CN112347276A - Information prompting method, device and system, client, server and storage medium - Google Patents

Abstract

The present disclosure relates to an information prompting method, device and system, a client, a server and a storage medium, wherein the method comprises the following steps: displaying the target multimedia resource to a target user account; aiming at a target user account, determining that a target multimedia resource meets a marking prompt condition, and generating corresponding marking prompt information, wherein the marking prompt information is used for prompting the target user account to mark the target multimedia resource; the display state of the target multimedia resource is determined to be in accordance with the mark prompt state, and the mark prompt information is displayed to the account of the target user, so that the problem that the normal watching of the user on the multimedia resource is easily interfered and the watching experience of the user is influenced by the mode of popping up the mark prompt information for each multimedia resource in the related technology is solved.

Description

Information prompting method, device and system, client, server and storage medium

Technical Field

The present disclosure relates to the field of information prompting application technologies, and in particular, to an information prompting method, an information prompting device, an information prompting system, a client, a server, and a storage medium.

Background

With the popularization of mobile terminals and the increasing speed of networks, the short and fast large-flow multimedia resource spreading is gradually favored by people, especially short videos. The videos played on the new media platforms comprise a plurality of theme contents, so that much joy is brought to users. After the user finishes watching the video, the user is usually prompted to collect the video through pop-up information, so that the user can quickly locate the video to review through collecting the video, and the video watching efficiency of the user is improved.

However, in the actual application process, the information for prompting the collected video is popped up after each video is played, which may interfere with the normal video watching process of the user and affect the video watching experience of the user.

Disclosure of Invention

The disclosure provides an information prompting method, an information prompting device, an information prompting system, a client, a server and a storage medium. The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided an information prompting method, including: displaying the target multimedia resource to a target user account; aiming at the target user account, determining that the target multimedia resource meets a marking prompt condition, and generating corresponding marking prompt information, wherein the marking prompt information is used for prompting the target user account to mark the target multimedia resource; and determining that the display state of the target multimedia resource accords with a mark prompt state, and displaying the mark prompt information to the target user account.

Further, the step of determining, for the target user account, that the target multimedia resource meets a markup prompt condition includes: acquiring user characteristics of the target user account and resource characteristics of the target multimedia resource; and determining that the target multimedia resource meets a marking prompt condition according to the user characteristics and the resource characteristics, wherein the marking prompt condition is a condition for determining that the target user account needs to be marked and prompted on the target multimedia resource according to the data acquired by the user characteristics and the resource characteristics.

Further, the step of determining that the target multimedia resource meets the mark prompting condition according to the user characteristic and the resource characteristic comprises: obtaining a user feature vector according to the target user account and the user features; obtaining an interactive feature vector according to the user feature and the resource feature of the target multimedia resource; obtaining target data according to the user feature vector and the interaction feature vector, wherein the target data comprises: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource and the probability of rebroadcasting the target multimedia resource; and determining that the target multimedia resource meets the marking prompt condition according to the target data.

Further, the step of determining that the target multimedia resource meets the mark prompting condition according to the target data comprises: and if the probability of marking the target multimedia resource is greater than a first preset threshold value, the probability of reviewing the target multimedia resource is greater than a second preset threshold value, and the probability of repeatedly broadcasting the target multimedia resource is greater than a third preset threshold value, determining that the target multimedia resource meets a marking prompt condition.

Further, the step of obtaining a user feature vector according to the target user account and the user feature includes: determining a list of historical multimedia resources, wherein the list of historical multimedia resources is a list of multimedia resources displayed on the target user account according to the display time sequence; determining an identifier of each multimedia resource in the list of multimedia resources; determining a weight value corresponding to each multimedia resource according to the identifier of each multimedia resource; obtaining the behavior sequence characteristics of the target user account according to the characteristic vector of each multimedia resource and the weight value corresponding to each multimedia resource; obtaining a user feature vector according to the behavior sequence feature of the target user account and the user feature, wherein the user feature comprises one of the following: user portrait information, user consumption statistics, and user behavior sequence features.

Further, the step of obtaining the interactive feature vector by the user feature and the resource feature of the target multimedia resource includes: obtaining a weight value between the target multimedia resource and each multimedia resource according to the resource feature vector of the target multimedia resource and the feature vector of each multimedia resource in the list of multimedia resources; and obtaining the interaction feature vector according to the resource feature vector of the target multimedia resource and each weight value.

Further, the step of obtaining target data according to the user feature vector and the interaction feature vector includes: inputting the user feature vector and the interaction feature vector from an attention model; receiving the output from the attention model: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource, and the probability of rebroadcasting the target multimedia resource.

Further, the step of determining that the presentation status of the target multimedia resource meets the markup prompt status comprises: when the target multimedia resource is displayed for a preset time or when the target multimedia resource is displayed for a preset proportion time, determining that the display state of the target multimedia resource meets a mark prompt state; or determining a target time period based on the target user account, and determining that the display state of the target multimedia resource meets a mark prompt state when the target multimedia resource is displayed in the target time period.

Further, the step of presenting the branding hints information to the target user account comprises: controlling the mark prompt information according to a preset moving direction, and performing moving display on the target user account in a preset icon style; or controlling the marking prompt information according to a preset time interval, and displaying on the target user account in a preset icon style; or controlling the marking prompt information according to a preset time interval and a preset moving direction, and displaying on the target user account in a preset icon style.

Further, the step of determining, for the target user account, that the target multimedia resource meets a markup prompt condition includes: triggering a target request to a server, wherein the target request carries information of the target user account; receiving target information returned by the server in response to the target request; and determining that the target multimedia resource meets the marking prompt condition based on the target information.

Further, the step of determining that the target multimedia resource meets a mark prompting condition based on the target information comprises: and if the target field in the target information is marked as the target value, determining that the target multimedia resource meets the marking prompt condition.

According to a second aspect of the embodiments of the present disclosure, there is provided an information prompting method, including: receiving a target request triggered by a client, wherein the target request carries information of a target user account; sending the information of the target user account and the resource characteristics of the target multimedia resources to a self-attention model, and receiving data information output by the self-attention model; and determining target information based on the data information, and sending the target information to a client, wherein the target information is used for determining whether the target multimedia resource meets a marking prompt condition.

Further, the data information includes: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource, and the probability of rebroadcasting the target multimedia resource, and determining target information based on the data information includes: if the probability of marking the target multimedia resource is greater than a first preset threshold, the probability of reviewing the target multimedia resource is greater than a second preset threshold, and the probability of repeatedly playing the target multimedia resource is greater than a third preset threshold, marking a target field as a target value to determine the target information, wherein the target value is used for identifying that the target multimedia resource meets a marking prompt condition.

According to a third aspect of the embodiments of the present disclosure, there is provided an information presentation apparatus including: the first presentation unit is configured to perform presentation of the target multimedia resource to the target user account; the first generating unit is configured to execute, aiming at the target user account, determining that the target multimedia resource meets a marking prompt condition, and generating corresponding marking prompt information, wherein the marking prompt information is used for prompting the target user account to perform a marking operation on the target multimedia resource; and the second display unit is configured to execute the steps of determining that the display state of the target multimedia resource meets a mark prompt state and displaying the mark prompt information to the target user account.

Further, the first generation unit includes: a first obtaining subunit configured to perform obtaining a user characteristic of the target user account and a resource characteristic of the target multimedia resource; the first determining subunit is configured to perform, according to the user characteristics and the resource characteristics, determining that the target multimedia resource meets a marking prompt condition, where the marking prompt condition is a condition for determining that the target multimedia resource needs to be marked and prompted by the target user account according to data obtained by the user characteristics and the resource characteristics.

Further, the first determining subunit includes: the first acquisition module is configured to execute the user feature vector according to the target user account and the user features; the second acquisition module is configured to execute the processing according to the user characteristics and the resource characteristics of the target multimedia resources to obtain an interactive characteristic vector; a third obtaining module, configured to execute obtaining target data according to the user feature vector and the interaction feature vector, where the target data includes: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource and the probability of rebroadcasting the target multimedia resource; a first determining module configured to perform determining that the target multimedia resource meets a marking prompt condition according to the target data.

Further, the first determining module comprises: the first determining submodule is configured to execute that if the probability of marking the target multimedia resource is greater than a first preset threshold, the probability of reviewing the target multimedia resource is greater than a second preset threshold, and the probability of replaying the target multimedia resource is greater than a third preset threshold, it is determined that the target multimedia resource meets a marking prompt condition.

Further, the first obtaining module comprises: a second determining sub-module configured to perform determining a list of historical multimedia assets, wherein the list of historical multimedia assets is a list of multimedia assets that have been presented on the target user account in chronological order of presentation; a third determining sub-module configured to perform determining an identity of each multimedia asset in the list of multimedia assets; the fourth determining submodule is configured to determine a weight value corresponding to each multimedia resource according to the identifier of each multimedia resource; the second obtaining submodule is configured to execute the action sequence characteristics according to the feature vector of each multimedia resource and the weight value corresponding to each multimedia resource to obtain the action sequence characteristics of the target user account; a third obtaining sub-module, configured to perform, according to the behavior sequence feature of the target user account and the user feature, obtaining a user feature vector, where the user feature includes one of: user portrait information, user consumption statistics, and user behavior sequence features.

Further, the second obtaining module includes: the second obtaining subunit is configured to execute obtaining a weight value between the target multimedia resource and each multimedia resource according to the resource feature vector of the target multimedia resource and the feature vector of each multimedia resource in the list of multimedia resources; and the third obtaining subunit is configured to execute the obtaining of the interaction feature vector according to the resource feature vector and each weight value of the target multimedia resource.

Further, the third obtaining module includes: a first input submodule configured to perform input of the user feature vector and the interaction feature vector from an attention model; a first receiving submodule configured to perform receiving the output from the attention model: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource, and the probability of rebroadcasting the target multimedia resource.

Further, the second display unit includes: the second determining subunit is configured to determine that the display state of the target multimedia resource meets a mark prompting state when the target multimedia resource is displayed for a preset time or when the target multimedia resource is displayed for a preset proportion time; or, the third determining subunit is configured to perform determining a target time period based on the target user account, and determine that the presentation state of the target multimedia resource meets a mark prompting state when the target multimedia resource is presented within the target time period.

Further, the second display unit comprises a first display subunit configured to perform control of the marking prompt message according to a preset moving direction, and perform moving display on the target user account in a preset icon style; or, the second display subunit is configured to perform control of the marking prompt information according to a preset time interval, and display the marking prompt information on the target user account in a preset icon style; or, the third display subunit is configured to perform control on the marking prompt information according to a preset time interval and a preset moving direction, and display the marking prompt information on the target user account in a preset icon style.

Further, the first generation unit includes: the triggering subunit is configured to execute a triggering target request to a server, wherein the target request carries information of the target user account; a receiving subunit, configured to perform receiving target information returned by the server in response to the target request; a fourth determining subunit configured to perform determining that the target multimedia resource meets a markup prompting condition based on the target information.

Further, the fourth determining subunit includes: and the second determination module is configured to determine that the target multimedia resource meets the marking prompt condition if the target field in the target information is marked as the target value.

According to a fourth aspect of the embodiments of the present disclosure, there is provided an information presentation apparatus including: the system comprises a first receiving unit, a second receiving unit and a third receiving unit, wherein the first receiving unit is configured to receive a target request triggered by a client, and the target request carries information of a target user account; a second receiving unit, configured to send the information of the target user account and the resource characteristics of the target multimedia resource to a self-attention model, and receive data information output by the self-attention model; and the sending unit is configured to determine target information based on the data information and send the target information to a client, wherein the target information is used for determining whether the target multimedia resource meets a marking prompt condition.

Further, the data information includes: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource, and the probability of rebroadcasting the target multimedia resource, the transmitting unit further includes: a fifth determining subunit, configured to mark a target field as a target value to determine the target information if the probability of marking the target multimedia resource is greater than a first preset threshold, the probability of reviewing the target multimedia resource is greater than a second preset threshold, and the probability of replaying the target multimedia resource is greater than a third preset threshold, where the target value is used to identify that the target multimedia resource meets a marking prompt condition.

According to a fifth aspect of embodiments of the present disclosure, there is provided a client, comprising a memory and a processor; the memory is to store executable instructions; the processor is configured to execute any one of the above information prompting methods according to the executable instructions.

According to a sixth aspect of the embodiments of the present disclosure, there is provided a server, comprising a storage unit and a processing component; the storage unit is used for storing executable instructions; the processing component is configured to execute any one of the information prompting methods according to the executable instructions.

According to a seventh aspect of the embodiments of the present disclosure, there is provided an information presentation system, including the above-described client and the above-described server.

According to an eighth aspect of embodiments of the present disclosure, there is provided a storage medium, wherein instructions that, when executed by a processor of an electronic device, enable the electronic device to perform the information prompting method according to any one of the above.

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

in the embodiment of the application, in the process of displaying the target multimedia resource to the target user account, it is determined that the target multimedia resource meets the mark prompting condition for the target user account, corresponding mark prompting information is generated, and when the display state of the target multimedia resource meets the mark prompting state, the mark prompting information is displayed to the target user account, so that the mark prompting of the user account to the multimedia resource is guided when the mark requirement of the user account is identified in the process of displaying the multimedia resource to different user accounts, the display effect is prevented from being influenced by frequent mark prompting information in the multimedia resource displaying process, and meanwhile, the mark requirements of different users to the multimedia resource can be effectively met.

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 flow chart illustrating a method of prompting for information, according to an example embodiment.

FIG. 2 is a flowchart one illustrating an alternative information prompting method according to an example embodiment.

FIG. 3 is a flow chart diagram two illustrating an alternative information prompting method according to an example embodiment.

Fig. 4 is a flowchart illustrating an information prompting method according to an example embodiment.

Fig. 5 is a block diagram illustrating a structure of a client according to an exemplary embodiment.

Fig. 6 is a block diagram illustrating a configuration of a server according to an exemplary embodiment.

FIG. 7 is a schematic diagram of an information prompting system according to an exemplary embodiment.

Fig. 8 is a block diagram of an information presentation device according to a sixth illustrative embodiment.

Fig. 9 is a block diagram of an information presentation device according to a seventh illustrative 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.

For convenience of description, some terms or expressions referred to in the embodiments of the present application are explained below:

OCR, Optical Character Recognition, OCR for short, and a technology for recognizing characters by an Optical technology.

Fig. 1 is a flowchart illustrating an information prompting method according to an exemplary embodiment, where, as shown in fig. 1, the information prompting method is used in a client, and includes the following steps:

in step S101, the target multimedia resource is presented to the target user account.

The target user account is a user account used by a target user to view multimedia resources on a client, for example, a user a logs in an account of the user a in an application program of a mobile phone, and then browses and views multimedia resources pushed by the application program for the account of the user a, that is, for the client, the target multimedia resources are displayed to an account of the target user. The target multimedia asset may be real-time video (e.g., live), non-real-time video, audio, teletext content, or other media asset.

In step S102, it is determined that the target multimedia resource meets the tagging prompting condition for the target user account, and corresponding tagging prompting information is generated, where the tagging prompting information is used for prompting the target user account to perform a tagging operation on the target multimedia resource.

The information carried by the target user account can reflect the preference of the user, so that whether the target multimedia resource meets the marking prompting condition can be determined based on the preference of the user, wherein the marking prompting condition is used for determining that the target user account needs to be marked and prompted on the target multimedia resource. For example, if the target multimedia resource is a media resource preferred by the user, the target multimedia resource is determined to meet the marking prompt condition. And if the target multimedia resource meets the marking prompt condition, generating corresponding marking prompt information. The marking prompt information is used for prompting the target user account to perform marking operation on the target multimedia resource, the marking operation can be collection operation, that is, the marking prompt information can be used for prompting the target user account to perform collection operation on the target multimedia resource.

In step S103, it is determined that the display status of the target multimedia resource meets the tag prompt status, and tag prompt information is displayed to the target user account.

The above-mentioned mark prompting state may be understood as a timing when the currently displayed target multimedia resource can be subjected to mark prompting, for example, when the target multimedia resource is displayed for 10s, the display state of the target multimedia resource is considered to be in accordance with the mark prompting state. Under the condition that the display state of the target multimedia resource accords with the mark prompt state, the mark prompt information is displayed to the target user account, so that the mark prompt information can be displayed to the user account to guide the user account to mark and prompt the multimedia resource when the mark requirement of the user account is identified in the process of displaying the multimedia resource aiming at different user accounts, the display effect is prevented from being influenced by frequent mark prompt information in the multimedia resource display process, and meanwhile, the mark requirements of different users on the multimedia resource can be effectively met.

Optionally, as shown in fig. 2, step S102 may further include the following:

step S1021, the user characteristics of the target user account and the resource characteristics of the target multimedia resources are obtained.

The user characteristics of the target user account may include: user base representation, user consumption statistical features, user sequence features, and the like. Wherein, user base portrait can include age, gender, region etc. and user consumption statistical characteristics can include: registration time, application program active days, average session control time, watching times, collecting times, comment times and the like; the user sequence features may include: history collection, clicks, praise, forward, focus, etc.

The resource characteristics of the target multimedia resource may include: the basic characteristics of the target multimedia resource and the statistical characteristics of the target multimedia resource, wherein the basic characteristics of the target multimedia resource may include: the ID of the target multimedia resource, the ID of the target multimedia resource publisher, the uploading time of the target multimedia resource, the classification of the target multimedia resource, the label of the target multimedia resource, the title, the OCR word segmentation, the voice recognition word segmentation and the like. The statistical characteristics of the target multimedia asset may include: viewing times, collection times, praise times, forwarding times, and the like.

Step S1022, determining that the target multimedia resource meets the mark prompting condition according to the user characteristic and the resource characteristic, where the mark prompting condition is a condition for determining that the target user account needs to perform mark prompting on the target multimedia resource according to the data acquired by the user characteristic and the resource characteristic.

Because the user characteristics can reflect the preference of the user, and the matching degree with the preference of the user can be analyzed through the resource characteristics of the target multimedia resources, whether the target multimedia resources meet the marking prompt conditions or not can be accurately determined based on the user characteristics and the resource characteristics.

Optionally, as shown in fig. 3, step S1022 may further include the following:

step S10221, a user feature vector is obtained according to the target user account and the user feature.

Step S10222, obtaining an interactive feature vector according to the user feature and the resource feature of the target multimedia resource.

For example, the interaction feature vector can be obtained according to user portrait information, user consumption statistical features, user behavior sequence features and resource features of the target multimedia resource included in the user features.

Step S10223, obtaining target data according to the user feature vector and the interaction feature vector, wherein the target data comprises: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource, and the probability of rebroadcasting the target multimedia resource.

Step S10224, according to the target data, determining that the target multimedia resource meets the mark prompt condition.

Through the steps S10221 to S10224, whether the target multimedia resource meets the mark prompting condition can be accurately determined based on the digitalized target data.

Optionally, step S10224 may further include the following: and if the probability of marking the target multimedia resource is greater than the first preset threshold, the probability of reviewing the target multimedia resource is greater than the second preset threshold, and the probability of repeatedly broadcasting the target multimedia resource is greater than the third preset threshold, determining that the target multimedia resource meets the marking prompt condition.

For example, the first preset threshold is 0.1, the second preset threshold is 0.05, and the third preset threshold is 0.02. If the probability of marking the target multimedia resource is greater than 0.1, the probability of reviewing the target multimedia resource is greater than 0.05, and the probability of rebroadcasting the target multimedia resource is greater than 0.02, it can be determined that the target multimedia resource meets the marking prompt condition. That is, whether the target multimedia resource meets the mark prompting condition or not can be quickly determined by comparing the index in the target data with the preset threshold value.

Optionally, step S10221 may further include the following: determining a list of historical multimedia resources, wherein the list of historical multimedia resources is a list of multimedia resources displayed on a target user account according to the display time sequence; determining the identification of each multimedia resource in the list of multimedia resources; determining a weight value corresponding to each multimedia resource according to the identifier of each multimedia resource; acquiring behavior sequence characteristics of a target user account according to the characteristic vector of each multimedia resource and the weight value corresponding to each multimedia resource; obtaining a user feature vector according to the behavior sequence feature and the user feature of the target user account, wherein the user feature comprises one of the following: user portrait information, user consumption statistics, and user behavior sequence features.

In the above solution, the list of the historical multimedia resources may be determined according to the target user account, for example, the multimedia resources that have been shown on the target user account in the order of the showing time within the previous 30 days are recorded in the list of the historical multimedia resources. The identifiers of the multimedia resources recorded in the list of the historical multimedia resources can be determined according to the user characteristics, for example, the identifier of the multimedia resource which is interested by the user is determined as a first identifier, and the identifier of the multimedia resource which is not interested by the user is determined as a second identifier. The multimedia asset identified as the first identity is weighted to 0.7 and the multimedia asset identified as the first identity is weighted to 0.3. Obtaining the behavior sequence characteristics of the target user account according to the characteristic vector of each multimedia resource and the weight value corresponding to each multimedia resource comprises the following steps: and multiplying the vector characteristics of each multimedia resource by the corresponding weight value of each multimedia resource, and then adding the weighted vector characteristics to obtain the sequence behavior characteristics of the target user account. And then, splicing the sequence behavior characteristics of the target user account with the user characteristic information to obtain a user characteristic vector.

Optionally, the obtaining the interaction feature vector according to the user feature and the resource feature of the target multimedia resource in step S10222 may further include: obtaining a weight value between the target multimedia resource and each multimedia resource according to the resource feature vector of the target multimedia resource and the feature vector of each multimedia resource in the list of the multimedia resources; and obtaining an interactive feature vector according to the resource feature vector and each weight value of the target multimedia resource.

In the technical solution in step S10222, the weight value between the target multimedia resource and each multimedia resource may be understood as a matching degree or a similarity between the target multimedia resource and each multimedia resource, and the interaction feature vector between the target user account and the target multimedia resource may be obtained according to the resource feature vector of the target multimedia resource and the weight value between the target multimedia resource and each multimedia resource. By the scheme, the interactive feature vector can be rapidly and accurately determined, and then data preparation is made for subsequently calculating target data.

Optionally, the obtaining of the target data according to the user feature vector and the interaction feature vector in step S10223 may further include: inputting the user feature vector and the interaction feature vector into the attention model; received from the attention model output: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource, and the probability of rebroadcasting the target multimedia resource.

In order to improve the processing efficiency, a self-attention model is introduced in the application, and the user feature vector and the interaction feature vector are input into the self-attention model for processing. In addition, the environment information may be subjected to multiple layers of a self-attention model multi-layer fully-connected network (DNN network) and then output a vector feature of the environment information with a preset length, where the environment information may be: location information of the user, current time, equipment used, current network, target user account login duration, and the like. Then, after the user feature vector and the vector features of the interactive feature vector and the environmental information are spliced, the width of the hidden layer of the DNN network input from the attention model gradually decreases to 1, for example, the dimension after the user feature vector and the vector features of the interactive feature vector and the environmental information are spliced is 1024, and the width of the hidden layer of the DNN network is respectively changed to 1024- >512- >256- >128- > 1. And calculating target data according to the data finally output from the attention model, so that the target data can be obtained after the attention model can be rapidly output and processed. By the scheme, the processing efficiency of calculating the target data can be improved, so that whether the target multimedia resource meets the marking prompt condition or not is rapidly determined according to the target data.

Optionally, the determining that the presentation status of the target multimedia resource meets the marked prompting status in step S103 may further include: when the target multimedia resource is displayed for a preset time or when the target multimedia resource is displayed for a preset proportion time, determining that the display state of the target multimedia resource meets the mark prompt state; or, determining a target time period based on the target user account, and determining that the display state of the target multimedia resource meets the mark prompt state when the target multimedia resource is displayed in the target time period.

For example, the total duration of the presentation of the target multimedia resource is 30s, and when the duration of the presentation of the target multimedia resource reaches 1/2 of the total duration of the presentation, the presentation status of the target multimedia resource is considered to be in accordance with the markup prompt status. Or counting the favorite contents of the target user account user in the 20s-30s time period of each multimedia resource, and determining that the display state of the target multimedia resource meets the mark prompt state when the target multimedia resource is displayed in the 20s-30s time period. Or estimating the wonderful content of the target multimedia resource within the 15s-25s time period, and determining that the display state of the target multimedia resource accords with the mark prompt state when the target multimedia resource is displayed within the 15s-25s time period. By the method, whether the display state of the target multimedia resource meets the mark prompting state or not can be reasonably determined, so that when the target multimedia resource is marked in the following process, the display effect is prevented from being influenced by frequent mark prompting information in the multimedia resource display process, and meanwhile, the mark requirements of different users on the multimedia resource can be effectively met.

Optionally, the presenting of the tag prompt information to the target user account in step S103 may further include: controlling the mark prompt information according to a preset moving direction, and performing moving display on the target user account in a preset icon style; or controlling the mark prompt information according to a preset time interval, and displaying on the target user account in a preset icon style; or controlling the mark prompt information according to a preset time interval and a preset moving direction, and displaying on the target user account in a preset icon style.

For example, the preset icon style may be a bubble type pattern or a bubble type icon, and when the mark prompt information is displayed to the target user account, the bubble type pattern or the bubble type icon may be movably displayed on the target user account from bottom to top. Or, when the display state of the target multimedia resource meets the mark prompt state, the bubble type pattern or the bubble type icon may be displayed on the target user account every 3 s. Or, the bubble type pattern or the bubble type icon is displayed on the target user account every 3s in the direction from bottom to top.

Through the control mode and the display mode of the marking prompt information provided in the scheme, the marking prompt information is displayed in a proper mode, and a user can see the marking prompt information at a proper time so as to mark multimedia resources, so that the display effect is prevented from being influenced by frequent marking prompt information in the multimedia resource display process, and meanwhile, the marking requirements of different users on the multimedia resources can be effectively met.

Optionally, the determining that the target multimedia resource meets the mark prompting condition for the target user account in step S103 may further include: triggering a target request to a server, wherein the target request carries information of a target user account; receiving target information returned by the server in response to the target request; and determining that the target multimedia resource meets the marking prompt condition based on the target information.

In order to improve the efficiency of determining whether the target multimedia resource meets the mark prompting condition, when the target user account shows the target multimedia resource, the target request is triggered to the server, and the server responds to the target information returned by the target request, so that whether the target multimedia resource meets the mark prompting condition can be rapidly determined. After the server receives the target request carrying the information of the target user account, the server can extract the information of the target user account and the resource characteristics of the target multimedia resources from the cache for processing, and therefore the target information is returned quickly. And if the target field in the target information returned by the server is marked as the target value, determining that the target multimedia resource meets the marking prompt condition. For example, the server marks the returned data structure Popup field as true, which indicates that the target multimedia resource meets the mark prompt condition. That is, by judging whether the target field is marked as the target value, whether the target multimedia resource meets the marking prompt condition can be quickly determined.

Fig. 4 is a flowchart illustrating an information prompting method according to an exemplary embodiment, where as shown in fig. 4, the information prompting method is used in a server, and includes the following steps:

step S401, receiving a target request triggered by a client, wherein the target request carries information of a target user account.

When the target multimedia resource is displayed on the target user account, the target request can be triggered to the server, so that the efficiency of determining whether the target multimedia resource meets the marking prompt condition is improved through the server.

Step S402, the information of the target user account and the resource characteristics of the target multimedia resources are sent to the self-attention model, and the data information output by the self-attention model is received.

After the server receives the target request, the server can extract the information of the target user account and the resource characteristics of the target multimedia resources from the cache and send the information to the self-attention model, the self-attention model is introduced into the application, the information of the target user account and the resource characteristics of the target multimedia resources are input into the self-attention model for processing, the self-attention model can output and process the information quickly to obtain data information, and therefore the processing efficiency of obtaining the data information is improved.

And S403, determining target information based on the data information, and sending the target information to the client, wherein the target information is used for determining whether the target multimedia resource meets the mark prompting condition.

And analyzing the data information in the server, and if the target multimedia resource obtained by analysis meets the marking prompt condition, marking the target field as a target value so as to determine the target information. For example, if the data structure Popup field is marked as true, it indicates that the target multimedia resource meets the marking prompt condition.

Through the technical scheme in the steps S401-S403, whether the target multimedia resource meets the mark prompting condition or not can be quickly determined by the server, so that the mark prompting information for the target multimedia resource is triggered under the condition that the target multimedia resource meets the mark prompting condition, thereby improving the rationality of displaying the mark prompting information, realizing that the mark prompting information can be displayed to a user account only when the user account has mark requirements in the process of displaying the multimedia resource aiming at different user accounts, so as to guide the user account to perform mark prompting on the multimedia resource, thereby avoiding the influence of frequent mark prompting information in the process of displaying the multimedia resource on the display effect, and simultaneously effectively meeting the mark requirements of different users on the multimedia resource.

Optionally, in order to determine the target information quickly and accurately, the data information includes: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource, and the probability of rebroadcasting the target multimedia resource, and the determining the target information based on the data information in step S203 may further include: if the probability of marking the target multimedia resource is greater than the first preset threshold, the probability of reviewing the target multimedia resource is greater than the second preset threshold, and the probability of repeatedly playing the target multimedia resource is greater than the third preset threshold, the target field is marked as a target value to determine target information, wherein the target value is used for identifying that the target multimedia resource meets the marking prompt condition.

For example, the first preset threshold is 0.1, the second preset threshold is 0.05, and the third preset threshold is 0.02. If the probability of marking the target multimedia resource is greater than 0.1, the probability of reviewing the target multimedia resource is greater than 0.05, and the probability of repeatedly broadcasting the target multimedia resource is greater than 0.02, the target field is marked as a target value, which indicates that the target multimedia resource meets the marking prompt condition, so that the target information can be quickly and accurately determined according to the target field marked as the target value.

Fig. 5 is a schematic block diagram illustrating a structure of a client according to an exemplary embodiment, wherein the client includes a processor 121 and a memory 122; the memory is to store executable instructions; the processor is configured to execute any one of the above information prompting methods according to the executable instructions.

The memory 122 may be configured to store software programs and modules, such as program instructions/modules corresponding to the page processing method and apparatus in the embodiments of the disclosure, and the processor 121 executes various functional applications and data processing by running the software programs and modules stored in the memory, so as to implement the above-mentioned page processing method. The memory 122 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 122 may further include memory located remotely from the processor, which may be connected to the computer terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

Fig. 6 is a block diagram illustrating a configuration of a server according to an exemplary embodiment. As shown in fig. 6, the server 110 may include: one or more (only one shown in fig. 6) processing components 111, a storage unit 112 for storing instructions executable by the processing components 111, a power supply component 113 for supplying power, a network interface 114 for implementing communication with an external network, and an I/O input/output interface 115 for data transmission with the outside; wherein the processing component 111 is configured to execute instructions to implement any of the information prompting methods described above.

The storage unit may be configured to store software programs and modules, such as program instructions/modules corresponding to the interface processing method and apparatus in the embodiments of the present disclosure, and the processing component executes various functional applications and data processing by running the software programs and modules stored in the storage unit, so as to implement the interface processing method. The memory cells may include high speed random access memory cells, and may also include non-volatile memory cells, such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory cells. In some examples, the memory unit may further include a memory unit remotely disposed from the processing component.

Fig. 7 is a schematic diagram of an information prompting system according to an exemplary embodiment, as shown in fig. 7, including: client 110 and server 120.

The client 110 is configured to display the target multimedia resource to a target user account; aiming at a target user account, determining that a target multimedia resource meets a marking prompt condition, and generating corresponding marking prompt information, wherein the marking prompt information is used for prompting the target user account to mark the target multimedia resource; determining that the display state of the target multimedia resource accords with the mark prompt state, and displaying mark prompt information to a target user account; the server 120 is configured to receive a target request triggered by the client 110, where the target request carries information of a target user account; sending the information of the target user account and the resource characteristics of the target multimedia resources to a self-attention model, and receiving data information output by the self-attention model; and determining target information based on the data information, and sending the target information to the client 110, wherein the target information is used for determining whether the target multimedia resource meets the marking prompt condition.

Through the interaction between the client 110 and the server 120, it can be quickly determined that the mark prompt information is displayed to the target user account when the display state of the target multimedia resource meets the mark prompt state, so that the mark prompt information can be displayed to the user account only when the mark requirement of the user account is identified in the process of displaying the multimedia resource aiming at different user accounts, so as to guide the user account to perform mark prompt on the multimedia resource, thereby avoiding the influence of frequent mark prompt information in the multimedia resource display process on the display effect, and simultaneously effectively meeting the mark requirements of different users on the multimedia resource.

Fig. 8 is a block diagram of an information presentation device according to a sixth illustrative embodiment. Referring to fig. 8, the apparatus includes: a first display unit 601, a first generation unit 602 and a second display unit 603.

Specifically, the first presentation unit 601 is configured to perform presentation of the target multimedia asset to the target user account.

A first generating unit 602, configured to execute, for a target user account, determining that a target multimedia resource meets a tagging prompting condition, and generating corresponding tagging prompting information, where the tagging prompting information is used for prompting the target user account to perform a tagging operation on the target multimedia resource.

And a second presentation unit 603 configured to perform determining that the presentation status of the target multimedia resource meets the tag prompt status, and presenting the tag prompt information to the target user account.

To sum up, in the information prompting device provided in the sixth embodiment of the present application, the first display unit 601 displays the target multimedia resource to the target user account; the first generating unit 602 determines, for a target user account, that a target multimedia resource meets a tagging prompt condition, and generates corresponding tagging prompt information, where the tagging prompt information is used for prompting the target user account to perform a tagging operation on the target multimedia resource; the second presentation unit 603 determines that the presentation state of the target multimedia resource conforms to the mark prompt state, and presents the mark prompt information to the account of the target user, thereby solving the problem that the manner of popping up the mark prompt information for each multimedia resource in the related art easily interferes with the normal viewing of the multimedia resource by the user and affects the viewing experience of the user. The mark prompting information is generated aiming at the target user account, and the mark prompting information is displayed to the target user account when the display state of the target multimedia resource accords with the mark prompting state, so that the mark prompting information is displayed to the user account to guide the user account to mark and prompt the multimedia resource when the user account is identified to have mark requirements in the process of displaying the multimedia resource aiming at different user accounts, the display effect is prevented from being influenced by frequent mark prompting information in the process of displaying the multimedia resource, and the mark requirements of different users on the multimedia resource can be effectively met.

Optionally, in the information prompting apparatus provided in the sixth embodiment of the present application, the first generating unit 602 includes: a first obtaining subunit, configured to perform obtaining a user characteristic of a target user account and a resource characteristic of a target multimedia resource; the first determining subunit is configured to determine that the target multimedia resource meets a marking prompting condition according to the user characteristics and the resource characteristics, wherein the marking prompting condition is a condition for determining that a target user account needs to be marked and prompted on the target multimedia resource according to data acquired by the user characteristics and the resource characteristics.

Optionally, in the information prompt apparatus provided in the sixth embodiment of the present application, the first determining subunit includes: the first acquisition module is configured to execute the steps of obtaining a user characteristic vector according to a target user account and user characteristics; the second acquisition module is configured to execute the resource characteristics according to the user characteristics and the target multimedia resources to obtain an interactive characteristic vector; a third obtaining module configured to obtain target data according to the user feature vector and the interaction feature vector, where the target data includes: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource and the probability of rebroadcasting the target multimedia resource; and the first determination module is configured to determine that the target multimedia resource meets the marking prompt condition according to the target data.

Optionally, in the information prompt apparatus provided in the sixth embodiment of the present application, the first determining module includes: and the first determining submodule is configured to determine that the target multimedia resource meets the marking prompt condition if the probability of marking the target multimedia resource is greater than a first preset threshold, the probability of reviewing the target multimedia resource is greater than a second preset threshold, and the probability of rebroadcasting the target multimedia resource is greater than a third preset threshold.

Optionally, in the information prompt apparatus provided in the sixth embodiment of the present application, the first obtaining module includes: a second determining sub-module configured to perform determining a list of historical multimedia assets, wherein the list of historical multimedia assets is a list of multimedia assets that have been presented on the target user account in chronological order of presentation; a third determining sub-module configured to perform determining an identity of each multimedia asset in the list of multimedia assets; the fourth determining submodule is configured to determine a weight value corresponding to each multimedia resource according to the identifier of each multimedia resource; the second obtaining submodule is configured to execute the action sequence characteristics according to the feature vector of each multimedia resource and the weight value corresponding to each multimedia resource to obtain the action sequence characteristics of the target user account; the third obtaining sub-module is configured to execute the action sequence feature and the user feature according to the target user account to obtain a user feature vector, wherein the user feature comprises one of the following: user portrait information, user consumption statistics, and user behavior sequence features.

Optionally, in the information prompt apparatus provided in the sixth embodiment of the present application, the second obtaining module includes: the second acquiring subunit is configured to execute the processing according to the resource feature vector of the target multimedia resource and the feature vector of each multimedia resource in the list of multimedia resources to obtain a weight value between the target multimedia resource and each multimedia resource; and the third obtaining subunit is configured to execute the resource feature vector and each weight value according to the target multimedia resource to obtain an interactive feature vector.

Optionally, in the information prompt apparatus provided in the sixth embodiment of the present application, the third obtaining module includes: a first input submodule configured to perform input of the user feature vector and the interaction feature vector from the attention model; a first receiving submodule configured to perform receiving, from an attention model output: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource, and the probability of rebroadcasting the target multimedia resource.

Optionally, in the information prompt apparatus provided in the sixth embodiment of the present application, the second display unit includes: the second determining subunit is configured to determine that the display state of the target multimedia resource meets the mark prompting state when the target multimedia resource is displayed for a preset time or when the target multimedia resource is displayed for a preset proportion time; or, the third determining subunit is configured to perform determining the target time period based on the target user account, and determine that the presentation state of the target multimedia resource meets the mark prompting state when the target multimedia resource is presented within the target time period.

Optionally, in the information prompt apparatus provided in the sixth embodiment of the present application, the second display unit includes a first display subunit, configured to execute controlling the mark prompt information according to a preset moving direction, and perform moving display on the target user account in a preset icon style; or the second display subunit is configured to control the mark prompt information according to a preset time interval, and display the mark prompt information on the target user account in a preset icon style; or, the third display subunit is configured to perform display on the target user account in a preset icon style according to a preset time interval and a preset moving direction control mark prompt message.

Optionally, in the information prompt apparatus provided in the sixth embodiment of the present application, the first generating unit includes: the triggering subunit is configured to execute a triggering target request to the server, wherein the target request carries information of a target user account; a receiving subunit configured to execute receiving of the target information returned by the server in response to the target request; and the fourth determining subunit is configured to execute determining that the target multimedia resource meets the marking prompt condition based on the target information.

Optionally, in the information prompt apparatus provided in the sixth embodiment of the present application, the fourth determining subunit includes: and the second determination module is configured to determine that the target multimedia resource meets the marking prompt condition if the target field in the target information is marked as the target value.

Fig. 9 is a block diagram of an information presentation device according to a seventh illustrative embodiment. Referring to fig. 9, the apparatus includes: a first receiving unit 701, a second receiving unit 702 and a transmitting unit 703.

Specifically, the first receiving unit 701 is configured to receive a target request triggered by a client, where the target request carries information of a target user account.

A second receiving unit 702 configured to send information of the target user account and resource characteristics of the target multimedia resource to the self-attention model and receive data information output from the attention model.

A sending unit 703 configured to determine target information based on the data information, and send the target information to the client, where the target information is used to determine whether the target multimedia resource meets the mark prompting condition.

To sum up, in an information prompting device shown in the seventh embodiment of the present application, a target request triggered by a client is received through a first receiving unit 701, where the target request carries information of a target user account; the second receiving unit 702 sends the information of the target user account and the resource characteristics of the target multimedia resource to the self-attention model, and receives data information output from the attention model; the sending unit 703 determines target information based on the data information, and sends the target information to the client, where the target information is used to determine whether the target multimedia resource meets the mark prompting condition. The problem that the normal watching of the user on the multimedia resources is easily interfered by a mode of popping up the mark prompt information on each multimedia resource in the related technology, and the watching experience of the user is influenced is solved. The mark prompting information is generated aiming at the target user account, and the mark prompting information is displayed to the target user account when the display state of the target multimedia resource accords with the mark prompting state, so that the mark prompting information is displayed to the user account to guide the user account to mark and prompt the multimedia resource when the user account is identified to have mark requirements in the process of displaying the multimedia resource aiming at different user accounts, the display effect is prevented from being influenced by frequent mark prompting information in the process of displaying the multimedia resource, and the mark requirements of different users on the multimedia resource can be effectively met.

Optionally, in the information prompting device provided in the seventh embodiment of the present application, the data information includes: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource, and the probability of rebroadcasting the target multimedia resource, the transmitting unit further includes: and the fifth determining subunit is configured to mark the target field as the target value to determine the target information if the probability of marking the target multimedia resource is greater than the first preset threshold, the probability of reviewing the target multimedia resource is greater than the second preset threshold, and the probability of rebroadcasting the target multimedia resource is greater than the third preset threshold, wherein the target value is used for identifying that the target multimedia resource meets the marking prompt condition.

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 an exemplary embodiment, there is also provided a storage medium comprising instructions, such as a memory comprising instructions, executable by a processor of an apparatus to perform the above method. Alternatively, the storage medium may be a non-transitory computer readable storage medium, for example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, there is also provided a computer program product comprising: the program in the computer program product, when executed by a processor of an electronic device, enables the electronic device to perform the information prompting method of any of the above.

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 (10)

1. An information prompting method, comprising:

displaying the target multimedia resource to a target user account;

aiming at the target user account, determining that the target multimedia resource meets a marking prompt condition, and generating corresponding marking prompt information, wherein the marking prompt information is used for prompting the target user account to mark the target multimedia resource;

and determining that the display state of the target multimedia resource accords with a mark prompt state, and displaying the mark prompt information to the target user account.

2. The information prompting method of claim 1, wherein the step of determining, for the target user account, that the target multimedia resource meets a markup prompting condition comprises:

acquiring user characteristics of the target user account and resource characteristics of the target multimedia resource;

and determining that the target multimedia resource meets a marking prompt condition according to the user characteristics and the resource characteristics, wherein the marking prompt condition is a condition for determining that the target user account needs to be marked and prompted on the target multimedia resource according to the data acquired by the user characteristics and the resource characteristics.

3. The information prompting method of claim 2, wherein the step of determining that the target multimedia resource meets a markup prompting condition according to the user characteristics and the resource characteristics comprises:

obtaining a user feature vector according to the target user account and the user features;

obtaining an interactive feature vector according to the user feature and the resource feature of the target multimedia resource;

obtaining target data according to the user feature vector and the interaction feature vector, wherein the target data comprises: the probability of marking the target multimedia resource, the probability of reviewing the target multimedia resource and the probability of rebroadcasting the target multimedia resource;

and determining that the target multimedia resource meets the marking prompt condition according to the target data.

4. An information prompting method, comprising:

receiving a target request triggered by a client, wherein the target request carries information of a target user account;

sending the information of the target user account and the resource characteristics of the target multimedia resources to a self-attention model, and receiving data information output by the self-attention model;

and determining target information based on the data information, and sending the target information to a client, wherein the target information is used for determining whether the target multimedia resource meets a marking prompt condition.

5. An information presentation device, comprising:

the first presentation unit is configured to perform presentation of the target multimedia resource to the target user account;

the first generating unit is configured to execute, aiming at the target user account, determining that the target multimedia resource meets a marking prompt condition, and generating corresponding marking prompt information, wherein the marking prompt information is used for prompting the target user account to perform a marking operation on the target multimedia resource;

and the second display unit is configured to execute the steps of determining that the display state of the target multimedia resource meets a mark prompt state and displaying the mark prompt information to the target user account.

6. An information presentation device, comprising:

the system comprises a first receiving unit, a second receiving unit and a third receiving unit, wherein the first receiving unit is configured to receive a target request triggered by a client, and the target request carries information of a target user account;

a second receiving unit, configured to send the information of the target user account and the resource characteristics of the target multimedia resource to a self-attention model, and receive data information output by the self-attention model;

and the sending unit is configured to determine target information based on the data information and send the target information to a client, wherein the target information is used for determining whether the target multimedia resource meets a marking prompt condition.

7. A client comprising a memory and a processor; the memory is to store executable instructions; the processor is configured to execute the information prompting method according to any one of claims 1 to 3 or the information prompting method according to claim 4 according to the executable instruction.

8. A server, comprising a storage unit and a processing component; the storage unit is used for storing executable instructions; the processing component is configured to execute the information prompting method according to any one of claims 1 to 3 or the information prompting method according to claim 4 according to the executable instruction.

9. An information prompting system comprising a client described in claim 7 and a server described in claim 8.

10. A storage medium in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform the information prompting method of any one of claims 1 to 3, or the information prompting method of claim 4.

Images