Multimedia push method, apparatus, device and storage medium based on OTT video

Abstract

This invention relates to big data technology and discloses a multimedia push method, apparatus, device, and storage medium based on OTT video. The method includes: identifying a set of user information from a centralized login account set of terminal devices under a target network, and identifying the basic identity information and network behavior information of the user information set to construct an organizational user profile; constructing a device browsing profile of the target terminal based on its historical video playback set; calculating the similarity between the device browsing profile and the organizational user profile to obtain the usage degree value of each organizational member in the organizational user profile for the target terminal; and pushing content to the target terminal based on the usage degree value and the real-time updated profiles of each organizational member. This invention can improve the accuracy of OTT video push on multimedia terminals.

Description

Technical Field

[0001] This invention relates to the field of big data technology, and in particular to a multimedia push method, apparatus, device, and computer-readable storage medium based on OTT video. Background Technology

[0002] With the development of network communication technology, the convergence of three networks and OTT video delivery has gradually become an important way for video producers to quickly acquire viewers.

[0003] Nowadays, there are more and more terminal devices for OTT video push mode, including TV, PC, mobile phone and tablet, etc. However, the users of the same device may be different members of the family, making it difficult to identify the most accurate user push content in the scenario of multiple terminals and multiple users. Summary of the Invention

[0004] This invention provides a multimedia push method, apparatus, device, and storage medium based on OTT video, the main purpose of which is to improve the accuracy of OTT video push on multimedia terminals.

[0005] To achieve the above objectives, the present invention provides a multimedia push method based on OTT video, comprising:

[0006] Obtain the set of login account information of the terminal device set under the target network, and identify the set of user information corresponding to the set of login account information;

[0007] Obtain the basic identity information and network behavior information of each user in the user information set, and construct an organizational user profile based on the preset organizational profile construction rules, the basic identity information and the network behavior information;

[0008] Obtain the historical video playback set of the target terminal in the terminal device set, and perform entity tag extraction operation on the historical video playback set to obtain tag extraction results. Then, according to the preset time proximity weight configuration rules, perform a profile construction operation on the tag extraction results to obtain the device browsing profile of the target terminal.

[0009] The similarity score of each organizational member in the organizational user profile to the target terminal is calculated by using the device browsing profile. Then, the similarity score is normalized to obtain the usage degree value of each organizational member to the target terminal.

[0010] Obtain real-time updated profiles of each of the organization members, and push content to the target terminal based on the usage level values ​​of each organization member for the target terminal and the real-time updated profiles.

[0011] Optionally, constructing an organizational user profile based on preset organizational profile construction rules, the basic identity information, and the network behavior information includes:

[0012] Based on the preset organizational profile construction rules, each account user is identified using the basic identity information, and the associated users corresponding to each account user are identified.

[0013] Obtain the associated identity information and associated network behavior of each of the associated users, and perform clustering and cleaning operations on each of the account users and the associated users based on the associated identity information, the associated network behavior, the network behavior information and the basic identity information to obtain the organizational member set;

[0014] Based on the associated identity information, the associated network behavior, the network behavior information, and the basic identity information, a personal profile of each organization member in the organization member set is constructed, and the personal profiles are connected to obtain an organization user profile.

[0015] Optionally, the step of using the device browsing profile to calculate the similarity between the organizational user profile and the target terminal, to obtain the similarity score of each organizational member in the organizational user profile with respect to the target terminal, includes:

[0016] Based on the device browsing profile, identify a preset number of content tags with the highest browsing weight, and configure a first weight value for each content tag;

[0017] Based on the user profile of the organization, clustering is performed to obtain the interest tags corresponding to the members of the organization, and a second weight value is configured for each interest tag;

[0018] Based on the tag types of the content tags and the interest tags, and the first weight value and the second weight value, the similarity score of the organization members to the target terminal is calculated.

[0019] Optionally, the target network is one or any combination of telecommunications networks, cable television networks, and computer communication networks.

[0020] Optionally, the step of pushing content to the target terminal based on the usage level values ​​of each organization member for the target terminal and each of the real-time updated profiles includes:

[0021] Based on the real-time updated profiles, identify the best content list for each organization member;

[0022] Based on the usage level of the target terminal by each organization member, a corresponding number of push content are extracted from each of the optimal push content lists, mixed and arranged to obtain the target push interface, and then the target push interface is pushed to the target terminal.

[0023] Optionally, obtaining the real-time updated profiles of each of the organization members includes:

[0024] Obtain comprehensive information about the organization's members, perform data binning on the comprehensive information, and perform outlier cleaning on the binning results to obtain clean text.

[0025] Perform word segmentation and quantization on the clean text to obtain word segmentation vectors;

[0026] Feature extraction is performed on the word segmentation vectors to obtain a text feature set, and a conditional random field network is used to perform label recognition on the text feature set to obtain a label set;

[0027] Similarity clustering is performed on the tags to obtain real-time updated profiles of the organization members.

[0028] Optionally, after obtaining the historical video playback set of the target terminals in the terminal device set, the method further includes:

[0029] The historical video playback set is grouped based on time periods, and a time-based device browsing profile of the target terminal is constructed based on the grouping results for each time period.

[0030] Based on the time-sensitive device browsing profile and the organizational user profile, calculate the second usage level value of each organizational member for the target terminal within a preset target time period;

[0031] Based on the second usage level value and each of the real-time updated profiles, content is pushed to the target terminal within the target time period.

[0032] To address the above problems, the present invention also provides a multimedia push device based on OTT video, the device comprising:

[0033] The account information acquisition module is used to acquire the login account information set of the terminal device set under the target network, and identify the user information set corresponding to the login account information set;

[0034] The organizational profile building module is used to obtain the basic identity information and network behavior information of each user in the user information set, and to build an organizational user profile according to the preset organizational profile building rules, the basic identity information and the network behavior information.

[0035] The device browsing profile construction module is used to obtain the historical video playback set of the target terminal in the terminal device set, perform entity tag extraction operation on the historical video playback set to obtain tag extraction results, and perform profile construction operation on the tag extraction results according to the preset time proximity weight configuration rules to obtain the device browsing profile of the target terminal.

[0036] The member-terminal usage query module is used to calculate the similarity between the device browsing profile and the organizational user profile, obtain the similarity score of each organizational member in the organizational user profile to the target terminal, and perform a normalization operation on each similarity score to obtain the usage value of each organizational member to the target terminal.

[0037] The push module is used to obtain the real-time updated profiles of each of the organization members, and to push content to the target terminal based on the usage level value of each organization member on the target terminal and the real-time updated profiles.

[0038] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0039] At least one processor; and,

[0040] A memory communicatively connected to the at least one processor; wherein,

[0041] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the multimedia push method based on OTT video described above.

[0042] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the aforementioned multimedia push method based on OTT video.

[0043] This invention, based on organizational user profiles and device browsing profiles, can obtain the usage level of target terminals by each organizational member. This transforms the previous method of pushing content based on individual interests into a hybrid approach based on the device usage of multiple organizational members. Therefore, the multimedia push method, apparatus, device, and storage medium based on OTT video provided by this invention can improve the accuracy of OTT video push on multimedia terminals. Attached Figure Description

[0044] Figure 1This is a flowchart illustrating a multimedia push method based on OTT video provided in an embodiment of the present invention.

[0045] Figure 2 This is a detailed flowchart illustrating one step of a multimedia push method based on OTT video provided in an embodiment of the present invention.

[0046] Figure 3 This is a detailed flowchart illustrating one step of a multimedia push method based on OTT video provided in an embodiment of the present invention.

[0047] Figure 4 This is a detailed flowchart illustrating one step of a multimedia push method based on OTT video provided in an embodiment of the present invention.

[0048] Figure 5 A functional block diagram of a multimedia push device based on OTT video provided in an embodiment of the present invention;

[0049] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the multimedia push method based on OTT video, according to an embodiment of the present invention.

[0050] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0051] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0052] This application provides a multimedia push method based on OTT video. In this application, the executing entity of the multimedia push method based on OTT video includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the multimedia push method based on OTT video can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0053] Reference Figure 1The diagram shown is a flowchart illustrating a multimedia push method based on OTT video according to an embodiment of the present invention. In this embodiment, the multimedia push method based on OTT video includes:

[0054] S1. Obtain the login account information set of the terminal device set under the target network, and identify the user information set corresponding to the login account information set.

[0055] In this embodiment of the invention, the target network is one or any of the following: a telecommunications network, a cable television network, and a computer communication network, or an OTT network that integrates them; and the terminal device set includes television terminals, PC terminals, mobile phone terminals, tablet terminals, etc.

[0056] It should be understood that the video playback model after the convergence of OTT networks in my country is based on a membership system. A family or group only needs one membership account to log in to the video playback terminal device to meet the group's needs. Therefore, even with the same playback terminal device and the same login account, there are often different scenarios where different people use it, making it difficult to recommend videos based on individual profiles and interests.

[0057] Specifically, in this embodiment of the invention, the target network is a WiFi network in computer communication networks; the set of terminal devices includes several mobile phones, computers, televisions, tablets, etc. Among them, mobile phones are more numerous and more private and personalized, and may have many accounts; while computers, televisions, and other devices are usually shared by multiple users using a single account.

[0058] Therefore, in this embodiment of the invention, the login account information set can be obtained by querying each terminal device through the WiFi module, and then the user information set can be obtained based on the user authentication information bound to each account information. The number of elements in the login account information set and the user information set may not be equal.

[0059] S2. Obtain the basic identity information and network behavior information of each user in the user information set, and construct an organizational user profile according to the preset organizational profile construction rules, the basic identity information and the network behavior information.

[0060] In this embodiment of the invention, massive amounts of network data are acquired through a pre-built data source anchor market. This includes basic user identity information, such as name, gender, and age, as well as network behavior information, such as viewing, commenting, following, and friend activity. The data source anchor market is a database constructed by crawling data from internet platforms such as Zhihu, Weibo, and Shuo.

[0061] For details, please refer to the following: Figure 2As shown in this embodiment of the invention, constructing an organizational user profile based on preset organizational profile construction rules, the basic identity information, and the network behavior information includes:

[0062] S21. Based on the preset organizational profile construction rules, use the basic identity information to identify each account user and identify the associated users corresponding to each account user.

[0063] S22. Obtain the associated identity information and associated network behavior of each of the associated users, and perform clustering and cleaning operations on each of the account users and the associated users based on the associated identity information, the associated network behavior, the network behavior information and the basic identity information to obtain the organizational member set;

[0064] S23. Based on the associated identity information, the associated network behavior, the network behavior information, and the basic identity information, construct a personal profile of each organization member in the organization member set, and connect the personal profiles to obtain an organization user profile.

[0065] The organizational profile construction rule is a rule that filters organizational members from a large number of users and connects organizational members into profiles.

[0066] Based on the aforementioned basic information, this invention can construct a personal profile and thereby obtain each user's associated users, which refer to user nodes such as friends, colleagues, family members, and classmates. Then, the associated identity information and associated network information of the associated users are obtained.

[0067] In this embodiment of the invention, the clustering relationship of each account user can be identified based on the associated identity information, the associated network behavior, the network behavior information, and the basic identity information to obtain the group type formed by each account user, such as a family or a company. Then, special points among users are removed according to the group type, while the regular structure of the organization is retained to obtain the set of organizational members. For example, when the group type is a family, the "friend account node" in the user information set can be deleted, and the immediate family members can be retained.

[0068] Furthermore, in this embodiment of the invention, obtaining the real-time updated profiles of each of the organization members includes:

[0069] Obtain comprehensive information about the organization's members, perform data binning on the comprehensive information, and perform outlier cleaning on the binning results to obtain clean text.

[0070] Perform word segmentation and quantization on the clean text to obtain word segmentation vectors;

[0071] Feature extraction is performed on the word segmentation vectors to obtain a text feature set, and a conditional random field network is used to perform label recognition on the text feature set to obtain a label set;

[0072] Similarity clustering is performed on the tags to obtain real-time updated profiles of the organization members.

[0073] Specifically, in this embodiment of the invention, the comprehensive information of the organization members refers to the combination of the basic identity information and network behavior information of all organization members. Further, this embodiment of the invention achieves data classification and grouping through data binning, then cleans outlier values, missing values, and duplicate values ​​in the data to obtain clean text. Next, a named entity recognition network model is used for tag recognition to obtain a tag set. Finally, an arbitrary profile construction method is used to cluster, combine, and weight each tag to form a real-time updated profile of each organization member. These profiles are then connected to obtain the organization user profile. Here, named entity recognition refers to a method for identifying entities with specific meanings in text, which can be implemented through a neural network model and will not be elaborated here.

[0074] S3. Obtain the historical video playback set of the target terminal in the terminal device set, and perform entity tag extraction operation on the historical video playback set to obtain tag extraction results. Then, according to the preset time proximity weight configuration rules, perform a profile construction operation on the tag extraction results to obtain the device browsing profile of the target terminal.

[0075] In this embodiment of the invention, the target terminal is any device in the set of terminal devices, such as a computer or a television. The present invention will be described below using a television as the target terminal.

[0076] This invention records television playback content based on preset data points, obtaining a historical video playback set [**football,** World Championship Finals, Romance of the Three Kingdoms…]. Entity tag extraction results can be obtained [Player A, Football, Player B, Esports, Cao Cao,…]. Based on historical viewing frequency and time, each tag is weighted, with higher weight coefficients for more views and longer cumulative viewing time, gradually decreasing over time. Finally, the extracted tag results are used to construct a user profile, resulting in a device browsing profile for the television.

[0077] Furthermore, in another embodiment of the present invention, after obtaining the historical video playback set of the target terminals in the terminal device set, the method further includes:

[0078] The historical video playback set is grouped based on time periods, and a time-based device browsing profile of the target terminal is constructed based on the grouping results for each time period.

[0079] Based on the time-sensitive device browsing profile and the organizational user profile, calculate the second usage level value of each organizational member for the target terminal within a preset target time period;

[0080] Based on the second usage level value and each of the real-time updated profiles, content is pushed to the target terminal within the target time period.

[0081] In this embodiment of the invention, the historical video playback set can be classified based on time periods, and a separate profile can be constructed for each time period, which can yield more accurate profile construction results. For example, there may be a situation where user C and user D share the same TV, with user C using it most of the time, but user D using it at 7 pm. When the TV is turned on around 7 pm, user D's profile should be given greater weight when recommending content, thereby increasing the accuracy of OTT video content push.

[0082] S4. Calculate the similarity between the organization user profile and the device browsing profile to obtain the similarity score of each organization member in the organization user profile to the target terminal, and normalize each similarity score to obtain the usage degree value of each organization member to the target terminal.

[0083] For details, please refer to the following: Figure 3 As shown in this embodiment of the invention, the step of calculating the similarity between the device browsing profile and the organizational user profile to obtain the similarity score of each organizational member in the organizational user profile with respect to the target terminal includes:

[0084] S41. Based on the device browsing profile, identify a preset number of content tags with the highest browsing weight, and configure a first weight value for each content tag;

[0085] S42. Based on the organizational user profile, cluster the interest tags corresponding to the organizational members and assign a second weight value to each interest tag.

[0086] S43. Calculate the similarity score of the organization member to the target terminal based on the tag type of the content tag and the interest tag, and the first weight value and the second weight value.

[0087] In this embodiment of the invention, the N content tags with the largest weight in the device browsing profile of the television, such as 5 content tags [Player A, Football, Player B, Esports, Cao Cao], are configured with a first weight value and sorted to obtain [Football: 70%, Player A: 50%, Player B: 30%, ...].

[0088] Furthermore, based on the organizational user profiles of each member, member E might have a profile of [Korean dramas: 80%, Park Geun-hye: 50%, etc.], member F might have a profile of [football: 80%, player: 70%, etc.], and member G might have a profile of [anime: 70%, Three Kingdoms: 50%, etc.]. Therefore, based on similarity weights, the device browsing profiles of this television have the highest similarity in the following order: member F > member G > member E. Note that the similarity scores in this embodiment can be calculated statistically using big data, and the specific method is not unique.

[0089] Furthermore, in this embodiment of the invention, a normalization operation is performed to convert each similarity score into a usage degree value, for example, a usage degree value of user F: 0.5, user G: 0.4, and user E: 0.1 may be obtained.

[0090] S5. Obtain the real-time updated profile of each of the organization members, and push content to the target terminal based on the usage level value of each organization member on the target terminal and the real-time updated profile.

[0091] For details, please refer to the following: Figure 4 As shown in this embodiment of the invention, the step of pushing content to the target terminal based on the usage level value of each organization member for the target terminal and each of the real-time updated profiles includes:

[0092] S51. Based on the real-time updated profiles, identify the best content list for each organization member;

[0093] S52. Based on the usage level of each organization member on the target terminal, extract the corresponding number of push content from each of the optimal push content lists, mix and arrange them to obtain the target push interface, and push the target push interface to the target terminal.

[0094] In this embodiment of the invention, based on each real-time updated profile, the optimal content list for each organizational member is obtained, such as member F [content a1, ..., content a10], member G [content b1, ..., content b10], and member E [content c1, ..., content c10]. Then, based on the usage level of each organizational member on the target terminal, a target push interface [content a1...content a5, content b1...content b4, content c1] may be obtained and pushed to the television.

[0095] Based on the organizational user profile and the device browsing profile, this invention can obtain the usage level value of each organizational member for the target terminal. This further transforms the previous method of pushing content based on individual interests into a hybrid push based on the device usage of multiple organizational members. Therefore, the multimedia push method based on OTT video provided by this invention can improve the accuracy of OTT video push on multimedia terminals.

[0096] like Figure 5 The diagram shown is a functional block diagram of a multimedia push device based on OTT video provided in an embodiment of the present invention.

[0097] The OTT video-based multimedia push device 100 of this invention can be installed in an electronic device. Depending on the functions implemented, the OTT video-based multimedia push device 100 may include an account information acquisition module 101, an organization profile construction module 102, a device browsing profile construction module 103, a member-terminal usage query module 104, and a push module 105. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0098] In this embodiment, the functions of each module / unit are as follows:

[0099] The account information acquisition module 101 is used to acquire the login account information set of the terminal device set under the target network, and identify the user information set corresponding to the login account information set;

[0100] The organization profile construction module 102 is used to obtain the basic identity information and network behavior information of each user in the user information set, and construct an organization user profile according to the preset organization profile construction rules, the basic identity information and the network behavior information.

[0101] The device browsing profile construction module 103 is used to obtain the historical video playback set of the target terminal in the terminal device set, and perform entity tag extraction operation on the historical video playback set to obtain tag extraction results. According to the preset time proximity weight configuration rules, the module performs profile construction operation on the tag extraction results to obtain the device browsing profile of the target terminal.

[0102] The member-terminal usage query module 104 is used to calculate the similarity between the device browsing profile and the organizational user profile, obtain the similarity score of each organizational member in the organizational user profile to the target terminal, and perform a normalization operation on each similarity score to obtain the usage value of each organizational member to the target terminal.

[0103] The push module 105 is used to obtain the real-time updated profiles of each of the organization members, and to push content to the target terminal based on the usage level value of each organization member on the target terminal and the real-time updated profiles.

[0104] In detail, the modules in the OTT video-based multimedia push device 100 described in this application embodiment adopt the same characteristics as described above during use. Figures 1 to 4 The method uses the same technical means as the multimedia push method based on OTT video described above and can produce the same technical effect, so it will not be repeated here.

[0105] like Figure 6 The diagram shown is a structural schematic of an electronic device 1 that implements a multimedia push method based on OTT video according to an embodiment of the present invention.

[0106] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13. It may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a multimedia push program based on OTT video.

[0107] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device 1, connecting various components of the electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing multimedia push programs based on OTT video) and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0108] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code of a multimedia push program based on OTT video, but also to temporarily store data that has been output or will be output.

[0109] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0110] The communication interface 13 is used for communication between the electronic device 1 and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or, optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0111] Figure 6 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 6The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0112] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0113] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0114] The multimedia push program based on OTT video stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, which, when run in the processor 10, can achieve the following:

[0115] Obtain the set of login account information of the terminal device set under the target network, and identify the set of user information corresponding to the set of login account information;

[0116] Obtain the basic identity information and network behavior information of each user in the user information set, and construct an organizational user profile based on the preset organizational profile construction rules, the basic identity information and the network behavior information;

[0117] Obtain the historical video playback set of the target terminal in the terminal device set, and perform entity tag extraction operation on the historical video playback set to obtain tag extraction results. Then, according to the preset time proximity weight configuration rules, perform a profile construction operation on the tag extraction results to obtain the device browsing profile of the target terminal.

[0118] The similarity score of each organizational member in the organizational user profile to the target terminal is calculated by using the device browsing profile. Then, the similarity score is normalized to obtain the usage degree value of each organizational member to the target terminal.

[0119] Obtain real-time updated profiles of each of the organization members, and push content to the target terminal based on the usage level values ​​of each organization member for the target terminal and the real-time updated profiles.

[0120] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0121] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0122] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0123] Obtain the set of login account information of the terminal device set under the target network, and identify the set of user information corresponding to the set of login account information;

[0124] Obtain the basic identity information and network behavior information of each user in the user information set, and construct an organizational user profile based on the preset organizational profile construction rules, the basic identity information and the network behavior information;

[0125] Obtain the historical video playback set of the target terminal in the terminal device set, and perform entity tag extraction operation on the historical video playback set to obtain tag extraction results. Then, according to the preset time proximity weight configuration rules, perform a profile construction operation on the tag extraction results to obtain the device browsing profile of the target terminal.

[0126] The similarity score of each organizational member in the organizational user profile to the target terminal is calculated by using the device browsing profile. Then, the similarity score is normalized to obtain the usage degree value of each organizational member to the target terminal.

[0127] Obtain real-time updated profiles of each of the organization members, and push content to the target terminal based on the usage level values ​​of each organization member for the target terminal and the real-time updated profiles.

[0128] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0129] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0131] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0132] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0133] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0134] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0135] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A multimedia push method based on OTT video, characterized in that, The method includes: Obtain the set of login account information of the terminal device set under the target network, and identify the set of user information corresponding to the set of login account information; Obtain the basic identity information and network behavior information of each user in the user information set, and construct an organizational user profile based on the preset organizational profile construction rules, the basic identity information and the network behavior information; Obtain the historical video playback set of the target terminal in the terminal device set, and perform entity tag extraction operation on the historical video playback set to obtain tag extraction results. Then, according to the preset time proximity weight configuration rules, perform a profile construction operation on the tag extraction results to obtain the device browsing profile of the target terminal. The similarity score of each organizational member in the organizational user profile to the target terminal is calculated by using the device browsing profile. Then, the similarity score is normalized to obtain the usage degree value of each organizational member to the target terminal. Obtain real-time updated profiles of each of the organization members, and push content to the target terminal based on the usage level values ​​of each organization member for the target terminal and the real-time updated profiles.

2. The multimedia push method based on OTT video as described in claim 1, characterized in that, The step of constructing an organizational user profile based on preset organizational profile construction rules, the basic identity information, and the network behavior information includes: Based on the preset organizational profile construction rules, each account user is identified using the basic identity information, and the associated users corresponding to each account user are identified. Obtain the associated identity information and associated network behavior of each of the associated users, and perform clustering and cleaning operations on each of the account users and the associated users based on the associated identity information, the associated network behavior, the network behavior information and the basic identity information to obtain the organizational member set; Based on the associated identity information, the associated network behavior, the network behavior information, and the basic identity information, a personal profile of each organization member in the organization member set is constructed, and the personal profiles are connected to obtain an organization user profile.

3. The multimedia push method based on OTT video as described in claim 1, characterized in that, The step of using the device browsing profile to perform similarity calculation on the organizational user profile, and obtaining the similarity score of each organizational member in the organizational user profile to the target terminal, includes: Based on the device browsing profile, identify a preset number of content tags with the highest browsing weight, and configure a first weight value for each content tag; Based on the user profile of the organization, clustering is performed to obtain the interest tags corresponding to the members of the organization, and a second weight value is configured for each interest tag; Based on the tag types of the content tags and the interest tags, and the first weight value and the second weight value, the similarity score of the organization members to the target terminal is calculated.

4. The multimedia push method based on OTT video as described in claim 1, characterized in that, The target network is one or any combination of telecommunications networks, cable television networks, and computer communication networks.

5. The multimedia push method based on OTT video as described in claim 1, characterized in that, The step of pushing content to the target terminal based on the usage level values ​​of each organization member for the target terminal and each of the real-time updated profiles includes: Based on the real-time updated profiles, identify the best content list for each organization member; Based on the usage level of the target terminal by each organization member, a corresponding number of push content are extracted from each of the optimal push content lists, mixed and arranged to obtain the target push interface, and then the target push interface is pushed to the target terminal.

6. The multimedia push method based on OTT video as described in claim 1, characterized in that, The process of obtaining real-time updated profiles of each of the organization members includes: Obtain comprehensive information about the organization's members, perform data binning on the comprehensive information, and perform outlier cleaning on the binning results to obtain clean text. Perform word segmentation and quantization on the clean text to obtain word segmentation vectors; Feature extraction is performed on the word segmentation vectors to obtain a text feature set, and a conditional random field network is used to perform label recognition on the text feature set to obtain a label set; Similarity clustering is performed on the tags to obtain real-time updated profiles of the organization members.

7. The multimedia push method based on OTT video as described in claim 1, characterized in that, After obtaining the historical video playback set of the target terminals in the terminal device set, the method further includes: The historical video playback set is grouped based on time periods, and a time-based device browsing profile of the target terminal is constructed based on the grouping results for each time period. Based on the time-sensitive device browsing profile and the organizational user profile, calculate the second usage level value of each organizational member for the target terminal within a preset target time period; Based on the second usage level value and each of the real-time updated profiles, content is pushed to the target terminal within the target time period.

8. A multimedia push device based on OTT video, characterized in that, The device includes: The account information acquisition module is used to acquire the login account information set of the terminal device set under the target network, and identify the user information set corresponding to the login account information set; The organizational profile building module is used to obtain the basic identity information and network behavior information of each user in the user information set, and to build an organizational user profile according to the preset organizational profile building rules, the basic identity information and the network behavior information. The device browsing profile construction module is used to obtain the historical video playback set of the target terminal in the terminal device set, perform entity tag extraction operation on the historical video playback set to obtain tag extraction results, and perform profile construction operation on the tag extraction results according to the preset time proximity weight configuration rules to obtain the device browsing profile of the target terminal. The member-terminal usage query module is used to calculate the similarity between the device browsing profile and the organizational user profile, obtain the similarity score of each organizational member in the organizational user profile to the target terminal, and perform a normalization operation on each similarity score to obtain the usage value of each organizational member to the target terminal. The push module is used to obtain the real-time updated profiles of each of the organization members, and to push content to the target terminal based on the usage level value of each organization member on the target terminal and the real-time updated profiles.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the multimedia push method based on OTT video as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the multimedia push method based on OTT video as described in any one of claims 1 to 7.

Images