A question and answer method, device, computer device and storage medium

Abstract

The present disclosure provides a question and answer method, device, computer equipment and storage medium, wherein the method comprises: in response to a user initiating a question, determining a target scene of a question of the user; displaying question assistance information matched with the target scene; wherein the information format and / or information completeness of the question assistance information is related to the scene type of the target scene, and the question assistance information is used to assist the user in editing target question information for asking questions; in response to receiving the target question information edited according to the question assistance information, displaying an artificial intelligence answer result matched with the target question information.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of information processing, and in particular, to a question and answer method, device, computer equipment and storage medium. BACKGROUND

[0002] Using artificial intelligence technology can solve related search problems for users, and users can obtain answers to questions by inputting question information on an artificial intelligence question and answer page. The answer provided by artificial intelligence is affected by the completeness of the content in the question information. If the input question information is incomplete or not comprehensive, artificial intelligence will not be able to provide an accurate answer that meets the user's needs.

[0003] For users, it is difficult to directly organize complete question information. In this case, artificial intelligence cannot accurately identify the user's question intention from the question information, and thus the answer provided to the user cannot meet the user's actual needs. SUMMARY

[0004] The embodiments of the present disclosure at least provide a question and answer method, device, computer equipment and storage medium.

[0005] In a first aspect, the embodiments of the present disclosure provide a question and answer method, comprising: in response to a user initiating a question, determining a target scene of the user's question; displaying question assistance information matched with the target scene; wherein the information format and / or information completeness of the question assistance information is related to the scene type of the target scene, and the question assistance information is used to assist the user in editing target question information for the question; in response to receiving the target question information edited based on the question assistance information, displaying an artificial intelligence answer result matched with the target question information.

[0006] In an optional implementation, in response to the user initiating the question, determining the target scene of the user's question comprises: displaying multiple candidate scenes on an artificial intelligence answer page, and in response to a selection operation of the user on the candidate scenes, determining the target scene of the user's question; or receiving at least part of the question information input by the user in a question input area on the artificial intelligence answer page, and determining a target scene matched with the at least part of the question information.

[0007] In an optional implementation, the question assistance information matched with the target scene is determined according to the following manner: based on the scene type of the target scene, determining a target assistance information type from multiple assistance information types; the information format and / or information completeness corresponding to different assistance information types are different; and generating the question assistance information matched with the target scene according to the target assistance information type.

[0008] In an alternative implementation, the determining the target auxiliary information type from the plurality of auxiliary information types based on the scene type of the target scene comprises: in response to the target scene belonging to a first scene type, the first scene type comprising a scene type that does not require supplementary personalized information, determining that the target auxiliary information type comprises a complete question information type; and the generating the question-asking auxiliary information matching the target scene according to the target auxiliary information type comprises: generating editable complete question information matching the target scene based on scene information of the target scene, for use as the question-asking auxiliary information.

[0009] In an alternative implementation, the determining the target auxiliary information type from the plurality of auxiliary information types based on the scene type of the target scene comprises: in response to the target scene belonging to a second scene type, the second scene type comprising a work-study type scene, determining that the target auxiliary information type comprises a fill-in-the-blank question information type; and the generating the question-asking auxiliary information matching the target scene according to the target auxiliary information type comprises: generating at least one to-be-filled sentence matching the target scene according to the fill-in-the-blank question information type, the to-be-filled sentence containing first to-be-filled field information; the first to-be-filled field information being used to indicate that the empty content in the to-be-filled sentence is to be supplemented; and the to-be-filled sentence generates the target question information after the empty content is supplemented.

[0010] In an alternative implementation, the determining the target auxiliary information type from the plurality of auxiliary information types based on the scene type of the target scene comprises: in response to the target scene belonging to a third scene type, the third scene type comprising a document type scene, determining that the target auxiliary information type comprises a form question information type; and the generating the question-asking auxiliary information matching the target scene according to the target auxiliary information type comprises: generating a form matching the target scene according to the form question information type, the form containing a plurality of second to-be-filled field information; the second to-be-filled field information being used to indicate that the selection or input of field information is to be performed for a specified field; and the filled form information is used to generate the target question information according to a preset format.

[0011] In an alternative implementation, the displaying the question-asking auxiliary information matching the target scene comprises: displaying a plurality of question dimensions corresponding to the target scene, and displaying the to-be-filled field information matching the question dimensions.

[0012] In an optional implementation, the target auxiliary information type is determined from the multiple auxiliary information types based on a scene type of the target scene, including: in response to the target scene belonging to a fourth scene type, the fourth scene type including a scene in which a user actively inputs partial question information, determining that the target auxiliary information type includes a predicted question information type; and the question auxiliary information matching the target scene is generated according to the target auxiliary information type, including: performing intent recognition on the partial question information to generate multiple candidate predicted question information; and selected question information in the candidate predicted question information is used as the question auxiliary information.

[0013] In an optional implementation, the multiple candidate predicted question information is generated according to the following manner: historical search data associated with the partial question information is obtained; historical search data corresponding to a same search link is determined by performing search link clustering on the historical search data; the search link includes multiple continuous search records, and the multiple continuous search records include continuous supplementary searches performed after an initial search is initiated; and candidate predicted question information corresponding to each search link is generated based on historical search data of each search link.

[0014] In a second aspect, the embodiments of the present disclosure further provide a question and answer device, including: a determination module configured to determine a target scene of a question initiated by a user in response to the user initiating the question; a first display module configured to display question auxiliary information matching the target scene; wherein an information format and / or an information completeness of the question auxiliary information is related to a scene type of the target scene, and the question auxiliary information is used to assist a user in editing target question information for the question; and a second display module configured to display an artificial intelligence answer result matching the target question information in response to receiving the target question information edited based on the question auxiliary information.

[0015] In an optional implementation, the determination module, when determining the target scene of the question initiated by the user in response to the user initiating the question, is configured to: display multiple candidate scenes on an artificial intelligence answer page, and determine the target scene of the question initiated by the user in response to a selection operation of the user on the candidate scenes; or receive at least partial question information input by the user in a question input area on the artificial intelligence answer page, and determine a target scene matching the at least partial question information.

[0016] In an alternative implementation, the device further comprises a processing module, and the question assistance information matching the target scene is determined by the processing module in the following manner: determining a target assistance information type from a plurality of assistance information types based on a scene type of the target scene; different assistance information types correspond to different information formats and / or information completeness; and generating the question assistance information matching the target scene according to the target assistance information type.

[0017] In an alternative implementation, when determining the target assistance information type from a plurality of assistance information types based on a scene type of the target scene, the processing module is configured to: in response to the target scene belonging to a first scene type, the first scene type including a scene type that does not require supplementary personalized information, determine that the target assistance information type includes a complete question information type; and when generating the question assistance information matching the target scene according to the target assistance information type, the processing module is configured to: generate editable complete question information matching the target scene based on scene information of the target scene, for use as the question assistance information.

[0018] In an alternative implementation, when determining the target assistance information type from a plurality of assistance information types based on a scene type of the target scene, the processing module is configured to: in response to the target scene belonging to a second scene type, the second scene type including a work or study type scene, determine that the target assistance information type includes a fill-in-the-blank question information type; and when generating the question assistance information matching the target scene according to the target assistance information type, the processing module is configured to: generate at least one to-be-filled sentence matching the target scene according to the fill-in-the-blank question information type, the to-be-filled sentence containing first to-be-filled field information; the first to-be-filled field information is used to indicate that the empty content in the to-be-filled sentence is to be supplemented; and the to-be-filled sentence generates the target question information after the empty content is supplemented.

[0019] In an alternative implementation, when determining the target assistance information type from a plurality of assistance information types based on a scene type of the target scene, the processing module is configured to: in response to the target scene belonging to a third scene type, the third scene type including a document type scene, determine that the target assistance information type includes a form question information type; and when generating the question assistance information matching the target scene according to the target assistance information type, the processing module is configured to: generate a form matching the target scene according to the form question information type, the form including a plurality of second to-be-filled field information; the second to-be-filled field information is used to indicate that the selection or input of field information is to be performed for a specified field; and the filled form information is used to generate the target question information according to a preset format.

[0020] In an optional implementation, the first display module is configured to display a plurality of question dimensions corresponding to the target scene, and display the matched to-be-filled field information under the question dimensions, when displaying the question auxiliary information matched with the target scene.

[0021] In an optional implementation, the processing module is configured to determine that the target auxiliary information type includes a predicted question information type, in response to the target scene belonging to a fourth scene type, the fourth scene type including a scene in which a user actively inputs partial question information, when determining the target auxiliary information type from a plurality of auxiliary information types based on a scene type of the target scene; and the processing module is configured to perform intent recognition on the partial question information to generate a plurality of candidate question information, when generating the question auxiliary information matched with the target scene according to the target auxiliary information type; and the selected question information in the candidate question information is used as the question auxiliary information.

[0022] In an optional implementation, the plurality of candidate question information is generated according to the following manner: obtaining historical search data associated with the partial question information; performing search link clustering on the historical search data to determine historical search data corresponding to a same search link; the search link including a plurality of continuous search records, the plurality of continuous search records including a continuous subsequent search performed after an initial search; and generating candidate question information corresponding to the search link based on the historical search data of each search link.

[0023] In a third aspect, an optional implementation of the present disclosure further provides a computer device, a processor and a memory, the memory stores machine readable instructions executable by the processor, and the processor is configured to execute the machine readable instructions stored in the memory, and the machine readable instructions are executed by the processor to execute the steps of the first aspect or any possible implementation manner of the first aspect.

[0024] In a fourth aspect, an optional implementation of the present disclosure further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed to execute the steps of the first aspect or any possible implementation manner of the first aspect.

[0025] The question and answer method, device, computer device and storage medium provided by the embodiments of the present disclosure can show the user with question-asking auxiliary information matched with the target scene according to the target scene in which the user initiates the question-asking; here, the information format and / or information completeness of the question-asking auxiliary information provided for different scene types are different, so that the question-asking auxiliary information with different information format and / or information completeness can be provided according to the requirements of the scene type, to better assist the user in editing the target question information. In this way, when the user has the demand of asking questions to the artificial intelligence model, the question-asking auxiliary information matched with the current scene requirement can be shown to the user to help the user quickly organize the target question information meeting the requirement, so that the artificial intelligence model can give the answer result meeting the user's requirement better based on the relatively perfect target question information.

[0026] In order to make the above objectives, characteristics and advantages of the present disclosure more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described in detail as follows. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly introduce the drawings needed to be used in the embodiments. The drawings herein are incorporated into the specification and form a part of the specification, which show the embodiments consistent with the present disclosure, and are used to illustrate the technical solutions of the present disclosure together with the specification. It should be understood that the following drawings only show some embodiments of the present disclosure, and therefore should not be considered as a limitation to the scope, and other related drawings can also be obtained by those skilled in the art without creative labor.

[0028] Figure 1 A flowchart of a question and answer method provided by the embodiments of the present disclosure is shown;

[0029] Figure 2 A schematic diagram of an artificial intelligence answer page provided by the embodiments of the present disclosure is shown;

[0030] Figure 3 A schematic diagram of the embodiments of the present disclosure when showing question-asking auxiliary information under a first scene type is shown;

[0031] Figure 4 A schematic diagram of the embodiments of the present disclosure when showing question-asking auxiliary information under a second scene type is shown;

[0032] Figure 5 A schematic diagram of the embodiments of the present disclosure when showing question-asking auxiliary information under a third scene type is shown;

[0033] Figure 6A schematic diagram of the present disclosure is shown in the fourth scenario type under the display of the question auxiliary information;

[0034] Figure 7 A schematic diagram of the present disclosure is shown in the fourth scenario type under the display of the question auxiliary information;

[0035] Figure 8 A schematic diagram of the present disclosure is shown in the fourth scenario type under the display of the question auxiliary information. DETAILED DESCRIPTION

[0036] To make the objectives, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described below in connection with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure and not all the embodiments. The components of the embodiments of the present disclosure described and shown herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure is not intended to limit the scope of the claimed present disclosure, but only represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present disclosure.

[0037] It is found through research that, for a user, if an artificial intelligence model is to provide an answer that meets the actual needs of the user, the user needs to organize relatively complete question information according to the actual needs. However, in general, it is difficult for a user to organize complete and comprehensive question information, such as searching only through a few keywords. In this case, since the question information provided by the user is not complete enough, the artificial intelligence model cannot accurately identify the question intention of the user, and thus the answer provided to the user cannot meet the actual needs of the user.

[0038] Based on the above research, the embodiments of the present disclosure provide a question and answer method, which can display question auxiliary information matched with a target scenario to a user according to the target scenario in which the user initiates a question. Here, the information format and / or information completeness of the question auxiliary information provided for different scenario types are different, so that question auxiliary information with different information formats and / or information completeness can be provided according to the needs of the scenario types, to better assist the user in editing the target question information. In this way, when the user has a need to ask a question to an artificial intelligence model, the user can be shown question auxiliary information that matches the current scenario needs, to help the user quickly organize target question information that meets the needs, so that the artificial intelligence model can provide an answer that better meets the needs of the user based on the relatively complete target question information.

[0039] The above problems and solutions are the results of the inventors' practice and careful research, and therefore, the discovery process and the solutions proposed by the present disclosure to solve the above problems are the contributions of the inventors to the present disclosure.

[0040] It should be noted that similar reference numbers and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0041] To facilitate the understanding of the present embodiment, first, a question-answering method disclosed by the present embodiment is introduced in detail, and the execution subject of the question-answering method provided by the present embodiment is generally a computer device with certain computing capability, which includes, for example, a terminal device or a server or other processing device. The terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementation manners, the question-answering method can be realized by a processor calling computer-readable instructions stored in a memory.

[0042] The question-answering method provided by the present embodiment is described below. The question-answering method provided by the present embodiment can be specifically applied to a search platform or applied to an artificial intelligence platform alone. In the platform, in addition to querying existing searchable information, the platform can also create information meeting user needs according to target problem information edited by the user, such as creating an article, planning a schedule, checking whether an article has a grammatical error, making a resume and a document, etc.

[0043] Referring to FIG. 1, Figure 1 The question-answering method provided by the present embodiment is shown in a flowchart, and the method includes steps S101-S103, wherein:

[0044] S101: In response to a user initiating a question, determining a target scene of a question of the user;

[0045] S102: Displaying question-answering auxiliary information matching the target scene; wherein the information format and / or information completeness of the question-answering auxiliary information are related to the scene type of the target scene, and the question-answering auxiliary information is used to assist the user in editing target problem information for the question;

[0046] S103: In response to receiving the target problem information edited according to the question-answering auxiliary information, displaying an artificial intelligence answering result matching the target problem information.

[0047] For the above S101, when the user has a question demand, the answer result can be obtained through the above-mentioned platform in the form of a question. The specific search demand can be determined according to the actual demand of the user, such as for an engineer user A, the actual demand can be to obtain a project opening file of the project "environmental protection and energy saving element" through a question; or for a job seeker user B, the actual demand can be to generate a resume for a selected job; or for a user C who plans to travel, the actual demand can be a travel guide for a certain area, and so on.

[0048] In order to provide the user with an answer result that meets the user's question demand, the platform can provide an artificial intelligence answer page to the user, so that the user can initiate a question through relevant operations on the artificial intelligence answer page after entering the artificial intelligence answer page provided by the platform. Referring to Figure 2 , it is a schematic diagram of an artificial intelligence answer page provided by an embodiment of the present disclosure.

[0049] In the artificial intelligence answer page shown in Figure 2 , for example, an input box for inputting question information is provided in the middle area of Figure 2 , which prompts the user to enter specific questions here through "Please enter your question", and also provides a voice input function, and can also provide a photograph query function, so that the user can choose the appropriate way to input the question.

[0050] In the upper area of Figure 2 , the last question and answer result are displayed, such as the question "write an essay about spring" and the essay example below shown in the figure. If the user uses it for the first time and does not have a history of asking questions, other examples can also be displayed here to help the user understand how to get an answer result through the question information.

[0051] In the lower area of Figure 2 , a plurality of buttons are provided in the form of examples, and the buttons are labeled with text to prompt the user to provide specific question and answer functions, to help the user understand what kind of question and answer services can be provided on the platform. For example, for "weather conditions" shown in the figure, the user can easily know that after selecting, the weather conditions can be viewed, or for "weekly report generation" shown in the figure, the user can easily know that after selecting, it can be used to help organize learning weekly reports, work weekly reports, etc. When arranging these buttons corresponding to different functions, the user's historically selected buttons can be arranged in the front for display, and the hot functions and buttons corresponding to functions such as learning and teaching aids, work assistants, and encyclopedia organization can be classified and displayed.

[0052] That is, when the user asks questions through the artificial intelligence answering page, the user can select the buttons provided in the artificial intelligence answering page to ask questions under the corresponding functions, or can actively organize question information and ask questions.

[0053] Therefore, in the embodiments of the present disclosure, in response to the user initiating the question, when the target scene of the user's question is determined, the following methods can be used: multiple candidate scenes are displayed on the artificial intelligence answering page, and in response to the user's selection operation on the candidate scenes, the target scene of the user's question is determined; or at least part of the question information input by the user in the question input area of the artificial intelligence answering page is received, and the target scene matching the at least part of the question information is determined.

[0054] The following will be described in detail. First, the user can ask questions through the buttons provided in the artificial intelligence answering page, in which case the user is instructed to select a scene from the existing candidate scenes. For example, multiple candidate scenes are pre-displayed on the artificial intelligence answering page, and each candidate scene corresponds to a specific function, such as the "weather condition" displayed in the above example, which corresponds to the function of checking the weather, and the target scene of the user's question is the question scene for the weather condition.

[0055] Secondly, the user can input specific questions in the question input area of the artificial intelligence answering page, that is, after the user inputs the question, the target scene is determined by analyzing the question input by the user. For example, if the question information input by the user includes "find possible semantic errors in the following context: XX", the target scene determined by the user when asking the question can be determined by keywords such as "find" and "semantic error", for example, the target scene of this specific query syntax error.

[0056] In this way, in the embodiments of the present disclosure, when the target scene of the user's question is determined, if the user specifically selects from multiple candidate scenes, the target scene of the user's question is determined according to the selected candidate scene. Or, when the user asks questions by inputting at least part of the question information, the target scene needs to be determined by analyzing the question information.

[0057] For S102 described above, after the target scene of the user's question is determined, in order to help the user write complete and comprehensive target question information to get a more satisfactory artificial intelligence answering result for the user's question intention, in the embodiments of the present disclosure, the target scene type determined in the above step is also used to display question assistance information matching the target scene to the user.

[0058] Here, in the case of assisting the user in editing the target question information with the aid of the question assistance information, in a possible case, only simple text can be provided, such as only an example is provided. For example, in the case of needing to sort out the materials to obtain summary materials, the text information "I hope you can sort out the materials as a historian, and specifically sort out the development and changes of cultural, economic, and social events in history to obtain summary materials for historical research" can be displayed. It can be known that, since in the case of sorting out the materials to obtain the summary materials, there can be many academic fields, but it is not possible to display all possible cases under each academic field to the user, and therefore the above-mentioned one case is usually displayed to the user as an example in the case of asking questions.

[0059] However, in this case, the specific example displayed to the user can not be transferable, such as in the case where the user also needs to sort out the materials to obtain the summary materials, if the user needs to sort out the files related to electrical engineering and engineering mechanics, the focus can be on the iteration of technology, and therefore after referring to the "development and changes of cultural, economic, and social events" in the above-mentioned example, the user can not be able to obtain appropriate question information by simply replacing the text. Therefore, in some cases, the above-mentioned way of explicitly giving a specific example can not assist the user in editing the target question information that meets the user's own question needs, because the provided example is too specific and bottom-level, and therefore it is difficult to have universality.

[0060] In addition, in this way, even if the user wants to replace part of the content in the example to obtain the target question information under his own needs, he needs to copy and paste it to the question input area of the artificial intelligence answer page first, and then select the words that need to be replaced to delete them, and then enter the information that can be filled in under his own question needs to ask questions. This operation method is not convenient for the user.

[0061] Therefore, in the embodiments of the present disclosure, the question assistance information matched with the target scene is determined by the following way: determining a target assistance information type from a plurality of assistance information types based on a scene type of the target scene; different assistance information types correspond to different information formats and / or information completeness; and generating question assistance information matched with the target scene according to the target assistance information type.

[0062] Specifically, the question assistance information provided to the user is different under different scene types. For example, for the scene of making legal documents, the question assistance information provided can be specifically the format under the document style, such as the contract format, and the fixed format clauses therein are displayed, and the information to be filled in by the user is left blank. For the scene of inquiring about the weather, since the range of the question is already limited, a plurality of exact question sentences can be provided, such as “the temperature and humidity and ultraviolet intensity of today's weather”, “the temperature change of today” and the like.

[0063] That is, for different scene types under different target scenes, the question assistance information that can be specifically provided is different, and this difference is not only reflected in the difference in textual expression information, but also reflected in the difference in information format and / or information completeness. In addition, before providing the question assistance information to the user, a plurality of auxiliary information types can be determined in advance, such as the above-mentioned examples, the contract template for generating documents, the lawsuit template, and the like, the fill-in-the-blank type question type, or the plurality of possible questions for the weather, and the like, the complete type question information type. After determining the scene type of the target scene, the target auxiliary information type can be matched from the plurality of auxiliary information types, and the question assistance information matched with the target scene can be generated accordingly.

[0064] Next, by taking examples of different scene types, how to determine the target auxiliary information type according to the scene type, and generate the question assistance information matched with the target scene accordingly will be described.

[0065] (1) The target scene belongs to the first scene type. The first scene type includes a scene type that does not need to supplement personalized information.

[0066] For example, for the above-mentioned question about the weather condition, since the specific question range has been determined, it belongs to the scene type that does not need to supplement personalized information. In addition to the above-mentioned weather condition, the first scene type can also include the scene type of asking about the school for further study, the occupation for employment, and the like.

[0067] In this kind of scene, it can be determined that the target auxiliary information type includes the complete type question information type. The characteristic of this complete type question information type is that there is a certain and complete question information.

[0068] Correspondingly, when generating the question assistance information matched with the target scene according to the target auxiliary information type, the following way can be adopted: based on the scene information of the target scene, generating an editable complete type question information matched with the target scene, which is used as the question assistance information.

[0069] For example, for the above-mentioned scenario of asking about the weather condition, the complete question information that can be provided can specifically include "temperature change in each hour today", "UV index today", "weather change in the past seven days", and the like. Since "weather condition" has already made a relatively clear limitation on the range that can be asked, when providing the question assistance information, the user can be directly provided with a plurality of complete question information that can be possible around the range, so that the user can directly select the appropriate complete question information according to the question intention. In addition, the provided complete question information is also specifically editable, and the user can directly perform text editing on the provided information to obtain the target question information for asking.

[0070] For example, referring to Figure 3 Fig. 1 shows a schematic diagram of the embodiment of the present disclosure for displaying question assistance information in the first scenario type. In the schematic diagram, in response to the trigger operation of "weather condition" in the page shown by the left arrow, for example, the page shown by the right arrow in Fig. 2 can be displayed. Figure 3 In the page indicated by the right arrow in Fig. 2, a plurality of editable complete question information is specifically displayed, and in response to the trigger operation of any complete question information, the complete question information can be displayed in the question input area. For example, selecting "weather change in the past seven days" in the question input area will correspondingly display the question information, and the selection state will be changed accordingly. Figure 3 In the page indicated by the right arrow in Fig. 2, a plurality of editable complete question information is specifically displayed, and in response to the trigger operation of any complete question information, the complete question information can be displayed in the question input area. For example, selecting "weather change in the past seven days" in the question input area will correspondingly display the question information, and the selection state will be changed accordingly. Figure 3 In the page indicated by the right arrow in Fig. 2, a plurality of editable complete question information is specifically displayed, and in response to the trigger operation of any complete question information, the complete question information can be displayed in the question input area. For example, selecting "weather change in the past seven days" in the question input area will correspondingly display the question information, and the selection state will be changed accordingly.

[0071] After displaying the question information in the question input area, the user can also edit it through editing operation, for example, in the question input area shown in the page indicated by the right arrow in Fig. 3, the selected "weather change in the past seven days" is edited to "weather change in the past three days" as the target question information. Figure 3 After displaying the question information in the question input area, the user can also edit it through editing operation, for example, in the question input area shown in the page indicated by the right arrow in Fig. 3, the selected "weather change in the past seven days" is edited to "weather change in the past three days" as the target question information.

[0072] (2) The target scenario belongs to the second scenario type. The second scenario type includes work and study scenarios.

[0073] For example, for the requirement of work arrangement, when arranging the work content in the work category, there are fixed requirements of work nature, such as different positions have specific requirements for the report format when making work reports, but also have different selected ranges of report content, such as different R&D departments have different project contents when making reports.

[0074] Therefore, in this scenario, it can be determined that the target assistance type includes the fill-in-the-blank question type information. Here, for the specific requirements in the report format mentioned above, the sentence containing the filling position can be determined, and the selected project content can be used as the filling information of the sentence.

[0075] Thus, when generating question assistance information matching the target scenario according to the target assistance information type, the following method can be adopted: according to the fill-in-the-blank question information type, generate at least one statement to be filled that matches the target scenario, wherein the statement to be filled contains a first field to be filled; the first field to be filled is used to indicate that the empty content in the statement to be filled should be supplemented; the target question information is generated after the empty content in the statement to be filled is supplemented.

[0076] Here, we will use the work report scenario described above as an example for illustration. See [link / reference] Figure 4 The diagram shown illustrates a scenario where auxiliary information for asking questions is displayed in a second scenario, according to an embodiment of this disclosure. Figure 4 In section (a), the first step is to display multiple question dimensions that can be selected under the work report through various tags, specifically including "Project Proposal Report," "Mid-term Progress Report," and "Project Summary." Taking "Project Proposal Report" as an example, the following can be generated: Figure 4 The statement to be filled in shown in (a) contains multiple pieces of information to be filled in, including the statement "The name of this project is" and "My job is". For example, after "The name of this project is", you can fill in the specific project name, such as "energy-saving and environmental protection equipment". After "My job is", you can fill in the specific job content according to the job you are responsible for in this project, such as "coordinating and managing the progress of various departments".

[0077] In this embodiment of the disclosure, the first field information to be filled is used to indicate the filling of empty content in the statement to be filled, for example, the above. Figure 4 In section (a), the first field to be filled includes information such as "Project Name" and "Task Content." After filling in the empty content of the statement to be filled, the target question information can be generated. In the actual display, the defined text portion of the statement to be filled is displayed directly, while the empty content is displayed as a text box, with a "Click to Enter" prompt for the user to fill it in. See [link to details] for more information. Figure 4 The example diagram shown in (b) allows for the completion of the target problem information by filling in specific project names such as "energy-saving and environmental protection equipment" and work content such as "coordinating and managing the progress of various departments," which means supplementing the blank content.

[0078] (3) The target scenario belongs to the third scenario type. The third scenario type includes document scenarios.

[0079] For example, when drafting contracts or pleadings, which involve legal documents, it's important to consider that these documents typically include information about both parties, the grounds for the lawsuit, and other standard clauses. Therefore, when assisting users in drafting legal documents, the system can provide the necessary information by allowing them to input the agreed-upon terms, grounds for the lawsuit, and other relevant details.

[0080] Specifically, since the information items required for user input in legal documents are usually standardized and may include many categories, forms can be provided to users to help them fill in the information in an organized manner. In this type of scenario, the target auxiliary information type can be identified as form-based question information.

[0081] In specific implementation, when generating question assistance information matching the target scenario according to the target assistance information type, the following method can be adopted: generate a form matching the target scenario according to the form-type question information type, the form including multiple second fields to be filled; the second fields to be filled are used to indicate the selection or input of field information for a specified field; the filled form information is used to generate the target question information according to a preset format.

[0082] For example, see Figure 5 The diagram shown is a schematic representation of displaying question-answering assistance information in a third scenario type, according to an embodiment of this disclosure. Figure 5 (a) The form displays multiple question dimensions, primarily including document type. The required information varies depending on the document type. For example, selecting the "debt" document type involves details such as the debt type and claim shown below. Similarly, selecting the "contract dispute" document type (not shown) involves details such as the subject matter and contract stipulations. These additional dimensions, displayed after selecting a document type, can also be called question dimensions. These multiple question dimensions corresponding to the target scenario can be directly determined or adaptively adjusted or selected after the user makes certain choices.

[0083] As for the information to be filled in the form under multiple question dimensions, it can be entered by typing or selected.

[0084] Among them, for the part of the corresponding filled information under the displayed multiple problem dimensions, it specifically corresponds to the second to-be-filled field in the form, such as the document type in the form; specifically for the specified field that should be filled in under the problem dimension, selection and input are performed. After supplementing the field information under these problem dimensions shown in the figure, the corresponding target problem information can be generated. Specifically, in Figure 5 The schematic diagram corresponding to the form filled by the user in (b) is shown.

[0085] Here, for the two different target scenarios corresponding to "2" and "3" above, according to the above description, when the question assistance information matching the target scenario is displayed, the multiple problem dimensions corresponding to the target scenario are displayed, and the matching to-be-filled field information is displayed under the problem dimensions. Specifically, under the target scenario of the second scenario type, the dimensions of "project initiation" and "interim progress report" are displayed, and under the target scenario of the third scenario type, the dimensions of "document type" and "arrears type" and "litigation request" are displayed based on the selection of the document type. Under each dimension, the matching to-be-filled field information is displayed through selection or input, and after filling in the to-be-filled field information, the target problem information can be generated.

[0086] (4) The target scenario belongs to the fourth scenario type. The third scenario type includes a scenario in which the user actively inputs part of the problem information.

[0087] For example, for the above-mentioned scenarios displayed through buttons or labels, within the scope of artificial intelligence that can complete question and answer, only a small part of commonly used or user's usual use is actually displayed. If the user has other question requirements, some keywords, sentences, etc. for predicting or constructing problem information can also be actively input. Accordingly, it can be determined that the target assistance information type includes the predicted problem information type.

[0088] Taking travel planning as an example, if multiple possible travel scenarios are listed similarly to those in the other scenarios mentioned above, along with dimensions such as time, number of travelers, and travel budget, the corresponding methods used in those scenarios can be used to provide users with supplementary information for their questions. However, in this scenario, the listed time, number of travelers, etc., may not be the information that users necessarily need when asking about travel planning. Alternatively, because the theme of travel may not involve specific, definitive dimensions, users might focus on items to bring during the trip, or rest stops to consider when driving, in addition to the time and budget dimensions listed above. Therefore, in this type of scenario, it is more appropriate to receive a portion of the question information proactively entered by the user, perform intent recognition based on this information, predict possible questions, and use this as supplementary information that the user can choose from.

[0089] That is, in specific implementation, when generating questioning assistance information matching the target scenario according to the target assistance information type, the following method can be adopted: perform intent recognition on the partial question information to generate multiple predicted candidate question information; the selected question information among the candidate question information is used as the questioning assistance information.

[0090] For example, see Figure 6 The diagram shown is a schematic representation of displaying question-answering assistance information in a fourth scenario type, according to an embodiment of this disclosure. Figure 6 In (a), users can type their questions in the input box, such as "I want to go to Shanghai for fun". Next to the semantic input icon on the right side of the input box, there is also a suggestion button.

[0091] In response to triggering the Lenovo button, you can jump to... Figure 6 On page (b), multiple candidate questions predicted based on the entered question are displayed below the input box. The number of candidate questions, such as "5", is also displayed in the upper right corner of the suggestion button. If the user does not select a suitable question from the three currently displayed candidate questions, they can view the remaining candidate questions (not shown) by swiping up or down, and / or treat the swiping up or down operation as an update operation, updating and displaying other relevant candidate question information based on the user's entered question information.

[0092] From the user Figure 6 If one candidate question is selected in (b), for example, if a second candidate question is selected, then the process can jump to... Figure 6In the page of (c), the selected candidate question information is displayed to replace the information input by the user in the text box, and the input keyboard is popped up accordingly to input the selected question information as the question assistance information, so that the user can obtain the target question information through direct search or modification based on the input information.

[0093] Here, in a possible case, the candidate question information displayed below changes as the user input information is continuously expanded. The trigger for the change can be the reception of new user input information or the user actively triggering the association button after inputting new information. For example, in the page shown in (b), if the user continues to input "3 days and 4 nights" based on the input "I want to go to Shanghai", the candidate question information displayed below can be updated to "Plan a 3-day and 4-night city tour in Shanghai, take parents, and do not go to Disneyland" from "Plan a 5-day and 6-night city tour in Shanghai, take parents, and do not go to Disneyland". Figure 6

[0094] In addition, in determining the candidate question information, in a possible case, the user gradually inputs information in this question to determine the candidate question information, and the candidate question information displayed to the user can also be determined based on the historical question information authorized by the user to obtain, or by referring to the question selection information of other users under the same theme.

[0095] In specific implementation, historical search data associated with the part of question information can be obtained; the historical search data is clustered according to search links to determine historical search data corresponding to the same search link; the search link includes multiple continuous search records, and the multiple continuous search records include continuous supplementary search after initiating initial search; based on the historical search data of each search link, candidate question information corresponding to the search link is generated.

[0096] The above three possible examples are used for illustration. For the case where the user gradually inputs information in this question, for example, the first input information includes "Shanghai tourism", the second supplementary information is "3 days and 4 nights", and the third supplementary information is "1,000 yuan". These input information can form a search link and serve as historical data under the search link. Based on the above input information, candidate question information corresponding to the search link can be generated.

[0097] ​For the case that the user authorizes the obtainable history question information, still taking the example that the user inputs "Shanghai travel" in this time question as an example, if the user authorizes the obtainable history question information to include the records related to "Shanghai" or "travel", such as "Shanghai Disneyland" or "short trip", the related information mentioned in these records can also be taken as the continuous next supplementary search after the initial search of "Shanghai travel", and "Shanghai travel", "Shanghai Disneyland" and "short trip" are clustered into the same search link, and each history search data under the search link is obtained to generate the candidate question information corresponding to the search link, such as "formulating the plan of Shanghai travel, including going to Shanghai Disneyland, and the trip is expected to be short".

[0098] For the case that the user authorizes the obtainable history question information, still taking the example that the user inputs "Shanghai travel" in this time question as an example, if the user authorizes the obtainable history question information to include the records related to "Shanghai" or "travel", such as "Shanghai Disneyland" or "short trip", the related information mentioned in these records can also be taken as the continuous next supplementary search after the initial search of "Shanghai travel", and "Shanghai travel", "Shanghai Disneyland" and "short trip" are clustered into the same search link, and each history search data under the search link is obtained to generate the candidate question information corresponding to the search link, such as "formulating the plan of Shanghai travel, including going to Shanghai Disneyland, and the trip is expected to be short".

[0099] Here, the above three ways of determining the candidate question information can be selected and used, and the combination is not limited in the embodiment of the present disclosure. For the provided candidate question information, the user can select it as the question auxiliary information, and directly as the target question information, or edit and modify to obtain the target question information, which is not limited in the embodiment of the present disclosure.

[0100] In this way, according to the above steps, the user can be shown the question auxiliary information matched with the target scene.

[0101] For the above S103, the user can also edit the displayed question auxiliary information to obtain the target question information. For example, in the above Figure 4 、 Figure 5 corresponding scene, the user can supplement the question auxiliary information to obtain the target question information. Or, the user can directly obtain the target question information by selecting the question auxiliary information, such as for the scene shown in the above Figure 3 or Figure 6 , the question auxiliary information can be directly taken as the target question information.

[0102] In the case of determining the target question information, the platform can process the target question information by using the related technology of artificial intelligence to obtain an artificial intelligence answer result matched with the target question information. After the artificial intelligence answer result is displayed, the user can copy, for example, the right lower corner of the composition about spring shown in the upper part of Figure 2 In the above example, the user can also directly obtain the completed file by downloading. In addition, the function of "regeneration" can be provided to obtain other possible answers under the target question information. The specific implementation can be determined according to the actual processing of the artificial intelligence and the specific question demand of the user, and will not be repeated here.

[0103] Those skilled in the art can understand that in the above method of the specific implementation, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined according to its function and possible internal logic.

[0104] Based on the same inventive concept, the disclosure embodiments also provide a question and answer method corresponding to the question and answer method. Since the principle of solving problems in the device of the disclosure embodiments is similar to the above question and answer method of the disclosure embodiments, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be repeated.

[0105] Referring to Figure 7 FIG. 1 shows a schematic diagram of a question and answer device provided by the disclosure embodiments, the device includes a determination module 71, a first display module 72, and a second display module 73; wherein

[0106] The determination module 71 is configured to determine a target scene of a user's question in response to the user initiating the question.

[0107] The first display module 72 is configured to display question auxiliary information matched with the target scene; wherein the information format and / or information completeness of the question auxiliary information is related to the scene type of the target scene, and the question auxiliary information is used to assist the user in editing target question information for the question.

[0108] The second display module 73 is configured to display an artificial intelligence answer result matched with the target question information in response to receiving the target question information edited based on the question auxiliary information.

[0109] In an optional implementation, the determining module 71, in response to the user initiating the question, is configured to determine the target scene of the user question in the following manner: displaying multiple candidate scenes on an artificial intelligence answering page, and determining the target scene of the user question in response to a selection operation of the user on the candidate scenes; or receiving at least partial question information input by the user in a question input area on the artificial intelligence answering page, and determining a target scene matching the at least partial question information.

[0110] In an optional implementation, the device further includes a processing module 74, and the question assistance information matching the target scene is determined by the processing module 74 in the following manner: determining a target assistance information type from multiple assistance information types based on a scene type of the target scene; different assistance information types correspond to different information formats and / or information completeness; and generating the question assistance information matching the target scene according to the target assistance information type.

[0111] In an optional implementation, when the processing module 74 determines the target assistance information type from the multiple assistance information types based on the scene type of the target scene, the processing module 74 is configured to: in response to the target scene belonging to a first scene type, the first scene type including a scene type that does not require supplementary personalized information, determine that the target assistance information type includes a complete question information type; and when the processing module 74 generates the question assistance information matching the target scene according to the target assistance information type, the processing module 74 is configured to: generate editable complete question information matching the target scene based on scene information of the target scene, and use the editable complete question information as the question assistance information.

[0112] In an optional implementation, when the processing module 74 determines the target assistance information type from the multiple assistance information types based on the scene type of the target scene, the processing module 74 is configured to: in response to the target scene belonging to a second scene type, the second scene type including a work-study scene type, determine that the target assistance information type includes a fill-in-the-blank question information type; and when the processing module 74 generates the question assistance information matching the target scene according to the target assistance information type, the processing module 74 is configured to: generate at least one to-be-filled sentence matching the target scene according to the fill-in-the-blank question information type, the to-be-filled sentence including first to-be-filled field information; the first to-be-filled field information is used to indicate that the to-be-filled sentence is to be supplemented with blank content; and the to-be-filled sentence generates the target question information after the blank content is supplemented.

[0113] In an optional implementation, when the processing module 74 determines the target auxiliary information type from the plurality of auxiliary information types based on the scene type of the target scene, the processing module 74 is configured to: in response to the target scene belonging to a third scene type, the third scene type including a document type scene, determine that the target auxiliary information type includes a form type question information type; and when the processing module 74 generates the question auxiliary information matching the target scene according to the target auxiliary information type, the processing module 74 is configured to: generate a form matching the target scene according to the form type question information type, the form including a plurality of second to-be-filled field information; and the second to-be-filled field information is used to indicate selection or input of field information for a specified field; and the filled form information is used to generate the target question information according to a preset format.

[0114] In an optional implementation, when the first display module 72 displays the question auxiliary information matching the target scene, the first display module 72 is configured to: display a plurality of question dimensions corresponding to the target scene, and display the matching to-be-filled field information under the question dimensions.

[0115] In an optional implementation, when the processing module 74 determines the target auxiliary information type from the plurality of auxiliary information types based on the scene type of the target scene, the processing module 74 is configured to: in response to the target scene belonging to a fourth scene type, the fourth scene type including a scene in which a user actively inputs part of question information, determine that the target auxiliary information type includes a prediction type question information type; and when the processing module 74 generates the question auxiliary information matching the target scene according to the target auxiliary information type, the processing module 74 is configured to: perform intent recognition on the part of question information to generate a plurality of candidate question information; and the selected question information in the candidate question information is used as the question auxiliary information.

[0116] In an optional implementation, the plurality of candidate question information is generated in the following manner: historical search data associated with the part of question information is obtained; each historical search data corresponding to a same search link is determined by performing search link clustering on the historical search data; the search link includes a plurality of continuous search records, and the plurality of continuous search records include a continuous subsequent search performed after an initial search is initiated; and the candidate question information corresponding to the search link is generated based on each historical search data of the search link.

[0117] The processing procedure of each module in the apparatus and the interaction procedure between the modules can refer to the related description in the method embodiments, and will not be described in detail here.

[0118] The present disclosure also provides a computer device, which can include the apparatus. Figure 8As shown, a computer device structure schematic diagram provided by the embodiment of the present disclosure includes:

[0119] The processor 10 and the memory 20; the memory 20 stores machine readable instructions executable by the processor 10, and the processor 10 is configured to execute the machine readable instructions stored in the memory 20, and when the machine readable instructions are executed by the processor 10, the processor 10 executes the following steps:

[0120] In response to the user initiating the question, the target scene of the user's question is determined; the question auxiliary information matched with the target scene is displayed; wherein the information format and / or information completeness of the question auxiliary information are related to the scene type of the target scene, and the question auxiliary information is used to assist the user in editing the target question information for the question; in response to receiving the target question information edited according to the question auxiliary information, the artificial intelligence answer result matched with the target question information is displayed.

[0121] The above-mentioned memory 20 includes the memory 210 and the external memory 220; the memory 210 is also called the internal memory, and is used to temporarily store the operation data in the processor 10 and the data exchanged with the external memory 220 such as a hard disk, and the processor 10 exchanges data with the external memory 220 through the memory 210.

[0122] The specific execution process of the above-mentioned instructions can refer to the steps of the question and answer method described in the embodiment of the present disclosure, which will not be described here.

[0123] The embodiment of the present disclosure also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by the processor to execute the steps of the question and answer method described in the above method embodiment. Wherein, the storage medium can be a volatile or non-volatile computer readable storage medium.

[0124] The embodiment of the present disclosure also provides a computer program product, and the computer program product carries a program code, and the instructions included in the program code can be used to execute the steps of the question and answer method described in the above method embodiment, and the specific steps can be referred to in the above method embodiment, which will not be described here.

[0125] Wherein, the above-mentioned computer program product can be specifically realized by hardware, software or combination thereof. In one optional embodiment, the computer program product is specifically embodied as a computer storage medium, and in another optional embodiment, the computer program product is specifically embodied as a software product, such as software development kit (Software Development Kit, SDK) and the like.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here. In several embodiments provided in the present disclosure, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and another division can be made in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices or units, and can be electrical, mechanical or other forms.

[0127] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., they can be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0128] In addition, the functional units in each embodiment of the present disclosure can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0129] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present disclosure essentially or the part of the prior art or the part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the various embodiments of the present disclosure. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program codes that can be stored in the medium.

[0130] Finally, it should be noted that the above-described embodiments are merely specific embodiments of the present disclosure, used to illustrate the technical solutions of the present disclosure, and are not intended to limit the present disclosure. The protection scope of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can make modifications or easy changes to the technical solutions described in the foregoing embodiments, or easily think of changes or equivalent replacements for some of the technical features; and these modifications, changes or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A question and answer method, characterized by, The method comprises the following steps: in response to a user initiating a question to an artificial intelligence model through an artificial intelligence answering page, determining a target scene of the user's question; displaying question assistance information matching the target scene; wherein the information format and / or information completeness of the question assistance information is related to the scene type of the target scene, the question assistance information is used to assist the user in editing target question information for the question, and the question assistance information matches the scene requirement of the target scene, so as to provide question assistance information with different expression information, different information format and / or different information completeness for different scene types; in response to receiving target question information obtained by the user editing the question assistance information, displaying an artificial intelligence answering result fed back by the artificial intelligence model matching the target question information; wherein the question assistance information matching the target scene is determined in the following manner: based on the scene type of the target scene, determining a target assistance information type from a plurality of assistance information types; different assistance information types correspond to different information formats and / or information completeness; generating question assistance information matching the target scene according to the target assistance information type.

2. The method of claim 1, wherein, in response to a user initiating a question, determining a target scene of the user's question, comprising: displaying a plurality of candidate scenes on an artificial intelligence answering page, and in response to a user selection operation on the candidate scenes, determining a target scene of the user's question; or receiving at least part of the question information input by the user in the question input area of the artificial intelligence answering page, and determining a target scene matching the at least part of the question information.

3. The method of claim 1, wherein, The method comprises the following steps: in response to the target scene belonging to a first scene type, the first scene type including a scene type that does not require supplementary personalized information, determining that the target assistance information type includes a complete question information type; based on the scene information of the target scene, generating editable complete question information matching the target scene, which is used as the question assistance information. in response to the target scene belonging to a second scene type, the second scene type including a work and study type scene, determining that the target assistance information type includes a fill-in-the-blank question information type; 4. The method of claim 1, wherein, generating at least one to-be-filled sentence matching the target scene according to the fill-in-the-blank question information type, the to-be-filled sentence containing first to-be-filled field information; the first to-be-filled field information is used to indicate that the empty content in the to-be-filled sentence is supplemented; and the to-be-filled sentence generates the target question information after the empty content is supplemented. ​ ​ ​ 5. The method of claim 1, wherein, determining a target auxiliary information type from a plurality of auxiliary information types based on a scene type of the target scene, including: in response to the target scene belonging to a third scene type, the third scene type including a document type scene, determining the target auxiliary information type to include a form type question information type; generating, according to the target auxiliary information type, the question auxiliary information matched with the target scene, including: generating, according to the form type question information type, a form matched with the target scene, the form including a plurality of second to-be-filled field information; the second to-be-filled field information is used to indicate selection or input of field information for a specified field; and filled form information is used to generate the target question information according to a preset format.

6. The method according to claim 4 or 5, characterized in that, displaying the question auxiliary information matched with the target scene, including: displaying a plurality of question dimensions corresponding to the target scene, and displaying the matched to-be-filled field information under the question dimensions.

7. The method of claim 1, wherein, determining a target auxiliary information type from a plurality of auxiliary information types based on a scene type of the target scene, including: in response to the target scene belonging to a fourth scene type, the fourth scene type including a scene in which a user actively inputs part of question information, determining the target auxiliary information type to include a prediction type question information type; generating, according to the target auxiliary information type, the question auxiliary information matched with the target scene, including: performing intent recognition on the part of question information to generate a plurality of candidate question information; and selected question information in the candidate question information is used as the question auxiliary information.

8. The method of claim 7, wherein, the plurality of candidate question information is generated according to the following manner: obtaining historical search data associated with the part of question information; performing search link clustering on the historical search data to determine historical search data corresponding to a same search link; the search link includes a plurality of continuous search records, and the plurality of continuous search records include a continuous supplementary search performed after an initial search is initiated; generating candidate question information corresponding to each search link based on historical search data of each search link.

9. A question answering apparatus characterized by comprising: including: a determination module configured to determine a target scene of a user question in response to the user initiating the question to an artificial intelligence model through an artificial intelligence answering page; a first display module configured to display question auxiliary information matched with the target scene; wherein an information format and / or an information completeness of the question auxiliary information is related to a scene type of the target scene, the question auxiliary information is used to assist a user in editing target question information for the question, and the question auxiliary information is matched with a scene requirement of the target scene to provide question auxiliary information with different expression information and different information format and / or information completeness for different scene types; a second display module configured to display an artificial intelligence answering result fed back by the artificial intelligence model in response to receiving target question information obtained by the user editing the question auxiliary information; wherein the question auxiliary information matched with the target scene is determined according to the following manner: determine a target auxiliary information type from a plurality of auxiliary information types based on a scene type of the target scene, wherein different auxiliary information types correspond to different information formats and / or information completeness; generate question auxiliary information matching the target scene according to the target auxiliary information type.

10. A computer device, comprising: The method comprises the following steps: a processor and a memory, wherein the memory stores machine readable instructions executable by the processor, and the processor is configured to execute the machine readable instructions stored in the memory, and the machine readable instructions, when executed by the processor, cause the processor to perform the steps of the question and answer method according to any one of claims 1 to 8.

11. A computer readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program, when executed by a computer device, causes the computer device to perform the steps of the question and answer method according to any one of claims 1 to 8.

Images