Knowledge base and its construction, retrieval method, question setting method and system based on it

Abstract

A knowledge base and its construction and retrieval methods, and a question-setting method and system based thereon. The knowledge base construction method includes: storing knowledge points of minimum granularity in a single entry to form the knowledge base. The present invention also proposes a question-setting method based on the knowledge base, including: retrieving the knowledge base to obtain a knowledge entry; dividing the knowledge entry into a plurality of content words; processing one or more content words according to the question type, thereby obtaining the question stem and answer to be set. The knowledge base constructed by the present invention has a simple structure and a fast retrieval speed, which is very convenient for primary and secondary school students to set questions of various types, and can greatly save storage space, save question-setting resources and costs.

Description

Technical Field

[0001] The present invention belongs to the technical field of data knowledge bases, and more specifically relates to a knowledge base and its construction method, retrieval method, question-setting method and system based thereon, as well as electronic equipment and computer-readable media using the same. Background Art

[0002] With the advancement of technology, various software to help students learn have emerged. One major category is question bank software. This type of software can provide students with exercises and test questions corresponding to grades and levels, and can automatically complete corrections and comments. It has become a good helper for students' learning.

[0003] The question bank contains a variety of question types, such as multiple-choice questions, fill-in-the-blank questions, true-or-false questions, and word problems. In student exercises, a concept is often tested repeatedly. For example, in mathematics, questions are often asked based on the deliberate lack of a feature in an axiom, theorem, or a certain rule, such as a multiplication formula. If every question is stored in the form of a question stem and an answer, a large amount of storage space will be wasted. In this case, when different questions are asked based on the same concept, the answers may be redesigned, stored, and searched from different angles and different question types. How to avoid wasting energy and costs is a question worth studying. Summary of the Invention

[0004] In view of this, the main purpose of the present invention is to propose a knowledge base and its construction, retrieval method, question-setting method and system based thereon, in order to at least partially solve at least one of the above-mentioned technical problems.

[0005] To achieve the above objectives, as a first aspect of the present invention, a method for constructing a knowledge base is provided, comprising the following steps:

[0006] The knowledge base is formed by storing the knowledge points of the smallest granularity in a single entry.

[0007] The minimum granularity of the knowledge point is an axiom, a theorem or a rule.

[0008] The step of storing the minimum-granularity knowledge points in a single entry to form a knowledge base includes: storing the minimum-granularity knowledge points in a single entry in the form of assertions to form the knowledge base; or extracting the entity relationships of the minimum-granularity knowledge points and storing them in a single entry using structured representation or knowledge graph representation to form the knowledge base.

[0009] Optionally, the step of storing the minimum-granularity knowledge points in a single entry in the form of assertions to form a knowledge base includes: extracting assertions from the knowledge to be stored, each extracted assertion corresponding to a minimum-granularity knowledge point; and storing each assertion in a single entry to form the knowledge base.

[0010] Preferably, when performing assertion extraction, the assertion statement is captured and segmented, and whether the segmented assertion is a complete assertion is determined based on the correlation between the segmented assertion and the context.

[0011] Optionally, the knowledge base also stores question information corresponding to the knowledge points.

[0012] Optionally, the question information includes at least one of the following: the subject category, applicable grade, and applicable student age group corresponding to the knowledge point.

[0013] As a second aspect of the present invention, a knowledge base is also provided, which is constructed by any of the construction methods described above.

[0014] As the third aspect of the present invention, a method for retrieving knowledge items is also provided, comprising the following steps: searching for a number of keywords in the knowledge base, and when all the keywords fall into a single entry in the knowledge base, it means that the retrieval hits the corresponding knowledge item, and the number of keywords are based on the knowledge points to be retrieved or the topics to be retrieved.

[0015] Optionally, when the plurality of keywords are based on the topic to be retrieved, the method further includes: identifying the type of the topic before retrieval; and when the type of the topic is a knowledge-based topic, searching the knowledge base for the plurality of keywords.

[0016] Optionally, before performing the search, the knowledge item search method further includes: searching for synonyms and / or approximate expressions of the keyword; and when searching in the knowledge base, using the keyword, and the synonyms and / or approximate expressions of the keyword for search.

[0017] As the fourth aspect of the present invention, a question-setting method based on a knowledge base is also provided, comprising the following steps: retrieving knowledge items in the knowledge base according to question-setting information provided by a question-setter; determining one or more knowledge items from the retrieved knowledge items as a basis for question-setting according to the question-setter's instructions; dividing each of the one or more knowledge items used as a basis for question-setting into a plurality of content words; and performing question-setting processing on one or more of the plurality of content words according to the question type, thereby obtaining a question stem and an answer to be set.

[0018] Optionally, the question types include multiple-choice questions, fill-in-the-blank questions, true-or-false questions, and / or error correction questions;

[0019] Preferably, the step of processing the content words according to the question type includes:

[0020] selecting at least one content word from the plurality of content words;

[0021] If it is a multiple-choice question, several phrases with different meanings from the selected content word are retrieved from the pre-set alternative answer library as options; if it is a true or false question or an error correction question, the selected content word is retained or replaced with another content word; if it is a fill-in-the-blank question, the selected content word is directly replaced with a blank and the selected content word is used as the answer;

[0022] Preferably, the following steps are included before the search: based on the question information, the search scope of the knowledge base is limited to the corresponding question range, and then the search is performed within the question range based on the question information.

[0023] As a sixth aspect of the present invention, a question-setting system based on a knowledge base is also provided, comprising:

[0024] A knowledge point retrieval unit randomly retrieves knowledge items from the knowledge base as described above based on the question information provided by the question setter;

[0025] The knowledge point segmentation unit is used to segment the retrieved knowledge items into multiple independent content words;

[0026] The question-setting unit is used to process one or more content words according to the specified question type to obtain the question stem and answer.

[0027] As a seventh aspect of the present invention, an electronic device is also provided, including a processor and a memory, wherein the memory is used to store a computer executable program, and when the computer executable program is executed by the processor, the processor executes the method as described above.

[0028] As an eighth aspect of the present invention, a computer-readable medium is further provided, storing a computer-executable program, which implements the method described above when executed.

[0029] Based on the above technical solutions, it can be seen that the knowledge base and its construction, retrieval method, and question-setting method and system based on the present invention have at least one of the following beneficial effects compared to the prior art:

[0030] The knowledge base designed by the present invention is different from the existing multi-project and multi-grid knowledge bases. It simply collects single knowledge items one by one, which saves space, simplifies the database structure, and reduces the search time.

[0031] The knowledge base designed by the present invention can be used in a unique way in the question-generating system. Through the auxiliary processing of the knowledge base auxiliary system, various types of test questions can be flexibly and flexibly generated, which greatly simplifies the storage space of test questions with the same concept and saves design time and cost.

[0032] The question-setting system designed in the present invention splits the question information (generally including the question stem and answer information) into the finest-grained knowledge assertions, so that no matter how they are arranged and combined, the corresponding resources can be found in the knowledge base of the present invention according to the minimum granularity to complete the question setting and answering, thereby greatly saving storage resources and the cost of question development and answering. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of the data structure of the knowledge base of the present invention;

[0034] Figure 2 is a schematic diagram of the method for constructing and maintaining a knowledge base of the present invention;

[0035] Figure 3 It is a block flow chart of the question-setting method of the present invention;

[0036] Figure 4 is a schematic structural diagram of an electronic device of the present invention;

[0037] Figure 5 is a schematic diagram of a computer-readable recording medium of the present invention; DETAILED DESCRIPTION

[0038] In the introduction of specific embodiments, the detailed description of the structure, performance, effect or other features is intended to enable those skilled in the art to fully understand the embodiments. However, this does not preclude those skilled in the art from implementing the present invention with a technical solution that does not include the aforementioned structure, performance, effect or other features under specific circumstances.

[0039] The flowcharts in the accompanying drawings are merely illustrative of the process flow and do not necessarily include all of the content, operations, and steps in the flowcharts, nor do they necessarily imply that all of the steps in the flowcharts must be executed in the order shown. For example, some of the steps in the flowcharts may be separated, some may be combined or partially combined, and so on. The execution order shown in the flowcharts may be changed according to actual circumstances without departing from the spirit of the present invention.

[0040] Frames in the accompanying drawings Figure 1The term "functional entity" generally refers to a functional entity and does not necessarily correspond to a physically independent entity. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processing unit devices and / or microcontroller devices.

[0041] The same reference numerals in the accompanying drawings represent the same or similar elements, components or parts, and thus repeated descriptions of the same or similar elements, components or parts may be omitted below. It should also be understood that although the first, second, third and other numbered adjectives may be used herein to describe various devices, elements, components or parts, these devices, elements, components or parts should not be limited by these adjectives. In other words, these adjectives are only used to distinguish one from another. For example, the first device may also be called the second device, but this does not deviate from the essential technical solution of the present invention. In addition, the terms "and / or" and "and / or" refer to all combinations including any one or more of the listed items.

[0042] The present invention is proposed in response to the situation where a concept is often tested repeatedly in current student exercises. For example, in the field of mathematics, for an axiom, theorem or a certain rule, such as the multiplication formula, questions are often asked based on the deliberate lack of a feature. If each question is stored in the form of question stem-answer, a large amount of storage space will be wasted. In addition, when asking questions for the same concept, it is necessary to repeatedly redesign, store and search for answers from different angles, which also results in a great waste of energy and cost.

[0043] Based on this, the present invention proposes a method for constructing a knowledge base, comprising: storing knowledge points of minimum granularity in a single entry to form the knowledge base.

[0044] Preferably, the knowledge points are stored in a single entry in the form of assertions to form the knowledge base. Subsequently, test questions can be formed based on the entry, or questions that test knowledge can be obtained by querying the entries in the knowledge base.

[0045] Among them, the knowledge point described in this embodiment is, for example, an axiom, a theorem, or a rule, such as "two parallel lines never intersect", "the sum of the three internal angles of a triangle is 180°", "four eight three two", and so on.

[0046] Among them, the "minimum granularity" here is a limitation on knowledge points, requiring that the stored knowledge points are independent of each other, cannot be further divided, and are logically complete. A minimum granularity knowledge point only involves one knowledge point, rather than a combination of multiple knowledge points. However, it should be noted that although the knowledge point here is of minimum granularity and cannot be further divided, it is still a complete narrative, rather than an isolated noun or concept. For example, the knowledge point is an axiom, a theorem, or a rule, such as "two parallel lines never intersect", "the sum of the three internal angles of a triangle is 180°", "four eight three two", etc. A negative example is that only a noun concept, such as "triangle" or "inner angle" cannot constitute a knowledge point here.

[0047] The method of the present invention can be further optimized as follows:

[0048] Storing the minimum granularity knowledge point in a single entry in the form of assertions to form the knowledge base; or

[0049] The entity relationships of the minimum-granularity knowledge points are extracted and stored in a single entry using a structured representation or a knowledge graph representation to form the knowledge base.

[0050] In the present invention, "assertion" is originally a term in the field of programming, representing some Boolean expressions. It is borrowed here to represent a statement that expresses affirmation, because it is generally necessary for a description to be included in the knowledge base to be correct and complete, without defects, doubts, or rhetorical questions. In the present invention, the earliest research and development ideas came from mathematical problems, but the knowledge points are not limited to mathematics. For example, physics, chemistry, history, geography, etc. can also be used. As long as the knowledge points can form a complete logical closed loop (assertion) that is recognized by everyone, the content of the rest can be accurately determined based on the majority of the content. Examples from other fields include: "A normal human has 23 pairs of chromosomes" in biology, etc. However, for open-ended questions, it is impossible to form an assertion. For example, "What is your ideal career in life?" can answer "teacher", "entrepreneur", "scientist", etc. Various answers can be given. Since everyone's views are different, there is no standard answer, and it is impossible to form an assertion for inclusion.

[0051] The structured representation or knowledge graph representation herein is, for example, a representation known in the art, which is a text representation of a plurality of content words with a structure or relationship generated by a graphic such as a mind map or by inserting tags or specific symbols. Text representation is preferably used here because it is easier to store and further process.

[0052] The specific steps of storing the smallest granularity knowledge points in a single entry in the form of assertions to form a knowledge base may include, for example:

[0053] Perform assertion extraction on the knowledge to be stored, and each extracted assertion corresponds to a knowledge point of minimum granularity;

[0054] Storing each assertion in a single entry to form the knowledge base;

[0055] The assertion extraction step may also include capturing and segmenting the assertion statement, and determining whether the segmented assertion is complete based on its relevance to the context. Through assertion recognition and segmentation, the smallest granularity of knowledge points can be captured.

[0056] The knowledge base also stores question information corresponding to the knowledge points;

[0057] The question information may include, for example, at least one of the following: the subject category, applicable grade, applicable student age group, common / reference examination points, etc. corresponding to the knowledge point. The question information may be stored in the same entry as the knowledge point or independently, but the two may maintain a corresponding relationship. The present invention also provides a knowledge base constructed using the construction method described above.

[0058] like Figure 1 As shown, the structure of this knowledge base is very simple, consisting of index numbers and knowledge entries. It can also be appropriately expanded to include entries such as subject categories, applicable grades, and applicable age groups. Since the entries are very simple, a lot of storage space can be saved.

[0059] The present invention also proposes a method for retrieving knowledge items based on the above-mentioned knowledge base, which specifically includes the following steps:

[0060] Determine a number of keywords for retrieval, wherein the keywords may be based on, for example, the knowledge points to be retrieved or the topics to be retrieved;

[0061] The plurality of keywords are searched in the knowledge base. When all the keywords fall into a single entry in the knowledge base, it means that the search has hit the corresponding knowledge entry.

[0062] The step of determining the keywords to be used for the search can involve, for example, directly entering the keywords to be searched for, or determining the keywords from existing questions. When setting questions, keywords can be determined based on the knowledge points to be searched, or the question information can include, for example, the grade, subject, and difficulty level of the students to be tested. In scenarios where the answers to questions are retrieved, such as by taking a photo to search, keywords can be extracted / generated from the search questions.

[0063] Preferably, the search topic is obtained by, for example, taking a photo, scanning and identifying an image, or crawling the Internet, and keywords are captured therefrom by conventional text processing, segmenting the text, removing stop words, and sorting to obtain corresponding keywords.

[0064] The knowledge base may also pre-establish an index table, extract corresponding keywords from knowledge items and / or corresponding question information to establish an index table, and searching through the index table can standardize invalid search results in keyword searches.

[0065] Among them, before using keywords for retrieval, they can also be expanded, for example, by first looking for synonyms of the keywords or their approximate expressions, so as to avoid certain non-standard expressions that are not included in the knowledge base and cannot hit the corresponding knowledge entries. For example, "the sum of the three internal angles of a triangle is 180°" can usually be retrieved using the keywords "triangle", "sum of internal angles" and "180°". If the keyword "sum of triangle" is entered for retrieval, no results will be retrieved. In this way, an extended library of synonyms and approximate expressions can be established for some keywords. Before using them to search in the knowledge base, it is first checked in the extended library whether there are synonyms and / or approximate expressions. After changing to a different expression for retrieval, the correct knowledge entry may be retrieved.

[0066] The specific steps of the expansion are, for example, to search for synonyms or similar expressions of the keyword, and to search for them simultaneously with the original keyword in an "or" manner. Thus, the search method includes, for example, the following sub-steps:

[0067] (1) Expand the knowledge points (keywords) to be retrieved (search for synonyms, approximate expressions, etc. in the predefined synonym database, or by looking up a dictionary or both);

[0068] (2) All knowledge points (keywords) are searched in the knowledge base in the form of "or" to find knowledge items that meet all the search conditions at the same time.

[0069] Among them, in order to avoid the situation where a certain expression exceeds the synonym library of the included keywords, it is recommended that the knowledge base include as many different expressions as possible for the same knowledge point. Because although the keywords are expanded as much as possible during retrieval, there are still some changes in the expression that the machine cannot fully recognize. Therefore, it is recommended to include as many variations of the same knowledge point as possible in the knowledge base to avoid omissions. For example, for "the sum of the three internal angles of a triangle is 180°", another way to say it is "one internal angle in a triangle is equal to 180° minus the difference between the other two internal angles". Continuing to deduce, we can get "the supplementary angle of an internal angle in a triangle is equal to the sum of the other two non-adjacent internal angles". These three can be stored as three knowledge items.

[0070] In other embodiments, variants of the same knowledge point can be stored in the same entry. During retrieval, after hitting the entry with keywords, the question to be retrieved is then compared with the various variants of the same knowledge point in the same entry, and the most matching one is given as the retrieval result based on the comparison results.

[0071] The present invention also proposes a method for modifying / maintaining the above-mentioned knowledge base, which specifically includes the following steps:

[0072] A single entry that needs to be modified is located in the knowledge base as described above, and the knowledge entry is deleted, modified and / or updated.

[0073] The step of locating is achieved by the above-mentioned search method, and a single item that needs to be modified can be located by using keywords.

[0074] The present invention also proposes a method for setting questions based on the above-mentioned knowledge base, which specifically includes the following steps:

[0075] Retrieving knowledge items in the knowledge base according to the question information provided by the question setter, wherein the question information includes but is not limited to, for example, subject, grade, knowledge point keywords, etc.;

[0076] According to the instruction of the question setter, one or more knowledge items are determined from the retrieved knowledge items as the basis for setting questions;

[0077] Segmenting each of the one or more knowledge items used as a basis for setting questions into a plurality of content words;

[0078] One or more of the multiple nouns are processed according to the question type, that is, the question stem and answer to be asked are obtained; question processing refers to removing one or more of the multiple nouns, replacing them with easily confused nouns, replacing them with antonyms, etc. according to the question type.

[0079] The question types may include, for example, multiple-choice questions, fill-in-the-blank questions, true-or-false questions, and / or error correction questions. However, the question types are not limited to these. As the variety of questions increases, the question types may also include other types such as connect-the-dot questions, balloon questions, etc., as long as the question itself has a relatively closed and fixed answer.

[0080] The steps of processing content words according to the question type may include but are not limited to:

[0081] selecting at least one content word from the plurality of content words;

[0082] If it is a multiple-choice question, a predetermined number of options with synonyms or different meanings as the selected noun will be retrieved from the alternative library; among them, since multiple-choice questions include three-choice, four-choice, multiple-choice, etc., including single-choice, multiple-choice and indefinite-choice, the correct answer may not be unique, and the options are not required to be only four.

[0083] If it is a true or false question or an error correction question, keep the original content word unchanged or replace it with other content words; the other content words can be synonymous or different in meaning.

[0084] If it is a fill-in-the-blank question, simply match several content words to the blank positions and use them as the answer. For some fill-in-the-blank questions, there may be multiple blanks to fill in.

[0085] Optionally, the knowledge base may also store a database of questions corresponding to the knowledge points for reference by question setters when setting questions. However, when searching for answers to questions, this database can be set to be invisible to the searcher. The questions in the database can include, for example, questions based on the same knowledge point collected during a photo search.

[0086] The alternative library used when setting questions can be set in advance, or it can be based on the relevant nouns extracted from various questions based on the same knowledge point collected in scenarios such as photo search.

[0087] When setting a question, if the question setter clicks or boxes one or more nouns as a test point, the selected nouns will be automatically blurred, and related nouns selected from a library will appear nearby as question suggestions. For the simple item "The sum of the interior angles of a triangle is 180 degrees," when the question setter clicks or boxes "Triangle," the "Triangle" will be blurred, and menus such as "Replace with brackets ()?" and "Replace with bracketed quadrilateral?" will appear next to the "Triangle" position, assisting the question setter in question preparation and simplifying the question setting process.

[0088] Among them, before the search, the following steps may also be included: according to the question information, the search scope of the knowledge base is limited to the corresponding question range, and then the search is performed within the question range according to the question information.

[0089] The narrowing down to the corresponding question range refers to limiting the search scope to knowledge points of the grade or subject that meet the needs of the question setter based on question information such as the grade and subject to which the knowledge point belongs.

[0090] In addition, this question-setting method does not exclude the possibility of simultaneously retrieving multiple different single knowledge items and combining them to set questions. However, since such a question-setting method involves the cross-use of multiple knowledge items, a stronger semantic logic recognition system is required to avoid conflicts and errors.

[0091] The present invention also proposes a question-setting system based on the above-mentioned knowledge base, which specifically includes:

[0092] a questioner instruction input unit, used to input the questioner's instructions and / or information;

[0093] A knowledge point retrieval unit, configured to retrieve knowledge items in the knowledge base based on the instruction and / or information of the question setter;

[0094] A knowledge point segmentation unit, configured to segment the knowledge items retrieved by the knowledge point retrieval unit into a plurality of independent content words;

[0095] The question setting unit is used to process one or more of the content words output by the knowledge point segmentation unit according to the question type specified by the question setter to obtain the question stem and answer.

[0096] The question types include, for example, multiple-choice questions, fill-in-the-blank questions, true-or-false questions, and / or error correction questions.

[0097] The knowledge point search unit may also narrow the search scope to knowledge points of the grade or level that meets the needs of the question setter according to the classification of the knowledge points.

[0098] The steps of processing the content words according to the question type by the question setting unit include, but are not limited to:

[0099] If it is a multiple-choice question, a preset number of multiple-choice question options that are synonymous or different in meaning with the selected content word are retrieved from a pre-established alternative library;

[0100] If it is a true or false question or an error correction question, keep the original content word unchanged or replace it with another content word;

[0101] If it is a fill-in-the-blank question, directly match the content word to the blank position and use it as the answer.

[0102] The present invention also discloses an electronic device, which includes a processor and a memory, wherein the memory is used to store a computer executable program, wherein when the computer executable program is executed by the processor, the processor executes the method as described above.

[0103] The electronic device may be, for example, a general-purpose computing device. The processor may be one or multiple processors operating in concert. The present invention also does not exclude distributed processing, meaning that the processors may be dispersed across different physical devices. The electronic device of the present invention is not limited to a single entity but may also be the sum of multiple physical devices.

[0104] The memory stores a computer executable program, usually a machine-readable code, which can be executed by the processor to enable the electronic device to perform the method of the present invention, or at least some steps in the method.

[0105] The memory includes a volatile memory, such as a random access memory unit (RAM) and / or a cache memory unit, and may also be a non-volatile memory, such as a read-only memory unit (ROM).

[0106] Optionally, in this embodiment, the electronic device further includes an I / O interface for exchanging data with an external device. The I / O interface can represent one or more of several types of bus structures, including a storage unit bus or storage unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus structures.

[0107] The electronic devices of the present invention may also include elements or components not shown in the above examples. For example, some electronic devices also include display units such as screens, and some electronic devices also include human-computer interaction elements such as buttons and keyboards. As long as the electronic device can execute a computer-readable program stored in its memory to implement the method of the present invention or at least some of the steps of the method, it is considered an electronic device covered by the present invention.

[0108] The present invention also discloses a computer-readable medium having a computer-executable program stored thereon, wherein when the computer-executable program is executed, the method described above is implemented.

[0109] Computer-readable storage media may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0110] The program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Python, Java, C++, and the like, as well as conventional procedural programming languages ​​such as C, assembly language, or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a standalone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0111] To make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to specific embodiments and accompanying drawings. It should be noted that the following embodiments are only used to illustrate the present invention and are not used to limit the present invention.

[0112] Example 1

[0113] Figure 1 is a schematic diagram of the data structure of the knowledge base of the present invention, Figure 2 Schematic diagram of the knowledge base construction and maintenance method of the present invention. Figure 1 、 2 As shown, the method for constructing a knowledge base in this embodiment specifically includes the following steps:

[0114] The knowledge base is formed by storing knowledge points in a single entry in the form of assertions.

[0115] The figure uses the mathematical knowledge points "the sum of the three internal angles of a triangle is 180°" and "four eight three two" as examples. Figure 1 As shown, you can see that each knowledge point is stored in the form of an entry.

[0116] Figure 4 This is a structural diagram of an electronic device according to embodiment 1 of the present invention. The electronic device includes a processor and a memory, wherein the memory is used to store a computer executable program. When the computer executable program is executed by the processor, the processor executes the method described above.

[0117] Figure 5 is a schematic diagram of a computer-readable recording medium according to embodiment 1 of the present invention, Figure 5 As shown, a computer-readable recording medium stores a computer-executable program, and when the computer-executable program is executed, the method of the present invention as described above is implemented.

[0118] Example 2

[0119] This embodiment is a knowledge base retrieval method, which specifically includes the following steps:

[0120] Several index words are searched in the knowledge base. When all the index words fall into a single entry in the knowledge base, it means that the corresponding knowledge entry is retrieved.

[0121] The index words to be retrieved are expanded (synonyms and approximate expressions are searched), and then all index words are searched in the knowledge base in the form of "or" to find knowledge items that meet all the search conditions at the same time.

[0122] For example, the index terms "triangle" and "180°" can be expanded to "trilateral", "flat angle", "one hundred and eight", "one hundred and eighty degrees", etc.

[0123] Searching the above index terms in the knowledge base yields the following entries:

[0124] “The sum of the three interior angles of a triangle is 180°”;

[0125] "An interior angle in a triangle is equal to 180° minus the difference of the other two interior angles";

[0126] "The sum of an interior angle of a triangle and its complementary angle is 180°"

[0127] …

[0128] If we add the index term "sum of interior angles", we can accurately locate "the sum of the three interior angles of a triangle is 180°".

[0129] Example 3

[0130] like Figure 3 As shown, the question-setting method based on the knowledge base of this embodiment includes the following steps:

[0131] In the knowledge base as described above, the scope of questions is limited to a suitable range, and then a corresponding single entry is randomly retrieved within the range, which is divided into multiple content words. One of the content words is processed according to the question type to obtain the question stem and answer.

[0132] Here, we also take the above knowledge item "The sum of the three internal angles of a triangle is 180°" as an example. For example, if we want to give a junior high school geometry test, the question types include multiple-choice questions, fill-in-the-blank questions, and true-or-false questions. After retrieving this knowledge item, the system first splits it into "triangle", "three internal angles", "sum of internal angles", and "180°". Then, according to the question type, it processes one of the content words, such as "180°", including:

[0133] Multiple-choice questions: Randomly search for several options with different meanings from the selected content word from the candidate database. The search results include "120°", "150°", "210°", etc., and "180°" as options A, B, C, and D.

[0134] True or False: Keep the original content word unchanged, that is, judge whether "the sum of the three internal angles of a triangle is 180°" is correct; when replacing it with other content words, for example, using "150°" instead of "180°", judge whether "the sum of the three internal angles of a triangle is 150°" is correct;

[0135] For fill-in-the-blank questions, simply match the content words to the blanks, for example, "The sum of the three internal angles of a triangle is", the answer is "180°".

[0136] Through the description of the above implementation methods, it is easy for technical personnel in this field to understand that the knowledge base constructed by the present invention has a simple structure and a fast retrieval speed, which is very convenient for primary and secondary school students to change questions of various types, and can greatly save storage space, save question-setting resources and costs.

[0137] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the present invention is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can also implement the present invention. The above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. A method for constructing a knowledge base, characterized in that: Storing the minimum-granularity knowledge points in a single entry to form the knowledge base includes: extracting assertions from the knowledge to be stored, wherein each extracted assertion corresponds to a minimum-granularity knowledge point, and storing each assertion in a single entry to form the knowledge base; The assertion represents a positive statement and a correct description; and, when performing assertion extraction, the assertion statement is captured and segmented, and based on the relevance of the segmented assertion to the context, it is determined whether the segmented assertion is a recognized complete logical closed loop that represents a positive statement; Among them, the smallest granularity of knowledge points indicates that multiple knowledge points form a complete narrative that is independent of each other and cannot be further divided, and are logically complete; Storing question information corresponding to the knowledge points of the minimum granularity in the knowledge base, and extracting corresponding keywords from the knowledge items and / or the corresponding question information to establish an index table and a knowledge base structure including index numbers and knowledge items; The minimum granularity of the knowledge point is an axiom, a theorem or a rule.

2. The method for constructing a knowledge base according to claim 1, wherein: The question information includes at least one of the following: the subject category corresponding to the knowledge point, the applicable grade, the applicable student age group, and the examination point.

3. A knowledge base, characterized in that: The knowledge base is constructed by the method for constructing the knowledge base according to any one of claims 1 to 2.

4. A knowledge item retrieval method based on a knowledge base, characterized in that: include: Constructing the knowledge base according to claim 3 by the method according to any one of claims 1 to 2; Directly input keywords to be searched or extract or generate keywords to be searched from existing topics to determine a number of keywords for search, wherein the keywords are based on the knowledge points to be searched or the topics to be searched; Searching for a plurality of keywords in the knowledge base, and when all keywords fall into a single entry in the knowledge base, it indicates that the search has hit the corresponding knowledge entry; Wherein, when the plurality of keywords are based on the topic to be searched, the type of the topic is identified before the search is performed; and when the type of the topic is a knowledge-based topic, the plurality of keywords are searched in the knowledge base.

5. The knowledge item retrieval method according to claim 4, characterized in that: Before searching for a plurality of keywords in the knowledge base, the method further includes: searching for synonyms and / or approximate expressions of the keywords to establish an extended library of the keywords; Searching the knowledge base for a plurality of keywords also includes: searching using the keywords and synonyms and / or approximate expressions of the keywords.

6. A question-setting method based on a knowledge base, characterized in that: include: Constructing the knowledge base according to claim 3 by the method according to any one of claims 1 to 2; Retrieving knowledge items from the knowledge base according to the question information provided by the question setter; According to the instruction of the question setter, one or more knowledge items are determined from the retrieved knowledge items as the basis for setting questions; Segmenting each of the one or more knowledge items used as a basis for setting questions into a plurality of content words; Performing question processing on one or more of the multiple content words according to the question type, that is, obtaining a question stem and an answer to be asked; The question types include multiple choice questions, fill-in-the-blank questions, true / false questions and / or error correction questions; The step of processing the content words according to the question type includes: selecting at least one content word from the plurality of content words; If it is a multiple-choice question, several phrases with different meanings from the selected content word are retrieved from a pre-set alternative answer library as options; If it is a true or false question or an error correction question, keep the selected content word unchanged or replace it with another content word; If it is a fill-in-the-blank question, simply replace the selected content word with the blank and use the selected content word as the answer; Furthermore, before the search, the following steps are also included: based on the question information, the search scope of the knowledge base is limited to the corresponding question range, and then the search is performed within the question range based on the question information.

7. A question setting system based on a knowledge base, characterized in that: include: Constructing the knowledge base according to claim 3 by the method according to any one of claims 1 to 2; A knowledge point retrieval unit, which retrieves knowledge items in the knowledge base according to the question information provided by the question setter; The knowledge point segmentation unit is used to segment the retrieved knowledge items into multiple independent content words; The question-setting unit is used to process one or more content words according to the specified question type to obtain the question stem and answer.

8. An electronic device comprising a processor and a memory, wherein the memory is used to store a computer executable program, wherein: When the computer-executable program is executed by the processor, the processor performs the method according to any one of claims 1 to 2 and 4 to 6.

Images