CN114676308A

CN114676308A - Search term recommendation method and device, electronic equipment, storage medium and product

Info

Publication number: CN114676308A
Application number: CN202210260775.7A
Authority: CN
Inventors: 曹文强
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2022-03-16
Filing date: 2022-03-16
Publication date: 2022-06-28

Abstract

The present disclosure provides a search term recommendation method, apparatus, electronic device, storage medium, and product, including: determining alternative search terms corresponding to the currently played video based on the historical search logs and the real-time frame of the currently played video; determining a target score of each alternative search word, and sequencing each alternative search word according to the target score to obtain a sequencing result; and determining a target search word from the alternative search words based on the sequencing result, and displaying the target search word in a playing interface of the currently played video. Therefore, the alternative search words are determined based on the historical search logs and the real-time frame of the currently played video, the target search words are determined based on the target scores and displayed on the playing interface of the currently played video, the user can directly search based on the target search words, the search path of the user is shortened, and the divergence requirements of the user can be quickly and directly met.

Description

Search term recommendation method and device, electronic equipment, storage medium and product

Technical Field

The present disclosure relates to the field of video playing technologies, and in particular, to a method and an apparatus for recommending search terms, an electronic device, a storage medium, and a product.

Background

With the continuous development of network technology, various short videos gradually rise, become one of the main means for users to record life, and also become one of the main forms for users to consume and entertain daily.

Due to the wide variety of short videos and various contents, users often need to search to meet their own needs. In the prior art, a short video application program in electronic equipment often provides a specific search interface, and when a user needs to search, the user first needs to close the current interface and open the search interface, and then inputs a search word to search. The search mode has a long search path, and the divergent requirements of the user cannot be directly met in scenes such as video playing and the like.

Disclosure of Invention

In order to overcome the problems in the related art, the present disclosure provides a search term recommendation method, apparatus, electronic device, storage medium, and product.

According to a first aspect of the embodiments of the present disclosure, there is provided a search term recommendation method, including:

determining alternative search terms corresponding to the currently played video based on a historical search log and a real-time frame of the currently played video;

determining a target score of each alternative search word, and sequencing each alternative search word according to the target score to obtain a sequencing result;

And determining a target search word from the alternative search words based on the sequencing result, and displaying the target search word in a playing interface of the currently played video.

Optionally, the determining, based on the historical search log and the real-time frame of the currently played video, the alternative search term corresponding to the currently played video includes:

acquiring the historical search logs, and determining a plurality of first search terms associated with the currently played video in the historical search logs;

determining target parameters of the first search terms, and sequencing the first search terms according to the target parameters; the target parameter comprises at least one of click rate and long-play rate;

selecting a first search word with the target parameter ranked at the top M to obtain a first alternative search word; and M is an integer greater than 1.

determining a similar video corresponding to the currently playing video, and determining a plurality of second search terms associated with the similar video in the historical search log;

Determining target parameters corresponding to the second search terms, and sequencing the second search terms according to the target parameters;

selecting a second search term with the top N-bit ranking of the target parameters to obtain a second alternative search term; and N is an integer greater than 1.

acquiring a real-time frame of the currently played video, and acquiring a real-time audio corresponding to the real-time frame and in a preset historical period;

determining a third search word corresponding to the real-time frame and a fourth search word corresponding to the real-time audio based on a preset recognition algorithm;

and determining a third alternative search word corresponding to the currently played video based on the third search word and the fourth search word.

Optionally, the determining the target score of each candidate search term includes:

determining target characteristics corresponding to the alternative search terms respectively; the target characteristics comprise one or more of search word type, relevance, timeliness, simplicity and click rate;

And inputting each alternative search word and the target characteristics corresponding to the alternative search words into a target sorting model to obtain a target score corresponding to each alternative search word.

Optionally, the displaying the target search term in the playing interface of the currently played video includes:

displaying a preset number of target search terms in a preset area of the playing interface;

and after a preset period, displaying a next group of target search terms with preset quantity.

Optionally, the method further includes:

under the condition that a preset input instruction for the target search word is received, searching based on the target search word corresponding to the preset input instruction;

and displaying a target video corresponding to the target search term.

According to a second aspect of the embodiments of the present disclosure, there is provided a search word recommendation apparatus including:

the device comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is configured to determine an alternative search word corresponding to a currently playing video based on a historical search log and a real-time frame of the currently playing video;

the second determining module is configured to determine a target score of each alternative search word, and rank each alternative search word according to the target score to obtain a ranking result;

A first display module configured to determine a target search word from the candidate search words based on the sorting result, and display the target search word in a playing interface of the currently playing video.

Optionally, the first determining module is specifically configured to:

Optionally, the first determining module is further configured to:

Optionally, the second determining module is specifically configured to:

Optionally, the first display module is specifically configured to:

Optionally, the apparatus further comprises:

the searching module is configured to search based on a target search word corresponding to a preset input instruction under the condition that the preset input instruction aiming at the target search word is received;

a second display module configured to display a target video corresponding to the target search term.

In accordance with a third aspect of the present disclosure, there is provided an electronic device comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the search term recommendation method of any of the above.

According to a fourth aspect of the present disclosure, there is provided a storage medium, wherein instructions, when executed by a processor of an electronic device, cause the electronic device to perform a method of implementing search term recommendation as in any one of the above.

According to a fifth aspect of the present disclosure, there is provided a computer program product comprising readable program instructions which, when executed by a processor of an electronic device, cause the electronic device to perform the search term recommendation method according to any one of the above.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

in the embodiment of the disclosure, based on a historical search log and a real-time frame of a currently played video, an alternative search word corresponding to the currently played video is determined; determining a target score of each alternative search word, and sequencing each alternative search word according to the target score to obtain a sequencing result; and determining a target search word from the alternative search words based on the sequencing result, and displaying the target search word in a playing interface of the currently played video. Therefore, the alternative search words are determined based on the historical search logs and the real-time frame of the currently played video, the target search words are determined based on the target scores and displayed on the playing interface of the currently played video, the user can directly search based on the target search words without performing operations of closing the current interface, opening the search interface and inputting the search words, the search path of the user is shortened, and the divergent requirements of the user can be quickly and directly 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.

FIG. 1 is a flow chart of steps of a method of search term recommendation in an embodiment of the present disclosure;

FIG. 2 is a schematic illustration of a target search term display of an embodiment of the present disclosure;

fig. 3 is a block diagram of a search word recommending apparatus according to an embodiment of the present disclosure;

FIG. 4 is a block diagram of an electronic device of an embodiment of the present disclosure;

fig. 5 is a block diagram of another search word recommendation apparatus according to an embodiment of the present disclosure.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. 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. It should be noted that the user information (including but not limited to device information of the user, personal information of the user, etc.), related data, etc. referred to in the present disclosure are all information authorized by the user or authorized by each party.

Fig. 1 is a flowchart illustrating steps of a method for recommending search terms according to an embodiment of the present disclosure. The execution main body of the method can be an electronic device, and specifically can be a smart phone, a computer, a notebook, a tablet computer, a vehicle-mounted computer, and the like, which is not limited in the embodiment of the disclosure. As shown in fig. 1, the search term recommendation method specifically includes the following steps:

step 101, determining an alternative search term corresponding to a currently played video based on a historical search log and a real-time frame of the currently played video.

In the embodiment of the present disclosure, the historical search log may refer to a search log of a user in a short video Application (APP), and includes operations of searching, clicking, playing and the like of the user, and also includes contents such as a search result corresponding to the search operation of the user. The historical search log may be a search log for all users of the short video application program, or may be a search log for a user group with a high similarity between the short video application program and a current user, which is not limited in this embodiment of the present disclosure.

The currently playing video may refer to the video that the user is playing in the short video application. The real-time frame may refer to an image frame corresponding to a currently played video. The alternative search term may refer to a plurality of search terms (query) determined based on the historical search log and the currently playing video.

In this step, in the process of playing the short video, the electronic device may obtain a history search log, obtain a real-time frame of the currently played video, determine an alternative search word associated with the currently played video based on the history search log, identify the alternative search word based on the real-time frame, obtain the alternative search word corresponding to the currently played video after merging, and subsequently, may perform screening and sorting on the alternative search word to obtain a target search word that is finally displayed.

And 102, determining a target score of each alternative search word, and sequencing each alternative search word according to the target score to obtain a sequencing result.

In the embodiment of the present disclosure, the target score may refer to a score value corresponding to the candidate search term, and the target score may represent a recommendation value of the candidate search term. The higher the target score, the higher the recommendation value of the alternative search term. The target score may be determined based on various target features of the alternative search term, where the target features may be timeliness, simplicity, click rate, and relevance between the alternative search term and the currently played video, and the specific category of the target features and the specific calculation manner of the target score are not limited in the embodiments of the present disclosure.

In this step, after obtaining the alternative search terms corresponding to the currently played video, the electronic device may score each alternative search term, calculate a target score of each alternative search term, and then sort all the alternative search terms according to the size of the target score to obtain a sorting result. The target search terms that are ultimately presented to the user may then be determined based on the ranking results.

Step 103, determining a target search word from the alternative search words based on the sorting result, and displaying the target search word in the playing interface of the currently played video.

In the embodiment of the present disclosure, the target search term may refer to a search term that is determined based on the alternative search term and is finally displayed to the user. The playing interface may refer to a video playing page in an application program.

In this step, after the target scores of the alternative search terms are determined and the ranking results of the alternative search terms are determined according to the target scores, the target search terms can be determined according to the ranking order of the alternative search terms. The determination method of the target search term may be to use a candidate search term with a target score ranked at the top X as the target search term, where the value X may be 5, 10, and the like, and may be specifically set based on actual requirements. The determination method of the target search term may also be to select an alternative search term with a target score greater than a preset threshold as the target search term, where the preset threshold may be a preset critical value of the target score. The specific determination mode of the target search term is not limited in the embodiments of the present disclosure.

In one implementation, in a playing interface of an application short video, content often displayed by an electronic device is information of a video itself, such as a short video cover text, a short video author name, and the like. In the short video playing interface, if a user wants to perform a search operation, the user needs to close the current short video playing interface, open the search interface and input a search word for searching.

In the embodiment of the disclosure, the determined target search term can be directly displayed on the playing interface of the currently played video, and the user can subsequently and directly search through touch operations such as clicking and the like, so that the divergence requirement of the user is met, the search operation of the user is simpler, and the satisfaction degree of the user is improved.

To sum up, in the embodiment of the present disclosure, a search term recommendation method is provided, in which an alternative search term corresponding to a currently played video is determined based on a historical search log and a real-time frame of the currently played video; determining a target score of each alternative search word, and sequencing each alternative search word according to the target score to obtain a sequencing result; and determining a target search word from the alternative search words based on the sequencing result, and displaying the target search word in a playing interface of the currently played video. Therefore, the alternative search words are determined based on the historical search logs and the real-time frame of the currently played video, the target search words are determined based on the target scores and displayed on the playing interface of the currently played video, the user can directly search based on the target search words without performing operations of closing the current interface, opening the search interface and inputting the search words, the search path of the user is shortened, and the divergent requirements of the user can be quickly and directly met.

Optionally, in this embodiment of the present disclosure, step 101 may include the following steps S21 to S23:

and step S21, obtaining the history search log, and determining a plurality of first search terms associated with the currently played video in the history search log.

In the embodiment of the present disclosure, the first search term may refer to a search term associated with a currently playing video. When the user searches based on the first search word, the currently playing video can be included in the search result. The historical search log may refer to a recent search log, such as within three days or within a week, etc., so as to ensure the validity of the data.

It should be noted that the electronic device may further determine a search term used by the current user to search for the currently played video, and remove the search term from the first search term. Because the user is the currently played video determined by the search terms, the search terms which are searched by the user do not need to be recommended to the user at this time, the search terms which are used by the user can be removed from the first search terms, repeated recommendation of the search terms is avoided, and the search divergence requirements of the user are further improved.

Step S22, determining target parameters of the first search terms, and sequencing the first search terms according to the target parameters; the target parameters comprise at least one of click rate and long play rate.

In the embodiment of the present disclosure, the target parameter may refer to various statistical parameters of the first search term. The click through rate may refer to a click through rate for a currently playing video after a user obtains a search result based on the first search term. The specific calculation mode of the click rate may be to calculate a ratio of the number of users clicking the currently played video to the total number of users, which is not limited in the embodiment of the present disclosure.

The long play rate may be a ratio of the number of times that the user playing duration accounts for the current video playing duration to be greater than a preset ratio threshold to the total number of times that the user playing video is played. Exemplarily, when the short video duration is 10 seconds, the preset proportion threshold may be 90%, when the user searches based on the first search term, after the electronic device displays the search result, if the user exits from the play interface after clicking the currently played video for 1 second, at this time, the proportion of the user play duration to the currently played video duration is 10%, which is obviously less than the preset proportion threshold, and the short play behavior is performed. If the user exits the playing interface after clicking the currently played video for 9.5 seconds, the ratio of the playing time of the user to the current playing video time is 95%, which is a long playing behavior. The electronic equipment can count the times of the user aiming at the long play behavior of the currently played video and the total playing times of the currently played video so as to calculate the long play rate.

S23, selecting a first search word with the top M-bit target parameter sequence to obtain a first alternative search word; and M is an integer greater than 1.

In the embodiment of the present disclosure, the first alternative search term may refer to a high-consumption search term associated with a currently playing video. The first alternative search term, namely the high-consumption query, is the first search term with higher target parameters, such as click rate, long-play rate and the like.

In this step, after the target parameter of the first search term is determined, the plurality of first search terms may be ranked based on the target parameter value, and then Top M first search terms, that is, the first search term with the target parameter ranked at the Top M bits, are selected as the first candidate search terms. The value M may be specifically 5, 10, and the like, and may be flexibly set based on actual requirements, which is not limited in this disclosure.

In the step, a historical search log is obtained, and a plurality of first search terms related to the currently played video are determined in the historical search log; determining target parameters of the first search terms, and sequencing the first search terms according to the target parameters; the target parameter comprises at least one of click rate and long-play rate; and selecting a first search word with the target parameter ordered at the top M positions to obtain a first alternative search word. Therefore, in the embodiment of the disclosure, the first search term which is associated with the currently played video and has a high target parameter is selected as the first candidate search term, so that the accuracy and the rationality of determining the candidate search term can be improved, and the accuracy of recommending the subsequent search terms is further improved.

Optionally, in this embodiment of the present disclosure, step 101 may further include the following steps S31 to S33:

step S31, determining a similar video corresponding to the currently playing video, and determining a plurality of second search terms associated with the similar video in the history search log.

In the embodiment of the present disclosure, the similar video may refer to a video similar to the currently played video content. The similar video may be determined based on the content, such as the video title, the video tag, the category to which the video belongs, the content brief description, and the cover image, which are not limited in this disclosure. The second search term may refer to a search term associated with a similar video.

In this step, the electronic device may first determine, based on the currently played video, a similar video similar to the currently played video, then determine a plurality of second search terms associated with the similar video, and then may screen the plurality of second search terms to obtain a second candidate search term.

Step S32, determining target parameters corresponding to the plurality of second search terms, and sorting the plurality of second search terms according to the target parameters.

S33, selecting a second search term with the top N-bit target parameter sequence to obtain a second alternative search term; and N is an integer greater than 1.

In the embodiment of the present disclosure, after a plurality of second search terms are determined, target parameters corresponding to each second search term may be determined, and ranking is performed based on the target parameters, and then the second search term with the top N ranked target parameters is used as a second candidate search term. The click distribution (video similarity, target parameter similarity) of the second alternative search term is similar to that of the first alternative search term, and can be regarded as a concurrent search term of the first alternative search term. The value of the value N may be 5, 10, etc., which is not limited in the embodiment of the present disclosure.

Specifically, the specific implementation process of steps S32 to S33 may refer to steps S22 to S23, and the embodiment of the disclosure is not described herein again.

In the embodiment of the disclosure, a similar video corresponding to a currently played video is determined, and a plurality of second search terms associated with the similar video are determined in a historical search log; determining target parameters corresponding to the second search terms, and sequencing the second search terms according to the target parameters; and selecting a second search term with the top N-bit target parameter sequence to obtain a second alternative search term. Therefore, the similar video of the currently played video is determined, and the second alternative search term is determined based on the similar video, so that the comprehensiveness of determining the alternative search terms can be improved, and the breadth of the determination range of the alternative search terms can be expanded to a certain extent.

Optionally, in this embodiment of the present disclosure, step 101 may further include the following steps S41 to S43:

and step S41, acquiring the real-time frame of the currently played video, and acquiring the real-time audio corresponding to the real-time frame and in a preset history period.

In the embodiment of the present disclosure, the preset history period may refer to a preset video playing period, specifically, may be 2 seconds, 3 seconds, or 5 seconds, and the like, and may be flexibly set based on actual requirements, which is not limited in the embodiment of the present disclosure. Real-time audio may refer to background music of the currently playing video.

In this step, the electronic device may acquire a real-time frame of the currently played video and a real-time audio corresponding to the real-time frame during the process of playing the currently played video, and may subsequently determine the candidate search term based on the real-time frame and the real-time audio.

Step S42, determining a third search term corresponding to the real-time frame and a fourth search term corresponding to the real-time audio based on a preset recognition algorithm.

In the embodiment of the present disclosure, the preset recognition algorithm may refer to a preset image recognition algorithm, an audio recognition algorithm, and the like. The third search term may be a search term identified and determined by an image identification algorithm on the real-time frame, and specifically may be a character name, a movie name, a property name, and the like in the real-time frame. The fourth search term may refer to a search term determined by identifying real-time audio through an audio identification algorithm, and specifically may refer to a song name, a word author, a song author, a singer, and the like corresponding to the real-time audio. The specific categories of the third search term and the fourth search term are not limited in the embodiments of the present disclosure.

Step S43, determining a third candidate search term corresponding to the currently played video based on the third search term and the fourth search term.

In the embodiment of the present disclosure, the third candidate search term may refer to a search term associated with a real-time frame and real-time audio corresponding to the real-time frame, that is, a frame-related search term.

In this step, after the third search term and the fourth search term are determined, a third candidate search term may be further obtained through screening. The specific screening manner may be to screen based on preset evaluation indexes of each search term, where the preset evaluation indexes may be correlations between the search terms and currently played videos, and the like. Of course, the electronic device may also randomly select a third candidate search term from the third search term and the fourth search term, and so on. The embodiment of the present application does not limit a specific screening process of the third candidate search term.

In the embodiment of the disclosure, a real-time frame of a currently played video is acquired, and a real-time audio corresponding to the real-time frame and in a preset history period is acquired; determining a third search word corresponding to the real-time frame and a fourth search word corresponding to the real-time audio based on a preset recognition algorithm; and determining a third alternative search word corresponding to the currently played video based on the third search word and the fourth search word. Therefore, the third alternative search word is finally obtained by identifying and screening the real-time frame and the real-time audio corresponding to the real-time frame, the relevance between the alternative search word and the currently played video can be improved, and the divergent requirements of the user are met.

Optionally, in this embodiment of the present disclosure, step 102 may specifically include the following steps 1021 to 1022:

1021, determining target characteristics corresponding to the alternative search terms respectively; the target characteristics comprise one or more of search word type, relevance, timeliness, conciseness and click rate.

In the embodiment of the present disclosure, the target feature may refer to various feature parameters of the alternative search term. The search term type may refer to a type of an alternative search term, specifically, may refer to a first alternative search term, a second alternative search term, or a third alternative search term, where the search term type may be characterized by a One-hot code (One-hot), and the One-hot code may convert a category variable into a coding form that is easily utilized by a machine learning algorithm.

Relevance may refer to the relevance of the alternative search terms to the currently playing video. The higher the relevance, the higher the association degree of the alternative search term with the currently playing video. The correlation can be obtained by an algorithm such as a multi-modal correlation. The multi-modal correlation can judge the correlation between data of different modalities, such as text and image, text and video, and image and video, and the judgment process of the multi-modal correlation can be realized based on a multi-modal pre-training model. Of course, the determination process of the correlation may also be implemented by other algorithms, which is not limited in the embodiment of the present disclosure.

Timeliness may be used to characterize the timeliness of alternative search terms. The determining process of timeliness may be determined based on a specific time corresponding to the alternative search term. For example, for a candidate search word such as news that is more time-efficient, the time-efficiency of the candidate search word may be determined based on the time when the news event occurs.

The simplicity may refer to the degree of simplicity of the candidate search term, and specifically may refer to the word segmentation length of the candidate search term, and the like. The smaller the segmentation length is, the higher the compactness of the alternative search term is.

The click rate can refer to the historical click rate corresponding to the alternative search term, and can be specifically determined according to the number of users and the historical click times; the feature may also refer to a posterior feature of the candidate search term, for example, a click rate of the user for the candidate search term when the candidate search term is recommended under a currently played video.

It should be noted that, when the candidate search terms are ranked, the one or more target features may be selected to calculate the target score, which may be specifically determined based on actual needs and the computing capability of the electronic device, and this is not limited in this embodiment of the present application.

And 1022, inputting the candidate search terms and the target features corresponding to the candidate search terms into a target ordering model to obtain target scores corresponding to the candidate search terms.

In the embodiment of the present disclosure, the target ranking model may refer to a pre-trained scoring and ranking model. The input of the target sorting model may be alternative search terms and target characteristics corresponding to the alternative search terms, and the output may be target scores corresponding to the alternative search terms.

In this step, the target ranking model may be a tree model (XGBOOST) or a deep recommendation model (deep fm). Of course, the target ranking model may also be a simple linear model, for example, a user may first determine the type of the target feature, and then set a weight for each target feature, where the target score of the candidate search term is the weighted sum of each target feature value of the candidate search term. The embodiment of the present disclosure does not limit the specific type and implementation manner of the target ranking model.

In the embodiment of the disclosure, target characteristics corresponding to each alternative search term are determined; the target characteristics comprise one or more of search word type, relevance, timeliness, simplicity and click rate; and inputting each alternative search word and the target characteristics corresponding to the alternative search words into the target ordering model to obtain the target score corresponding to each alternative search word. Therefore, the target scores of the alternative search terms are determined based on the target characteristics, the accuracy and the reasonability of determining the target scores can be improved, and the reasonability of recommending the search terms is further improved.

Optionally, in this embodiment of the present disclosure, step 103 may specifically include the following steps 1031 to 1032:

and step 1031, displaying a preset number of target search terms in a preset area of the playing interface.

In the embodiment of the present disclosure, the preset area may refer to a specific area of the playing interface. The preset number may refer to the number of preset target search terms displayed at one time, and the preset number may be 2, 3, or 5, and may be specifically set based on actual needs, and this is not limited in this disclosure.

Step 1032, after the preset period, displaying a next group of target search terms with preset number.

In the embodiment of the present disclosure, the preset period may refer to a preset refresh period of the target search term, and a specific duration of the preset period may be 0.5 second, 0.7 second, 1 second, or the like.

In this step, after the target search term is determined, the electronic device may scroll and display the target search term in a preset area in a playing interface of the currently played video, where a specific display manner may be that a preset number of target search terms are used as a group, and a group of target search terms is displayed in a preset period. Therefore, the display of the target search word can not cause the shielding of the video playing, and the normal display of the target search word can also be ensured.

In the embodiment of the disclosure, a preset number of target search terms are displayed in a preset area of a playing interface; and after a preset period, displaying a next group of target search terms with preset quantity. Therefore, the target search word is displayed in the preset area of the playing interface in a rolling mode, the search word is recommended to the user on the video playing page, the search path of the user is shortened, and the divergent requirement of the user is met.

Exemplarily, fig. 2 shows a display diagram of a target search term according to an embodiment of the present disclosure. As shown in fig. 2, the playing interface of the electronic device 20 is playing a currently playing video 201, and the main content of the currently playing video 201 is "swordsman fighting with ironmen", wherein the target search terms 203 "ironmen 2" and 204 "little robert tangni" are displayed in a preset area 202 of the playing interface.

Therefore, in the embodiment of the disclosure, the electronic device determines the target search word according to the historical search log and the real-time frame of the currently played video and displays the target search word to the user, and the searched path is used for meeting the potential interest of the user, so that the user experience is improved. The target search word can be displayed to the user when the user searches for a found scene, namely, the search word recommendation of the search page, so that the search recommendation reasonability is improved. Meanwhile, high consumption results (high click rate and high long play rate target videos) of the target search terms can feed back the system recommendation service, namely the high consumption results corresponding to the target search terms are directly recommended to the user in a video recommendation scene, and the system recommendation effect can be further improved.

Optionally, in this embodiment of the present disclosure, the method for recommending search terms may further include the following steps S51 to S52:

and step S51, under the condition that a preset input instruction for the target search word is received, searching based on the target search word corresponding to the preset input instruction.

In the embodiment of the present disclosure, the preset input instruction may refer to a preset instruction for performing a search operation. The preset input instruction may be a touch instruction such as a click instruction or a slide instruction, and the specific type of the preset input instruction is not limited in the embodiment of the present disclosure.

In this step, after determining the target search term and displaying the target search term on the playing interface, the electronic device may receive a preset input instruction of the user, and then perform a search based on the target search term selected by the preset input instruction of the user.

And step S52, displaying the target video corresponding to the target search term.

In the embodiment of the present disclosure, the target video may refer to each video in the search result after the search is performed based on the target search term. After searching based on the target search term corresponding to the preset input instruction of the user, the electronic device may display a target video corresponding to the target search term to show the search result to the user.

In the embodiment of the disclosure, under the condition that a preset input instruction for a target search word is received, searching is carried out based on the target search word corresponding to the preset input instruction; and displaying the target video corresponding to the target search term. Therefore, the user can directly touch the target search word to search on the video playing page, the search path of the user is shortened, and the operation of the user is simplified.

Fig. 3 is a block diagram illustrating a search word recommending apparatus according to an exemplary embodiment, and as shown in fig. 3, the search word recommending apparatus 30 may include:

a first determining module 301, configured to determine, based on a historical search log and a real-time frame of a currently playing video, an alternative search term corresponding to the currently playing video;

a second determining module 302, configured to determine a target score of each candidate search term, and rank each candidate search term according to the target score to obtain a ranking result;

a first display module 303, configured to determine a target search word from the candidate search words based on the sorting result, and display the target search word in a playing interface of the currently playing video.

The search word recommendation device provided by the embodiment of the disclosure determines an alternative search word corresponding to a currently played video based on a historical search log and a real-time frame of the currently played video; determining a target score of each alternative search word, and sequencing each alternative search word according to the target score to obtain a sequencing result; and determining a target search word from the alternative search words based on the sequencing result, and displaying the target search word in a playing interface of the currently played video. Therefore, the alternative search words are determined based on the historical search logs and the real-time frame of the currently played video, the target search words are determined based on the target scores and displayed on the playing interface of the currently played video, the user can directly search based on the target search words without performing operations of closing the current interface, opening the search interface and inputting the search words, the search path of the user is shortened, and the divergent requirements of the user can be quickly and directly met.

Optionally, the first determining module 301 is specifically configured to:

determining target parameters of the first search terms, and sequencing the first search terms according to the target parameters; the target parameters comprise at least one of click rate and long-play rate;

selecting first search terms with the top M positions of the target parameters to obtain first alternative search terms; and M is an integer greater than 1.

Optionally, the first determining module 301 is specifically configured to:

Optionally, the first determining module 301 is further configured to:

Optionally, the second determining module 302 is specifically configured to:

and inputting the alternative search terms and the target characteristics corresponding to the alternative search terms into a target sorting model to obtain target scores corresponding to the alternative search terms.

Optionally, the first display module 303 is specifically configured to:

after a preset period, displaying a next group of a preset number of target search terms.

Optionally, the apparatus 30 further includes:

and the second display module is configured to display the target video corresponding to the target search term.

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.

According to an embodiment of the present disclosure, there is provided an electronic apparatus including: a processor, a memory for storing processor-executable instructions, wherein the processor is configured to perform the steps of the search term recommendation method as in any of the embodiments described above when executed.

According to an embodiment of the present disclosure, there is also provided a storage medium, in which instructions are executed by a processor of an electronic device, so that the electronic device can perform the steps in the search term recommendation method as in any one of the above embodiments.

There is also provided, according to an embodiment of the present disclosure, a computer program product including readable program instructions which, when executed by a processor of an electronic device, enable the electronic device to perform the steps of the search term recommendation method as in any one of the above embodiments.

Fig. 4 is a block diagram illustrating a terminal according to an example embodiment. For example, the terminal 400 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

Referring to fig. 4, the apparatus 400 may include one or more of the following components: a processing component 402, a memory 404, a power component 406, a multimedia component 408, an audio component 410, an interface for input/output (I/O) 412, a sensor component 414, and a communication component 416.

The processing component 402 generally controls overall operation of the device 400, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 402 may include one or more processors 420 to execute instructions to perform all or a portion of the steps of the search term recommendation method described above. Further, processing component 402 may include one or more modules that facilitate interaction between processing component 402 and other components. For example, the processing component 402 may include a multimedia module to facilitate interaction between the multimedia component 408 and the processing component 402.

The memory 404 is configured to store various types of data to support operations at the device 400. Examples of such data include instructions for any application or method operating on the device 400, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 404 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 406 provides power to the various components of the device 400. The power components 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 400.

The multimedia component 408 includes a screen that provides an output interface between the device 400 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 400 is in an operational mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 410 is configured to output and/or input audio signals. For example, audio component 410 includes a Microphone (MIC) configured to receive external audio signals when apparatus 400 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in the memory 404 or transmitted via the communication component 416. In some embodiments, audio component 410 also includes a speaker for outputting audio signals.

The I/O interface 412 provides an interface between the processing component 402 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor component 414 includes one or more sensors for providing various aspects of status assessment for the apparatus 400. For example, the sensor component 414 may detect the open/closed state of the device 400, the relative positioning of components, such as a display and keypad of the apparatus 400, the sensor component 414 may also detect a change in position of the apparatus 400 or a component of the apparatus 400, the presence or absence of user contact with the apparatus 400, orientation or acceleration/deceleration of the apparatus 400, and a change in temperature of the apparatus 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 414 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 416 is configured to facilitate wired or wireless communication between the apparatus 400 and other devices. The apparatus 400 may access a wireless network based on a communication standard, such as WiFi, an operator network (such as 2G, 3G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component 416 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 400 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above search term recommendation method.

In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 404 comprising instructions, executable by the processor 420 of the apparatus 400 to perform the search term recommendation method described above is also provided. 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.

Fig. 5 is a block diagram illustrating a search word recommending apparatus according to an exemplary embodiment. For example, the apparatus 500 may be provided as a server. Referring to fig. 5, the apparatus 500 includes a processing component 522 that further includes one or more processors and memory resources, represented by memory 532, for storing instructions, such as applications, that are executable by the processing component 522. The application programs stored in memory 532 may include one or more modules that each correspond to a set of instructions. Further, the processing component 522 is configured to execute instructions to perform the search term recommendation method described above.

The apparatus 500 may also include a power component 526 configured to perform power management of the apparatus 500, a wired or wireless network interface 550 configured to connect the apparatus 500 to a network, and an input/output (I/O) interface 558. The apparatus 500 may operate based on an operating system stored in the memory 532, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the invention 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 in 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 search term recommendation method, comprising:

2. The method of claim 1, wherein determining the alternative search term corresponding to the currently playing video based on the historical search logs and a real-time frame of the currently playing video comprises:

acquiring the historical search log, and determining a plurality of first search terms associated with the currently played video in the historical search log;

3. The method of claim 2, wherein the determining the alternative search term corresponding to the currently playing video based on the historical search log and the real-time frame of the currently playing video comprises:

4. The method of claim 1, wherein determining the alternative search term corresponding to the currently playing video based on the historical search logs and a real-time frame of the currently playing video comprises:

5. The method of claim 1, wherein said determining a target score for each of said candidate search terms comprises:

6. The method according to any one of claims 1 to 5, wherein the displaying the target search term in the playing interface of the currently playing video comprises:

7. A search word recommendation apparatus characterized by comprising:

the first determination module is configured to determine an alternative search word corresponding to a currently playing video based on a historical search log and a real-time frame of the currently playing video;

and the first display module is configured to determine a target search word from the alternative search words based on the sorting result, and display the target search word in a playing interface of the currently playing video.

8. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the search term recommendation method of any one of claims 1 to 6.

9. A storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, cause the electronic device to perform the search term recommendation method of any one of claims 1 to 6.

10. A computer program product comprising readable program instructions which, when executed by a processor of an electronic device, cause the electronic device to perform the search term recommendation method of any of claims 1-6.