Search processing method and apparatus, and computer readable storage medium

Abstract

The present invention relates to the technical field of artificial intelligence, and relates to a search processing method and apparatus, and a computer readable storage medium. The search processing method in the present invention comprises: receiving a question input by a user; and on the basis of the question, displaying an answer of the question and a plurality of answer videos related to the question in a search result page, wherein the answer is a sentence which is generated by machine understanding of the plurality of answer videos and described in natural language, and comprises description information of each answer video among the plurality of answer videos generated by machine understanding of the answer video.

Description

Search processing method, device, and computer-readable storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on the application with CN application number 202311140509.1 and application date September 5, 2023, and claims its priority. The disclosed content of the CN application is hereby introduced as a whole into this application. Technical Field

[0003] The present disclosure relates to the field of artificial intelligence technology, and in particular to a search processing method, device, and computer-readable storage medium. Background Art

[0004] With the development of Internet technology, users obtain various information from Internet platforms, and information acquisition becomes more and more convenient.

[0005] Search is a common way to obtain information. Usually, users enter keywords, sentences, etc. to search for related content for display.

[0006] Summary of the Invention

[0007] This summary is provided to briefly introduce concepts that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0008] According to some embodiments of the present disclosure, a search processing method is provided, comprising: receiving a question input by a user; and displaying an answer to the question and a plurality of answer videos related to the question in a search results page based on the question, wherein the answer is a sentence described in natural language generated by machine understanding of the plurality of answer videos, and comprises description information of each answer video generated by machine understanding of each of the plurality of answer videos.

[0009] In some embodiments, displaying the answer to a question and multiple answer videos related to the question in a search results page includes: displaying a reference identifier of each answer video at a corresponding position of the description information of each answer video in the answer; and displaying a reference identifier of each answer video on each answer video.

[0010] In some embodiments, the search processing method further includes: receiving a trigger operation of a user on a reference identifier displayed in the answer; and playing an answer video corresponding to the reference identifier.

[0011] In some embodiments, the search processing method further includes: displaying one or more candidate questions in a search result page based on the question and the multiple answer videos.

[0012] In some embodiments, the search processing method further includes: receiving a user's selection operation on any candidate question from one or more candidate questions, jumping to a conversation page; and displaying an answer to the selected candidate question on the conversation page.

[0013] In some embodiments, the search processing method further includes: displaying an entry control for continuing to ask questions on the search results page; receiving a user trigger operation on the entry control, and jumping to the conversation page.

[0014] In some embodiments, the search processing method further includes: displaying at least one of the answer and the candidate question in a conversation page.

[0015] In some embodiments, displaying the answer to the question and multiple answer videos related to the question in the search results page includes: automatically playing some or all of the multiple answer videos when the display range of the answer is within a first preset range.

[0016] In some embodiments, displaying the answer to the question and multiple answer videos related to the question in the search result page also includes: when the display position of the answer is outside the first preset range, displaying preview information of the multiple answer videos.

[0017] In some embodiments, when the display range of the answer is within a preset range, automatically playing part or all of the answer videos of multiple answer videos includes: when the display position of the bottom of the last row of answers is above the first reference line, automatically playing part or all of the answer videos of multiple answer videos.

[0018] In some embodiments, when the display range of the answer is within a preset range, automatically playing part or all of the answer videos of multiple answer videos also includes: when the display position of the bottom of the last row of answers is below a first reference line and the display position of the top of the first row of answers is above a second reference line, automatically playing part or all of the answer videos of multiple answer videos, wherein the second reference line is above the first reference line.

[0019] In some embodiments, the search results page includes a fixed display area and a search card area that supports sliding display, and displaying the answer to the question and multiple answer videos related to the question in the search results page also includes: displaying the answer and multiple answer videos in the search card area.

[0020] In some embodiments, the search card area includes a first area and a second area, and displaying answers and multiple answer videos in the search card area includes: displaying the answer in the first area, wherein the display range of the first area is adaptively adjusted according to the length of the answer within a second preset range; and displaying multiple answer videos in the second area, wherein the multiple answer videos support sliding display in the second area.

[0021] In some embodiments, displaying the answer in the first area includes: when the length of the answer exceeds a second preset range, hiding the content of the answer that exceeds the second preset range and displaying an expansion control; receiving a user trigger operation on the expansion control and displaying the answer in full.

[0022] In some embodiments, displaying the answer in the first area also includes: displaying a hidden control when the length of the answer exceeds a second preset range and the answer is displayed in full; receiving a user trigger operation on the hidden control to hide the content in the answer that exceeds the second preset range.

[0023] In some embodiments, the search processing method further includes: receiving a first operation of a user on any answer video among a plurality of answer videos; and switching the answer video corresponding to the first operation from a first display state to a second display state.

[0024] In some embodiments, the search processing method further includes: receiving a second operation of the user on a control in the search results page; and switching the control corresponding to the second operation from the third display state to the fourth display state.

[0025] In some embodiments, the search processing method further includes: displaying a plurality of recommended videos related to the question on the search results page, wherein the search strategies of the plurality of recommended videos and the plurality of answer videos are different.

[0026] In some embodiments, the search processing method further includes: receiving a user's triggering operation on any recommended video among a plurality of recommended videos; and playing the any recommended video.

[0027] In some embodiments, a trigger operation of a user on any answer video among a plurality of answer videos is received; and the arbitrary answer video is played.

[0028] In some embodiments, based on the question, displaying the answer to the question and multiple answer videos related to the question in the search results page includes: based on the question, using a first neural network model to perform machine understanding on multiple videos in a first database, obtaining multiple answer videos related to the question from the multiple videos, and generating description information for each answer video; generating an answer based on the description information of each answer video.

[0029] In some embodiments, the search processing method further includes: receiving information input by a user; when the input information is not a question, using a second neural network to perform machine understanding of multiple multimedia contents in a second database based on the input information, and obtaining multiple target multimedia contents related to the input information from the multiple multimedia contents; and displaying the multiple target multimedia contents in a search results page.

[0030] According to other embodiments of the present disclosure, a search processing device is provided, including: a receiving module configured to receive a question input by a user; a display module configured to display an answer to the question and multiple answer videos related to the question in a search results page based on the question, wherein the answer is a sentence described in natural language generated by machine understanding of the multiple answer videos, and includes description information of each answer video generated by machine understanding of each answer video in the multiple answer videos.

[0031] According to some further embodiments of the present disclosure, a search processing device is provided, comprising: a processor; and a memory coupled to the processor, for storing instructions, which, when executed by the processor, causes the processor to execute a search processing method as described in any embodiment of the present disclosure.

[0032] According to some further embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the program is executed by a processor, the search processing method of any embodiment of the present disclosure is implemented.

[0033] According to some further embodiments of the present disclosure, a computer program product is provided, comprising: instructions, wherein when the instructions are executed by a processor, the search processing method of any embodiment of the present disclosure is implemented.

[0034] According to some further embodiments of the present disclosure, a computer program is provided, comprising: instructions, wherein when the instructions are executed by a processor, the search processing method of any embodiment of the present disclosure is implemented.

[0035] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The drawings described herein are used to provide a further understanding of the present disclosure. Each of the drawings, together with the following detailed description, is included in this specification and forms a part of the specification to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and do not constitute a limitation of the present disclosure. In the drawings:

[0037] FIG1 is a schematic flow chart showing a search processing method according to some embodiments of the present disclosure;

[0038] FIG2 is a schematic diagram illustrating a search result page according to some embodiments of the present disclosure;

[0039] FIG3 is a schematic diagram showing a search result page according to some other embodiments of the present disclosure;

[0040] FIG4 shows a schematic diagram of a search result page according to yet other embodiments of the present disclosure;

[0041] FIG5 shows a schematic diagram of a search result page according to still other embodiments of the present disclosure;

[0042] FIG6 shows a schematic diagram of a search result page according to yet other embodiments of the present disclosure;

[0043] FIG7 is a schematic structural diagram of a search processing device according to some embodiments of the present disclosure;

[0044] FIG8 is a schematic structural diagram of a search processing device according to yet other embodiments of the present disclosure;

[0045] FIG9 shows a schematic structural diagram of a search processing device according to still other embodiments of the present disclosure.

[0046] It should be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not necessarily drawn to scale. The same or similar reference numerals are used throughout the drawings to indicate the same or similar parts. Therefore, once an item is defined in one drawing, it may not be discussed further in subsequent drawings. DETAILED DESCRIPTION

[0047] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. However, it is obvious that the embodiments described are only some embodiments of the present disclosure, rather than all embodiments. The following description of the embodiments is actually only illustrative and is in no way intended to limit the present disclosure and its application or use. It should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein.

[0048] It should be understood that the various steps described in the method embodiments of the present disclosure can be performed in different orders and / or performed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments should be interpreted as being merely exemplary and do not limit the scope of the present disclosure.

[0049] As used in this disclosure, the term "include" and its variations are intended to be open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to." Furthermore, the term "comprise" and its variations are intended to be open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to." Therefore, "include" and "include" are synonymous. The term "based on" means "based, at least in part, on."

[0050] Reference throughout this specification to "one embodiment," "some embodiments," or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. For example, the term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Furthermore, the appearances of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment, but may.

[0051] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules, or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules, or units. Unless otherwise specified, concepts such as "first" and "second" are not intended to imply that the objects described in such a manner must be in a given order in time, space, ranking, or any other manner.

[0052] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0053] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0054] The following detailed description of the embodiments of the present disclosure is provided in conjunction with the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. In addition, in one or more embodiments, specific features, structures, or characteristics may be combined in any suitable manner that will be apparent to those skilled in the art from this disclosure.

[0055] In the related art, users search by entering keywords, sentences, etc., and relevant content is displayed. In particular, for video search, by matching the keywords entered by the user with the video, only some related videos and video titles are displayed to the user, resulting in poor search results and a poor user experience.

[0056] A technical problem to be solved by the present disclosure is: how to improve the accuracy and effectiveness of search and enhance the search effect.

[0057] This disclosure proposes a search processing method that is applicable to video search scenarios and human-computer conversation scenarios, which can improve the accuracy and effectiveness of searches, enhance search and display effects, and enhance user experience. The following description is based on Figures 1 to 5.

[0058] Figure 1 is a flow chart of some embodiments of the search processing method disclosed herein. As shown in Figure 1 , the method of this embodiment includes steps S102 to S104.

[0059] In step S102 , a question input by a user is received.

[0060] A search box can be set up to receive user input in the form of text, voice, or images. Information inputted by the user can be received in a variety of ways. Information inputted by the user can be received directly on the search page, or it can be received on another page and then redirected to the search page for display. For example, information inputted by the user can be received on a human-computer interaction conversation page and then redirected to the search page. This is not limited to the examples given.

[0061] In some embodiments, the user input is used to determine whether the information is a question. For example, semantic and grammatical recognition may be performed on the text input by the user to determine whether the text is a question; speech recognition may be performed on the user's voice to determine whether the speech is a question; or image recognition may be performed on the user's image to determine whether the image is a question, without limitation. If the information input by the user is a question, the question-and-answer search function is automatically triggered.

[0062] In step S104, based on the question, the answer to the question and a plurality of answer videos related to the question are displayed on the search result page.

[0063] In some embodiments, the answer is a sentence described in natural language generated by machine understanding of multiple answer videos, and includes description information of each answer video generated by machine understanding of each answer video in the multiple answer videos.

[0064] In some embodiments, based on the question, a first neural network model (or a first machine learning model) is used to perform machine understanding on multiple videos in a first database, obtain multiple answer videos related to the question from the multiple videos, and generate description information for each answer video; and generate an answer based on the description information of each answer video.

[0065] The first database can be configured to store multiple videos for answering questions raised by users, that is, multiple videos can be used for video Q&A. The first database can also store other resources such as text, images, audio, etc. for answering questions raised by users. Each video is input into the first neural network for machine understanding to obtain description information of each video. For example, the first neural network can perform multimodal recognition of the subtitles, titles, images, voice, etc. of each video to understand the content of each video, generate description information of each video and select answer videos related to the question. For example, each video can be sorted according to one or more indicators such as the relevance of each video to the question, search popularity (number or frequency), number of user comments, number of user likes, number of user views, etc., and the video ranked before the preset ranking is selected as the answer video related to the question. For example, each video is sorted and the top 3 or top 4 videos are selected as the answer video.

[0066] After selecting multiple answer videos, a natural language answer can be generated based on the descriptions of each answer video, or by combining the descriptions of each answer video with knowledge from a pre-set knowledge base. The answer can be a paragraph consisting of one or more sentences, tailored to the user's reading habits and meeting pre-set requirements for coherence and fluency, thereby enhancing the user experience.

[0067] The answer can be presented in the form of text or played through voice, etc. For example, the answer is displayed in the form of text, and a voice playback control is set at the corresponding position of the text. When the user triggers the voice playback control, the voice corresponding to the text is played.

[0068] In some embodiments, a reference identifier of each answer video is displayed at a corresponding position of the description information of each answer video in the answer; and a reference identifier of each answer video is displayed on each answer video.

[0069] The specific form of the reference mark can be set according to the actual situation. For example, the reference mark can take various forms such as numbers, video keywords, and video titles. The reference mark can be set after the description information of the corresponding answer video to indicate that the description information of the corresponding answer video is before the reference mark. The position of the reference mark can also be adjusted according to the actual situation. The reference mark can be displayed on each answer video by adding a layer (such as a mask), or other forms can be used, not limited to the examples given.

[0070] For example, as shown in FIG2 , the reference identifier may be set in the form of a superscript after the description information of each answer video.

[0071] In some embodiments, a trigger operation of a user on a reference mark displayed in an answer is received; and an answer video corresponding to the reference mark is played.

[0072] The triggering operation can be in various forms, such as clicking or selecting, and is not limited in this disclosure. The answer video corresponding to the reference identifier can be played on a video playback page different from the search results page, or the answer video can be played on the search results page, or in a floating window. The playback form is not limited to the examples given.

[0073] The search results page, also known as the Q&A results page, displays the answer and multiple answer videos based on the user's question, though it's also possible to display only one answer video. In some embodiments, the search results page as a whole supports sliding display. For example, it can receive a user's left-right or up-down swipe in a preset direction to display more content. When the swipe reaches a preset boundary, a prompt message can be displayed. The search results page as a whole also supports zooming in and out, allowing users to zoom in and out of the search results page using preset operations.

[0074] In some embodiments, the search results page includes a fixed display area and a search card area that supports sliding display. The answer and multiple answer videos are displayed in the search card area, that is, the answer and multiple answer videos as a whole support sliding display. Of course, the area displaying the answer can also be located in the fixed display area, and the area displaying multiple answer videos can also be located in the fixed display area, which will not be repeated here.

[0075] For example, the fixed display area includes at least one of an input area and an options area. As shown in Figure 2, the top of the search results page is the input area, which can be used to set at least one of a search control and a voice control. For example, in response to a user clicking on the input area, a keyboard area pops up to receive user input and a user triggering operation on the search control, and then a search card area is displayed.

[0076] As shown in Figure 2, the fixed display area also includes an options area, which is located below the input area. The options area includes multiple option controls, each of which is used to trigger different search scenarios or search scopes. Upon receiving a user trigger operation on any option control, search results related to the user input are obtained based on the search scenario or search scope corresponding to the triggered option control, and the search results are displayed.

[0077] For example, the first option control is used to trigger a video Q&A scenario, receives a user trigger on the first option control and the user's input question, and displays the answer and multiple answer videos. For example, the second option control is used to trigger a user search scenario, receives a user trigger on the second option control and the user's input information, and displays multiple related user information. For example, the third option control is used to trigger a video search scenario, receives a user trigger on the third option control and the user's input information, and displays multiple related videos. For example, the fourth option control is used to trigger an audio search scenario, receives a user trigger on the fourth option control and the user's input information, and displays multiple related audios. For example, the fifth option control is used to trigger a shopping search scenario, receives a user trigger on the fifth option control and the user's input information, and displays multiple related audios. For example, the sixth option control is used to trigger a live broadcast search scenario, receives a user trigger on the sixth option control and the user's input information, and displays multiple related live broadcasts.

[0078] The order of triggering the option control and receiving the information input by the user can be adjusted, and is not limited to the examples given above. The setting of the option control and the search scenario can be based on actual needs and is not limited to the examples given above. Different search scenarios can use different databases and different neural networks (or machine learning models) for search. The option area can also be set in the search card area, or as a separate area, supporting sliding display, for example, the option area supports left and right sliding display.

[0079] In some embodiments, the search card area includes a first area and a second area, with the answer displayed in the first area and multiple answer videos displayed in the second area. As shown in Figure 2, the first area can be located above the second area to better suit the user's reading habits and improve the display effect.

[0080] In some embodiments, multiple answer videos can be displayed in a sliding manner within the second area. Upon receiving a user's sliding operation, the answer videos within the second area are displayed. This allows more answer videos to be displayed within a limited page area, providing users with richer content.

[0081] Each answer video is displayed in a preset size. When the total display range of multiple answer videos exceeds the display range of the second area, some of the multiple answer videos can be fully displayed, and the remaining answer videos may be incompletely displayed or not displayed. Upon receiving the user's sliding operation, the remaining answer videos within the display range of the second area are displayed.

[0082] As shown in FIG2 , there are three answer videos in the second area. The first two answer videos are displayed in full, and the third video is displayed incompletely. The third answer video can be displayed by the user sliding to the left.

[0083] In some embodiments, the display range of the answer is adjusted based on the length of the answer. As shown in Figures 3 and 4, when the answer is short, the display range of the answer is smaller, allowing more of the remaining information to be displayed on the page. When the answer is long, the display range of the answer is larger, occupying a larger area on the page.

[0084] Multiple answer videos can display preview information, play automatically, or have some videos display preview information and others play automatically. When the answer display range is adjusted to the length of the answer, the position of the answer video on the search results page is uncertain. Furthermore, when the search card area supports sliding display, the position of the answer video on the search results page is also uncertain. Therefore, the automatic playback or display of preview information for the answer video can be adjusted based on the display situation.

[0085] In some embodiments, if the display range of the answer is within a first preset range, some or all of the multiple answer videos are automatically played. If the display position of the answer is outside the first preset range, preview information of the multiple answer videos is displayed. For example, if the display range of the answer is within the first preset range, the answer videos within the display range of the second area are automatically played. For example, as shown in Figure 2, if there are three answer videos in the second area, the first two answer videos are automatically played. Alternatively, if the display range of the answer is within the first preset range, the first answer video is automatically played.

[0086] In some embodiments, when the display position of the bottom of the last row of answers is above the first reference line, some or all of the multiple answer videos are automatically played.

[0087] The first reference line can be fixed. For example, the first reference line can be used to limit the display range of the answer. For example, as shown in Figure 3, a title can be displayed above the answer to indicate that the text is the answer. The first reference line can be set to a preset distance from the bottom of the title.

[0088] If the display position of the bottom of the last line of the answer (for example, the horizontal line at the bottom of the last line of text) is above the first reference line, it means that the current display range of the answer is small, and the answer video is displayed completely on the search results page and is located relatively centrally or above the search results page. In this case, the answer video is within the user's field of view, and automatically playing part or all of the answer video can improve the display effect and attract users to watch the answer video without jumping to the page, making it easier for users to watch the answer video.

[0089] In some embodiments, when the display position of the bottom of the last line of answers is below a first reference line and the display position of the top of the first line of answers (for example, the horizontal line at the top of the first line of text) is above a second reference line, some or all of the answer videos in a plurality of answer videos are automatically played, wherein the second reference line is above the first reference line.

[0090] The second reference line can be fixed, and the second reference line can be the top position of the search card area. For example, as shown in Figure 4, the second reference line can be the bottom position of the option area. The display position of the top of the first row of answers is above the second reference line, which can indicate that the search card area is slid upward, and the answer video is fully displayed in the search results page and is located in a relatively central or upper position in the search results page. In this case, the answer video is within the user's line of sight, and automatic playback of part or all of the answer video can improve the display effect and attract users to watch the answer video. There is no need to jump to the page, which is convenient for users to watch the answer video.

[0091] The fully displayed answer videos can be automatically played, or a preset number of answer videos can be automatically played in the order of display, or all answer videos can be automatically played. The specific answer videos to be automatically played can be set and are not limited to the examples given.

[0092] In some embodiments, a user triggering operation for any of a plurality of answer videos is received; and the corresponding answer video is played. The corresponding answer video can be played on a video playback page different from the search results page, on the search results page, or in a floating window, without limitation to the examples given.

[0093] In some embodiments, the display range of the first area is adaptively adjusted according to the length of the answer within the second preset range. The display range of the first area is the display range of the answer, and the second preset range is used to limit the maximum display range of the answer.

[0094] In some embodiments, when the length of the answer exceeds a second preset range, the content of the answer that exceeds the second preset range is hidden, and an expansion control is displayed; upon receiving a user trigger operation on the expansion control, the answer is fully displayed.

[0095] In some embodiments, when the length of the answer exceeds a second preset range and the answer is displayed in full, a hiding control is displayed; upon receiving a user trigger operation on the hiding control, the content of the answer that exceeds the second preset range is hidden.

[0096] As shown in Figure 2, an expansion control (View Larger) can be displayed at the end of the answer display. The user can trigger it by clicking, etc. The display effect after expansion is shown in Figure 5. As shown in Figure 5, a hide control can also be displayed at the end of the answer display. The user can hide part of the content by triggering the hide control (Show Less). The display effect after hiding is shown in Figure 2.

[0097] In the case of long answers, partial answer content can be hidden to allow more of the answer video to be displayed, allowing the search results page to display richer content, improving the display effect and enhancing the user's reading experience. By expanding the hidden content, users can easily view the complete answer.

[0098] In some embodiments, one or more candidate questions are displayed in a search results page based on the question and the multiple answer videos.

[0099] One or more candidate questions are related to the question and some or all of the multiple answer videos. For example, a candidate question could be "Can more answer videos be displayed?" One or more candidate questions can be generated by machine understanding the question and multiple answer videos. As shown in Figure 2, one or more candidate questions can be displayed in a third area, which can be below the second area to align with the user's reading order and improve the display quality. The third area can be located in the search card area.

[0100] In some embodiments, a user selection operation of any candidate question from one or more candidate questions is received, and the page is redirected to a conversation page; on the conversation page, an answer to the selected candidate question is displayed.

[0101] The conversation page can receive questions entered by the user and display the corresponding answers. For example, the conversation page is a human-computer interaction page. The conversation page can display the selected candidate question and the corresponding answer, and can also display other candidate questions.

[0102] By directly displaying one or more candidate questions, users can directly ask subsequent questions without having to input questions, thereby improving convenience and display effects.

[0103] In some embodiments, an entry control for continuing to ask questions is displayed on the search results page; a user triggers the entry control to jump to a conversation page. In some embodiments, at least one of an answer and a candidate question is displayed on the conversation page.

[0104] As shown in Figure 2, the entry control can be set in the third area, in the same area as one or more candidate questions. The entry control can be set in front of one or more candidate questions according to the reading direction, and is not limited to the examples given. When entering the conversation page through the entry control, the conversation page can display the answer from the search results page, and can also display one or more candidate questions. The user receives a selection operation for any candidate question from the one or more candidate questions, and the answer to the selected candidate question is displayed on the conversation page.

[0105] In some embodiments, a plurality of recommended videos related to a question are displayed on a search result page, wherein a search strategy for the plurality of recommended videos is different from a search strategy for the plurality of answer videos. The search strategy may include at least one of a search algorithm and a selection index.

[0106] The neural network model (or machine learning model) used to generate the recommended videos can be different from the neural network model (or machine learning model) used to generate the answer videos, that is, the search algorithms are different. The selection criteria for selecting recommended videos and answer videos can be different. For example, a comprehensive index can be determined based on multiple indicators such as the relevance of each video to the question, search popularity (number or frequency), number of user comments, number of user likes (degree of popularity), and number of user views. The videos can be sorted based on the comprehensive index, and the videos ranked before the first preset ranking can be selected as the answer videos related to the question; the videos can be sorted based on the number of user likes, and the videos ranked before the second preset ranking can be selected as the recommended videos related to the question.

[0107] As shown in FIG. 2 , a plurality of recommended videos may be displayed in the fourth area, and the fourth area may be set in the search card area.

[0108] In some embodiments, a user triggering operation for any of a plurality of recommended videos is received; and the corresponding recommended video is played. The recommended video can be played on a video playback page different from the search results page, on the search results page, or in a floating window, without limitation to the examples given.

[0109] By displaying recommended videos, the content in the search results page can be enriched, the display effect can be improved, and the different needs of users can be met, thereby improving the user experience.

[0110] In some embodiments, reference indicators are displayed on each answer video and / or each recommended video. Reference indicators may include, for example, relevance to the question, search popularity (number or frequency), number of user comments, number of user likes (degree of popularity), number of user views, and so on. For example, the reference indicators may be displayed in a new layer on the video, without limitation to the examples given.

[0111] In some embodiments, a first operation of a user on any answer video among a plurality of answer videos is received; and the answer video corresponding to the first operation is switched from a first display state to a second display state.

[0112] In some embodiments, a second operation of the user on a control in the search results page is received; and the control corresponding to the second operation is switched from the third display state to the fourth display state.

[0113] The first operation and the second operation may be the same or different operations. For example, the first operation and the second operation are both pressing, or the first operation is pressing and the second operation is selecting, without limitation to the examples given.

[0114] As shown in Figure 6, after receiving the user's first operation, the answer video corresponding to the first operation can be switched from the first display state to the second display state by setting a first mask. For example, the display color, transparency, and other states of the answer video can be changed by the first mask. After receiving the user's second operation, the control corresponding to the second operation can be switched from the third display state to the fourth display state by setting a second mask. Changing the display color, transparency, and other states of the control by the second mask is not limited to the examples given. The color, transparency, and other states of the first and second masks can be different.

[0115] The switching of the display state of the answer video is also applicable to the recommended video. A first operation of the user on any recommended video among multiple recommended videos is received; and the recommended video corresponding to the first operation is switched from the first display state to the second display state.

[0116] By switching the display status of the video or control, users can intuitively feel the operation of the video or control, improving the display effect and user experience.

[0117] In the search processing method of the above embodiment, a question input by a user is received, and the answer to the question and multiple answer videos related to the question can be displayed on the search results page according to the question. The answer is a sentence described in natural language generated by machine understanding of multiple answer videos, and the answer includes description information of each answer video generated by machine understanding of each answer video in the multiple answer videos. The method of the above embodiment changes the traditional video search method and can automatically answer the question input by the user and display relevant answer videos. The answer is generated based on machine understanding of the video, and the description information of multiple answer videos in the answer is associated and fused and expressed in natural language. After entering the question, the user can intuitively see the answer to the question and the answer video, and clearly know the relationship between the answer video and the answer, understand the content of the answer video description, and facilitate further viewing of the detailed content of the answer video. The method of the above embodiment improves the accuracy and effectiveness of the search, improves the search effect and display effect, and enhances the user experience.

[0118] The above embodiments mainly describe how to respond to and display questions input by users.

[0119] In some embodiments, information input by a user is received; if the input information is not a question, a second neural network (or a second machine learning model) is used to perform machine understanding on multiple multimedia contents in a second database based on the input information, and multiple target multimedia contents related to the input information are obtained from the multiple multimedia contents; and the multiple target multimedia contents are displayed in a search results page.

[0120] A second database may be provided to store multimedia content for search. The multimedia content may include, for example, at least one of text, voice, image, and video. If the multimedia content is a video, the methods for displaying the answer video or recommended video described in the above embodiments are also applicable.

[0121] In some embodiments, a user trigger operation on any target multimedia content is received, and detailed information of the corresponding multimedia content is further displayed, for example, playing a video or audio, or enlarging and displaying text or images.

[0122] Different searches are performed and different content is displayed for different types of information input by users, which improves the search and display effects, meets the different needs of users, and improves the user experience.

[0123] The directions of up, down, left, and right in this disclosure are based on the general reading direction of the page. The triggering operations for different videos and controls in this disclosure can be different types of operations, for example, some triggering operations are clicks, and some triggering operations are selections, which are not limited here.

[0124] The present disclosure also provides a search processing device, which will be described below in conjunction with FIG. 7 .

[0125] FIG7 is a structural diagram of some embodiments of the search processing device disclosed herein. As shown in FIG7 , the device 70 of this embodiment includes: a receiving module 710 and a display module 720 .

[0126] The receiving module 710 is configured to receive a question input by a user.

[0127] The display module 720 is configured to display the answer to the question and multiple answer videos related to the question in the search result page according to the question, wherein the answer is a sentence described in natural language generated by machine understanding of the multiple answer videos, and includes description information of each answer video generated by machine understanding of each answer video in the multiple answer videos.

[0128] In some embodiments, the display module 720 is configured to display a reference identifier of each answer video at a corresponding position of the description information of each answer video in the answer; and to display a reference identifier of each answer video on each answer video.

[0129] In some embodiments, the receiving module 710 is further configured to receive a user's triggering operation on a reference identifier displayed in the answer; the display module 720 is further configured to play an answer video corresponding to the reference identifier.

[0130] In some embodiments, the display module 720 is further configured to display one or more candidate questions in the search result page based on the question and the multiple answer videos.

[0131] In some embodiments, the receiving module 710 is further configured to receive a user's selection operation of any candidate question from the one or more candidate questions;

[0132] In some embodiments, the display module 720 is further configured to jump to a conversation page where answers to the selected candidate questions are displayed.

[0133] In some embodiments, the display module 720 is also configured to display an entry control for continuing to ask questions in the search results page; the receiving module 710 is also configured to receive the user's trigger operation on the entry control, and the display module 720 is also configured to jump to the conversation page and display the conversation page.

[0134] In some embodiments, the display module 720 is further configured to display at least one of the answer and the candidate question in the conversation page.

[0135] In some embodiments, the display module 720 is configured to automatically play part or all of the multiple answer videos when the display range of the answer is within a first preset range.

[0136] In some embodiments, the display module 720 is configured to display preview information of multiple answer videos when the display position of the answer is outside the first preset range.

[0137] In some embodiments, the display module 720 is configured to automatically play part or all of the multiple answer videos when the display position of the bottom of the last row of answers is above the first reference line.

[0138] In some embodiments, the display module 720 is configured to automatically play some or all of the multiple answer videos when the display position of the bottom of the last row of answers is below a first reference line and the display position of the top of the first row of answers is above a second reference line, wherein the second reference line is above the first reference line.

[0139] In some embodiments, the search result page includes a fixed display area and a search card area that supports sliding display, and the display module 720 is configured to display the answer and multiple answer videos in the search card area.

[0140] In some embodiments, the search card area includes a first area and a second area, and the display module 720 is configured to display the answer in the first area, wherein the display range of the first area is adaptively adjusted according to the length of the answer within a second preset range; and display multiple answer videos in the second area, wherein the multiple answer videos support sliding display in the second area.

[0141] In some embodiments, the display module 720 is configured to hide the content in the answer that exceeds the second preset range and display an expansion control when the length of the answer exceeds the second preset range; the receiving module 710 is also configured to receive the user's trigger operation on the expansion control, and the display module 720 is configured to display the answer in full.

[0142] In some embodiments, the display module 720 is configured to display a hidden control when the length of the answer exceeds a second preset range and the answer is displayed in full; the receiving module 710 is also configured to receive a user trigger operation on the hidden control, and the display module 720 is configured to hide the content in the answer that exceeds the second preset range.

[0143] In some embodiments, the receiving module 710 is further configured to receive a first operation of a user on any answer video among a plurality of answer videos; the display module 720 is further configured to switch the answer video corresponding to the first operation from a first display state to a second display state.

[0144] In some embodiments, the receiving module 710 is further configured to receive a second operation of the user on a control in the search results page; the display module 720 is further configured to switch the control corresponding to the second operation from the third display state to the fourth display state.

[0145] In some embodiments, the display module 720 is further configured to display a plurality of recommended videos related to the question on the search result page, wherein the search strategies of the plurality of recommended videos and the plurality of answer videos are different.

[0146] In some embodiments, the receiving module 710 is further configured to receive a user's triggering operation on any recommended video among the plurality of recommended videos; and the display module 720 is further configured to play the any recommended video.

[0147] In some embodiments, the receiving module 710 is further configured to receive a user's triggering operation on any answer video among the multiple answer videos; the display module 720 is further configured to play the arbitrary answer video.

[0148] In some embodiments, the search processing device also includes: a control module 730, which is configured to use a first neural network model to perform machine understanding on multiple videos in the first database based on the question, obtain multiple answer videos related to the question from the multiple videos, and generate description information for each answer video; generate an answer based on the description information of each answer video.

[0149] In some embodiments, the receiving module 710 is further configured to receive information input by a user; the control module 730 is further configured to use a second neural network to perform machine understanding of multiple multimedia contents in the second database based on the input information, and obtain multiple target multimedia contents related to the input information from the multiple multimedia contents; the display module 720 is further configured to display multiple target multimedia contents in the search results page.

[0150] The search processing apparatus in the embodiments of the present disclosure may be implemented by various computing devices or computer systems, which will be described below in conjunction with FIG. 8 and FIG. 9 .

[0151] FIG8 is a block diagram of some embodiments of the search processing apparatus of the present disclosure. As shown in FIG8 , the apparatus 80 of this embodiment includes: a memory 810 and a processor 820 coupled to the memory 810 , wherein the processor 820 is configured to execute the search processing method of any of the embodiments of the present disclosure based on instructions stored in the memory 810 .

[0152] The memory 810 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, a database, and other programs.

[0153] FIG9 is a structural diagram of some other embodiments of the search processing device disclosed herein. As shown in FIG9 , the device 90 of this embodiment includes: a memory 910 and a processor 920, which are similar to the memory 810 and the processor 820, respectively. It may also include an input / output interface 930, a network interface 940, a storage interface 950, and the like. These interfaces 930, 940, 950 and the memory 910 and the processor 920 can be connected, for example, via a bus 960. Among them, the input / output interface 930 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 940 provides a connection interface for various networked devices, such as a database server or a cloud storage server. The storage interface 950 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0154] The present disclosure further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the search processing method of any embodiment of the present disclosure is implemented.

[0155] The present disclosure also provides a computer program having instructions stored thereon, wherein when the instructions are executed by a processor, the search processing method of any embodiment of the present disclosure is implemented.

[0156] The present disclosure further provides a computer program product having instructions stored thereon, wherein when the instructions are executed by a processor, the search processing method of any embodiment of the present disclosure is implemented.

[0157] Those skilled in the art will appreciate that embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0158] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be interpreted as each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0159] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0161] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A search processing method, comprising: Receive user input questions; Based on the question, the answer to the question and multiple answer videos related to the question are displayed in the search results page, wherein the answer is a sentence described in natural language generated by machine understanding of the multiple answer videos, and includes description information of each answer video generated by machine understanding of the multiple answer videos.

2. The search processing method according to claim 1, wherein: The step of displaying the answer to the question and a plurality of answer videos related to the question in the search result page comprises: Displaying a reference identifier of each answer video at a corresponding position of the description information of each answer video in the answer; A reference mark of each answer video is displayed on each answer video.

3. The search processing method according to claim 2, further comprising: receiving a triggering operation of the user on the reference identifier displayed in the answer; Play the answer video corresponding to the reference identifier.

4. The search processing method according to any one of claims 1 to 3, further comprising: One or more candidate questions are displayed in the search result page based on the question and the multiple answer videos.

5. The search processing method according to claim 4, further comprising: receiving a selection operation of the user on any candidate question among the one or more candidate questions, and jumping to a conversation page; On the conversation page, answers to the selected candidate questions are displayed.

6. The search processing method according to any one of claims 1 to 5, further comprising: Displaying an entry control for continuing to ask questions on the search result page; Receive the user's triggering operation on the entry control and jump to the session page.

7. The search processing method according to claim 6, further comprising: At least one of the answer and the candidate question is displayed in the conversation page.

8. The search processing method according to any one of claims 1 to 7, wherein: The step of displaying the answer to the question and a plurality of answer videos related to the question in the search result page comprises: When the display range of the answer is within a first preset range, part or all of the multiple answer videos are automatically played.

9. The search processing method according to claim 8, wherein: The displaying of the answer to the question and a plurality of answer videos related to the question in the search result page also includes: When the display position of the answer is outside the first preset range, preview information of the multiple answer videos is displayed.

10. The search processing method according to claim 8 or 9, wherein: When the display range of the answer is within a preset range, automatically playing part or all of the multiple answer videos includes: When the display position of the bottom of the last row of the answer is above the first reference line, some or all of the multiple answer videos are automatically played.

11. The search processing method according to claim 10, wherein: When the display range of the answer is within a preset range, automatically playing part or all of the multiple answer videos also includes: When the display position of the bottom of the last row of answers is below a first reference line and the display position of the top of the first row of answers is above a second reference line, some or all of the multiple answer videos are automatically played, wherein the second reference line is above the first reference line.

12. The search processing method according to any one of claims 1 to 11, wherein: The search result page includes a fixed display area and a search card area that supports sliding display, and the answer to the question and multiple answer videos related to the question displayed in the search result page also include: The answer and the plurality of answer videos are displayed in the search card area.

13. The search processing method according to claim 12, wherein: The search card area includes a first area and a second area, and displaying the answer and the plurality of answer videos in the search card area includes: Displaying the answer in the first area, wherein the display range of the first area is adaptively adjusted within a second preset range according to the length of the answer; The multiple answer videos are displayed in the second area, wherein the multiple answer videos support sliding display in the second area.

14. The search processing method according to claim 13, wherein: Displaying the answer in the first area includes: When the length of the answer exceeds the second preset range, hiding the content of the answer that exceeds the second preset range, and displaying an expansion control; A triggering operation of the expansion control by the user is received, and the answer is fully displayed.

15. The search processing method according to claim 14, wherein: The displaying the answer in the first area further comprises: When the length of the answer exceeds the second preset range and the answer is completely displayed, displaying a hidden control; A triggering operation of the hiding control by the user is received, and the content of the answer exceeding the second preset range is hidden.

16. The search processing method according to any one of claims 1 to 15, further comprising: Receiving a first operation of the user on any answer video among the multiple answer videos; The answer video corresponding to the first operation is switched from a first display state to a second display state.

17. The search processing method according to any one of claims 1 to 16, further comprising: receiving a second operation of the user on a control in the search result page; The control corresponding to the second operation is switched from the third display state to the fourth display state.

18. The search processing method according to any one of claims 1 to 17, further comprising: A plurality of recommended videos related to the question are displayed on the search result page, wherein the search strategies of the plurality of recommended videos and the plurality of answer videos are different.

19. The search processing method according to claim 18, further comprising: receiving a triggering operation of the user on any recommended video among the plurality of recommended videos; Play any of the recommended videos.

20. The search processing method according to any one of claims 1 to 19, further comprising: Receiving a trigger operation of the user on any answer video among the multiple answer videos; Play the arbitrary answer video.

21. The search processing method according to any one of claims 1 to 20, wherein: According to the question, displaying the answer to the question and a plurality of answer videos related to the question in the search result page includes: According to the question, using a first neural network model, machine understanding is performed on multiple videos in a first database, multiple answer videos related to the question are obtained from the multiple videos, and description information of each answer video is generated; The answer is generated according to the description information of each answer video.

22. The search processing method according to claim 21, further comprising: receiving information input by the user; In the case where the input information is not a problem, using a second neural network to perform machine understanding on a plurality of multimedia contents in a second database according to the input information, and obtaining a plurality of target multimedia contents related to the input information from the plurality of multimedia contents; The plurality of target multimedia contents are displayed in the search result page.

23. A search processing device, comprising: A receiving module, configured to receive a question input by a user; The display module is configured to display the answer to the question and multiple answer videos related to the question in a search result page according to the question, wherein the answer is a sentence described in natural language generated by machine understanding of the multiple answer videos, and includes description information of each answer video generated by machine understanding of the multiple answer videos.

24. A search processing device, comprising: processor; as well as A memory coupled to the processor, for storing instructions, wherein when the instructions are executed by the processor, the processor executes the search processing method according to any one of claims 1 to 22.

25. A computer-readable storage medium having a computer program stored thereon, wherein: When the program is executed by a processor, the search processing method described in any one of claims 1 to 22 is implemented.

26. A computer program product comprising: Instructions, wherein when the instructions are executed by a processor, the search processing method according to any one of claims 1 to 22 is implemented.

27. A computer program comprising: Instructions, wherein when the instructions are executed by a processor, the search processing method according to any one of claims 1 to 22 is implemented.

Images