Question-answering method, question-answering model construction method, electronic device and storage medium

Abstract

The present invention discloses a question-answering method, a question-answering model construction method, an electronic device and a storage medium. In the question-answering method, user question information is obtained; based on the question-answering model, an answer corresponding to the user question information is determined; wherein the question-answering model is constructed based on a question-answering material table, the question-answering material table includes at least one header tag attribute, each of the header attribute tags has at least one corresponding attribute data, and each of the header tag attributes has corresponding question-answering annotation information, the question-answering annotation information includes question annotation information or answer annotation information. Thus, the rapid construction of a question-answering model based on a table document is realized, and the constructed question-answering model can realize accurate responses to aggregate calculation type questions.

Description

Technical Field

[0001] The present invention belongs to the field of Internet technology, and in particular relates to a question-answering method, a question-answering model building method, an electronic device and a storage medium. Background Art

[0002] Today, artificial intelligence is developing rapidly. The AI ​​field can conduct in-depth mining based on the massive data provided by users, and provide users with knowledge questions and answers through various technologies such as knowledge query, reasoning, reverse reasoning, and algorithms. Currently supported technologies include: QA question-answer pairs, knowledge graphs, etc., which provide users with multi-domain, fine-grained knowledge questions and answers.

[0003] After users upload domain-level raw data, the underlying engine technology generally goes through the stages of knowledge construction, knowledge acquisition, knowledge fusion, knowledge reasoning, and knowledge application, and answers users’ questions after being processed by the engine. However, the current engine’s question-answering function is relatively weak, and the construction operation is cumbersome.

[0004] In addition, the question-answering technology on the market generally obtains answers based on text similarity algorithms, keyword algorithms, or deep correlation analysis of knowledge graphs, but does not support question types such as "aggregation", "check data trends", "statistics by attributes", etc., such as "How many employees does a company have?", "Balance of in-vehicle visits", and "Analysis of visits by province".

[0005] In view of the above problems, the industry has not yet provided a better solution. Summary of the invention

[0006] Embodiments of the present invention provide a question-answering method, a question-answering model building method, an electronic device, and a storage medium, which are used to solve at least one of the above-mentioned technical problems.

[0007] In a first aspect, an embodiment of the present invention provides a question-and-answer method, comprising: obtaining user question information; determining an answer corresponding to the user question information based on a question-and-answer model; wherein the question-and-answer model is constructed based on a question-and-answer material table, the question-and-answer material table comprises at least one header tag attribute, each of the header attribute tags respectively has at least one corresponding attribute data, and each of the header tag attributes respectively has corresponding question-and-answer annotation information, the question-and-answer annotation information comprises question annotation information or answer annotation information.

[0008] In a second aspect, an embodiment of the present invention provides a method for constructing a question and answer model, comprising: determining at least one header tag attribute and corresponding attribute data in an initial material table; obtaining question and answer annotation information for each of the header tag attributes; wherein the question and answer annotation information includes question annotation information or answer annotation information; determining a question and answer material table based on each corresponding header tag attribute, the question and answer annotation information and the attribute data; and constructing a question and answer model based on the question and answer material table.

[0009] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the above method.

[0010] In a fourth aspect, an embodiment of the present invention provides a storage medium, in which one or more programs including execution instructions are stored. The execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to execute the steps of the above-mentioned method of the present invention.

[0011] In a fifth aspect, an embodiment of the present invention further provides a computer program product, wherein the computer program product comprises a computer program stored on a storage medium, wherein the computer program comprises program instructions, and when the program instructions are executed by a computer, the computer executes the steps of the above method.

[0012] The beneficial effects of the embodiments of the present invention are:

[0013] The question-answering model built based on the question-answering material table can better achieve accurate answers to questions about different header attributes raised by users, and can accurately respond to aggregate calculation questions such as "aggregation type", "check data trends", and "statistics by attribute". In addition, developers only need to mark the corresponding questions or answers for each header label attribute in the initial material table to train and build the corresponding question-answering model, which reduces the difficulty of developing the question-answering model. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1A flowchart of an example of a question-answering method according to an embodiment of the present invention is shown;

[0016] Figure 2 A flowchart showing an example of a method for constructing a question-answering model according to an embodiment of the present invention is shown;

[0017] Figure 3 A flowchart showing an example of a method for constructing a question-answering model according to an embodiment of the present invention is shown;

[0018] Figure 4 A schematic diagram showing an example of an initial material table according to an embodiment of the present invention;

[0019] Figure 5 A schematic diagram showing a display interface of an electronic device after the table is imported;

[0020] Figure 6 A flow chart of training, publishing, production and consumption for a question-answering model according to an embodiment of the present invention is shown;

[0021] Figure 7 A schematic diagram showing a test result of an example of testing a question-answering model according to an embodiment of the present invention is shown;

[0022] Figure 8 It is a schematic diagram of the hardware structure of an electronic device for executing a question-and-answer method or a question-and-answer model building method provided in another embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0025] The present invention may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0026] In the present invention, "module", "system" and the like refer to related entities applied to computers, such as hardware, a combination of hardware and software, software or software in execution, etc. In detail, for example, an element can be, but is not limited to, a process, a processor, an object, an executable element, an execution thread, a program and / or a computer running on a processor. In addition, an application program or a script program, a server running on a server can be an element. One or more elements can be in the process and / or thread of execution, and an element can be localized on a computer and / or distributed between two or more computers, and can be operated by various computer-readable media. An element can also communicate by a local and / or remote process according to a signal with one or more data packets, for example, a signal from a local system, another element interacting in a distributed system, and / or a signal of data interacting with other systems through a signal on a network of the Internet.

[0027] Finally, it should be noted that, in this article, the terms "include" and "comprise" include not only those elements, but also other elements not explicitly listed, or elements inherent to such processes, methods, articles or equipment. In the absence of further restrictions, the elements defined by the sentence "include..." do not exclude the existence of other identical elements in the process, method, article or equipment that includes the elements.

[0028] It should be noted that the current question-answering model is generally implemented using the chat algorithm, HSQA algorithm or key algorithm, such as "QA question-answer pair" for a question-answer data set. However, if the user's question is an inference or statistical question, it will result in an inability to give a correct response due to the limitations of the algorithm.

[0029] Currently, competing products on the market do not support accurate responses to questions such as "aggregation", "check data trends", and "statistics by attributes". For example, the "aggregation" question-answering type belongs to the function-computing type of question, and the underlying technical database is generally Elasticsearch, a non-relational database mainly used for full-text search tools, so accurate questions and answers cannot be achieved for computing questions.

[0030] Figure 1 The flowchart of an example of the question-answering method according to the embodiment of the present invention is shown. Regarding the execution subject of the method of the embodiment of the present invention, it can be any electronic device with processing capability, such as an electronic device with a question-answering software program installed.

[0031] like Figure 1As shown, in step 110, user question information is obtained. Here, the user question information can be of various types, such as text question information input by the user, or user question information obtained by performing voice recognition on the user question audio.

[0032] In step 120, based on the question-answering model, an answer corresponding to the user's question information is determined.

[0033] Here, the question and answer model is constructed based on the question and answer material table, which includes at least one header tag attribute, each header attribute tag has at least one corresponding attribute data, and each header tag attribute has corresponding question and answer annotation information, and the question and answer annotation information includes question annotation information or answer annotation information.

[0034] In some cases, the user's question information includes: a calculation-type question associated with a header tag attribute having question annotation information. In this way, by using the question-answering model constructed based on the question-answering material table, it is possible to achieve accurate responses to calculation-type questions of the "aggregation type" and "statistics by attribute" type.

[0035] Figure 2 A flowchart of an example of a method for building a question-answering model according to an embodiment of the present invention is shown. Regarding the execution subject of the method of the embodiment of the present invention, it can be any electronic device with processing capabilities, such as an electronic device with a model building environment or a skill open platform, so that developers can develop corresponding question-answering products.

[0036] like Figure 2 As shown, at least one header tag attribute and corresponding attribute data in the initial material table are determined in step 210. Here, the initial material table can be any electronic spreadsheet document type, such as xls format or xlsx format, etc., and the table can be imported through the interface opened by the table skill login interface.

[0037] In step 220, question and answer annotation information for each header tag attribute is obtained. Here, the question and answer annotation information includes question annotation information or answer annotation information. Specifically, on the one hand, the developer can annotate each header tag attribute in the initial material table, marking whether the attribute belongs to a condition or an answer. On the other hand, the electronic device can display each header tag attribute in the initial material table for the user to perform corresponding annotation operations.

[0038] In step 230, the question and answer material table is determined based on the corresponding header tag attributes, question and answer annotation information and attribute data.

[0039] In step 240, a question-answering model is constructed based on the question-answering material table. Exemplarily, the question-answering material table is used to train the dialogue model, thereby constructing a table-customized question-answering model, so that the table skill can realize the question-answering service capability.

[0040] Figure 3 A flowchart of an example of a method for constructing a question-answering model according to an embodiment of the present invention is shown.

[0041] like Figure 3 As shown, in the initial material table importing phase 310, the developer can import the pre-prepared initial material table in the skill opening platform (such as the DUI platform) by triggering a specific control (such as a table importing control). Here, the question-and-answer materials provided by the developer can be implemented using an Excel spreadsheet.

[0042] Figure 4 FIG. 2 is a schematic diagram showing an effect of an example of an initial material table according to an embodiment of the present invention. Figure 4 In the example in , there are multiple header tag attributes (title, director, type, etc.) and corresponding attribute data in the initial material table.

[0043] In the training sample set preparation phase 320 , developers can perform question-answer annotation operations on each header label attribute.

[0044] Continue above Figure 4 For example, see Figure 5 FIG. 4 is a schematic diagram showing a display interface of an electronic device after the table is imported. Figure 5 As shown, the electronic device displays each header label attribute and the corresponding question and answer annotation control. Here, the question and answer annotation control is used to receive an operation instruction to switch or confirm between the question annotation option and the answer annotation option. Figure 5 In the example in , "column name" can represent the header label attribute, and "column type" displays the corresponding question and answer annotation control for each header label attribute. Users can choose between "condition" or "answer". Then, based on each question and answer annotation control, the question and answer annotation information corresponding to each header label attribute is determined. For example, developers can determine the corresponding question and answer annotation information by switching the "column type" control.

[0045] In some business scenarios, multiple questions are coupled and progressive, and a single question-and-answer interaction may not meet the user's question-and-answer needs. In view of this, for the header tag attributes with question annotation information, the electronic device can also obtain the corresponding follow-up question words; then, based on each corresponding header tag attribute, question-and-answer annotation information, attribute data and follow-up question words, determine the question-and-answer material table. Figure 5In the example, the "Start Questioning" control is set behind the corresponding "column name" when the "column type" is "condition". Developers can choose whether to enable this function and enter specific "questioning words" when enabling it. Set the "column type" and "data type" for the column name. If the column type is "condition", you can set "Start Questioning" and set the questioning words to support multiple rounds of question and answer operations.

[0046] Combined with the above Figure 1 In the example of "Providing Q&A Service Process", after the above step 110, the electronic device can also identify whether there is a target follow-up question script associated with the user's question information based on the question and answer model. Here, the question and answer material table also includes a follow-up question script for the header tag attribute with question annotation information. When there is a target follow-up question script, the electronic device can output the answer and target follow-up question script corresponding to the user's question information. Therefore, the question and answer model developed based on the table skill can provide a multi-round question and answer interaction process.

[0047] In the question-and-answer model building phase 330 , when the user clicks on training or publishing, a table resource is generated, and then the dialogue model is trained to generate a table-customized question-and-answer model.

[0048] Figure 6 FIG. 1 shows a flow chart of training, publishing, production and consumption of a question-answering model according to an embodiment of the present invention. Figure 6 As shown, the following operations can be used to generate table resources: first, call the resource service to store the config.json skill information and cdm dialogue service information; then, call the mscp-table-resouce table resource service to store the table structure and data, generate a dynamic SQL table, and set an index for the condition column; then, notify the NLQ engine service to generate semantic resources, the engine service will call the pasc configuration storage service to obtain the cdm dialogue resources, and then access the mscp-table-resource table resource service library to generate resources.

[0049] Further, continue to refer to Figure 6 In the example, after successful training or publishing, you can also test the question-answer pair for the question-answer model. The specific test steps are as follows: First, the user request is forwarded to the DM dispathch central control dispatch service through DDS (Data Distribution Servic); then, the DM service calls the pasc configuration storage service to obtain product configuration information, and forwards it to the downstream cdm server dialogue service and NLQ table engine service; then, the NLQ table engine service calls pasc to obtain the cdm dialogue resource, and obtains the table configuration, parses if there is a semantic resource, adapts the "table resource storage database" to query the corresponding result, and outputs it as the answer.

[0050] Figure 7 FIG. 2 is a schematic diagram showing a test result of an example of testing a question-answering model according to an embodiment of the present invention. Figure 7 As shown in the figure, the question-answering model trained based on the table skill can accurately answer user questions and can also accurately answer aggregated calculation questions. For example, for the questions "the score is greater than 9.4" and "Chinese", the output result is "Farewell My Concubine".

[0051] It should be noted that during the process of users conducting question-and-answer services, the questions asked by users may be relatively casual, such as using aliases. In order to accurately identify the intention of user questions, the question-and-answer model needs to have the ability to identify extended words (for example, synonyms or near-synonyms).

[0052] Specifically, when determining the question and answer material table, the electronic device can obtain semantic expansion words about the header tag attributes and / or attribute data, such as the semantic expansion words input by the developer. Then, based on the corresponding header tag attributes, question and answer annotation information, attribute data and semantic expansion words, the question and answer material table is determined. Exemplarily, in the training sample preparation stage 320, the Excel table imported by the developer supports three sheets, the first sheet describes the table attributes and data, the second sheet sets the synonyms of the table column names, and the third sheet sets the synonyms of the table data. Thus, the training samples are enriched with semantic expansion words, so that the question and answer model can have the semantic recognition ability for questions with synonymous conditional attributes.

[0053] Combined with the above Figure 1 In the example of "providing question-and-answer service process", regarding the implementation details of the above step 120, the electronic device determines the user header tag attributes that semantically match the user's question information based on the question-and-answer model, and determines the answer corresponding to the user's question based on the various attribute data corresponding to the user header tag attributes.

[0054] In some business scenarios of the embodiments of the present invention, table skills can be listed as a single atomic capability on a skill open platform (for example, DUI platform) and provided to customers. Customers only need to customize the table skill material data and purchase product usage to achieve Q&A. Here, table skills can also be used as one of the full-link solutions. After recognition, semantics, dialogue and synthesis technologies are used to build a full-link product and deliver it to customers. Customers can use it out of the box, simplifying the personalized customization process of the Q&A service.

[0055] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of combined actions, but those skilled in the art should be aware that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention. In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0056] In some embodiments, an embodiment of the present invention provides a non-volatile computer-readable storage medium, which stores one or more programs including execution instructions, and the execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to execute any of the above-mentioned question and answer methods or question and answer model building methods of the present invention.

[0057] In some embodiments, an embodiment of the present invention also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes any one of the above-mentioned question-answering methods or question-answering model building methods.

[0058] In some embodiments, an embodiment of the present invention also provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a question-and-answer method or a question-and-answer model building method.

[0059] Figure 8 is a schematic diagram of the hardware structure of an electronic device for executing a question-answering method or a question-answering model building method provided by another embodiment of the present invention, such as Figure 8 As shown, the device includes:

[0060] One or more processors 810 and memory 820, Figure 8 A processor 810 is taken as an example.

[0061] The device for executing the question-answering method or the question-answering model building method may further include: an input device 830 and an output device 840 .

[0062] The processor 810, the memory 820, the input device 830 and the output device 840 may be connected via a bus or other means. Figure 8 The example of connecting through bus is taken in the following.

[0063] The memory 820, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the question-answering method or the question-answering model building method in the embodiment of the present invention. The processor 810 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 820, that is, realizing the question-answering method or the question-answering model building method in the above method embodiment.

[0064] The memory 820 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the voice interaction device, etc. In addition, the memory 820 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 820 may optionally include a memory remotely arranged relative to the processor 810, and these remote memories may be connected to the voice interaction device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0065] The input device 830 can receive input digital or character information and generate signals related to user settings and function control of the voice interaction device. The output device 840 can include display devices such as display screens.

[0066] The one or more modules are stored in the memory 820, and when executed by the one or more processors 810, perform the question-answering method or question-answering model building method in any of the above method embodiments.

[0067] The above product can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0068] The electronic devices of the embodiments of the present invention exist in various forms, including but not limited to:

[0069] (1) Mobile communication equipment: This type of equipment is characterized by having mobile communication functions and its main purpose is to provide voice and data communications. This type of terminal includes: smart phones, multimedia phones, functional phones, and low-end phones.

[0070] (2) Ultra-mobile personal computer devices: These devices belong to the category of personal computers, have computing and processing functions, and generally also have mobile Internet access features. These terminals include: PDA, MID and UMPC devices, etc.

[0071] (3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players, handheld game consoles, e-books, smart toys, and portable car navigation devices.

[0072] (4) Other onboard electronic devices with data interaction functions, such as on-board devices installed in vehicles.

[0073] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0074] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A question-answering method, comprising: Get user question information; Based on the question-answer model, determine an answer corresponding to the user's question information; wherein the question-answer model is constructed based on a question-answer material table, the question-answer material table includes at least one header tag attribute, each of the header tag attributes has at least one corresponding attribute data, and each of the header tag attributes has corresponding question-answer annotation information, and the question-answer annotation information includes question annotation information or answer annotation information; The question-answer material table is a training sample set of the question-answer model, and the sample label of each training sample is question annotation information or answer annotation information; The question marking information is used to indicate that each attribute data under the corresponding header tag attribute is conditional data; The answer marking information is used to indicate that each attribute data under the corresponding header tag attribute is answer data.

2. The method according to claim 1, wherein: The step of determining an answer corresponding to the user's question information based on the question-answering model includes: Based on the question-answer model, determine the user header tag attributes that semantically match the user question information, and determine the answer corresponding to the user question based on the various attribute data corresponding to the user header tag attributes; wherein the question-answer material table also includes semantic expansion words about the header tag attributes and / or the attribute data.

3. The method according to claim 1, wherein: After obtaining the user question information, the method further includes: Based on the question-answering model, identifying whether there is a target follow-up questioning speech associated with the user question information; the question-answering material table further includes a follow-up questioning speech for a header tag attribute having question annotation information; Wherein, when the target questioning words exist, the method further includes: The answer and the target questioning words corresponding to the user's question information are output.

4. The method according to any one of claims 1 to 3, wherein: The user question information includes: a calculation question sentence associated with the header tag attribute having question annotation information.

5. A method for constructing a question-answering model, comprising: Determine at least one header tag attribute and corresponding attribute data in the initial material table; Obtaining question and answer annotation information for each of the header tag attributes; wherein the question and answer annotation information includes question annotation information or answer annotation information; Determining a question and answer material table based on the corresponding header tag attributes, the question and answer annotation information, and the attribute data; and Based on the question and answer material table, construct a question and answer model; The question-answer material table is a training sample set of the question-answer model, and the sample label of each training sample is question annotation information or answer annotation information; The question marking information is used to indicate that each attribute data under the corresponding header tag attribute is conditional data; The answer marking information is used to indicate that each attribute data under the corresponding header tag attribute is answer data.

6. The method according to claim 5, wherein: The obtaining of question-answer annotation information for each of the header tag attributes includes: Displaying each header label attribute and a corresponding question and answer annotation control; the question and answer annotation control is used to receive an operation instruction to switch or confirm between a question annotation option and an answer annotation option; Based on each of the question and answer annotation controls, the question and answer annotation information corresponding to each of the header label attributes is determined.

7. The method according to claim 5, wherein: The determining of the question and answer material table based on the corresponding header tag attributes, question and answer annotation information and attribute data includes: Acquire semantic expansion words about the header tag attributes and / or the attribute data; A question and answer material table is determined based on the corresponding header tag attributes, the question and answer annotation information, the attribute data and the semantic expansion words.

8. According to the method of claim 5, after obtaining the question-answer annotation information for each of the header tag attributes, the method further comprises: Get follow-up question words for the header tag attributes with question annotation information; The step of determining the question and answer material table based on the corresponding header tag attributes, the question and answer annotation information and the attribute data includes: A question and answer material table is determined based on the corresponding header tag attributes, the question and answer annotation information, the attribute data and the follow-up question words.

9. An electronic device, comprising: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the method described in any one of claims 1 to 8.

10. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

Images