CN110019706B - Question generation method and device - Google Patents
Question generation method and device Download PDFInfo
- Publication number
- CN110019706B CN110019706B CN201711092223.5A CN201711092223A CN110019706B CN 110019706 B CN110019706 B CN 110019706B CN 201711092223 A CN201711092223 A CN 201711092223A CN 110019706 B CN110019706 B CN 110019706B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- question
- historical
- answers
- questions
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses a question generation method and device, a feature extraction rule corresponding to a question type can be determined according to the question type of a historical question through an acquired historical question, a knowledge point can be extracted from an answer of the historical question according to the feature extraction rule, and a new question is generated according to the knowledge point, so that the number of questions in a knowledge system is expanded, the questions stored in the knowledge system can not be obtained only according to the question of a user any more, a brand-new question expansion mode is expanded, and the question retention amount in the knowledge system is effectively increased. And because the extracted knowledge points are related to the knowledge content which the user may want to know, the question generated according to the knowledge points is probably the question which the user wants to know the knowledge points, so that when the user proposes the question, the knowledge system can quickly provide the answer of the question, and the situation that the user asks the question only to wait for the answer of other users is reduced to a certain extent.
Description
Technical Field
The present application relates to the field of data processing, and in particular, to a problem generation method and apparatus.
Background
The interactive knowledge system stores a plurality of questions and answers corresponding to the questions, and the user can be helped by asking the knowledge system, for example, if the questions are the same as or similar to the questions stored in the knowledge system, the knowledge system can provide the user with the saved answers corresponding to the questions
However, once the user's question is different from the question stored in the knowledge system, the knowledge system will push the question to other users for answer, and the user who asked the question can only wait while the other users give the answer.
If the questions and answers in the knowledge system can be effectively expanded, the probability of matching the questions provided by the user can be improved, and the condition that the user waits for the answers is reduced. However, since the questions saved in the knowledge system are generally questions asked by the user in the historical data, the number of the questions saved in the knowledge system is limited, and is related to whether the user has asked the questions, so that no effective mechanism for expanding the questions and answers in the knowledge system exists at present.
Disclosure of Invention
In order to solve the technical problems, the application provides a problem generation method and a problem generation device, a brand-new problem expansion mode is expanded, the problem retention amount in a knowledge system is effectively increased, the situation that a user asks a question only to wait for other users to answer is reduced to a certain extent, and the experience of the user in using the knowledge system is improved.
The embodiment of the application discloses the following technical scheme:
in a first aspect, an embodiment of the present application provides a problem generation method, where the method includes:
acquiring historical problems;
determining a feature extraction rule corresponding to the question type according to the question type of the historical question;
extracting knowledge points from the answers of the historical questions according to the feature extraction rules;
and generating a question according to the knowledge points.
Optionally, the extracting knowledge points from the answers to the historical questions according to the feature extraction rule includes:
extracting meta knowledge from the answers of the historical questions according to the feature extraction rules, wherein the meta knowledge is used for embodying knowledge content associated with the knowledge points in the answers of the historical questions;
and determining the knowledge point according to the meta-knowledge and the answers of the historical questions.
Optionally, the generating a question according to the knowledge point includes:
selecting a corresponding question mode according to the incidence relation between the meta-knowledge and the knowledge points;
and generating the question according to the selected question mode and the knowledge point.
Optionally, after generating the problem according to the knowledge point, the method further includes:
and determining a corresponding answer for the generated question according to the meta-knowledge.
Optionally, the extracting knowledge points from the answers to the historical questions according to the feature extraction rule includes:
and extracting knowledge points from the answers of the historical questions by combining the historical questions according to the feature extraction rules.
Optionally, the generating a question according to the knowledge point includes:
and generating a question according to a preset question mode and the knowledge point.
In a second aspect, an embodiment of the present application provides a question generation apparatus, which includes an acquisition unit, a determination unit, an extraction unit, and a generation unit:
the acquisition unit is used for acquiring historical problems;
the determining unit is used for determining a feature extraction rule corresponding to the question type according to the question type of the historical question;
the extraction unit is used for extracting knowledge points from the answers of the historical questions according to the feature extraction rules;
and the generating unit is used for generating a problem according to the knowledge point.
Optionally, the extracting unit includes: a meta knowledge extraction subunit and a knowledge point determination subunit;
the meta knowledge extracting subunit is configured to extract meta knowledge from the answers to the historical questions according to the feature extraction rule, where the meta knowledge is used to embody knowledge content associated with the knowledge points in the answers to the historical questions;
and the knowledge point determining subunit is used for determining the knowledge point according to the meta-knowledge and the answers of the historical questions.
Optionally, the generating unit includes: selecting a subunit and generating a subunit;
the selecting subunit is used for selecting a corresponding question mode according to the incidence relation between the meta-knowledge and the knowledge points;
and the generating subunit is used for generating the question according to the selected question mode and the knowledge point.
Optionally, the apparatus further includes an answer determining unit, configured to determine a corresponding answer for the generated question according to the meta-knowledge.
Optionally, the extracting unit includes:
and the knowledge point extraction subunit is used for extracting knowledge points from the answers of the historical questions by combining the historical questions according to the feature extraction rules.
Optionally, the generating unit is further configured to generate a question according to a preset question mode and the knowledge point.
In a third aspect, embodiments of the present application provide a processing apparatus for problem generation, including a memory, and one or more programs, where the one or more programs are stored in the memory, and configured to be executed by the one or more processors includes instructions for:
acquiring historical problems;
determining a feature extraction rule corresponding to the question type according to the question type of the historical question;
extracting knowledge points from the answers of the historical questions according to the feature extraction rules;
and generating a question according to the knowledge points.
In a fourth aspect, embodiments of the present application provide a machine-readable medium having stored thereon instructions, which when executed by one or more processors, cause an apparatus to perform the problem generation method as in the first aspect.
According to the technical scheme, the characteristic extraction rule corresponding to the question type can be determined according to the question type of the historical question through the acquired historical question, the knowledge point can be extracted from the answer of the historical question according to the characteristic extraction rule, and a new question is generated according to the knowledge point, so that the number of the questions in the knowledge system is expanded, the questions stored in the knowledge system can not be obtained only according to the user question, a brand-new problem expansion mode is expanded, and the problem retention amount in the knowledge system is effectively increased. Moreover, the extracted knowledge points are related to the knowledge content which the user may want to know, so that the problem generated according to the knowledge points is likely to be the problem which the user wants to know the knowledge points, when the user proposes the problem, the knowledge system can quickly provide the answer to the problem, the situation that the user asks the question only to wait for the answer of other users is reduced to a certain extent, and the experience of the user in using the knowledge system is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a flowchart of a method of a problem generation method according to an embodiment of the present application;
fig. 2 is a device structure diagram of a problem generation device according to an embodiment of the present application;
FIG. 3 is a block diagram of an apparatus for question generation according to an embodiment of the present application;
fig. 4 is a block diagram of a server for problem generation according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described below with reference to the accompanying drawings.
The interactive knowledge system stores a large number of questions and answers corresponding to the questions, and the user can be helped by asking the knowledge system for questions. However, all the questions and the replies corresponding to the questions which are provided by the previous users are stored in the knowledge system, and if no previous user provides the questions which are provided by the current user, the knowledge system cannot obtain the replies of the questions which are provided by the current user, and the knowledge system can only push the questions to other platforms or other users so as to obtain the answers. In practical application, the time for waiting for obtaining the answer is generally long when the question is pushed to other platforms or other users, so that low experience is brought to the users.
If the problem stock in the knowledge system can be expanded as much as possible, the situation that a user who asks a question waits for other users to answer the question can be reduced to a certain extent. However, in the conventional knowledge system construction, the saved problems mainly depend on historical problem data, that is, the problems which are once asked by the user are required to be possibly expanded into the knowledge system, the knowledge system does not have the capability of creating new problems by space, so that the number of the problems saved in the knowledge system is relatively limited, and the only expansion can be expected to be only to be provided by the user. Therefore, at present, no effective mechanism for expanding questions and answers in the knowledge system exists, and the problem reserves in the knowledge system can be expanded without depending on the question asking of the user.
Therefore, the embodiment of the application provides a question generation method, through the acquired historical questions, a feature extraction rule corresponding to the question type can be determined according to the question type of the historical questions, a knowledge point is extracted from the answers of the historical questions according to the feature extraction rule, and a new question is generated according to the knowledge point, so that the number of the questions in the knowledge system is expanded, the questions stored in the knowledge system can not be obtained only according to the questions of the user any more, a brand-new question expansion mode is expanded, and the question retention amount in the knowledge system is effectively increased. Moreover, the extracted knowledge points are related to the knowledge content which the user may want to know, so that the problem generated according to the knowledge points is likely to be the problem which the user wants to know the knowledge points, when the user proposes the problem, the knowledge system can quickly provide the answer to the problem, the situation that the user asks the question only to wait for the answer of other users is reduced to a certain extent, and the experience of the user in using the knowledge system is improved.
Fig. 1 is a flowchart of a method of a problem generation method according to an embodiment of the present application, where the method includes:
s101: and acquiring historical problems.
The historical problem can be a problem which is once proposed by a historical user, and can also be a problem which is formed aiming at common knowledge or basic knowledge in the Internet. The historical problem may have been saved in a knowledge system that needs to augment the problem. Since it is a historical question that has already been presented, the historical question should have a corresponding answer. For example, one historical question may be "what interesting story is in great wall? "the corresponding answer may be" the girl of ginger girl "," goat carries bricks "," ice road fortune stone "etc.
S102: and determining a feature extraction rule corresponding to the question type according to the question type of the historical question.
The questions have different patterns, semantic expression modes and the like, so that the question types of the historical questions can be determined, and the question types can comprise non-classes, enumeration classes, information confirmation classes and the like. Different question types can correspond to different feature extraction rules, and the feature extraction rule of one question type refers to a rule for extracting features from answers corresponding to questions with the question type. The feature extraction rule may include an extraction manner, a position of the feature to be extracted in the question to be extracted, for example, a component of a sentence corresponding to the question to be extracted belonging to the feature to be extracted. According to the feature extraction rule corresponding to one question type, the required content can be effectively extracted from the answer of the question with the question type.
S103: and extracting knowledge points from the answers of the historical questions according to the feature extraction rules.
As explained in S102 for the feature extraction rule, knowledge points can be effectively extracted from the answers to the historical questions according to the feature extraction rule. The knowledge point may be a feature that includes associated knowledge content that may embody the user's knowledge needs of the knowledge point.
The knowledge point may be directly included in the answers to the historical questions or may be related to the content in the answers to the historical questions. The associated knowledge content may or may not appear in the answers to the historical questions.
For example, the historical problem is "how to feel numb and itchy hands after peeling taros? The corresponding answer is that the washbasin is used for containing a little clear water, a little table vinegar is added, and the mixture is uniformly stirred and then used for washing hands and relieving itching. The question type of the historical question is an enumeration type, and a knowledge point 'vinegar' can be extracted from the answer according to a feature extraction rule corresponding to the enumeration type. The associated knowledge content included in the knowledge point of the vinegar can include the fact that the special function of the vinegar can prevent the itching caused by peeling taros by hands, and the associated knowledge content reflects the requirement that a user may want to know the special use of the vinegar. Of course, the knowledge point "vinegar" may include other related knowledge contents, such as diet-related, stain-removing-related, and the like.
Besides extracting knowledge points from the answers of the historical questions according to the feature extraction rules, when the knowledge points are extracted from the answers, the knowledge points can be extracted from the answers by combining the historical questions corresponding to the answers. The possible meanings of different parts in the answers of the historical questions can be more definite by analyzing the historical questions, so that the accuracy of extracting knowledge points from the answers can be further improved.
S104: generating a question according to the knowledge points.
Since the knowledge point acquired in S103 belongs to a feature for which the user may have a need to know, the problem generated from the knowledge point will be a problem that the user may have posed due to the need to know.
The embodiment of the present application does not limit how to generate questions based on knowledge points, and may be any question sentence in language-character habits. For example, a knowledge point "goat packs bricks" is determined according to historical questions and answers, and the generated question can be "story of what goat packs bricks? ".
In order to improve the similarity between the generated questions and the questions which may be asked by the user, the questions can be generated according to a preset question mode and the knowledge points, the preset question mode can be obtained by extracting the questions asked by the user in the historical data, and can be similar to the sentence patterns and the words which are asked by the user conventionally, so that the probability of matching the questions asked by the user is improved.
For example, a knowledge point "vinegar" is determined from historical questions and answers, and a preset questioning mode may include "what is …? "," … what does it? "etc., then the question generated from the knowledge point may be" what is vinegar? "," what action vinegar has? "and the like.
Therefore, through the acquired historical questions, the feature extraction rule corresponding to the question type can be determined according to the question type of the historical questions, the knowledge points are extracted from the answers of the historical questions according to the feature extraction rule, and new questions are generated according to the knowledge points, so that the number of the questions in the knowledge system is expanded, the questions stored in the knowledge system can not be obtained only according to the questions asked by the user any more, a brand-new question expansion mode is expanded, and the question retention amount in the knowledge system is effectively increased. Moreover, the extracted knowledge points are related to the knowledge content which the user may want to know, so that the problem generated according to the knowledge points is likely to be the problem which the user wants to know the knowledge points, when the user proposes the problem, the knowledge system can quickly provide the answer to the problem, the situation that the user asks the question only to wait for the answer of other users is reduced to a certain extent, and the experience of the user in using the knowledge system is improved.
An alternative embodiment to S103 will be further described below.
In step S103, the meta knowledge may be extracted from the answers to the historical questions according to the feature extraction rule, and then the knowledge point may be determined according to the meta knowledge and the answers to the historical questions.
The meta knowledge is used for embodying knowledge content associated with knowledge points in the answers of the historical questions. The knowledge content can make the user know the information related to the knowledge point.
By extracting the meta knowledge first, the range of the required knowledge points can be effectively determined, the probability that the knowledge points extracted within the range determined by the meta knowledge have knowledge contents which the user wants to know is better, and the usability of the knowledge points is improved.
For example, the historical problem is "how do it after peeling taro feel numb and itchy hands? The answer is that a washbasin is used for containing a little clear water, a little table vinegar is added, and the mixture is uniformly stirred and then used for washing hands and relieving itching. The meta-knowledge determined from the answer may be "taro peeling", "itching and intolerance", and the determined knowledge points should be related to the meta-knowledge. The knowledge point 'vinegar' related to the meta knowledge can be determined according to the meta knowledge and the answers of the historical questions.
The question may be generated according to the manner described in S104, for example, according to a preset question mode and the knowledge point. In addition, the embodiment of the present application also provides a way to generate a question with respect to S104.
The method specifically comprises the following steps: after the knowledge points are determined according to the meta knowledge, the incidence relation between the meta knowledge and the knowledge points can be determined, the corresponding question mode is selected according to the determined incidence relation, and the question is generated according to the selected question mode and the knowledge points.
If the association relationship between the identification point and the corresponding meta-knowledge obtained in S103 can be clarified, a question mode that can embody the association relationship can be selected according to the association relationship. If the knowledge point is generated into a question through the questioning mode, the answer corresponding to the question may include the meta-knowledge or be determined and obtained according to the meta-knowledge. Therefore, the time and the data processing process of the knowledge system for determining answers for the generated questions are omitted, and the processing efficiency is improved.
That is, after S104, an answer may be further determined for the question generated by S104. In addition to the above-mentioned question generated by selecting the questioning mode according to the association relationship between the knowledge point and the corresponding meta knowledge, the corresponding answer can be obtained according to the meta knowledge, the generated question can be pushed to the user in advance or crawled through the network under the condition that the question generated under other conditions or the answer is difficult to be determined directly, and then the verified answer is taken as the answer of the question, so that when the user asks a question similar to the question, the corresponding answer can be directly called and provided for the user.
For example, it is determined from the historical questions and answers that the meta knowledge is "vinegar-specific action can prevent itching due to taro peeling by hand", the corresponding knowledge point is "vinegar", and "vinegar-specific action can prevent itching due to taro peeling by hand", which reflects a special purpose of "vinegar", so that a corresponding questioning mode can be selected according to the association relation "special purpose", an enumeration-type questioning mode that can reflect an unconventional purpose can be selected, and finally a new question generated according to the selected questioning mode can be "what unexpected use of vinegar? ".
Moreover, since the question mode is selected according to the association relationship between the knowledge points and the meta knowledge, the question can be generated, and the answer corresponding to the generated question can be determined according to the meta knowledge, namely that if the two hands itch due to taro scratching, a little vinegar can be added into the clear water, and the itching can be relieved after washing. Thus, when a user is interested in a particular use of vinegar when using the knowledge system, the problem posed is likely to be more than the above-described problem "what unexpected use did vinegar? In the matching process, the knowledge system can push a predetermined answer to the user, wherein if the two hands itch due to taro scraping, a little vinegar can be added into clear water, and itching can be relieved after washing is finished, and the answer has high possibility of meeting the requirements of the user, so that the use experience of the user is improved.
Fig. 2 is a device structure diagram of a problem generation device provided in an embodiment of the present application, where the device includes an acquisition unit 201, a determination unit 202, an extraction unit 203, and a generation unit 204:
the obtaining unit 201 is configured to obtain a history question;
the determining unit 202 is configured to determine, according to a question type of the historical question, a feature extraction rule corresponding to the question type;
the extracting unit 203 is configured to extract a knowledge point from the answer of the historical question according to the feature extraction rule;
the generating unit 204 is configured to generate a problem according to the knowledge point.
Optionally, the extracting unit includes: a meta knowledge extraction subunit and a knowledge point determination subunit;
the meta knowledge extracting subunit is configured to extract meta knowledge from the answers to the historical questions according to the feature extraction rule, where the meta knowledge is used to embody knowledge content associated with the knowledge points in the answers to the historical questions;
and the knowledge point determining subunit is used for determining the knowledge point according to the meta-knowledge and the answers of the historical questions.
Optionally, the generating unit includes: selecting a subunit and generating a subunit;
the selecting subunit is used for selecting a corresponding question mode according to the incidence relation between the meta-knowledge and the knowledge points;
and the generating subunit is used for generating the question according to the selected question mode and the knowledge point.
Optionally, the apparatus further includes an answer determining unit, configured to determine a corresponding answer for the generated question according to the meta-knowledge.
Optionally, the extracting unit includes a knowledge point extracting subunit, configured to extract a knowledge point from the answer to the historical question according to the feature extraction rule in combination with the historical question.
Optionally, the generating unit is further configured to generate a question according to a preset question mode and the knowledge point.
Therefore, through the acquired historical questions, the feature extraction rule corresponding to the question type can be determined according to the question type of the historical questions, the knowledge points are extracted from the answers of the historical questions according to the feature extraction rule, and new questions are generated according to the knowledge points, so that the number of the questions in the knowledge system is expanded, the questions stored in the knowledge system can not be obtained only according to the questions asked by the user any more, a brand-new question expansion mode is expanded, and the question retention amount in the knowledge system is effectively increased. Moreover, the extracted knowledge points are related to the knowledge content which the user may want to know, so that the problem generated according to the knowledge points is likely to be the problem which the user wants to know the knowledge points, when the user proposes the problem, the knowledge system can quickly provide the answer to the problem, the situation that the user asks the question only to wait for the answer of other users is reduced to a certain extent, and the experience of the user in using the knowledge system is improved.
Fig. 3 is a block diagram illustrating an apparatus 300 for speech synthesis according to an example embodiment. For example, the apparatus 300 may be a robot, a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.
Referring to fig. 3, the apparatus 300 may include one or more of the following components: processing component 302, memory 304, power component 306, multimedia component 308, audio component 310, input/output (I/O) interface 312, sensor component 314, and communication component 316.
The processing component 302 generally controls overall operation of the device 300, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing elements 302 may include one or more processors 320 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 302 can include one or more modules that facilitate interaction between the processing component 302 and other components. For example, the processing component 302 may include a multimedia module to facilitate interaction between the multimedia component 303 and the processing component 302.
The memory 304 is configured to store various types of data to support operations at the apparatus 300. Examples of such data include instructions for any application or method operating on device 300, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 304 may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The power supply component 306 provides power to the various components of the device 300. The power components 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the apparatus 300.
The multimedia component 308 includes a screen that provides an output interface between the device 300 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 308 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 300 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 310 is configured to output and/or input audio signals. For example, audio component 310 includes a Microphone (MIC) configured to receive external audio signals when apparatus 300 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 304 or transmitted via the communication component 316. In some embodiments, audio component 310 also includes a speaker for outputting audio signals.
The I/O interface 312 provides an interface between the processing component 302 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor assembly 314 includes one or more sensors for providing various aspects of status assessment for the device 300. For example, sensor assembly 314 may detect an open/closed state of device 300, the relative positioning of components, such as a display and keypad of device 300, the change in position of device 300 or a component of device 300, the presence or absence of user contact with device 300, the orientation or acceleration/deceleration of device 300, and the change in temperature of device 300. Sensor assembly 314 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 314 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 316 is configured to facilitate wired or wireless communication between the apparatus 300 and other devices. The device 300 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication section 316 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 316 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 300 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.
In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 304 comprising instructions, executable by the processor 320 of the apparatus 300 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
A non-transitory computer readable storage medium having instructions therein which, when executed by a processor of a mobile terminal, enable the mobile terminal to perform a question generation method, the method comprising:
acquiring historical problems;
determining a feature extraction rule corresponding to the question type according to the question type of the historical question;
extracting knowledge points from the answers of the historical questions according to the feature extraction rules;
and generating a question according to the knowledge points.
Fig. 4 is a schematic structural diagram of a server in an embodiment of the present invention. The server 400 may vary significantly due to configuration or performance, and may include one or more Central Processing Units (CPUs) 422 (e.g., one or more processors) and memory 432, one or more storage media 430 (e.g., one or more mass storage devices) storing applications 442 or data 444. Wherein the memory 432 and storage medium 430 may be transient or persistent storage. The program stored on the storage medium 430 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 422 may be arranged to communicate with the storage medium 430, and execute a series of instruction operations in the storage medium 430 on the server 400.
The server 400 may also include one or more power supplies 424, one or more wired or wireless network interfaces 450, one or more input-output interfaces 458, one or more keyboards 454, and/or one or more operating systems 441, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium may be at least one of the following media: various media that can store program codes, such as read-only memory (ROM), RAM, magnetic disk, or optical disk.
It should be noted that, in the present specification, all the embodiments are described in a progressive manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus and system embodiments, since they are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only one specific embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (12)
1. A question generation method, wherein the method is performed by a processing device, the method comprising:
acquiring historical problems;
determining a feature extraction rule corresponding to the question type according to the question type of the historical question;
extracting knowledge points from the answers of the historical questions according to the feature extraction rules;
generating a question according to the knowledge points;
wherein, extracting knowledge points from the answers of the historical questions according to the feature extraction rules comprises:
extracting meta knowledge from the answers of the historical questions according to the feature extraction rules, wherein the meta knowledge is used for embodying knowledge content associated with the knowledge points in the answers of the historical questions;
and determining the knowledge point according to the meta-knowledge and the answers of the historical questions.
2. The method of claim 1, wherein generating a question based on the knowledge points comprises:
selecting a corresponding question mode according to the incidence relation between the meta-knowledge and the knowledge points;
and generating the question according to the selected question mode and the knowledge point.
3. The method of claim 2, further comprising, after said generating a question from said knowledge points:
and determining a corresponding answer for the generated question according to the meta-knowledge.
4. The method of claim 1, wherein extracting knowledge points from answers to the historical questions according to the feature extraction rules comprises:
and extracting knowledge points from the answers of the historical questions by combining the historical questions according to the feature extraction rules.
5. The method of claim 1 or 4, wherein the generating a question from the knowledge points comprises:
and generating a question according to a preset question mode and the knowledge point.
6. A question generation apparatus characterized by comprising an acquisition unit, a determination unit, an extraction unit, and a generation unit:
the acquisition unit is used for acquiring historical problems;
the determining unit is used for determining a feature extraction rule corresponding to the question type according to the question type of the historical question;
the extraction unit is used for extracting knowledge points from the answers of the historical questions according to the feature extraction rules;
the generating unit is used for generating a problem according to the knowledge point;
wherein the extraction unit includes: a meta knowledge extraction subunit and a knowledge point determination subunit;
the meta knowledge extracting subunit is configured to extract meta knowledge from the answers to the historical questions according to the feature extraction rule, where the meta knowledge is used to embody knowledge content associated with the knowledge points in the answers to the historical questions;
and the knowledge point determining subunit is used for determining the knowledge point according to the meta-knowledge and the answers of the historical questions.
7. The apparatus of claim 6, wherein the generating unit comprises: selecting a subunit and generating a subunit;
the selecting subunit is used for selecting a corresponding question mode according to the incidence relation between the meta-knowledge and the knowledge points;
and the generating subunit is used for generating the question according to the selected question mode and the knowledge point.
8. The apparatus according to claim 7, further comprising an answer determination unit for determining a corresponding answer for the generated question according to the meta knowledge.
9. The apparatus of claim 6, wherein the extraction unit comprises:
and the knowledge point extraction subunit is used for extracting knowledge points from the answers of the historical questions by combining the historical questions according to the feature extraction rules.
10. The apparatus according to claim 6 or 9, wherein the generating unit is further configured to generate a question according to a preset question pattern and the knowledge point.
11. A processing apparatus for problem generation comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured for execution by the one or more processors, the one or more programs including instructions for:
acquiring historical problems;
determining a feature extraction rule corresponding to the question type according to the question type of the historical question;
extracting knowledge points from the answers of the historical questions according to the feature extraction rules;
generating a question according to the knowledge points;
wherein, extracting knowledge points from the answers of the historical questions according to the feature extraction rules comprises:
extracting meta knowledge from the answers of the historical questions according to the feature extraction rules, wherein the meta knowledge is used for embodying knowledge content associated with the knowledge points in the answers of the historical questions;
and determining the knowledge point according to the meta-knowledge and the answers of the historical questions.
12. A machine-readable medium having stored thereon instructions, which when executed by one or more processors, cause an apparatus to perform the problem generation method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711092223.5A CN110019706B (en) | 2017-11-08 | 2017-11-08 | Question generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711092223.5A CN110019706B (en) | 2017-11-08 | 2017-11-08 | Question generation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110019706A CN110019706A (en) | 2019-07-16 |
| CN110019706B true CN110019706B (en) | 2021-11-19 |
Family
ID=67186774
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711092223.5A Active CN110019706B (en) | 2017-11-08 | 2017-11-08 | Question generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110019706B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378818B (en) * | 2019-07-22 | 2022-03-11 | 广西大学 | Personalized exercise recommendation method, system and medium based on difficulty |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902652A (en) * | 2014-02-27 | 2014-07-02 | 深圳市智搜信息技术有限公司 | Automatic question-answering system |
| CN104991965A (en) * | 2015-07-23 | 2015-10-21 | 上海智臻网络科技有限公司 | Method and apparatus for creating extended question based on standard question |
| CN105608199A (en) * | 2015-12-25 | 2016-05-25 | 上海智臻智能网络科技股份有限公司 | Extension method and device for standard questions in intelligent question answering system |
-
2017
- 2017-11-08 CN CN201711092223.5A patent/CN110019706B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902652A (en) * | 2014-02-27 | 2014-07-02 | 深圳市智搜信息技术有限公司 | Automatic question-answering system |
| CN104991965A (en) * | 2015-07-23 | 2015-10-21 | 上海智臻网络科技有限公司 | Method and apparatus for creating extended question based on standard question |
| CN105608199A (en) * | 2015-12-25 | 2016-05-25 | 上海智臻智能网络科技股份有限公司 | Extension method and device for standard questions in intelligent question answering system |
Non-Patent Citations (1)
| Title |
|---|
| "Generating Questions Automatically from Informational Text";Chen等;《Proceedings of the 2nd Workshop on Question Generation》;20090731;第3页第15行至第6页第32行 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110019706A (en) | 2019-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107037949B (en) | Split screen display method and device | |
| CN105338409B (en) | Network video preloading method and device | |
| CN105511777B (en) | Session display method and device on touch display screen | |
| EP3734472A1 (en) | Method and device for text processing | |
| CN111831806A (en) | Semantic integrity determination method and device, electronic equipment and storage medium | |
| WO2023040202A1 (en) | Face recognition method and apparatus, electronic device, and storage medium | |
| CN108766427B (en) | Voice control method and device | |
| CN104951522B (en) | Method and device for searching | |
| CN107943317B (en) | Input method and device | |
| CN111596832B (en) | Page switching method and device | |
| CN110019706B (en) | Question generation method and device | |
| CN108573697B (en) | Language model updating method, device and equipment | |
| CN110648657A (en) | Language model training method, language model construction method and language model construction device | |
| CN110213062B (en) | Method and device for processing message | |
| CN108108356B (en) | Character translation method, device and equipment | |
| CN110968523A (en) | Memory defragmentation method and device | |
| CN112988956A (en) | Method and device for automatically generating conversation and method and device for detecting information recommendation effect | |
| US9774730B2 (en) | Method, device, and system for telephone interaction | |
| CN113127613B (en) | Chat information processing method and device | |
| CN109917927B (en) | Candidate item determination method and device | |
| CN108762944B (en) | Processing method, device, equipment and medium of business system | |
| CN109120499B (en) | Information processing method and device | |
| CN112015281A (en) | Cloud association method and related device | |
| CN112732098A (en) | Input method and related device | |
| CN111339263A (en) | Information recommendation method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |