CN111105819A

CN111105819A - Clipping template recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN111105819A
Application number: CN201911280989.5A
Authority: CN
Inventors: 何代勇
Original assignee: Reach Best Technology Co Ltd
Current assignee: Reach Best Technology Co Ltd; Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2019-12-13
Filing date: 2019-12-13
Publication date: 2020-05-05
Anticipated expiration: 2039-12-13
Also published as: CN111105819B

Abstract

The present disclosure relates to a method of recommending a clipping template. The method comprises the following steps: responding to recommendation triggering operation of a target user account on a clipping template, and acquiring template use characteristics of the target user account; selecting a target clipping template which meets a preset recommendation condition from the candidate clipping template set according to the template use characteristics; and displaying the target clipping template on a clipping template recommendation interface. The recommendation method of the editing template can improve the efficiency of video editing.

Description

Clipping template recommendation method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer data processing technologies, and in particular, to a method and an apparatus for recommending a clipping template, an electronic device, and a storage medium.

Background

Videos taken by users often require video clips for better visual results. While video clips are difficult for the average user to grasp by generally involving more complicated operations.

At present, some video editing software provides customized editing templates, so that common users can directly call the customized editing templates to edit videos, the video editing operation of the users is simplified, and the editing efficiency of the users is improved.

Disclosure of Invention

The present disclosure provides a recommendation method and apparatus for a clipping template, an electronic device, and a storage medium, so as to at least solve the problem of low video clipping efficiency of a video clipping template in the related art. The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided a recommendation method for a clipping template, the clipping template being used for clipping a multimedia resource, the method including:

responding to recommendation triggering operation of a target user account on a clipping template, and acquiring template use characteristics of the target user account;

selecting a target clipping template which meets a preset recommendation condition from the candidate clipping template set according to the template use characteristics;

and displaying the target clipping template on a clipping template recommendation interface.

Optionally, the template usage feature comprises at least a user representation; the obtaining of the template usage characteristics of the target user account includes: acquiring user attribute information and historical behavior data of the target user account; wherein the user attribute information is used for describing user attributes of the target user account; the historical behavior data comprises data resulting from the target user account performing different operation type behaviors on a historical clip template during a historical statistics period; and determining the user portrait according to the user attribute information and the historical behavior data.

Optionally, the user representation includes at least one of user features and template preference features; determining the user representation according to the user attribute information and the historical behavior data includes: extracting the user features from the user attribute information; the user characteristics at least comprise one of age, gender and geographic position; performing aggregation processing on the historical behavior data to obtain the preference characteristics of the template; the template preference characteristics at least comprise one of a template preference type, a template preference style or a template preference theme.

Optionally, the operation type includes at least one of using, deriving, or sharing, the historical behavior data includes a frequency of performing different operation type behaviors on a historical clipping template by the target user account in the historical statistical period, and a template feature of the corresponding historical clipping template, where the template feature includes at least one of a template type, a template style, or a template theme; the clustering the historical behavior data to obtain the preference characteristics of the template comprises: acquiring the total use frequency of each historical clipping template according to the frequency of different operation type behaviors of the target user account on the historical clipping templates in the historical statistic period; using the template feature of the history clip template with the highest total frequency as the template preference feature.

Optionally, the operation type includes at least two of using, deriving, and sharing, and the obtaining the total frequency of use of each history clip template according to the frequency of performing different operation type behaviors on the history clip template in the history statistical period by the target user account includes: and according to the frequency of different operation type behaviors of each historical clipping template implemented by the target user account in the historical statistic time period, carrying out weighting processing through preset weights respectively corresponding to the different operation types, and summing to obtain the total use frequency of each historical clipping template.

Optionally, the user representation further comprises a user tag; determining the user representation according to the user attribute information and the historical behavior data includes: and determining the user classification of the target user account as the user label according to the user attribute information or the historical behavior data.

Optionally, the template usage characteristics at least include the material characteristics, and the obtaining the template usage characteristics of the target user account includes: and acquiring the material type and the material parameters of the material to be edited of the target user account, and determining the material characteristics.

Optionally, the preset recommendation condition includes that the recommendation index of the target clip module is greater than a preset threshold; according to the template use characteristics, selecting a target clip template meeting preset recommendation conditions from the candidate clip template set, wherein the target clip template meeting the preset recommendation conditions comprises the following steps: acquiring template features of each candidate clipping template in the candidate clipping template set; acquiring a recommendation index of each candidate clipping template according to the template use characteristics and the template characteristics of each candidate clipping template; and selecting the candidate clipping template with the recommendation index larger than a preset threshold value as a target clipping template.

Optionally, the obtaining the recommendation index of each candidate clipping template according to the template use characteristic and the template characteristic of each candidate clipping template includes: inputting the template use characteristics and the template characteristics of each candidate clipping template into a pre-acquired template recommendation model for processing to obtain a recommendation index of each candidate clipping template; the template recommendation model is obtained through training of a preset type of neural network according to a sample set constructed according to user behavior data and is used for outputting a corresponding template recommendation index according to input template use characteristics and template characteristics.

Optionally, the method further includes obtaining a set of candidate clip templates for the target user account, including: acquiring a related user account of the target user account; and acquiring a historical clip template used by the associated user account in a preset use period, and constructing the candidate clip template set.

Optionally, the method further includes obtaining a set of candidate clip templates for the target user account, including: selecting a similar user account from a user set according to the user representation of the target user account; and acquiring historical clip templates used by the similar user accounts in a preset use period, and constructing the candidate clip template set.

Optionally, the preset recommendation condition includes that the recommendation index of the target clip module is greater than a preset threshold; the displaying the target clipping template on the clipping template recommendation interface comprises: and displaying the target clip template on a clip template recommendation interface according to the recommendation index sorting order of the target clip template.

Optionally, the method further comprises: and sending a template recommendation request to a server, triggering the server to acquire the template use characteristics of the target user account, selecting a target clipping template meeting preset recommendation conditions from the candidate clipping template set according to the template use characteristics, and returning.

According to a second aspect of embodiments of the present disclosure, a recommendation method of a clipping template for clipping a multimedia asset, the method includes:

receiving a template recommendation request; the template recommendation request is generated by a client according to recommendation triggering operation of a target user account on the editing template;

responding to the template recommendation request, and acquiring the template use characteristics of the target user account;

and sending the target clipping template to the client so that the client displays the target clipping template on a clipping template recommendation interface.

Optionally, the method further includes obtaining a set of candidate clip templates for the target user account, including: acquiring a related user account of the target user account; obtaining the associated user account usage clipping template; and taking the used clipping template as a candidate clipping template of the target user account to obtain the candidate clipping template set.

According to a third aspect of the embodiments of the present disclosure, an apparatus for recommending a clipping template for clipping a multimedia asset, the apparatus comprising:

the template use characteristic acquisition module is used for responding to recommendation triggering operation of a target user account on a clipping template and acquiring the template use characteristic of the target user account;

the first target clip template selecting module is used for selecting a target clip template meeting a preset recommendation condition from the candidate clip template set according to the template use characteristics;

and the display module is used for displaying the target clipping template on a clipping template recommendation interface.

According to a fourth aspect of embodiments of the present disclosure, an apparatus for recommending a clipping template for clipping a multimedia asset, the apparatus comprising:

the request receiving module is used for receiving a template recommendation request; the template recommendation request is generated by a client according to recommendation triggering operation of a target user account on the editing template;

the request response module is used for responding to the template recommendation request and acquiring the template use characteristics of the target user account;

the second target clip template selecting module is used for selecting a target clip template meeting a preset recommendation condition from the candidate clip template set according to the template use characteristics;

and the sending module is used for sending the target clipping template to the client so that the client can display the target clipping template on a clipping template recommendation interface.

According to a fifth aspect of the embodiments of the present disclosure, there is provided a client, including a processor and a memory, where the memory stores a computer program, and the processor implements the following steps when executing the computer program:

According to a sixth aspect of the embodiments of the present disclosure, there is provided a server, including a processor and a memory, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

According to a seventh aspect of the embodiments of the present disclosure, there is provided a clip template recommendation system, including the client described above, and the server described above.

According to an eighth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:

According to a ninth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

according to the recommendation method and device for the clipping template, the electronic equipment and the storage medium, the target clipping template is recommended to the target user according to the template use characteristics of the target user account, the video clipping template which meets the habit of the user can be recommended according to the use styles of different users, the video clipping requirement of the user can be accurately identified, the personalized video clipping template recommendation can be carried out in a self-adaptive manner, the user is assisted to quickly obtain the video clipping template which meets the requirement, the user is prevented from consuming a large amount of time to select the clipping template, and the video clipping efficiency of the user is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

FIG. 1 is a diagram of an application environment of a recommendation method for a clipping template in one embodiment.

Fig. 2 is a flowchart illustrating a recommendation method of a clip template according to an exemplary embodiment.

FIG. 3 is a diagram of an incoming clip template selection interface in one embodiment.

FIG. 4 is a diagram of an incoming clip template selection interface in another embodiment.

FIG. 5 is a flowchart illustrating a step of selecting a target clip template that meets a preset recommendation condition according to an exemplary embodiment.

Fig. 6 is a flowchart illustrating a recommendation method of a clip template applied to a server according to an exemplary embodiment.

Fig. 7 is a flowchart illustrating a client-server interaction of a recommendation method of a clip template according to an exemplary embodiment.

Fig. 8 is a block diagram illustrating a recommendation apparatus for a clip template according to an exemplary embodiment.

Fig. 9 is a block diagram illustrating a recommendation apparatus of a clip template according to another exemplary embodiment.

FIG. 10 is a diagram of the internal structure of a client in one embodiment.

Fig. 11 is an internal configuration diagram of a server in one embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

The recommendation method of the clipping template provided by the application can be applied to the application environment shown in fig. 1. Wherein the client 102 communicates with the server 104 over a network. The client 102 responds to recommendation triggering operation of a target user account on a clipping template, and obtains template use characteristics of the target user account; selecting a target clipping template which meets a preset recommendation condition from the candidate clipping template set according to the template use characteristics; and displaying the target clipping template on a clipping template recommendation interface. The client 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster composed of a plurality of servers.

Fig. 2 is a flowchart illustrating a method for recommending a clipping template according to an exemplary embodiment, where the method for recommending a clipping template is applied to the client 102 in fig. 1, and the clipping template is used for clipping a multimedia resource, and includes the following steps.

In step S110, in response to a recommendation trigger operation of a target user account on a clip template, a template use characteristic of the target user account is acquired.

The target user account is a user account needing to use the clip template, and the recommendation triggering operation may be an operation of the target user entering the clip template selection interface from the clip video interface, including but not limited to clicking a selection of the selection template into the clip template selection interface (as shown in fig. 3), clicking a virtual button of the selection template into the clip template selection interface in fig. 3, or sliding upwards from the clip video interface to pull the clip template selection interface (as shown in fig. 4), where an arrow in fig. 4 indicates a direction of finger sliding; as shown in fig. 3 and 4, the clip template interface includes clip template 1, clip template 2, and clip template 3, and the clip template being buffered. Determining the using characteristics of the template according to the material characteristics or the user portrait of the material to be edited of the target user account; the template use characteristics are determined according to the environment of the target user account and the characteristics of the target user account, and parameters of the personalized clipping template which accords with the target user account are selected from the candidate clipping templates; the user representation includes but is not limited to information such as gender, age, place of birth, place of residence, occupation, marital status, etc.

In step S120, a target clip template meeting a preset recommendation condition is selected from the candidate clip template set according to the template use characteristics.

The candidate clipping template set may be all templates in the database, or may be a clipping template recently used by a user account concerned by the target user account, or may be a clipping template used by a user account in the same region, the same label, the same age, or the same occupation as the target user account, or may be a clipping template used by a user account having other similar characteristics.

The preset recommendation condition may be based on the characteristics of the target user and the preference of using the clip template, for example, the characteristics of the current user include sex, age, place of birth, place of residence, occupation, etc., and the preference of using the template includes a template biased to use the type of gourmet clip or a template that likes to use a fresh style.

In step S130, the target clip template is presented on a clip template recommendation interface.

The target clip template may be multiple, the target clip template may be displayed in the clip template recommendation interface according to a certain sequence, for example, according to the popularity value of the target clip template, or the target clip template may be displayed in the clip template recommendation interface according to the matching degree with the self-characteristics of the target user account or the preference of using the clip template.

According to the recommendation method of the clipping template, the target clipping template is recommended to the target user according to the template use characteristics of the target user account, the video clipping template which meets the habit of the user can be recommended according to the use styles of different users, the video clipping requirement of the user can be accurately identified, personalized video clipping template recommendation is carried out in a self-adaptive mode, the user is assisted to quickly obtain the video clipping template which meets the requirement, the user is prevented from consuming a large amount of time to select the clipping template, and the video clipping efficiency of the user is improved.

In one embodiment, the template usage characteristics include at least a user representation; the obtaining of the template usage characteristics of the target user account includes: acquiring user attribute information and historical behavior data of the target user account; wherein the user attribute information is used for describing user attributes of the target user account; the historical behavior data comprises data resulting from the target user account performing different operation type behaviors on a historical clip template during a historical statistics period; and determining the user portrait according to the user attribute information and the historical behavior data.

The user attribute information comprises one or more of user gender, user age, user geographical position and trigger time point. The historical statistics period may be the time the target user account started using the clip template to the current time, and the historical clip template may be the clip template used by the target user account. The operation type includes at least one of a use clipping template behavior, a share clipping template behavior, and an export clipping template behavior. A plurality of personalized feature data of the target user account can be determined through the user attribute information and the historical behavior data, a user portrait is determined through the plurality of personalized feature data, namely the user portrait is the plurality of personalized feature data of the target user account, and each personalized feature data can be matched with a corresponding clipping template.

For example, the gender of the user includes men and women, and the selection of the clipping template for men and women may be different, for example, men focuses more on the logic of the video clip, women focuses more on the aesthetic feeling of the video clip, and the clipping templates recommended to the target user according to different genders are different, where the user a is a woman, that is, one personalized feature data of the user a is a woman, and the clipping template emphasizing the aesthetic feeling of the video clip is matched for the user a according to the feature of the woman; the habits of users using the clipping template in different age groups are different; of course, the clipping templates that users in different geographic locations tend to use are also different; the trigger time points can be divided according to festivals, and specifically, a video clip template related to a certain festival material can be set, for example, if the trigger time points are mid-autumn festival, a clip template related to mid-autumn festival can be preferentially recommended. Specifically, a clipping template meeting the user requirements is preferentially recommended to the target user account by combining the portrait information of the target user account.

According to the user portrait determining method and device, the user portrait is determined through the user attribute information and the historical behavior data, so that the template use characteristics of the target user account are determined, the multi-aspect attributes of the target user account and the habits of the target user can be integrated, the user portrait can be constructed, the description of the template use characteristics on the target user use clipping template is more accurate, and the recommended clipping template meets the requirements of the target user better.

In one embodiment, the user representation includes at least one of a user characteristic and a template preference characteristic; determining the user representation according to the user attribute information and the historical behavior data includes: extracting the user features from the user attribute information; the user characteristics at least comprise one of age, gender and geographic position; performing aggregation processing on the historical behavior data to obtain the preference characteristics of the template; the template preference characteristics at least comprise one of a template preference type, a template preference style or a template preference theme. In the embodiment, the user characteristics are determined through one of age, gender and geographic position, and the clipping template recommendation can be performed on the target user from the aspects of region, age group or gender; according to the template recommendation method and device, the template preference characteristics are obtained by performing aggregation processing on the historical behavior data, and the template recommendation can be performed on the target user according to the use habits of the user.

In one embodiment, the operation type includes at least one of using, deriving, or sharing, the historical behavior data includes frequency of performing different operation type behaviors on a historical clip template by the target user account in the historical statistic period, and template features of the corresponding historical clip template, and the template features include at least one of a template type, a template style, or a template theme; the clustering the historical behavior data to obtain the preference characteristics of the template comprises: acquiring the total use frequency of each historical clipping template according to the frequency of different operation type behaviors of the target user account on the historical clipping templates in the historical statistic period; using the template feature of the history clip template with the highest total frequency as the template preference feature.

The target user account carries out different operation type behaviors on the history clipping template in the history statistical period, the number of times of using behaviors, the number of times of deriving behaviors and the number of times of sharing behaviors carried out on the history clipping template by the target user account are multiple, and the number of times of carrying out different operation type behaviors is calculated for each history clipping template; the template features may be one or more, the template features at least include one of a template type, a template style or a template theme, and of course, the template features may also be template content parameters; for example, the template types may be divided according to applicable scenes, such as a food clip, a video clip, and the like, the template theme may be a theme name, such as a birthday theme, a wedding theme, the template style may include freshness, nostalgia, europe, america, port, and the like, the template content parameters may include the number of supporting materials, the size of the materials, and the like, and the materials include pictures to be clipped, videos to be clipped, and the like.

In the embodiment, the total use frequency of each historical editing template is calculated by calculating the frequency of different operation types of behaviors of the target user account on the historical editing template, so that the template characteristic of the historical editing template with the highest total frequency is used as the preference characteristic of the template, and the preference characteristic of the user using the editing template can be effectively determined according to the operation behaviors of the user.

In one embodiment, the operation type includes at least two of using, deriving, and sharing, and the obtaining the total frequency of use of each history clip template according to the frequency of performing different operation type behaviors on the history clip template in the history statistic period by the target user account includes: and according to the frequency of different operation type behaviors of each historical clipping template implemented by the target user account in the historical statistic time period, carrying out weighting processing through preset weights respectively corresponding to the different operation types, and summing to obtain the total use frequency of each historical clipping template.

The preset weight may be set according to the emphasis point of a certain behavior of usage, derivation, or sharing, for example, the usage behavior, the derivation behavior, and the sharing behavior are set to different weights a1, a2, and a3(a1+ a2+ a3 is 1, a1> a2> a 3). For example, user a has uploaded three scene photos to make a video using a clipping template a, and uploaded a food video to make a video via a clipping template b, and there is no sharing behavior or derivation behavior, so that the total frequency of use Sa of the clipping template a is 1 a1+0 a2+0 a3, and the total frequency of use Sb of the clipping template a is 1 a1+0 a2+0 a 3.

According to the method and the device, the frequency of different operation type behaviors of each historical clipping template is weighted according to the preset weight, the total use frequency of each historical clipping template is obtained through summation, the total use frequency of each historical clipping template can be determined according to the importance degree of the operation type, and the clip template with important operation type is guaranteed to be preferentially recommended.

In one embodiment, the user representation further comprises a user tag; determining the user representation according to the user attribute information and the historical behavior data includes: and determining the user classification of the target user account as the user label according to the user attribute information or the historical behavior data.

The user tags include occupation tags and impression tags, for example, the occupation tags include young white-collar workers, industrial grandlaolas, senior junior farmers, and the impression tags include knowless persons, profound persons, smart persons, and the like, and may be divided according to specific application scenarios or requirements. The user characteristics are determined through the user classification (user label), and the clipping template recommendation can be performed on the target user according to the specific classification.

In one embodiment, the template usage characteristics at least include the material characteristics, and the obtaining the template usage characteristics of the target user account includes: and acquiring the material type and the material parameters of the material to be edited of the target user account, and determining the material characteristics.

The material characteristics include material types and material parameters, for example, the material types include gourmet, character, scene, film and television series, and the material parameters include material number and material size. The template using characteristics are determined according to the characteristics of the material to be edited, and therefore different types of materials to be edited can be guaranteed to be corresponding to the more matched editing template for editing.

In one embodiment, as shown in fig. 5, the preset recommendation condition includes that the recommendation index modulo the target clip is greater than a preset threshold; the step S120 includes: s121, acquiring template features of each candidate clipping template in the candidate clipping template set; s122, acquiring a recommendation index of each candidate clipping template according to the template use characteristics and the template characteristics of each candidate clipping template; and S123, selecting the candidate clipping template with the recommendation index larger than a preset threshold value as a target clipping template.

The template characteristics at least comprise one of template type, template style, template theme or template content parameters. The template features of each candidate clipping template may be obtained by classification parameters of the candidate clipping template itself, each clipping template having associated parameters about the template features in the clipping template database. The step S122 determines the recommendation index of each of the candidate clip templates by calculating a matching degree of the template-use feature with the template feature of each of the candidate clip templates, the recommendation index being higher as the matching degree is higher. The preset threshold value can be set according to needs, the higher the preset threshold value is, the fewer recommended target clipping templates are, and the preset threshold value can be set by weighing the target clipping templates.

According to the method and the device, the target clipping template is determined by calculating the recommendation index of each candidate clipping template and filtering out the candidate clipping template with the low recommendation index through the preset threshold, so that the number of the target clipping templates is ensured, the target user can select the target clipping template according to the target clipping template with the appropriate data, and the time for the target user to select the clipping template is saved.

In one embodiment, the obtaining the recommendation index of each candidate clipping template according to the template use characteristics and the template characteristics of each candidate clipping template includes: inputting the template use characteristics and the template characteristics of each candidate clipping template into a pre-acquired template recommendation model for processing to obtain a recommendation index of each candidate clipping template; the template recommendation model is obtained through training of a preset type of neural network according to a sample set constructed according to user behavior data and is used for outputting a corresponding template recommendation index according to input template use characteristics and template characteristics.

The preset type of neural network comprises neural networks such as LeNet-5, AlexNet, ZFNET, VGG-16, GoogLeNet, ResNet and the like, and of course, the preset type of neural network also comprises a logistic regression function; the historical behavior data comprises data generated by the target user account performing different operation types on the historical clip template in a historical statistic period, wherein the operation types at least comprise one of using, deriving or sharing. The sample set constructed by the user behavior data comprises at least one of a set of historical behavior data of a user group on the editing template, a set of historical behavior data of each classification of the user group classified according to the user attribute information, a set of historical behavior data of each classification of the user group classified according to the user label and a material feature set of edited materials of the user group. And constructing a characteristic vector according to the sample set constructed by the user behavior data, training a preset type of neural network to obtain a template recommendation model, and outputting the template recommendation model as a recommendation index of a cutting template. For example, the sample set includes: template preference characteristics, template characteristics, material characteristics, and corresponding result values, in a user group, user a uploaded three scenic photographs and made a video using template a, and used once without sharing and deriving behaviors, different weights a1, a2, a3 may be set for user a usage behavior, deriving behavior, and sharing behavior (a1+ a2+ a3 ═ 1, a1> a2> a3), in this sample, the result value Y ═ 1 × a1+0 × a2+0 × a3 ═ a1, assuming that user a's template preference is a gourmet clip, and the template preferences in the user group include gourmet clip, life clip, music clip, movie clip, user a's corresponding user a user template preference characteristic vector T1: [1, 0,0, 0], further, assuming that the template preference of the user A is a life clip, the template preference feature vector T1 of the user A includes: [0,1,0,0], corresponding feature vectors T2 and T3 can be similarly constructed about other template features and material features, and finally, a sample set [ T1, T2, T3, Y ] is constructed by the user template preference feature vector, the template feature vector, the material feature vector and the result value. And in the using process of the template recommendation model, inputting data of the template recommendation model, wherein the data are consistent with the sample data for constructing the template recommendation model.

According to the method and the device, the recommendation index of the clipping template is calculated through the pre-acquired template recommendation model, different template recommendation models can be constructed through sample sets constructed by various user behavior data, so that different recommendation index calculations can be realized in different demand occasions, and recommendation of the target clipping template in various demand occasions is guaranteed.

In one embodiment, the method for recommending the clipping template further includes obtaining a candidate clipping template set of a target user account, including: acquiring a related user account of the target user account; and acquiring a historical clip template used by the associated user account in a preset use period, and constructing the candidate clip template set. Wherein the associated user account of the target user account includes at least one of a user account focused by the target user, a user account approved by the target user account, and the preset usage period may be a period of time (e.g., a month or a year) closer to the current time. In the embodiment, the candidate clip template set is constructed by associating the user account, so that the candidate clip template set can be ensured to include the clip template which is interested by the user.

In one embodiment, the method for recommending the clipping template further includes obtaining a candidate clipping template set of a target user account, including: selecting a similar user account from a user set according to the user representation of the target user account; and acquiring historical clip templates used by the similar user accounts in a preset use period, and constructing the candidate clip template set. Wherein the user representation is determined from said user attribute information and said historical behaviour data, the user attribute information and the historical behaviour data referring to the definitions in the above embodiments. The similar user accounts are similar to the user representation of the target user account, e.g., the similar user accounts are in the same age group as the target user account, or the occupation of the similar user accounts are the same as the occupation of the target user account, or the marital status of the similar user accounts is the same as the marital status of the target user account. The preset usage period may be a period of time (e.g., last month, last year) that is closer to the current time. In the embodiment, the candidate clip template set is constructed through similar user accounts, so that the candidate clip template set can be ensured to comprise clip templates which are interested by the user.

In one embodiment, the preset recommendation condition includes that the recommendation index of the target clip module is greater than a preset threshold; the displaying the target clipping template on the clipping template recommendation interface comprises: and displaying the target clip template on a clip template recommendation interface according to the recommendation index sorting order of the target clip template. In the embodiment, the target editing templates are displayed according to the recommended index sorting order of the target editing templates, so that the target editing templates with high recommended indexes are preferentially displayed, a target user can more conveniently obtain the target editing templates to be used, and the time for selecting the editing templates is saved.

In one embodiment, the recommendation method for the clipping template further includes: and sending a template recommendation request to a server, triggering the server to acquire the template use characteristics of the target user account, selecting a target clipping template meeting preset recommendation conditions from the candidate clipping template set according to the template use characteristics, and returning. According to the method and the device, the target clip template is selected by the server, and the system performance requirement on data processing of the client is lowered.

Fig. 6 is a flowchart illustrating a method of recommending a clip template according to another exemplary embodiment, where the method of recommending a clip template, as illustrated in fig. 6, is applied to the server 104 of fig. 1, and the clip template is used for clipping a multimedia asset, and includes the following steps.

In step S210, a template recommendation request is received; the template recommendation request is generated by a client according to recommendation triggering operation of a target user account on the clipping template.

In step S220, in response to the template recommendation request, the template usage characteristics of the target user account are obtained.

In step S230, a target clip template meeting a preset recommendation condition is selected from the candidate clip template set according to the template use characteristics.

In step S240, the target clip template is sent to the client, so that the client displays the target clip template on a clip template recommendation interface.

In one embodiment, the user representation includes at least one of a user characteristic and a template preference characteristic; determining the user representation according to the user attribute information and the historical behavior data includes: extracting the user features from the user attribute information; the user characteristics at least comprise one of age, gender and geographic position; performing aggregation processing on the historical behavior data to obtain the preference characteristics of the template; the template preference characteristics at least comprise one of a template preference type, a template preference style or a template preference theme.

In one embodiment, the preset recommendation condition includes that the recommendation index of the target clip module is greater than a preset threshold; the step 230 includes: acquiring template features of each candidate clipping template in the candidate clipping template set; acquiring a recommendation index of each candidate clipping template according to the template use characteristics and the template characteristics of each candidate clipping template; and selecting the candidate clipping template with the recommendation index larger than a preset threshold value as a target clipping template.

In one embodiment, the method further comprises obtaining a set of candidate clip templates for the target user account, including: acquiring a related user account of the target user account; obtaining the associated user account usage clipping template; and taking the used clipping template as a candidate clipping template of the target user account to obtain the candidate clipping template set.

In one embodiment, the method further comprises obtaining a set of candidate clip templates for the target user account, including: selecting a similar user account from a user set according to the user representation of the target user account; and acquiring historical clip templates used by the similar user accounts in a preset use period, and constructing the candidate clip template set.

In a specific embodiment, as shown in fig. 7, the method for implementing recommendation of a clipping template of the present application through interaction between the client 102 and the server 104 includes: s7001, the client 102 sends a template recommendation request; s7002, responding to the template recommendation request, and acquiring the template use characteristics of the target user account by the server 104; s7003, the server 104 selects a target clipping template which meets the preset recommendation condition from the candidate clipping template set according to the template use characteristics; s7004, the server 104 sends the target clip template to the client 102; s7005, the client 102 displays the target clipping template on the clipping template recommendation interface.

The specific implementation method of the recommendation method for the clipping template applied to the server is the same as the specific implementation method of the recommendation method for the clipping template applied to the client, and is not described herein again.

It should be understood that although the various steps in the flowcharts of fig. 2, 5-7 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2, 5-7 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.

Fig. 8 is a block diagram illustrating a recommendation apparatus for a clip template according to an exemplary embodiment. Referring to fig. 8, the apparatus 300 includes a template-use characteristic acquiring module 310, a target clip template selecting module 320, and a presentation module 330.

The template use characteristic acquiring module 310 is configured to acquire a template use characteristic of a target user account in response to a recommendation triggering operation of the target user account on a clip template.

The first target clip template selecting module 320 is configured to select a target clip template meeting a preset recommendation condition from the candidate clip template set according to the template usage characteristics.

And the display module 330 is configured to display the target clip template on a clip template recommendation interface.

In one embodiment, the template usage characteristics include at least a user representation; the template usage characteristic acquiring module 310 includes: the target user account information acquisition submodule is used for acquiring user attribute information and historical behavior data of the target user account; wherein the user attribute information is used for describing user attributes of the target user account; the historical behavior data comprises data resulting from the target user account performing different operation type behaviors on a historical clip template during a historical statistics period; and the user portrait determining submodule is used for determining the user portrait according to the user attribute information and the historical behavior data.

In one embodiment, the user representation includes at least one of a user characteristic and a template preference characteristic; the user representation determination sub-module comprises: a user feature extraction unit, configured to extract the user feature from the user attribute information; the user characteristics at least comprise one of age, gender and geographic position; the template preference characteristic acquisition unit is used for carrying out aggregation processing on the historical behavior data to obtain the template preference characteristic; the template preference characteristics at least comprise one of a template preference type, a template preference style or a template preference theme.

In one embodiment, the operation type includes at least one of using, deriving, or sharing, the historical behavior data includes frequency of performing different operation type behaviors on a historical clip template by the target user account in the historical statistic period, and template features of the corresponding historical clip template, and the template features include at least one of a template type, a template style, or a template theme; the template preference feature obtaining unit includes: the total frequency obtaining subunit is configured to obtain the total frequency of use of each history clip template according to the frequency of different operation types of the target user account for implementing the history clip template in the history statistics period; a template preference feature determination subunit configured to use, as the template preference feature, the template feature of the history clip template with the highest total frequency.

In one embodiment, the operation type includes at least two of use, export, or share; the total frequency obtaining subunit is further configured to perform weighting processing on each history clip template through preset weights respectively corresponding to different operation types according to the frequency of different operation type behaviors performed on each history clip template by the target user account in the history statistics period, and sum to obtain the total frequency of use of each history clip template.

In one embodiment, the user representation further comprises a user tag; the user portrait determination submodule is further configured to determine a user classification of the target user account according to the user attribute information or the historical behavior data, and use the user classification as the user tag.

In one embodiment, the template usage characteristics include at least the material characteristics; the template usage characteristic obtaining module 310 is further configured to obtain a material type and a material parameter of a material to be edited of the target user account, and determine the material characteristic.

In one embodiment, the preset recommendation condition includes that the recommendation index of the target clip module is greater than a preset threshold; the first target clip template selection module 320 comprises: the template characteristic acquisition sub-module is used for acquiring the template characteristic of each candidate clipping template in the candidate clipping template set; the recommendation index obtaining sub-module is used for obtaining the recommendation index of each candidate clipping template according to the template use characteristics and the template characteristics of each candidate clipping template; and the target clipping template determining submodule is used for selecting the candidate clipping template with the recommendation index larger than the preset threshold value as the target clipping template.

In one embodiment, the recommendation index obtaining sub-module is further configured to input the template use characteristics and the template characteristics of each candidate clipping template into a pre-obtained template recommendation model for processing, so as to obtain a recommendation index of each candidate clipping template; the template recommendation model is obtained through training of a preset type of neural network according to a sample set constructed according to user behavior data and is used for outputting a corresponding template recommendation index according to input template use characteristics and template characteristics.

In one embodiment, the apparatus 300 for recommending clip templates further comprises: the first candidate clipping template set acquisition module is used for acquiring a candidate clipping template set of a target user account; the first candidate clip template set acquisition module includes: the associated user account acquisition sub-module is used for acquiring an associated user account of the target user account; and the candidate clip template set constructing submodule is used for acquiring the historical clip template used by the associated user account in a preset using period and constructing the candidate clip template set.

In one embodiment, the apparatus 300 for recommending clip templates further comprises: the first candidate clipping template set acquisition module is used for acquiring a candidate clipping template set of a target user account; the first candidate clip template set acquisition module includes: the similar user account selection submodule is used for selecting a similar user account from a user set according to the user representation of the target user account; and the candidate clip template set constructing submodule is used for acquiring the historical clip templates used by the similar user accounts in a preset using period and constructing the candidate clip template set.

In one embodiment, the preset recommendation condition includes that the recommendation index of the target clip module is greater than a preset threshold; the presentation module 330 is further configured to present the target clip template on a clip template recommendation interface according to the recommended index sorting order of the target clip template.

In one embodiment, the apparatus 300 for recommending clip templates further comprises: and the sending module is used for sending a template recommendation request to a server, triggering the server to obtain the template use characteristics of the target user account, selecting a target clipping template meeting the preset recommendation conditions from the candidate clipping template set according to the template use characteristics, and returning.

Fig. 9 is a block diagram illustrating a recommendation apparatus of a clip template according to another exemplary embodiment. Referring to fig. 9, the apparatus 400 includes a request receiving module 410, a request responding module 420, a second target clip template selecting module 430, and a transmitting module 440.

A request receiving module 410, configured to receive a template recommendation request; the template recommendation request is generated by a client according to recommendation triggering operation of a target user account on the clipping template.

A request response module 420, configured to, in response to the template recommendation request, obtain a template usage characteristic of the target user account.

And a second target clip template selecting module 430, configured to select a target clip template meeting a preset recommendation condition from the candidate clip template set according to the template usage characteristics.

The sending module 440 is configured to send the target clip template to the client, so that the client displays the target clip template on a clip template recommendation interface.

In one embodiment, the template usage characteristics include at least a user representation; the request response module 420 includes: the target user account information acquisition submodule is used for acquiring user attribute information and historical behavior data of the target user account; wherein the user attribute information is used for describing user attributes of the target user account; the historical behavior data comprises data resulting from the target user account performing different operation type behaviors on a historical clip template during a historical statistics period; and the user portrait determining submodule is used for determining the user portrait according to the user attribute information and the historical behavior data.

In one embodiment, the template usage characteristics include at least the material characteristics; the request response module 420 includes: and the system is also used for acquiring the material type and the material parameters of the material to be edited of the target user account and determining the material characteristics.

In one embodiment, the preset recommendation condition includes that the recommendation index of the target clip module is greater than a preset threshold; the second target clip template selection module 430 comprises: the template characteristic acquisition sub-module is used for acquiring the template characteristic of each candidate clipping template in the candidate clipping template set; the recommendation index obtaining sub-module is used for obtaining the recommendation index of each candidate clipping template according to the template use characteristics and the template characteristics of each candidate clipping template; and the target clipping template determining submodule is used for selecting the candidate clipping template with the recommendation index larger than the preset threshold value as the target clipping template.

In one embodiment, the apparatus 400 for recommending clip templates further comprises: the second candidate clipping template set acquisition module is used for acquiring a candidate clipping template set of the target user account; the second candidate clipping template set obtaining module includes: the associated user account acquisition sub-module is used for acquiring an associated user account of the target user account; and the candidate clip template set constructing submodule is used for acquiring the historical clip template used by the associated user account in a preset using period and constructing the candidate clip template set.

In one embodiment, the apparatus 400 for recommending clip templates further comprises: the second candidate clipping template set acquisition module is used for acquiring a candidate clipping template set of the target user account; the second candidate clipping template set obtaining module includes: the similar user account selection submodule is used for selecting a similar user account from a user set according to the user representation of the target user account; and the candidate clip template set constructing submodule is used for acquiring the historical clip templates used by the similar user accounts in a preset using period and constructing the candidate clip template set.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

In one embodiment, a clip template recommendation system is provided, which includes the client 102 as described in the above embodiments, and the server 104 as described in the above embodiments.

The client 102 and the server 104 are described below with reference to fig. 10 and 11.

As shown in fig. 10, fig. 10 is an internal structure diagram of a client including a processor, a memory, a network interface, a display screen, and an input device connected through a system bus in one embodiment. Wherein the processor of the client is configured to provide computing and control capabilities. The memory of the client comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the client is used for communicating with an external device through a network connection. The computer program is executed by a processor to implement a method of posting comment information. The display screen of the client can be a liquid crystal display screen or an electronic ink display screen, and the input device of the client can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a shell of the client, an external keyboard, a touch pad or a mouse and the like.

As shown in fig. 11, fig. 11 is an internal structure diagram of a server in one embodiment. The server may include a processor, memory, a network interface, and a database connected by a system bus. Wherein the processor of the server is configured to provide computing and control capabilities. The memory of the server comprises a nonvolatile storage medium and an internal memory. The nonvolatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the server is used for communicating with external devices through network connection. The computer program is executed by a processor to implement a method of posting comment information.

Those skilled in the art will appreciate that the configurations shown in fig. 10 and 11 are only block diagrams of partial configurations relevant to the present disclosure, and do not constitute a limitation on the clients and servers to which the present disclosure may be applied, and that a particular client and server may include more or less components than those shown, or combine certain components, or have a different arrangement of components.

In one embodiment, there is provided a client comprising a processor and a memory, the memory storing a computer program which when executed by the processor performs the steps of: responding to recommendation triggering operation of a target user account on a clipping template, and acquiring template use characteristics of the target user account; selecting a target clipping template which meets a preset recommendation condition from the candidate clipping template set according to the template use characteristics; and displaying the target clipping template on a clipping template recommendation interface.

In one embodiment, the preset recommendation condition includes that the recommendation index of the target clip module is greater than a preset threshold; according to the template use characteristics, selecting a target clip template meeting preset recommendation conditions from the candidate clip template set, wherein the target clip template meeting the preset recommendation conditions comprises the following steps: acquiring template features of each candidate clipping template in the candidate clipping template set; acquiring a recommendation index of each candidate clipping template according to the template use characteristics and the template characteristics of each candidate clipping template; and selecting the candidate clipping template with the recommendation index larger than a preset threshold value as a target clipping template.

In one embodiment, the processor, when executing the computer program, implements the steps of: obtaining a set of candidate clipping templates for a target user account, comprising: acquiring a related user account of the target user account; and acquiring a historical clip template used by the associated user account in a preset use period, and constructing the candidate clip template set.

In one embodiment, the processor, when executing the computer program, implements the steps of: obtaining a set of candidate clipping templates for a target user account, comprising: selecting a similar user account from a user set according to the user representation of the target user account; and acquiring historical clip templates used by the similar user accounts in a preset use period, and constructing the candidate clip template set.

In one embodiment, the preset recommendation condition includes that the recommendation index of the target clip module is greater than a preset threshold; the displaying the target clipping template on the clipping template recommendation interface comprises: and displaying the target clip template on a clip template recommendation interface according to the recommendation index sorting order of the target clip template.

In one embodiment, the processor, when executing the computer program, implements the steps of: and sending a template recommendation request to a server, triggering the server to acquire the template use characteristics of the target user account, selecting a target clipping template meeting preset recommendation conditions from the candidate clipping template set according to the template use characteristics, and returning.

In one embodiment, there is provided a server comprising a processor and a memory, the memory storing a computer program which when executed by the processor performs the steps of: receiving a template recommendation request; the template recommendation request is generated by a client according to recommendation triggering operation of a target user account on the editing template; responding to the template recommendation request, and acquiring the template use characteristics of the target user account; selecting a target clipping template which meets a preset recommendation condition from the candidate clipping template set according to the template use characteristics; and sending the target clipping template to the client so that the client displays the target clipping template on a clipping template recommendation interface.

In one embodiment, the processor, when executing the computer program, implements the steps of: obtaining a set of candidate clipping templates for a target user account, comprising: acquiring a related user account of the target user account; obtaining the associated user account usage clipping template; and taking the used clipping template as a candidate clipping template of the target user account to obtain the candidate clipping template set.

It will be understood by those skilled in the art that all or part of the processes in the method for publishing comment information described in any of the above embodiments may be implemented by a computer program, which may be stored in a non-volatile computer-readable storage medium, to instruct related hardware, and when executed, the computer program may include the processes of the above embodiments of the methods. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, wherein the program when executed by a processor implements the steps of: responding to recommendation triggering operation of a target user account on a clipping template, and acquiring template use characteristics of the target user account; selecting a target clipping template which meets a preset recommendation condition from the candidate clipping template set according to the template use characteristics; and displaying the target clipping template on a clipping template recommendation interface.

In one embodiment, the program when executed by a processor implements the steps of: obtaining a set of candidate clipping templates for a target user account, comprising: acquiring a related user account of the target user account; and acquiring a historical clip template used by the associated user account in a preset use period, and constructing the candidate clip template set.

In one embodiment, the program when executed by a processor implements the steps of: obtaining a set of candidate clipping templates for a target user account, comprising: selecting a similar user account from a user set according to the user representation of the target user account; and acquiring historical clip templates used by the similar user accounts in a preset use period, and constructing the candidate clip template set.

In one embodiment, the program when executed by a processor implements the steps of: and sending a template recommendation request to a server, triggering the server to acquire the template use characteristics of the target user account, selecting a target clipping template meeting preset recommendation conditions from the candidate clipping template set according to the template use characteristics, and returning.

In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, wherein the program when executed by a processor implements the steps of: receiving a template recommendation request; the template recommendation request is generated by a client according to recommendation triggering operation of a target user account on the editing template; responding to the template recommendation request, and acquiring the template use characteristics of the target user account; selecting a target clipping template which meets a preset recommendation condition from the candidate clipping template set according to the template use characteristics; and sending the target clipping template to the client so that the client displays the target clipping template on a clipping template recommendation interface.

In one embodiment, the program when executed by a processor implements the steps of: obtaining a set of candidate clipping templates for a target user account, comprising: acquiring a related user account of the target user account; obtaining the associated user account usage clipping template; and taking the used clipping template as a candidate clipping template of the target user account to obtain the candidate clipping template set.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method of recommending a clipping template, wherein said clipping template is used for clipping a multimedia asset, said method comprising:

2. The method of claim 1, wherein the template usage characteristics include at least a user representation; the obtaining of the template usage characteristics of the target user account includes:

acquiring user attribute information and historical behavior data of the target user account; wherein the user attribute information is used for describing user attributes of the target user account; the historical behavior data comprises data resulting from the target user account performing different operation type behaviors on a historical clip template during a historical statistics period;

and determining the user portrait according to the user attribute information and the historical behavior data.

3. The method of claim 1, wherein the template usage characteristics include at least the material characteristics, and wherein obtaining the template usage characteristics of the target user account comprises:

and acquiring the material type and the material parameters of the material to be edited of the target user account, and determining the material characteristics.

4. The method of claim 1, wherein the preset recommendation condition comprises a recommendation index modulo the target clip being greater than a preset threshold;

according to the template use characteristics, selecting a target clip template meeting preset recommendation conditions from the candidate clip template set, wherein the target clip template meeting the preset recommendation conditions comprises the following steps:

acquiring template features of each candidate clipping template in the candidate clipping template set;

acquiring a recommendation index of each candidate clipping template according to the template use characteristics and the template characteristics of each candidate clipping template;

and selecting the candidate clipping template with the recommendation index larger than a preset threshold value as a target clipping template.

5. A method of recommending a clipping template, wherein said clipping template is used for clipping a multimedia asset, said method comprising:

6. An apparatus for recommending a clipping template, wherein said clipping template is used for clipping a multimedia asset, said apparatus comprising:

7. An apparatus for recommending a clipping template, wherein said clipping template is used for clipping a multimedia asset, said apparatus comprising:

8. A client comprising a processor and a memory, the memory storing a computer program, wherein the processor, when executing the computer program, performs the steps of the method of any of claims 1 to 4.

9. A server comprising a processor and a memory, said memory storing a computer program, wherein said processor, when executing said computer program, performs the steps of the method of claim 5.

10. A recommendation system for a clip template, comprising a client as claimed in claim 8, and a server as claimed in claim 9.