CN111259173B

CN111259173B - Search information recommendation method and device

Info

Publication number: CN111259173B
Application number: CN202010062777.6A
Authority: CN
Inventors: 彭睿棋
Original assignee: Beijing ByteDance Network Technology Co Ltd
Current assignee: Douyin Vision Co Ltd; Douyin Vision Beijing Co Ltd
Priority date: 2020-01-19
Filing date: 2020-01-19
Publication date: 2023-03-21
Anticipated expiration: 2040-01-19
Also published as: CN111259173A

Abstract

The present disclosure provides a search information recommendation method and apparatus, including: responding to a search request of a user side, and pushing at least one media content corresponding to the search request to the user side; the media content is used for being displayed in a search result display page of the user side; after detecting that the triggering operation aiming at any media content in the search result display page meets a preset condition, determining recommended search information associated with the any media content; and pushing the recommended search information to the user side, wherein the recommended search information is used for being displayed in a search result display page for displaying any media content.

Description

Search information recommendation method and device

Technical Field

The disclosure relates to the technical field of computers, in particular to a search information recommendation method and device.

Background

When a user searches information, the user generally inputs search information, and then the server determines a corresponding search result based on the search information input by the user. However, this searching method is only suitable for searching text, and when searching for video, audio, picture, etc., the user may not be able to input accurate description information for video, audio, picture, etc. when searching, resulting in low searching efficiency.

Disclosure of Invention

The embodiment of the disclosure at least provides a search information recommendation method and device.

In a first aspect, an embodiment of the present disclosure provides a search information recommendation method, including:

responding to a search request of a user side, and pushing at least one media content corresponding to the search request to the user side; the media content is used for being displayed in a search result display page of the user side;

after detecting that the triggering operation aiming at any media content in the search result display page meets a preset condition, determining recommended search information associated with the any media content;

and pushing the recommended search information to the user side, wherein the recommended search information is used for being displayed in a search result display page for displaying any media content.

In a possible implementation manner, the detecting that the trigger operation for any media content in the search result presentation page satisfies a preset condition includes:

detecting that the playing time length of any media content in the search result display page is greater than a set time length threshold; and/or the presence of a gas in the gas,

detecting that a page displayed on a current screen of the user side is returned to the search result display page from a playlist page for playing target media content; the target media content is any one of the media contents triggered to be played in the search result display page or the media content played in the playlist page after any one of the media contents.

In one possible embodiment, the determining recommended search information associated with the any media content includes:

determining at least one first search keyword associated with any media content according to a pre-established first association relation library, wherein the first association relation library comprises information representing association relation between the media content and the first search keyword;

determining a second search keyword associated with each first search keyword in the at least one first search keyword according to a pre-established second association relation library, wherein the second association relation library comprises information representing association relations among different search keywords;

and determining recommended search information associated with any media content based on the first search keyword and the second search keyword.

In one possible implementation, the first association relation library is established according to the following steps:

establishing the first incidence relation library according to historical playing records and historical searching information of a plurality of user sides; the history playing record comprises identification information and playing time information of the played media content, and the history searching information comprises history searching time and corresponding searching keywords.

In a possible implementation manner, the establishing the first association relationship library according to the historical playing records and the historical search information of multiple user terminals includes:

aiming at the same user side, if the playing time in the historical playing record exists and the time interval between the playing time in the historical searching information and the historical searching time in the historical searching information is within a preset time interval range, the played media content corresponding to the historical playing record and the searching keywords in the historical searching information are used as a candidate media content keyword group;

determining the number of user sides corresponding to each candidate media content key phrase according to the candidate media content key phrases corresponding to the plurality of user sides respectively;

and determining the candidate media content key phrases of which the corresponding user side number meets a first preset condition as the media content key phrases in the first association relation library.

In a possible implementation, the second association relation library is established according to the following steps:

establishing a second incidence relation library according to historical search information of a plurality of user sides; the historical search information includes historical search time and corresponding search keywords.

In a possible implementation manner, the establishing the second association relationship library according to historical search information of a plurality of user terminals includes:

acquiring at least one candidate search keyword group used by a user side, wherein the time interval of initiating search requests corresponding to different candidate search keywords in each candidate search keyword group is within a preset time length range;

determining the number of user sides corresponding to each candidate search key phrase according to the at least one candidate search key phrase used by the plurality of user sides respectively;

and determining the candidate search key phrases of which the corresponding user side number meets a second preset condition as the search key phrases in the second association relation library.

In a possible implementation manner, the first association relation library further includes a first association coefficient, where the first association coefficient is used to represent the association closeness degree between the media content in each media content search keyword group in the first association relation library and the search keyword; the second incidence relation library also comprises a second incidence coefficient which is used for expressing the incidence tightness degree among the search keywords in the search keyword group;

the determining recommended search information associated with any media content based on the first search keyword and the second search keyword comprises:

screening out a first target search keyword from the first search keyword based on a first correlation coefficient between the first search keyword and any media content;

screening a second target search keyword from the second search keywords based on a second correlation coefficient between the first search keyword and the second search keyword;

and determining the first target search keyword and the second target search keyword as recommended search information which is not associated with any media content.

In one possible embodiment, the determining recommended search information associated with the any media content based on the first search keyword and the second search keyword includes:

determining user characteristic information of the user side based on historical search information of the user side;

and screening target keywords from the first search keywords and the second search keywords based on the user characteristic information, and determining the target keywords as recommended search information associated with any media content.

In a second aspect, an embodiment of the present disclosure provides a search information recommendation method, applied to a user side, including:

initiating a search request to a server;

receiving at least one piece of media content returned by the server based on the search request, and displaying the media content in a search result display page;

receiving recommended search information which is pushed by the server and is associated with any media content after the triggering operation aiming at any media content displayed in the search result display page meets a preset condition;

and displaying the recommended search information on the search result display page.

In one possible embodiment, after the search result presentation page presents the recommended search information, the method further includes:

and responding to sliding operation aiming at the search result display page, and hiding the recommended search information in the search result display page after detecting that the recommended search information is not in the current screen display range.

In a third aspect, an embodiment of the present disclosure provides a search information recommendation apparatus deployed in a server, including:

the first pushing module is used for responding to a search request of a user side and pushing at least one media content corresponding to the search request to the user side; the media content is used for being displayed in a search result display page of the user side;

the determining module is used for determining recommended search information associated with any media content after detecting that the triggering operation aiming at any media content in the search result display page meets a preset condition;

and the second pushing module is used for pushing the recommended search information to the user side, and the recommended search information is used for being displayed in a search result display page for displaying any media content.

In a possible implementation manner, the determining module, when detecting that a trigger operation for any media content in the search result presentation page satisfies a preset condition, is configured to:

detecting that the playing time length of any media content in the search result display page is greater than a set time length threshold; and/or the presence of a gas in the atmosphere,

In one possible embodiment, the determining module, when determining the recommended search information associated with any of the media contents, is configured to:

In a possible implementation manner, the determining module is further configured to establish the first association relation library according to the following steps:

In a possible implementation manner, the determining module, when establishing the first association relation library according to historical playing records and historical search information of a plurality of user terminals, is configured to:

In a possible implementation manner, the determining module is further configured to establish the second association relation library according to the following steps:

In a possible implementation manner, the determining module, when establishing the second association relation library according to historical search information of a plurality of user terminals, is configured to:

the determining module, when determining the recommended search information associated with any of the media contents based on the first search keyword and the second search keyword, is configured to:

In one possible embodiment, the determining module, when determining the recommended search information associated with the any media content based on the first search keyword and the second search keyword, is configured to:

and based on the user characteristic information, screening out target keywords from the first search keywords and the second search keywords, and determining the target keywords as recommended search information associated with any media content.

In a fourth aspect, an embodiment of the present disclosure provides a search information recommendation device, deployed at a user side, including:

the request module is used for initiating a search request to the server;

the first receiving module is used for receiving at least one piece of media content returned by the server based on the search request and displaying the media content in a search result display page;

the second receiving module is used for receiving recommended search information which is pushed by the server and is related to any media content after the triggering operation aiming at any media content displayed in the search result display page meets a preset condition;

and the display module is used for displaying the recommended search information on the search result display page.

In a possible embodiment, the display module is further configured to: after the recommended search information is displayed on the search result display page, responding to sliding operation aiming at the search result display page, and hiding the recommended search information in the search result display page after detecting that the recommended search information is not in the current screen display range.

In a fifth aspect, an embodiment of the present disclosure further provides a computer device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the computer device is running, the machine-readable instructions when executed by the processor performing the steps of the first aspect, or any one of the possible embodiments of the first aspect, or the second aspect, or any one of the possible embodiments of the second aspect.

In a sixth aspect, this disclosed embodiment also provides a computer readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs the steps in the first aspect, or any one of the possible embodiments of the first aspect, or performs the steps in the second aspect, or any one of the possible embodiments of the second aspect.

The search information recommendation method and device provided by the embodiment of the disclosure can determine the recommended search information to be pushed to the user side based on the media content of which the corresponding trigger operation in the search result display page meets the preset condition, and the media content of which the trigger operation in the search result display page meets the preset condition can be regarded as the media content of interest to the user.

In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly described below, and the drawings herein incorporated in and forming a part of the specification illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the technical solutions of the present disclosure. It is appreciated that the following drawings depict only certain embodiments of the disclosure and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.

Fig. 1 shows a flowchart of a search information recommendation method provided by an embodiment of the present disclosure;

fig. 2 shows a flowchart of a method for determining recommended search information according to an embodiment of the present disclosure;

fig. 3 is a flowchart illustrating a first association relationship library establishing method according to an embodiment of the present disclosure;

fig. 4 is a flowchart illustrating a second association relation library establishing method according to an embodiment of the present disclosure;

FIG. 5 is a flowchart illustrating another method for determining recommended search information according to an embodiment of the present disclosure;

FIG. 6 is a diagram illustrating a search result presentation page provided by an embodiment of the present disclosure;

fig. 7 is a flowchart illustrating another search information recommendation method provided by an embodiment of the present disclosure;

fig. 8 is a schematic diagram illustrating an architecture of a search information recommendation apparatus provided in an embodiment of the present disclosure;

fig. 9 is a schematic diagram illustrating an architecture of another search information recommendation apparatus provided in the embodiment of the present disclosure;

fig. 10 shows a schematic structural diagram of an electronic device 1000 provided by an embodiment of the present disclosure;

fig. 11 shows a schematic structural diagram of an electronic device 1100 provided by an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure, presented in the figures, is not intended to limit the scope of the claimed disclosure, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.

At present, when a user searches information, the user generally inputs search information, and then a server determines a corresponding search result based on the search information input by the user, however, the search mode is only suitable for searching characters, and when searching videos, audios, pictures and the like, the user cannot describe contents to be searched through accurate characters.

In the related art, when a user is recommended search information, the user generally recommends the search information based on a search word input by the user, however, in this way, the search word input by the user is not necessarily accurate description information of media content (such as video, audio, pictures, etc.) that the user wants to search, and therefore, the search information recommended based on the search word input by the user does not necessarily meet the search requirement of the user.

Based on this, the present disclosure provides a search information recommendation method and apparatus, which may determine recommended search information to be pushed to a user terminal based on media content whose corresponding trigger operation in a search result display page satisfies a preset condition, and the media content whose trigger operation satisfies the preset condition in the search result display page may be regarded as media content which is interested by the user.

The above-mentioned drawbacks are the results of the inventor after practical and careful study, and therefore, the discovery process of the above-mentioned problems and the solutions proposed by the present disclosure to the above-mentioned problems should be the contribution of the inventor in the process of the present disclosure.

The technical solutions in the present disclosure will be described below clearly and completely with reference to the accompanying drawings in the present disclosure, and it is to be understood that the described embodiments are only some embodiments of the present disclosure, not all embodiments. The components of the present disclosure, as generally described and illustrated in the figures herein, could be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure, presented in the figures, is not intended to limit the scope of the claimed disclosure, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

Referring to fig. 1, a flowchart of a search information recommendation method provided in an embodiment of the present disclosure is applied to a server, and the method includes the following steps:

step 101, responding to a search request of a user side, and pushing at least one media content corresponding to the search request to the user side; the media content is used for being displayed in a search result display page of the user side.

And 102, determining recommended search information associated with any media content after detecting that the triggering operation aiming at any media content in the search result display page meets a preset condition.

And 103, pushing the recommended search information to the user side, wherein the recommended search information is used for being displayed in a search result display page for displaying any media content.

The following is a detailed description of steps 101 to 103.

For step 101:

the type of the at least one media content corresponding to the search request pushed by the server to the user terminal includes, but is not limited to, video, moving pictures, voice, and the like. The user can input a search keyword through a search interface at the user terminal, and then sends a search button to initiate a search request to the server.

When the media contents pushed to the user side by the server comprise a plurality of media contents, the media contents can be sorted according to the close association relationship between the media contents and the search keywords carried in the search request, and the close association relationship is preferentially displayed; the ranking may also be performed according to popularity information of the media content, wherein the popularity information of the media content may include, for example, forwarding times, praise times, browsing times, or a combination thereof.

With respect to step 102:

the condition that the trigger operation for any media content in the search result page satisfies the preset condition may include, but is not limited to, one or two of the following two cases:

in case one, it is detected that the playing time for any media content in the search result page is greater than a set time threshold.

Specifically, an automatic playing area may be set in the search result display page, and the media content located in the automatic playing area may be automatically played. If it is detected that the playing time for any media content in the search result page is greater than the set time threshold, it is detected that any media content in the search result display page is located in the automatic playing area, automatic playing is performed, and the automatic playing time is greater than the set time threshold.

In another possible implementation manner, the media content may be played after the user clicks the media content, and the duration of playing after the click is greater than the set duration threshold. The clicking manner includes, but is not limited to, clicking, double clicking, long pressing, re-pressing, and the like.

And in the second situation, the situation that the page displayed on the current screen of the user side is returned to the search result display page from the playlist page for playing the target media content is detected.

The target media content is any one of the media contents triggered to be played in the search result display page or the media content played in the playlist page after any one of the media contents.

After clicking any media content in the search result display page, the user can enter the playlist page to play the clicked media content, and the user can select other media contents except the clicked media content to play on the playlist page at the same time, namely enter the playlist page of the clicked media content and play the playlist pages of other media contents except the clicked media content.

When the situation that the user returns to the search result display page from the playlist page of the target media content is detected, in a possible situation, after clicking a certain media content, the user enters the playlist page of the media content, and the user does not select other media content to play on the playlist page, in this situation, when the situation returns to the search result display page again, the target media content is the media content which is clicked by the user initially; in another possible case, when the user clicks on a certain media content, the user enters the playlist page of the media content, and the user enters the playlist pages of other media contents from the playlist page of the media content, at this time, when the user returns to the search result presentation page, the target media content is other media content.

It should be noted that the other media contents are all the media contents in the search result presentation page. The manner of entering from the playlist page of the clicked media content, the playlist pages of other media contents except the clicked media content may be by sliding up and down, sliding left and right, etc., which is not limited by the present disclosure.

When determining the recommended search information associated with any media content, the method for determining the recommended search information shown in fig. 2 may be referred to, and includes the following steps:

step 201, determining at least one first search keyword associated with any media content according to a first association relation library established in advance, wherein the first association relation library comprises information representing association relation between the media content and the first search keyword;

step 202, determining a second search keyword associated with each first search keyword in the at least one first search keyword according to a pre-established second association relation library, wherein the second association relation library comprises information representing association relations among different search keywords;

step 203, determining recommended search information associated with any media content based on the first search keyword and the second search keyword.

When the first association relation library is established, the first association relation library can be established according to historical playing records and historical search information of a plurality of user terminals. The historical playing record of the user side comprises identification information of the played media content and playing time information, and the playing time information is the identification information of the corresponding played media content; the historical search information comprises historical search time and corresponding search keywords, the historical search time is the time when the user terminal initiates a search request, and the search keywords are keywords carried in the search request initiated by the user terminal.

Specifically, when the first association library is established according to the historical play records and the historical search information of the multiple user terminals, reference may be made to the method shown in fig. 3, which includes the following steps:

step 301, regarding to the same user side, if the playing time in the history playing record exists and the time interval between the playing time in the history searching information and the history searching time in the history searching information is within a preset time interval range, taking the played media content corresponding to the history playing record and the searching keyword in the history searching information as a candidate media content keyword group.

The time interval between the historical playing time and the historical searching time is within a preset time interval range, and the media content corresponding to the historical playing time and the searching keyword corresponding to the historical searching time may have an association relationship, so that the media content and the searching keyword can be used as a candidate media content keyword group. For example, after a user watches a certain video, the user initiates a search request carrying a certain search keyword, or after the user searches according to a certain search keyword, the user watches a certain video in the search result, in this case, it can be determined that the search keyword and the video may have an association relationship, so that the media content and the search keyword can be used as a candidate media content keyword group.

Step 302, determining the number of the user sides corresponding to each candidate media content keyword group according to the candidate media content keyword groups respectively corresponding to the plurality of user sides.

Each user side corresponds to a plurality of candidate media content key phrases, so that the number of the user sides corresponding to each candidate media content key phrase can be determined.

For example, as shown in table 1 below, if the user side a corresponds to the candidate media content keyword group 1, the candidate media content keyword group 2, the candidate media content keyword group 3, and the candidate media content keyword group 4, the user side B corresponds to the candidate media content keyword group 2 and the candidate media content keyword group 5; the user end C corresponds to the candidate media content key phrase 1, the candidate media content key phrase 2, and the candidate media content key phrase 4, so that it can be determined that the number of user ends corresponding to the candidate media content key phrase 1 is 2, the number of user ends corresponding to the candidate media content key phrase 2 is 3, the number of user ends corresponding to the candidate media content key phrase 3 is 1, the number of user ends corresponding to the candidate media content key phrase 4 is 2, and the number of user ends corresponding to the candidate media content key phrase 5 is 1.

TABLE 1

Step 303, determining the candidate media content keyword groups of which the corresponding user side number satisfies the first preset condition as the media content keyword groups in the first association relation library.

Specifically, when determining the candidate media content keyword groups of which the corresponding user side number satisfies the first preset condition, the candidate media content keyword groups of which the corresponding user side number is greater than the first set user side number may be determined as the candidate media content keyword groups satisfying the first preset condition; or, all the candidate media content keyword groups are sequenced from large to small according to the number of the corresponding user sides, and the top N candidate media content keyword groups are determined as the candidate media content keyword groups meeting the first preset condition.

When the second association relation library is established, the second association relation library can be established according to historical search information of a plurality of user sides, wherein the historical search information comprises historical search time and corresponding search keywords.

Specifically, when the second association relation library is established according to the historical search information of a plurality of user terminals, the method shown in fig. 4 may be referred to, and includes the following steps:

step 401, at least one candidate search keyword group used by a user side is obtained, and a time interval of initiating search requests corresponding to different candidate search keywords in each candidate search keyword group is within a preset duration range.

If the time interval of the initiation of the search requests corresponding to different search keywords is within the preset time length range, it is indicated that there may be a relationship between the search keywords, for example, if the user terminal initiates a search request carrying a search keyword 1 and then initiates a search request carrying a search keyword 2, then there may be a case that the user does not find a desired search result by the search keyword 1 and wants to search by the search keyword 2, and therefore, there may be a relationship between the search keyword 1 and the search keyword 2, and the search keyword 1 and the search keyword 2 may be determined to be in the same candidate search keyword group.

For example, if the time interval between the initiation of the search request a, the initiation of the search request B, and the initiation of the search request C at the same user end is within the preset time range, the search keywords carried by the search request a, the search request B, and the search request C may be determined as a group of candidate search keyword groups.

Step 402, determining the number of user sides corresponding to each candidate keyword group according to the at least one candidate search keyword group used by the plurality of user sides respectively.

Exemplarily, as shown in the following table 2, if the user side a corresponds to the candidate search keyword group 1, the candidate search keyword group 3, and the candidate search keyword group 4; the user side B corresponds to the candidate search keyword group 1, the candidate search keyword group 2 and the candidate search keyword group 3; if the user terminal C corresponds to the candidate search key word group 2 and the candidate search key word group 3, it may be determined that the number of user terminals corresponding to the candidate search key word 1 is 2, the number of user terminals corresponding to the candidate search key word group 2 is 2, the number of user terminals corresponding to the candidate search key word group 3 is 3, and the number of user terminals corresponding to the candidate search key word group 4 is 4.

TABLE 2

User terminal	Candidate search key phrase
		User terminal A	1、3、4
User terminal B	1、2、3
		User terminal C	2、3

Step 403, determining the candidate keyword groups of which the corresponding user side number meets a second preset condition as the search keyword groups in the second association relation library.

Specifically, when determining the candidate search keyword groups of which the corresponding user side number satisfies the second preset condition, the candidate search keyword groups of which the corresponding user side number is greater than the second set user side number may be determined as the candidate search keyword groups of which the corresponding user side number satisfies the second preset condition; or the candidate search key phrases are sorted according to the number of the corresponding user sides in the descending order, and the top M candidate search key phrases are determined as the candidate search key phrases of which the number of the corresponding user sides meets the second preset condition.

In a possible implementation manner, the first association relation library further includes a first association coefficient, where the first association coefficient is used to represent the degree of closeness of association between the media content in each media content search keyword group in the first association relation library and the search keyword; the second association relation library also comprises a second association coefficient, and the second association coefficient is used for representing the association degree of the search keywords in the search keyword group.

When determining the first association coefficient, the number of the user sides corresponding to the media content keyword group can be directly determined as the first association coefficient between the media content in the media content keyword group and the search keyword; when the second association coefficient is determined, the number of the user terminals corresponding to the search keyword group can be directly determined as the second association coefficient between the search keywords in the search keyword group.

In determining recommended search information associated with any one of the media contents based on the first search keyword and the second search keyword, reference may be made to a method as shown in fig. 5, which includes the following steps:

step 501, based on a first correlation coefficient between the first search keyword and any media content, a first target search keyword is screened from the first search keyword.

Specifically, the first search keyword whose corresponding first association coefficient is greater than the set value may be determined as the first target search keyword.

For example, for the media content 1, the corresponding first search keywords are a, B, C, and D, a first correlation coefficient between the media content 1 and the first search keyword a, a first correlation coefficient between the media content 1 and the first search keyword B, a first correlation coefficient between the media content 1 and the first search keyword C, and a first correlation coefficient between the media content 1 and the first search keyword D may be determined, respectively, and then the corresponding first correlation coefficient greater than the set first search keyword is determined as the first target search keyword.

Step 502, screening a second target search keyword from the second search keywords based on a second correlation coefficient between the first search keyword and the second search keyword.

Specifically, when the second target search keyword is screened based on the second correlation coefficient between the first search keyword and the second search keyword, the second correlation coefficient between the first target search keyword and the second search keyword may be determined first, and then the second search keyword whose second correlation coefficient is greater than a set value may be determined as the second target search keyword.

Step 503, determining the recommended search information which is not associated with any media content according to the first target search keyword and the second target search keyword.

In another possible implementation, when determining the recommended search information associated with any media content based on the first search keyword and the second search keyword, the user characteristic information of the user side may be determined based on the historical search information of the user side, then the target keyword is screened from the first search keyword and the second search keyword based on the user characteristic information, and the target keyword is determined as the recommended search information associated with any media content.

The user characteristic information may include, for example, the age, sex, and the like of the user, and the user characteristic information may be counted according to the historical search information of the user terminal.

When the target keywords are screened from the first search keywords and the second search keywords based on the user characteristic information, the first search keywords and the second search keywords can be input into a pre-trained neural network model, the matching degree of each search keyword and the user is output, and the first search keywords and the second search keywords are screened based on the output matching degree.

The neural network model can be obtained by training based on sample user characteristic information, sample search keywords and sample labels, the sample labels are used for representing the matching degree between the sample user characteristic information and the sample search keywords, after the sample search keywords and the sample user characteristic information are input into the neural network model with training, the prediction matching degree is output, then the loss value in the training process is determined based on the prediction matching degree and the sample labels, and the model parameter value of the neural network model is adjusted based on the loss value.

In another possible implementation manner, the search times corresponding to each search term may be determined first, where the search times are times carried by the search term when a plurality of user terminals initiate search requests, and when determining recommended search information associated with any media content based on the first search keyword and the second search keyword, the search keyword whose corresponding search times are greater than the set times may be determined as the recommended search information.

For step 103:

after the recommended search information is pushed to the user side, the recommended search information may be displayed in a search result display page displaying any media content, for example, may be displayed below the media content whose trigger operation satisfies a preset condition, so as to prompt the user to search based on the displayed recommended search information. When any search keyword in the recommended search information is detected to be triggered, a search request can be initiated based on the triggered search keyword.

The search keyword is triggered, for example, by clicking, double clicking, long pressing, and double pressing the search keyword.

For example, as shown in fig. 6, the search result display page may show a search keyword "ABCD" input by a user in a search box in fig. 6, a plurality of videos searched based on the search keyword are shown in the search result display page, a user name corresponding to each video is uploaded, heat information corresponding to each video, such as the number of votes, the number of comments, the number of forwards, and the like, may also be shown below a video played for a period longer than a preset period, a comment area is shown below the heat information, a user comment may be shown in the comment area, a prompt that "everybody is searching" is shown below the comment area, and a plurality of recommended search keywords (i.e., recommended search information) are shown below the prompt that the user searches based on the recommended search keywords.

The search information recommendation method provided by the embodiment of the disclosure can determine the recommended search information to be pushed to the user side based on the media content meeting the preset condition by the corresponding trigger operation in the search result display page, and the media content meeting the preset condition by the trigger operation in the search result display page can be regarded as the media content interested by the user.

Based on the same concept, the present disclosure also provides another search information recommendation method, which is applied to a user side, and as shown in fig. 7, a flow diagram of another search information recommendation method provided by the embodiment of the present disclosure includes the following steps:

step 701, initiating a search request to a server;

step 702, receiving at least one media content returned by the server based on the search request, and displaying the media content in a search result display page;

step 703, receiving recommended search information related to any media content pushed by the server after the triggering operation for any media content displayed in the search result display page meets a preset condition;

and 704, displaying the recommended search information on the search result display page.

After the recommended search information is displayed on the search result display page, the sliding operation aiming at the search result display page can be responded, and when the recommended search information is detected not to be in the current screen display range, the recommended search information in the search result display page can be hidden in order to improve the proportion of the media content in the page in the screen and improve the user experience.

It will be understood by those of skill in the art that in the above method of the present embodiment, the order of writing the steps does not imply a strict order of execution and does not impose any limitations on the implementation, as the order of execution of the steps should be determined by their function and possibly inherent logic.

Based on the same inventive concept, the embodiment of the present disclosure further provides a search information recommendation device corresponding to the search information recommendation method, and as the principle of solving the problem of the device in the embodiment of the present disclosure is similar to the search information recommendation method in the embodiment of the present disclosure, the implementation of the device may refer to the implementation of the method, and repeated details are not repeated.

Referring to fig. 8, a schematic diagram of an architecture of a search information recommendation apparatus provided in the fifth embodiment of the present disclosure includes a first pushing module 801, a determining module 802, and a second pushing module 803, specifically:

a first pushing module 802, configured to respond to a search request of a user side, and push at least one media content corresponding to the search request to the user side; the media content is used for being displayed in a search result display page of the user side;

a determining module 802, configured to determine recommended search information associated with any media content in the search result display page after detecting that a trigger operation for any media content in the search result display page meets a preset condition;

a second pushing module 803, configured to push the recommended search information to the user side, where the recommended search information is used to be displayed in a search result display page for displaying any media content.

In one possible implementation, the determining module 802, when detecting that the triggering operation for any media content in the search result presentation page satisfies a preset condition, is configured to:

detecting that a page displayed on a current screen of the user side is returned to the search result display page from a playlist page for playing target media content; the target media content is any media content triggered to be played in the search result display page, or is media content played on a playlist page after any media content.

In one possible implementation, the determining module 802, when determining the recommended search information associated with any of the media contents, is configured to:

In a possible implementation manner, the determining module 802 is further configured to establish the first association relation library according to the following steps:

In a possible implementation manner, the determining module 802, when building the first association relation library according to historical playing records and historical search information of multiple user terminals, is configured to:

In a possible implementation manner, the determining module 802 is further configured to establish the second association relationship library according to the following steps:

In a possible implementation manner, the determining module 802, when building the second association relation library according to historical search information of a plurality of user terminals, is configured to:

In a possible implementation manner, the first association relation library further includes a first association coefficient, where the first association coefficient is used to represent the association closeness degree between the media content in each media content search keyword group in the first association relation library and the search keyword; the second incidence relation library also comprises a second incidence coefficient, and the second incidence coefficient is used for representing the incidence tightness degree between the search keywords in the search keyword group;

the determining module 802, when determining the recommended search information associated with any media content based on the first search keyword and the second search keyword, is configured to:

In one possible implementation, the determining module 802, when determining the recommended search information associated with any of the media contents based on the first search keyword and the second search keyword, is configured to:

Based on the same concept, an embodiment of the present disclosure further provides another search information recommendation apparatus, as shown in fig. 9, which is a schematic structural diagram of another search information recommendation apparatus provided in the embodiment of the present disclosure, and includes a request module 901, a first receiving module 902, a second receiving module 903, and a presentation module 904, specifically:

a request module 901, configured to initiate a search request to a server;

a first receiving module 902, configured to receive at least one media content returned by the server based on the search request, and display the media content in a search result display page;

a second receiving module 903, configured to receive recommended search information related to any media content that is displayed in the search result display page and is pushed by the server after a trigger operation for the any media content meets a preset condition;

a display module 904, configured to display the recommended search information on the search result display page.

In a possible implementation, the display module 904 is further configured to: after the recommended search information is displayed on the search result display page, responding to sliding operation aiming at the search result display page, and hiding the recommended search information in the search result display page after detecting that the recommended search information is not in the current screen display range.

The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.

Based on the same technical concept, the embodiment of the application also provides the electronic equipment. Referring to fig. 10, a schematic structural diagram of an electronic device 1000 provided in the embodiment of the present application includes a processor 1001, a memory 1002, and a bus 1003. The memory 1002 is used for storing execution instructions, and includes a memory 10021 and an external memory 10022; the memory 10021 is also referred to as a memory, and is used for temporarily storing operation data in the processor 1001 and data exchanged with the external memory 10022 such as a hard disk, the processor 1001 exchanges data with the external memory 10022 through the memory 10021, and when the electronic device 1000 operates, the processor 1001 and the memory 1002 communicate with each other through the bus 1003, so that the processor 1001 executes the following instructions:

after detecting that the trigger operation aiming at any media content in the search result display page meets a preset condition, determining recommended search information associated with any media content;

In a possible implementation manner, in the instructions executed by the processor 1001, the detecting that the trigger operation for any media content in the search result presentation page satisfies a preset condition includes:

In a possible implementation, the instructions executed by the processor 1001 for determining the recommended search information associated with any one of the media contents includes:

In one possible implementation, the processor 1001 executes instructions to establish the first association relationship library according to the following steps:

In a possible implementation manner, in the instructions executed by the processor 1001, the building the first association relationship library according to the historical playing records and the historical search information of the multiple user terminals includes:

In one possible implementation, the processor 1001 executes instructions to establish the second association library according to the following steps:

establishing the second incidence relation library according to historical search information of a plurality of user sides; the historical search information includes historical search time and corresponding search keywords.

In a possible implementation manner, in the instructions executed by the processor 1001, the building the second association relationship library according to the historical search information of the plurality of user terminals includes:

In a possible implementation manner, in the instructions executed by the processor 1001, the first association library further includes a first association coefficient, where the first association coefficient is used to indicate how closely the association between the media content in each media content search keyword group in the first association library and the search keyword is; the second incidence relation library also comprises a second incidence coefficient, and the second incidence coefficient is used for representing the incidence tightness degree between the search keywords in the search keyword group;

the determining recommended search information associated with the any media content based on the first search keyword and the second search keyword includes:

In one possible implementation, the instructions executed by the processor 1001 for determining the recommended search information associated with the any media content based on the first search keyword and the second search keyword include:

Based on the same technical concept, the embodiment of the application also provides the electronic equipment. Referring to fig. 11, a schematic structural diagram of an electronic device 1100 provided in the embodiment of the present application includes a processor 1101, a memory 1102, and a bus 1103. The storage 1102 is used for storing execution instructions and includes a memory 11021 and an external storage 11022; the memory 11021 is also referred to as a memory, and temporarily stores operation data in the processor 1101 and data exchanged with the external memory 11022 such as a hard disk, and the processor 1101 exchanges data with the external memory 11022 through the memory 11021, and when the electronic device 1100 operates, the processor 1101 communicates with the memory 1102 through the bus 1103, so that the processor 1101 executes the following instructions:

initiating a search request to a server;

In a possible implementation manner, in the instructions executed by the processor 1101, after the search result presentation page presents the recommended search information, the method further includes:

The disclosed embodiments also provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the search information recommendation method described in the above method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

The computer program product of the search information recommendation method provided in the embodiments of the present disclosure includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute steps of the search information recommendation method in the above method embodiments, which may be referred to in the above method embodiments specifically, and are not described herein again.

The embodiments of the present disclosure also provide a computer program, which when executed by a processor implements any one of the methods of the foregoing embodiments. The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be through some communication interfaces, indirect coupling or communication connection between devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Finally, it should be noted that: the above-mentioned embodiments are merely specific embodiments of the present disclosure, which are used for illustrating the technical solutions of the present disclosure and not for limiting the same, and the scope of the present disclosure is not limited thereto, and although the present disclosure is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive of the technical solutions described in the foregoing embodiments or equivalent technical features thereof within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present disclosure, and should be construed as being included therein. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A search information recommendation method is applied to a server and is characterized by comprising the following steps:

after detecting that the trigger operation aiming at any media content in the search result display page meets a preset condition, determining recommended search information associated with any media content; the recommended search information is obtained by screening a first search keyword and a second search keyword after the first search keyword, the second search keyword and user characteristic information corresponding to the user side are input into a neural network model; the first search keyword is a search keyword which is determined from a pre-established first incidence relation library and is associated with any media content, and the first incidence relation library comprises information representing incidence relation between the media content and the first search keyword; the second search keyword is a search keyword which is determined from a pre-established second incidence relation library and is associated with the first search keyword, and the second incidence relation library comprises information representing incidence relations among different search keywords;

2. The method of claim 1, wherein the detecting that the trigger operation for any media content in the search result presentation page meets a preset condition comprises:

detecting that the playing time length of any media content in the search result display page is greater than a set time length threshold value; and/or the presence of a gas in the gas,

3. The method of claim 1, wherein the first associative relation library is established according to the following steps:

4. The method according to claim 3, wherein the establishing the first association relationship library according to historical playing records and historical search information of a plurality of user terminals comprises:

determining the number of user sides corresponding to each candidate media content key phrase according to the candidate media content key phrases respectively corresponding to a plurality of user sides;

5. The method of claim 1, wherein the second associative relation library is established according to the following steps:

6. The method according to claim 5, wherein the establishing the second association relation library according to historical search information of a plurality of user terminals comprises:

7. The method according to claim 1, wherein the first association library further comprises a first association coefficient, and the first association coefficient is used for representing the degree of closeness of association between the media content in each media content search keyword group in the first association library and the search keyword; the second incidence relation library also comprises a second incidence coefficient which is used for expressing the incidence tightness degree among the search keywords in the search keyword group;

the method further includes determining recommended search information associated with the any of the media content according to the following steps:

and determining the first target search keyword and the second target search keyword as recommended search information associated with any media content.

8. The method of claim 1, wherein determining the recommended search information associated with the any media content comprises:

9. A search information recommendation method is applied to a user side and is characterized by comprising the following steps:

initiating a search request to a server;

receiving recommended search information which is pushed by the server and is associated with any media content after the triggering operation for any media content displayed in the search result display page meets a preset condition; the recommended search information is obtained by screening a first search keyword and a second search keyword after the first search keyword, the second search keyword and user characteristic information corresponding to the user side are input into a neural network model; the first search keyword is a search keyword which is determined from a pre-established first incidence relation library and is associated with any media content, and the first incidence relation library comprises information representing incidence relation between the media content and the first search keyword; the second search keyword is a search keyword which is determined from a pre-established second incidence relation library and is associated with the first search keyword, and the second incidence relation library comprises information representing incidence relations among different search keywords;

10. The method of claim 9, wherein after the search result presentation page presents the recommended search information, the method further comprises:

11. A search information recommendation device deployed in a server, comprising:

the determining module is used for determining recommended search information associated with any media content after detecting that the triggering operation aiming at any media content in the search result display page meets a preset condition; the recommended search information is obtained by screening a first search keyword and a second search keyword after the first search keyword, the second search keyword and user characteristic information corresponding to the user side are input into a neural network model; the first search keyword is a search keyword which is determined from a pre-established first incidence relation library and is associated with any media content, and the first incidence relation library comprises information representing incidence relation between the media content and the first search keyword; the second search keyword is a search keyword which is determined from a pre-established second incidence relation library and is associated with the first search keyword, and the second incidence relation library comprises information representing incidence relations among different search keywords;

12. A search information recommendation device deployed at a user side is characterized by comprising:

the request module is used for initiating a search request to the server;

the second receiving module is used for receiving recommended search information which is pushed by the server and is associated with any media content after the triggering operation of any media content displayed in the search result display page meets a preset condition; the recommended search information is obtained by screening a first search keyword and a second search keyword after the first search keyword, the second search keyword and user characteristic information corresponding to the user side are input into a neural network model; the first search keyword is a search keyword which is determined from a pre-established first incidence relation library and is associated with any media content, and the first incidence relation library comprises information representing incidence relation between the media content and the first search keyword; the second search keyword is a search keyword which is determined from a pre-established second incidence relation library and is associated with the first search keyword, and the second incidence relation library comprises information representing incidence relations among different search keywords;

13. A computer device, comprising: a processor, a memory and a bus, the memory storing machine readable instructions executable by the processor, the processor and the memory communicating over the bus when a computer device is running, the machine readable instructions when executed by the processor performing the search information recommendation method of any of claims 1 to 8 or performing the steps of the search information recommendation method of any of claims 9 to 10.

14. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, performs the search information recommendation method according to any one of claims 1 to 8, or performs the steps of the search information recommendation method according to any one of claims 9 to 10.