Information search method and device, electronic equipment and storage medium
By introducing intelligent dialogue search function in multimedia social applications and using artificial intelligence to aggregate multimedia resources, the problem of inaccurate search results in multimedia social applications is solved, the search accuracy and efficiency are improved, and the user experience is provided.
Patent Information
- Application Number
- CN202310545130.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-15
- Publication Date
- 2024-11-19
AI Technical Summary
In multimedia social applications, existing search technologies are difficult to provide accurate search results, especially in video search scenarios, where users need to open one by one to understand the content, resulting in inefficiency.
By introducing intelligent conversation search function in multimedia social applications, using artificial intelligence-driven natural language processing, aggregating multimedia resources to provide dialogue and chat-style search results display, users can view historical questions and answers in the intelligent conversation display area, which is easy to correct Ask a question.
It improves search accuracy and efficiency and provides a better search experience. Users do not need to filter answers again. The accuracy of answers in intelligent dialogue search scenarios is further improved, making historical searches easy to view.
Smart Images

Figure CN118981547A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to an information search method, device, electronic device and storage medium. Background Art
[0002] With the development of Internet applications, the use of social applications is becoming more and more widespread, such as the widespread use of short video applications. In such applications that use multimedia resources to carry social interactions, users also have search needs. However, although the search results obtained in related technologies are filtered, they are still a large number of multimedia resources, which requires users to search from the search results to find the answers they want, resulting in the search not being accurately provided to users; especially when the search results are mostly videos, they need to click on them to get the specific content, making the search results neither accurate nor convenient to view, and the efficiency is low. Summary of the invention
[0003] The present disclosure provides an information search method, device, electronic device and storage medium to at least solve the problem of how to improve the search accuracy in multimedia social applications in the related art. The technical solution of the present disclosure is as follows:
[0004] According to a first aspect of an embodiment of the present disclosure, there is provided an information search method, comprising:
[0005] Display the target page of the multimedia social application;
[0006] In response to an intelligent dialogue search instruction for searching a question object, a dialogue input area and an intelligent dialogue display area are displayed;
[0007] Among them, the dialogue input area is used to input dialogue question information of questions; the intelligent dialogue display area is used to display the identifier corresponding to the search question object and the dialogue question information, as well as the dialogue response result of the search reply object; wherein, the search reply object is an object that performs natural language processing based on artificial intelligence drive, and the dialogue response result is obtained by the search reply object through data aggregation processing of multimedia resources matching the dialogue question information in the multimedia social application.
[0008] In a possible implementation, the method further includes:
[0009] In response to a confirmation instruction of inputting the dialogue question information in the dialogue input area, the identifier corresponding to the search question object and the dialogue question information are displayed in the intelligent dialogue display area, the dialogue question information in the dialogue input area is cleared, and the dialogue response result replied by the search response object and the source indication information of the dialogue response result are displayed in the intelligent dialogue display area; the source indication information is used to indicate the multimedia resource from which the dialogue response result comes;
[0010] In response to a triggering operation of the source indication information, a target multimedia resource from which the dialogue reply result originates is displayed.
[0011] In a possible implementation, the dialogue reply result is a dialogue reply text, the dialogue reply text includes at least one reply text segment, each reply text segment corresponds to at least one source indication information; the source indication information is at least one of a source subscript and a source tag; the triggering operation in response to the source indication information, displaying the target multimedia resource from which the dialogue reply result originates, includes:
[0012] In response to a triggering operation of the target source indication information, displaying a source content indication special effect at a location associated with the target source indication information;
[0013] Detecting that the source content indicates that the special effect is triggered, displaying the target multimedia resource from which the target reply text segment originates;
[0014] Among them, the target source indication information is any of the source indication information; the target reply text segment is the reply text segment corresponding to the target source indication information.
[0015] In a possible implementation, the display dialogue input area and the intelligent dialogue display area include:
[0016] Displaying the dialogue input area and the intelligent dialogue display area in a half-screen pop-up window on the target page;
[0017] or,
[0018] Displaying an intelligent dialogue search page, displaying the dialogue input area and the intelligent dialogue display area on the intelligent dialogue search page;
[0019] Alternatively, the dialogue input area and the intelligent dialogue display area are incrementally displayed in the target area of the target page.
[0020] In a possible implementation, when the dialogue input area and the smart dialogue display area are displayed in the half-screen pop-up window, the method further includes:
[0021] A sliding operation on the half-screen pop-up window is detected, and the page is jumped to the smart dialogue search page, and the dialogue input area and the smart dialogue display area are displayed on the smart dialogue search page.
[0022] In a possible implementation, the target page is any one of a search homepage, a search result page, a multimedia resource display page, and a sidebar page; the target page displays intelligent dialogue indication information that triggers the intelligent dialogue search instruction;
[0023] The display of the dialogue input area and the intelligent dialogue display area in response to the intelligent dialogue search instruction for searching the question object includes:
[0024] In response to the intelligent dialogue search instruction triggered by the search question object based on the intelligent dialogue indication information, a dialogue input area and an intelligent dialogue display area are displayed.
[0025] In a possible implementation, the target page is a search homepage, the search homepage displays a search input area, and the search input area includes an information deletion control for deleting information input in the search input area;
[0026] The display of the dialogue input area and the intelligent dialogue display area in response to the intelligent dialogue search instruction for searching the question object includes:
[0027] In response to question information being input in the search input area, incrementally displaying intelligent dialogue entry guidance information at a location associated with the search input area;
[0028] In response to triggering the intelligent dialogue entry guidance information, a dialogue input area and an intelligent dialogue display area are displayed.
[0029] In a possible implementation, the target page displays a navigation control for guiding the intelligent dialogue search; the display of the dialogue input area and the intelligent dialogue display area in response to the intelligent dialogue search instruction for searching the question object includes:
[0030] In response to a trigger instruction of the navigation control, the dialogue input area and the intelligent dialogue display area are displayed.
[0031] In a possible implementation, the target page is a search result page, and the search result page displays a search input area; the method further includes:
[0032] Detecting that the number of search question information input in the search input area reaches a number threshold, incrementally displaying entry prompt information for intelligent dialogue search on the search results page;
[0033] In response to the triggering operation of the entry prompt information of the intelligent dialogue search, the intelligent dialogue search instruction is generated.
[0034] In a possible implementation, the target page is a search result page, and the search result page displays a search input area, search results, and source indication information corresponding to the search results; the method further includes:
[0035] In response to a triggering operation of the source indication information corresponding to the search result, a target multimedia resource from which the search result originates is displayed.
[0036] In a possible implementation, the search homepage includes search mode selection information, where the search mode selection information is used to indicate whether the search results are obtained by aggregating the searched multimedia resources; the method further includes:
[0037] When search question information is input in the search input area of the search homepage and the search mode selection information is triggered to be processed through aggregation, the search input area, the search results and the source indication information corresponding to the search results are displayed on the search results page.
[0038] In a possible implementation, the inputting of search question information in the search input area of the search homepage and displaying the search input area, the search results, and the source indication information corresponding to the search results on the search results page when the search mode selection information is triggered to be processed by aggregation include:
[0039] Enter search question information in the search input area of the search homepage, and display search result type selection information when the search mode selection information is triggered to be processed through aggregation; the search result type selection information includes at least one result display type of video, image or text;
[0040] Based on the operation selected by the search result type selection information, the search results under the target result display type are displayed; the target result display type is any one of the result display types.
[0041] In a possible implementation, the search result is a non-text search result; and the method further includes:
[0042] In response to dialog instruction information for converting the target result presentation type of the search result being input into the dialog input area, the search result is converted into a text search result.
[0043] In a possible implementation manner, the search question information and the dialogue question information may be one of text, voice and image information.
[0044] In a possible implementation, the display type of the dialogue response result is at least one of text, image, and video.
[0045] In a possible implementation, the method further includes:
[0046] In response to inputting search question information in a search input area of a search homepage or a search result page, extracting a target result display type from the search question information;
[0047] The search results corresponding to the search question information are displayed on the search result page in the target result display type, and source indication information corresponding to the search results is displayed.
[0048] In a possible implementation, the method further includes:
[0049] In response to a tag generation instruction triggered in a multimedia resource publishing request, the dialogue input area and the intelligent dialogue display area are displayed, wherein the intelligent dialogue display area displays at least one tag information of the multimedia resource to be published replied by the search reply object.
[0050] In a possible implementation, when the dialogue response result is a video, the method further includes:
[0051] When a pause operation is detected during the video playback process, text description information corresponding to the target progress in the video replied by the search reply object is displayed in the intelligent dialogue display area; the target progress is the playback progress corresponding to the pause of the video playback process.
[0052] According to a second aspect of an embodiment of the present disclosure, there is provided an information search device, including:
[0053] A display module, configured to execute and display a target page of a multimedia social application;
[0054] The intelligent dialogue display module 1103 is configured to execute an intelligent dialogue search instruction in response to searching for a question object, and display a dialogue input area and an intelligent dialogue display area;
[0055] Among them, the dialogue input area is used to input dialogue question information of questions; the intelligent dialogue display area is used to display the identifier corresponding to the search question object and the dialogue question information, as well as the dialogue response result of the search reply object; wherein, the search reply object is an object that performs natural language processing based on artificial intelligence drive, and the dialogue response result is obtained by the search reply object through data aggregation processing of multimedia resources matching the dialogue question information in the multimedia social application.
[0056] In a possible implementation manner, the device further includes:
[0057] The dialogue display module is configured to execute a confirmation instruction in response to inputting the dialogue question information in the dialogue input area, display the identifier corresponding to the search question object and the dialogue question information in the intelligent dialogue display area, clear the dialogue question information in the dialogue input area, and display the dialogue reply result replied by the search reply object and the source indication information of the dialogue reply result in the intelligent dialogue display area; the source indication information is used to indicate the multimedia resource from which the dialogue reply result comes;
[0058] The first source viewing module is configured to execute a triggering operation in response to the source indication information and display a target multimedia resource from which the dialogue reply result originates.
[0059] In a possible implementation, the dialogue reply result is a dialogue reply text, the dialogue reply text includes at least one reply text segment, each reply text segment corresponds to at least one source indication information; the source indication information is at least one of a source subscript and a source label; the source viewing module includes:
[0060] A source content indication special effect display unit is configured to perform a trigger operation in response to the target source indication information and display a source content indication special effect at a location associated with the target source indication information;
[0061] A source viewing unit is configured to detect that the source content indicates that a special effect is triggered, and display a target multimedia resource from which the target reply text segment originates;
[0062] Among them, the target source indication information is any of the source indication information; the target reply text segment is the reply text segment corresponding to the target source indication information.
[0063] In a possible implementation, the intelligent dialogue display module 1103 includes:
[0064] A first intelligent dialogue display unit is configured to display the dialogue input area and the intelligent dialogue display area in a half-screen pop-up window on the target page;
[0065] or,
[0066] A second intelligent dialogue display unit is configured to execute display of an intelligent dialogue search page, and display the dialogue input area and the intelligent dialogue display area on the intelligent dialogue search page;
[0067] or,
[0068] The third intelligent dialogue display unit is configured to perform incremental display of the dialogue input area and the intelligent dialogue display area in the target area of the target page.
[0069] In a possible implementation manner, the device further includes:
[0070] The sliding unit is configured to execute a sliding operation detected on the half-screen pop-up window, jump to the smart dialogue search page, and display the dialogue input area and the smart dialogue display area on the smart dialogue search page.
[0071] In a possible implementation, the target page is any one of a search homepage, a search result page, a multimedia resource display page, and a sidebar page; the target page displays intelligent dialogue indication information that triggers the intelligent dialogue search instruction; and the intelligent dialogue display module 1103 includes:
[0072] The first dialogue display triggering unit is configured to execute the intelligent dialogue search instruction triggered by the search question object based on the intelligent dialogue indication information, and display the dialogue input area and the intelligent dialogue display area.
[0073] In a possible implementation, the target page is a search homepage, the search homepage displays a search input area, and the search input area includes an information deletion control for deleting information input in the search input area; the intelligent dialogue display module 1103 includes:
[0074] An intelligent dialogue entry guiding unit is configured to respond to question information input in the search input area and incrementally display intelligent dialogue entry guiding information at a position associated with the search input area;
[0075] The second dialogue display triggering unit is configured to display the dialogue input area and the intelligent dialogue display area in response to triggering the intelligent dialogue entry guidance information.
[0076] In a possible implementation, the target page displays a navigation control for guiding the intelligent dialogue search; the intelligent dialogue display module 1103 includes:
[0077] The third dialogue display trigger unit is configured to execute a trigger instruction in response to the navigation control to display the dialogue input area and the intelligent dialogue display area.
[0078] In a possible implementation, the target page is a search result page, and the search result page displays a search input area; the device further includes:
[0079] A search times detection module is configured to detect that the number of search question information input in the search input area reaches a times threshold, and incrementally display entry prompt information of the intelligent dialogue search on the search results page;
[0080] The intelligent dialogue search instruction trigger module is configured to execute a trigger operation in response to the entry prompt information of the intelligent dialogue search and generate the intelligent dialogue search instruction.
[0081] In a possible implementation, the target page is a search result page, and the search result page displays a search input area, search results, and source indication information corresponding to the search results; the device further includes:
[0082] The second source viewing module is configured to execute a triggering operation in response to the source indication information corresponding to the search result, and display the target multimedia resource from which the search result originates.
[0083] In a possible implementation, the search homepage includes search mode selection information, where the search mode selection information is used to indicate whether the search results are obtained by aggregating the searched multimedia resources; and the device further includes:
[0084] The search result page display module is configured to execute the input of search question information in the search input area of the search homepage, and when the search mode selection information is triggered to be processed through aggregation, display the search input area, the search results and the source indication information corresponding to the search results on the search result page.
[0085] In a possible implementation, the search result page display module includes:
[0086] A result type selection unit is configured to execute input of search question information in the search input area of the search homepage, and display search result type selection information when the search mode selection information is triggered to be processed by aggregation; the search result type selection information includes at least one result display type of video, image or text;
[0087] The search result display unit is configured to perform an operation selected based on the search result type selection information, and display the search results under a target result display type; the target result display type is any of the result display types.
[0088] In a possible implementation, the search result is a non-text search result; and the device further includes:
[0089] The search result conversion module is configured to execute, in response to the dialogue instruction information for converting the target result display type of the search result input in the dialogue input area, the search result to convert the search result into a text search result.
[0090] In a possible implementation manner, the search question information and the dialogue question information may be one of text, voice and image information.
[0091] In a possible implementation, the display type of the dialogue response result is at least one of text, image, and video.
[0092] In a possible implementation manner, the device further includes:
[0093] A result display type extraction module is configured to execute, in response to inputting search question information in the search input area of the search homepage or search result page, extracting a target result display type from the search question information;
[0094] The search result display module is configured to display the search results corresponding to the search question information in the target result display type on the search result page, and to display the source indication information corresponding to the search results.
[0095] In a possible implementation manner, the device further includes:
[0096] The tag information generation module is configured to execute a tag generation instruction triggered in response to a multimedia resource publishing request, and display the dialogue input area and the intelligent dialogue display area, wherein the intelligent dialogue display area displays at least one tag information of the multimedia resource to be published in response to the search reply object.
[0097] In a possible implementation, when the dialogue response result is a video, the device further includes:
[0098] The pause response module is configured to execute an operation of detecting that the video is paused during playback, and display text description information corresponding to the target progress in the video replied by the search reply object in the intelligent dialogue display area; the target progress is the playback progress corresponding to the pause of the video during playback.
[0099] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement a method as described in any one of the above-mentioned first aspects.
[0100] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any method described in the first aspect of the embodiment of the present disclosure.
[0101] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising computer instructions, which, when executed by a processor, enable a computer to execute any one of the methods described in the first aspect of an embodiment of the present disclosure.
[0102] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:
[0103] By providing intelligent dialogue search functions in multimedia social applications, information search can be realized in a dialogue chat manner. The dialogue reply results obtained from the search are obtained by data aggregation processing of multimedia resources that match the dialogue question information, that is, the answers are integrated and accurate answers are given directly without the need for users to screen again, thereby improving search efficiency and search accuracy. This intelligent dialogue search scenario can also improve the search experience. And the objects used to give answers are based on artificial intelligence-driven natural language processing, which further improves the accuracy of the answers. In addition, in the intelligent dialogue search scenario, you can easily see the questions and answers of historical searches in the intelligent dialogue display area, which is convenient for correcting questions and providing a better search experience.
[0104] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0105] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.
[0106] Figure 1 It is a schematic diagram of an application environment according to an exemplary embodiment.
[0107] Figure 2 The invention is a flowchart of an information search method according to an exemplary embodiment.
[0108] Figure 3a It is a schematic diagram of triggering an intelligent dialogue search scenario in a search homepage according to an exemplary embodiment.
[0109] Figure 3b It is a schematic diagram of triggering an intelligent dialogue search scenario in a search result page according to an exemplary embodiment.
[0110] Figure 3c The diagram is a schematic diagram of triggering an intelligent dialogue search scenario in a multimedia resource display page according to an exemplary embodiment.
[0111] Figure 3d It is a schematic diagram of triggering an intelligent dialogue search scenario in a sidebar page according to an exemplary embodiment.
[0112] Figure 4a It is a schematic diagram of a half-screen pop-up window display of an intelligent dialogue search scenario according to an exemplary embodiment.
[0113] Figure 4b It is a schematic diagram of a page display of an intelligent dialogue search scenario according to an exemplary embodiment.
[0114] Figure 4c The present invention is a schematic diagram showing an intelligent dialogue search scenario embedded in a search results page according to an exemplary embodiment.
[0115] Figure 5 The present invention is a schematic diagram of triggering source indication information in an intelligent dialogue search scenario according to an exemplary embodiment.
[0116] Figure 6a The figure is a schematic diagram of selecting a search mode according to an exemplary embodiment.
[0117] Figure 6b The figure is a schematic diagram showing a display of a search result page in a normal search mode according to an exemplary embodiment.
[0118] Figure 7a The present invention is a schematic diagram showing a search result page in a smart search mode according to an exemplary embodiment.
[0119] Figure 7b The present invention is a schematic diagram showing another display of a search result page in a smart search mode according to an exemplary embodiment.
[0120] Figure 8 The present invention is a schematic diagram of triggering source indication information in a non-intelligent dialogue search scenario according to an exemplary embodiment.
[0121] Fig. 9 The diagram is a diagram of a dialog showing type conversion according to an exemplary embodiment.
[0122] Fig.10 The present invention is a schematic diagram showing a text description of progress according to an exemplary embodiment.
[0123] Fig.11 The figure is a block diagram of an information search device according to an exemplary embodiment.
[0124] Fig.12 The invention is a block diagram of an electronic device for information search according to an exemplary embodiment.
[0125] Fig.13 The invention is a block diagram of an electronic device for information search according to an exemplary embodiment. DETAILED DESCRIPTION
[0126] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.
[0127] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0128] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology and machine learning / deep learning.
[0129] In recent years, with the research and progress of artificial intelligence technology, artificial intelligence technology has been widely used in many fields. The solution provided in the embodiment of the present application involves technologies such as natural language processing, which is specifically described by the following embodiments:
[0130] See also Figure 1 , Figure 1 is a schematic diagram of an application environment according to an exemplary embodiment. Figure 1 As shown, the application environment may include a server 01 and a terminal 02 .
[0131] In an optional embodiment, the terminal 02 can be used for interaction and display of information search. Specifically, the terminal 02 can include but is not limited to smart phones, desktop computers, tablet computers, laptop computers, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, smart wearable devices and other types of electronic devices. Optionally, the operating system running on the electronic device can include but is not limited to Android system, IOS system, Linux, Windows, etc.
[0132] In an optional embodiment, the server 01 can be used to receive the dialogue question information or search question information sent by the terminal 02, and search and integrate multimedia resources based on the dialogue question information or search question information to provide answers, and can make the answers conform to the natural language expression in the intelligent dialogue search scenario to enhance the interactive experience; and provide the answers to the terminal 02 for display. Specifically, the server 01 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.
[0133] In addition, it should be noted that Figure 1 What is shown is only one application environment of the information search method provided by the present disclosure.
[0134] In the embodiments of this specification, the server 01 and the terminal 02 may be directly or indirectly connected via wired or wireless communication, and this application does not impose any limitation thereto.
[0135] It should be noted that the following figure shows a possible order of steps, which is not actually limited to this order. Some steps can be executed in parallel without relying on each other. The user information (including but not limited to user device information, user personal information, user behavior information, etc.) and data (including but not limited to data for display, training data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.
[0136] Figure 2 FIG. 1 is a flow chart of an information search method according to an exemplary embodiment, which can be applied to a terminal (which can be regarded as a client of a multimedia application). Figure 2 As shown, the following steps may be included.
[0137] In step S201, a target page of a multimedia social application is displayed.
[0138] In the embodiments of this specification, a multimedia social application may refer to an application that provides social interaction based on multimedia resources, such as a graphic social application, a video social application, etc. A video social application may be a short video social application, which is not limited in this disclosure. The target page of a multimedia social application may refer to any page in a multimedia social application, as long as the entry or prompt of the intelligent dialogue search function can be embedded in the page for display, which is not limited in this disclosure. It should be noted that the application here may refer to an application program.
[0139] As an example, see Figure 3a to Figure 3d The target page can be any one of the search homepage, search result page, multimedia resource display page, and sidebar page. The present disclosure does not limit the target page. In short video social applications, multimedia resource display pages can include but are not limited to single-column video stream display pages and double-column video stream display pages.
[0140] In actual applications, you can open a multimedia social application to enter the homepage of the multimedia social application, and then enter other pages after further selection. The homepage and other pages here can all be regarded as target pages. After selecting the target page, the multimedia social application can display the corresponding target page.
[0141] In step S203, in response to the intelligent dialogue search instruction for searching the question object, the dialogue input area and the intelligent dialogue display area are displayed.
[0142] In the embodiment of the present specification, the search question object may refer to any social account in the multimedia social application, and the social account can be used to uniquely identify different users in the multimedia social application.
[0143] The intelligent dialogue search instruction can be used to start the intelligent dialogue search scenario in the multimedia social application. In the intelligent dialogue search scenario, questions (dialogue question information) and answers (dialogue response results) can be asked through dialogue; and the answer is obtained by data aggregation processing of multimedia resources matched with dialogue question information in the multimedia social application based on the object driven by artificial intelligence for natural language processing, that is, the answer is to integrate the searched multimedia resources, not to directly present the searched and matched multimedia resources as answers. It can be understood that the multimedia resources already exist in the multimedia social application, such as the constructed encyclopedia knowledge, web pages, short videos, etc. The answer is dynamically generated based on the multimedia resources already existing in the multimedia social application, and may not exist in the multimedia social application. Specifically, the generation method here can be obtained after natural language processing based on artificial intelligence drive, that is, it can be through natural language processing to understand the searched multimedia resources, so as to perform data merging, data fusion, etc., to give a more fluent, complete and accurate answer, which is easy to understand. In other words, the answer is given in a chat way. In an example, such as one question and one answer, the number of answers is one, and it is an integration of related resources, which is more accurate and comprehensive.
[0144] The dialogue input area can be used to input dialogue question information, such as Figure 4a 42; The intelligent dialogue display area shown can be used to display the identifier and dialogue question information corresponding to the search question object, as well as the dialogue response result of the search reply object. The search reply object can be an object that performs natural language processing based on artificial intelligence drive. It can be understood that the search reply object can be an object that can perform intelligent chat interaction. For example, the search reply object can perform natural language processing based on artificial intelligence drive, so that it can conduct dialogue by understanding and learning natural language, and can also interact according to the context of the chat to achieve chat communication. As an example, the search reply object can be a language generation model based on deep learning.
[0145] For example, the search reply object can be obtained by collecting a large amount of training data to train the initial language generation model. The training can be self-supervised, reinforced learning, etc. The present disclosure does not limit the training method of the language generation model. Taking learning multimedia resources as an example, inputting a sample question text can obtain sample multimedia matching the sample question text, so that the content of the sample multimedia can be aggregated to obtain a sample answer, and the sample answer can be scored to achieve reinforced learning until the iteration ends and the language generation model is obtained.
[0146] The dialogue reply result can be obtained by performing data aggregation processing on the multimedia resources that match the dialogue question information in the multimedia social application by the search reply object. Data aggregation may include data merging, data fusion, etc., which is not limited in the present disclosure. The search question object and the search reply object here can be regarded as two objects of the chat. The search question object can be used to ask questions, and the search reply object can be used to give intelligent answers based on the questions. Specifically, matching multimedia resources can be searched based on the questions, such as searching matching multimedia resources based on keywords in the questions, so that text content can be extracted from the multimedia resources, and then the text content can be aggregated to generate answers. As an example, the process of searching and aggregating to generate answers can request the server to execute, so that the answers can be received and displayed.
[0147] In practical applications, multimedia resources may include but are not limited to video, graphics, and text resources. Videos may include long videos, short videos, and the like; graphics and text resources may include images and text, such as H5 web pages, and the present disclosure does not limit this.
[0148] Optionally, the smart conversation display area can also display the logo corresponding to the search reply object.
[0149] As an example, the intelligent dialogue display area can be as follows Figure 4a 41 shown. The search for the identifier corresponding to the question object can be as follows Figure 4a 411 as shown, for example, a headshot; the conversation question information can be as shown in 4a 412. The identifier corresponding to the search reply object can be as shown in Figure 4a As shown in 413, for example, a virtual image of a reply object is searched, and the virtual image may be preset, and may be one or more; the dialogue reply result may be as follows: Figure 4a 414 shown.
[0150] Exemplarily, the display type of the dialogue response result can be at least one of text, image, and video; it should be noted that when the display type of the dialogue response result is an image or video, it is also an aggregated result obtained after natural language understanding, such as fine-tuning the image, cropping or adding image content, or clipping and splicing the video, etc., which is not limited in this disclosure. Based on the diversity of multimedia resources in multimedia social applications, the dialogue response results after natural language processing driven by artificial intelligence can be flexible and diverse.
[0151] In a possible implementation, the target page may be any one of the search homepage, search result page, multimedia resource display page, and sidebar page; the target page may display intelligent dialogue indication information that triggers the intelligent dialogue search instruction. In one example, the intelligent dialogue indication information may be as follows: Figure 3b to Figure 3d The smart conversation indicator icon shown, for example Figure 3b 34 shown, Figure 3c 35 shown in FIG. 3d and 36 shown in FIG. 3d. Alternatively, in another example, the intelligent dialogue indication information may be as follows: Figure 3c 33 in the figure may be a text prompt information for prompting the intelligent dialogue. The present disclosure does not limit the intelligent dialogue indication information.
[0152] Accordingly, in response to the intelligent dialogue search instruction of the search question object, displaying the dialogue input area and the intelligent dialogue display area may include: in response to the intelligent dialogue search instruction triggered by the search question object based on the intelligent dialogue indication information, such as clicking the intelligent dialogue indication information, the intelligent dialogue search instruction may be generated, and the dialogue input area and the intelligent dialogue display area may be displayed. By setting clear intelligent dialogue indication information on the target page, users can be effectively guided to use the intelligent dialogue search instruction.
[0153] For example, if Figure 3c As shown, you can click on Figure 3c 35 in the figure, thereby triggering the intelligent dialogue search command, thereby displaying the dialogue input area and the intelligent dialogue display area, such as displaying Figure 4b .
[0154] Or, if Figure 3d As shown, you can click when browsing videos (such as short videos). Figure 3d 36 in the figure, thereby triggering the intelligent dialogue search instruction, thereby displaying the dialogue input area and the intelligent dialogue display area, such as displaying Figure 4b It should be noted that when sliding the video to switch between different videos, Figure 3d 36 of them can be displayed continuously.
[0155] Or, if Figure 3b As shown, you can click Figure 3b 34 in this way, the intelligent dialogue search command can be triggered, so that the dialogue input area and the intelligent dialogue display area can be displayed, such as displaying Figure 4a , Figure 4b or Figure 4c One of them.
[0156] In a possible implementation, the target page may be a search homepage, which displays a search input area. The search input area is, for example, Figure 3a 37. The search input area includes an information deletion control for deleting the information input in the search input area, such as Figure 3a The information in the search input area shown as 38 can be regarded as the title of the search and needs to be manually deleted before other questions can be entered.
[0157] Accordingly, in response to the intelligent dialogue search instruction for searching the question object, displaying the dialogue input area and the intelligent dialogue display area may include: in response to inputting the question information in the search input area, incrementally displaying the intelligent dialogue entry guidance information at the associated position of the search input area, for example Figure 3a As shown in 31, the intelligent dialogue entry guidance information can be the guidance information for the intelligent dialogue search dynamically displayed based on the question information input in the search input area, so that the page display is more flexible and can accurately meet the user's search needs.
[0158] Furthermore, in response to the triggering of the intelligent dialogue entry guidance information, the dialogue input area and the intelligent dialogue display area can be displayed, for example, Figure 4b .
[0159] In a possible implementation, the target page may display a navigation control for guiding the intelligent dialogue search. The navigation control for guiding the intelligent dialogue search may be as follows: Figure 3b 32 "Chat" shown. Accordingly, in response to the intelligent dialogue search instruction for searching the question object, displaying the dialogue input area and the intelligent dialogue display area may include: in response to the trigger instruction of the navigation control, the dialogue input area and the intelligent dialogue display area may be displayed, for example, Figure 4a to Figure 4c By setting a navigation control for guiding the intelligent conversation search, it is possible to increase the entry methods for the intelligent conversation search function and improve the convenience of using the intelligent conversation search for users.
[0160] In one possible implementation, the target page may be a search results page, which displays a search input area and, optionally, an information deletion control for deleting the information entered in the search input area. This is similar to the search input area of the search homepage. In this case, the method may also include: detecting that the number of search question information entered in the search input area reaches a number threshold, and incrementally displaying entry prompt information for the intelligent dialogue search on the search results page. The entry prompt information for the intelligent dialogue search may be in the form of text, icons, special effects, etc., which is not limited in this disclosure. Taking an icon as an example, it may be as follows: Figure 3b As shown in 34, for example, if it is detected that the number of search question information entered in the search input area reaches a number threshold, the search result page can be incrementally displayed. Figure 3b 34 shown, that is Figure 3b The 34 shown can be a continuous display or a dynamically triggered display, which is not limited in the present disclosure.
[0161] Furthermore, in response to the triggering operation of the entry prompt information of the intelligent dialogue search, an intelligent dialogue search instruction is generated. By setting a number threshold to actively trigger the incremental display of the entry prompt information of the intelligent dialogue search, the intelligent dialogue search scenario can be actively guided in the search input scenario, so as to avoid the user from repeatedly deleting the search question letter in the search input area and asking inaccurate questions, and provide the user with accurate and easy-to-understand intelligent dialogue search services in a timely manner.
[0162] As an example, the search question information and dialogue question information may be a type of information in the form of text, voice, and image, which may provide users with a richer search method and make the search more convenient.
[0163] Reference Figures 4a to 4c The above steps of displaying the dialogue input area and the intelligent dialogue display area may include:
[0164] In the target page, a half-screen pop-up window is used to display the dialogue input area and the smart dialogue display area; for example, a smart dialogue search command can be triggered on the search results page, and a half-screen pop-up window can be used to display the dialogue input area and the smart dialogue display area. Figure 4a Optionally, the conversation question information and conversation answer results in the smart conversation display area in the half-screen pop-up window can be the search question information and search results entered in the search results page before the half-screen pop-up window is displayed, so that when the search scene is switched, the presentation of historical searches can be maintained.
[0165] or,
[0166] Display the intelligent dialogue search page, display the dialogue input area and the intelligent dialogue display area on the intelligent dialogue search page; for example Figure 4b As shown; it should be noted that the smart dialogue search page here can also be regarded as the full-screen mode of the above-mentioned half-screen pop-up window, that is, the smart dialogue search page can be the page after the jump or can be a full-screen pop-up window page in the target page, and the present disclosure does not limit this.
[0167] Alternatively, the dialog input area and the intelligent dialog display area are incrementally displayed in the target area of the target page, for example Figure 4c 43. In this case, when the target page is a search result page, the historical search content may not be copied to the smart dialogue display area for display, because the dialogue input area and the smart dialogue display area are embedded in the search result page, such as embedded in a card manner, and the search result page displays the latest historical search content.
[0168] By displaying the conversation input area and the smart conversation display area in a half-screen pop-up window, a smart conversation search page, or a target area of a target page, the flexibility and convenience of the smart conversation search service can be improved.
[0169] Accordingly, when the conversation input area and the smart conversation display area are displayed in the half-screen pop-up window, the method may further include: detecting a sliding operation on the half-screen pop-up window, jumping to the smart conversation search page, that is, displaying the smart conversation search page in full-screen mode, and displaying the conversation input area and the smart conversation display area on the smart conversation search page. The half-screen mode and full-screen mode of the smart conversation search page can be flexibly operated.
[0170] In a possible implementation, the method may further include: in response to a confirmation instruction for inputting dialogue question information in the dialogue input area, displaying an identifier and dialogue question information corresponding to the search question object in the intelligent dialogue display area, clearing the dialogue question information in the dialogue input area, and displaying a dialogue reply result replied by the search reply object and source indication information of the dialogue reply result in the intelligent dialogue display area; the source indication information is used to indicate the multimedia resource from which the dialogue reply result comes;
[0171] Furthermore, in response to the triggering operation of the source indication information, the target multimedia resource from which the dialogue reply result comes can be displayed. By setting up intelligent dialogue search scenarios, the search accuracy can be improved without requiring users to search in a large number of search results; it can also avoid frequent manual deletion of historical questions during the search process, improving the search interaction experience; and it can provide the source of the integrated answer, thereby providing a convenient way to view the source of the answer on the basis of giving accurate and intelligent answers, facilitating the viewing of the source, and on this basis, it can also dig out high-quality sources and increase the display of high-quality sources.
[0172] As an example, Figure 4b For example, the source indication information may be a source subscript, such as Figure 4b 415 shown; alternatively, the source indication information may be a source tag, such as Figure 4b 416 shown. The present disclosure does not limit the specific form of the source indication information. Exemplarily, the source indication information can be used to guide the source of the answer, and the source of the answer can refer to the resources used to form the answer, that is, the answer is obtained based on source aggregation, where the source refers to the existing resources in the multimedia social application. Based on this, the source view can be regarded as a detailed view of the original resources that form the answer. In this way, when providing accurate and intelligent aggregated answers, the source view before aggregation can be provided, which is convenient for users to browse the original resources, so as to better understand the answer in combination with the aggregated answer.
[0173] Optionally, when the number of source tags is greater than the threshold value of the number of source tags that can be displayed in the display area, some of the source tags can be displayed and other source tags can be hidden. Accordingly, the display area of the source tags can be expanded by a preset trigger method, so that all source tags can be displayed, which can be regarded as a flexible switching between the collapsed and expanded states of the display area of the source tags, and the present disclosure does not limit this.
[0174] In an optional implementation manner, the dialogue reply result may be a dialogue reply text, such as Figure 4b As shown. The dialogue reply text may include at least one reply text segment, for example, Figure 4b The example shown includes three reply text segments. Each reply text segment may correspond to at least one source indication information; the source indication information is at least one of a source subscript and a source label. Figure 4b For example, the first reply text segment corresponds to one source tag; the second reply text segment corresponds to two source tags; and the third reply text segment corresponds to one source tag. The source tag and source label can be different ways of describing multimedia resources from the same source, i.e. Figure 4b The sources pointed to by 415 and 416 in the reference source can correspond to each other. Based on this, the arrangement order of the source tags in the reference source can be in accordance with the arrangement order of the source subscripts corresponding to the reply text segment. Optionally, the arrangement order of the source tags in the reference source can be randomly arranged, which is not limited by the present disclosure.
[0175] Accordingly, in response to the triggering operation of the source indication information, displaying the target multimedia resource from which the dialogue reply result originates may include: in response to the triggering operation of the target source indication information, displaying a source content indication special effect at a location associated with the target source indication information. Figure 5 As shown, 51 is a content bubble, and the content in the content bubble may be the searched question information, or may be the title of the source multimedia resource, or may be the summary content of the corresponding reply text segment, which is not limited in the present disclosure.
[0176] Furthermore, if the source content is detected and the special effect is triggered, the target multimedia resource from which the target reply text segment originates can be displayed. Figure 5 51 in is triggered, such as being clicked, and can be displayed Figure 5 The display on the right side can display the target multimedia resource in a half-screen pop-up window. The present disclosure does not limit this, and you can also jump directly to the page of the target multimedia resource, such as watching the short video in the display page of the short video. Optionally, the title and author can also be displayed above the target multimedia resource.
[0177] Among them, the target source indication information can be any of the source indication information; the target reply text segment can be the reply text segment corresponding to the target source indication information.
[0178] Through the triggering operation of the target source indication information, the source content indication special effect is displayed at the associated position of the target source indication information, so as to accurately locate the source multimedia resource based on the source content indication special effect, which is flexible, convenient and provides a rich interactive experience.
[0179] Optionally, in actual applications, you can select a search mode on the search homepage, that is, you can choose whether to aggregate the searched multimedia resources, that is, whether to select the normal search mode to directly display the searched multimedia resources, or to aggregate the searched multimedia resources to obtain more accurate and complete search results.
[0180] In a possible implementation, the search homepage may include search mode selection information, which may be used to indicate whether the search results are obtained by aggregating the searched multimedia resources. As an example, see Figure 6a 61 shown. Accordingly, the method may also include:
[0181] When search question information is input in the search input area of the search homepage and the search mode selection information is triggered to be processed through aggregation, the search input area, search results, and source indication information corresponding to the search results are displayed on the search results page.
[0182] Exemplarily, when the smart search mode is selected, the search results may be as follows: Figure 7a or Figure 7b As shown, the search results can be accurate text search results after aggregation, which is a generative search result, that is, the integration of existing multimedia resources. The number of text search results can be one, and the user does not need to filter again, which can get accurate answers and improve the search experience. In an optional method, the number of text search results can be less than the quantity threshold to ensure accurate reach of the search results.
[0183] Optionally, in the case of selecting the normal search mode, the search results can be as follows: Figure 6b As shown, the displayed multimedia resources are the existing ones that are searched, without aggregating the multimedia resources matched by the search. The search results are not accurate and require further review and screening by the user. However, this can adapt to the search habits of some users, so that the intelligent search question-and-answer service can be more smoothly transitioned.
[0184] By setting the search mode selection information, the multimedia social application can transition from the ordinary search mode to the intelligent search mode; and when the intelligent search mode is selected, the source of the search results can be provided, which can not only provide accurate generative collection results, but also provide a convenient way to view the source of the search results.
[0185] It should be noted that the selection of search mode is to select whether to aggregate the multimedia resources matched by the search, that is, whether the search results are processed through aggregation. As for the difference in search scenarios, the search scenarios provided by the search input area on the search homepage and the search results page are non-intelligent dialogue search scenarios, where the search input area requires manual deletion of questions in order to ask multiple questions; the intelligent dialogue search scenario is the display dialogue input area and the intelligent dialogue display area, which is a scenario for searching through intelligent dialogue, and does not require manual deletion of questions and other information in the dialogue input area, and belongs to the chat-style search interaction.
[0186] In a possible implementation, when search question information is input in the search input area of the search homepage and the search mode selection information is triggered to be processed by aggregation, the search input area, search results, and source indication information corresponding to the search results are displayed on the search results page, which may include:
[0187] Enter search question information in the search input area of the search homepage, and display search result type selection information when the search mode selection information is triggered to be processed through aggregation; the search result type selection information includes at least one result display type of video, image or text;
[0188] Based on the operation selected by the search result type selection information, the search results under the target result display type are displayed; the target result display type is any one of the result display types.
[0189] By setting the search result type selection information, we can make full use of the richness of data forms in multimedia social applications and provide users with choices of search result display types, so that users can choose their preferred display type to view search results, which can not only make full use of the diversity of resources, but also improve the search experience; and in the intelligent search mode, the display flexibility of intelligent search results can be improved, which is both accurate and can provide rich display styles, thereby improving the search interaction experience.
[0190] In an optional embodiment, the method may also include: in response to search question information being input into the search input area of the search home page or search results page, extracting a target result display type from the search question information; thereby displaying the search results corresponding to the search question information on the search results page with the target result display type, and displaying source indication information corresponding to the search results.
[0191] For example, if the input search question information is "Please find me a picture of XX", the picture here can be extracted as the target result display type, so that the search results are displayed in the form of pictures. The original display type of the search results here can be a picture, or it can be a video or text. In this case, the picture form of the search results can be obtained by converting the searched video or text. The present disclosure does not limit the specific method of the conversion. The display type of the search results is indicated by the user in the question, which improves the flexibility of the search and flexibly utilizes the richness of multimedia resources.
[0192] In the embodiment of the present specification, the target page may be a search result page, which may display a search input area, search results, and source indication information corresponding to the search results. Based on this, the method may also include: in response to a trigger operation of the source indication information corresponding to the search result, displaying the target multimedia resource from which the search result comes.
[0193] Reference Figure 8 In one example, the source badge 1 can be clicked to display the source content indication effect of the source badge 1, such as displaying the bubble content above the source badge 1, such as Figure 8 81 shown, the specific process can be found in Figure 5 Therefore, by clicking on the bubble content, the target multimedia resource from which the search results come can be displayed.
[0194] Through the triggering operation of the target source indication information, the source content indication special effect is displayed at the associated position of the target source indication information, so as to accurately locate the source multimedia resource based on the source content indication special effect, which is flexible, convenient and provides a rich interactive experience.
[0195] In the embodiment of this specification, the search results may be non-text search results; accordingly, the method may further include: in response to the dialogue instruction information for converting the target result display type of the search results in the dialogue input area, converting the search results into text search results. For example, when the smart search mode is used on the search results page but the smart search scenario is not used, if the display type is converted relative to the non-text search results, the "chat" navigation control can be triggered to enter Fig. 9 In the smart search scenario on the right, the non-text search results on the search results page are converted to display types through a dialogue. Alternatively, a "chat" can be triggered to dynamically embed the following information on the search results page: Fig. 9The smart search scene card on the lower left side can be used to indicate through dialogue that the non-text search results on the search results page should be converted to a display type. The search results here also trigger the smart search scene, which is not limited to triggering the "chat" navigation control. You can refer to the various methods described above, which will not be repeated here.
[0196] For example, see Fig. 9 You can also convert a certain segment in the video into text. For example, if the video introduces the complete steps of a method, you can enter "Convert the beginning steps in the video into text for easy viewing". In this way, the search reply object can extract the content of the beginning steps in the video based on the understanding of natural language, such as the audio explanation content, and generate text, which is displayed in the intelligent dialogue display area. For example Fig. 9 The text below "Okay, right away" is shown.
[0197] By providing a conversion of the result display type in the dialogue input area, the display method of the search results can be converted by displaying information in a dialogue. For example, the searched video can be converted into text using intelligent dialogue, making reading more convenient and efficient; or text can be converted into video, which is easier to understand. This can effectively expand the function of the dialogue input area, and can not only provide a search question function, but also provide a function for type conversion of answers to search questions, thereby making the functions of the intelligent dialogue search scenario richer and more convenient, and more effectively utilizing the richness of multimedia resources in multimedia social applications, so that a large number of conversion processes can be mapped between resource types without resulting in a large consumption of processing resources.
[0198] Reference Fig.10 , when the result of the dialogue reply can be a video, the method may further include: detecting a pause operation during video playback, and displaying text description information corresponding to the target progress in the video replied by the search reply object in the smart dialogue display area; wherein the target progress is the playback progress corresponding to the pause of the video during playback. Optionally, the pause processing method may also use the same Fig. 9 Scenes of browsing videos in the search results page.
[0199] Reference Fig.10 , the target progress can be Fig.10 1001 in the target progress, the text description information corresponding to the target progress can be Fig.10 1002 in . For example, when browsing a step-by-step solution video, you may pause at a difficult step to get more time to understand the step. In this case, a text description of the step can be triggered, so that the step can be understood in combination with the text, and the text can be presented continuously, so there is no need to check the progress repeatedly, and the search experience is better.
[0200] As an example, the text description may be a content description within a progress range, and the progress range may include a target progress. The specific method for determining the progress range is not limited, as long as the content involved in the target progress can be fully and clearly expressed.
[0201] In an optional implementation, the method may further include: in response to a tag generation instruction triggered in a multimedia resource publishing request, displaying a conversation input area and an intelligent conversation display area, wherein at least one tag information of the multimedia resource to be published replied by the search reply object is displayed in the intelligent conversation display area. For example, when a user wants to publish a short video after making it, if the tag generation instruction is triggered, the intelligent search scene can be automatically entered, so that in the intelligent search scene, at least one tag information of the multimedia resource to be published replied by the search reply object can be displayed in the intelligent conversation display area, that is, the search reply object can reply to the user's available tag information in a conversational manner. In multimedia social applications, automatically tagging the multimedia resources to be published through intelligent search scenes can improve the accuracy of tags and improve user experience.
[0202] Fig.11 is a block diagram of an information search device according to an exemplary embodiment. Fig.11 , the device may include:
[0203] The display module 1101 is configured to execute and display a target page of a multimedia social application;
[0204] The intelligent dialogue display module 1103 is configured to execute an intelligent dialogue search instruction in response to searching for a question object, and display a dialogue input area and an intelligent dialogue display area;
[0205] Among them, the dialogue input area is used to input dialogue question information of questions; the intelligent dialogue display area is used to display the identifier corresponding to the search question object and the dialogue question information, as well as the dialogue response result of the search reply object; wherein, the search reply object is an object that performs natural language processing based on artificial intelligence drive, and the dialogue response result is obtained by the search reply object through data aggregation processing of multimedia resources matching the dialogue question information in the multimedia social application.
[0206] By providing intelligent dialogue search functions in multimedia social applications, information search can be realized in a dialogue chat manner. The dialogue reply results obtained from the search are obtained by data aggregation processing of multimedia resources that match the dialogue question information, that is, the answers are integrated and accurate answers are given directly without the need for users to screen again, thereby improving search efficiency and search accuracy. This intelligent dialogue search scenario can also improve the search experience. And the objects used to give answers are based on artificial intelligence-driven natural language processing, which further improves the accuracy of the answers. In addition, in the intelligent dialogue search scenario, you can easily see the questions and answers of historical searches in the intelligent dialogue display area, which is convenient for correcting questions and providing a better search experience.
[0207] In a possible implementation, the device may further include:
[0208] The dialogue display module is configured to execute a confirmation instruction in response to inputting the dialogue question information in the dialogue input area, display the identifier corresponding to the search question object and the dialogue question information in the intelligent dialogue display area, clear the dialogue question information in the dialogue input area, and display the dialogue reply result replied by the search reply object and the source indication information of the dialogue reply result in the intelligent dialogue display area; the source indication information is used to indicate the multimedia resource from which the dialogue reply result comes;
[0209] The first source viewing module is configured to execute a triggering operation in response to the source indication information and display a target multimedia resource from which the dialogue reply result originates.
[0210] In a possible implementation, the dialogue reply result is a dialogue reply text, the dialogue reply text includes at least one reply text segment, each reply text segment corresponds to at least one source indication information; the source indication information is at least one of a source subscript and a source label; the source viewing module may include:
[0211] A source content indication special effect display unit is configured to perform a trigger operation in response to the target source indication information and display a source content indication special effect at a location associated with the target source indication information;
[0212] A source viewing unit is configured to detect that the source content indicates that a special effect is triggered, and display a target multimedia resource from which the target reply text segment originates;
[0213] Among them, the target source indication information is any of the source indication information; the target reply text segment is the reply text segment corresponding to the target source indication information.
[0214] In a possible implementation, the intelligent dialogue display module 1103 includes:
[0215] A first intelligent dialogue display unit is configured to display the dialogue input area and the intelligent dialogue display area in a half-screen pop-up window on the target page;
[0216] or,
[0217] A second intelligent dialogue display unit is configured to execute display of an intelligent dialogue search page, and display the dialogue input area and the intelligent dialogue display area on the intelligent dialogue search page;
[0218] or,
[0219] The third intelligent dialogue display unit is configured to perform incremental display of the dialogue input area and the intelligent dialogue display area in the target area of the target page.
[0220] In a possible implementation, the device may further include:
[0221] The sliding unit is configured to execute a sliding operation detected on the half-screen pop-up window, jump to the smart dialogue search page, and display the dialogue input area and the smart dialogue display area on the smart dialogue search page.
[0222] In a possible implementation, the target page is any one of a search homepage, a search result page, a multimedia resource display page, and a sidebar page; the target page displays intelligent dialogue indication information that triggers the intelligent dialogue search instruction; the intelligent dialogue display module 1103 may include:
[0223] The first dialogue display triggering unit is configured to execute the intelligent dialogue search instruction triggered by the search question object based on the intelligent dialogue indication information, and display the dialogue input area and the intelligent dialogue display area.
[0224] In a possible implementation, the target page is a search homepage, the search homepage displays a search input area, and the search input area includes an information deletion control for deleting information input in the search input area; the intelligent dialogue display module 1103 may include:
[0225] An intelligent dialogue entry guiding unit is configured to respond to question information input in the search input area and incrementally display intelligent dialogue entry guiding information at a position associated with the search input area;
[0226] The second dialogue display triggering unit is configured to display the dialogue input area and the intelligent dialogue display area in response to triggering the intelligent dialogue entry guidance information.
[0227] In a possible implementation, the target page displays a navigation control for guiding the intelligent dialogue search; the intelligent dialogue display module 1103 may include:
[0228] The third dialogue display trigger unit is configured to execute a trigger instruction in response to the navigation control to display the dialogue input area and the intelligent dialogue display area.
[0229] In a possible implementation, the target page is a search result page, and the search result page displays a search input area; the device may further include:
[0230] A search times detection module is configured to detect that the number of search question information input in the search input area reaches a times threshold, and incrementally display entry prompt information of the intelligent dialogue search on the search results page;
[0231] The intelligent dialogue search instruction trigger module is configured to execute a trigger operation in response to the entry prompt information of the intelligent dialogue search and generate the intelligent dialogue search instruction.
[0232] In a possible implementation, the target page is a search result page, and the search result page displays a search input area, search results, and source indication information corresponding to the search results; the device may also include:
[0233] The second source viewing module is configured to execute a triggering operation in response to the source indication information corresponding to the search result, and display the target multimedia resource from which the search result originates.
[0234] In a possible implementation, the search homepage includes search mode selection information, where the search mode selection information is used to indicate whether the search results are obtained by aggregating the searched multimedia resources; the device may further include:
[0235] The search result page display module is configured to execute the input of search question information in the search input area of the search homepage, and when the search mode selection information is triggered to be processed through aggregation, display the search input area, the search results and the source indication information corresponding to the search results on the search result page.
[0236] In a possible implementation, the search result page display module may include:
[0237] A result type selection unit is configured to execute input of search question information in the search input area of the search homepage, and display search result type selection information when the search mode selection information is triggered to be processed by aggregation; the search result type selection information includes at least one result display type of video, image or text;
[0238] The search result display unit is configured to perform an operation selected based on the search result type selection information, and display the search results under a target result display type; the target result display type is any of the result display types.
[0239] In a possible implementation, the search result is a non-text search result; and the device may further include:
[0240] The search result conversion module is configured to execute, in response to the dialogue instruction information for converting the target result display type of the search result input in the dialogue input area, the search result to convert the search result into a text search result.
[0241] In a possible implementation manner, the search question information and the dialogue question information may be one of text, voice and image information.
[0242] In a possible implementation, the display type of the dialogue response result is at least one of text, image, and video.
[0243] In a possible implementation, the device may further include:
[0244] A result display type extraction module is configured to execute, in response to inputting search question information in the search input area of the search homepage or search result page, extracting a target result display type from the search question information;
[0245] The search result display module is configured to display the search results corresponding to the search question information in the target result display type on the search result page, and to display the source indication information corresponding to the search results.
[0246] In a possible implementation, the device may further include:
[0247] The tag information generation module is configured to execute a tag generation instruction triggered in response to a multimedia resource publishing request, and display the dialogue input area and the intelligent dialogue display area, wherein the intelligent dialogue display area displays at least one tag information of the multimedia resource to be published in response to the search reply object.
[0248] In a possible implementation, when the dialogue response result is a video, the device may further include:
[0249] The pause response module is configured to execute an operation of detecting that the video is paused during playback, and display text description information corresponding to the target progress in the video replied by the search reply object in the intelligent dialogue display area; the target progress is the playback progress corresponding to the pause of the video during playback.
[0250] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0251] Fig.12 is a block diagram of an electronic device for information search according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.12 As shown. The electronic device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for information search is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc.
[0252] Those skilled in the art will understand that Fig.12 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0253] Fig.13 is a block diagram of an electronic device for information search according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. Fig.13As shown. The electronic device includes a processor, a memory and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for information search is implemented.
[0254] Those skilled in the art will understand that Fig.13 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0255] In an exemplary embodiment, an electronic device is also provided, including: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the information search method in the embodiment of the present disclosure.
[0256] In an exemplary embodiment, a computer-readable storage medium is also provided, and when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the information search method in the embodiment of the present disclosure. The computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
[0257] In an exemplary embodiment, a computer program product containing instructions is also provided. When the computer program product is run on a computer, the computer is caused to execute the information search method in the embodiment of the present disclosure.
[0258] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0259] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.
[0260] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims
1. An information search method, It is characterized in that include: Display the target page of the multimedia social application; In response to an intelligent dialogue search instruction for searching a question object, a dialogue input area and an intelligent dialogue display area are displayed; Among them, the dialogue input area is used to input dialogue question information of questions; the intelligent dialogue display area is used to display the identifier corresponding to the search question object and the dialogue question information, as well as the dialogue response result of the search reply object; wherein, the search reply object is an object that performs natural language processing based on artificial intelligence drive, and the dialogue response result is obtained by the search reply object through data aggregation processing of multimedia resources matching the dialogue question information in the multimedia social application.
2. The method according to claim 1, It is characterized in that The method further comprises: In response to a confirmation instruction of inputting the dialogue question information in the dialogue input area, the identifier corresponding to the search question object and the dialogue question information are displayed in the intelligent dialogue display area, the dialogue question information in the dialogue input area is cleared, and the dialogue response result replied by the search response object and the source indication information of the dialogue response result are displayed in the intelligent dialogue display area; the source indication information is used to indicate the multimedia resource from which the dialogue response result comes; In response to a triggering operation of the source indication information, a target multimedia resource from which the dialogue reply result originates is displayed.
3. The method according to claim 2, It is characterized in that The dialogue reply result is a dialogue reply text, the dialogue reply text includes at least one reply text segment, each reply text segment corresponds to at least one source indication information; the source indication information is at least one of a source subscript and a source label; The displaying of the target multimedia resource from which the dialogue reply result originates in response to the triggering operation of the source indication information comprises: In response to a triggering operation of the target source indication information, displaying a source content indication special effect at a location associated with the target source indication information; Detecting that the source content indicates that the special effect is triggered, displaying the target multimedia resource from which the target reply text segment originates; Among them, the target source indication information is any of the source indication information; the target reply text segment is the reply text segment corresponding to the target source indication information.
4. The method according to any one of claims 1 to 3, It is characterized in that The display dialogue input area and the intelligent dialogue display area include: Displaying the dialogue input area and the intelligent dialogue display area in a half-screen pop-up window on the target page; or, Displaying an intelligent dialogue search page, displaying the dialogue input area and the intelligent dialogue display area on the intelligent dialogue search page; Alternatively, the dialogue input area and the intelligent dialogue display area are incrementally displayed in the target area of the target page.
5. The method according to claim 4, It is characterized in that When the dialogue input area and the intelligent dialogue display area are displayed in the half-screen pop-up window, the method further includes: A sliding operation on the half-screen pop-up window is detected, and the page is jumped to the smart dialogue search page, and the dialogue input area and the smart dialogue display area are displayed on the smart dialogue search page.
6. The method according to any one of claims 1 to 3, It is characterized in that The target page is any one of a search homepage, a search result page, a multimedia resource display page, and a sidebar page; the target page displays intelligent dialogue indication information that triggers the intelligent dialogue search instruction; The display of the dialogue input area and the intelligent dialogue display area in response to the intelligent dialogue search instruction for searching the question object includes: In response to the intelligent dialogue search instruction triggered by the search question object based on the intelligent dialogue indication information, a dialogue input area and an intelligent dialogue display area are displayed.
7. The method according to any one of claims 1 to 3, It is characterized in that The target page is a search homepage, the search homepage displays a search input area, and the search input area includes an information deletion control for deleting information input in the search input area; The display of the dialogue input area and the intelligent dialogue display area in response to the intelligent dialogue search instruction for searching the question object includes: In response to question information being input in the search input area, incrementally displaying intelligent dialogue entry guidance information at a location associated with the search input area; In response to triggering the intelligent dialogue entry guidance information, a dialogue input area and an intelligent dialogue display area are displayed.
8. The method according to any one of claims 1 to 3, It is characterized in that The target page displays a navigation control for guiding the intelligent dialogue search; the intelligent dialogue search instruction in response to the search question object displays the dialogue input area and the intelligent dialogue display area, including: In response to a trigger instruction of the navigation control, the dialogue input area and the intelligent dialogue display area are displayed.
9. The method according to any one of claims 1 to 3, It is characterized in that The target page is a search result page, and the search result page displays a search input area; the method further includes: Detecting that the number of search question information input in the search input area reaches a number threshold, incrementally displaying entry prompt information for intelligent dialogue search on the search results page; In response to the triggering operation of the entry prompt information of the intelligent dialogue search, the intelligent dialogue search instruction is generated.
10. The method according to any one of claims 1 to 3, It is characterized in that The target page is a search result page, and the search result page displays a search input area, search results, and source indication information corresponding to the search results; the method further includes: In response to a triggering operation of the source indication information corresponding to the search result, a target multimedia resource from which the search result originates is displayed.
11. The method according to claim 10, It is characterized in that The search homepage includes search mode selection information, and the search mode selection information is used to indicate whether the search results are obtained by aggregating the searched multimedia resources; the method further includes: When search question information is input in the search input area of the search homepage and the search mode selection information is triggered to be processed through aggregation, the search input area, the search results and the source indication information corresponding to the search results are displayed on the search results page.
12. The method according to claim 11, It is characterized in that The step of inputting search question information in the search input area of the search homepage and displaying the search input area, the search results, and the source indication information corresponding to the search results on the search results page when the search mode selection information is triggered to be processed by aggregation includes: Enter search question information in the search input area of the search homepage, and display search result type selection information when the search mode selection information is triggered to be processed through aggregation; the search result type selection information includes at least one result display type of video, image or text; Based on the operation selected by the search result type selection information, the search results under the target result display type are displayed; the target result display type is any one of the result display types.
13. The method according to claim 12, It is characterized in that The search results are non-text search results; the method further includes: In response to dialog instruction information for converting the target result presentation type of the search result being input into the dialog input area, the search result is converted into a text search result.
14. The method according to claim 10, It is characterized in that The search question information and the dialogue question information may be one of text, voice and image information.
15. The method according to claim 1, It is characterized in that The display type of the dialogue response result is at least one of text, image, and video.
16. The method according to claim 11, It is characterized in that The method further comprises: In response to inputting search question information in a search input area of a search homepage or a search result page, extracting a target result display type from the search question information; The search results corresponding to the search question information are displayed on the search result page in the target result display type, and source indication information corresponding to the search results is displayed.
17. The method according to claim 1, It is characterized in that The method further comprises: In response to a tag generation instruction triggered in a multimedia resource publishing request, the dialogue input area and the intelligent dialogue display area are displayed, wherein the intelligent dialogue display area displays at least one tag information of the multimedia resource to be published replied by the search reply object.
18. The method according to claim 2, It is characterized in that When the dialogue response result is a video, the method further includes: When a pause operation is detected during the video playback process, text description information corresponding to the target progress in the video replied by the search reply object is displayed in the intelligent dialogue display area; the target progress is the playback progress corresponding to the pause of the video playback process.
19. An information search device, It is characterized in that include: A display module, configured to execute and display a target page of a multimedia social application; An intelligent dialogue module, configured to execute an intelligent dialogue search instruction in response to searching for a question object, and to display a dialogue input area and an intelligent dialogue display area; Among them, the dialogue input area is used to input dialogue question information of questions; the intelligent dialogue display area is used to display the identifier corresponding to the search question object and the dialogue question information, as well as the dialogue response result of the search reply object; wherein, the search reply object is an object that performs natural language processing based on artificial intelligence drive, and the dialogue response result is obtained by the search reply object through data aggregation processing of multimedia resources matching the dialogue question information in the multimedia social application.
20. An electronic device, It is characterized in that include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the information search method as claimed in any one of claims 1 to 18.
21. A computer-readable storage medium, It is characterized in that When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the information search method according to any one of claims 1 to 18.
Citation Information
Patent Citations
Search results integrated with interactive conversation service interface
CN110088751A
Search request processing method and device, computer equipment and storage medium
CN114372160A
Cited By
Conversation content display method based on user permission separation and related device
CN119357383A
Conversation content display method and related device based on user authority separation
CN119357383B
Online conversation and intelligent sales assistant working method, system and device
CN121255976A
