Question and answer search method and device and terminal equipment

Abstract

The invention provides a question and answer search method and device and terminal equipment. The method comprises the steps that question information is acquired; according to the question information, determining at least one search mode corresponding to the question information in a plurality of search modes; and processing the question information according to the at least one search mode to obtain answer information corresponding to the question information, and performing answer display according to the answer information. The accuracy of searched answers is improved, and the efficiency of searching answers is improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of data processing technology, and in particular to a question and answer search method, apparatus, and terminal device. Background Art

[0002] Search engines can provide users with answers to questions. For example, a user can enter a question in the search engine's input field, and the search engine can display the answer after obtaining the answer to the question.

[0003] At present, traditional search engines can process user input questions based on knowledge graphs or question-answer text extraction technology to obtain answers to the questions. However, with the development of multimedia technology, the Internet contains more image and video information, and the above methods cannot fully and accurately obtain answers to questions, resulting in low accuracy of search answers. Summary of the invention

[0004] The present disclosure provides a question-answer search method, apparatus, and terminal device, which are used to solve the technical problem of low accuracy of search answers in the prior art.

[0005] In a first aspect, the present disclosure provides a question-answer search method, the method comprising:

[0006] Get problem information;

[0007] According to the question information, determining at least one search method corresponding to the question information from multiple search methods;

[0008] The question information is processed according to the at least one search method to obtain answer information corresponding to the question information, and the answer is displayed according to the answer information.

[0009] In a second aspect, the present disclosure provides a question-answer search device, which includes an acquisition module, a determination module, a processing module, and a display module, wherein:

[0010] The acquisition module is used to obtain problem information;

[0011] The determination module is used to determine at least one search method corresponding to the question information from multiple search methods according to the question information;

[0012] The processing module is used to process the question information according to the at least one search method to obtain answer information corresponding to the question information;

[0013] The display module is used to display the answer according to the answer information.

[0014] In a third aspect, an embodiment of the present disclosure provides an electronic device including: a processor and a memory;

[0015] The memory stores computer-executable instructions;

[0016] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the question-and-answer search method as described in the first aspect and various aspects that may be involved in the first aspect.

[0017] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the question-and-answer search method as described in the first aspect and various possible aspects of the first aspect are implemented.

[0018] The present disclosure provides a question-answer search method, device, and terminal device. The terminal device can obtain question information, and according to the question information, determine at least one search method corresponding to the question information from a plurality of search methods. The terminal device can process the question information through at least one search method, obtain answer information corresponding to the question information, and display the answer according to the answer information. In the above method, since the terminal device can determine the search method that matches the question information, the terminal device can fully and accurately obtain the answer corresponding to the question based on the search method, thereby improving the reliability of the obtained answer. Moreover, since the search method matches the question, the terminal device can quickly obtain the answer corresponding to the question, thereby improving the accuracy of the searched answer and the efficiency of the searched answer. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0021] Figure 2 A flowchart of an answer search method provided by an embodiment of the present disclosure;

[0022] Figure 3 A schematic diagram of a process for obtaining problem information provided by an embodiment of the present disclosure;

[0023] Figure 4 A schematic diagram of a search method provided by an embodiment of the present disclosure;

[0024] Figure 5 A schematic diagram of determining a problem category provided by an embodiment of the present disclosure;

[0025] Fig. 6A A schematic diagram of displaying target display information provided by an embodiment of the present disclosure;

[0026] Figure 6B A schematic diagram of another display target display information provided by an embodiment of the present disclosure;

[0027] Figure 6C A schematic diagram of another display target display information provided by an embodiment of the present disclosure;

[0028] Figure 7 A schematic diagram of a method for determining answer information provided by an embodiment of the present disclosure;

[0029] Figure 8 A schematic diagram of a process for determining a sub-answer information group provided by an embodiment of the present disclosure;

[0030] Fig. 9 A process diagram of a question-answer search method provided by an embodiment of the present disclosure;

[0031] Fig.10 A schematic diagram of the structure of a question-answer search device provided in an embodiment of the present disclosure;

[0032] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. 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.

[0034] To facilitate understanding, the concepts involved in the embodiments of the present disclosure are explained below.

[0035] Terminal device: a device with wireless transceiver function. The terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted. The terminal device can be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a vehicle-mounted terminal device, a wireless terminal in self-driving, a wireless terminal device in remote medical, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in smart city, a wireless terminal device in smart home, a wearable terminal device, etc. The terminal device involved in the embodiments of the present disclosure can also be called a terminal, a user equipment (UE), an access terminal device, a vehicle-mounted terminal, an industrial control terminal, a UE unit, a UE station, a mobile station, a mobile station, a remote station, a remote terminal device, a mobile device, a UE terminal device, a wireless communication device, a UE agent or a UE device, etc. Terminal devices can also be fixed or mobile.

[0036] In the related art, a user can enter the question that the user wants to ask in the input bar of the search engine, and the search engine can identify the question and obtain the answer to the question in the database. After obtaining the answer, the search engine can display the answer to the user. At present, traditional search engines can obtain answers to questions input by users based on knowledge graphs or question-and-answer text extraction technology. For example, multiple knowledge graphs can be pre-stored in the database. After the search engine obtains the user's question, it can determine the answer associated with the question based on the knowledge graph. With the development of multimedia technology, the Internet can include more image information and video information, and image information and video information can also be displayed as answers. However, the search engine cannot accurately identify image information and video information based on the knowledge graph or question-and-answer text extraction technology, which makes it impossible for the search engine to accurately and fully obtain the answer to the question, which in turn leads to low accuracy of the search answer.

[0037] In order to solve the technical problems in the related art, the embodiment of the present disclosure provides a question-answer search method, wherein the terminal device can obtain question information, and perform semantic recognition processing on the question information to obtain target demand information of the question information, and the terminal device can determine at least one search method from multiple search methods according to the target demand information, and the terminal device can obtain sub-answer information corresponding to each search method to obtain at least one sub-answer information, wherein the sub-answer information is obtained by processing the question information through the search method, and the terminal device can determine the number of at least one sub-answer information, and determine the answer information corresponding to the question information according to the number of at least one sub-answer information and at least one sub-answer information, and display the answer according to the answer information. In the above method, since the terminal device can determine at least one search method that matches the question information, the terminal device can accurately and quickly obtain the answer to the question based on the search method, thereby improving the accuracy of the search answer and the efficiency of the search answer, and since the terminal device can determine the answer to the question based on the answer information obtained by each search method, the reliability of the search answer can be improved.

[0038] Next, combine Figure 1 , the application scenarios of the embodiments of the present disclosure are described in detail.

[0039] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present disclosure. Figure 1 , including a terminal device. The display page of the terminal device is a search engine page, and the search engine page may include a search bar. The user may enter a question in the search bar and click the search control, and the terminal device may determine at least one search method corresponding to the question and obtain an answer to the question based on the search method. Answer 1 may include text content, answer 2 may include an image, and answer 3 may include a video. In this way, the terminal device may obtain an answer to the question based on a search method that matches the question, thereby improving the accuracy and efficiency of obtaining the answer, and the terminal device may display the answer based on a multimodal method, thereby improving the display effect of the answer and improving the user experience.

[0040] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0041] Figure 2 A flowchart of an answer search method provided by an embodiment of the present disclosure. Figure 2 , the method may include:

[0042] S201. Obtain problem information.

[0043] The execution subject of the embodiment of the present disclosure may be a terminal device, or a question-and-answer search device provided in the terminal device. The question-and-answer search device may be implemented based on software, or may be implemented based on a combination of software and hardware, which is not limited in the embodiment of the present disclosure. Optionally, the terminal device may be any device with a display function, for example, a computer, a mobile phone, etc., which is not limited in the embodiment of the present disclosure.

[0044] The question information may be information related to the question input by the user. The terminal device may determine the question information based on the search content input by the user. For example, the search engine may include a question input field, the user may input text content in the question input field, and the terminal device may determine the text content as the question information.

[0045] Optionally, the question information in the embodiment of the present disclosure may be information that needs to be answered. For example, the question information may be information that can be answered, such as what is the highest peak in the world, what is the deepest trench in the world, who is the tallest person in the world, etc. For example, if the user only enters the name of a city in the input bar of the search engine, the city name is not question information. However, if the user enters not only the city name but also the text "What day was it established" in the input bar of the search engine, the terminal device may determine the text content in the search bar as question information.

[0046] Next, combine Figure 3 , the process of obtaining question information in the embodiment of the present disclosure is explained.

[0047] Figure 3 A schematic diagram of a process for obtaining problem information provided by an embodiment of the present disclosure. Figure 3 , including a terminal device. The display page of the terminal device may include a search application. When the user clicks the search application, the display page of the terminal device may jump to the search page corresponding to the search application. The search page may include a search bar. After the user enters the text "What is the highest peak in the world" into the search bar and clicks the search control, the terminal device may identify the text content entered by the user and obtain the question information. The question information may be: What is the highest peak in the world.

[0048] S202: Determine, based on the question information, at least one search method corresponding to the question information from among multiple search methods.

[0049] The search method may be a method for obtaining an answer corresponding to the question information. For example, the terminal device processes the question information based on the search method and may obtain an answer corresponding to the question information in the case of the search method.

[0050] Optionally, the search method may include at least one of the following: full-network resource mining, structured data query, generative artificial intelligence query, and professional database query.

[0051] Among them, the whole network resource mining can be a search method for the terminal device to obtain answers in the index resources of the whole network. For example, there are a lot of content in the index resources of the whole network, and the terminal device can understand and extract the content related to the question information based on this search method, and then obtain the answer to the question information.

[0052] The structured data query is used to query the answer to the question information with structured attributes. For example, if the question information is which scenic spots are included in the city, the question information has structured attributes (i.e., the attributes of the city), and the terminal device can obtain the answer to the question information based on the search method of the structured data query.

[0053] Among them, the generative artificial intelligence query is used to query the answer to the question information including low-frequency words. For example, if the question information includes a large number of low-frequency words (such as long-tail words, difficult-to-understand words, etc., which are not limited in the embodiments of the present disclosure), the terminal device can obtain the answer to the question information based on the generative artificial intelligence query method.

[0054] The professional database query is used to query the answers to questions including professional terms. For example, if the question information includes a large number of medical terms, the terminal device can obtain the answer to the question information based on the search method of the professional database query.

[0055] Next, combine Figure 4 , explain the search method.

[0056] Figure 4 A schematic diagram of a search method provided by an embodiment of the present disclosure. Figure 4 , including: search methods for full-network resource mining, search methods for structured data queries, search methods for generative artificial intelligence queries, and search methods for professional database queries. Among them, full-network resource mining can be searched based on video resource mining, graphic resource mining, and web resource mining. Structured data queries can be searched based on structured data mining, structured data access, and knowledge graph access. Generative artificial intelligence queries can be searched based on artificial intelligence answer extraction and artificial intelligence multi-conversation. Professional database queries can search text resources, graphic resources, and video resources.

[0057] Optionally, the terminal device may use a generative artificial intelligence query search method based on third-party access, and a generative artificial intelligence query device may also be provided in the terminal device, which is not limited in this regard in the embodiments of the present disclosure.

[0058] It should be noted that the text resources, graphic resources and video resources in the search method of professional database query can be pre-stored resources. For example, in actual application scenarios, it is difficult to find accurate answers to most professional questions. Therefore, the terminal device can pre-store answers corresponding to questions in multiple professional fields in the professional database, so that the terminal device can accurately answer professional questions.

[0059] It should be noted that the terminal device can obtain the professional database based on any feasible implementation method. For example, a user can report multiple professional-related questions. After the professional answers, the terminal device can obtain the answer to the professional question and store the answer in the professional database. Alternatively, after the user collects the answer to the professional question, it is stored in the professional database. The present disclosed embodiment is not limited to this.

[0060] It should be noted that the question information may correspond to one search method, or may correspond to multiple search methods, which is not limited in the embodiments of the present disclosure.

[0061] It should be noted that the search method may be a pre-set method, or may be based on any other feasible search method (eg, a search method accessed by a third party), which is not limited in the embodiments of the present disclosure.

[0062] Among them, the terminal device can determine at least one search method corresponding to the question information among multiple search methods based on the following feasible implementation methods: perform semantic recognition processing on the question information to obtain target demand information of the question information, and determine at least one search method among multiple search methods based on the target demand information.

[0063] The target demand information may indicate the user's demand for querying the problem information. For example, the target demand information may include the user's motivation for querying the problem information. For example, the target demand information may be querying the customer's knowledge, learning a method for solving a problem, obtaining information related to the problem information, etc., which is not limited in the embodiments of the present disclosure.

[0064] Optionally, the terminal device may process the question information based on the semantic recognition model to obtain the target demand information. For example, the terminal device may input the question information into the trained semantic recognition model, and the semantic recognition model may output the target demand information corresponding to the question information.

[0065] Optionally, the terminal device may process the question information based on a query algorithm to obtain target demand information. For example, the terminal device may process the question information based on a query algorithm (eg, a query analysis algorithm) to obtain target demand information of the question information.

[0066] It should be noted that the terminal device may also determine the target demand information of the question information based on any feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0067] Among them, the terminal device determines at least one search method from multiple search methods based on the target demand information, which can be specifically: determining at least one problem category corresponding to the problem information based on the target demand information, determining at least one search method corresponding to the at least one problem category, and determining the at least one search method corresponding to the at least one problem category as the search method corresponding to the problem information.

[0068] Among them, the question category may include at least one of the following: basic question type, structured question type, long-tail word question type, and professional question type.

[0069] The basic question type refers to a question whose difficulty level is relatively low. For example, if the target requirement information corresponding to the question information is to query objective knowledge, the difficulty level of the question corresponding to the question information is relatively low, and the question category of the question information can be a basic question type.

[0070] The structured question type may be a question whose text content in the question information includes structured attributes. For example, if the target demand information corresponding to the question information is to query objective knowledge, and the question information includes a city name, the question category of the question information may be a structured question type.

[0071] The long-tail word question type may be a question in which the text content in the question information includes a long-tail word. For example, if the target demand information corresponding to the question information is to obtain inspiration for writing, and the question information includes a long-tail word, the question category of the question information may be a long-tail word question type.

[0072] The professional question type may be a question whose text content in the question information includes professional terms. For example, if the target demand information corresponding to the question information is to learn a method for solving a problem, and the question information includes professional terms, the question category of the question information may be a professional question category.

[0073] Optionally, the terminal device may process the target demand information corresponding to the question information based on the question classification model, thereby obtaining at least one question category corresponding to the question information. For example, the question classification model may be a pre-trained model, and after receiving the target demand information, the question classification model may determine the category to which the target demand information belongs, thereby obtaining the question category corresponding to the question information.

[0074] Next, combine Figure 5 , explain the problem category corresponding to the determined problem information.

[0075] Figure 5 A schematic diagram of determining a problem category provided by an embodiment of the present disclosure. Figure 5 , including: problem information. Terminal equipment ( Figure 5 (not shown) can perform semantic recognition on the question information to obtain the target demand information of the question information. The terminal device can input the target demand information into the question classification model, and the question classification model can output the probability that the question information belongs to each question type. Among them, the probability that the question information belongs to the basic question type is 1, the probability that the question information belongs to the structured question type is 1, the probability that the question information belongs to the long-tail word question type is 0, and the probability that the question information belongs to the professional question type is 0. Therefore, the question types corresponding to the question information include basic question types and structured question types.

[0076] Among them, the question categories correspond to the search methods one by one, and the terminal device can determine at least one search method corresponding to at least one question category corresponding to the question information based on the correspondence between the question categories and the search methods. For example, each question category has a corresponding search method, among which the basic question category can correspond to the search method of full network resource mining, the structured question type can correspond to the search method of structured data query, the long-tail word question type can correspond to the search method of generative artificial intelligence query, and the professional question type can correspond to the search method of professional database query.

[0077] Optionally, the terminal device may determine at least one search method corresponding to at least one question category as the search method corresponding to the question information. For example, if the question categories corresponding to the question information are basic question types and structured question types, the search method corresponding to the basic question types is a method of mining resources across the entire network, and the search method corresponding to the structured question types is a method of querying structured data, therefore, the terminal device may determine that the search method corresponding to the question information may include a search method of mining resources across the entire network and a search method of querying structured data.

[0078] For example, for basic questions, the terminal device can query based on more index resources on the entire network; for questions related to the attributes or relationships of physical forms such as names of people, places, books, and movies (structured question types), the terminal device can query more information based on the pre-processed structured database; for professional questions or questions that require higher user answers, the terminal device can obtain answers based on preset professional databases; if difficult-to-understand words or long-tail words appear, the terminal device can further clarify the specific questions queried by the user based on the multi-round conversation capabilities of artificial intelligence, and then obtain answers to the questions.

[0079] In this way, for different types of questions, the terminal device can determine the search method corresponding to the question, thereby improving the accuracy of the answer to the search question.

[0080] S203: Process the question information according to at least one search method to obtain answer information corresponding to the question information.

[0081] Optionally, the terminal device may process the question information according to at least one search method to obtain answer information corresponding to the question information. For example, if the question information corresponds to a search method of full-network resource mining and structured data query, the terminal device may process the question information based on a full-network resource mining method to obtain answer 1 corresponding to the question information. The terminal device may process the question information based on a search method of structured data query to obtain answer 2 corresponding to the question information. The terminal device may obtain answer information corresponding to the question information based on answer 1 and answer 2.

[0082] S204. Display the answer according to the answer information.

[0083] Among them, the terminal device displays the answer according to the answer information, which can be specifically: extracting at least one information to be displayed from the answer information, determining the target display information corresponding to each information to be displayed, obtaining at least one target display information, and displaying at least one target display information.

[0084] The display information may include text, video and image. For example, after the terminal device processes the question information based on at least one search method, the answer information obtained may include text, video and image, and the terminal device may extract the text, video and image from the answer information to obtain the display information.

[0085] Optionally, the terminal device may extract text, video and images from the answer information based on any feasible implementation method, which is not limited in the embodiments of the present disclosure.

[0086] Optionally, for any information to be displayed, the terminal device determines the target display information corresponding to the information to be displayed, and there are the following three situations:

[0087] Case 1: The information to be displayed is text.

[0088] If the information to be displayed is text, the terminal device may determine that the target display information is text. For example, if the information to be displayed extracted by the terminal device includes text but does not include images and videos, the terminal device may determine that the target display information is text.

[0089] Case 2: The information to be displayed is a video.

[0090] If the information to be displayed is a video, the terminal device can determine the key description information corresponding to the video, or determine at least one key frame in the video, and determine that the target display information includes the video and the key description information, or determine that the target display information includes the video and at least one key frame.

[0091] The key description information may be text content describing the video. For example, the key description information may be a title of the video, subtitles in the video, etc., which is not limited in the embodiments of the present disclosure.

[0092] For example, if the key description information is the title of a video, the terminal device can obtain the title of the video when acquiring the video.

[0093] For example, if the key description information is the subtitles in a video, after the terminal device obtains the video, it can identify the video frames in the video to obtain the subtitles of each video frame. The terminal device can obtain the key description information based on multiple phrases with higher frequencies in multiple video frames. The terminal device can also process the subtitles of multiple video frames based on any other feasible implementation method to obtain the key description information. The embodiments of the present disclosure are not limited to this.

[0094] The key frame is associated with the answer corresponding to the question information. For example, the key frame may be the starting video frame of the answer information corresponding to the question information. For example, if the video answers the question information starting from the 100th frame in the video, the terminal device may determine the 100th frame of the video as the key frame; for example, if the 200th to 2000th frames in the video are the video's answers to the question information, the terminal device may determine the 200th frame of the video as the key frame.

[0095] Optionally, the terminal device can process the video based on the image-to-text model to obtain key frames in the video. For example, the terminal device can understand the key frames in the video based on the image-to-text model to obtain the image content corresponding to each key frame. The terminal device can determine the answer corresponding to the question information based on the image content corresponding to each image frame, and determine the key frames in the video. For example, if the question information is how to make scrambled eggs with tomatoes, and the searched information to be displayed includes a video, the terminal device processes each video frame in the video based on the image-to-text model to obtain the text content corresponding to each video frame. If the text content corresponding to the 100th frame is "tomatoes and eggs", the terminal device can determine that the 100th frame is a key frame of the video.

[0096] Optionally, the terminal device can obtain the key frame in the video based on the subtitles of each video frame in the video. For example, if the question information is how to make scrambled eggs with tomatoes, and the searched information to be displayed includes a video, the terminal device can obtain the subtitles in each video frame (the terminal device can be based on any feasible implementation method, which is not limited in the embodiments of the present disclosure), and obtain the subtitles corresponding to each video frame. If the subtitle corresponding to the 300th frame is "First prepare 1 tomato and 2 eggs", the terminal device can determine that the 1300th frame is the key frame of the video.

[0097] It should be noted that the terminal device can determine the key frames of the video based on any feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0098] Case 3: The information to be displayed is an image.

[0099] If the information to be displayed is an image, the terminal device may determine that the target display information is an image, or determine that the target display information includes an image and image description information of the image. For example, if the display information is an image, the terminal device may determine that the target display information is an image and text describing the image content (image description information).

[0100] Optionally, the terminal device may determine the image description information of the image based on any feasible implementation method, which is not limited in the embodiments of the present disclosure.

[0101] Next, combine Figure 6A-6C , describing a scenario in which a terminal device displays at least one target display information.

[0102] Fig. 6A A schematic diagram of displaying target display information provided by an embodiment of the present disclosure. Fig. 6A, including a terminal device. The display page of the terminal device is a search page. The search page may include a search bar. After the user enters a question in the search bar, the terminal device may obtain information to be displayed for the question, wherein, since the information to be displayed is text, the terminal device determines that the target display information is text, and the answer displayed by the terminal device is text content.

[0103] Figure 6B This is a schematic diagram of another embodiment of the present disclosure providing information on displaying a target. Figure 6B , including a terminal device. The display page of the terminal device is a search page. The search page may include a search bar. After the user enters a question in the search bar, the terminal device may obtain the information to be displayed for the question, wherein, since the information to be displayed is an image, the terminal device may determine the image description information corresponding to the image, and determine that the target display information is the image and the image description information, and the answer displayed by the terminal device includes the image and the image description information of the image.

[0104] Figure 6C This is a schematic diagram of another embodiment of the present disclosure providing information on displaying a target. Figure 6C , including a terminal device. The display page of the terminal device is a search page. The search page may include a search bar. After the user enters a question in the search bar, the terminal device can obtain the information to be displayed for the question, wherein, since the information to be displayed is a video, the terminal device can determine the key frame corresponding to the video (the key frame is the 8th second of the video), and determine that the target display information is the video and the key frame, and the answer displayed by the terminal device includes the video and the key frame of the video. When the user clicks the key frame: the 8th second, the terminal device can play the 8th second of the video.

[0105] It should be noted that the answer displayed by the terminal device may include multiple texts, multiple images and multiple videos, and the video may also include multiple key frames, which is not limited in the embodiments of the present disclosure.

[0106] In this way, the terminal device can display the answer corresponding to the question information based on multimodality, and thus can provide a display effect of the answer.

[0107] The disclosed embodiment provides a question-answer search method, wherein a terminal device can obtain question information, and perform semantic recognition processing on the question information to obtain target demand information of the question information. The terminal device can determine at least one search method from a plurality of search methods according to the target demand information, and process the question information according to at least one search method to obtain answer information corresponding to the question information. The terminal device can extract at least one information to be displayed from the answer information, determine the target display information corresponding to each information to be displayed, obtain at least one target display information, and display at least one target display information. In this way, since the terminal device can determine at least one search method that matches the question information, the terminal device can accurately and quickly obtain the answer to the question based on the search method, thereby improving the accuracy of the search answer and the efficiency of the search answer. Moreover, since the terminal device can determine the answer to the question based on the answer information obtained by each search method, the reliability of the search answer can be improved.

[0108] exist Figure 2 Based on the embodiment shown below, combined with Figure 7 , a method for processing question information according to at least one search method in the above-mentioned question and answer search method to obtain answer information corresponding to the question information is described in detail.

[0109] Figure 7 A schematic diagram of a method for determining answer information provided by an embodiment of the present disclosure. Figure 7 The method flow includes:

[0110] S701. Obtain sub-answer information corresponding to each search method to obtain at least one sub-answer information.

[0111] Among them, the sub-answer information is obtained by processing the question information through a search method. For example, if the terminal device determines that the search method corresponding to the question information is full-network resource mining, the terminal device can process the question information based on the full-network resource mining method, and then obtain the sub-answer information corresponding to the question information. For example, if the terminal device determines that the search method corresponding to the question information is full-network resource mining and structured data query, the terminal device can process the question information based on the full-network resource mining method to obtain sub-answer information 1, and the terminal device can process the question information based on the structured data query method to obtain sub-answer information 2.

[0112] It should be noted that the terminal device can process the question information by searching in any feasible implementation manner to obtain sub-answer information, and the embodiments of the present disclosure are not limited to this.

[0113] S702: Determine the quantity of at least one sub-answer information.

[0114] It should be noted that a search method can also obtain multiple sub-answer information. For example, if the search method corresponding to the question information is full-network resource mining, the terminal device processes the question information based on the full-network resource mining method, and can obtain one sub-answer information or multiple sub-answer information, which is not limited in the embodiments of the present disclosure.

[0115] Optionally, the terminal device may determine the quantity of at least one sub-answer information based on any feasible implementation manner, which is not limited in the embodiments of the present disclosure.

[0116] S703: Determine answer information corresponding to the question information according to the number of at least one sub-answer information and at least one sub-answer information.

[0117] The terminal device determines the answer information corresponding to the question information according to the number of at least one sub-answer information and at least one sub-answer information, and there are two cases as follows:

[0118] Case 1: The number of sub-answer information is 1.

[0119] If the number of at least one sub-answer information is 1, the terminal device can determine the sub-answer information as the answer information. For example, if the terminal device only obtains 1 sub-answer information after processing the question information based on the search method, the terminal device can determine the sub-answer information as the answer information corresponding to the question information.

[0120] Case 2: The number of sub-answer information is greater than 1.

[0121] If the number of at least one sub-answer information is greater than 1, the terminal device can determine the similarity between the multiple sub-answer information, and determine the answer information based on the similarity between the multiple sub-answer information. For example, if the terminal device processes the question information based on multiple search methods and obtains multiple sub-answer information, the terminal device can summarize and conclude the multiple sub-answer information, and then obtain the answer information corresponding to the question information.

[0122] Optionally, the terminal device can determine the similarity between multiple sub-answers based on a similarity algorithm. For example, if the sub-answer information includes text, the terminal device can calculate the text similarity between the sub-answer information, and then obtain the similarity between the sub-answers; if the sub-answer information includes images, the terminal device can calculate the image similarity between the sub-answers, and then obtain the similarity between the sub-answers; if the sub-answer information includes videos, the terminal device can determine the similarity between the videos (the similarity between the sub-answers) based on the similarity between the titles of the videos. The terminal device can also determine the similarity between the videos based on any other feasible implementation method, which is not limited in the embodiments of the present disclosure.

[0123] It should be noted that in this case, before the terminal device determines the similarity between the sub-answers, it can determine the type of the sub-answer information. The sub-answer information of the same type has similarity, and the similarity between sub-answer information of different types is 0. For example, if the terminal device determines that the sub-answer information corresponding to the question information includes text, image, and video, the terminal device can calculate the similarity between texts, the similarity between images, and the similarity between videos, respectively, where the similarity between text and image is 0, the similarity between text and video is 0, and the similarity between image and video is also 0.

[0124] Optionally, the terminal device determines the answer information based on the similarity between at least one sub-answer information. Specifically, it can be: grouping at least one sub-answer information according to the similarity between at least one sub-answer information to obtain at least one sub-answer information group, determining the target sub-answer information corresponding to each sub-answer information group, and determining that multiple answer information includes the target sub-answer information corresponding to each sub-answer information group.

[0125] The similarity between each sub-answer information in the sub-answer information group is greater than or equal to a preset similarity. For example, the sub-answer information is text 1, text 2, image, and video, and the similarity between text 1 and text 2 is greater than a preset threshold. Then the terminal device can determine three sub-answer information groups, wherein the first sub-answer information group includes text 1 and text 2, the second sub-answer information group includes an image, and the third sub-answer information group includes a video.

[0126] Next, combine Figure 8 , the process of determining the sub-answer information group is explained.

[0127] Figure 8 A schematic diagram of a process for determining a sub-answer information group provided by an embodiment of the present disclosure. Figure 8 , including sub-answer 1, sub-answer 2, sub-answer 3 and sub-answer 4. Among them, sub-answer 1 includes the text "The world's first peak is Mount Everest", sub-answer 2 includes the text "Mount Everest is the highest of all mountains", sub-answer 3 includes an image of Mount Everest, and sub-answer 4 includes a video introducing famous mountains in the world.

[0128] See also Figure 8 , terminal equipment ( Figure 8 (not shown) It can be determined that the text similarity between sub-answer 1 and sub-answer 2 is greater than a preset threshold. Since sub-answer 3 is an image and sub-answer 4 is a video, the similarity between sub-answer 3 and sub-answer 1, sub-answer 2, and sub-answer 3 is less than the preset threshold, and the similarity between sub-answer 4 and sub-answer 1 and sub-answer 2 is less than the preset threshold.

[0129] See also Figure 8 , the terminal device can obtain sub-answer group A, sub-answer group B and sub-answer group C based on the similarity between the sub-answers. Among them, sub-answer group A includes sub-answer 1 and sub-answer 2, sub-answer group B includes sub-answer 3 (an image of Mount Everest), and sub-answer group C includes sub-answer 4 (a video introducing famous mountains in the world). In this way, the terminal device can accurately group the sub-answer information based on the similarity between the sub-answer information, thereby improving the diversity of the answer information and the accuracy of the answer.

[0130] Optionally, the target sub-answer information may be the answer extracted by the terminal device from the sub-answer information group. For example, if the sub-answer information group includes multiple texts, the terminal device may summarize, conclude and integrate the multiple texts, and then obtain the target sub-answer information corresponding to the sub-answer information group, so that repeated display between answers can be avoided and the display effect of the answer can be improved. For example, if the sub-answer information group includes multiple images, the terminal device may filter the multiple images (at least one image may be selected arbitrarily, or it may be determined based on information such as image resolution, which is not limited in the disclosed embodiment) to obtain the target sub-answer information corresponding to the sub-answer information group. For example, if the sub-answer information group includes multiple videos, the terminal device may filter the multiple videos (at least one video may be selected arbitrarily, or it may be determined based on information such as video clarity, frame rate, etc., which is not limited in the disclosed embodiment) to obtain the target sub-answer information corresponding to the sub-answer information group.

[0131] Optionally, the terminal device may determine that the answer information corresponding to the question information includes the target sub-answer information corresponding to each sub-answer information group. For example, if the target sub-answer information of sub-answer information group A is text, the target sub-answer information of sub-answer information group B is an image, and the target sub-answer information of sub-answer information group C is a video, then the terminal device may determine that the answer information corresponding to the question information includes text, images, and videos.

[0132] The disclosed embodiment provides a method for determining answer information, obtaining sub-answer information corresponding to each search method, obtaining at least one sub-answer information, determining the number of at least one sub-answer information, if the number of at least one sub-answer information is 1, the terminal device can determine the sub-answer information as answer information, if the number of at least one sub-answer information is greater than 1, the terminal device can determine the similarity between multiple sub-answer information, and determine the answer information based on the similarity between multiple sub-answer information. In this way, the terminal device can summarize and conclude the answers obtained by multiple search methods, improve the diversity of answers, and improve the accuracy of answers.

[0133] Based on any of the above embodiments, Fig. 9, the process of the above question-answer search method is explained in detail.

[0134] Fig. 9 A process diagram of a question-answer search method provided by an embodiment of the present disclosure. Fig. 9 , including a terminal device. The display page of the terminal device is a search page, and the search page includes a search bar and a search control. The user enters the question information "Is Mount Everest the highest peak?" in the search bar and clicks the search control. The terminal device can determine that the search method corresponding to the question information is a method of mining resources across the entire network and a method of querying structured data.

[0135] See also Fig. 9 The terminal device processes the question information based on the whole network resource mining method, and obtains sub-answer 1 and sub-answer 3. Among them, sub-answer 1 is the text "The world's first peak is Mount Everest", and sub-answer 3 is the image of Mount Everest. The terminal device processes the question information based on the structured data query method, and obtains sub-answer 2 and sub-answer 4. Among them, sub-answer 2 is the text "Mount Everest is the highest peak of all mountains", and sub-answer 4 is a video introducing the world's famous mountains.

[0136] See also Fig. 9 , the terminal device divides sub-answer 1, sub-answer 2, sub-answer 3 and sub-answer 4 into sub-answer group A, sub-answer group B and sub-answer group C based on the similarities between sub-answer 1, sub-answer 2, sub-answer 3 and sub-answer 4. Among them, sub-answer sub-A includes sub-answer 1 and sub-answer 2, sub-answer group B includes sub-answer 3, and sub-answer sub-C includes sub-answer 4.

[0137] See also Fig. 9 , the terminal device can determine that the target sub-answer information corresponding to sub-answer group A is the text "Mount Everest is the highest peak". The terminal device can determine that the target sub-answer information corresponding to sub-answer group B is an image of Mount Everest. The terminal device can determine that the target sub-answer information corresponding to sub-answer group C is a video introducing famous mountains in the world.

[0138] See also Fig. 9 , the terminal device can display the answers on the display page, where answer 1 is the text "Mount Everest is the highest peak", answer 2 is an image of Mount Everest, and answer 3 is a video introducing the world's famous mountains and key frame: the 5th second (i.e., the introduction of Mount Everest begins at the 5th second). When the user clicks the key frame: the 5th second, the terminal device can play the 5th second of the video introducing the world's famous mountains.

[0139] In this way, since the terminal device can determine at least one search method that matches the question information, the terminal device can accurately and quickly obtain the answer to the question based on the search method, thereby improving the accuracy of the search answer and the efficiency of the search answer. Moreover, since the terminal device can comprehensively obtain the answer corresponding to the question information based on the answer information obtained by each search method, the reliability of the search answer can be improved.

[0140] Fig.10 This is a schematic diagram of the structure of a question-answer search device provided by an embodiment of the present disclosure. Fig.10 The question-answer search device 100 includes an acquisition module 101, a determination module 102, a processing module 103 and a display module 104, wherein:

[0141] The acquisition module 101 is used to acquire problem information;

[0142] The determination module 102 is used to determine at least one search method corresponding to the question information from multiple search methods according to the question information;

[0143] The processing module 103 is used to process the question information according to the at least one search method to obtain answer information corresponding to the question information;

[0144] The display module 104 is used to display the answer according to the answer information.

[0145] According to one or more embodiments of the present disclosure, the determining module 102 is specifically configured to:

[0146] Performing semantic recognition processing on the question information to obtain target demand information of the question information;

[0147] According to the target demand information, at least one search method is determined from the multiple search methods.

[0148] According to one or more embodiments of the present disclosure, the determining module 102 is specifically configured to:

[0149] Determining at least one problem category corresponding to the problem information according to the target demand information;

[0150] Determine at least one search method corresponding to the at least one question category, wherein the question categories correspond to the search methods one by one;

[0151] At least one search method corresponding to the at least one question category is determined as the search method corresponding to the question information.

[0152] According to one or more embodiments of the present disclosure, the processing module 103 is specifically used to:

[0153] Obtaining sub-answer information corresponding to each search method, obtaining at least one sub-answer information, wherein the sub-answer information is obtained by processing the question information through the search method;

[0154] determining the quantity of the at least one sub-answer information;

[0155] Answer information corresponding to the question information is determined according to the number of the at least one sub-answer information and the at least one sub-answer information.

[0156] According to one or more embodiments of the present disclosure, the processing module 103 is specifically used to:

[0157] If the number of the at least one sub-answer information is 1, determining the sub-answer information as the answer information;

[0158] If the number of the at least one sub-answer information is greater than 1, the similarities between the multiple sub-answer information are determined, and the answer information is determined based on the similarities between the multiple sub-answer information.

[0159] According to one or more embodiments of the present disclosure, the processing module 103 is specifically used to:

[0160] According to the similarity between the at least one sub-answer information, the at least one sub-answer information is grouped to obtain at least one sub-answer information group, wherein the similarity between each sub-answer information in the sub-answer information group is greater than or equal to a preset similarity;

[0161] Determine the target sub-answer information corresponding to each sub-answer information group;

[0162] Determine that the plurality of answer information includes target sub-answer information corresponding to each sub-answer information group.

[0163] According to one or more embodiments of the present disclosure, the display module 104 is specifically used for:

[0164] Extracting at least one piece of information to be displayed from the answer information, wherein the information to be displayed includes: text, video and image;

[0165] Determine the target display information corresponding to each piece of information to be displayed, and obtain at least one target display information;

[0166] The at least one target display information is displayed.

[0167] According to one or more embodiments of the present disclosure, the display module 104 is specifically used for:

[0168] If the information to be displayed is the text, determining that the target display information is the text;

[0169] If the information to be displayed is the video, determining key description information corresponding to the video or determining at least one key frame in the video, and determining that the target display information includes the video and the key description information, or determining that the target display information includes the video and the at least one key frame;

[0170] If the information to be displayed is the image, it is determined that the target display information is the image, or it is determined that the target display information includes the image and image description information of the image.

[0171] The question and answer search device provided in the embodiment of the present disclosure can be used to execute the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0172] Fig.11 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Fig.11 , which shows a schematic diagram of the structure of an electronic device 1100 suitable for implementing the embodiment of the present disclosure. The electronic device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.11 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0173] like Fig.11 As shown, the electronic device 1100 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage device 1108 to a random access memory (RAM) 1103. Various programs and data required for the operation of the electronic device 1100 are also stored in the RAM 1103. The processing device 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0174] Typically, the following devices may be connected to the I / O interface 1105: input devices 1106 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 1107 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1108 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1109. The communication devices 1109 may allow the electronic device 1100 to communicate with other devices wirelessly or by wire to exchange data. Although Fig.11 The electronic device 1100 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0175] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 1109, or installed from a storage device 1108, or installed from a ROM 1102. When the computer program is executed by the processing device 1101, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0176] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0177] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0178] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0179] An embodiment of the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the question-and-answer search processing method that may be involved in various embodiments as described above is implemented.

[0180] An embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the question-and-answer search method that may be involved in various embodiments as described above.

[0181] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0182] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0183] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0184] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0185] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0186] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0187] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0188] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0189] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server or storage medium that performs the operation of the technical solution of the present disclosure based on the prompt message. As an optional but non-limiting implementation method, in response to receiving an active request from a user, the method of sending a prompt message to the user can be, for example, a pop-up window, and the prompt message can be presented in text in the pop-up window. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0190] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0191] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of the relevant laws and regulations. The data may include information, parameters and messages, such as flow switching indication information.

[0192] In a first aspect, according to one or more aspects of the present disclosure, the present disclosure includes a question-answer search method, the method comprising:

[0193] According to one or more embodiments of the present disclosure, determining at least one search method corresponding to the question information from multiple search methods according to the question information includes:

[0194] Performing semantic recognition processing on the question information to obtain target demand information of the question information;

[0195] According to the target demand information, at least one search method is determined from the multiple search methods.

[0196] According to one or more embodiments of the present disclosure, determining the at least one search method from the multiple search methods according to the target demand information includes:

[0197] Determining at least one problem category corresponding to the problem information according to the target demand information;

[0198] Determine at least one search method corresponding to the at least one question category, wherein the question categories correspond to the search methods one by one;

[0199] At least one search method corresponding to the at least one question category is determined as the search method corresponding to the question information.

[0200] According to one or more embodiments of the present disclosure, the processing of the question information according to the at least one search method to obtain answer information corresponding to the question information includes:

[0201] Obtaining sub-answer information corresponding to each search method, obtaining at least one sub-answer information, wherein the sub-answer information is obtained by processing the question information through the search method;

[0202] determining the quantity of the at least one sub-answer information;

[0203] Answer information corresponding to the question information is determined according to the number of the at least one sub-answer information and the at least one sub-answer information.

[0204] According to one or more embodiments of the present disclosure, determining answer information corresponding to the question information according to the number of the at least one sub-answer information and the at least one sub-answer information includes:

[0205] If the number of the at least one sub-answer information is 1, determining the sub-answer information as the answer information;

[0206] If the number of the at least one sub-answer information is greater than 1, the similarities between the multiple sub-answer information are determined, and the answer information is determined based on the similarities between the multiple sub-answer information.

[0207] According to one or more embodiments of the present disclosure, determining the answer information according to the similarity between the at least one sub-answer information includes:

[0208] According to the similarity between the at least one sub-answer information, the at least one sub-answer information is grouped to obtain at least one sub-answer information group, wherein the similarity between each sub-answer information in the sub-answer information group is greater than or equal to a preset similarity;

[0209] Determine the target sub-answer information corresponding to each sub-answer information group;

[0210] Determine that the plurality of answer information includes target sub-answer information corresponding to each sub-answer information group.

[0211] According to one or more embodiments of the present disclosure, displaying the answer according to the answer information includes:

[0212] Extracting at least one piece of information to be displayed from the answer information, wherein the information to be displayed includes: text, video and image;

[0213] Determine the target display information corresponding to each piece of information to be displayed, and obtain at least one target display information;

[0214] The at least one target display information is displayed.

[0215] According to one or more embodiments of the present disclosure, for any information to be displayed, determining target display information corresponding to the information to be displayed includes:

[0216] If the information to be displayed is the text, determining that the target display information is the text;

[0217] If the information to be displayed is the video, determining key description information corresponding to the video or determining at least one key frame in the video, and determining that the target display information includes the video and the key description information, or determining that the target display information includes the video and the at least one key frame;

[0218] If the information to be displayed is the image, it is determined that the target display information is the image, or it is determined that the target display information includes the image and image description information of the image.

[0219] In a second aspect, according to one or more embodiments of the present disclosure, the present disclosure includes a question-answer search device, the question-answer search device including an acquisition module, a determination module, a processing module, and a display module, wherein:

[0220] The acquisition module is used to obtain problem information;

[0221] The determination module is used to determine at least one search method corresponding to the question information from multiple search methods according to the question information;

[0222] The processing module is used to process the question information according to the at least one search method to obtain answer information corresponding to the question information;

[0223] The display module is used to display the answer according to the answer information.

[0224] According to one or more embodiments of the present disclosure, the determination module is specifically used to:

[0225] Performing semantic recognition processing on the question information to obtain target demand information of the question information;

[0226] According to the target demand information, at least one search method is determined from the multiple search methods.

[0227] According to one or more embodiments of the present disclosure, the determination module is specifically used to:

[0228] Determining at least one problem category corresponding to the problem information according to the target demand information;

[0229] Determine at least one search method corresponding to the at least one question category, wherein the question categories correspond to the search methods one by one;

[0230] At least one search method corresponding to the at least one question category is determined as the search method corresponding to the question information.

[0231] According to one or more embodiments of the present disclosure, the processing module is specifically used for:

[0232] Obtaining sub-answer information corresponding to each search method, obtaining at least one sub-answer information, wherein the sub-answer information is obtained by processing the question information through the search method;

[0233] determining the quantity of the at least one sub-answer information;

[0234] Answer information corresponding to the question information is determined according to the number of the at least one sub-answer information and the at least one sub-answer information.

[0235] According to one or more embodiments of the present disclosure, the processing module is specifically used for:

[0236] If the number of the at least one sub-answer information is 1, determining the sub-answer information as the answer information;

[0237] If the number of the at least one sub-answer information is greater than 1, the similarities between the multiple sub-answer information are determined, and the answer information is determined based on the similarities between the multiple sub-answer information.

[0238] According to one or more embodiments of the present disclosure, the processing module is specifically used for:

[0239] According to the similarity between the at least one sub-answer information, the at least one sub-answer information is grouped to obtain at least one sub-answer information group, wherein the similarity between each sub-answer information in the sub-answer information group is greater than or equal to a preset similarity;

[0240] Determine the target sub-answer information corresponding to each sub-answer information group;

[0241] Determine that the plurality of answer information includes target sub-answer information corresponding to each sub-answer information group.

[0242] According to one or more embodiments of the present disclosure, the display module is specifically used for:

[0243] Extracting at least one piece of information to be displayed from the answer information, wherein the information to be displayed includes: text, video and image;

[0244] Determine the target display information corresponding to each piece of information to be displayed, and obtain at least one target display information;

[0245] The at least one target display information is displayed.

[0246] According to one or more embodiments of the present disclosure, the display module is specifically used for:

[0247] If the information to be displayed is the text, determining that the target display information is the text;

[0248] If the information to be displayed is the video, determining key description information corresponding to the video or determining at least one key frame in the video, and determining that the target display information includes the video and the key description information, or determining that the target display information includes the video and the at least one key frame;

[0249] If the information to be displayed is the image, it is determined that the target display information is the image, or it is determined that the target display information includes the image and image description information of the image.

[0250] In a third aspect, an embodiment of the present disclosure provides an electronic device including: a processor and a memory;

[0251] The memory stores computer-executable instructions;

[0252] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the first aspect as described above and various methods that may be involved in the first aspect.

[0253] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the first aspect and various possible methods involved in the first aspect are implemented.

[0254] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0255] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0256] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A question-answer search method, characterized in that: include: Get problem information; According to the question information, determining at least one search method corresponding to the question information from multiple search methods; The question information is processed according to the at least one search method to obtain answer information corresponding to the question information, and the answer is displayed according to the answer information.

2. The method according to claim 1, characterized in that: The step of determining, according to the question information, at least one search method corresponding to the question information from among multiple search methods includes: Performing semantic recognition processing on the question information to obtain target demand information of the question information; According to the target demand information, the at least one search method is determined from the multiple search methods.

3. The method according to claim 2, characterized in that Determining the at least one search method from the multiple search methods according to the target demand information includes: Determining at least one problem category corresponding to the problem information according to the target demand information; Determine at least one search method corresponding to the at least one question category, wherein the question categories correspond to the search methods one by one; At least one search method corresponding to the at least one question category is determined as the search method corresponding to the question information.

4. The method according to any one of claims 1 to 3, characterized in that: The processing of the question information according to the at least one search method to obtain answer information corresponding to the question information includes: Obtaining sub-answer information corresponding to each search method, obtaining at least one sub-answer information, wherein the sub-answer information is obtained by processing the question information through the search method; determining the quantity of the at least one sub-answer information; Answer information corresponding to the question information is determined according to the number of the at least one sub-answer information and the at least one sub-answer information.

5. The method according to claim 4, characterized in that Determining answer information corresponding to the question information according to the number of the at least one sub-answer information and the at least one sub-answer information includes: If the number of the at least one sub-answer information is 1, determining the sub-answer information as the answer information; If the number of the at least one sub-answer information is greater than 1, the similarities between the multiple sub-answer information are determined, and the answer information is determined based on the similarities between the multiple sub-answer information.

6. The method according to claim 5, characterized in that The determining the answer information according to the similarity between the at least one sub-answer information includes: According to the similarity between the at least one sub-answer information, the at least one sub-answer information is grouped to obtain at least one sub-answer information group, wherein the similarity between each sub-answer information in the sub-answer information group is greater than or equal to a preset similarity; Determine the target sub-answer information corresponding to each sub-answer information group; Determine that the plurality of answer information includes target sub-answer information corresponding to each sub-answer information group.

7. The method according to any one of claims 1 to 6, characterized in that: The displaying of answers according to the answer information includes: Extracting at least one piece of information to be displayed from the answer information, wherein the information to be displayed includes: text, video and image; Determine the target display information corresponding to each piece of information to be displayed, and obtain at least one target display information; The at least one target display information is displayed.

8. The method according to claim 7, characterized in that For any information to be displayed, the step of determining target display information corresponding to the information to be displayed includes: If the information to be displayed is the text, determining that the target display information is the text; If the information to be displayed is the video, determining key description information corresponding to the video or determining at least one key frame in the video, and determining that the target display information includes the video and the key description information, or determining that the target display information includes the video and the at least one key frame; If the information to be displayed is the image, it is determined that the target display information is the image, or it is determined that the target display information includes the image and image description information of the image.

9. A question-answer search device, characterized in that: It includes an acquisition module, a determination module, a processing module and a display module, among which: The acquisition module is used to obtain problem information; The determination module is used to determine at least one search method corresponding to the question information from multiple search methods according to the question information; The processing module is used to process the question information according to the at least one search method to obtain answer information corresponding to the question information; The display module is used to display the answer according to the answer information.

10. An electronic device, characterized in that: include: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the question-and-answer search method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the processor executes the computer-executable instructions, the question-and-answer search method according to any one of claims 1 to 8 is implemented.

Images