Question and answer display method and device, vehicle, storage medium and program product

Abstract

The invention discloses a question and answer display method and device, a vehicle, a storage medium and a program product. The method comprises the following steps: in response to a received to-be-answered question, determining classification information and a question and answer template type based on the to-be-answered question, and generating answer content according to the classification information and the question and answer template type; outputting answer content for the to-be-answered question; the problem of unreasonable answer display in the question answering process is solved, the classification information and the question answering template type are determined through the to-be-answered question, and the corresponding answer content is generated based on the classification information and the question answering template type, so that the to-be-answered question of the user can be accurately answered and reasonably displayed, and the user experience is improved. And then the answer content for the to-be-answered question is output, the answer content generated based on the classification information and the question and answer template type better conforms to the user requirement and the reading habit of the user, reasonable question and answer display can be achieved, and the user experience is improved.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a question-and-answer display method, apparatus, vehicle, storage medium, and program product. Background Technology

[0002] With the development of technology, smart cars have gradually become a part of our lives. Users can obtain answers by interacting with the smart devices in the vehicle through question-and-answer sessions; for example, the vehicle's infotainment system can provide corresponding answers to users' questions, thereby providing intelligent services.

[0003] However, in existing technologies, when receiving user questions and providing answers, the display of answers is relatively simple and cannot provide users with intuitive and reasonable displays based on their questions, resulting in a poor user experience. Summary of the Invention

[0004] This invention provides a question-and-answer display method, device, vehicle, storage medium, and program product that displays answers in a reasonable manner and improves user experience.

[0005] According to one aspect of the present invention, a question-and-answer display method is provided, comprising:

[0006] In response to receiving a question to be answered, the classification information and question-answer template type are determined based on the question to be answered;

[0007] Generate answer content based on the classification information and the question-and-answer template type;

[0008] Output the answer to the question to be answered.

[0009] According to one aspect of the present invention, a question-and-answer display device is provided, comprising:

[0010] The question response module is used to respond to receiving a question to be answered and determine the classification information and question-answer template type based on the question to be answered.

[0011] The answer content generation module is used to generate answer content based on the classification information and the question-and-answer template type.

[0012] The answer content output module is used to output the answer content for the question to be answered.

[0013] According to another aspect of the present invention, a vehicle is provided, the vehicle comprising:

[0014] At least one processor, and a memory communicatively connected to said at least one processor;

[0015] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the question-and-answer display method according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the question-and-answer display method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the question-and-answer display method described in any embodiment of the present invention.

[0018] The technical solution of this invention, in response to receiving a question to be answered, determines classification information and question-and-answer template type based on the question, generates answer content according to the classification information and question-and-answer template type, and outputs the answer content for the question to be answered. This solves the problem of unreasonable answer display during the question-and-answer process. By determining the classification information and question-and-answer template type through the question to be answered, and generating corresponding answer content based on the classification information and question-and-answer template type, accurate answers and reasonable display of the user's question to be answered can be achieved. The answer content generated based on the classification information and question-and-answer template type is more in line with the user's needs and reading habits. The question-and-answer display method provided by this application embodiment can achieve reasonable display of questions and answers and improve the user experience.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a question-and-answer display method provided in Embodiment 1 of the present invention;

[0022] Figure 2 This is a flowchart of a question-and-answer display method provided in Embodiment 2 of the present invention;

[0023] Figure 3 This is an example diagram illustrating the display of answer content according to Embodiment 2 of the present invention;

[0024] Figure 4 This is an example diagram showing another answer content provided by Embodiment 2 of the present invention;

[0025] Figure 5 This is a display example diagram of another answer content provided according to Embodiment 2 of the present invention;

[0026] Figure 6 This is a display example diagram of another answer content provided according to Embodiment 2 of the present invention;

[0027] Figure 7 This is a schematic diagram of the structure of a question-and-answer display device according to Embodiment 3 of the present invention;

[0028] Figure 8 This is a structural schematic diagram of a vehicle that implements the question-and-answer display method of this invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Example 1

[0032] Figure 1This is a flowchart of a question-and-answer display method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where questions and answers are displayed appropriately. The method can be executed by a question-and-answer display device, which can be implemented in hardware and / or software, and can be configured in a vehicle. Figure 1 As shown, the method includes:

[0033] S101. In response to receiving a question to be answered, determine the classification information and question-and-answer template type based on the question to be answered.

[0034] In this embodiment, the question to be answered can be understood as a question that requires an answer. The question to be answered can be raised by the user through voice, text, or other means. For example, while driving, the driver or passenger in the vehicle might speak, "What are the important news stories today?", or the driver or passenger might manually type "What are the important news stories today?" on the vehicle's display screen, etc. The category information can be entertainment, travel, encyclopedia, etc.; the category information can be obtained by directly categorizing the question to be answered, or it can be obtained by categorizing the response content to the question to be answered. For example, the response content can be the result obtained by searching for the question to be answered. The question-and-answer template type can be understood as the type of template used when conducting the question and answer process. The question-and-answer template type can be descriptive, general-to-specific, timeline, etc.

[0035] The method provided in this application can be executed by the vehicle's infotainment system or other processors, or by other smart devices. This execution device can monitor in real time whether the user utters voice or inputs text content to determine whether the user needs to query a question. The user can trigger question input through specific words or buttons; that is, the user's voice or input operation is only detected and analyzed after a specific word or operation is detected to determine the question to be answered. Alternatively, the user's voice or input operation can be monitored and analyzed in real time; as long as the user's intention to ask a question is detected, the question to be answered is determined and the question query is performed. When receiving information such as the user's voice or input operation, the information provided by the user may include not only the question but also information unrelated to the question. The question to be answered can be determined by analyzing and extracting questions from the user's voice or input data, or all information provided by the user can be used as the question to be answered. After acquiring the user's question to be answered, this execution device analyzes the question to determine the classification information and question-and-answer template type; or, it performs a content search on the question to be answered, which can be a search from the Internet or a search from a pre-built database, etc.; through the content search, it obtains the corresponding search results, and performs corresponding analysis based on the search results to determine the classification information and question-and-answer template type.

[0036] S102. Generate answer content based on classification information and question-and-answer template type.

[0037] In this embodiment, the answer content can be understood as the content of the answer when responding to the question to be answered. It can be the result obtained directly from a search, or the result obtained through multiple rounds of question and answer, and so on.

[0038] The system analyzes and processes categorized information and question-and-answer template types to determine the data types required to answer the questions. It then performs data search to generate answer content based on the data types, or generates answer content based on the data types using a large language model.

[0039] Large language models are artificial intelligence models based on deep learning technology. They are trained on massive amounts of text data to learn language patterns, structures, and semantics. These models typically have a huge number of parameters; for example, some advanced large language models can have billions, tens of billions, or even hundreds of billions of parameters. They are capable of generating natural language text, understanding human instructions, and performing a variety of natural language processing tasks.

[0040] S103. Output the answer to the question to be answered.

[0041] After determining the answer content, it can be output directly, output according to a set method, or the output method can be determined based on the category information and question-and-answer template type. The answer content can be output in a streaming manner or through other methods. This application's embodiments are not intended to be limiting.

[0042] This invention provides a question-and-answer display method. In response to receiving a question to be answered, the method determines category information and a question-and-answer template type based on the question, generates answer content according to the category information and the question-and-answer template type, and outputs the answer content for the question to be answered. This solves the problem of unreasonable answer display during the question-and-answer process. By determining the category information and question-and-answer template type through the question to be answered, and generating corresponding answer content based on the category information and question-and-answer template type, the method can achieve accurate answers and reasonable display of the user's question to be answered. The answer content generated based on the category information and question-and-answer template type is more in line with user needs and reading habits. The question-and-answer display method provided by this application embodiment can achieve reasonable display of questions and answers, improving user experience.

[0043] Example 2

[0044] Figure 2This is a flowchart of a question-and-answer display method provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiments. Figure 2 As shown, the method includes:

[0045] S201. In response to receiving a question to be answered, determine the classification information and question-and-answer template type based on the question to be answered.

[0046] As an optional embodiment, this optional embodiment further optimizes the determination of classification information based on the question to be answered to: performing content search based on the question to be answered, determining the search results; classifying the content of the search results, and determining the classification information.

[0047] The process involves analyzing the questions to be answered and performing content searches. These searches can be conducted from the internet, a pre-built database, or other sources. The search results are then determined. These results are analyzed using methods such as keyword matching, similarity calculation, and model prediction to categorize them and determine their corresponding classification information. For example, one or more keyword sets can be pre-generated, each containing one or more keywords, and each set corresponding to a category. Keywords are extracted from the search results and matched against the keywords in the pre-generated sets. Keyword matching can be achieved by calculating similarity. This determines the set of keywords that match each keyword in the search results. The final set of matched keywords is determined by combining all the matched keyword sets. For example, the set of keywords with the most frequent matches is used as the final set of matched keywords, and the category corresponding to this final set is used as the classification information for the search results. Alternatively, a classification model can be pre-trained. The search results are input into the classification model, which then categorizes the results and outputs classification information. By searching the content of the question to be answered, we can obtain search results that initially match the question. Further, we can categorize the content of the search results to obtain category information. The category information can accurately describe the type of the question and answer results and improve the rationality of the question and answer display.

[0048] Optionally, search results can be one or more combinations of text, images, video links, music links, webpage links, and application links. Users can click on the links to jump to the corresponding application for playback or access. For example, if the search result is a music link, clicking the music link can directly jump to the corresponding music player or play music, etc.; or, if the search result is a webpage link, clicking the webpage link can directly jump to the webpage for access; or, if the search result is an application link, clicking the application link can jump to the application and access the corresponding articles, videos, etc., thus enabling access to content within the application. Search results can be one or more of the above types of content, enriching the content displayed to users, facilitating corresponding user operations, and improving the user experience.

[0049] As an optional embodiment, this optional embodiment further optimizes the determination of the question-and-answer template type based on the question to be answered to: making a prediction based on the question to be answered in order to predict and determine the question-and-answer template type that matches the intention of the answer to be answered.

[0050] The semantics of the question to be answered are analyzed to determine the intended presentation of the answer. For example, the intended presentation might be a summary followed by specific points, or a descriptive approach. The template matching the intended presentation of the question is then predicted to obtain the corresponding question-and-answer template type. For instance, a large language model can be used to predict the template for the question. This model is pre-trained, and the question to be answered is used as input. Based on the knowledge learned during training, the model predicts and outputs the question-and-answer template type. When predicting the template type using the large model, the entire question can be directly input, or keywords can be extracted and only those keywords input.

[0051] S202. Determine the answer template based on the classification information and question-and-answer template type.

[0052] In this embodiment, the answer template can be understood as the template for displaying the answer when answering a question. For example, the answer template may display the answer in a general-to-specific format with recommendations on the right, or it may display the answer in a descriptive format with recommendations at the bottom, and so on. The question-and-answer template type can describe the overall answer template. For example, if the question-and-answer template type is general-to-specific, it means that the answer template displays the content according to a general-to-specific structure. The answer template can include more detailed information, such as whether to include recommended content, the position of the recommended content, etc. One question-and-answer template type can correspond to multiple different answer templates. For example, if the answer template type is descriptive, the answer template can be descriptive with recommendations at the bottom, or it can be descriptive with recommendations on the right, and so on. Different classification information and the answer templates corresponding to question-and-answer model types are pre-determined, that is, a mapping relationship between classification information, question-and-answer template types, and answer templates is pre-established. After determining the classification information and question-and-answer template types, the mapping relationship is queried to determine the answer template corresponding to the classification information and question-and-answer template type. This answer template is the answer template corresponding to the question to be answered.

[0053] For example, Table 1 is a mapping table of answer templates, which provides an example of answer templates corresponding to different classification information and question-and-answer template types.

[0054] Table 1 Mapping Table of Answer Templates

[0055] Classifieds - Question and Answer Template Type Answer template Entertainment / Travel - Descriptive Descriptive - with recommendations below Travel - Total / Subtype Total-to-subject Entertainment - Total / Score Total Score - Recommended on the right Entertainment / News - Timeline Timeline Other - Descriptive / Total / Score Type Descriptive / Total-to-Small

[0056] S203. Generate answer content based on the answer template.

[0057] This system generates answer content that matches a given answer template. Generating answer content based on a template can be achieved using a large-scale model. For example, a large model can be pre-trained using training samples, which can be of different types. The input to the model can be the question to be answered and the answer template, or search results and the answer template. Once input, the model can generate the answer content based on the knowledge learned during training. Generating answer content based on a template makes the generated content more aligned with user reading habits, allowing users to quickly locate important content and information, thus improving the user experience.

[0058] Optionally, the answer template corresponding to the answer content includes a generated content display area and a recommended content display area; wherein, the generated content display area is used to display the question and answer results generated based on the search results corresponding to the question to be answered; the recommended content display area is used to display the original multimedia content determined based on the search results.

[0059] In this embodiment, the generated content display area can be understood as the area displaying content generated after data processing; the recommended content display area can be understood as the area displaying content recommended to the user. The size and positional relationship of the generated content display area and the recommended content display area can be designed in different forms according to different answer templates. The question-and-answer result can be understood as the answer obtained by answering the question to be answered. The original multimedia content can be audio / video playback links, images, application links, etc. In this embodiment, the generated content display area can be used to display question-and-answer results, which can be generated based on the search results corresponding to the question to be answered; the recommended content display area can be used to display original multimedia content, which can be determined based on the search results.

[0060] S204. Display the answer content according to the display layout of the content display area and the content to be recommended display area generated in the answer template.

[0061] The display layout of the generated content display area and the recommended content display area is determined based on the answer template. The display layout can include at least one of the following: the location information of the generated content display area, the size of the generated content display area, the location information of the recommended content display area, the size of the recommended content display area, and the relative positional relationship between the generated content display area and the recommended content display area. Based on the display layout, the positions of different information within the answer content are determined and displayed accordingly. For example, the generated content display area is displayed in the upper area of ​​the screen, and the recommended content display area is displayed in the lower area of ​​the screen. By displaying the answer content using the layout of the generated content display area and the recommended content display area in the answer template, the page layout is more reasonable, making it easier for users to capture key content and read the content more easily.

[0062] As an optional embodiment, this optional embodiment further optimizes the generation of answer content based on the answer template to: generating the question and answer results in the answer content based on the display requirements of the content display area generated in the answer template and the search results corresponding to the question to be answered.

[0063] In this embodiment, the display requirements can be one or more content requirements, such as content, word count, and structure. These requirements can be any requirement that directs the large model to generate content. By analyzing the display requirements of the generated content display area in the answer template and the search results corresponding to the question to be answered, question-and-answer results that meet the display requirements are generated. For example, the search results and the display requirements of the generated content display area in the answer template can be used as input to the large model. After input, the large model can generate content based on the knowledge learned during training, generate question-and-answer results, and output them. For example, if the display requirements include word count requirements, the question-and-answer results are generated according to the word count requirements, and the word count of the question-and-answer results meets the word count requirements. Or, if the display requirements include structural requirements, the question-and-answer results are generated according to the structural requirements, and the structure of the question-and-answer results meets the structural requirements. Generating question-and-answer results based on display requirements yields more reasonable results and improves the user's reading experience.

[0064] As an optional embodiment, this optional embodiment further optimizes the generation of question-and-answer results in the answer content based on the display requirements of the content display area generated in the answer template and the search results corresponding to the question to be answered, to: generating question-and-answer results in the answer content based on the display structure requirements of the content display area generated in the answer template and the search results corresponding to the question to be answered, wherein the question-and-answer results include at least one piece of structured content.

[0065] In this embodiment, the display structure requirement can be understood as the structural requirements for the content displayed when presenting question-and-answer results. For example, a display structure requirement of "general-to-specific" means that the structure of the question-and-answer results is general-to-specific, and the results are displayed in this format. Question-and-answer results are typically a piece of text. When displaying answers based on answer templates, the content needs to be presented in a specific way. For example, if the answer content is a single paragraph of text, and the display structure requirement for the content display area in the answer template is general-to-specific, then a structured general-to-specific question-and-answer result needs to be generated to facilitate user viewing of the answer. For instance, a question-and-answer result with a title + body text structure can be generated according to the display structure requirement.

[0066] The presentation structure requirements for the content display area in the answer template are determined. The presentation structure requirements and the search results corresponding to the questions to be answered are analyzed. Corresponding question-and-answer results are generated according to the presentation structure requirements, where each result includes at least one piece of structured content. For example, the presentation structure requirements and search results are used as input to a large model. After being input into the large model, it can generate content based on the knowledge learned during training, generating question-and-answer results that meet the presentation structure requirements and outputting them. The question-and-answer results include one or more pieces of structured content. For example, if the presentation structure requirement is a total score, then each sub-point corresponds to one piece of structured content; the summary content can also be one piece of structured content. If the presentation structure requirement is a description, then the entire question-and-answer result is one piece of structured content. This embodiment of the application generates question-and-answer results by displaying structure requirements, resulting in structured question-and-answer results that are more convenient for users to read. Users can directly view the key points in the answer content, improving the user reading experience.

[0067] The structuring in this embodiment can be achieved through a large model, which generates a structured summary of the answer in a streaming manner, such as subheadings + body text, and finally provides the answer to be distributed and displayed in a structured form of subheadings + body text.

[0068] As an optional embodiment, this optional embodiment further optimizes the generation of question-and-answer results in the answer content based on the display structure requirements of the content display area generated in the answer template and the search results corresponding to the question to be answered, as follows: extract titles from the search results according to the display structure requirements of the content display area generated in the answer template; if titles are extracted, generate structured content based on the extracted titles and the content corresponding to each title; if no titles are extracted, generate titles based on the search results, and generate structured content based on the generated titles and the content corresponding to each title.

[0069] Analyze the content contained in the search results and extract the titles. The search results may or may not contain suitable title data; therefore, when extracting titles, you may extract one or more titles, or zero titles. If titles are extracted, determine the corresponding content for each title, and treat the titles and their corresponding content as structured content.

[0070] If no title is extracted, the search results are analyzed to generate one or more suitable titles. For example, the search results can be segmented semantically, each segment analyzed and summarized to generate a corresponding title; alternatively, the content of each segment can be searched, and the title of the matched content with high similarity can be used as the generated title. The process of generating titles for search results can be achieved by segmenting the search results using semantic segmentation algorithms, or by directly inputting the search results into a pre-trained large model to generate the corresponding titles. The generated titles and their corresponding content are then treated as structured content.

[0071] In this embodiment of the application, when displaying the structured content in the question-and-answer results, the position of each title and its corresponding content can be determined according to the number of titles, the size of the content corresponding to the title, and the size of the screen, and each title and its corresponding content can be displayed in the appropriate position.

[0072] This application embodiment obtains titles by extracting titles from search results or generates titles based on search results, and achieves structured display through titles, making it easier for users to view the key points in the search results, saving users time and improving user experience.

[0073] In this embodiment, if a large model is used to extract or generate titles from search results, and then to predict answer templates using the same model, the large model used in both cases can be the same model. When processing with the large model, different prompts can be input based on the task. The large model processes the data based on the prompts and the output content to generate the corresponding answer. For example, if the input content is a question to be answered and the prompts are prediction templates, the large model performs the corresponding template prediction task to generate a question-and-answer template type.

[0074] In this embodiment, when generating question-and-answer results, titles are extracted according to the display structure requirements. If no titles are extracted, titles are generated. Structured content is then generated using the titles and their corresponding content. By generating structured content as the question-and-answer results and displaying it, it is easier for users to read. Users can directly see the key points in the answer and decide whether to view details based on their interests. The overall display method highlights the key points and facilitates user viewing.

[0075] As an optional embodiment, this optional embodiment further optimizes the generation of answer content based on the answer template to A1-A2:

[0076] A1. Analyze the search results corresponding to the question to be answered to determine the recommendation type.

[0077] In this embodiment, the recommendation type can be music, video, news, sports, events, application links, etc. For example, an application link could be a travel guide on Xiaohongshu (Little Red Book). Content analysis is performed on the search results corresponding to the question to be answered. This analysis can be done through keyword recognition, model recognition, and other methods to determine the recommendation type.

[0078] A2. Based on the recommendation type and category information, as well as the display requirements of the content to be recommended in the answer template, determine the content to be recommended in the answer content.

[0079] In this embodiment, the content to be recommended can be understood as data recommended to the user, which can be one or more of the following: images, text, links, etc. The display requirements for the content to be recommended in the answer template are determined. These requirements may include word count, content type, and data type; for example, the data type could be images or links. The recommendation type, category information, and display requirements of the content to be recommended are analyzed. Content matching these requirements is retrieved from search results or from data sources such as the internet and databases. By generating content to be recommended through analysis of recommendation type, category information, and display requirements, more reasonable and user-friendly content can be obtained, improving the user experience.

[0080] As an optional embodiment, this optional embodiment further determines the content to be recommended in the answer content based on the recommendation type, classification information, and the display requirements of the content to be recommended display area in the answer template, optimizing it into B1-B3:

[0081] B1. Determine whether there is any content in the search results that meets the requirements for recommendation type, category information, and display of recommended content in the answer template.

[0082] Analyze the content included in the search results to determine if any content exists that meets the requirements of the recommendation type, category information, and display area for the content to be recommended. If so, proceed to step B2; otherwise, proceed to step B1. For example, if the recommendation type is an application link, the category information is travel, and the display requirement for the content to be recommended is a size not exceeding 10cm*10cm, analyzing the content in the search results reveals that the search results include an application link. This application can be used for purchasing travel tickets, and the link size is 8cm*8cm. Therefore, it can be determined that there is content to be recommended that meets the requirements of the recommendation type, category information, and display area for the content to be recommended in the answer template.

[0083] B2. If the conditions are met, then determine the content to be recommended.

[0084] If there is content that meets the requirements of recommendation type, category information, and display in the recommended content display area of ​​the answer template, then the recommended content can be determined. That is, content that meets the requirements of recommendation type, category information, and display in the recommended content display area of ​​the answer template is selected from the search results as recommended content. The recommended content can be one or more data entries.

[0085] B3. If not satisfied, generate at least one query question based on the question to be answered, and determine the content to be recommended based on the query question and the recommendation type.

[0086] In this embodiment, the question to be queried can be understood as a question that needs to be answered through querying. The question to be queried is a secondary generated question, and the number of questions to be queried is one or more.

[0087] The system extracts or analyzes questions to generate query questions. For example, it analyzes all questions to generate one or more query questions, or it extracts questions from the questions to merge them with the questions to generate one or more query questions. Based on the query question and recommendation type, it searches the internet or a pre-generated knowledge base to determine the answer to the query question, and uses the answer as the recommended content. When searching for the answer to a query question, different knowledge bases corresponding to different recommendation types can be pre-set. Before the query, the knowledge base for this query is determined based on the correspondence between recommendation types and knowledge bases, and the corresponding knowledge base is queried for each query question. For example, the query question is sent to the knowledge base, which searches the knowledge base based on the query question to determine the recommended content and feeds it back to the execution device; or the query question and recommendation type are sent to the knowledge base, which searches the knowledge base based on the query question and recommendation type to determine the recommended content that matches the query question and recommendation type and feeds it back to the execution device. A knowledge base can be a database, the internet, an application, etc.—anything that provides question-and-answer knowledge can serve as a knowledge base. This execution device receives the query results, determines the query outcome for each question, and generates the final recommended content based on the query outcome for each question. For example, the query outcome can be used directly as the recommended content, or the recommended content can be generated again based on the query outcome through web search or large-scale question-and-answer models. The recommended content can be text, images, links, etc. For example, if the knowledge base is an application, the recommended content could be a link to that application, allowing users to click the link to jump to an article, note, video, etc., within the application.

[0088] When searching for the answer to a question, you can pre-set a rich knowledge base and query this knowledge base for each question.

[0089] This application embodiment determines the recommendation type by analyzing search results, and determines the content to be recommended based on the recommendation type, category information, and display requirements of the content to be recommended display area in the answer template. It generates corresponding content to be recommended under different circumstances for recommendation display. By using different methods to generate corresponding content to be recommended, it provides users with reasonable recommendation display, making the question and answer display more reasonable and convenient, and improving the user experience.

[0090] As an optional embodiment, this optional embodiment further generates at least one query question based on the question to be answered, optimized to C1-C2:

[0091] C1. If the question to be answered is determined to be of the total score type based on the answer template, generate the corresponding query question based on the question to be answered and each sub-answer in the question and answer results generated for the question to be answered.

[0092] In this embodiment, sub-answers are information that can be used as subheadings in the overall question-and-answer results to describe different content or focuses, similar to subheadings. Sub-answers can describe the subheadings in detail. For example, the question-and-answer results include different subheadings and sub-answers corresponding to each subheading. For example, the subheading is "Natural History Museum", and the sub-answer corresponding to the subheading is "A comprehensive museum with a large number of precious specimens and fossils, which can help children learn natural science knowledge in a vivid way."

[0093] Analyze the answer template to determine the template type corresponding to the question to be answered. If the template type is a total-point type, since the answer results of this type usually contain different sub-points, each with a different emphasis, we can analyze the answer results to determine each sub-point and its corresponding sub-answer. Based on the question to be answered and the sub-answers corresponding to the sub-points, we can generate a question. For example, we can extract questions from the sub-answers corresponding to the sub-points, generate a question, and then merge this question with the question to be answered to generate the query question corresponding to that sub-point. Alternatively, we can use both the question and the question to be answered as the query question. Or, we can input the question to be answered and the sub-answers corresponding to each sub-point in the answer results into a larger model to generate the query question, and so on.

[0094] For example, Figure 3This document provides an example of a display of answer content. The question to be answered is "What are some suitable places to take children in xx city?". The answer results include the following three headings: 01 Natural History Museum, 02 Amusement Park, and 03 Wildlife Park, along with corresponding content for each heading. Each heading can also be used as a sub-answer, with the description below each sub-answer for that heading. The sub-answers are combined with the question to generate a query question. Based on the query question, an application is queried (**APP in the image represents a specific application). Two travel notes are generated as recommended content and displayed at the bottom of the screen, as shown in Note 1 and Note 2. Users can click on the recommended content to jump to the corresponding APP to view other users' travel notes.

[0095] C2. If the question to be answered is determined to be of the description type based on the answer template, extract the question to be answered and the corresponding question and answer results to generate at least one question to be queried.

[0096] Analyze the answer template to determine the question-and-answer template type corresponding to the question to be answered. If the question-and-answer template type is descriptive, the question-and-answer results can be considered as not needing to distinguish between different focuses. Directly extract questions from the question to be answered and the question-and-answer results. For example, extract questions from the question-and-answer results and merge the extracted questions with the question to be answered to obtain one or more questions to be queried; or directly input the question to be answered and the question-and-answer results into the large model for question extraction to obtain one or more questions to be queried output by the large model.

[0097] This application embodiment can generate query questions based on the type of question to be answered, resulting in more reasonable query questions that are closer to the question to be answered, which helps to improve the accuracy of recommended content.

[0098] It is important to know that in this embodiment, when using a large model to extract titles, generate titles, predict templates, and generate query questions, the same large model can be used, and different prompt words can be input according to different tasks.

[0099] In this embodiment of the application, when generating content to be recommended, it can also determine whether the search results and question-and-answer results match. If they match, the content to be recommended is generated based on the search results; if they do not match, the content to be recommended is determined by generating a query to be queried. The determination of whether the search results and question-and-answer results match can be performed after determining that there is content in the search results that meets the display requirements of the recommendation type, category information, and the recommended content display area in the answer template, or it can be performed before determining whether there is content in the search results that meets the display requirements of the recommendation type, category information, and the recommended content display area in the answer template.

[0100] The method for determining whether search results and question-and-answer results match can be by calculating similarity. Matching is determined based on the degree of similarity between the content of the search results and the question-and-answer results. For example, a similarity below a certain threshold indicates a mismatch, while a similarity above a certain threshold indicates a match. When the search results or question-and-answer results contain multiple segments or points of content, similarity calculation can be performed on the overall similarity or on segments or points. Then, the calculated similarities are summed, weighted, and the maximum or minimum value is taken as the final similarity score between the search results and the question-and-answer results. The result determines whether to display recommended content. For example, if the match is found, recommended content is generated based on the search results; if the match is not found, recommended content is not displayed. In this case, the recommended content can be empty, or the search can be repeated until a matching search result is found, and then recommended content is generated based on this search result, and so on. Generating recommended content based on search results can involve directly using the search results as recommended content, or selecting a portion of the search results as recommended content, and so on.

[0101] As an optional embodiment, this optional embodiment is further optimized by: determining the display position corresponding to the content to be recommended.

[0102] When displaying recommended content, the placement can be determined based on the answer template. For example, if the answer template includes "Recommended Content Below," the content will be displayed at the bottom of the screen. The display position can also consider factors such as screen size, the size occupied by the question and answer results, and the size of the content itself. The size of the content can be determined based on the total text size of the search results, font size, image size, and link display size. The placement of recommended content can be determined through specific analysis of the content and by combining this with the answer template.

[0103] The display location can be represented by one or more parameters such as coordinates, length, and width. For example, the size of the rectangle to be recommended is determined by the length and width, the rectangle is positioned by the coordinates, and finally the area on the screen to be recommended is determined, and the recommended content is displayed in this area.

[0104] For example, Figure 4 Another example of the answer content is provided, in which "What do the lyrics of the song xxx express?" is the question to be answered; the first paragraph is the title of the question and answer results, the second paragraph is the content corresponding to the title of the question and answer results; at the bottom, a link to the music "xxx" is displayed, and users can play the song by clicking the play button. The music link is the content to be recommended, which is generated based on the search results.

[0105] For example, taking the question to be answered as "What are some good songs by singer A?", the question-and-answer results are "X1", "X2", and "X3", while the search results are "X4", "X5", and "X6". After matching, it is determined that the question-and-answer results and the search results do not match. In this case, the content to be recommended may not be displayed.

[0106] In this embodiment of the application, the answer generation process can be achieved through streaming generation and streaming distribution. Streaming generation refers to generating the answer word by word, rather than generating the entire answer at once. Streaming distribution refers to distributing the word-by-word generated answer step by step according to special markers, rather than waiting for all answers to be generated before distributing them all at once.

[0107] Optionally, search results may include at least one of the following: text, images, video links, music links, web page links, and application links.

[0108] Optionally, the content to be recommended may include at least one of the following: text, images, video links, music links, web page links, and application links.

[0109] For example, Figure 5 This example provides another way to display the answer content. The question, "What are some good songs by singer A?", is the question to be answered. Titles 01 (XX1), 02 (XX2), and 03 (XX3) are extracted from the question-and-answer results. Below each title is the corresponding text content, which can be a detailed introduction to that title. On the right, corresponding recommended content can be displayed for each title. This recommended content can include images, music links, etc. The image uses images as an example, displaying the corresponding image to the right of the title and its text content. Images 1, 2, and 3 are used as examples in the image; in practical applications, these can be authorized, authentic photos. Images 1-3 can also display a play button, allowing users to play the song by clicking it. Below the image, recommended content is also exemplified, such as "Singer A's latest songs" or "Where has singer A held their latest concert?". These can be links that redirect users to corresponding web pages, applications, etc.

[0110] For example, Figure 6Another example of displaying answer content is provided. The question "What news is there on May 10th?" is the question to be answered. "01 Movie XXX premieres," "02 XX car launches," and "03 Singer B's concert" are titles extracted from the question-and-answer results. Below each title is the corresponding text content, which can be a detailed introduction to that title. The title and its corresponding text content can be displayed within a rectangle, which can serve as a link to the relevant news article when the user clicks anywhere within the rectangle. The image also exemplifies recommended content, such as "What is the main content of movie XXX?" and "What are the features of singer B's concert?", which users can also view by clicking. This allows for further news recommendations to users through the recommended content.

[0111] In this embodiment, if a large model is used to extract or generate a title from the answer content, and then used to predict the answer template, the large model used in both cases can be the same large model. When processing the answer using the large model, different prompts can be input based on the task. The large model processes the data based on the prompts and the output content to generate the corresponding answer. For example, if the input content is the question to be answered and the prompts are the prediction template, then the large model performs the corresponding template prediction task and generates the template type.

[0112] For example, when displaying answer content, the display positions of the question-and-answer results and the content to be recommended within the answer content can be determined separately. Based on the answer template, the display position corresponding to the question-and-answer results is determined to be the center of the screen, and the display position corresponding to the content to be recommended is the right side of the screen. The display position of the answer content can also be determined based on the screen size and the screen size occupied by the answer content. That is, the positional relationship between the question-and-answer results and the content to be recommended is determined based on the answer template, i.e., the approximate positional range, and then the positions of the question-and-answer results and the content to be recommended are further determined based on the screen size occupied by each. The screen size occupied by the answer content can be determined based on the text size, font size, image size, etc., within the answer content.

[0113] This invention provides a method for displaying question-and-answer results, solving the problem of unreasonable answer display during the question-and-answer process. It determines the question-and-answer template type by predicting the question to be answered, and identifies classification information by analyzing search results. Based on the question-and-answer template type and classification information, it determines the answer template. Based on the display requirements of the content display area in the answer template, it generates the question-and-answer results in the answer content. Based on the display requirements of the recommended content display area in the answer template, it generates the recommended content in the answer content. Finally, it displays the answer content based on the display layout. This method of generating and displaying answer content makes it easier for users to read. Users can directly see the key points in the answer content and decide whether to view details based on their interests. The entire display method highlights key points and facilitates user viewing. Furthermore, when displaying recommended content, this application can directly determine the content based on search results or generate new questions for secondary queries, providing users with reasonable recommended content. The information displayed to users can be one or more of text, images, video links, music links, web page links, and application links, offering a rich variety of display methods. The data source can be the internet or applications, enabling real-time updates and a more diverse and engaging experience, effectively improving the user experience.

[0114] Example 3

[0115] Figure 7 This is a schematic diagram of a question-and-answer display device provided in Embodiment 3 of the present invention. Figure 7 As shown, the device includes: a question response module 31, a question content generation module 32, and a question content output module 33.

[0116] The question response module 31 is used to respond to receiving a question to be answered and determine the classification information and question-answer template type based on the question to be answered.

[0117] Answer content generation module 32 is used to generate answer content based on the classification information and the question-and-answer template type;

[0118] The answer content output module 33 is used to output the answer content for the question to be answered.

[0119] This invention provides a question-and-answer display device that solves the problem of unreasonable answer display during the question-and-answer process. It determines the category information and question-and-answer template type based on the question to be answered, and generates corresponding answer content based on the category information and question-and-answer template type. This enables accurate and reasonable answers to users' questions and outputs the answer content for the question to be answered. The answer content generated based on the category information and question-and-answer template type is more in line with user needs and reading habits. The question-and-answer display method provided by this application can achieve reasonable display of questions and answers, improving user experience.

[0120] Optionally, the question response module 31 includes:

[0121] The search unit is used to perform content search based on the question to be answered and determine the search results; the classification information determination unit is used to classify the search results and determine the classification information.

[0122] Optionally, the answer content generation module 32 includes:

[0123] The answer template determination unit is used to determine the answer template based on the classification information and the question-and-answer template type.

[0124] The answer content generation unit is used to generate answer content based on the answer template.

[0125] Optionally, the answer template corresponding to the answer content includes a generated content display area and a recommended content display area; wherein, the generated content display area is used to display the question-and-answer results generated based on the search results corresponding to the question to be answered; and the recommended content display area is used to display the original multimedia content determined based on the search results.

[0126] Optionally, the question response module 31 includes:

[0127] The template prediction unit is used to make predictions based on the question to be answered, so as to predict and determine the question-and-answer template type that matches the intention of the answer to the question to be answered.

[0128] Optionally, the answer content generation unit is specifically used to: generate the question and answer results in the answer content based on the display requirements of the content display area generated in the answer template and the search results corresponding to the question to be answered.

[0129] Optionally, generating the question-and-answer result in the answer content based on the display requirements of the content display area generated in the answer template and the search results corresponding to the question to be answered includes: generating the question-and-answer result in the answer content based on the display structure requirements of the content display area generated in the answer template and the search results corresponding to the question to be answered, wherein the question-and-answer result includes at least one piece of structured content.

[0130] Optionally, generating the question-and-answer results in the answer content based on the display structure requirements of the content display area generated in the answer template and the search results corresponding to the question to be answered includes: extracting titles from the search results according to the display structure requirements of the content display area generated in the answer template; if titles are extracted, generating structured content based on the extracted titles and the content corresponding to each title; if no titles are extracted, generating titles based on the search results, and generating structured content based on the generated titles and the content corresponding to each title.

[0131] Optionally, the answer content generation unit is specifically used to: analyze the search results corresponding to the question to be answered to determine the recommendation type; and determine the content to be recommended in the answer content based on the recommendation type, classification information, and the display requirements of the content to be recommended display area in the answer template.

[0132] Optionally, based on the recommendation type, classification information, and display requirements of the content to be recommended display area in the answer template, the content to be recommended in the answer content is determined to include:

[0133] Determine whether there is any content in the search results that meets the requirements of the recommendation type, category information, and the display requirements of the content to be recommended display area in the answer template;

[0134] If the conditions are met, then the content to be recommended is determined;

[0135] If the conditions are not met, at least one query question is generated based on the question to be answered, and the content to be recommended is determined based on the query question and the recommendation type.

[0136] Optionally, generating at least one query question based on the question to be answered includes:

[0137] If the question to be answered is determined to be of the total score type according to the answer template, a corresponding query question is generated based on the question to be answered and each sub-answer in the question-and-answer results generated for the question to be answered.

[0138] If the question to be answered is determined to be a description type based on the answer template, question extraction is performed on the question to be answered and the corresponding question and answer results to generate at least one question to be queried.

[0139] Optionally, the answer content output module 33 is specifically used to: display the answer content according to the display layout of the content display area and the content to be recommended display area generated in the answer template.

[0140] The question-and-answer display device provided in the embodiments of the present invention can execute the question-and-answer display method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0141] Example 4

[0142] Figure 8 A schematic diagram of the structure of a vehicle 40 that can be used to implement an embodiment of the present invention is shown. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0143] like Figure 8 As shown, vehicle 40 includes at least one processor 41 and a memory, such as read-only memory (ROM) 42 and random access memory (RAM) 43, communicatively connected to at least one processor 41. The memory stores computer programs executable by at least one processor. Processor 41 can perform various appropriate actions and processes based on the computer program stored in ROM 42 or loaded from storage unit 48 into RAM 43. RAM 43 can also store various programs and data required for the operation of vehicle 40. Processor 41, ROM 42, and RAM 43 are interconnected via bus 44. Input / output (I / O) interface 45 is also connected to bus 44.

[0144] Multiple components in vehicle 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of displays, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows vehicle 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0145] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as question-answering display methods.

[0146] In some embodiments, the question-and-answer display method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on vehicle 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the question-and-answer display method described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the question-and-answer display method by any other suitable means (e.g., by means of firmware).

[0147] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0148] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0149] This invention provides a computer program product, which includes a computer program that, when executed by a processor, implements the question-and-answer display method described in any embodiment of this invention.

[0150] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0151] To provide interaction with the user, the systems and technologies described herein can be implemented in a vehicle having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the vehicle. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0152] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0153] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0154] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0155] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of presenting a question and answer, characterized by, The method comprises the following steps: in response to receiving a question to be answered, determining classification information and a question and answer template type based on the question to be answered; generating answer content according to the classification information and the question and answer template type; outputting the answer content for the question to be answered.

2. The method of claim 1, wherein, The step of generating answer content according to the classification information and the question and answer template type comprises the following steps: determining an answer template according to the classification information and the question and answer template type; generating answer content based on the answer template.

3. The method according to claim 1 or 2, characterized in that, The answer template corresponding to the answer content comprises a generated content display area and a recommended content display area; the generated content display area is used to display a question and answer result generated based on a search result corresponding to the question to be answered; and the recommended content display area is used to display original multimedia content determined based on the search result.

4. The method according to any of claims 1 to 3, characterized in that, The step of determining classification information based on the question to be answered comprises the following steps: performing content search according to the question to be answered to determine a search result; classifying the content of the search result to determine classification information.

5. The method according to any of claims 1 to 4, characterized in that, The step of determining a question and answer template type based on the question to be answered comprises the following step: performing prediction based on the question to be answered to predict a question and answer template type matching an answer display intention of the question to be answered.

6. The method according to claim 2 or 3, characterized in that, The step of generating answer content based on the answer template comprises the following step: generating a question and answer result in the answer content based on display requirements of the generated content display area in the answer template and a search result corresponding to the question to be answered.

7. The method of claim 6, wherein, The step of generating a question and answer result in the answer content based on display requirements of the generated content display area in the answer template and a search result corresponding to the question to be answered comprises the following step: generating a question and answer result in the answer content based on display structure requirements of the generated content display area in the answer template and a search result corresponding to the question to be answered, wherein the question and answer result comprises at least one piece of structured content.

8. The method of claim 7, wherein, The step of generating a question and answer result in the answer content based on display structure requirements of the generated content display area in the answer template and a search result corresponding to the question to be answered comprises the following steps: performing title extraction from the search result according to the display structure requirements of the generated content display area in the answer template; if a title is extracted, generating structured content according to the extracted title and content corresponding to each title; if no title is extracted, generating a title according to the search result and generating structured content according to the generated title and content corresponding to each title.

9. The method according to any one of claims 2-8, characterized in that, The step of generating answer content based on the answer template comprises the following steps: analyzing a search result corresponding to the question to be answered to determine a recommendation type; determining recommended content in the answer content according to the recommendation type, classification information and display requirements of the recommended content display area in the answer template.

10. The method of claim 9, wherein, The step of determining recommended content in the answer content according to the recommendation type, classification information and display requirements of the recommended content display area in the answer template comprises the following steps: determining whether there is recommended content in the search result satisfying the recommendation type, classification information and display requirements of the recommended content display area in the answer template; if yes, determining the recommended content; If the condition is not met, at least one query question is generated according to the to-be-answered question, and the to-be-recommended content is determined according to the to-be-query question and the recommended type.

11. The method of claim 10, wherein, The generating at least one query question according to the to-be-answered question comprises: If it is determined according to the answer template that the to-be-answered question is of a total score type, a corresponding query question is generated according to the to-be-answered question and each sub-answer in the answer result corresponding to the to-be-answered question. If it is determined according to the answer template that the to-be-answered question is of a description type, at least one query question is generated by performing question extraction on the to-be-answered question and the answer result corresponding to the to-be-answered question.

12. The method according to any one of claims 2-11, characterized in that, The outputting of the answer content for the to-be-answered question comprises: According to the display layout of the generated content display area and the to-be-recommended content display area in the answer template, the answer content is displayed.

13. A question and answer display device, characterized by Comprise: The answering question response module is configured to, in response to receiving a to-be-answered question, determine classification information and a question and answer template type based on the to-be-answered question. The answer content generation module is configured to generate answer content according to the classification information and the question and answer template type. The answer content output module is configured to output the answer content for the to-be-answered question.

14. A vehicle characterized by comprising: The vehicle comprises: At least one processor, and a memory connected in communication with the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the question and answer display method of any one of claims 1-12.

15. A computer readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the question and answer display method of any one of claims 1-12 when executed.

16. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by the processor to implement the question and answer display method according to any one of claims 1-12. The computer program product comprises a computer program, and the computer program is executed by the processor to implement the question and answer display method according to any one of claims 1-12.

Images