Answer answering method and device, equipment, storage medium and program product
By receiving user questions in the answering system and generating response answers, the problem of lack of personalization of answer information in the prior art is solved, and the auxiliary and intelligence are improved, and users' in-depth understanding of answer information is met.
Patent Information
- Application Number
- CN202411762982.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-03
- Publication Date
- 2025-04-11
AI Technical Summary
When answering user's questions, the answer information lacks personalization and cannot meet the understanding of different users' needs for the same question, resulting in low auxiliary and poor intelligence.
A method of answering questions is provided, after obtaining the first answer information of the question to be answered, it receives the user's question data, and generates the second answer information to respond to the user's specific questions based on the questions to be answered, the first answer information and the question data.
The assistiveness and intelligence of the answering system to users is improved, allowing users to understand the answer information more deeply and meet personalized learning needs.
Smart Images
Figure CN119808936A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a question answering method, device, equipment, storage medium and program product. Background Art
[0002] With the continuous advancement of Internet technology, more and more users are using technology to solve their own learning problems. For example, users will use electronic devices to answer questions they don’t know how to answer, but the current solution gives the same answer information to the same question requested by different users. There will be cases where some users cannot fully understand the answer information, which is less helpful to users and less intelligent. Summary of the invention
[0003] In view of the above problems, the present application provides a method, device, equipment, storage medium and program product for answering questions intelligently and improving the assistance to users. The specific scheme is as follows:
[0004] The first aspect of the present application provides a method for answering questions, the method comprising:
[0005] Obtaining first answer information corresponding to the question to be answered;
[0006] After outputting the first answer information, receiving input question data;
[0007] Based on the question to be answered, the first answer information and the question data, obtaining second answer information corresponding to the question data;
[0008] The second answer information is output.
[0009] In a possible implementation, before receiving the input question data, the method further includes: displaying a target interactive control;
[0010] The receiving input question data includes:
[0011] In response to a triggering operation on the target interactive control, displaying an interactive interface;
[0012] The input question data is received through the interactive interface.
[0013] In a possible implementation, obtaining second answer information corresponding to the question data based on the question to be answered, the first answer information, and the question data includes:
[0014] If the question data is related to the question to be answered and the first answer information, extract first content related to the question data from the question to be answered and the first answer information, and obtain the second answer information based on the first content and the question data;
[0015] If the question data is not related to the question to be answered and the first answer information, the second answer information is obtained based on the question data.
[0016] In a possible implementation, whether the question data is related to the question to be answered and the first answer information is determined in the following manner:
[0017] Obtaining a first characterizing feature of the question data, and a second characterizing feature of the question to be answered and the first answer information;
[0018] If the similarity between the first characterization feature and the second characterization feature meets the condition, it is determined that the question data is related to the question to be answered and the first answer information; otherwise, it is determined that the question data is not related to the question to be answered and the first answer information.
[0019] In a possible implementation, the first characterizing feature is a first knowledge point involved in the question data; the second characterizing feature is a second knowledge point involved in the question to be answered and the first answer information;
[0020] The similarity between the first characterizing feature and the second characterizing feature satisfies a condition, including:
[0021] The second knowledge point includes the first knowledge point.
[0022] In a possible implementation, the first characterizing feature is a first characteristic vector of the question data obtained by extracting characteristics of the question data; the second characterizing feature is a second characteristic vector of the question to be answered and the first answer information obtained by extracting characteristics of the question to be answered and the first answer information;
[0023] The similarity between the first characterizing feature and the second characterizing feature satisfies a condition, including:
[0024] Calculating the similarity between the first feature vector and the second feature vector as the similarity between the first characterizing feature and the second characterizing feature;
[0025] If the similarity between the first characterizing feature and the second characterizing feature is greater than a similarity threshold, it is determined that the similarity between the first characterizing feature and the second characterizing feature satisfies a condition.
[0026] In a possible implementation, obtaining the second answer information based on the question data includes:
[0027] Determine whether the question data is related to target knowledge; the target knowledge includes at least one of the following: subject knowledge, encyclopedic knowledge;
[0028] If the question data is related to the target knowledge, second content related to the question data is extracted from the target knowledge, and the second answer information is obtained based on the second content and the question data.
[0029] A second aspect of the present application provides a question answering device, the device comprising:
[0030] A first answer module, used to obtain first answer information corresponding to the question to be answered;
[0031] An interactive module, configured to receive input question data after outputting the first answer information;
[0032] A second answer module, configured to obtain second answer information corresponding to the question data based on the question to be answered, the first answer information and the question data;
[0033] The interaction module is further configured to output the second answer information.
[0034] The third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the question-answering method of the first aspect or any implementation of the first aspect.
[0035] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:
[0036] The memory is used to store computer programs;
[0037] The processor is used to execute the computer program so that the electronic device can implement the question-answering method of the above-mentioned first aspect or any implementation manner of the first aspect.
[0038] A fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the question-answering method of the above-mentioned first aspect or any implementation of the first aspect.
[0039] By means of the above technical solution, the answering method, device, equipment, storage medium and program product provided by the present application obtain the first answer information corresponding to the question to be answered; after outputting the first answer information, receive the input question data; based on the question to be answered, the first answer information and the question data, obtain the second answer information corresponding to the question data; and output the second answer information. In other words, after the present application gives the first answer information for the question to be answered, it also supports the user to ask questions, and answers the user's questions based on the question to be answered and the first answer information, so that the user can ask questions about specific content in the first answer information, helping the user to understand the first answer information more comprehensively, improving the auxiliary effect on the user, and improving the intelligence of the answering solution. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.
[0041] Figure 1 A flowchart for implementing the answering method provided in this application;
[0042] Figure 2 A flowchart for implementing receiving input question data provided by the present application;
[0043] Figure 3 A flowchart for determining whether question data is related to the question to be answered and the first answer information provided by the present application;
[0044] Figure 4 A flowchart for implementing obtaining second answer information based on question data provided by the present application;
[0045] Figure 5 A structural schematic diagram of the answering device provided in this application;
[0046] Figure 6 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION
[0047] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.
[0048] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0049] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.
[0050] In order to improve the auxiliary effect of the answering scheme on user learning, this application scheme is proposed.
[0051] like Figure 1 As shown, a flowchart of an implementation of the answering method provided in the embodiment of the present application may include:
[0052] Step S101: Obtain answer information corresponding to the question to be answered (for ease of description and distinction, recorded as the first answer information).
[0053] The question to be answered is a question specified by the user, for example, it may be a question input by the user, or it may be a question selected by the user from several questions provided by the electronic device, or it may be a question obtained by scanning a paper document provided by the user, or it may be a question obtained by taking a photo of the paper document provided by the user and performing text recognition on the photo.
[0054] The answer information corresponding to the question to be answered may include but is not limited to at least one of the following: the answer to the question to be answered, the solution idea, the calculation process for obtaining the answer, the knowledge points involved in the question to be answered, etc.
[0055] You can search for unanswered questions in the question bank, and use the answer information stored in the question bank in association with the unanswered questions as the first answer information. The question bank stores a number of questions and the answer information corresponding to each question; the answer information corresponding to the question may include but is not limited to at least one of the following: the answer to the question, the solution idea, the calculation process for obtaining the answer, the knowledge points involved in the question, etc.
[0056] Alternatively, the knowledge base may be searched for knowledge points corresponding to the question to be answered, and the large model may answer the question to be answered based on the searched knowledge points to obtain third answer information; the third answer information includes but is not limited to at least one of the following: the answer to the question, the solution idea, the calculation process of obtaining the answer, etc. The first answer information includes at least one of the following: the knowledge point corresponding to the question to be answered, and the third answer information.
[0057] Of course, the first answer information may also be obtained through other methods, which are not specifically limited in this application.
[0058] Step S102: After outputting the first answer information, receiving input question data.
[0059] After obtaining the first answer information, the first answer information is output to provide to the user. The first answer information may be output in at least one of the following ways: outputting the first answer information in the form of a video (i.e., outputting a video, the content of which includes the first answer information), outputting the first answer information in the form of an audio (i.e., broadcasting the first answer information by voice), and outputting the first answer information in the form of a text (i.e., outputting a text, the content of which is the first answer information).
[0060] When the first answer information is output in at least two ways, the at least two output ways may be executed simultaneously or sequentially, and the order of output is not specifically limited.
[0061] The question data is a question asked by the user after seeing or hearing the first answer information. The question may be a question related to the first answer information or a question unrelated to the first answer information.
[0062] Step S103: Based on the question to be answered, the first answer information and the question data, obtain the second answer information corresponding to the question data.
[0063] That is, the question data is answered based on the question to be answered and the first answer information to obtain the second answer information corresponding to the question data.
[0064] Among them, if the question data is related to the question to be answered and the first answer information, then the second answer information is related to the question to be answered and the first answer information; if the question data is not related to the question to be answered and the first answer information, then the second answer information is not related to the question to be answered and the first answer information.
[0065] Step S104: output second answer information.
[0066] The second answer information may be output in at least one of the following ways: outputting the second answer information in the form of video (i.e., outputting a video, the content of the video playback includes the second answer information), outputting the second answer information in the form of audio (i.e., voice broadcasting the second answer information), and outputting the second answer information in the form of text (i.e., outputting text, the content of the text is the second answer information).
[0067] When the second answer information is output in at least two ways, the at least two output ways may be executed simultaneously or sequentially, and the order of output is not specifically limited.
[0068] The answering method provided in the embodiment of the present application, after giving the first answer information for the question to be answered, also supports the user to ask questions, and answers the user's questions based on the question to be answered and the first answer information, so that the user can ask questions about specific content in the first answer information, helping the user to understand the first answer information more comprehensively, improving the auxiliary effect of the answering plan on the user, and improving the intelligence of the answering plan.
[0069] In addition, after the first answer information is given for the question to be answered, if the user's question is not about the specific content in the first answer information, by answering the user's question, the user's knowledge can be expanded, and the auxiliary effect of the answering method on the user can be improved, thereby improving the intelligence of the answering plan.
[0070] In an optional embodiment, after outputting the first answer information and before receiving the input question data, the following may also be included:
[0071] Displaying a target interactive control. The target interactive control may be displayed on one side of the first answer information, and the target interactive control may carry a preset icon to prompt the user to ask a question.
[0072] Correspondingly, a flowchart of the above-mentioned receiving input question data is as follows: Figure 2 As shown, this may include:
[0073] Step S201: In response to a triggering operation on a target interactive control, an interactive interface is displayed.
[0074] The user can perform a preset operation (such as single click or double click) on the target interactive control to trigger the electronic device to display an interactive interface. The interactive interface is a data receiving interface, which has at least one of the following interactive interfaces: a text input interface, an audio input interface, and a picture input interface.
[0075] Step S202: receiving input question data through the interactive interface.
[0076] Optionally, based on the text input interface, question data in text form input by the user through an input device (eg, a physical keyboard or a virtual keyboard) may be received.
[0077] Optionally, based on the audio input interface, question data in the form of audio input by the user through an audio acquisition device can be received.
[0078] Optionally, through the picture input interface, question data in the form of pictures imported by the user (for example, a picture obtained by taking a photo of the question data) may be received.
[0079] The user can enter the question data in either way.
[0080] In an optional embodiment, one implementation of obtaining the second answer information corresponding to the question data based on the question to be answered, the first answer information and the question data may be:
[0081] If the question data is related to the question to be answered and the first answer information, first content related to the question data is extracted from the question to be answered and the first answer information, and second answer information is obtained based on the first content and the question data.
[0082] If the question data is related to the question to be answered and the first answer information, it means that the user does not understand at least part of the content in the first answer information. Therefore, the first content related to the question data is extracted from the question to be answered and the first answer information, and the question data is answered based on the first content, so as to further explain the first content and help the user better understand the first content.
[0083] If the question data is not related to the question to be answered and the first answer information, the second answer information is obtained based on the question data.
[0084] If the question data is not related to the question to be answered and the first answer information, it means that the user may have fully understood the first answer information and is interested in some extended knowledge. Therefore, when answering the question data, there is no need to consider the content of the question to be answered and the first answer information, thereby answering questions about extended knowledge for users, which is conducive to improving the quality of user learning.
[0085] In an optional embodiment, the present application provides a flowchart for determining whether the question data is related to the question to be answered and the first answer information. Figure 3 As shown, this may include:
[0086] Step S301: Obtain a characterizing feature of the question data (referred to as the first characterizing feature for ease of description and distinction).
[0087] Optionally, the characterization feature of the question data may be a feature vector of the question data (recorded as the first feature vector for ease of description and distinction), or may be a knowledge point involved in the question data (recorded as the first knowledge point for ease of description and distinction).
[0088] As an example, when the characterizing feature of the question data is a feature vector of the question data, the question data may be encoded to obtain the encoded feature of the question data as the first feature vector of the question data.
[0089] As an example, when the characterization feature of the question data is a feature vector of the question data, the first knowledge point involved in the question data can be obtained first, the first knowledge point can be encoded, and the encoding feature of the first knowledge point can be obtained as the first feature vector of the question data.
[0090] As an example, when the characterization feature of the question data is the knowledge point involved in the question data, the question data can be encoded to obtain the encoded feature of the question data, and the similarity between the encoded feature of the question data and the encoded features of each knowledge point in the knowledge base is calculated, and the knowledge point whose similarity with the encoded feature of the question data is greater than a threshold is determined as the first knowledge point involved in the question data.
[0091] As an example, when the characterization feature of the question data is a knowledge point involved in the question data, the question data may be processed by the big model so that the big model generates a first knowledge point involved in the question data.
[0092] Step S302: Obtaining the characterizing features of the question to be answered and the first answer information (referred to as the second characterizing features for ease of description and distinction).
[0093] Optionally, the characterization features of the question-related information (i.e., the question to be answered and the first answer information) can be a feature vector of the question-related information (recorded as a second feature vector for ease of description and distinction), or can be a knowledge point involved in the question-related information (recorded as a second knowledge point for ease of description and distinction).
[0094] As an example, when the characterizing feature of the topic-related information is a feature vector of the topic-related information, the topic-related information may be encoded to obtain the encoded feature of the topic-related information as a second feature vector of the topic-related information.
[0095] As an example, when the characterization feature of the question-related information is a feature vector of the question-related information, the second knowledge point involved in the question-related information can be obtained first, the second knowledge point can be encoded, and the encoding feature of the second knowledge point can be obtained as the second feature vector of the question-related information.
[0096] As an example, when the characterizing features of the question-related information are the knowledge points involved in the question-related information, the question-related information can be encoded to obtain the encoded features of the question-related information, and the similarity between the encoded features of the question-related information and the encoded features of each knowledge point in the knowledge base is calculated, and the knowledge point whose similarity with the encoded features of the question-related information is greater than a threshold is determined as the second knowledge point.
[0097] As an example, when the characterization feature of the topic-related information is a knowledge point involved in the topic-related information, the topic-related information can be processed by the big model so that the big model generates a second knowledge point involved in the topic-related information.
[0098] It should be noted that the present application does not specifically limit the execution order of step S301 and step S302. Step S301 may be executed first, and then step S302, or step S302 may be executed first, and then step S301, or both steps may be executed simultaneously.
[0099] Step S303: If the similarity between the first characterization feature and the second characterization feature meets the condition, it is determined that the question data is related to the question to be answered and the first answer information; otherwise, it is determined that the question data is not related to the question to be answered and the first answer information.
[0100] Optionally, in the case where the characterization feature is a knowledge point, if the second knowledge point includes the first knowledge point, that is, the first knowledge point is a part of the second knowledge point, it can be determined that the similarity between the first characterization feature and the second characterization feature meets the condition.
[0101] Optionally, when the characterizing feature is a feature vector, the similarity between the first characterizing feature and the second characterizing feature may satisfy the condition that:
[0102] The similarity between the first characterizing feature and the second characterizing feature is calculated based on the first feature vector and the second feature vector.
[0103] The distance between the first eigenvector and the second eigenvector may be calculated, and the distance represents the similarity between the first characterization feature and the second characterization feature. As an example, the distance between the first eigenvector and the second eigenvector may be a Euclidean distance, or may be a cosine distance. The larger the Euclidean distance, the smaller the similarity between the first eigenvector and the second eigenvector, otherwise, the smaller the similarity between the first eigenvector and the second eigenvector. The larger the cosine distance, the larger the similarity between the first eigenvector and the second eigenvector, otherwise, the smaller the similarity between the first eigenvector and the second eigenvector.
[0104] Alternatively, the distance between the first feature vector and the second feature vector can be calculated, and the similarity between the first characterization feature and the second characterization feature can be calculated based on the distance. As an example, when the distance is the Euclidean distance, the similarity between the first knowledge point and the second knowledge point can be calculated as follows: s=1 / (d+1), where s represents the similarity between the first characterization feature and the second characterization feature, and d represents the distance between the first feature vector and the second feature vector. The larger the s value, the greater the similarity between the first characterization feature and the second characterization feature.
[0105] If the similarity is greater than the similarity threshold, it is determined that the similarity between the first characterizing feature and the second characterizing feature satisfies a condition.
[0106] In an optional embodiment, a flowchart for implementing the above-mentioned acquisition of the second answer information based on the question data is as follows: Figure 4 As shown, this may include:
[0107] Step S401: Determine whether the question data is related to target knowledge; the target knowledge includes at least one of the following: subject knowledge, encyclopedic knowledge.
[0108] That is to say, when the question data is not related to the question to be answered and the first answer information, it can be further determined whether the question data is related to learning or encyclopedic knowledge.
[0109] Optionally, the question data may be classified by a large model to obtain a classification result, which represents whether the question data is related to learning or encyclopedic knowledge.
[0110] Step S402: If the question data is related to the target knowledge, extract second content related to the question data from the target knowledge, and obtain second answer information based on the second content and the question data.
[0111] Furthermore, if the question data is not relevant to the target knowledge, obtaining the second answer information based on the question data is prohibited. That is, if the question data is not relevant to the target knowledge, no reply is given to the question data.
[0112] Optionally, if the question data is related to the target knowledge, the second answer information may be obtained based only on the question data.
[0113] In an optional embodiment, another implementation method of obtaining the second answer information based on the question to be answered, the first answer information and the question data may be:
[0114] The question to be answered, the first answer information and the question data are added to the prompt template to obtain the target prompt; the target prompt instructs the large model to obtain the first knowledge point involved in the question data, and the second knowledge point involved in the question to be answered and the first answer information; if the second knowledge point includes the first knowledge point, the content related to the question data is extracted from the question to be answered and the first answer information, and the question data is answered based on the extracted content; if the second knowledge point does not include the first knowledge point, it is further determined whether the question data is related to learning or encyclopedic knowledge, and if so, the question data is answered, otherwise, the question data is refused to be answered.
[0115] The target indication instruction is input into the large model to obtain the second answer information generated by the large model, or the information representing the refusal to answer.
[0116] Corresponding to the method embodiment, the present application also provides a question answering device, such as Figure 5 As shown, a schematic diagram of a structure of a question answering device provided in an embodiment of the present application may include:
[0117] A first answering module 501, an interaction module 502, and a second answering module 503;
[0118] The first answer module 501 is used to obtain first answer information corresponding to the question to be answered;
[0119] The interaction module 502 is used to receive input question data after outputting the first answer information;
[0120] The second answer module 503 is used to obtain second answer information corresponding to the question data based on the question to be answered, the first answer information and the question data; the second answer module 503 and the first answer module 501 can be the same answer module or different answer modules.
[0121] The interaction module 502 is further configured to output the second answer information.
[0122] The question answering device provided in the embodiment of the present application, after giving the first answer information for the question to be answered, also supports the user to ask questions, and answers the user's questions based on the question to be answered and the first answer information, so that the user can ask questions about specific content in the first answer information, helping the user to understand the first answer information more comprehensively, improving the auxiliary effect of the answering plan on the user, and improving the intelligence of the answering plan.
[0123] In addition, after the first answer information is given for the question to be answered, if the user's question is not about the specific content in the first answer information, by answering the user's question, the user's knowledge can be expanded, and the auxiliary effect of the answering method on the user can be improved, thereby improving the intelligence of the answering plan.
[0124] In an optional embodiment, before receiving the input question data, the interaction module 502 is further used to: display the target interaction control;
[0125] When the interactive module 502 receives the input question data, it is used to:
[0126] In response to a triggering operation on the target interactive control, displaying an interactive interface;
[0127] The input question data is received through the interactive interface.
[0128] In an optional embodiment, when the second answer module 503 obtains the second answer information corresponding to the question data based on the question to be answered, the first answer information and the question data, it is used to:
[0129] If the question data is related to the question to be answered and the first answer information, extract first content related to the question data from the question to be answered and the first answer information, and obtain the second answer information based on the first content and the question data;
[0130] If the question data is not related to the question to be answered and the first answer information, the second answer information is obtained based on the question data.
[0131] In an optional embodiment, the second answer module 503 determines whether the question data is related to the question to be answered and the first answer information in the following manner:
[0132] Obtaining a first characterizing feature of the question data, and a second characterizing feature of the question to be answered and the first answer information;
[0133] If the similarity between the first characterization feature and the second characterization feature meets the condition, it is determined that the question data is related to the question to be answered and the first answer information; otherwise, it is determined that the question data is not related to the question to be answered and the first answer information.
[0134] In an optional embodiment, the first characterizing feature is a first knowledge point involved in the question data; the second characterizing feature is a second knowledge point involved in the question to be answered and the first answer information;
[0135] The similarity between the first characterizing feature and the second characterizing feature satisfies a condition, including:
[0136] The second knowledge point includes the first knowledge point.
[0137] In an optional embodiment, the first characterizing feature is a first characteristic vector of the question data obtained by extracting characteristics of the question data; the second characterizing feature is a second characteristic vector of the question to be answered and the first answer information obtained by extracting characteristics of the question to be answered and the first answer information;
[0138] The similarity between the first characterizing feature and the second characterizing feature satisfies a condition, including:
[0139] Calculating the similarity between the first characterizing feature and the second characterizing feature based on the first feature vector and the second feature vector;
[0140] If the similarity between the first characterizing feature and the second characterizing feature is greater than a similarity threshold, it is determined that the similarity between the first characterizing feature and the second characterizing feature satisfies a condition.
[0141] In an optional embodiment, when the second answer module 503 obtains the second answer information based on the question data, it is used to:
[0142] Determine whether the question data is related to target knowledge; the target knowledge includes at least one of the following: subject knowledge, encyclopedic knowledge;
[0143] If the question data is related to the target knowledge, second content related to the question data is extracted from the target knowledge, and the second answer information is obtained based on the second content and the question data.
[0144] The present application also provides an electronic device in an embodiment. Figure 6 As shown, it shows a structural schematic diagram of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application can be a terminal device (such as a mobile phone, a tablet computer, a laptop computer, a desktop computer, etc.), or a server (can be a single server, can be a server cluster, or can be a cloud server, etc.). Figure 6 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0145] like Figure 6 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0146] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.
[0147] Also provided in an embodiment of the present application is a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the question-answering methods provided in the embodiments of the present application.
[0148] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When one or more computer programs are executed by an electronic device, the electronic device can implement any one of the question-answering methods provided in the embodiment of the present application.
[0149] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.
[0150] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0151] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product. Professionals and technicians may use different methods to implement the described functions for each specific solution, but such implementation should not be considered beyond the scope of this application.
[0152] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.
[0153] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0154] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for answering questions, characterized in that: The method comprises: Obtaining first answer information corresponding to the question to be answered; After outputting the first answer information, receiving input question data; Based on the question to be answered, the first answer information and the question data, obtaining second answer information corresponding to the question data; The second answer information is output.
2. The method according to claim 1, characterized in that: Before receiving the input question data, the method further includes: displaying a target interactive control; The receiving input question data includes: In response to a triggering operation on the target interactive control, displaying an interactive interface; The input question data is received through the interactive interface.
3. The method according to claim 1, characterized in that The obtaining, based on the question to be answered, the first answer information and the question data, second answer information corresponding to the question data includes: If the question data is related to the question to be answered and the first answer information, extract first content related to the question data from the question to be answered and the first answer information, and obtain the second answer information based on the first content and the question data; If the question data is not related to the question to be answered and the first answer information, the second answer information is obtained based on the question data.
4. The method according to claim 3, characterized in that Whether the question data is related to the question to be answered and the first answer information is determined in the following manner: Obtaining a first characterizing feature of the question data, and a second characterizing feature of the question to be answered and the first answer information; If the similarity between the first characterizing feature and the second characterizing feature satisfies a condition, determining that the question data is related to the question to be answered and the first answer information; Otherwise, it is determined that the question data is not relevant to the question to be answered and the first answer information.
5. The method according to claim 4, characterized in that The first characterizing feature is a first knowledge point involved in the question data; the second characterizing feature is a second knowledge point involved in the question to be answered and the first answer information; The similarity between the first characterizing feature and the second characterizing feature satisfies a condition, including: The second knowledge point includes the first knowledge point.
6. The method according to claim 4, characterized in that The first characterizing feature is a first characteristic vector of the question data obtained by extracting characteristics of the question data; the second characterizing feature is a second characteristic vector of the question to be answered and the first answer information obtained by extracting characteristics of the question to be answered and the first answer information; The similarity between the first characterizing feature and the second characterizing feature satisfies a condition, including: Calculating the similarity between the first characterizing feature and the second characterizing feature based on the first feature vector and the second feature vector; If the similarity between the first characterizing feature and the second characterizing feature is greater than a similarity threshold, it is determined that the similarity between the first characterizing feature and the second characterizing feature satisfies a condition.
7. The method according to claim 3, characterized in that The obtaining the second answer information based on the question data comprises: Determine whether the question data is related to target knowledge; the target knowledge includes at least one of the following: subject knowledge, encyclopedic knowledge; If the question data is related to the target knowledge, second content related to the question data is extracted from the target knowledge, and the second answer information is obtained based on the second content and the question data.
8. A question answering device, characterized in that: The device comprises: A first answer module, used to obtain first answer information corresponding to the question to be answered; An interactive module, configured to receive input question data after outputting the first answer information; A second answer module, configured to obtain second answer information corresponding to the question data based on the question to be answered, the first answer information and the question data; The interaction module is further configured to output the second answer information.
9. A computer program product, characterized in that It includes computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the question-answering method as described in any one of claims 1 to 7.
10. An electronic device, characterized in that: The electronic device comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the question answering method as described in any one of claims 1 to 7.
11. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the question-answering method as described in any one of claims 1 to 7.