CN113779408A

CN113779408A - Search recommendation method and device, electronic equipment and computer-readable storage medium

Info

Publication number: CN113779408A
Application number: CN202111092510.2A
Authority: CN
Inventors: 张双翼; 杜炎睿
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2021-09-17
Filing date: 2021-09-17
Publication date: 2021-12-10

Abstract

The disclosure relates to a search recommendation method, a search recommendation device, an electronic device and a computer-readable storage medium. The search recommendation method comprises the following steps: acquiring a recommended search card related to a target video, wherein the target video is a video displayed in a recommended page and browsed by a user, the recommended page is used for displaying at least two recommended multimedia resources, the multimedia resources comprise videos, and the recommended search card comprises at least two recommended search terms; displaying a recommended search card on a recommendation page; and responding to the operation of clicking the recommended search word by the user, and displaying a multimedia resource search result page corresponding to the clicked recommended search word. By displaying the recommended search cards related to videos clicked and browsed by the user in the recommended pages displaying the recommended multimedia resources, search terms which may be interested in the user can be recommended to the user at a time when the search requirement of the user is strong, the possibility that the recommended content meets the requirement of the user is improved, and the calculation effectiveness of the recommended search terms is improved.

Description

Search recommendation method and device, electronic equipment and computer-readable storage medium

Technical Field

The present disclosure relates to the field of search technologies, and in particular, to a search recommendation method and apparatus, an electronic device, and a computer-readable storage medium.

Background

In the search field, a series of results related to a search term can be found by inputting the search term, but a user sometimes cannot input an accurate search term. For short video distribution platforms, to solve this problem, there is a scheme of mining search terms that may be of interest to a user from search terms used by the user or videos consumed. According to the scheme, the search words are usually actively recommended to the user when the user initiates the search, however, compared with the current search initiation, the historical search behavior and the historical consumption behavior based on the recommended search words may have already been subjected to a long period of time, so that the recommended search words do not accord with the current search requirements of the user, even if the search words are recommended, the user does not adopt the recommended search words, and the waste of calculation amount is caused.

Disclosure of Invention

The present disclosure provides a search recommendation method, apparatus, electronic device, and computer-readable storage medium, to solve at least the problem in the related art that recommended content does not meet user requirements, and may not solve any of the above problems.

According to a first aspect of the present disclosure, there is provided a search recommendation method including: acquiring a recommended search card related to a target video, wherein the target video is a video displayed in a recommended page and browsed by a user, the recommended page is used for displaying at least two multimedia resources, the multimedia resources comprise videos, and the recommended search card comprises at least two recommended search words; displaying the recommended search card on the recommended page; responding to the operation of clicking the recommended search word by the user, and displaying a multimedia resource search result page corresponding to the clicked recommended search word.

Optionally, the step of obtaining the recommended search card related to the target video includes: and responding to a first returning operation of returning to the recommendation page from the browsing page of the target video, and acquiring the recommendation search card related to the target video.

Optionally, the step of displaying the recommended search card on the recommendation page includes: displaying the recommended search card in a target area of the recommended page, wherein the target area is a display area of the target video or an area adjacent to the display area of the target video.

Optionally, the target area is a cover area overlaid on a display area of the target video; or the target area is an area connected below a display area of the target video.

Optionally, in a case where the target area is an area adjacent to a display area of the target video, the step of displaying the recommended search card in the target area of the recommended page includes: and determining that the size of the target area is larger than a set size, and displaying the recommended search card in the target area.

Optionally, the step of displaying the recommended search card in the target area of the recommendation page includes: and determining that a trigger condition is met, and displaying the recommended search card on the recommended page.

Optionally, the trigger condition comprises at least one of: the method comprises an anti-interference triggering condition and an effectiveness triggering condition, wherein the anti-interference triggering condition is a condition which needs to be met by reducing user interference, and the effectiveness triggering condition is a condition which needs to be met by predicting that the recommended search card can be clicked.

Optionally, the tamper-proof trigger condition comprises at least one of: the number of the recommended search cards which are displayed in an accumulated mode in the same recommended page is smaller than or equal to a first set number, and the number of the recommended search cards which are displayed in an accumulated mode for the same user in a statistical period is smaller than or equal to a second set number.

Optionally, the validity trigger condition comprises at least one of: the number of the recommended search words in the recommended search card is greater than or equal to a set number, the playing time of the target video is greater than or equal to a set time, and the predicted click rate of the recommended search card is greater than or equal to a set click rate.

Optionally, in a case that the trigger condition includes that the predicted click rate of the recommended search card is greater than or equal to a set click rate, the search recommendation method further includes: acquiring user information; and determining the predicted click rate according to at least one of the target video, the at least two recommended search terms and the user information.

Optionally, the recommended search card further includes recommended images corresponding to the at least two recommended search terms one to one, where the recommended images are cover images of the first video corresponding to the corresponding recommended search terms.

Optionally, the at least two recommended search terms differ in semantics.

Optionally, the search recommendation method further includes: and responding to a second returning operation of returning the recommended page from the multimedia resource search result page, and displaying the recommended page.

According to a second aspect of the present disclosure, there is provided a search recommendation apparatus including: an acquisition unit configured to: acquiring a recommended search card related to a target video, wherein the target video is a video displayed in a recommended page and browsed by a user, the recommended page is used for displaying at least two multimedia resources, the multimedia resources comprise videos, and the recommended search card comprises at least two recommended search words; a recommendation unit configured to: displaying the recommended search card on the recommended page; a search unit configured to: responding to the operation of clicking the recommended search word by the user, and displaying a multimedia resource search result page corresponding to the clicked recommended search word.

Optionally, the obtaining unit is further configured to: and responding to a first returning operation of returning to the recommendation page from the browsing page of the target video, and acquiring the recommendation search card related to the target video.

Optionally, the recommending unit is further configured to: displaying the recommended search card in a target area of the recommended page, wherein the target area is a display area of the target video or an area adjacent to the display area of the target video.

Optionally, in a case where the target area is an area adjacent to a display area of the target video, the recommending unit is further configured to: and determining that the size of the target area is larger than a set size, and displaying the recommended search card in the target area.

Optionally, the recommending unit is further configured to: and determining that a trigger condition is met, and displaying the recommended search card on the recommended page.

Optionally, in a case that the trigger condition includes that the predicted click rate of the recommended search card is greater than or equal to a set click rate, the obtaining unit is further configured to: acquiring user information; the search recommendation apparatus further includes a prediction unit configured to: and determining the predicted click rate according to at least one of the target video, the at least two recommended search terms and the user information.

Optionally, the at least two recommended search terms differ in semantics.

Optionally, the search recommendation apparatus further includes a display unit configured to: and responding to a second returning operation of returning the recommended page from the multimedia resource search result page, and displaying the recommended page.

According to a third aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; at least one memory storing computer-executable instructions, wherein the computer-executable instructions, when executed by the at least one processor, cause the at least one processor to perform a search recommendation method according to the present disclosure.

According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium in which instructions, when executed by at least one processor, cause the at least one processor to perform a search recommendation method according to the present disclosure.

According to a fifth aspect of the present disclosure, there is provided a computer program product comprising computer instructions which, when executed by at least one processor, implement a search recommendation method according to the present disclosure.

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

according to the search recommendation method and the search recommendation device disclosed by the embodiment of the disclosure, the recommended search card comprising at least two recommended search words is displayed in the recommended page displaying a plurality of recommended multimedia resources, and the recommended search words are related to videos clicked and browsed by users on the recommended page, so that search words possibly interested in the users can be recommended to the users at the time when the search demands of the users are stronger, the possibility that the recommended contents meet the requirements of the users is improved, the calculation effectiveness of the recommended search words is increased, the search pain points of the users are solved, and the retention of the users is improved. In addition, on the user level, the user actively selects the video on the recommendation page, and after consuming the video, the consumption demand can be further positioned through interest downward exploration, so that the consumption habit of the user with strong purpose is met. The recommended search card can also provide richer experience and stronger discovery for the user, give the expectation of consumption certainty and meet the requirement that the user wants to see more related contents.

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 flowchart illustrating a search recommendation method according to an exemplary embodiment of the present disclosure.

Fig. 2 is a schematic diagram illustrating a recommended search card according to an exemplary embodiment of the present disclosure.

Fig. 3 is a schematic diagram illustrating a recommended search card according to another exemplary embodiment of the present disclosure.

Fig. 4 is a flowchart illustrating a search recommendation method according to another exemplary embodiment of the present disclosure.

Fig. 5 is a block diagram illustrating a search recommendation apparatus according to an exemplary embodiment of the present disclosure.

Fig. 6 is a block diagram of an electronic device according to an example embodiment of the present disclosure.

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 embodiments described in the following examples do not represent all embodiments 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.

In this case, the expression "at least one of the items" in the present disclosure means a case where three types of parallel expressions "any one of the items", "a combination of any plural ones of the items", and "the entirety of the items" are included. For example, "include at least one of a and B" includes the following three cases in parallel: (1) comprises A; (2) comprises B; (3) including a and B. For another example, "at least one of the first step and the second step is performed", which means that the following three cases are juxtaposed: (1) executing the step one; (2) executing the step two; (3) and executing the step one and the step two.

For the short video distribution platform, search terms or contents meeting the watching interests of the user are pushed to the user, and the stickiness of the platform and the user is enhanced. The existing search term recommendation generally mines search terms manually input by a user or a group of head search terms with higher statistical benefit based on consumption data (referring to a group of search terms with the highest searching frequency after a video is consumed), and recommends the search terms to the user when the user initiates a search. Although seemingly certain choices of search terms are provided for the user, since the time when the user sends a search is separated from the current search behavior and the probability of the video consumption behavior, the search requirement of the user is probably irrelevant to the behaviors when the search is initiated, so that the recommended search terms are not adopted, and the calculation amount for obtaining the recommended search terms is wasted.

At present, there is also a search term recommendation scheme, in which after a user inputs a search term and enters a corresponding multimedia resource search result page, no matter whether the user browses a video in the multimedia resource search result page, a search card related to the video is displayed below the individual video. Although the relevant recommendations are made according to the videos in the multimedia resource search result page after the user initiates the search, since the user does not browse the corresponding videos yet and still cannot determine whether the recommendations meet the user requirements, a higher risk of invalid recommendations also exists. Meanwhile, the short video distribution platform often has a page for actively recommending multimedia resources to a user, for example, a discovery page of a platform home page, and such a page can actively recommend multimedia resources without any search operation or action by the user. However, only multimedia resources are recommended at present, and no search entry is configured, so that browsing consumption behaviors of users on such pages can be fully utilized, search term recommendation is performed by combining videos browsed by the users, search terms which may be interested in the users can be recommended to the users at a time when the users just finish browsing and the search requirements are still strong, the possibility that the recommendation content meets the requirements of the users is improved, the calculation effectiveness of the recommended search terms is improved, the search pain points of the users are solved, and the user retention is improved.

Hereinafter, a search recommendation method and a search recommendation apparatus according to an exemplary embodiment of the present disclosure will be described in detail with reference to fig. 1 to 6.

Fig. 1 is a flowchart illustrating a search recommendation method according to an exemplary embodiment of the present disclosure. It should be understood that the search recommendation method according to the exemplary embodiment of the present disclosure may be implemented in a terminal device (as a client of a short video distribution platform) such as a smartphone, a tablet computer, a Personal Computer (PC), or may be implemented in a device (as a server of the short video distribution platform) such as a server.

Referring to fig. 1, in step 101, a recommended search card related to a target video is obtained. The target video is a video displayed in a recommendation page and browsed by a user, and the recommendation page is used for displaying at least two recommended multimedia resources, for example, a double-row recommendation page as shown in fig. 2. The multimedia resources can comprise videos, and cover pages of the videos are displayed in the recommendation page at the moment; the multimedia resources may also include live feeds, user recommendation cards, merchandise recommendation cards, and the like. When a user clicks on one of the multimedia assets, for example on a video, a browsing page of the content, usually an immersive presentation page, is entered, within which only the content is presented.

Alternatively, how to determine whether a video has been viewed by the user may be determining whether the client has played the video or analyzing the line of sight of the user. For the latter, specifically, when the client plays a video, whether the user's sight line falls on the display screen of the client is analyzed, and if so, the user is considered to be browsing the video.

Specifically, the relevant recommended search card is only acquired for the video browsed by the user, and the target video is a finished video, for example, the target video may be a video obtained by further editing a movie video, a video obtained by a producer by himself/herself shooting and editing, or an album video composed of multiple pictures. And for other contents, no search recommendation is carried out. Since the search requirement is not high after the user consumes the content, the recommendation frequency can be properly controlled, which not only helps to reduce the unnecessary calculation amount, but also can reduce the disturbance to the user.

The recommended search card comprises at least two recommended search terms, namely, the at least two recommended search terms related to the target video can be obtained, and the recommended search card is formed, so that a plurality of search choices are provided for the user. The recommended content is related to the target video, and as the video content naturally has the potential of downward mining, different characteristics can be disassembled according to the content, the content appeal of the user is clarified, the user can be assisted to further explore, and the method has certain capability of assisting the user in exploring the interest.

The acquisition of the recommended search card is essentially the acquisition of each recommended search word in the recommended search card. First, related search terms may be mined. For example, search terms input by total station users after consuming a target video are directly mined; if the content of the target video is analyzed first, search terms related to the semantics of the target video are found, for example, the title and the cover text of the target video are extracted, and then the keywords in the target video are extracted, and the method can be further expanded to related other keywords, for example, the target video is a song introduction of a singer, the name, the nickname and the song name of the singer can be extracted as the keywords, and the method can be further expanded to hot topics and new works of the singer. And recalling and sequencing the mined search terms, and taking the optimal ones as recommended search terms. During recalling and sorting, for example, the preference of the current user and the click rate of the recommended word can be combined, and sensitive word filtering can be performed. It is understood that the number of the target videos may be at least one, that is, the recommended search card may be obtained in combination with at least one video browsed by the user in the recommendation page. For the condition that a plurality of target videos are available, centralized recommendation can be performed after the plurality of videos are browsed, so that the exposure times of recommending search cards are reduced, and the interference to users is reduced. For the case that the target video is one, a plurality of search terms can be recommended for the one video, and coverage and diversity of the search terms are increased. As an example, at least one target video may be selected from all videos browsed by the user in the recommendation page, for example, several videos recently browsed by the user may be selected, and specifically, one video recently browsed by the user may be selected; and if the user browses at least one video with longer time, the user can be preferentially selected. After the target videos are determined, at least one recommended search word can be acquired for each target video, and then the recommended search words corresponding to each target video are collected to obtain recommended search cards. Of course, when a plurality of target videos are selected, the number of recommended search terms obtained for each target video may be equal or unequal, for example, the longer the browsing time of the target video by the user is, the more recommended search terms are obtained correspondingly. The foregoing is merely an exemplary illustration, and the disclosure is not limited thereto for specific acquisition schemes.

Optionally, the number of recommended search terms included in the recommended search card may be selected comprehensively according to the size, the display effect, and the like of an actually available display area (for example, a target area in an embodiment shown in fig. 4) in the recommended page, so that the occurrence of a situation that the recommended search terms overflow the display area due to too many recommended search terms is avoided, normal consumption of other contents in the recommended page is guaranteed, and the number of recommended search terms is sufficient to improve the click rate and achieve effective recommendation.

Optionally, the semantics of at least two recommended search terms are different, so that the diversity of the recommended search terms can be improved, and the resource waste caused by repeated semantics can be reduced. Fig. 2 is a schematic diagram illustrating a recommended search card according to an exemplary embodiment of the present disclosure. Referring to fig. 2, for example, the target video is a production video of fish-flavored shredded meat, and the recommended search words included in the recommended search card 201 may include fish-flavored shredded meat, pepper mushrooms, diced chicken bouillon, and home vegetables of the fish-flavored shredded meat, which have different semantics. This object can be achieved in particular at the stage of recalling a search term, i.e. only one of a plurality of search terms having the same semantic meaning can be retained.

Optionally, the recommended search card further includes recommended images corresponding to the at least two recommended search terms one to one, and the recommended image is a cover image of the first video corresponding to the corresponding recommended search term. When a user initiates a search based on a recommended search term, the user jumps to a corresponding multimedia resource search result page, and a plurality of multimedia resources related to the search term, including videos, are displayed in the page. By introducing the cover page image of the first related video corresponding to each recommended search word into the recommended search card, the user can sense the meaning of each recommended search word more intuitively, and the user can be facilitated to make a decision. Fig. 3 is a schematic diagram illustrating a recommended search card according to another exemplary embodiment of the present disclosure. Referring to fig. 3, a recommended search card 301 includes 5 recommended search words and corresponding recommended images.

It can be understood that, if the search recommendation method of the exemplary embodiment of the present disclosure is implemented in the client, the recommended search card may be obtained from the server, that is, the server calculates and determines the recommended search card and then issues the recommended search card to the client, or the recommended search card may be calculated by the client when the computing power of the client is sufficient; if the search card is implemented in the server, the recommended search card can be calculated and determined by the server.

At step 102, a recommended search card is displayed on a recommendation page. The user usually views the multimedia resources in the recommendation page in a manner of sliding the recommendation page, and it is the time when the user has a browsing demand but has no clear browsing target. The acquired recommended search card is additionally displayed while the recommended page is displayed, which is equivalent to displaying the recommended page comprising the recommended search card, so that search words which may be interested in the user can be timely recommended to the user, the user is assisted in clearly browsing the target, the consumption habit of the user with strong purpose is met, the possibility that the recommended content meets the user requirement is improved, the calculation effectiveness of the recommended search words is improved, the user pain point is solved, and the user retention is facilitated. For example, a certain space may be made available between two adjacent multimedia resources for displaying the recommended search card, or a cover layer may be used on the display area of a video that has just been browsed, and the recommended search card may be displayed in the cover layer area.

It can be understood that, if the search recommendation method of the exemplary embodiment of the present disclosure is implemented in the client, a recommendation page including a recommended search card may be displayed at the client; if the recommendation method is implemented in the server, the contents, the display positions and the display commands of the recommendation page and the recommendation search card can be issued to the client together, and the client is instructed to perform corresponding display. In addition, the displayed word number can be automatically adapted by the client according to the model, and characters which cannot be displayed after exceeding the limit can be replaced by symbols such as ellipses and the like.

In step 103, in response to the operation of clicking the recommended search term by the user, a multimedia resource search result page corresponding to the clicked recommended search term is displayed. The recommended search words in the recommended search card are configured into links which can be clicked by the user, so that a search entry can be directly formed in the recommended search words, the search operation path is shortened, and the user can conveniently and directly initiate search.

It can be understood that, if the search recommendation method of the exemplary embodiment of the present disclosure is implemented in the client, the operation of clicking a recommended search word performed by the user at the client may be directly detected, and the corresponding content of the multimedia resource search result page is requested from the server, and then the multimedia resource search result page issued by the server is displayed at the client; if the search is realized in the server, the information that the user clicks the recommended search word uploaded by the client can be received, the corresponding content of the multimedia resource search result page is sent to the client, and the client is instructed to perform corresponding display.

Referring to fig. 4, in step 401, in response to a first return operation from a browsing page of a target video to a recommendation page, a recommended search card related to the target video is acquired. This step is different from step 101 shown in fig. 1 in that the timing to acquire the recommended search card is specifically determined as the timing to return to the recommended page from the browsing page of the target video. It can be understood that the target video is only one, that is, the video browsed by the user in the recommended page last click, and when the user finishes browsing and executes the first return operation, the browsed page of the video, for example, the immersive presentation page, is exited and returned to the recommended page. The detected first returning operation is used as the time for searching and recommending, so that the consumption of the user on the immersive display page is not interrupted, the search terms which may be interested in can be recommended to the user at the time when the search requirement of the user is the strongest, and the possibility that the recommended content meets the requirement of the user is improved.

Specifically, the target video is a finished video, and may be, for example, a video obtained by further editing a movie video, a video obtained by a producer who takes a picture of the video, or an album video composed of a plurality of pictures. Optionally, the first returning operation does not include an operation of returning the content, such as the user's live broadcast, user recommendation, and commodity recommendation, to the recommendation page, that is, when the user consumes such content, the user returns to the recommendation page, and no search recommendation is performed. Since the search requirement is not high after the user consumes the content, the recommendation frequency can be properly controlled, which not only helps to reduce the unnecessary calculation amount, but also can reduce the disturbance to the user.

It can be understood that, if the search recommendation method of the exemplary embodiment of the present disclosure is implemented in the client, the first return operation executed by the user at the client may be directly detected, and the recommended search card may be obtained from the server, that is, the server calculates and determines the recommended search card and then issues the recommended search card to the client, or the recommended search card may be calculated by the client when the client has sufficient calculation capability; if the search card recommendation is realized in the server, the information of the first return operation uploaded by the client can be received, and the server calculates and determines the recommended search card.

At step 402, a recommended search card is displayed in a target area of a recommendation page. With reference to fig. 2, alternatively, the target area may be a display area of the target video, that is, a recommended search card is displayed by using an area of the recommended page where the target video is originally displayed, for example, a cover layer may be used in the area, and the recommended search card is displayed in the cover layer area. At the moment, other areas in the recommendation page do not need to be occupied, the maximization of the display content in the recommendation page can be guaranteed, and the probability that the user consumes the target video again is low, so that the normal consumption of the user is not influenced. Alternatively, the target area may be an area adjacent to the display area of the target video. Referring to fig. 3, an area connected below the display area of the target video may be set as a target area in conformity with the viewing habits of the user.

Optionally, in a case that the target area is an area adjacent to the display area of the target video, the target area of the recommended page does not necessarily have a sufficient display space, and at this time, step 402 may be specifically performed as: and determining that the size of the target area is larger than the set size, and displaying the recommended search card in the target area. The size is set to, for example, 0, that is, when there is no space available in the recommendation page to use as the target area, no corresponding recommendation is made. Taking the example that the target area is an area connected below the display area of the target video, no recommendation is made when the lower boundary of the display area is just at the lower boundary of the recommended page. It is understood that, when only a part of the target video is shown in the recommendation page, the lower boundary of the display area is the lower boundary of the part displayed in the target video, and therefore, the case where the size of the target area is 0 is included, and no recommendation is made.

It can be understood that, if the search recommendation method of the exemplary embodiment of the present disclosure is implemented in the client, the recommended search card may be directly displayed when the size of the target area is larger than the set size, otherwise, the recommended search card is not displayed; if the method is realized in the server, the contents, the display positions and the display commands of the recommendation page and the recommended search card can be issued to the client together when the size of the target area is larger than the set size, the client is indicated to perform corresponding display, and otherwise, the client is not issued directly. Furthermore, when the size of the target area is smaller than or equal to the set size, the calculation and determination of the recommended search card may not be directly performed in step 401, for the client, the information of the first return operation may not be directly uploaded to the server, or the information of the target area with the too small size may be uploaded while the information of the first return operation is uploaded, so as to notify the server that the recommended calculation does not need to be performed; for the server, the information of the first return operation and the size information of the target area uploaded by the client can be received, and when the size of the target area is judged to be too small, the recommendation calculation is not executed. This helps to substantially reduce the amount of computation. Of course, the recommended search card may also be determined by normal calculation, and the size of the target area is determined by the display stage of step 402 to determine whether to display the recommended search card. For the client, the relevant information of the recommended search card may not be received, or the information may not be displayed after being received. For the server, the relevant information of the recommended search card is not sent to the client after calculation, or an instruction which is not needed to be displayed is sent while the information is sent. Regardless of whether the recommended search card is displayed, it is necessary to display the recommended page in response to the first return operation, with the only difference being whether the recommended search card is included in the displayed recommended page. That is, the exemplary embodiments of the present disclosure only define that the recommended search card is displayed in the target area of the recommended page when the size of the target area is larger than the set size, but for the case where the size of the target area is too small, specific steps are only executed without limitation as long as the result that the recommended search card is not displayed when the size of the target area is too small can be achieved.

In step 403, in response to the operation of clicking the recommended search term by the user, a multimedia resource search result page corresponding to the clicked recommended search term is displayed. This step is the same as step 103 shown in fig. 1, and is not described herein.

As an example, optionally, similar to the embodiment of determining the size of the target area in step 402, either step 102 as shown in fig. 1 or step 402 as shown in fig. 4, may be performed as: and determining that the trigger condition is met, and displaying the recommended search card on the recommended page. The user will not have a need to initiate a related search after consuming the video. By configuring the trigger condition, search word recommendation can be selectively performed, exposure times of recommended search cards are controlled, calculation burden is reduced, recommendation pertinence is improved, and accordingly the bit ratio of the recommended search cards is improved. It can be understood that, for the case where the trigger condition and the size condition of the target area are required, the two conditions need to be satisfied simultaneously for the search term recommendation.

Optionally, the trigger condition comprises at least one of:

firstly, preventing interference triggering conditions. Such trigger conditions are set to reduce the interference of the recommended search card to the user, and may be specifically realized by reducing the number of recommendations, that is, reducing the cumulative number of times of displaying the recommended search card (i.e., reducing the exposure amount). The tamper-proof trigger condition may specifically include at least one of: the number of the recommended search cards which are displayed in an accumulated mode in the same recommended page is smaller than or equal to a first set number, and the number of the recommended search cards which are displayed in an accumulated mode for the same user in a statistical period is smaller than or equal to a second set number. The two conditions count the exposure number from different dimensions, so that the user is prevented from being disturbed by excessive exposure, and the point ratio is improved.

And II, validity triggering conditions. Such trigger conditions are set to achieve effective recommendations and are only displayed when the predicted user clicks on the recommended search card.

1. The number of recommended search terms included in the recommended search card is greater than or equal to a set number. The value of the set number may range from 2 to 6, for example. When the number of the acquired recommended search words is small, the coverage is considered to be poor, the search requirement of the user is often not met, and the recommendation income is low. At the moment, corresponding recommendation is not made, and the recommendation effectiveness is improved.

2. The playing time length of the target video is larger than or equal to the set time length. If the playing time of the target video is short, the user has no interest in the video with high probability and has no need of further searching. By configuring the set duration, the method is beneficial to screening out videos which are possibly interested by the user, and is beneficial to improving the effectiveness of recommendation. For the case that the number of the target videos is multiple, specifically, the playing time length of each target video may be greater than or equal to the set time length. Of course, referring to the foregoing description of how to obtain the recommended search card in step 101, the condition that the playing time length is greater than or equal to the set time length may be directly used as the condition for screening the target video.

3. And the predicted click rate of the recommended search card is greater than or equal to the set click rate. By predicting the click rate of the recommended search card and comparing the predicted click rate with the set click rate, the decision of whether to recommend can be made more intuitively.

Optionally, for a trigger condition that the predicted click rate of the recommended search card is greater than or equal to the set click rate, as an example, the search recommendation method according to the exemplary embodiment of the present disclosure may further include: acquiring user information; and determining the predicted click rate according to at least one of the target video, all recommended search terms and the user information. The target video is content directly consumed by the user, and if most users initiate a search after consuming the video, it can be estimated that the current user is also likely to initiate the search. The recommended search terms are the core of initiating the search, and if the consumption level of the recommended search terms per se at the total station is high, the possibility that the current user is interested in the recommended search terms can be estimated to be high. The user information reflects the personal interests and hobbies of the user, and if the target video conforms to the interests and hobbies of the user, for example, the user likes makeup videos, and the target video is just makeup, the possibility that the current user conducts further related search is estimated to be high. Of course, in the case that the number of the target videos is multiple, each target video needs to be predicted by combining the recommended search terms related to the target video. The prediction may be specifically performed in combination with a prediction model, for example, the probability that the recommended search card is clicked may be predicted from three dimensions of the search feature of the target video, the consumption feature of all recommended search terms, and the interest feature of the user, or the prediction model of the click rate may be trained by using a certain amount of posterior consumption data including a point ratio as a sample for the displayed recommended search card after collecting the posterior consumption data, and the disclosure is not limited specifically herein.

It can be understood that, if the search recommendation method of the exemplary embodiment of the present disclosure is implemented in the client, the recommended search card may be directly displayed when the trigger condition is satisfied, and may not be displayed when the trigger condition is not satisfied; if the method is realized in the server, the contents, the display positions and the display commands of the recommendation page and the recommended search card can be issued to the client together when the triggering condition is met, the client is indicated to perform corresponding display, and the recommendation page and the recommended search card are not issued directly when the triggering condition is not met. Furthermore, when the specific content of the recommended search card is not involved, for example, when the number of the recommended search cards which are accumulatively displayed in the same recommended page is not less than or equal to the first set number, the number of the recommended search cards which are accumulatively displayed for the same user in one statistical period is less than or equal to the second set number, and the playing time length of the target video is greater than or equal to any one of the set time lengths, the size condition of the target area may be referred to, the calculation and the determination of the recommended search card are not directly performed, or the recommended search card is still calculated and determined, and the judgment is performed by combining various trigger conditions in the display stage, which is not described herein again. That is, the exemplary embodiments of the present disclosure only define that the recommended search card is displayed on the recommended page when the trigger condition is satisfied, but do not limit which steps are specifically executed when the trigger condition is not satisfied, and the result of the recommended search card is not displayed as long as the trigger condition is not satisfied.

As an example, optionally, for the embodiments shown in fig. 1 and 4, after the multimedia resource search result page is displayed, the search recommendation method of the exemplary embodiment of the present disclosure may further include: and responding to a second returning operation of returning the recommendation page from the multimedia resource search result page, and displaying the recommendation page. By configuring the second return operation, the user can conveniently return to the initial recommendation page, so that the user can continue to return to the recommendation page to browse the content therein. For example, the second returning operation may be an operation of returning to the previous page step by step, or a button for directly returning to the recommended page may be configured, specifically, the second returning operation may be a virtual button, or an existing physical button of the client may be borrowed, and then the second returning operation is an operation of triggering the button, and the one-key returning to the recommended page may be implemented.

Experiments prove that by adopting the search recommendation method of the exemplary embodiment of the disclosure, the platform service time of a user can be prolonged, the number of active users of the platform is increased, and the next-day retention of a recommendation page is improved in the aspect of a short video distribution platform; from the aspect of the search side, the user penetration of the search function and the search card recommending function can be increased, function retention is improved, more platform users can use the search function and the search card recommending function, the guide scale of the search function can be improved, the number of times of initiating search in the platform is increased, the exposure and the point ratio of the recommended search card can be balanced and improved, and the coverage and the correlation of the recommended search words are considered.

Fig. 5 is a block diagram illustrating a search recommendation apparatus according to an exemplary embodiment of the present disclosure. It should be understood that the search recommendation apparatus according to the exemplary embodiments of the present disclosure may be implemented in a terminal device (as a client of a short video distribution platform) such as a smartphone, a tablet computer, a Personal Computer (PC) in a software, hardware, or software and hardware combination manner, and may also be implemented in a device (as a server of the short video distribution platform) such as a server.

Referring to fig. 5, the search recommendation apparatus 500 includes an acquisition unit 501, a recommendation unit 502, and a search unit 503.

The acquisition unit 501 may acquire a recommended search card related to a target video. The target video is a video displayed in a recommendation page and browsed by a user, and the recommendation page is used for displaying at least two recommended multimedia resources, for example, a double-row recommendation page as shown in fig. 2. The multimedia resources can comprise videos, and cover pages of the videos are displayed in the recommendation page at the moment; the multimedia resources may also include live feeds, user recommendation cards, merchandise recommendation cards, and the like. When a user clicks on one of the multimedia assets, for example on a video, a browsing page of the content, usually an immersive presentation page, is entered, within which only the content is presented.

It is understood that the number of the target videos may be at least one, that is, the recommended search card may be obtained in combination with at least one video browsed by the user in the recommendation page. For the condition that a plurality of target videos are available, centralized recommendation can be performed after the plurality of videos are browsed, so that the exposure times of recommending search cards are reduced, and the interference to users is reduced. For the case that the target video is one, a plurality of search terms can be recommended for the one video, and coverage and diversity of the search terms are increased.

It can be understood that, if the search recommendation apparatus 500 of the exemplary embodiment of the present disclosure is implemented in a client, the obtaining unit 501 may obtain the recommended search card from the server, that is, the server calculates and determines the recommended search card and then issues the recommended search card to the client, or the recommended search card may be calculated by the client when the computing power of the client is sufficient; if the search card is implemented in the server, the recommended search card can be calculated and determined by the server.

The recommendation unit 502 may display the recommended search card on a recommendation page. The user usually views the multimedia resources in the recommendation page in a manner of sliding the recommendation page, and it is the time when the user has a browsing demand but has no clear browsing target. By additionally displaying the acquired recommended search card while displaying the recommended page, which is equivalent to displaying the recommended page including the recommended search card, the recommending unit 502 can timely recommend search words which may be interested to the user to assist the user in defining browsing targets and meet the consumption habits of the user with strong purposes, so that the possibility that the recommended content meets the user requirements is improved, the calculation effectiveness of the recommended search words is increased, the pain points of the user are solved, and the user retention is facilitated.

It is understood that, if the search recommendation apparatus 500 of the exemplary embodiment of the present disclosure is implemented in a client, the recommendation unit 502 may display a recommendation page including a recommended search card on the client; if the recommendation is implemented in the server, the recommendation unit 502 may issue the recommendation page and the content, the display position, and the display command of the recommended search card to the client, and instruct the client to perform corresponding display. In addition, the displayed word number can be automatically adapted by the client according to the model, and characters which cannot be displayed after exceeding the limit can be replaced by symbols such as ellipses and the like.

The search unit 503 may display a multimedia resource search result page corresponding to the clicked recommended search term in response to an operation of clicking the recommended search term by the user. The recommended search words in the recommended search card are configured into links which can be clicked by the user, so that a search entry can be directly formed in the recommended search words, the search operation path is shortened, and the user can conveniently and directly initiate search.

It can be understood that, if the search recommendation apparatus 500 of the exemplary embodiment of the present disclosure is implemented in a client, the search unit 503 may directly detect an operation of clicking a recommended search word performed by a user at the client, request corresponding content of a multimedia resource search result page from a server, and then display the multimedia resource search result page delivered by the server at the client; if the search is implemented in the server, the search unit 503 may receive information that is uploaded by the client and that the user clicks the recommended search term, and issue the content of the corresponding multimedia resource search result page to the client to instruct the client to perform corresponding display.

As an example, optionally, the obtaining unit 501 may further obtain the recommended search card related to the target video in response to a first return operation of returning to the recommendation page from the browsing page of the target video. The action of the acquisition unit 501 at this time is different from the aforementioned action in that the timing of acquiring the recommended search card is specifically determined as the timing of returning to the recommended page from the browsing page of the target video. It can be understood that the target video is only one, that is, the video browsed by the user in the recommended page last click, and when the user finishes browsing and executes the first return operation, the browsed page of the video, for example, the immersive presentation page, is exited and returned to the recommended page. The detected first returning operation is used as the time for searching and recommending, so that the consumption of the user on the immersive display page is not interrupted, the search terms which may be interested in can be recommended to the user at the time when the search requirement of the user is the strongest, and the possibility that the recommended content meets the requirement of the user is improved.

It is understood that, if the search recommendation apparatus 500 of the exemplary embodiment of the present disclosure is implemented in a client, the obtaining unit 501 may directly detect a first return operation performed by a user at the client; if the search is implemented in the server, the obtaining unit 501 may receive information of the first return operation uploaded by the client, and the server calculates and determines the recommended search card.

In combination with the recommendation opportunity, the recommendation unit 502 may further display the recommended search card in the target area of the recommendation page when the recommended search card is displayed. With reference to fig. 2, alternatively, the target area may be a display area of the target video, that is, a recommended search card is displayed by using an area of the recommended page where the target video is originally displayed, for example, a cover layer may be used in the area, and the recommended search card is displayed in the cover layer area. At the moment, other areas in the recommendation page do not need to be occupied, the maximization of the display content in the recommendation page can be guaranteed, and the probability that the user consumes the target video again is low, so that the normal consumption of the user is not influenced. Alternatively, the target area may be an area adjacent to the display area of the target video. Referring to fig. 3, an area connected below the display area of the target video may be set as a target area in conformity with the viewing habits of the user.

Alternatively, in a case where the target area is an area adjacent to the display area of the target video, the target area of the recommendation page does not necessarily have a sufficient display space, and the recommendation unit 502 may specifically perform: and determining that the size of the target area is larger than the set size, and displaying the recommended search card in the target area. The size is set to, for example, 0, that is, when there is no space available in the recommendation page to use as the target area, no corresponding recommendation is made. Taking the example that the target area is an area connected below the display area of the target video, no recommendation is made when the lower boundary of the display area is just at the lower boundary of the recommended page. It is understood that, when only a part of the target video is shown in the recommendation page, the lower boundary of the display area is the lower boundary of the part displayed in the target video, and therefore, the case where the size of the target area is 0 is included, and no recommendation is made.

It is understood that, if the search recommendation apparatus 500 of the exemplary embodiment of the present disclosure is implemented in a client, the recommendation unit 502 may directly display the recommended search card when the size of the target area is larger than a set size, otherwise, not display it; if the recommendation is implemented in the server, the recommendation unit 502 may issue the content, the display position, and the display command of the recommendation page and the recommended search card to the client together when the size of the target area is larger than the set size, and instruct the client to perform corresponding display, otherwise, directly not issue the recommendation. Furthermore, when the size of the target area is smaller than or equal to the set size, the calculation and determination of the recommended search card may not be directly performed, and for the client, the obtaining unit 501 may not directly upload the information of the first return operation to the server, or may upload the information of the target area with the size being too small while uploading the information of the first return operation, so as to notify the server that the recommended calculation is not necessarily performed; for the server, the information of the first return operation and the size information of the target area uploaded by the client can be received, and when the size of the target area is judged to be too small, the recommendation calculation is not executed. This helps to substantially reduce the amount of computation. Of course, the recommended search card may also be determined by normal calculation, and the recommendation unit 502 performs size determination of the target area to determine whether to display the recommended search card. For the client, specifically, the relevant information of the recommended search card may not be received, or the recommendation unit 502 does not display after receiving. For the server, the recommendation unit 502 may not issue the information related to the recommended search card to the client after the calculation, or the recommendation unit 502 may issue an instruction that is not needed to be displayed while issuing the information. Regardless of whether the recommended search card is displayed, it is necessary to display the recommended page in response to the first return operation, with the only difference being whether the recommended search card is included in the displayed recommended page. That is, the exemplary embodiment of the present disclosure only defines that the recommendation unit 502 displays the recommended search card in the target area of the recommendation page when the size of the target area is larger than the set size, but for the case that the size of the target area is too small, it is not limited to specifically which steps are only executed as long as the result that the recommended search card is not displayed when the size of the target area is too small can be achieved.

As an example, optionally, similar to the embodiment in which the recommending unit 502 determines the size of the target area, the recommending unit 502 may further perform: and determining that the trigger condition is met, and displaying the recommended search card on the recommended page. The user will not have a need to initiate a related search after consuming the video. By configuring the trigger condition, search word recommendation can be selectively performed, exposure times of recommended search cards are controlled, calculation burden is reduced, recommendation pertinence is improved, and accordingly the bit ratio of the recommended search cards is improved. It can be understood that, for the case where the trigger condition and the size condition of the target area are required, the two conditions need to be satisfied simultaneously for the search term recommendation.

Optionally, the trigger condition comprises at least one of:

2. The playing time length of the target video is larger than or equal to the set time length. If the playing time of the target video is short, the user has no interest in the video with high probability and has no need of further searching. By configuring the set duration, the method is beneficial to screening out videos which are possibly interested by the user, and is beneficial to improving the effectiveness of recommendation. For the case that the number of the target videos is multiple, specifically, the playing time length of each target video may be greater than or equal to the set time length. Of course, the condition that the playing time length is greater than or equal to the set time length can also be directly used as the condition for screening the target video.

Optionally, for a trigger condition that the predicted click rate of the recommended search card is greater than or equal to the set click rate, as an example, the obtaining unit 501 may further obtain user information, and the search recommendation apparatus 500 according to an exemplary embodiment of the present disclosure may further include a prediction unit (not shown in the figure) that may determine the predicted click rate according to at least one of the target video, all recommended search terms, and the user information. The target video is content directly consumed by the user, and if most users initiate a search after consuming the video, it can be estimated that the current user is also likely to initiate the search. The recommended search terms are the core of initiating the search, and if the consumption level of the recommended search terms per se at the total station is high, the possibility that the current user is interested in the recommended search terms can be estimated to be high. The user information reflects the personal interests and hobbies of the user, and if the target video conforms to the interests and hobbies of the user, for example, the user likes makeup videos, and the target video is just makeup, the possibility that the current user conducts further related search is estimated to be high. Of course, in the case that the number of the target videos is multiple, each target video needs to be predicted by combining the recommended search terms related to the target video. The prediction of the prediction unit may be specifically performed in combination with a prediction model, for example, the probability that the recommended search card is clicked may be predicted from three dimensions of the search feature of the target video, the consumption feature of all recommended search terms, and the interest feature of the user, or, for the displayed recommended search card, after a certain amount of posterior consumption data including a point ratio is collected, the posterior consumption data is used as a sample, and the prediction model of the click rate is trained, which is not specifically limited in this disclosure.

It is understood that, if the search recommendation apparatus 500 of the exemplary embodiment of the present disclosure is implemented in a client, the recommendation unit 502 may directly display the recommended search card when the trigger condition is satisfied, and not display the recommended search card when the trigger condition is not satisfied; if the recommendation is implemented in the server, the recommendation unit 502 may issue the recommendation page and the content, the display position, and the display command of the recommended search card to the client together when the trigger condition is satisfied, instruct the client to perform corresponding display, and directly not issue the recommendation page and the recommended search card when the trigger condition is not satisfied. Furthermore, when the specific content of the recommended search card is not involved, for example, when the number of the recommended search cards that are accumulatively displayed in the same recommended page is not less than or equal to the first set number, the number of the recommended search cards that are accumulatively displayed for the same user in one statistical period is less than or equal to the second set number, or the playing duration of the target video is greater than or equal to any one of the set durations, the size condition of the target area may be referred to, the calculation and determination of the recommended search card may not be directly performed, or the recommended search card may still be determined by calculation, and the recommendation unit 502 determines whether to display the recommended search card by combining with each trigger condition, which is not described herein again. That is, the exemplary embodiment of the present disclosure only defines that the recommendation unit 502 displays the recommended search card on the recommendation page when the trigger condition is satisfied, but does not specifically limit which steps are executed when the trigger condition is not satisfied, and does not display the result of the recommended search card as long as the trigger condition is not satisfied.

As an example, optionally, the search recommendation apparatus 500 of an exemplary embodiment of the present disclosure may further include a display unit (not shown in the figure), and may display the recommendation page in response to a second return operation of returning the recommendation page from the multimedia resource search result page after the search unit 503 displays the multimedia resource search result page. By configuring the second return operation, the user can conveniently return to the initial recommendation page, so that the user can continue to return to the recommendation page to browse the content therein. For example, the second returning operation may be an operation of returning to the previous page step by step, or a button for directly returning to the recommended page may be configured, specifically, the second returning operation may be a virtual button, or an existing physical button of the client may be borrowed, and then the second returning operation is an operation of triggering the button, and the one-key returning to the recommended page may be implemented.

Referring to fig. 6, an electronic device 600 includes at least one memory 601 and at least one processor 602, the at least one memory 601 having stored therein a set of computer-executable instructions that, when executed by the at least one processor 602, perform a search recommendation method according to an exemplary embodiment of the present disclosure.

By way of example, the electronic device 600 may be a PC computer, tablet device, personal digital assistant, smartphone, or other device capable of executing the set of instructions described above. Here, the electronic device 600 need not be a single electronic device, but can be any arrangement or collection of circuits capable of executing the above-described instructions (or sets of instructions), either individually or in combination. The electronic device 600 may also be part of an integrated control system or system manager, or may be configured as a portable electronic device that interfaces with local or remote (e.g., via wireless transmission).

In the electronic device 600, the processor 602 may include a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a programmable logic device, a special purpose processor system, a microcontroller, or a microprocessor. By way of example, and not limitation, processors may also include analog processors, digital processors, microprocessors, multi-core processors, processor arrays, network processors, and the like.

The processor 602 may execute instructions or code stored in the memory 601, wherein the memory 601 may also store data. The instructions and data may also be transmitted or received over a network via a network interface device, which may employ any known transmission protocol.

The memory 601 may be integrated with the processor 602, for example, with RAM or flash memory disposed within an integrated circuit microprocessor or the like. Further, memory 601 may comprise a stand-alone device, such as an external disk drive, storage array, or any other storage device usable by a database system. The memory 601 and the processor 602 may be operatively coupled or may communicate with each other, e.g., through I/O ports, network connections, etc., such that the processor 602 can read files stored in the memory.

Further, the electronic device 600 may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, mouse, touch input device, etc.). All components of the electronic device 600 may be connected to each other via a bus and/or a network.

According to an exemplary embodiment of the present disclosure, there may also be provided a computer-readable storage medium, in which instructions, when executed by at least one processor, cause the at least one processor to perform a search recommendation method according to an exemplary embodiment of the present disclosure. Examples of the computer-readable storage medium herein include: read-only memory (ROM), random-access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random-access memory (RAM), dynamic random-access memory (DRAM), static random-access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD + R, CD-RW, CD + RW, DVD-ROM, DVD-R, DVD + R, DVD-RW, DVD + RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or compact disc memory, Hard Disk Drive (HDD), solid-state drive (SSD), card-type memory (such as a multimedia card, a Secure Digital (SD) card or a extreme digital (XD) card), magnetic tape, a floppy disk, a magneto-optical data storage device, an optical data storage device, a hard disk, a magnetic tape, a magneto-optical data storage device, a hard disk, a magnetic tape, a magnetic data storage device, a magnetic tape, a magnetic data storage device, a magnetic tape, a magnetic data storage device, a magnetic tape, a magnetic data storage device, a magnetic tape, a magnetic data storage device, A solid state disk, and any other device configured to store and provide a computer program and any associated data, data files, and data structures to a processor or computer in a non-transitory manner such that the processor or computer can execute the computer program. The computer program in the computer-readable storage medium described above can be run in an environment deployed in a computer apparatus, such as a client, a host, a proxy device, a server, and the like, and further, in one example, the computer program and any associated data, data files, and data structures are distributed across a networked computer system such that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed fashion by one or more processors or computers.

According to an exemplary embodiment of the present disclosure, there may also be provided a computer program product including computer instructions which, when executed by at least one processor, cause the at least one processor to perform a search recommendation method according to an exemplary embodiment of the present disclosure.

According to the search recommendation method and the search recommendation device of the exemplary embodiment of the disclosure, the recommended search card including at least two recommended search words is displayed in the recommended page showing a plurality of recommended multimedia resources, and the recommended search words are related to the videos clicked and browsed by the user on the recommended page, so that the search words possibly interested in the user can be recommended to the user at the time when the user search requirement is strong, the possibility that the recommended content meets the user requirement is improved, the calculation effectiveness of the recommended search words is increased, the search pain points of the user are solved, and the user retention is facilitated to be improved. In addition, on the user level, the user actively selects the video on the recommendation page, and after consuming the video, the consumption demand can be further positioned through interest downward exploration, so that the consumption habit of the user with strong purpose is met. The recommended search card can also provide richer experience and stronger discovery for the user, give the expectation of consumption certainty and meet the requirement that the user wants to see more related contents.

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

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

Claims

1. A search recommendation method, comprising:

acquiring a recommended search card related to a target video, wherein the target video is a video displayed in a recommended page and browsed by a user, the recommended page is used for displaying at least two recommended multimedia resources, the multimedia resources comprise videos, and the recommended search card comprises at least two recommended search words;

displaying the recommended search card on the recommended page;

responding to the operation of clicking the recommended search word by the user, and displaying a multimedia resource search result page corresponding to the clicked recommended search word.

2. The search recommendation method of claim 1, wherein the step of obtaining a recommended search card associated with the target video comprises:

and responding to a first returning operation of returning to the recommendation page from the browsing page of the target video, and acquiring the recommendation search card related to the target video.

3. The search recommendation method of claim 2, wherein the step of displaying the recommended search card on the recommendation page comprises:

displaying the recommended search card in a target area of the recommended page, wherein the target area is a display area of the target video or an area adjacent to the display area of the target video.

4. The search recommendation method of claim 3,

the target area is a cover area overlaid on a display area of the target video; or

The target area is an area connected below a display area of the target video.

5. The search recommendation method according to claim 3, wherein the step of displaying the recommended search card in the target area of the recommendation page in a case where the target area is an area adjacent to a display area of the target video comprises:

and determining that the size of the target area is larger than a set size, and displaying the recommended search card in the target area.

6. The search recommendation method of any one of claims 1 to 5, wherein the step of displaying the recommended search card on the recommendation page comprises:

and determining that a trigger condition is met, and displaying the recommended search card on the recommended page.

7. A search recommendation apparatus, comprising:

an acquisition unit configured to: acquiring a recommended search card related to a target video, wherein the target video is a video displayed in a recommended page and browsed by a user, the recommended page is used for displaying at least two recommended multimedia resources, the multimedia resources comprise videos, and the recommended search card comprises at least two recommended search words;

a recommendation unit configured to: displaying the recommended search card on the recommended page;

a search unit configured to: responding to the operation of clicking the recommended search word by the user, and displaying a multimedia resource search result page corresponding to the clicked recommended search word.

8. An electronic device, comprising:

at least one processor;

at least one memory storing computer-executable instructions,

wherein the computer-executable instructions, when executed by the at least one processor, cause the at least one processor to perform the search recommendation method of any one of claims 1-6.

9. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by at least one processor, cause the at least one processor to perform the search recommendation method of any of claims 1-6.

10. A computer program product comprising computer instructions, wherein the computer instructions, when executed by at least one processor, implement the search recommendation method of any of claims 1 to 6.