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

Abstract

This disclosure relates to a search processing method and apparatus, and a computer-readable storage medium, and relates to the field of artificial intelligence. The search processing method of this disclosure includes receiving a question entered by a user and, based on the question, displaying the answer to the question and a plurality of answer videos related to the question on a search results page, wherein the answer is a sentence written in natural language generated by machine understanding of the plurality of answer videos, and includes descriptive information of each answer video generated by machine understanding of each of the plurality of answer videos.

Description

Technical Field

[0001] Cross-reference to Related Applications This application is based on and claims priority to a Chinese patent application with application number 202311140509.1 and filing date September 5, 2023, the disclosure of which is hereby incorporated herein by reference in its entirety.

[0002] This disclosure relates to the field of artificial intelligence technology, and particularly to a search processing method and apparatus, and a computer-readable storage medium.

Background Art

[0003] With the development of Internet technology, users can obtain various information from the Internet platform, and information acquisition has become more and more convenient.

[0004] Search is a commonly used information acquisition means. Generally, users input keywords, sentences, etc. to search and display some related content.

Summary of the Invention

[0005] To introduce the concept in a simplified form, a summary part of the invention is provided. These concepts will be described in detail in the embodiment part for implementing the following invention. The summary part of the invention is not intended to identify the key features or essential features of the claimed technical solution, nor is it used to limit the scope of the claimed technical solution.

[0006] According to some embodiments of the present disclosure, a search processing method is provided. The method includes receiving a question input by a user, and based on the question, displaying an answer to the question and a plurality of answer videos related to the question on a search result page. Here, the answer is a sentence described in natural language generated by machine-understanding a plurality of answer videos, and includes description information of each answer video generated by machine-understanding each answer video among the plurality of answer videos.

[0007] In some embodiments, displaying the answer to a question and multiple answer videos related to the question on a search results page includes displaying a citation for each answer video at the appropriate location in the descriptive information for each answer video in the answer, and displaying a citation for each answer video within each answer video.

[0008] In some embodiments, the search processing method further includes receiving a trigger operation for a citation mark displayed in the user's response and playing the response video corresponding to the citation mark.

[0009] In some embodiments, the search processing method further includes displaying one or more suggested questions on the search results page based on the question and multiple answer videos.

[0010] In some embodiments, the search process further includes receiving a selection operation from the user for one or more candidate questions, jumping to a conversation page, and displaying the answer to the selected candidate question on the conversation page.

[0011] In some embodiments, the search processing method further includes displaying an entry control on the search results page for the user to continue asking questions, and accepting a trigger operation on the user's entry control to jump to a conversation page.

[0012] In some embodiments, the search processing method further includes displaying at least one of the answers and suggested questions on the conversation page.

[0013] In some embodiments, displaying the answer to a question and multiple answer videos related to the question on the search results page includes automatically playing some or all of the multiple answer videos when the display range of the answers falls within a first predetermined range.

[0014] In some embodiments, displaying the answer to a question and multiple answer videos related to the question on the search results page further includes displaying preview information for the multiple answer videos if the display position of the answer is outside a first predetermined range.

[0015] In some embodiments, automatically playing some or all of multiple answer videos when the display range of an answer is within a preset range includes automatically playing some or all of the multiple answer videos when the display position of the bottom of the last line of an answer is above a first reference line.

[0016] In some embodiments, automatically playing some or all of multiple answer videos when the display range of an answer is within a preset range further includes automatically playing some or all of the multiple answer videos when the display position of the bottom of the last line of an answer is below a first baseline and the display position of the top of the first line of an answer is above a second baseline, where the second baseline is above the first baseline.

[0017] In some embodiments, the search results page includes a fixed display area and a search card area that supports swipe display, and displaying the answer to a question and multiple answer videos related to the question on the search results page further includes displaying the answer and multiple answer videos in the search card area.

[0018] In some embodiments, the search card area includes a first area and a second area, and displaying the answer 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 swipe display within the second area.

[0019] In some embodiments, displaying the answer in a first area includes, if the length of the answer exceeds a second predetermined range, hiding the content of the answer that exceeds a second predetermined range, displaying an expand control, and accepting a trigger operation on the user's expand control to fully display the answer.

[0020] In some embodiments, displaying the answer in a first area further includes displaying a hide control when the length of the answer exceeds a second preset range and the answer is fully displayed, and accepting a user trigger operation on the hide control to hide the content of the answer that exceeds the second preset range.

[0021] In some embodiments, the search processing method further includes receiving a first operation on one of the user's multiple answer videos, and switching the answer video corresponding to the first operation from a first display state to a second display state.

[0022] In some embodiments, the search processing method further includes receiving a second operation on a control on the user's search results page and switching the control corresponding to the second operation from a third display state to a fourth display state.

[0023] In some embodiments, the search processing method further includes displaying multiple recommended videos related to the question on the search results page, wherein the multiple recommended videos differ from the search policy of multiple answer videos.

[0024] In some embodiments, the search processing method further includes receiving a trigger operation for one of the user's recommended videos and playing that recommended video.

[0025] In some embodiments, a trigger operation for any one of a plurality of response videos of a user is received, and any one of the response videos is played.

[0026] In some embodiments, displaying, based on a question, an answer to the question and a plurality of response videos related to the question on a search result page includes: using a first neural network model to mechanically understand a plurality of videos in a first database based on the question, obtaining a plurality of response videos related to the question from the plurality of videos, generating description information for each response video, and generating an answer based on the description information of each response video.

[0027] In some embodiments, the search processing method further includes: receiving information input by a user, and when the input information is not a question, mechanically understanding a plurality of multimedia contents in a second database based on the input information using a second neural network, obtaining a plurality of target multimedia contents related to the input information from the plurality of multimedia contents, and displaying the plurality of target multimedia contents on a search result page.

[0028] According to some other embodiments of the present disclosure, a search processing apparatus is provided, the apparatus includes: a receiving module configured to receive a question input by a user, and a display module configured to display an answer to the question and a plurality of response videos related to the question on a search result page based on the question, where the answer is a sentence described in natural language generated by mechanically understanding the plurality of response videos, and includes description information of each response video generated by mechanically understanding each response video among the plurality of response videos.

[0029] According to some other embodiments of the present disclosure, a search processing apparatus is provided, the apparatus includes a processor and a memory coupled to the processor for storing instructions, and when the instructions are executed by the processor, the processor is caused to execute the search processing method of any one of the embodiments of the present disclosure.

[0030] According to some further embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, where when the program is executed by a processor, the search processing method of any embodiment of the present disclosure is realized.

[0031] According to some other embodiments of the present disclosure, a computer program product is provided, the computer program product includes instructions, where when the instructions are executed by a processor, the search processing method of any embodiment of the present disclosure is realized.

[0032] According to some further embodiments of the present disclosure, a computer program is provided, the computer program includes instructions, where when the instructions are executed by a processor, the search processing method of any embodiment of the present disclosure is realized.

Brief Description of the Drawings

[0033] Other features and advantages of the present disclosure will become apparent by describing exemplary embodiments of the present disclosure in detail while referring to the following drawings.

[0034] Hereinafter, preferred embodiments of the present disclosure will be described in detail while referring to the drawings. The drawings described here are for providing a further understanding of the present disclosure, each drawing is included in this specification together with the following specific description, constitutes a part of this specification, and is used for interpreting the present disclosure. It should be understood that the drawings in the following description relate only to some embodiments of the present disclosure and do not limit the present disclosure. [Figure 1] A flowchart of the search processing method of some embodiments of the present disclosure is shown. [Figure 2] A schematic diagram of a search result page of some embodiments of the present disclosure is shown. [Figure 3] A schematic diagram of a search result page of some other embodiments of the present disclosure is shown. [Figure 4]A schematic diagram of the search results page for several other embodiments of this disclosure is shown. [Figure 5] A schematic diagram of the search results page for several further embodiments of this disclosure is shown. [Figure 6] A schematic diagram of the search results page for several other embodiments of this disclosure is shown. [Figure 7] Schematic diagrams of the structure of some embodiments of the present disclosure of the search processing apparatus are shown. [Figure 8] Schematic diagrams of the structure of several other embodiments of the present disclosure of the search processing apparatus are shown. [Figure 9] Schematic diagrams of the structure of some further embodiments of the present disclosure of the search processing apparatus are shown.

[0035] For the sake of clarity, it should be noted that the dimensions of each part shown in the drawings are not necessarily depicted to the actual scale. The same or similar drawing reference numerals are used in each drawing to represent the same or similar components. Therefore, if a term is defined in one drawing, it may not be further examined in subsequent drawings. [Modes for carrying out the invention]

[0036] The following describes the technical concepts in the embodiments of this disclosure clearly and completely, with reference to the drawings of the embodiments of this disclosure. Clearly, the embodiments described are only a selection of the embodiments of this disclosure, not all of them. The following descriptions of embodiments are merely illustrative and do not in any way limit the disclosure or its applications or use. It should be understood that this disclosure may be implemented in various forms and should not be construed as being limited to the embodiments described herein.

[0037] It should be understood that the steps described in the embodiments of the methods of this disclosure may be performed in a different order and / or in parallel. Furthermore, embodiments of the methods may include additional steps and / or may be performed without the indicated steps. The scope of this disclosure is not limited in this respect. Unless otherwise specified, the relative arrangements of components and steps, numerical expressions and numerical values ​​described in these embodiments are illustrative and should be construed as not limiting the scope of this disclosure.

[0038] As used in this disclosure, the term "includes" and its variations mean an open term that includes at least subsequent elements / features but does not exclude other elements / features, i.e., "includes, but is not limited to." Similarly, as used in this disclosure, the term "inclusion" and its variations mean an open term that includes at least subsequent elements / features but does not exclude other elements / features, i.e., "includes, but is not limited to." Therefore, "includes" and "inclusion" are synonymous. The term "based on" means "based at least in part."

[0039] Throughout this specification, the terms “one embodiment,” “some embodiments,” or “embodiments” mean that certain features, structures, or properties described in conjunction with the embodiments are 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 other embodiment,” and the term “some embodiments” means “at least some embodiments.” Furthermore, the occurrences of the phrases “in one embodiment,” “in some embodiments,” or “in embodiments” in various places throughout this specification do not necessarily all refer to the same embodiment, although they may refer to the same embodiment.

[0040] It should be noted that the concepts such as “first,” “second,” etc., as used in this disclosure are merely for distinguishing different devices, modules, or units, and are not intended to limit the order or interdependence of functions performed by these devices, modules, or units. Unless otherwise specified, the concepts such as “first,” “second,” etc., are not intended to imply that the objects described in this way must be in a predetermined order in time, space, hierarchy, or any other manner.

[0041] It should be noted that the modifiers “one” and “multiple” as used in this disclosure are not restrictive but schematic, and that those skilled in the art should understand them as “one or more” unless otherwise explicitly indicated in the context.

[0042] The names of messages or information exchanged between multiple devices in embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0043] The embodiments of this disclosure will be described in detail below with reference to the drawings, but this disclosure is not limited to these specific embodiments. These specific embodiments can be combined with one another, and descriptions of the same or similar concepts or processes may be omitted in some embodiments. In addition, in one or more embodiments, certain features, structures or properties can be combined in any suitable manner that will be apparent to those skilled in the art from this disclosure.

[0044] In related technologies, users enter keywords or sentences to search and are shown several related results. In particular, with video search, simply matching the keywords entered by the user with videos and displaying several related videos and video titles results in poor search effectiveness and a poor user experience.

[0045] One technical challenge that this disclosure aims to address is how to improve the accuracy and effectiveness of searches and enhance search effectiveness.

[0046] This disclosure provides a search processing method 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 improve the user experience. The following description will be accompanied by reference to Figures 1-5.

[0047] Figure 1 is a flowchart of a search processing method according to some embodiments of the present disclosure. As shown in Figure 1, the method of the embodiment includes steps S102 to S104.

[0048] In step S102, the question entered by the user is received.

[0049] The system may receive user-entered text by setting up a search box, or it may receive user-entered information in various forms, such as user-entered audio or images. Information entered by the user may be received directly on the search page, or information entered by the user on another page may be received and displayed on the search page. For example, information entered by the user may be received via a human-computer interaction conversation page and then displayed on the search page; however, this is not limited to the examples given.

[0050] In some embodiments, the system determines whether information entered by the user is a question. For example, semantic recognition, grammatical recognition, etc., may be performed on user-entered text to determine whether the entered text is a question, or speech recognition may be performed on user-entered speech to determine whether the entered speech is a question, or image recognition may be performed on user-entered images to determine whether the entered image is a question, and this is not limited to the examples given. If the information entered by the user is a question, the question answer search function is automatically triggered.

[0051] In step S104, based on the question, the search results page displays the answer to the question and several answer videos related to the question.

[0052] In some embodiments, the answer is a sentence written in natural language generated by machine understanding of multiple answer videos, and includes descriptive information for each answer video generated by machine understanding of each of the multiple answer videos.

[0053] In some embodiments, based on a question, a first neural network model (or first machine learning model) is used to machine understand multiple videos in a first database, multiple answer videos related to the question are retrieved from the multiple videos, descriptive information is generated for each answer video, and an answer is generated based on the descriptive information for each answer video.

[0054] A first database may be configured to store multiple videos for answering user questions; that is, multiple videos may be used to answer video questions. The first database may also store other resources for answering user questions, such as text, images, and audio. Each video is input into a first neural network for machine understanding to obtain descriptive information for each video. For example, the first neural network may perform multimodal recognition on the subtitles, title, images, audio, etc., of each video to understand the content of each video, generate descriptive information for each video, and select an answer video relevant to the question from among them. For example, each video may be sorted based on one or more indicators such as the relevance of each video to the question, search popularity (number of times or frequency), number of user comments, number of user likes, and number of user views, and the videos ranked before a predetermined ranking may be selected as answer videos relevant to the question. For example, each video may be sorted, and the first three or first four videos may be selected as answer videos.

[0055] After selecting multiple answer videos, a natural language response may be generated based on the descriptive information of each answer video, or by combining the descriptive information of each answer video with knowledge information from a pre-configured knowledge base. The response may be a paragraph containing one or more sentences, and should be adapted to the user's reading habits, with smoothness, fluency, etc., conforming to pre-configured conditions to enhance the user experience.

[0056] The response may be presented in text format or played back in a format such as audio. For example, the response may be displayed in text format, with audio playback controls set at the corresponding locations in the text, accepting user trigger operations on the audio playback controls, and playing the audio corresponding to the text.

[0057] In some embodiments, a citation mark for each answer video is displayed at the appropriate location in the descriptive information for each answer video in the answer, and a citation mark for each answer video is displayed within each answer video.

[0058] The specific format of the citation marker may be set according to the actual situation. For example, citation markers may take various forms, such as numbers, video keywords, or video titles. Citation markers may also be placed after the descriptive information of the corresponding answer video to make it easier to indicate that the information preceding the citation marker belongs to the corresponding answer video. The placement of the citation marker may be adjusted according to the actual situation. Citation markers may also be displayed by adding a new layer (e.g., a mask) to each answer video, or other formats may be used, and are not limited to the examples given.

[0059] For example, as shown in Figure 2, the citation may be placed after the descriptive information of each answer video, using a superscript format.

[0060] In some embodiments, the system accepts trigger operations for citation indicators displayed in the user's response and plays the response video corresponding to the citation indicator.

[0061] The trigger operation may take various forms, such as clicks or selections, and is not limited by this disclosure. The answer video corresponding to the citation may be played on a separate video playback page from the search results page, or on the search results page, or in a floating window, and the playback format is not limited to the examples given.

[0062] The search results page, also known as the question and answer results page, displays answers and multiple answer videos based on the user's question, and of course, can also display only one answer video. In some embodiments, the entire search results page supports swipe display, accepting swipe operations in predefined directions, such as left / right or up / down swipes, to display more content, and prompt information may be displayed when swiped to a predefined boundary. The entire search results page may also support zoom in and out, allowing the user to zoom in and out of the search results page using predefined operations.

[0063] In some embodiments, the search results page includes a fixed display area and a search card area that supports swipe display, with the search card area displaying the answer and multiple answer videos, i.e., the entire answer and multiple answer videos support swipe display. Of course, the area displaying the answer may be located in the fixed display area, and the area displaying multiple answer videos may also be located in the fixed display area, but this will not be explained further here.

[0064] For example, a 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 an input area, which may contain at least one of a search control and a voice control. For example, in response to a user clicking the input area, a keyboard area pops up, receives information entered by the user, accepts trigger operations on the user's search control, and displays a search card area.

[0065] As shown in Figure 2, the fixed display area further includes an options area set below the input area. The options area contains multiple options controls, which are used to trigger different search scenarios or search ranges. The system accepts a trigger operation from the user on any of the options controls, retrieves search results related to the information entered by the user based on the search scenario or search range corresponding to the triggered option control, and displays the search results.

[0066] For example, the first option control is used to trigger a video question answering scenario, accept a trigger for the user's first option control, receive the question entered by the user, and display the answer and multiple answer videos. For example, the second option control is used to trigger a user search scenario, accept a trigger for the user's second option control, receive the information entered by the user, and display information for multiple related users. For example, the third option control is used to trigger a video search scenario, accept a trigger for the user's third option control, receive the information entered by the user, and display multiple related videos. For example, the fourth option control is used to trigger an audio search scenario, accept a trigger for the user's fourth option control, receive the information entered by the user, and display multiple related audio. For example, the fifth option control is used to trigger a shopping search scenario, accept a trigger for the user's fifth option control, receive the information entered by the user, and display multiple related audio. For example, the sixth option control is used to trigger a live stream search scenario, accept user triggers on the sixth option control, receive information entered by the user, and display multiple relevant live streams.

[0067] The order in which option control triggers and user-entered information are received may be adjusted and is not limited to the examples given above. Option controls and search scenarios may be configured according to actual needs and are not limited to the examples given above. Different search scenarios may use different databases and different neural networks (or machine learning models) for searching. The option area may be configured as a search card area or as a separate area that supports swipe display; for example, the option area may support left and right swipe display.

[0068] In some embodiments, the search card area includes a first area and a second area, with the first area displaying the answer and the second area displaying multiple answer videos. As shown in Figure 2, the first area may be positioned above the second area to better suit the user's reading habits and enhance the display effect.

[0069] In some embodiments, multiple answer videos support swipe display within a second area. The system accepts the user's swipe gesture and displays the answer videos within the second area. This allows for the display of more answer videos and provides users with richer content, especially when page space is limited.

[0070] Each answer video is displayed at a pre-set size. If the combined display range of multiple answer videos exceeds the display range of the second area, some of the answer videos may be fully displayed, while the remaining answer videos may not be fully displayed or may not be displayed at all. The system accepts a swipe gesture from the user and displays the remaining answer videos that are within the display range of the second area.

[0071] As shown in Figure 2, in the second area, of the three answer videos, the first two answer videos are fully displayed, the third video is not fully displayed, and the user can display the third answer video by swiping left.

[0072] In some embodiments, the display area of ​​the response is adaptively adjusted according to the length of the response. As shown in Figures 3 and 4, if the response is short, the display area of ​​the response may be smaller, allowing more of the remaining information to be displayed on the page. If the response is long, the display area of ​​the response may be larger, occupying a larger area on the page.

[0073] Multiple answer videos may display preview information, or they may play automatically. Some videos may display preview information, while others may play automatically. When the display range of an answer is adaptively adjusted according to the length of the answer, the position of the answer video on the search results page may be uncertain. Furthermore, when the search card area supports swipe display, the position of the answer video on the search results page may also be uncertain. Therefore, the automatic playback or display preview information of the answer video may be adjusted depending on the display status.

[0074] In some embodiments, if the display range of an answer is within a first preset range, some or all of the answer videos are automatically played. If the display position of an answer is outside the first preset range, preview information for the answer videos is displayed. For example, if the display range of an answer is within the first preset range, the answer videos within the display range of a second area are automatically played. For example, as shown in Figure 2, the first two of the three answer videos in the second area are automatically played. Alternatively, if the display range of an answer is within the first preset range, the first answer video is automatically played.

[0075] In some embodiments, if the bottom of the last line of an answer is positioned above a first reference line, some or all of the answer videos among multiple answer videos are automatically played.

[0076] The first baseline may be fixedly set, and for example, the first baseline may be used to limit the display range of the answer. For example, as shown in Figure 3, a title may be displayed above the answer to prompt that the text is the answer. The first baseline may be set to a baseline whose distance from the bottom of the title is a predetermined distance.

[0077] If the bottom of the last line of an answer (for example, the horizontal line at the bottom of the text in the last line) is positioned above the first baseline, it indicates that the current display range of the answer is small, and the answer video is fully displayed on the search results page and positioned relatively centrally or towards the top of the page. In such cases, the answer video is within the user's line of sight, and some or all of the answer video can be automatically played to enhance the display effect, encourage the user to watch the answer video without having to jump to another page, making it easier for the user to view the answer video.

[0078] In some embodiments, some or all of the answer videos among several answer videos are automatically played when the bottom of the last line of the answer is positioned below a first baseline and the top of the first line of the answer (e.g., the horizontal line above the characters in the first line) is positioned above a second baseline, where the second baseline is positioned above the first baseline.

[0079] The second baseline may be fixed, or it may be located at the top of the search card area. For example, as shown in Figure 4, the second baseline may be located at the bottom of the options area. The display position of the top of the first line of the answer may be above the second baseline, indicating that the search card area is swiped upwards, the answer video is fully displayed on the search results page, and is located in the center or top of the search results page. In such a case, the answer video is within the user's line of sight, and some or all of the answer video can be automatically played to enhance the display effect, encourage the user to watch the answer video, and make it easier for the user to watch the answer video without having to jump to another page.

[0080] The system may automatically play the answer video in its entirety, or a predetermined number of answer videos according to their display order, or play all answer videos. The specific answer videos selected for automatic playback may be configured, and are not limited to the examples given.

[0081] In some embodiments, a trigger operation is received for one of the user's multiple response videos, and the corresponding response video is played. The corresponding response video may be played by a video playback page different from the search results page, by the search results page itself, or by a floating window, and is not limited to the examples given.

[0082] In some embodiments, the display range of the first region is adaptively adjusted according to the length of the response within a second preset range. The display range of the first region is the display range of the response, and the second preset range is used to limit the maximum display range of the response.

[0083] In some embodiments, if the length of the response exceeds a second preset range, the content of the response exceeding the second preset range is hidden, an expand control is displayed, a trigger operation on the user's expand control is received, and the response is fully displayed.

[0084] In some embodiments, if the length of the response exceeds a second preset range and the response is fully displayed, a hide control is displayed, a trigger operation on the hide control by the user is received, and the content of the response that exceeds the second preset range is hidden.

[0085] As shown in Figure 2, an expand control (Read More) may be displayed at the end of the answer display, and the user may trigger it by clicking or other means, and the display effect after expansion is as shown in Figure 5. Similarly, as shown in Figure 5, a hide control may be displayed at the end of the answer display, and the user may hide some of the content by triggering the hide control (Hide Partially), and the display effect after hiding is as shown in Figure 2.

[0086] When an answer is long, hiding part of the answer allows for more of the answer video to be displayed, enriching the search results page, increasing its effectiveness, and enhancing the user's reading experience. Expanding the hidden content makes it easier for users to view the complete answer.

[0087] In some embodiments, one or more suggested questions are displayed on the search results page based on the question and multiple answer videos.

[0088] One or more suggested questions relate to some or all of the videos among the question and multiple answer videos. For example, a suggested question might be, "You may show more answer videos." One or more suggested questions may be generated by machine understanding the question and multiple answer videos. As shown in Figure 2, one or more suggested questions may be displayed in a third area, which may be below the second area, to suit the user's reading order and enhance the display effect. The third area may be located in the search card area.

[0089] In some embodiments, the system receives a selection operation from the user for one or more candidate questions, jumps to a conversation page, and displays the answer to the selected candidate question on the conversation page.

[0090] A conversation page may receive questions entered by the user and display the corresponding answers. For example, a conversation page is a human-computer interaction page. The conversation page may display selected candidate questions and their corresponding answers, or it may display other candidate questions.

[0091] Directly displaying one or more suggested questions eliminates the need for users to type questions, making it easier for them to ask subsequent questions directly, thus improving convenience and display effectiveness.

[0092] In some embodiments, an entry control is displayed on the search results page to continue the question, and a trigger action is received on the user's entry control to jump to the conversation page. In some embodiments, at least one of the answers and suggested questions is displayed on the conversation page.

[0093] As shown in Figure 2, the entry control may be set in a third area, the same area as one or more candidate questions. The entry control may also be set before one or more candidate questions, depending on the reading direction, and is not limited to the examples given. When the user enters the conversation page via the entry control, the conversation page may display the answer from the search results page, or one or more candidate questions, and may receive a selection operation from the user for one or more candidate questions, and display the answer to the selected candidate question on the conversation page.

[0094] In some embodiments, the search results page displays multiple recommended videos related to the question, where the multiple recommended videos differ from the search policy of the multiple answer videos. The search policy may include at least one of a search algorithm and a selection metric.

[0095] The neural network model (or machine learning model) that generates recommendation videos may differ from the neural network model (or machine learning model) that generates answer videos, i.e., the search algorithms may differ. The selection criteria for selected recommendation videos and answer videos may differ. For example, a comprehensive metric may be determined based on multiple metrics such as the relevance of each video to the question, search popularity (number of times or frequency), number of user comments, number of user likes (liking), and number of user views. Based on this comprehensive metric, each video may be sorted, and videos ranked before a first pre-set ranking may be selected as answer videos relevant to the question. Alternatively, each video may be sorted based on the number of user likes, and videos ranked before a second pre-set ranking may be selected as recommendation videos relevant to the question.

[0096] As shown in Figure 2, multiple recommended videos may be displayed in the fourth area, and the fourth area may be set as the search card area.

[0097] In some embodiments, a trigger operation is received for one of the user's recommended videos, and the corresponding recommended video is played. The corresponding recommended video may be played by a video playback page different from the search results page, by the search results page itself, or by a floating window, and is not limited to the examples given.

[0098] Displaying recommended videos enriches the content of search results pages, enhances their effectiveness, meets diverse user needs, and improves the user experience.

[0099] In some embodiments, reference metrics are displayed on each answer video and / or each recommendation video. Reference metrics are one or more metrics such as relevance to the question, search popularity (number of times or frequency), number of user comments, number of user likes (liking), and number of user views. Reference metrics may be displayed by adding a new layer to the video, for example, and are not limited to the examples given.

[0100] In some embodiments, a first operation is received on one of the user's multiple response videos, and the response video corresponding to the first operation is switched from a first display state to a second display state.

[0101] In some embodiments, a second action on a control on the user's search results page is received, and the control corresponding to the second action is switched from a third display state to a fourth display state.

[0102] The first and second operations may be the same or different. For example, both the first and second operations may be pressing buttons, or the first operation may be pressing a button and the second operation may be selecting a button. The examples given are not limited to those provided.

[0103] As shown in Figure 6, after receiving the user's first operation, the response video corresponding to the first operation may be switched from a first display state to a second display state by setting a first mask. For example, the first mask may change the display color, transparency, and other properties of the response video. After receiving the user's second operation, the control corresponding to the second operation may be switched from a third display state to a fourth display state by setting a second mask. The display color, transparency, and other properties of the control may be changed by the second mask, and this is not limited to the examples given. The colors, transparency, etc., of the first mask and the second mask may be different.

[0104] The switching of the display state of answer videos is similarly applied to recommendation videos. Upon receiving a first action on one of the user's multiple recommendation videos, the system switches the recommendation video corresponding to the first action from the first display state to the second display state.

[0105] By switching the display state of a video or control, users can intuitively interact with the video or control, enhancing both the display effect and the user experience.

[0106] In the search processing method of the above embodiment, a question entered by the user is received, and based on the question, the answer to the question and multiple answer videos related to the question may be displayed on the search results page. The answer is a sentence written in natural language generated by machine understanding of the multiple answer videos, and the answer includes descriptive information of each answer video generated by machine understanding of each answer video among the multiple answer videos. The method of the above embodiment modifies the conventional video search method and can automatically answer questions entered by the user and display related answer videos. The answer is generated based on machine understanding of the videos, and the descriptive information of multiple answer videos in the answer is related and merged and expressed in natural language. As a result, after entering a question, the user can intuitively see the answer to the question and the answer video, clearly understand the relationship between the answer video and the answer, understand the descriptive content of the answer video, and more easily view the detailed content of the answer video. The method of the above embodiment improves the accuracy and effectiveness of the search, enhances the search effect and display effect, and improves the user experience.

[0107] In the above embodiment, we mainly described a method for responding to and displaying questions entered by the user.

[0108] In some embodiments, information entered by the user is received, and if the entered information is not a question, a second neural network (or second machine learning model) is used to machine understand multiple multimedia content in a second database based on the entered information, multiple target multimedia content related to the entered information is retrieved from the multiple multimedia content, and the multiple target multimedia content is displayed on the search results page.

[0109] A second database may be set up to store multimedia content for searching. Multimedia content may include, for example, at least one of text, audio, images, and video. If the multimedia content is video, the method for displaying the corresponding answer video or recommendation video in the above embodiment applies similarly.

[0110] In some embodiments, the system receives a trigger action from the user on any of the target multimedia content and displays further details about the corresponding multimedia content. Examples include playing video or audio, or enlarging text or images.

[0111] By performing different searches and displaying different content based on different types of information entered by users, we enhance search and display effectiveness, meet diverse user needs, and improve the user experience.

[0112] In this disclosure, directions such as up, down, left, and right refer to the general reading direction of a page. Trigger operations for different videos and controls in this disclosure may be of different types; for example, some trigger operations may be clicks, and others may be selections, but are not limited to these.

[0113] This disclosure further provides a search processing device, which will be described below in conjunction with Figure 7.

[0114] Figure 7 is a structural diagram of a search processing apparatus of several embodiments of the present disclosure. As shown in Figure 7, the apparatus 70 of the embodiment includes a receiving module 710 and a display module 720.

[0115] The receiving module 710 is configured to receive questions entered by the user.

[0116] The display module 720 is configured to display the answer to the question and multiple answer videos related to the question on the search results page based on the question, where the answer is a sentence written in natural language generated by machine understanding of the multiple answer videos, and includes descriptive information for each answer video generated by machine understanding of each of the multiple answer videos.

[0117] In some embodiments, the display module 720 is configured to display a citation for each answer video at the appropriate location in the descriptive information for each answer video in the answer, and to display a citation for each answer video within each answer video.

[0118] In some embodiments, the receiving module 710 is further configured to accept trigger operations for citation markers displayed in the user's response, and the display module 720 is further configured to play a response video corresponding to the citation marker.

[0119] In some embodiments, the display module 720 is further configured to display one or more suggested questions on the search results page based on the question and multiple answer videos.

[0120] In some embodiments, the receiving module 710 is further configured to accept a selection operation from the user for one or more candidate questions.

[0121] In some embodiments, the display module 720 is further configured to jump to a conversation page, where the conversation page displays the answers to the selected candidate questions.

[0122] In some embodiments, the display module 720 is further configured to display an entry control that allows the user to continue the question on the search results page, the receiving module 710 is further configured to accept trigger operations on the user's entry control, and the display module 720 is further configured to jump to a conversation page and display the conversation page.

[0123] In some embodiments, the display module 720 is further configured to display at least one of the answers and suggested questions on the conversation page.

[0124] In some embodiments, the display module 720 is configured to automatically play some or all of the answer videos when the display range of the answers falls within a first preset range.

[0125] In some embodiments, the display module 720 is configured to display preview information for multiple answer videos when the display position of an answer is outside a first preset range.

[0126] In some embodiments, the display module 720 is configured to automatically play some or all of the answer videos among the multiple answer videos when the display position of the bottom of the last line of the answer is above a first reference line.

[0127] In some embodiments, the display module 720 is configured to automatically play some or all of the answer videos among the multiple answer videos when the display position of the bottom of the last line of the answer is below a first baseline and the display position of the top of the first line of the answer is above a second baseline, where the second baseline is above the first baseline.

[0128] In some embodiments, the search results page includes a fixed display area and a search card area that supports swipe display, and the display module 720 is configured to display the answer and multiple answer videos in the search card area.

[0129] 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 to display multiple answer videos in the second area, wherein the multiple answer videos support swipe display within the second area.

[0130] In some embodiments, the display module 720 is configured to hide the content of the response that exceeds a second preset range and display an expand control when the length of the response exceeds a second preset range, the receiving module 710 is further configured to accept trigger operations on the user's expand control, and the display module 720 is configured to display the entire response.

[0131] In some embodiments, the display module 720 is configured to display a hide control when the length of the response exceeds a second preset range and the response is fully displayed, the receiving module 710 is further configured to accept trigger operations on the hide control by the user, and the display module 720 is configured to hide the content of the response that exceeds the second preset range.

[0132] In some embodiments, the receiving module 710 is further configured to receive a first operation on one of the user's multiple response videos, and the display module 720 is further configured to switch the response video corresponding to the first operation from a first display state to a second display state.

[0133] In some embodiments, the receiving module 710 is further configured to accept a second operation on a control on the user's search results page, and the display module 720 is further configured to switch the control corresponding to the second operation from a third display state to a fourth display state.

[0134] In some embodiments, the display module 720 is further configured to display multiple recommended videos related to the question on the search results page, where the multiple recommended videos differ from the search policy of multiple answer videos.

[0135] In some embodiments, the receiving module 710 is further configured to accept a trigger operation for any of the user's recommended videos, and the display module 720 is further configured to play any of the recommended videos.

[0136] In some embodiments, the receiving module 710 is further configured to accept a trigger operation for any of the user's multiple response videos, and the display module 720 is further configured to play any of the response videos.

[0137] In some embodiments, the search processing unit further includes a control module 730 configured to machine understand multiple videos in a first database using a first neural network model based on a question, retrieve multiple answer videos related to the question from the multiple videos, generate descriptive information for each answer video, and generate an answer based on the descriptive information for each answer video.

[0138] In some embodiments, the receiving module 710 is further configured to receive information entered by the user, the control module 730 is further configured to machine understand multiple multimedia content in a second database using a second neural network based on the input information and to retrieve multiple target multimedia content related to the input information from the multiple multimedia content, and the display module 720 is further configured to display the multiple target multimedia content on the search results page.

[0139] The search processing device in the embodiments of this disclosure may be implemented by various computing devices or computer systems, and will be described below in conjunction with Figures 8 and 9.

[0140] Figure 8 is a structural diagram of a search processing apparatus in some embodiments of the present disclosure. As shown in Figure 8, the apparatus 80 of the embodiment includes a memory 810 and a processor 820 coupled to the memory 810, the processor 820 being configured to execute a search processing method in any of the embodiments of the present disclosure based on instructions stored in the memory 810.

[0141] Here, memory 810 may include, for example, system memory, a fixed non-volatile storage medium, etc. System memory stores, for example, an operating system, application programs, a boot loader, a database, and other programs.

[0142] Figure 9 is a structural diagram of several other embodiments of the search processing apparatus of the present disclosure. As shown in Figure 9, the apparatus 90 of the embodiment includes a memory 910 and a processor 920, which are similar to the memory 810 and processor 820, respectively. It may further 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 processor 920 may be connected via, for example, a bus 960. Here, the input / output interface 930 provides a connection interface to input / output devices such as a display, mouse, keyboard, and touchscreen. The network interface 940 provides a connection interface to various network devices, which may be connected to, for example, a database server or a cloud storage server. The storage interface 950 provides a connection interface to external storage devices such as an SD card or U memory disk.

[0143] The present disclosure further provides a computer-readable storage medium on which a computer program is stored, wherein, when the program is executed by a processor, a search processing method of any embodiment of the present disclosure is realized.

[0144] This disclosure further provides a computer program having instructions stored thereon, where, when the instructions are executed by a processor, a search processing method of any embodiment of this disclosure is realized.

[0145] This disclosure further provides a computer program product having instructions stored thereon, where, when the instructions are executed by a processor, a search processing method of any embodiment of this disclosure is realized.

[0146] Those skilled in the art will see 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 complete hardware embodiments, complete software embodiments, or embodiments combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-available non-temporary storage media (including, but not limited to, disk memory, CD-ROM, optical memory, etc.) containing computer-available program code.

[0147] This disclosure has been described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of this disclosure. It should be understood that computer program instructions can realize each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams. By providing these computer program instructions to a processor of a general-purpose computer, a dedicated computer, an embedded processor, or other programmable data processing device, a device can be generated that realizes a function specified in one flow of a flowchart or one or more blocks of multiple flows and / or block diagrams by instructions executed by the processor of the computer or other programmable data processing device.

[0148] These computer program instructions may be stored in computer-readable memory that can guide a computer or other programmable data processing device to operate in a particular manner, thereby generating a product in which the instructions stored in the computer-readable memory generate an instruction unit that implements a function specified in one or more flows of a flowchart and / or one or more blocks of a block diagram.

[0149] These computer program instructions may be loaded into a computer or other programmable data processing device to perform a series of operational steps on the computer or other programmable device to generate processing that is implemented on the computer, thereby providing steps to implement a function specified in one or more flows of a flowchart and / or one or more blocks of a block diagram.

[0150] The foregoing are merely preferred embodiments of the Disclosure and do not limit the Disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the Disclosure should be included within the scope of the Disclosure.

Claims

1. A search processing method, Receiving questions entered by the user, A search processing method comprising displaying the answer to the question and a plurality of answer videos related to the question on a search results page based on the question, wherein the answer is a sentence written in natural language generated by machine understanding the plurality of answer videos, and includes descriptive information of each of the answer videos generated by machine understanding each of the plurality of answer videos.

2. Displaying the answer to the aforementioned question and multiple answer videos related to the aforementioned question on the search results page is, In the aforementioned answer, a citation mark for each of the aforementioned answer videos shall be displayed at the corresponding location in the descriptive information of each of the aforementioned answer videos, The search processing method according to claim 1, further comprising displaying a citation mark for each of the aforementioned answer videos in each of the aforementioned answer videos.

3. The system accepts trigger operations for the citation indicator displayed in the user's response, The search processing method according to claim 2, further comprising playing a response video corresponding to the aforementioned citation mark.

4. A search processing method according to any one of claims 1 to 3, further comprising displaying one or more candidate questions on the search results page based on the question and the plurality of answer videos.

5. The system receives a selection operation from the user for one or more of the candidate questions and jumps to the conversation page. The search processing method according to claim 4, further comprising displaying the answers to the selected candidate questions on the conversation page.

6. Display an entry control on the aforementioned search results page to continue asking questions, A search processing method according to any one of claims 1 to 5, further comprising receiving a trigger operation by the user on the entry control and jumping to a conversation page.

7. The search processing method according to claim 6, further comprising displaying at least one of the answers and candidate questions on the conversation page.

8. Displaying the answer to the aforementioned question and multiple answer videos related to the aforementioned question on the search results page is, A search processing method according to any one of claims 1 to 7, comprising automatically playing some or all of the multiple answer videos when the display range of the answer is within a first preset range.

9. Displaying the answer to the aforementioned question and multiple answer videos related to the aforementioned question on the search results page is, The search processing method according to claim 8, further comprising displaying preview information of the plurality of answer videos when the display position of the answer is outside a first preset range.

10. If the display range of the aforementioned answer is within a predetermined range, then automatically playing some or all of the multiple answer videos is: The search processing method according to claim 8 or 9, further comprising automatically playing some or all of the multiple answer videos when the display position of the bottom of the last line of the answer is located above a first reference line.

11. If the display range of the aforementioned answer is within a predetermined range, then automatically playing some or all of the multiple answer videos is: The search processing method according to claim 10, further comprising automatically playing some or all of the multiple answer videos when the display position of the bottom of the last line of the answer is below a first reference line and the display position of the top of the first line of the answer is above a second reference line, wherein the second reference line is above the first reference line.

12. The search results page includes a fixed display area and a search card area that supports swipe display, and the search results page displays the answer to the question and multiple answer videos related to the question. The search processing method according to any one of claims 1 to 11, further comprising displaying the answer and the plurality of answer videos in the search card area.

13. The search card area includes a first area and a second area, and the search card area displays the answer and the multiple answer videos. The answer is displayed in the first area, and the display range of the first area is adaptively adjusted within a second preset range according to the length of the answer. The search processing method according to claim 12, further comprising displaying the plurality of answer videos that support swipe display within the second area in the second area.

14. Displaying the answer in the first area means If the length of the response exceeds the second preset range, the content of the response that exceeds the second preset range is hidden, and an expansion control is displayed. The search processing method according to claim 13, comprising receiving a trigger operation from the user to the expansion control and fully displaying the answer.

15. Displaying the answer in the first area means If the length of the answer exceeds the second preset range and the answer is fully displayed, a hide control is displayed. The search processing method according to claim 14, further comprising receiving a trigger operation on the hide control by the user and hiding the content in the response that exceeds the second preset range.

16. Accepting a first operation on any of the user's multiple response videos, The search processing method according to any one of claims 1 to 15, further comprising switching the answer video corresponding to the first operation from a first display state to a second display state.

17. Accepting a second operation by the user on the controls on the search results page, The search processing method according to any one of claims 1 to 16, further comprising switching the control corresponding to the second operation from a third display state to a fourth display state.

18. The search processing method according to any one of claims 1 to 17, further comprising displaying a plurality of recommended videos related to the question on the search results page, wherein the plurality of recommended videos differ from the search policy of the plurality of answer videos.

19. The system accepts a trigger operation for any of the user's recommended videos, The search processing method according to claim 18, further comprising playing any of the aforementioned recommended videos.

20. The system accepts a trigger operation for any of the user's multiple response videos, A search processing method according to any one of claims 1 to 19, further comprising playing one of the aforementioned answer videos.

21. Based on the aforementioned question, displaying the answer to the question and multiple answer videos related to the question on the search results page is: Based on the aforementioned question, a first neural network model is used to machine understand multiple videos in a first database, multiple answer videos related to the aforementioned question are obtained from the multiple videos, and descriptive information for each of the answer videos is generated. A search processing method according to any one of claims 1 to 20, comprising generating the answer based on the descriptive information of each of the answer videos.

22. Receiving information entered by the aforementioned user, If the input information is not a question, the system uses a second neural network to machine-understand multiple multimedia content in a second database based on the input information, and obtains multiple target multimedia content related to the input information from the multiple multimedia content. The search processing method according to claim 21, further comprising displaying the plurality of target multimedia contents on the search results page.

23. A search processing device, A receiving module configured to receive questions entered by the user, A search processing device comprising a display module configured to display the answer to the question and a plurality of answer videos related to the question on a search results page based on the question, wherein the answer is a sentence written in natural language generated by machine understanding the plurality of answer videos, and includes descriptive information of each of the answer videos generated by machine understanding each of the plurality of answer videos.

24. A search processing device, Processor and A search processing device coupled to the processor and including a memory for storing instructions, wherein when an instruction is executed by the processor, the device causes the processor to execute the search processing method according to any one of claims 1 to 22.

25. A computer-readable storage medium in which a computer program is stored, wherein when the computer program is executed by a processor, the search processing method described in any one of claims 1 to 22 is realized.

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

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

Images