Video polyphonic ringtone user portrait generation method and device, electronic equipment and medium

Abstract

The invention discloses a video polyphonic ringtone user portrait generation method and apparatus, an electronic device and a medium. The method comprises the steps of obtaining multi-dimensional user behavior data of a target user through a plurality of preset video polyphonic ringtone burying points; performing entity extraction and data conversion on the multi-dimensional user behavior data to obtain a plurality of content entities and corresponding user behavior types; determining a video polyphonic ringtone multi-dimensional label corresponding to the content entity; determining a multi-dimensional user tag of the target user according to the video polyphonic ringtone multi-dimensional tag and the corresponding user behavior type; and generating a video polyphonic ringtone user portrait of the target user according to the multi-dimensional user tag. The method improves the accuracy and comprehensiveness of the video polyphonic ringtone user portrait, and can be widely applied to the technical field of polyphonic ringtones.

Description

Technical Field

[0001] The present invention relates to the technical field of color ring back tone, and in particular to a method, device, electronic device and medium for generating a user portrait of a video color ring back tone. Background Art

[0002] In telecommunications services, due to the development of 5G technology, a special service based on VOLTE, video ringback tone, has emerged. It has transformed the traditional "heard ringback tone" into "seen video", that is, when a user makes a voice call or video call on the VoLTE network, before waiting for the call to be connected, he will see a video content set by the called user without the need for any APP. Video ringback tone supports uploading video and audio at the same time. When the user's mobile phone supports video playback, the video will be played first; if it does not support it, the audio will be played.

[0003] As a new service technology, video ringback tone is only available to operators. Currently, there is a lack of mature solutions for user profile analysis specifically for video ringback tone scenarios. If solutions from other industries are applied to video ringback tone scenarios, data sampling will be incomplete or one-sided, and the real user profile of video ringback tone cannot be accurately reflected.

[0004] Terminology explanation:

[0005] Tracking analysis: is a method of collecting user behavior data on a website or application. By setting "tracking points" on specific user interaction events, user behaviors can be tracked and recorded, such as clicking buttons, browsing pages, sharing, purchasing, etc. This data is essential for understanding user behavior patterns, optimizing product design, improving user experience, and evaluating marketing effectiveness.

[0006] User portrait: Based on an in-depth understanding of the target user group, representative and typical user roles are constructed through research, interviews, data analysis, etc. User portraits usually include multiple dimensions such as the user's basic attributes, behavioral habits, psychological characteristics, and usage scenarios, aiming to help companies and product designers more accurately grasp user needs, formulate more accurate marketing strategies, optimize product design, and improve user experience.

[0007] ETL (Extract-Transform-Load): It is used to describe the process of extracting, transforming, and loading data from the source to the destination. It is the lifeline of the data warehouse. It is a data processing process used to extract data from different data sources, transform and clean the data, and load the processed data into the target system or data warehouse.

[0008] Video ringback tone: It is a special service of VoLTE, which evolves "audible ringback tone" into "visual ringback tone". When users make a voice call or video call on the VoLTE network, the video content they see before the call is connected is called "video ringback tone". Video ringback tone users can create or upload personalized video content or choose from the operator's video library. Different video content can also be set for different callers. Summary of the invention

[0009] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0010] To this end, an object of an embodiment of the present invention is to provide a method for generating a video ringback tone user portrait, which improves the accuracy and comprehensiveness of the video ringback tone user portrait.

[0011] Another object of an embodiment of the present invention is to provide a device for generating a video ringback tone user portrait.

[0012] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0013] On the one hand, an embodiment of the present invention provides a method for generating a video ringback tone user portrait, comprising the following steps:

[0014] Obtain multi-dimensional user behavior data of target users through multiple preset video ringback tone embedding points;

[0015] Performing entity extraction and data conversion on the multi-dimensional user behavior data to obtain multiple content entities and corresponding user behavior types;

[0016] Determine a multi-dimensional tag of a video ring back tone corresponding to the content entity;

[0017] Determine the multidimensional user tag of the target user according to the multidimensional tag of the video ringback tone and the corresponding user behavior type;

[0018] A video ringback tone user portrait of the target user is generated according to the multi-dimensional user tag.

[0019] Furthermore, in one embodiment of the present invention, the video ringback tone embedding point includes at least one of a video ringback tone recommendation page embedding point, a video ringback tone details page embedding point, a video ringback tone production page embedding point, and a user video ringback tone list embedding point, and the multi-dimensional user behavior data includes at least one of page browsing behavior data, ringback tone collection / ringback tone setting behavior data, ringback tone production behavior data, and cancel collection / ringback tone deletion behavior data.

[0020] Further, in an embodiment of the present invention, the step of obtaining multi-dimensional user behavior data of a target user through a plurality of preset video ringback tone embedding points includes at least one of the following:

[0021] Obtaining the target user's page dwell time / scrolling rate on the video ringback tone recommendation page through the video ringback tone recommendation page embedding point, and generating the page browsing behavior data according to the video ringback tone recommendation page and the corresponding page dwell time / page scrolling rate;

[0022] Acquire the ringback tone collection / ringback tone setting operation of the target user on the video ringback tone details page through the video ringback tone details page embedding point, and generate the ringback tone collection / ringback tone setting behavior data according to the video ringback tone details page and the ringback tone collection / ringback tone setting operation;

[0023] Acquire the text / picture input operation and ringtone template selection operation of the target user on the video ringtone production page through the video ringtone production page embedding point, and generate the ringtone production behavior data according to the text / picture input operation and the ringtone template selection operation and the corresponding operation object;

[0024] The uncollection / deletion operation of the target user in the user video ringback tone list is obtained through the user video ringback tone list embedding point, and the uncollection / deletion behavior data is generated according to the uncollection / deletion operation and the corresponding operation object.

[0025] Further, in one embodiment of the present invention, the entity extraction and data conversion of the multi-dimensional user behavior data to obtain multiple content entities and corresponding user behavior types includes at least one of the following:

[0026] Performing entity extraction and data conversion on the page browsing behavior data to obtain a browsing object entity, using the browsing object entity as the content entity, and determining that the corresponding user behavior type is a browsing behavior;

[0027] Performing entity extraction and data conversion on the ringback tone collection / ringback tone setting behavior data to obtain a ringback tone collection / ringback tone setting object entity, using the ringback tone collection / ringback tone setting object entity as the content entity, and determining the corresponding user behavior type as the ringback tone collection / ringback tone setting behavior;

[0028] Performing entity extraction and data conversion on the ringback tone production behavior data to obtain a text / picture entity and a ringback tone template entity, using the text / picture entity and the ringback tone template entity as the content entity, and determining that the corresponding user behavior type is a ringback tone production behavior;

[0029] Entity extraction and data conversion are performed on the cancel favorite / color ringtone deletion behavior data to obtain a cancel favorite / color ringtone deletion object entity, the cancel favorite / color ringtone deletion object entity is used as the content entity, and the corresponding user behavior type is determined to be a cancel favorite / color ringtone deletion behavior.

[0030] Further, in an embodiment of the present invention, the determining of the multi-dimensional tag of the video ring back tone corresponding to the content entity specifically includes:

[0031] When the content entity is one of a browsing object entity, a ringback tone collection / ringback tone setting object entity, and a cancel collection / ringback tone deletion object entity, searching for video ringback tone data corresponding to the content entity in a ringback tone database, and obtaining the video ringback tone multi-dimensional tag corresponding to the video ringback tone data, wherein the video ringback tone multi-dimensional tag includes a video ringback tone theme tag, a video ringback tone attribution tag, a video ringback tone content tag, a video picture tone tag, and a music style tag;

[0032] When the content entity is a text / picture entity and a ring back tone template entity, the text / picture data corresponding to the content entity is searched in the user database, and the text / picture data is semantically analyzed to obtain the corresponding video ring back tone theme tag, video ring back tone content tag and video ring back tone attribution tag, and the ring back tone template data corresponding to the ring back tone template entity is searched in the ring back tone template library, and the video picture tone tag and music style tag corresponding to the ring back tone template data are obtained, and then the video ring back tone multi-dimensional tag is generated according to the video ring back tone theme tag, the video ring back tone content tag, the video ring back tone attribution tag, the video picture tone tag and the music style tag.

[0033] Further, in an embodiment of the present invention, determining the user tag of the target user according to the multi-dimensional tag of the video ringback tone and the corresponding user behavior type specifically includes:

[0034] Determine the preference weight factor corresponding to each of the user behavior types;

[0035] Determine a first user preference score for each of the video ringback tone theme tags according to the preference weight factor, select a target theme tag from the video ringback tone theme tags according to the first user preference score, and use the target theme tag as the user theme preference tag for the target user;

[0036] Determine a second user preference score for each of the video ringback tone attribution tags according to the preference weight factor, select a target attribution tag from the video ringback tone attribution tags according to the second user preference score, and then determine a user social relationship tag for the target user according to the target attribution tag;

[0037] Determine a third user preference score of each of the video ringback tone content tags according to the preference weight factor, select a target content tag from the video ringback tone content tags according to the third user preference score, and use the target content tag as the user content preference tag of the target user;

[0038] Determine a fourth user preference score for each of the video picture tone labels according to the preference weight factor, select a target tone label from the video picture tone labels according to the fourth user preference score, determine a fifth user preference score for each of the music style labels according to the preference weight factor, select a target style label from the music style labels according to the fifth user preference score, and then predict the user personality / mood label of the target user according to the target tone label and the target style label;

[0039] The multi-dimensional user tag is generated according to the user topic preference tag, the user social relationship tag, the user content preference tag, and the user personality / mood tag.

[0040] Further, in an embodiment of the present invention, generating a video ringback tone user portrait of the target user according to the multi-dimensional user tag specifically includes:

[0041] Acquire basic user information of the target user according to the authentication login information of the target user;

[0042] Adding the basic user information and the multi-dimensional user tags to a preset user portrait data warehouse;

[0043] The basic user information and the multi-dimensional user tags are aggregated through a preset big data model component to obtain the video ringback tone user portrait.

[0044] On the other hand, an embodiment of the present invention provides a device for generating a video ringback tone user portrait, including:

[0045] A data acquisition module is used to acquire multi-dimensional user behavior data of target users through multiple preset video ringback tone embedding points;

[0046] A data processing module, used to perform entity extraction and data conversion on the multi-dimensional user behavior data to obtain multiple content entities and corresponding user behavior types;

[0047] A color ring back tone label determination module, used to determine a multi-dimensional label of a video color ring back tone corresponding to the content entity;

[0048] A user label determination module, used to determine the multi-dimensional user label of the target user according to the multi-dimensional label of the video ringback tone and the corresponding user behavior type;

[0049] A user portrait generation module is used to generate a video ringback tone user portrait of the target user according to the multi-dimensional user tag.

[0050] On the other hand, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein the program, when executed by the processor, realizes the method for generating a user portrait of a video ringtone as described above.

[0051] On the other hand, an embodiment of the present invention further provides a storage medium, which is a computer-readable storage medium used for computer-readable storage, and the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the video ringtone user portrait generation method as described above.

[0052] The advantages and beneficial effects of the present invention will be partly given in the following description, partly become apparent from the following description, or be understood through the practice of the present invention:

[0053] The embodiment of the present invention obtains multi-dimensional user behavior data of the target user through multiple preset video ringback tone embedding points, performs entity extraction and data conversion on the multi-dimensional user behavior data, obtains multiple content entities and corresponding user behavior types, determines the multi-dimensional label of the video ringback tone corresponding to the content entity, determines the multi-dimensional user label of the target user according to the multi-dimensional label of the video ringback tone and the corresponding user behavior type, and generates a video ringback tone user portrait of the target user according to the multi-dimensional user label. The embodiment of the present invention obtains multi-dimensional user behavior data through video ringback tone embedding points, thereby obtaining the content entity and the corresponding user behavior type of the user behavior object, and can obtain a multi-dimensional user label according to the multi-dimensional label of the video ringback tone of the content entity and the corresponding user behavior type, thereby generating a video ringback tone user portrait according to the multi-dimensional user label, thereby improving the accuracy and comprehensiveness of the video ringback tone user portrait. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solution in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solution of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0055] Figure 1 A flowchart of the steps of the method for generating a user portrait of a video ringback tone provided by an embodiment of the present invention;

[0056] Figure 2A schematic diagram of a specific process of a method for generating a user portrait of a video ringback tone provided by an embodiment of the present invention;

[0057] Figure 3 A step flow chart of step S101 provided in an embodiment of the present invention;

[0058] Figure 4 A step flow chart of step S102 provided in an embodiment of the present invention;

[0059] Figure 5 A step flow chart of step S103 provided in an embodiment of the present invention;

[0060] Figure 6 A step flow chart of step S104 provided in an embodiment of the present invention;

[0061] Figure 7 A step flow chart of step S105 provided in an embodiment of the present invention;

[0062] Figure 8 A schematic diagram of the structure of a device for generating a user portrait of a video ringback tone provided by an embodiment of the present invention;

[0063] Fig. 9 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention;

[0064] Fig.10 A schematic diagram of the structure of a storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0065] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limitations on the present application. It should be noted that, although the functional module division is performed in the system schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order from the module division in the system schematic diagram or the flow chart. For the step numbers in the following embodiments, they are only set for the convenience of explanation, and the order between the steps is not limited in any way. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0066] In the description of the present invention, the meaning of "a plurality" is two or more. If there is a description of the first or the second, it is only for the purpose of distinguishing the technical features, and it cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features. In addition, unless otherwise defined, all technical and scientific terms used in this document have the same meaning as those commonly understood by technicians in the technical field of this application. The terms used in this document are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0067] The video ringback tone user portrait generation method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a set-top box, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the video ringback tone user portrait generation method, etc., but is not limited to the above forms.

[0068] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0069] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with the relevant laws, regulations, and standards of the relevant countries and regions. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0070] The present invention aims to improve the accuracy and comprehensiveness of the user portrait analysis of video ringback tone, and provide data support for the refined operation and recommendation of video ringback tone. In addition, since the content and IP of video ringback tone also have copyright, they need to be purchased from different content providers every year. The user portrait analysis of video ringback tone can explore the user's preference for different content and IP, monitor the quality of content provided by content providers, establish a long-term content provider whitelist mechanism, and provide a basis and risk avoidance for launching new procurement projects.

[0071] like Figure 1 FIG. 1 is a flowchart of a method for generating a user portrait of a video ring back tone provided by an embodiment of the present invention. Figure 1 The embodiment of the present invention provides a method for generating a video ringback tone user portrait, which specifically includes the following steps:

[0072] S101, obtaining multi-dimensional user behavior data of target users through multiple preset video ringback tone embedding points;

[0073] S102, performing entity extraction and data conversion on the multi-dimensional user behavior data to obtain multiple content entities and corresponding user behavior types;

[0074] S103, determining a multi-dimensional tag of a video ringback tone corresponding to a content entity;

[0075] S104, determining a multi-dimensional user tag of a target user according to the multi-dimensional tag of the video ringback tone and the corresponding user behavior type;

[0076] S105: Generate a video ringback tone user portrait of the target user according to the multi-dimensional user tags.

[0077] The embodiment of the present invention acquires multi-dimensional user behavior data through video ringback tone embedding, thereby obtaining the content entity of the user behavior object and the corresponding user behavior type. A multi-dimensional user tag can be obtained based on the video ringback tone multi-dimensional tag of the content entity and the corresponding user behavior type, thereby generating a video ringback tone user portrait based on the multi-dimensional user tag, thereby improving the accuracy and comprehensiveness of the video ringback tone user portrait.

[0078] like Figure 2 The figure is a schematic diagram of a specific process of the method for generating a video ring back tone user portrait provided by an embodiment of the present invention. Figure 2 The steps of the embodiment of the present invention are further described.

[0079] Further as an optional implementation method, the video ringback tone embedding includes at least one of a video ringback tone recommendation page embedding, a video ringback tone details page embedding, a video ringback tone production page embedding and a user video ringback tone list embedding, and the multi-dimensional user behavior data includes at least one of page browsing behavior data, ringback tone collection / ringback tone setting behavior data, ringback tone production behavior data and cancel collection / ringback tone deletion behavior data.

[0080] like Figure 3 FIG. 1 is a flowchart of step S101 provided in an embodiment of the present invention, referring to FIG. Figure 3 As an optional implementation, obtaining multi-dimensional user behavior data of target users through a plurality of preset video ringback tone embedding points includes at least one of the following:

[0081] S1011, obtaining the target user's page dwell time / scrolling rate on the video ringtone recommendation page through embedding points on the video ringtone recommendation page, and generating page browsing behavior data according to the video ringtone recommendation page and the corresponding page dwell time / page scrolling rate;

[0082] S1012, obtaining the target user's ringtone collection / ringtone setting operation on the video ringtone details page through the video ringtone details page embedding point, and generating ringtone collection / ringtone setting behavior data according to the video ringtone details page and the ringtone collection / ringtone setting operation;

[0083] S1013, obtaining the text / picture input operation and ring back tone template selection operation of the target user on the video ring back tone production page through the video ring back tone production page embedding point, and generating the ring back tone production behavior data according to the text / picture input operation and the ring back tone template selection operation and the corresponding operation object;

[0084] S1014. Obtain the uncollection / deletion operation of the target user in the user video ringback tone list through the user video ringback tone list embedding point, and generate uncollection / deletion behavior data according to the uncollection / deletion operation and the corresponding operation object.

[0085] Specifically, user behavior data is collected through two methods: active reporting by the client APP and APP event-driven triggering. Active reporting by the client APP includes terminal information collected from user registration and login; user behavior history records generated by users browsing and playing video ringtones, etc. APP event-driven triggering includes user collection, likes, and setting as ringtone operation records; when users make AI DIY video ringtones, the corresponding AI capabilities, AI styles, AI themes, AI template tags and other style preference data; user cancels the collection of video ringtones, deletes ringtones in the ringtone library, and other weakening or required elimination and correction operation events.

[0086] In the embodiment of the present invention, the page dwell time and the user scrolling screen speed are set on the video ringtone recommendation page, and finally saved in the server in the form of log files; event-driven tracking is set on the video ringtone details page, and after the user clicks on the favorite or sets it as a ringtone, it is triggered by the back-end interface and saved to the database; click event tracking is set in each capability topic and template of the AI ​​video ringtone area, and the log file recorded in the server is reported when the user triggers it; the video ringtone event tracking when the user cancels the favorite or deletes the ringtone, because these two operations belong to hard deletion of the database, the background interface saves the data by recording logs.

[0087] like Figure 4 FIG. 1 is a flow chart of step S102 provided in an embodiment of the present invention, referring to FIG. Figure 4 As an optional implementation, entity extraction and data conversion are performed on the multi-dimensional user behavior data to obtain multiple content entities and corresponding user behavior types, including at least one of the following:

[0088] S1021, extracting entities and converting data from page browsing behavior data to obtain browsing object entities, using the browsing object entities as content entities, and determining the corresponding user behavior type as browsing behavior;

[0089] S1022, extracting entities and converting data of the ringback tone collection / ringback tone setting behavior data to obtain a ringback tone collection / ringback tone setting object entity, taking the ringback tone collection / ringback tone setting object entity as a content entity, and determining the corresponding user behavior type as a ringback tone collection / ringback tone setting behavior;

[0090] S1023, extracting entities and converting data on the ringback tone production behavior data to obtain text / picture entities and ringback tone template entities, taking the text / picture entities and the ringback tone template entities as content entities, and determining the corresponding user behavior type as the ringback tone production behavior;

[0091] S1024, extracting entities and converting data on the cancel favorite / ringback tone deletion behavior data to obtain a cancel favorite / ringback tone deletion object entity, using the cancel favorite / ringback tone deletion object entity as a content entity, and determining the corresponding user behavior type as the cancel favorite / ringback tone deletion behavior.

[0092] Specifically, the embodiment of the present invention uses ETL tools to extract data, such as log file data, offline database data, online database data, etc., including user and terminal data collected by APP, log data reported by embedding points, video ringback tone feature data extracted offline by AI big model tools, behavior triggered by user operation events and AI capability style preference data, etc. Then the data is cleaned, converted and integrated. This process includes data deduplication, format conversion, error correction, data association, calculation and other operations to ensure that the data meets the specifications and requirements of the target data warehouse. After the multi-dimensional user tags are generated, they need to be loaded into the data warehouse.

[0093] like Figure 5 FIG. 1 is a flow chart of step S104 provided in an embodiment of the present invention, referring to FIG. Figure 5 As an optional implementation, determining a multi-dimensional tag of a video ringback tone corresponding to a content entity specifically includes:

[0094] S1041, when the content entity is one of a browsing object entity, a ringback tone collection / ringback tone setting object entity, and a cancel collection / ringback tone deletion object entity, searching for video ringback tone data corresponding to the content entity in a ringback tone database, and obtaining a corresponding video ringback tone multi-dimensional tag of the video ringback tone data, the video ringback tone multi-dimensional tag including a video ringback tone theme tag, a video ringback tone attribution tag, a video ringback tone content tag, a video picture tone tag, and a music style tag;

[0095] S1042. When the content entity is a text / picture entity and a ringback tone template entity, search for text / picture data corresponding to the content entity in the user database, perform semantic analysis on the text / picture data, obtain the corresponding video ringback tone theme tag, video ringback tone content tag and video ringback tone attribution tag, search for the ringback tone template data corresponding to the ringback tone template entity in the ringback tone template library, and obtain the video picture tone tag and music style tag corresponding to the ringback tone template data, and then generate a video ringback tone multi-dimensional tag according to the video ringback tone theme tag, video ringback tone content tag, video ringback tone attribution tag, video picture tone tag and music style tag.

[0096] Specifically, video ringtones are declared independently by each content provider when they are entered into the database, and then go through the approval process in the operator's OA system. After approval, the copyright system's automatic tag extraction and AI big data tool analysis operations are triggered. After the offline analysis is completed, each video ringtone data is finally marked with the corresponding video ringtone theme label, video ringtone attribution label, video ringtone content label, video picture tone label and music style label.

[0097] When the extracted content entity is one of the browsing object entity, ringback tone collection / ringback tone setting object entity, and cancel collection / ringback tone deletion object entity, the corresponding video ringback tone data can be found in the ringback tone database, and the corresponding video ringback tone multi-dimensional label can also be obtained.

[0098] When the extracted content entity is a text / picture entity and a ringback tone template entity, it means that this part of the content is not the existing video ringback tone data, but the data used by the user in the process of making the ringback tone. At this time, a semantic analysis is performed on the text / picture data to obtain the corresponding video ringback tone theme tag, video ringback tone content tag and video ringback tone attribution tag. The ringback tone template data corresponding to the ringback tone template entity is searched in the ringback tone template library, and the video picture tone tag and music style tag corresponding to the ringback tone template data are obtained, so that the video ringback tone multi-dimensional tag of the content entity can be obtained.

[0099] like Figure 6 FIG. 1 is a flow chart of step S104 provided in an embodiment of the present invention, referring to FIG. Figure 6 As an optional implementation, the user tag of the target user is determined according to the multi-dimensional tag of the video ringback tone and the corresponding user behavior type, which specifically includes:

[0100] S1041, determining the preference weight factor corresponding to each user behavior type;

[0101] S1042: determining a first user preference score of each video ringback tone theme tag according to the preference weight factor, and selecting a target theme tag from the video ringback tone theme tags according to the first user preference score, and using the target theme tag as a user theme preference tag for the target user;

[0102] S1043, determining a second user preference score for each video ringback tone attribution tag according to the preference weight factor, selecting a target attribution tag from the video ringback tone attribution tags according to the second user preference score, and then determining a user social relationship tag of the target user according to the target attribution tag;

[0103] S1044, determining a third user preference score of each video ringback tone content tag according to the preference weight factor, and selecting a target content tag from the video ringback tone content tags according to the third user preference score, and using the target content tag as a user content preference tag for the target user;

[0104] S1045, determining a fourth user preference score for each video picture tone label according to the preference weight factor, selecting a target tone label from the video picture tone labels according to the fourth user preference score, determining a fifth user preference score for each music style label according to the preference weight factor, selecting a target style label from the music style labels according to the fifth user preference score, and then predicting a user personality / mood label of the target user according to the target tone label and the target style label;

[0105] S1046: Generate a multi-dimensional user tag based on the user topic preference tag, the user social relationship tag, the user content preference tag, and the user personality / mood tag.

[0106] Specifically, corresponding preference weight factors are set for each type of user behavior. For example, the preference weight factor for browsing behavior is set to 0.1, the preference weight factor for ringback tone collection / ringback tone setting behavior is set to 0.5, the preference weight factor for ringback tone production behavior is set to 1, and the preference weight factor for canceling collection / ringback tone deletion behavior is set to -0.5. After determining the preference weight factors of various types of user behavior, score each specific video ringback tone label in the video ringback tone multi-dimensional label according to the preference weight factors. For example, the video ringback tone theme label of a certain video ringback tone multi-dimensional label is "natural landscape", the video ringback tone content label is "Taishan scenery", the video ringback tone attribution label is "mountain and river scenery series", the video screen color tone label is "bright", and the music style label is "solemn and simple". The user behavior type corresponding to the video ringback tone multi-dimensional label is browsing behavior. Then, the score of the label "natural landscape" under the video ringback tone theme dimension can be increased by 0.5, the score of the label "Taishan scenery" under the video ringback tone content dimension can be increased by 0.5, the score of the label "mountain and river scenery series" under the video ringback tone attribution dimension can be increased by 0.5, the score of the label "bright" under the video screen color tone dimension can be increased by 0.5, and the score of the label "solemn and simple" under the music style dimension can be increased by 0.5.

[0107] After scoring the video ring back tone tags in all video ring back tone multi-dimensional tags, the first user preference score of each video ring back tone theme tag, the second user preference score of each video ring back tone attribution tag, the third user preference score of each video ring back tone content tag, the fourth user preference score of each video picture tone tag and the fifth user preference score of each music style tag can be obtained. Among them, according to the first user preference score, several target theme tags with high scores can be directly selected from the video ring back tone theme tags, and the target theme tags can be used as the user theme preference tags of the target users. According to the third user preference score, the score can be directly selected from the video ring back tone content tags. The top several target content tags are selected, and the target content tags are used as user content preference tags of the target users. According to the second user preference score, several target attribution tags with the top scores are selected from the video ringtone attribution tags, and then the corresponding IP and series are determined according to the target attribution tags, so as to determine the user social relationship tags of the target users. According to the fourth user preference score, several target tone tags with the top scores are selected from the video picture tone tags, and according to the fifth user preference score, several target style tags with the top scores are selected from the music style tags, and then the user personality / mood tags of the target users are predicted according to the target tone tags and the target style tags.

[0108] It should be noted that predicting the user personality / mood label of the target user according to the target tone label and the target style label can be achieved by pre-training a neural network model, which is not the focus of the embodiment of the present invention and will not be elaborated here.

[0109] like Figure 7 FIG. 1 is a flow chart of step S105 provided in an embodiment of the present invention, referring to FIG. Figure 7 As an optional implementation, a video ringback tone user portrait of a target user is generated according to the multi-dimensional user tag, which specifically includes:

[0110] S1051, obtaining basic user information of the target user according to the authentication login information of the target user;

[0111] S1052. Add basic user information and multi-dimensional user tags to a preset user portrait data warehouse;

[0112] S1053. Aggregate basic user information and multi-dimensional user tags through a preset big data model component to obtain a video ringback tone user portrait.

[0113] Specifically, when the user authenticates and logs in, after obtaining the user's consent, the user's mobile phone number and terminal information, including mobile phone brand, mobile phone model, CPU, memory, screen size and resolution, current network type and other data are collected and reported as basic user information. The basic user information and multi-dimensional user tags are added to the preset user portrait data warehouse, and the data is deeply mined through the big data framework presto SQL and hive, and the basic user information and multi-dimensional user tags are aggregated to draw user portraits and output user portrait analysis reports.

[0114] The above is a description of the method steps of the embodiment of the present invention. It can be recognized that the embodiment of the present invention obtains multi-dimensional user behavior data through video ringback tone embedding, thereby obtaining the content entity of the user behavior object and the corresponding user behavior type, and the multi-dimensional user tag can be obtained according to the multi-dimensional tag of the video ringback tone of the content entity and the corresponding user behavior type, thereby generating a video ringback tone user portrait according to the multi-dimensional user tag, thereby improving the accuracy and comprehensiveness of the video ringback tone user portrait.

[0115] like Figure 8 FIG. 1 is a schematic diagram of the structure of a device for generating a user portrait of a video ring back tone according to an embodiment of the present invention. Figure 8 The embodiment of the present invention provides a device for generating a video ring back tone user portrait, comprising:

[0116] A data acquisition module is used to acquire multi-dimensional user behavior data of target users through multiple preset video ringback tone embedding points;

[0117] A data processing module is used to extract entities and convert data from multi-dimensional user behavior data to obtain multiple content entities and corresponding user behavior types;

[0118] A color ring tone label determination module, used to determine a multi-dimensional label of a video color ring tone corresponding to a content entity;

[0119] A user tag determination module is used to determine the multi-dimensional user tag of the target user according to the multi-dimensional tag of the video ringback tone and the corresponding user behavior type;

[0120] The user portrait generation module is used to generate a video ringback tone user portrait of the target user based on multi-dimensional user tags.

[0121] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0122] The embodiment of the present invention also provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned video ring back tone user portrait generation method. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0123] like Fig. 9 FIG. 1 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Fig. 9 , an embodiment of the present invention provides an electronic device, including:

[0124] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention;

[0125] The memory 902 may be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 may store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the video ring back tone user portrait generation method of the embodiment of the present invention;

[0126] Input / output interface 903, used to implement information input and output;

[0127] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0128] A bus 905 that transmits information between the various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0129] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0130] like Fig.10FIG. 1 is a schematic diagram of the structure of a storage medium provided in an embodiment of the present invention, referring to FIG. Fig.10 The embodiment of the present invention also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs 1001, and the one or more programs 1001 can be executed by one or more processors to implement the above-mentioned video ringtone user portrait generation method.

[0131] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0132] The embodiment of the present invention also discloses a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 1 The method shown.

[0133] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0134] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified to the contrary, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0135] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0136] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0137] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the above-mentioned program is printed, since the above-mentioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in other suitable ways as necessary, and then stored in a computer memory.

[0138] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0139] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0140] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0141] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for generating a user portrait of a video ringback tone, characterized in that: The following steps are involved: Obtain multi-dimensional user behavior data of target users through multiple preset video ringback tone embedding points; Performing entity extraction and data conversion on the multi-dimensional user behavior data to obtain multiple content entities and corresponding user behavior types; Determine a multi-dimensional tag of a video ringback tone corresponding to the content entity; Determine the multidimensional user tag of the target user according to the multidimensional tag of the video ringback tone and the corresponding user behavior type; A video ringback tone user portrait of the target user is generated according to the multi-dimensional user tag.

2. The method for generating a video ringback tone user portrait according to claim 1, characterized in that: The video ringback tone embedding point includes at least one of a video ringback tone recommendation page embedding point, a video ringback tone details page embedding point, a video ringback tone production page embedding point and a user video ringback tone list embedding point, and the multi-dimensional user behavior data includes at least one of page browsing behavior data, ringback tone collection / ringback tone setting behavior data, ringback tone production behavior data and cancel collection / ringback tone deletion behavior data.

3. The method for generating a video ringback tone user portrait according to claim 2, characterized in that: The method of obtaining multi-dimensional user behavior data of the target user through a plurality of preset video ringback tone embedding points includes at least one of the following: Obtaining the target user's page dwell time / scrolling rate on the video ringback tone recommendation page through the video ringback tone recommendation page embedding point, and generating the page browsing behavior data according to the video ringback tone recommendation page and the corresponding page dwell time / page scrolling rate; Acquire the ringback tone collection / ringback tone setting operation of the target user on the video ringback tone details page through the video ringback tone details page embedding point, and generate the ringback tone collection / ringback tone setting behavior data according to the video ringback tone details page and the ringback tone collection / ringback tone setting operation; Acquire the text / picture input operation and ringtone template selection operation of the target user on the video ringtone production page through the video ringtone production page embedding point, and generate the ringtone production behavior data according to the text / picture input operation and the ringtone template selection operation and the corresponding operation object; The uncollection / deletion operation of the target user in the user video ringback tone list is obtained through the user video ringback tone list embedding point, and the uncollection / deletion behavior data is generated according to the uncollection / deletion operation and the corresponding operation object.

4. The method for generating a video ringback tone user portrait according to claim 2, characterized in that: The performing entity extraction and data conversion on the multi-dimensional user behavior data to obtain a plurality of content entities and corresponding user behavior types includes at least one of the following: Performing entity extraction and data conversion on the page browsing behavior data to obtain a browsing object entity, using the browsing object entity as the content entity, and determining the corresponding user behavior type as browsing behavior; Performing entity extraction and data conversion on the ringback tone collection / ringback tone setting behavior data to obtain a ringback tone collection / ringback tone setting object entity, using the ringback tone collection / ringback tone setting object entity as the content entity, and determining the corresponding user behavior type as the ringback tone collection / ringback tone setting behavior; Performing entity extraction and data conversion on the ringback tone production behavior data to obtain a text / picture entity and a ringback tone template entity, using the text / picture entity and the ringback tone template entity as the content entity, and determining that the corresponding user behavior type is a ringback tone production behavior; Entity extraction and data conversion are performed on the cancel favorite / color ringtone deletion behavior data to obtain a cancel favorite / color ringtone deletion object entity, the cancel favorite / color ringtone deletion object entity is used as the content entity, and the corresponding user behavior type is determined to be a cancel favorite / color ringtone deletion behavior.

5. A method for generating a video ringback tone user portrait according to claim 4, characterized in that: The step of determining the video ring back tone multi-dimensional tag corresponding to the content entity specifically includes: When the content entity is one of a browsing object entity, a ringback tone collection / ringback tone setting object entity, and a cancel collection / ringback tone deletion object entity, searching for video ringback tone data corresponding to the content entity in a ringback tone database, and obtaining the video ringback tone multi-dimensional tag corresponding to the video ringback tone data, wherein the video ringback tone multi-dimensional tag includes a video ringback tone theme tag, a video ringback tone attribution tag, a video ringback tone content tag, a video picture tone tag, and a music style tag; When the content entity is a text / picture entity and a ring back tone template entity, the text / picture data corresponding to the content entity is searched in the user database, and the text / picture data is semantically analyzed to obtain the corresponding video ring back tone theme tag, video ring back tone content tag and video ring back tone attribution tag, and the ring back tone template data corresponding to the ring back tone template entity is searched in the ring back tone template library, and the video picture tone tag and music style tag corresponding to the ring back tone template data are obtained, and then the video ring back tone multi-dimensional tag is generated according to the video ring back tone theme tag, the video ring back tone content tag, the video ring back tone attribution tag, the video picture tone tag and the music style tag.

6. A method for generating a video ringback tone user portrait according to claim 5, characterized in that: The step of determining the user tag of the target user according to the multi-dimensional tag of the video ringback tone and the corresponding user behavior type specifically includes: Determine a preference weight factor corresponding to each of the user behavior types; Determine a first user preference score for each of the video ringback tone theme tags according to the preference weight factor, select a target theme tag from the video ringback tone theme tags according to the first user preference score, and use the target theme tag as the user theme preference tag for the target user; Determine a second user preference score for each of the video ringback tone attribution tags according to the preference weight factor, select a target attribution tag from the video ringback tone attribution tags according to the second user preference score, and then determine a user social relationship tag for the target user according to the target attribution tag; Determine a third user preference score of each of the video ringback tone content tags according to the preference weight factor, select a target content tag from the video ringback tone content tags according to the third user preference score, and use the target content tag as the user content preference tag of the target user; Determine a fourth user preference score for each of the video picture tone labels according to the preference weight factor, select a target tone label from the video picture tone labels according to the fourth user preference score, determine a fifth user preference score for each of the music style labels according to the preference weight factor, select a target style label from the music style labels according to the fifth user preference score, and then predict the user personality / mood label of the target user according to the target tone label and the target style label; The multi-dimensional user tag is generated according to the user topic preference tag, the user social relationship tag, the user content preference tag, and the user personality / mood tag.

7. A method for generating a video ringback tone user portrait according to any one of claims 1 to 6, characterized in that: The step of generating a video ringback tone user portrait of the target user according to the multi-dimensional user tag specifically includes: Acquire basic user information of the target user according to the authentication login information of the target user; Adding the basic user information and the multi-dimensional user tags to a preset user portrait data warehouse; The basic user information and the multi-dimensional user tags are aggregated through a preset big data model component to obtain the video ringback tone user portrait.

8. A device for generating a user portrait of a video ring back tone, characterized in that: include: A data acquisition module is used to acquire multi-dimensional user behavior data of target users through multiple preset video ringback tone embedding points; A data processing module, used to perform entity extraction and data conversion on the multi-dimensional user behavior data to obtain multiple content entities and corresponding user behavior types; A color ring back tone label determination module, used to determine a multi-dimensional label of a video color ring back tone corresponding to the content entity; A user label determination module, used to determine the multi-dimensional user label of the target user according to the multi-dimensional label of the video ringback tone and the corresponding user behavior type; A user portrait generation module is used to generate a video ringback tone user portrait of the target user according to the multi-dimensional user tag.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the steps of the method for generating a video ringtone user portrait are realized as described in any one of claims 1 to 7.

10. A storage medium, the storage medium being a computer-readable storage medium, used for computer-readable storage, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the video ringback tone user portrait generation method as described in any one of claims 1 to 7.

Images