period are counted.
  • the user analysis system of this embodiment may also include:
  • the recommendation unit 14 is configured to obtain the current access status according to the multimedia access request when initiating the multimedia access request of the user ID to be analyzed; according to the multi-dimensional multimedia data corresponding to the user ID to be analyzed obtained by the statistics unit 13 According to the access characteristics and the current access status, corresponding multimedia resources are recommended.
  • the recommending unit 14 is specifically used to match the current access status with the multimedia access feature when recommending corresponding multimedia resources according to the multi-dimensional multimedia access features corresponding to the user identifier to be analyzed and the current access status ; Determining the features associated with the features matching the current access state among the multimedia access features, and using the multimedia resources corresponding to the determined associated features as the multimedia resources to be recommended.
  • the data acquisition unit 10 will acquire the multimedia access data of the user identification to be analyzed within a period of time, and the grouping unit 11 divides the multimedia access data into multiple groups of data based on the first dimension feature, and then The shared user unit 12 analyzes each set of data to obtain the information of the shared user corresponding to the multimedia access data in any set of data.
  • the multimedia access data is divided into multiple groups for analysis separately, and because each group of data The amount of data is less, so that the amount of analysis and calculation for each set of data is also relatively small, thus simplifying the entire user analysis process.
  • the embodiment of the present invention also provides a terminal device, the schematic diagram of which is shown in Figure 7.
  • the terminal device may have relatively large differences due to different configurations or performances, and may include one or more central processing units (central processing units).
  • processing units (CPU) 20 for example, one or more processors
  • memory 21 for example, one or more storage media 22 for storing application programs 221 or data 222 (for example, one or more mass storage devices).
  • the memory 21 and the storage medium 22 may be temporary storage or persistent storage.
  • the program stored in the storage medium 22 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the terminal device.
  • the central processing unit 20 may be configured to communicate with the storage medium 22, and execute a series of instruction operations in the storage medium 22 on the terminal device.
  • the application program 221 stored in the storage medium 22 includes an application program for user analysis, and the program may include the data acquisition unit 10, the grouping unit 11, the shared user unit 12, the statistics unit 13 and the recommendation unit in the above-mentioned user analysis system.
  • Unit 14 will not be described in detail here.
  • the central processing unit 20 may be configured to communicate with the storage medium 22, and execute a series of operations corresponding to the application program for user analysis stored in the storage medium 22 on the terminal device.
  • the terminal equipment can also include one or more power supplies 23, one or more wired or wireless network interfaces 24, one or more input and output interfaces 25, and/or, one or more operating systems 223, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • the steps performed by the user analysis system described in the foregoing method embodiments may be based on the structure of the terminal device shown in FIG. 7 .
  • Another aspect of the embodiments of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores a plurality of computer programs, and the computer programs are suitable for being loaded by a processor and executed as performed by the above-mentioned user analysis system. user analysis methods.
  • Another aspect of the embodiment of the present invention also provides a terminal device, including a processor and a memory;
  • the memory is used to store a plurality of computer programs, and the computer programs are used to be loaded by the processor and execute the user analysis method as performed by the above-mentioned user analysis system; the processor is used to implement the multiple computer programs. various computer programs.
  • a computer program product or computer program comprising computer instructions stored in a computer readable storage medium.
  • the processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the user analysis method provided in the various optional implementation manners above.
  • ROM Read Only Memory
  • RAM Random Access Memory
  • Magnetic or Optical Disk etc.

Abstract

本发明实施例公开了用户分析方法、系统及存储介质和终端设备,应用于信息处理技术领域。用户分析系统会获取待分析用户标识在一段时间内的多媒体访问数据,并基于第一维度特征将多媒体访问数据划分为多组数据,进而针对每组数据进行分析得到任一组数据中多媒体访问数据所对应的共享用户的信息。这样,将一个用户标识对应的多个共享用户区别开来,使得对用户数据的应用更精确;且在这个分析过程中,将多媒体访问数据划分为多组分别进行分析,而由于每组数据中的数据量较少,使得对每组数据的分析计算量也比较少,从而简化了整个用户分析的过程。

Description

用户分析方法、系统及存储介质和终端设备
本申请要求于2021年07月28日提交中国专利局、申请号为 202110857239.0、发明名称均为“用户分析方法、系统及存储介质和终端设备”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本发明涉及信息处理技术领域,特别涉及用户分析方法、系统及存储介质和终端设备。
背景技术
智能家居项目是家用类企业重点关注的项目,人们幸福感往往来自于家的温馨,如何令智能家居更好地服务家庭成员,令人更加舒适,成为核心目标。各种智能家居的应用离不开用户使用数据,这些用户使用数据能真实地反映人们在使用智能家居时的偏好,进而基于用户使用数据可以实现更智能化的家居,比如自动调节的热水器、家人临近回家调温的空调及根据食物调节的冰箱等。
其中,智能电视已成为家庭的一个重要的智能家居,而家庭中智能家居的技术很多都是以智能电视为核心的,比如智能门锁中可以设置当按铃响起时,可以在智能电视端查看门外来客,从而控制门锁是否打开等,又比如基于用户在智能电视的观影数据分析用户情绪,再根据用户情绪调节空调温度变化等,这样,对智能电视中用户使用数据的分析比较重要。
技术问题
本发明实施例提供用户分析方法、系统及存储介质和终端设备,实现了对一个用户标识对应的多个共享用户进行分析。
技术解决方案
本发明实施例一方面提供一种用户分析方法,包括:
获取待分析用户标识在预置时间段内的多条多媒体访问数据,所述待分析用户标识对应多个共享用户;
根据第一维度特征将所述多条多媒体访问数据划分为多组数据,任一组数据包括至少一条多媒体访问数据;
根据第二维度特征及预置策略确定所述任一组数据中多媒体访问数据所对应的共享用户的信息。
本发明实施例一方面提供一种用户分析系统,包括:
数据获取单元,用户获取待分析用户标识在预置时间段内的多条多媒体访问数据,所述待分析用户标识对应多个共享用户;
分组单元,用于根据第一维度特征将所述多条多媒体访问数据划分为多组数据,任一组数据包括至少一条多媒体访问数据;
共享用户单元,用于根据第二维度特征及预置策略确定所述任一组数据中多媒体访问数据所对应的共享用户的信息。
本发明实施例另一方面还提供一种计算机可读存储介质,所述计算机可读存储介质储存多个计算机程序,所述计算机程序适于由处理器加载并执行如本发明实施例一方面所述的用户分析方法。
本发明实施例另一方面还提供一种终端设备,包括处理器和存储器;
所述存储器用于储存多个计算机程序,所述计算机程序用于由处理器加载并执行如本发明实施例一方面所述的用户分析方法;所述处理器,用于实现所述多个计算机程序中的各个计算机程序。
有益效果
在本实施例的方法中,用户分析系统会获取待分析用户标识在一段时间内的多媒体访问数据,并基于第一维度特征将多媒体访问数据划分为多组数据,进而针对每组数据进行分析得到任一组数据中多媒体访问数据所对应的共享用户的信息。这样,将一个用户标识对应的多个共享用户区别开来,使得对用户数据的应用更精确;且在这个分析过程中,将多媒体访问数据划分为多组分别进行分析,而由于每组数据中的数据量较少,使得对每组数据的分析计算量也比较少,从而简化了整个用户分析的过程。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1是本发明实施例提供的一种用户分析方法的示意图;
图2是本发明一个实施例提供的一种用户分析方法的流程图;
图3是本发明一个应用实施例中提供的一种用户分析方法的流程图;
图4是本发明另一应用实施例中用户分析方法所应用于的分布式系统的示意图;
图5是本发明另一应用实施例中区块结构的示意图;
图6是本发明应用实施例提供的一种用户分析系统的逻辑结构示意图;
图7是本发明应用实施例提供的一种终端设备的逻辑结构示意图。
本发明的实施方式
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”“第四”等(如果存在)是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本发明的实施例例如能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排它的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
本发明实施例提供一种用户分析方法,主要可以应用于当多个共享用户通过一个用户标识登录多媒体服务器,并访问多媒体资源时,对该用户标识对应的多媒体访问数据分析,从而区别出不同的共享用户,实现了共享用户的分析。具体如图1所示,用户分析系统可以通过如下步骤实现用户分析:
获取待分析用户标识在预置时间段内的多条多媒体访问数据,所述待分析用户标识对应多个共享用户;
根据第一维度特征将所述多条多媒体访问数据划分为多组数据(图中以n组数据为例说明),任一组数据包括至少一条多媒体访问数据;
根据第二维度特征及预置策略确定所述任一组数据中多媒体访问数据所对应的共享用户的信息。
在具体应用中,一种情况下,上述的用户分析系统可以应用于智能设备中,由智能设备对当前智能设备的共享用户进行分析,该智能设备是任意可以支持多媒体展示的终端设备,比如智能电视或电脑等;又一种情况下,用户分析系统可以应用于多媒体服务器中,由多媒体服务器对各个使用各个智能设备的共享用户进行分析。
这样,将一个用户标识对应的多个共享用户区别开来,使得对用户数据的应用更精确;且在这个分析过程中,将多媒体访问数据划分为多组分别进行分析,而由于每组数据中的数据量较少,使得对每组数据的分析计算量也比较少,从而简化了整个用户分析的过程。
本发明实施例提供一种用户分析方法,主要是用户分析系统所执行的方法,流程图如图2所示,包括:
步骤101,获取待分析用户标识在预置时间段内的多条多媒体访问数据,待分析用户标识对应多个共享用户。
可以理解,用户可以操作智能设备,并使用一用户标识登录多媒体服务器(比如视频服务器等),且通过智能设备访问多媒体服务器中的多媒体资源。用户每次通过智能设备访问一个多媒体资源时,智能设备会向多媒体服务器发起多媒体资源的访问请求,这样会产生一条多媒体访问数据,储存到本地的智能设备中,或者将多媒体访问数据上传到多媒体服务器进行储存。其中,当用户通过,
这样,用户分析系统可以按照一定的周期发起本实施例的流程,直接提取智能设备或多媒体服务器中储存的任一用户标识在预置时间段内对应的多媒体访问数据。这里预置时间段可以是一天、三天或一周等时间段,且针对不同的用户标识可以获取不同预置时间段内的多媒体访问数据,且每个用户标识的预置时间段也可以根据实际应用动态地变化,例如,当连续多次获取到预置时间段内的多媒体访问数据的条数小于预置条数,则需要改变预置时间段,具体延长预置时间段的时长。
上述每条多媒体访问数据具体可以包括:开始访问时间、结束访问时间及多媒体资源的属性信息,比如多媒体资源所属的频道、多媒体资源的标题等信息。其中,频道是指按照一定规则对多媒体服务器中的所有多媒体资源进行分类后,得到的一个类型的多媒体资源即为一个频道的多媒体资源,例如:对于视频资源的频道可以包括电影频道、电视剧频道、少儿频道和纪录片频道等。
在实际应用中,多个用户可以使用一个用户标识登录多媒体服务器,并访问多媒体资源,这些用户可以称为共享用户,比如,一个家庭中多个成员都通过一个智能电视,并使用一个用户标识访问视频资源。本实施例中,需要对一个用户标识对应的多媒体访问数据进行分析,得到该用户标识对应的共享用户,并确定出各个共享用户的属性信息。
步骤102,根据第一维度特征将多条多媒体访问数据划分为多组数据,任一组数据包括至少一条多媒体访问数据。
这里第一维度特征是指多条多媒体访问数据中所涉及的一个维度的参数,具体地,用户分析系统可以根据单次访问多媒体资源所经历的访问时长将多条多媒体访问数据划分为多组数据,其中,单次访问多媒体资源所经历的访问时长可以根据多媒体访问数据中的开始访问时间和结束访问时间得到。
具体地,可以确定单次访问多媒体资源所经历的访问时长的多个范围,当根据某一条多媒体访问数据得到的访问时长属于某一范围,则将该条多媒体访问数据划分到对应的一组数据中,从而实现了对多媒体访问数据的划分。
步骤103,根据第二维度特征及预置策略确定任一组数据中多媒体访问数据所对应的共享用户的信息。
这里第二维度特征是指多条多媒体访问数据中所涉及的另一维度的参数,不同于上述的第一维度特征。具体地,用户分析系统根据多媒体资源所属频道及预置策略确定任一组数据中多媒体访问数据所对应的共享用户的信息。
其中,预置策略是事先设置在用户分析系统中的,主要是根据第二维度特征确定共享用户信息的策略,在一种具体的应用中,当确定共享用户的信息时,具体可以包括但不限于如下几种情况:
(1)当任一组数据中至少一条多媒体访问数据分别对应的多媒体资源所属频道相同,比如都为频道A,确定任一组数据中多媒体访问数据对应一个共享用户,该共享用户的频道属性为上述相同的频道,比如为频道A。
针对每条多媒体访问数据都对应一个多媒体资源,进而可以得到多媒体资源所属频道,这样,针对任一组数据可以得到相应的至少一个多媒体资源所属频道。
(2)当任一组数据中至少一条多媒体访问数据分别对应的多媒体资源所属频道包括多个不同频道时,统计任一组数据中多媒体资源所属频道的访问次数,这样:
(21)当最高访问次数小于预置次数(比如3次),确定任一组数据中多媒体访问数据对应一个共享用户,该共享用户的频道属性为最高访问次数对应的频道。
(22)当最高访问次数大于或等于预置次数时,确定任一组数据的至少一条多媒体访问数据中,相邻的两条多媒体访问数据之间的间隔时间,且这两条多媒体访问数据分别对应第一多媒体资源所属频道和第二多媒体资源所属频道,当间隔时间大于预置时间,确定第一多媒体资源所属频道对应的多媒体访问数据对应第一共享用户,第一共享用户的频道属性为第一多媒体资源所属频道;确定第二多媒体资源所属频道对应的多媒体访问数据对应第二共享用户,第二共享用户的频道属性为第二多媒体资源所属频道。
当间隔时间小于或等于预置时间时,则确定这两条多媒体访问数据是基于一个共享用户产生的,且该共享用户的频道属性为:访问时间在前的一条多媒体访问数据对应的多媒体资源所属频道。
例如,针对一组数据中包括的n条多媒体访问数据即多媒体访问数据1、多媒体访问数据2、……、多媒体访问数据n,分别对应的多媒体资源所属频道为频道1、频道2、……、频道n。当这n个频道都相同,都是频道A,则该组数据中的多媒体访问数据都是基于同一共享用户产生的,该共享用户的频道属性为频道A。
当这n个频道包括多个不同的频道,比如频道A、频道B和频道C,分别对应的访问次数为a、b和c,其中最高访问次数为c,若该最高访问次数c小于预置次数,则确定该组数据中的多媒体访问数据都是基于同一共享用户产生的,该共享用户的频道属性为最高访问次数c对应的频道C;若最高访问次数c大于或等于预置次数,当n条多媒体访问数据中两条相邻的多媒体访问数据之间的间隔时间大于预置时间,这两条多媒体访问数据分别对应频道A和频道C,则确定这两条多媒体访问数据分别是基于不同共享用户产生的,这两个共享用户的频道属性分别为频道A和频道C。
需要说明的是,上述步骤101到103是针对一个预置时间段内的多媒体访问数据确定出任一用户标识对应的共享用户的信息,在具体的应用中,可以综合根据至少一个预置时间段内的多媒体访问数据分别确定的共享用户的信息,及至少一个预置时间段内的多媒体访问数据,进一步统计出用户标识对应的多个维度的多媒体访问特征,即访问多媒体的习惯。具体可以包括但不限于如下几个维度:
对于共享用户的维度,统计每个共享用户访问多媒体资源的时间段及在相应时间段访问的多媒体资源所属频道,例如共享用户1在晚上11点到凌晨1点经常访问纪录片频道;
对于频道的维度,统计每个频道的多媒体资源被访问的时间段及相应的共享用户,例如,每周一下午2点到5点家庭中的成人访问电影频道;
对于时间段的维度,统计每个时间段访问多媒体资源的共享用户及对应的频道。
进一步地需要说明的是,当用户分析系统通过上述步骤对任一用户标识对应的共享用户及多媒体访问特征进行分析后,可以将这些分析结果应用于多种场景中,例如,在多媒体资源的推荐场景中:
当用户通过智能设备发起一用户标识(比如上述的待分析用户标识)对应的多媒体访问请求时,用户分析系统可以先根据该多媒体访问请求获取当前访问状态,该当前访问状态主要用于表示当前发起多媒体访问请求的状态,比如该多媒体访问请求的时间及待访问的多媒体资源的信息等状态;然后根据上述实施例中获取的待分析用户标识对应的多个维度的多媒体访问特征及当前访问状态,推荐相应的多媒体资源。具体地,用户分析系统在推荐相应的多媒体资源时:
可以先将当前访问状态与多媒体访问特征进行匹配,并确定多媒体访问特征中与当前访问状态相匹配的特征相关联的特征,进而再将与确定的相关联的特征对应的多媒体资源作为待推荐的多媒体资源,进而实现了多媒体资源的推荐。
例如,某一用户在智能设备通过一用户标识发起多媒体访问请求,该多媒体访问请求的时间是晚上12点,且请求访问的多媒体资源是电影频道中的某一电影资源,而上述获取的一用户标识对应的多媒体访问特征中包括:共享用户1在晚上11点到凌晨1点经常访问纪录片频道,及共享用户2经常访问电影频道中的喜剧电影和恐怖电影等。
则用户分析系统匹配到当前访问状态中的时间处于晚上11点到凌晨1点之间,其相关的特征包括共享用户1及纪录片频道,则可以向智能设备推荐纪录片的资源;且用户分析系统匹配到当前访问状态中的电影资源属于电影频道的喜剧电影,其相关的特征包括共享用户2和恐怖电影,则可以向智能设备推荐恐怖电影。
可见,在本实施例的方法中,用户分析系统会获取待分析用户标识在一段时间内的多媒体访问数据,并基于第一维度特征将多媒体访问数据划分为多组数据,进而针对每组数据进行分析得到任一组数据中多媒体访问数据所对应的共享用户的信息。这样,将一个用户标识对应的多个共享用户区别开来,使得对用户数据的应用更精确;且在这个分析过程中,将多媒体访问数据划分为多组分别进行分析,而由于每组数据中的数据量较少,使得对每组数据的分析计算量也比较少,从而简化了整个用户分析的过程。
以下以一个具体的应用实例来说明本发明的用户分析方法,在本实施例中,智能设备具体为智能电视,用户分析系统主要应用于多媒体服务器中,用以向各个家庭中智能电视的共享用户推荐多媒体数据,具体地,如图3所示,本实施例的方法可以包括如下步骤:
步骤201,当用户操作智能电视,并使用一用户标识登录多媒体服务器,并访问多媒体服务器,在这个过程中,多媒体服务器会记录多媒体访问数据,具体地,当智能设备向多媒体服务器发起一个多媒体资源的多媒体访问请求时,多媒体服务器会记录一条多媒体访问数据,且该多媒体访问数据与一用户标识对应,可以包括开始访问时间、结束访问时间及多媒体资源的属性等。
步骤202,多媒体服务器会按照一定的周期,获取任一用户标识在预置时间段内对应的多条多媒体访问数据。而一般情况下,一个用户标识可以对应一个家庭中的智能电视。
步骤203,多媒体服务器根据单次访问多媒体资源所经历的访问时长这个第一维度特征,将多条多媒体访问数据划分为多组数据,比如将访问时长在1小时左右的多媒体访问数据划分为一组,访问时长在2小时左右的多媒体访问数据划分为另一组。然后针对任一组数据分别执行如下步骤204到步骤211。
步骤204,多媒体服务器确定任一组数据中每条多媒体访问数据分别对应的多媒体资源所属频道,判断这些多媒体资源所属频道是否都相同,如果相同,则执行步骤205;如果不相同,则执行步骤206。
步骤205,确定任一组数据中的各条多媒体访问数据对应一个共享用户,该共享用户的频道属性为相同的频道。
步骤206,针对任一组数据中多媒体访问数据分别对应的多媒体资源所属频道涉及的多个不同频道,分别统计各个频道的访问次数,其中,一条多媒体访问数据对应一次访问,并判断其中的最高访问次数是否小于预置次数(比如3次),如果小于,则执行步骤207;如果不小于,则执行步骤208。
步骤207,确定任一组数据中多媒体访问数据对应一个共享用户,且该共享用户的频道属性为最高访问次数对应的频道。
步骤208,对于任一组数据中任意两条相邻的多媒体访问数据,且这两条多媒体访问数据分别对应两个不同的多媒体资源所属频道,判断这两条相邻的多媒体访问数据之间的间隔时间是否大于预置时间,如果大于,则执行步骤209;如果小于或等于,则执行步骤210。
步骤209,确定两条相邻的多媒体访问数据分别对应两个共享用户,其频道属性分别为:这两条多媒体访问数据分别对应的多媒体资源所属频道。
步骤210,确定两条相邻的多媒体访问数据对应一个共享用户,其频道属性为:访问时间在前的一条多媒体访问数据对应的多媒体资源所属频道。
步骤211,判断所有组数据都处理完,如果是,则结束流程,如果不是,则返回执行步骤204。
需要说明的是,上述步骤是对一用户标识在一个预置时间段的多条多媒体访问数据进行分析,得到该用户标识对应的共享用户的信息,在实际应用中,多媒体服务器可以结合根据多个预置时间段内的多每条访问数据得到的共享用户的信息,及各个预置时间段内的多媒体访问数据,统计得到与该用户标识相关的多媒体访问特征,进而可以将多媒体访问特征应用于多种场景中,比如数据推荐场景等应用中。
以下以另一具体的应用实例来说明本发明中用户分析方法,本发明实施例中的用户分析系统主要为分布式系统100,该分布式系统可以包括客户端300及多个节点200(接入网络中的任意形式的计算设备,如服务器、用户终端),客户端300与节点200之间通过网络通信的形式连接。
以分布式系统为区块链系统为例,参见图4是本发明实施例提供的分布式系统100应用于区块链系统的一个可选的结构示意图,由多个节点200(接入网络中的任意形式的计算设备,如服务器、用户终端)和客户端300形成,节点之间形成组成的点对点(P2P,Peer To Peer)网络,P2P 协议是一个运行在传输控制协议(TCP,Transmission Control Protocol )协议之上的应用层协议。在分布式系统中,任何机器如服务器、终端都可以加入而成为节点,节点包括硬件层、中间层、操作系统层和应用层。
参见图4示出的区块链系统中各节点的功能,涉及的功能包括:
1)路由,节点具有的基本功能,用于支持节点之间的通信。
节点除具有路由功能外,还可以具有以下功能:
2)应用,用于部署在区块链中,根据实际业务需求而实现特定业务,记录实现功能相关的数据形成记录数据,在记录数据中携带数字签名以表示任务数据的来源,将记录数据发送到区块链系统中的其它节点,供其它节点在验证记录数据来源以及完整性成功时,将记录数据添加到临时区块中。
例如,应用实现的业务包括实现用户分析功能的代码,该用户分析功能主要包括:
获取待分析用户标识在预置时间段内的多条多媒体访问数据,所述待分析用户标识对应多个共享用户;根据第一维度特征将所述多条多媒体访问数据划分为多组数据,任一组数据包括至少一条多媒体访问数据;根据第二维度特征及预置策略确定所述任一组数据中多媒体访问数据所对应的共享用户的信息。
3)区块链,包括一系列按照产生的先后时间顺序相互接续的区块(Block),新区块一旦加入到区块链中就不会再被移除,区块中记录了区块链系统中节点提交的记录数据。
参见图5为本发明实施例提供的区块结构(Block Structure)一个可选的示意图,每个区块中包括本区块存储交易记录的哈希值(本区块的哈希值)、以及前一区块的哈希值,各区块通过哈希值连接形成区块链。另外,区块中还可以包括有区块生成时的时间戳等信息。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了相关的信息,用于验证其信息的有效性(防伪)和生成下一个区块。
本发明实施例还提供一种用户分析系统,其结构示意图如图6所示,具体可以包括:
数据获取单元10,用户获取待分析用户标识在预置时间段内的多条多媒体访问数据,所述待分析用户标识对应多个共享用户;
分组单元11,用于根据第一维度特征将所述数据获取单元10获取的多条多媒体访问数据划分为多组数据,任一组数据包括至少一条多媒体访问数据;
共享用户单元12,用于根据第二维度特征及预置策略确定所述分组单元11得到的任一组数据中多媒体访问数据所对应的共享用户的信息。
在一个具体应用中,上述分组单元11,具体用于根据单次访问多媒体资源所经历的访问时长将所述多条多媒体访问数据划分为多组数据;共享用户单元12,具体用于根据多媒体资源所属频道及预置策略确定所述任一组数据中多媒体访问数据所对应的共享用户的信息。
进一步地,共享用户单元12,具体用于当所述任一组数据中至少一条多媒体访问数据分别对应的多媒体资源所属频道相同,确定所述任一组数据中多媒体访问数据对应一个共享用户,所述一个共享用户的频道属性为所述相同的频道。当所述任一组数据中至少一条多媒体访问数据分别对应的多媒体资源所属频道包括多个不同频道时,统计所述任一组数据中多媒体资源所属频道的访问次数;当最高访问次数小于预置次数,确定所述任一组数据中多媒体访问数据对应一个共享用户,所述一个共享用户的频道属性为所述最高访问次数对应的频道。进一步地,当最高访问次数大于或等于所述预置次数时,确定所述任一组数据的至少一条多媒体访问数据中,相邻的两条多媒体访问数据之间的间隔时间;所述两条多媒体访问数据分别对应第一多媒体资源所属频道和第二多媒体资源所属频道;当所述间隔时间大于预置时间,确定所述第一多媒体资源所属频道对应的多媒体访问数据对应第一共享用户,所述第一共享用户的频道属性为第一多媒体资源所属频道;确定所述第二多媒体资源所属频道对应的多媒体访问数据对应第二共享用户,所述第二共享用户的频道属性为第二多媒体资源所属频道。
进一步地,本实施例的用户分析系统还可以包括:
统计单元13,用于根据上述共享用户单元12得到的基于至少一个所述预置时间段内的多媒体访问数据分别确定的共享用户的信息,及所述至少一个预置时间段内的多媒体访问数据,统计所述用户标识对应的多个维度的多媒体访问特征。
该统计单元13,具体用于对于共享用户的维度,统计每个共享用户访问多媒体资源的时间段及在相应时间段访问的多媒体资源所属频道;对于频道的维度,统计每个频道的多媒体资源被访问的时间段及相应的共享用户;对于时间段的维度,统计每个时间段访问多媒体资源的共享用户及对应的频道。
进一步地,本实施例的用户分析系统还可以包括:
推荐单元14,用于当发起所述待分析用户标识的多媒体访问请求时,根据所述多媒体访问请求获取当前访问状态;根据所述统计单元13得到的待分析用户标识对应的多个维度的多媒体访问特征及所述当前访问状态,推荐相应的多媒体资源。
该推荐单元14在根据所述待分析用户标识对应的多个维度的多媒体访问特征及所述当前访问状态,推荐相应的多媒体资源时,具体用于将所述当前访问状态与多媒体访问特征进行匹配;确定所述多媒体访问特征中与当前访问状态相匹配的特征相关联的特征,及将与所述确定的相关联的特征对应的多媒体资源作为待推荐的多媒体资源。
可见,在本实施例的用户分析系统中,数据获取单元10会获取待分析用户标识在一段时间内的多媒体访问数据,分组单元11基于第一维度特征将多媒体访问数据划分为多组数据,进而共享用户单元12针对每组数据进行分析得到任一组数据中多媒体访问数据所对应的共享用户的信息。这样,将一个用户标识对应的多个共享用户区别开来,使得对用户数据的应用更精确;且在这个分析过程中,将多媒体访问数据划分为多组分别进行分析,而由于每组数据中的数据量较少,使得对每组数据的分析计算量也比较少,从而简化了整个用户分析的过程。
本发明实施例还提供一种终端设备,其结构示意图如图7所示,该终端设备可因配置或性能不同而产生比较大的差异,可以包括一个或一个以上中央处理器(central processing units,CPU)20(例如,一个或一个以上处理器)和存储器21,一个或一个以上存储应用程序221或数据222的存储介质22(例如一个或一个以上海量存储设备)。其中,存储器21和存储介质22可以是短暂存储或持久存储。存储在存储介质22的程序可以包括一个或一个以上模块(图示没标出),每个模块可以包括对终端设备中的一系列指令操作。更进一步地,中央处理器20可以设置为与存储介质22通信,在终端设备上执行存储介质22中的一系列指令操作。
具体地,在存储介质22中储存的应用程序221包括用户分析的应用程序,且该程序可以包括上述用户分析系统中的数据获取单元10,分组单元11,共享用户单元12,统计单元13和推荐单元14,在此不进行赘述。更进一步地,中央处理器20可以设置为与存储介质22通信,在终端设备上执行存储介质22中储存的用户分析的应用程序对应的一系列操作。
终端设备还可以包括一个或一个以上电源23,一个或一个以上有线或无线网络接口24,一个或一个以上输入输出接口25,和/或,一个或一个以上操作系统223,例如Windows ServerTM,Mac OS XTM,UnixTM, LinuxTM,FreeBSDTM等等。
上述方法实施例中所述的由用户分析系统所执行的步骤可以基于该图7所示的终端设备的结构。
本发明实施例另一方面还提供一种计算机可读存储介质,所述计算机可读存储介质储存多个计算机程序,所述计算机程序适于由处理器加载并执行如上述用户分析系统所执行的用户分析方法。
本发明实施例另一方面还提供一种终端设备,包括处理器和存储器;
所述存储器用于储存多个计算机程序,所述计算机程序用于由处理器加载并执行如上述用户分析系统所执行的用户分析方法;所述处理器,用于实现所述多个计算机程序中的各个计算机程序。
根据本申请的一个方面,提供了一种计算机程序产品或计算机程序,该计算机程序产品或计算机程序包括计算机指令,该计算机指令存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取该计算机指令,处理器执行该计算机指令,使得该计算机设备执行上述各种可选实现方式中提供的用户分析方法。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成,该程序可以存储于一计算机可读存储介质中,存储介质可以包括:只读存储器(ROM)、随机存取存储器(RAM)、磁盘或光盘等。
以上对本发明实施例所提供的用户分析方法、系统及存储介质和终端设备进行了详细介绍,本文中应用了具体个例对本发明的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本发明的方法及其核心思想;同时,对于本领域的一般技术人员,依据本发明的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本发明的限制。

Claims (12)

  1. 一种用户分析方法,其特征在于,包括:
    获取待分析用户标识在预置时间段内的多条多媒体访问数据,所述待分析用户标识对应多个共享用户;
    根据第一维度特征将所述多条多媒体访问数据划分为多组数据,任一组数据包括至少一条多媒体访问数据;
    根据第二维度特征及预置策略确定所述任一组数据中多媒体访问数据所对应的共享用户的信息。
  2. 如权利要求1所述的方法,其特征在于,所述根据第一维度特征将所述多条多媒体访问数据划分为多组数据,具体包括:根据单次访问多媒体资源所经历的访问时长将所述多条多媒体访问数据划分为多组数据;
    所述根据第二维度特征及预置策略确定所述任一组数据中多媒体访问数据所对应的共享用户的信息,具体包括:根据多媒体资源所属频道及预置策略确定所述任一组数据中多媒体访问数据所对应的共享用户的信息。
  3. 如权利要求2所述的方法,其特征在于,所述根据多媒体资源所属频道及预置策略确定任一组数据中多媒体访问数据所对应的共享用户的信息,具体包括:
    当所述任一组数据中至少一条多媒体访问数据分别对应的多媒体资源所属频道相同,确定所述任一组数据中多媒体访问数据对应一个共享用户,所述一个共享用户的频道属性为所述相同的频道。
  4. 如权利要求3所述的方法,其特征在于,所述根据多媒体资源所属频道及预置策略确定任一组数据中多媒体访问数据所对应的共享用户的信息,还包括:
    当所述任一组数据中至少一条多媒体访问数据分别对应的多媒体资源所属频道包括多个不同频道时,统计所述任一组数据中多媒体资源所属频道的访问次数;
    当最高访问次数小于预置次数,确定所述任一组数据中多媒体访问数据对应一个共享用户,所述一个共享用户的频道属性为所述最高访问次数对应的频道。
  5. 如权利要求4所述的方法,其特征在于,所述根据多媒体资源所属频道及预置策略确定任一组数据中多媒体访问数据所对应的共享用户的信息,还包括:
    当最高访问次数大于或等于所述预置次数时,确定所述任一组数据的至少一条多媒体访问数据中,相邻的两条多媒体访问数据之间的间隔时间;所述两条多媒体访问数据分别对应第一多媒体资源所属频道和第二多媒体资源所属频道;
    当所述间隔时间大于预置时间,确定所述第一多媒体资源所属频道对应的多媒体访问数据对应第一共享用户,所述第一共享用户的频道属性为第一多媒体资源所属频道;
    确定所述第二多媒体资源所属频道对应的多媒体访问数据对应第二共享用户,所述第二共享用户的频道属性为第二多媒体资源所属频道。
  6. 如权利要求1至5任一项所述的方法,其特征在于,所述方法还包括:
    根据至少一个所述预置时间段内的多媒体访问数据分别确定的共享用户的信息,及所述至少一个预置时间段内的多媒体访问数据,统计所述用户标识对应的多个维度的多媒体访问特征。
  7. 如权利要求6所述的方法,其特征在于,所述统计所述用户标识对应的多个维度的多媒体访问特征,具体包括:
    对于共享用户的维度,统计每个共享用户访问多媒体资源的时间段及在相应时间段访问的多媒体资源所属频道;
    对于频道的维度,统计每个频道的多媒体资源被访问的时间段及相应的共享用户;
    对于时间段的维度,统计每个时间段访问多媒体资源的共享用户及对应的频道。
  8. 如权利要求6所述的方法,其特征在于,所述方法还包括:
    当发起所述待分析用户标识的多媒体访问请求时,根据所述多媒体访问请求获取当前访问状态;
    根据所述待分析用户标识对应的多个维度的多媒体访问特征及所述当前访问状态,推荐相应的多媒体资源。
  9. 如权利要求8所述的方法,其特征在于,所述根据所述待分析用户标识对应的多个维度的多媒体访问特征及所述当前访问状态,推荐相应的多媒体资源,具体包括:
    将所述当前访问状态与多媒体访问特征进行匹配;
    确定所述多媒体访问特征中与当前访问状态相匹配的特征相关联的特征,及将与所述确定的相关联的特征对应的多媒体资源作为待推荐的多媒体资源。
  10. 一种用户分析系统,其特征在于,包括:
    数据获取单元,用户获取待分析用户标识在预置时间段内的多条多媒体访问数据,所述待分析用户标识对应多个共享用户;
    分组单元,用于根据第一维度特征将所述多条多媒体访问数据划分为多组数据,任一组数据包括至少一条多媒体访问数据;
    共享用户单元,用于根据第二维度特征及预置策略确定所述任一组数据中多媒体访问数据所对应的共享用户的信息。
  11. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质储存多个计算机程序,所述计算机程序适于由处理器加载并执行如权利要求1至9任一项所述的用户分析方法。
  12. 一种终端设备,其特征在于,包括处理器和存储器;
    所述存储器用于储存多个计算机程序,所述计算机程序用于由处理器加载并执行如权利要求1至9任一项所述的用户分析方法;所述处理器,用于实现所述多个计算机程序中的各个计算机程序。
PCT/CN2022/097938 2021-07-28 2022-06-09 用户分析方法、系统及存储介质和终端设备 WO2023005445A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110857239.0A CN113569063A (zh) 2021-07-28 2021-07-28 用户分析方法、系统及存储介质和终端设备
CN202110857239.0 2021-07-28

Publications (1)

Publication Number Publication Date
WO2023005445A1 true WO2023005445A1 (zh) 2023-02-02

Family

ID=78168511

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/097938 WO2023005445A1 (zh) 2021-07-28 2022-06-09 用户分析方法、系统及存储介质和终端设备

Country Status (2)

Country Link
CN (1) CN113569063A (zh)
WO (1) WO2023005445A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113569063A (zh) * 2021-07-28 2021-10-29 深圳Tcl新技术有限公司 用户分析方法、系统及存储介质和终端设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140075328A1 (en) * 2012-09-13 2014-03-13 Timothy E. Hansen Methods and apparatus for improving user experience
CN104822074A (zh) * 2015-04-14 2015-08-05 天脉聚源(北京)传媒科技有限公司 一种电视节目的推荐方法及装置
CN105373614A (zh) * 2015-11-24 2016-03-02 中国科学院深圳先进技术研究院 一种基于用户账号的子用户识别方法及系统
CN105430504A (zh) * 2015-11-27 2016-03-23 中国科学院深圳先进技术研究院 基于电视观看日志挖掘的家庭成员结构识别方法与系统
CN105516810A (zh) * 2015-12-04 2016-04-20 山东大学 一种基于lda模型的电视用户家庭成员分析方法
CN113569063A (zh) * 2021-07-28 2021-10-29 深圳Tcl新技术有限公司 用户分析方法、系统及存储介质和终端设备

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009156988A1 (en) * 2008-06-23 2009-12-30 Double Verify Ltd. Automated monitoring and verification of internet based advertising
CN104778010A (zh) * 2014-01-13 2015-07-15 内蒙古近远信息技术有限责任公司 基于云存储平台的媒体数据高效访问预取方法
CN105741210A (zh) * 2016-04-14 2016-07-06 西安夫子电子科技研究院有限公司 一种基于可穿戴设备的个性化多媒体智慧交互系统
CN109598526B (zh) * 2017-09-30 2023-05-16 北京国双科技有限公司 媒体贡献的分析方法及装置
CN111385606A (zh) * 2018-12-28 2020-07-07 Tcl集团股份有限公司 一种视频预览方法、装置及智能终端
CN111200607B (zh) * 2019-12-31 2022-04-19 浙江工业大学 一种基于多层lstm的线上用户行为分析方法
CN111144584B (zh) * 2019-12-31 2024-01-19 深圳Tcl新技术有限公司 参数调优方法、装置及计算机存储介质
CN112256893A (zh) * 2020-11-13 2021-01-22 腾讯科技(深圳)有限公司 多媒体数据的处理方法、装置、电子设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140075328A1 (en) * 2012-09-13 2014-03-13 Timothy E. Hansen Methods and apparatus for improving user experience
CN104822074A (zh) * 2015-04-14 2015-08-05 天脉聚源(北京)传媒科技有限公司 一种电视节目的推荐方法及装置
CN105373614A (zh) * 2015-11-24 2016-03-02 中国科学院深圳先进技术研究院 一种基于用户账号的子用户识别方法及系统
CN105430504A (zh) * 2015-11-27 2016-03-23 中国科学院深圳先进技术研究院 基于电视观看日志挖掘的家庭成员结构识别方法与系统
CN105516810A (zh) * 2015-12-04 2016-04-20 山东大学 一种基于lda模型的电视用户家庭成员分析方法
CN113569063A (zh) * 2021-07-28 2021-10-29 深圳Tcl新技术有限公司 用户分析方法、系统及存储介质和终端设备

Also Published As

Publication number Publication date
CN113569063A (zh) 2021-10-29

Similar Documents

Publication Publication Date Title
US9113208B2 (en) Personalized video channel control
TWI514132B (zh) 資料同步技術
US9621648B2 (en) Peer-to-peer architecture for web traffic management
CN110705683B (zh) 随机森林模型的构造方法、装置、电子设备及存储介质
US8763087B2 (en) System and method for content access control
US20140259037A1 (en) Predicted video content aggregation
CN103686237A (zh) 推荐视频资源的方法及系统
US20120209909A1 (en) Cloud access system and operating method thereof
TW202013234A (zh) 資料處理方法、設備以及儲存媒介
US20140259038A1 (en) Demographic prediction channel
US20140245334A1 (en) Personal videos aggregation
CN110929086A (zh) 一种音视频推荐方法、装置及存储介质
US10848434B2 (en) Performance management for query processing
US9111231B2 (en) Associating a web session with a household member
WO2023005445A1 (zh) 用户分析方法、系统及存储介质和终端设备
Xu et al. Modeling buffer starvations of video streaming in cellular networks with large-scale measurement of user behavior
CN108415908B (zh) 一种多媒体数据的处理方法及服务器
US11483202B2 (en) Method for automatically configuring router and routing system
TWI579708B (zh) Method and apparatus for interacting with user data
CN108810089A (zh) 一种信息推送方法、装置及存储介质
CN107547916A (zh) 播放列表推荐方法及装置
WO2015043549A1 (zh) 一种多媒体文件推荐方法及电子设备
WO2022001480A1 (zh) 热门应用识别方法、网络系统、网络设备及存储介质
Merani et al. An IP-TV P2P streaming system that improves the viewing quality and confines the startup delay of regular audience
US10929758B2 (en) Enhanced personalization in multi-user devices

Legal Events

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

Ref document number: 22848054

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE