CN116308931A

CN116308931A - Method, device, equipment and medium for explaining calculation questions

Info

Publication number: CN116308931A
Application number: CN202310351171.8A
Authority: CN
Inventors: 李明; 张西群; 金宇; 袁光辉
Original assignee: Shenzhen Xingtong Technology Co ltd
Current assignee: Shenzhen Xingtong Technology Co ltd
Priority date: 2023-03-24
Filing date: 2023-03-24
Publication date: 2023-06-23

Abstract

The present disclosure relates to a method, apparatus, device, and medium for interpreting a calculation question, including: acquiring a calculation question to be explained; analyzing the calculation title into a formula term and a sub-formula, and determining a first type attribute of the formula term and a second type attribute of the sub-formula; classifying the calculation types of the calculation questions under different granularities based on the formula items, the first type attribute, the sub-formula and the second type attribute to obtain target calculation types of the calculation questions; and determining a target solving method corresponding to the target computing type according to a preset matching relation between the computing type and the solving method. The technical scheme can improve the classification accuracy of the calculation questions, and is easy to match with a target solving method suitable for the calculation questions.

Description

Method, device, equipment and medium for explaining calculation questions

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for explaining a calculation problem.

Background

Automatic lecture is an important application of artificial intelligence technology in education field, and it can obtain proper lecture method in single topic mode (e.g. vertical calculation) or similar topic mode (e.g. two general calculation and vertical calculation). However, when the problems of abundant types of questions and a plurality of mathematical questions of the solving methods are faced, the calculation types are difficult to accurately classify, so that the current automatic question-teaching method cannot support the explanation of complex questions, and it is difficult to match proper question-teaching methods for different calculation types of questions through a simple strategy.

Disclosure of Invention

In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a method, an apparatus, a device, and a medium for teaching the calculation of the subject.

According to an aspect of the present disclosure, there is provided an explanation method of calculating a topic, including:

acquiring a calculation question to be explained;

analyzing the calculation title into a formula term and a sub-formula, and determining a first type attribute of the formula term and a second type attribute of the sub-formula;

classifying the calculation types of the calculation questions under different granularities based on the formula item, the first type attribute, the sub-formula and the second type attribute to obtain target calculation types of the calculation questions;

and determining a target solving method corresponding to the target computing type according to a preset matching relation between the computing type and the solving method.

According to another aspect of the present disclosure, there is provided an explanation device for calculating a topic, including:

the title acquisition module is used for acquiring a calculation title to be explained;

the title analyzing module is used for analyzing the calculation title into a formula item and a sub-formula, and determining a first type attribute of the formula item and a second type attribute of the sub-formula;

the classification module is used for classifying the calculation type of the calculation question under different granularities based on the formula item, the first type attribute, the sub-formula and the second type attribute to obtain a target calculation type of the calculation question;

and the problem solving module is used for determining a target problem solving method corresponding to the target calculation type according to a preset matching relation between the calculation type and the problem solving method.

According to another aspect of the present disclosure, there is provided an electronic device including:

a processor;

a memory for storing the processor-executable instructions;

the processor is used for reading the executable instructions from the memory and executing the instructions to realize the explanation method of the calculation problem.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions that, when executed on a terminal device, cause the terminal device to implement a method of interpreting a calculation question.

Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:

the explanation method, device, equipment and medium for the calculation questions provided in the embodiment of the application comprise the following steps: acquiring a calculation question to be explained; analyzing the calculation title into a formula term and a sub-formula, and determining a first type attribute of the formula term and a second type attribute of the sub-formula; classifying the calculation types of the calculation questions under different granularities based on the formula items, the first type attribute, the sub-formula and the second type attribute to obtain target calculation types of the calculation questions; and determining a target solving method corresponding to the target computing type according to a preset matching relation between the computing type and the solving method. The technical scheme can improve the classification accuracy of the calculation questions, and is easy to match with a target solving method suitable for the calculation questions.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.

In order to more clearly illustrate the embodiments of the present disclosure or the solutions in the prior art, the drawings that are required for the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.

FIG. 1 is a flow chart of a method for teaching the purpose of calculation questions provided in an embodiment of the disclosure;

fig. 2 is a schematic diagram of a formula tree structure according to an embodiment of the disclosure;

FIG. 3 is a schematic diagram of a device for explaining the calculation of the subject according to the embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.

Detailed Description

In order that the above objects, features and advantages of the present disclosure may be more clearly understood, embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below. It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The main flow of the automatic lecture comprises: photographing the questions, recognizing the formula text in the question image through an OCR model, processing the formula text through a preset automatic questions generation model, generating questions sequences and questions voice, and playing and displaying the questions through the front-end questions sequences and the questions voice. For automatic explanation of mathematical calculation questions, only some question types with primary comparison can be explained at present, such as vertical type, comparison size of two numbers and general four-rule mixed operation. But cannot support the explanation of complex questions such as calculation, calculation comparison, one question multiple explanation, etc. Therefore, it is difficult to match the proper question method to the questions with different calculation types through a simple strategy in the prior automatic question solving.

Based on the above situation, in order to better realize automatic explanation of various types of mathematical calculation questions, and expand the capability of automatic explanation of the mathematical calculation questions, the embodiments of the present disclosure provide an explanation method, apparatus, device and medium for calculating the questions; according to the method, the computing questions are analyzed into the formula items and the sub-formulas with higher refinement degree, and the computing types of the computing questions can be classified under different granularities by utilizing the formula items, the first type attribute of the formula items, the sub-formulas and the second type attribute of the formula items, so that the classification accuracy of the computing types is improved; under the condition of determining the target calculation type, the method is easy to be matched with a proper target solving method. For ease of understanding, embodiments of the present disclosure are described below.

Referring to fig. 1, a flowchart of a method for explaining the calculation of the subject may include the steps of:

step S102, obtaining a calculation question to be explained.

In one embodiment, an image containing calculation questions can be obtained through image shooting operation or image uploading operation and the like, and the calculation questions in LaTeX format are extracted from the image; calculation questions are as usual mathematical calculation questions.

Step S104, analyzing the calculation title into a formula term and a sub-formula, and determining a first type attribute of the formula term and a second type attribute of the sub-formula.

The present embodiment may include: and analyzing the element entity with the semantics in the calculation subject to obtain a formula term and a first type attribute of the formula term. During specific analysis, the element entity in the calculation question can be analyzed through a preset formula analyzer; elemental entities include, but are not limited to: formula connectors, operators, and algebraic signs representing numerical values. The above formula connectors such as equal number, about equal number, greater than number, less than number, etc., operators such as addition, subtraction, multiplication, division, brackets, etc., algebraic symbols such as numbers, letters, figures, etc., can represent numerical values.

The element entity analyzed from the calculation question is used as a formula term, namely the formula term comprises the contents of a formula connector, an operator, algebraic symbols and the like in the calculation question. Taking the calculation title of "32+1.5=33.5" as an example, the following formula term can be obtained by analyzing the calculation title: 32. ++, 1.5, =, 33.5, and obtain the first type attribute of each formula term; the first type of property of the formula term, e.g., the first type of property of formula term "32", includes: the integer, the number type of the integer bit number is the number of two bits, and the first type attribute of the formula term "+", comprises: the first type of attribute of the sum operator, formula term "=", includes: a formula connector representing equal values.

Using the formula term and its first type attribute in the calculation title obtained by parsing, the sub-formula and its second type attribute can be obtained by referring to the following:

the calculation title is divided into a plurality of sub-formulas consisting of at least one formula term according to the formula term. Inputting each formula term to a preset formula analyzer, and dividing the calculation title into a plurality of sub formulas according to formula connectors in the formula term by the formula analyzer, wherein the plurality of sub formulas form a tree formula structure through the formula connectors. As shown in fig. 2, according to the formula connector "=", the calculation title of 32+1.5=33.5 is divided into [ [32, + ], 1.5] and 33.5], and accordingly, two sub-formulas composed of formula terms are obtained, respectively: sub-formula 1 consisting of operator "+" connecting formula term "32" and formula term "1.5", sub-formula 2 consisting of formula term "33.5"; the sub-formula 1 and the sub-formula 2 are connected through a formula connector "=" and form a tree formula structure corresponding to the calculation title.

And determining the second type attribute of the sub-formula according to the first type attribute of each formula term in the sub-formula. The second type of attribute of the sub-formula is generally determined by the formula term it contains, in one example, in the sub-formula, the first type of attribute of the formula term it includes is a digital type, and then the second type of attribute of the sub-formula is determined to be a digital type (integer or decimal) according to the formula term of the digital type; the second type attribute of sub-equation 2"33.5" can be referred to specifically as the fractional number type.

In another example, in a sub-formula that includes a plurality of formula terms with different first type attributes, then a second type attribute of the sub-formula is commonly determined according to the first type attribute of each of the plurality of formula terms of an operator, algebraic sign, etc., the second type attribute includes: whether or not it is computable (yes or no), an algorithm (add, subtract, multiply, divide, compare size, etc.), computing the position of the symbol, whether or not it contains an unknown item (yes or no), a classification of an unknown item (digital type, operator or formula connector, etc.). Referring to sub-formula 1"32+1.5", it includes: the formula term "32" with the number type being an integer, the formula term "1.5" with the number type being a decimal, and the formula term "+" with the operator being a summation, based on which determining the second type attribute of the sub-formula 1 includes: the root node of the formula terms "32" and "1.5" can be calculated, with the algorithm being additive, and the position of the calculated symbol.

It is to be readily appreciated that the present embodiment may further determine the type attribute of the overall computational topic according to the sub-formula and its second type attribute, where the type attribute of the computational topic includes: the number of sub-formulas, the number of operators, whether there are unknown terms (yes or no), the algorithms, priorities between the algorithms, etc.

Step S106, classifying the calculation types of the calculation questions under different granularities based on the formula items, the first type attribute, the sub-formulas and the second type attribute to obtain the target calculation types of the calculation questions.

In this embodiment, the calculation questions are resolved into formula terms and sub-formulas with different coarse and fine granularities, and the calculation types of the calculation questions are classified step by using the formula terms and the sub-formulas, so that the information of the calculation questions under different granularities can be fully utilized, the classification accuracy is improved, and the code redundancy is reduced.

In one possible way of classifying the calculation type of the calculation topic, the coarse-grained classification can be performed by using the type attribute of the calculation topic from the whole calculation topic; secondly, starting from a sub-formula in the calculation subject, performing medium granularity classification by using the sub-formula and the second type attribute thereof; and finally, starting from the formula items in the sub-formulas, carrying out fine granularity classification by utilizing the formula items and the first type attribute thereof.

Step S108, determining a target solving method corresponding to the target computing type according to a preset matching relation between the computing type and the solving method.

Generally, in mathematics, the types of calculation types are limited, and the problem solving method corresponding to each calculation type is not infinite, based on which, the embodiment may pre-establish a database to store calculation types and problem solving methods matched with the calculation types. Furthermore, in this embodiment, a target solution method corresponding to a target calculation type of a calculation problem may be determined according to a matching relationship between the calculation type and the solution method, or, if the target calculation type does not exist in the database, a reference calculation type similar to the target calculation type may be searched, and the solution method corresponding to the reference calculation type may be used as the target solution method of the calculation problem.

According to the explanation method of the calculation questions provided by the embodiment, the calculation questions are firstly analyzed into formula items and sub-formulas with different granularity, and the first type attribute of the formula items and the second type attribute of the sub-formulas are determined; then classifying the calculation types of the calculation questions under different granularities based on the formula items, the first type attribute, the sub-formula and the second type attribute, so that the information of the calculation questions under different granularities can be fully utilized, the classification accuracy is improved, and the accurate target calculation types are obtained; under the condition of determining the target calculation type, a proper target solving method can be easily matched according to a preset matching relation between the calculation type and the solving method. Therefore, the technical scheme can improve the accuracy of classifying the calculation questions by fully utilizing the information of the formula items and the sub-formulas under different granularities, and further can be easily matched with a target solving method suitable for the calculation questions.

In order to better understand the above step S106, an embodiment of classifying the calculation types of the calculation questions is provided herein, as follows.

And determining the formula term and the sub-formula containing the term to be filled as unknown terms. Specifically, whether the formula item and the sub-formula contain items to be filled such as brackets, horizontal lines, circles and question marks for filling out answers can be identified, and the formula item and the sub-formula containing the items to be filled out are determined as unknown items in the calculation questions. The embodiment can classify the unknown item according to the formula item and the first type attribute before and after the unknown item and/or the sub formula and the second type attribute. Such as: the formula terms before and after the unknown term are two numbers, and the unknown term in the middle should be an operation symbol to be filled in, and the unknown term is pre-classified into the operation symbol.

The formula connector in the formula term is obtained.

Coarse-grained classification can be performed, and the calculation type of the calculation question is subjected to coarse-grained classification according to the first type attribute corresponding to the formula connector and the unknown item, so that the first calculation type is obtained. In practical applications, there are a variety of possible first calculation types under coarse-grained classification, such as numerical calculation, filling in relation symbols, solving equations, and the like. Illustratively, for the calculation of the title "32+1.5= ___" where the unknown term is "___" and the formula connector is "=", the result of the coarse-grained classification of the calculation of the title may be a numerical calculation.

For medium granularity classification, the embodiment can perform medium granularity classification on the calculation type of the calculation subject under the first calculation type according to the operation relation between the first type attribute of each formula item and the formula item in the sub-formula to obtain the second calculation type. After coarse-grained classification, a finer level of medium-grained classification is performed in a different first computational type. In a specific implementation manner, according to an operation relation formed by connecting formula terms by operators in a sub-formula and the first type attribute of the formula terms in the sub-formula, medium granularity classification is carried out on the calculation type of the calculation subject to obtain a second calculation type. The second calculation type includes, for example: addition, addition and subtraction of two numbers, mixed calculation, ratio of two numbers, size, proportional equation, and the like.

For fine-grained classification, the embodiment may perform fine-grained classification on the calculation type of the calculation question under the second calculation type according to the first type attribute of the formula term, to obtain a third calculation type. In practice, the user may decide whether to sort the second calculation type more finely according to individual needs. In particular, the fine-grained classification mainly uses the first type attribute of the formula term, such as the type of number, the number of bits of the number, the type of calculation symbol, and the like, and obtains the information of the maximum and minimum numbers, the final result size, the number of bits, and the like of the intermediate calculation process through the preprocessing, and the like, in this case, the calculation title may be further classified as: and adding two digits, adding and subtracting the mixed calculation within hundred, and the like.

The first calculation type, the second calculation type or the third calculation type is used as a target calculation type of the calculation subject. The first calculation type, the second calculation type or the third calculation type can be used as the final classification result of the calculation questions, and the target calculation type is used for matching with a proper question solving method.

Through the classification, the calculation questions can determine more accurate target calculation types, and in this case, a method for matching the target calculation types to proper questions is generally simpler. An embodiment of a method for determining a target solution problem corresponding to a target calculation type according to a matching relationship between the calculation type and the solution problem method may include:

and determining at least two candidate solving methods corresponding to the target calculation type according to a preset matching relation between the calculation type and the solving methods. It is easy to understand that, by the above three-level classification with different coarse and fine granularity, the calculation types corresponding to the calculation topic classification result are already very similar in structure, for example: the addition, subtraction, split, and combination of addition, subtraction, rounding are two types of computation, but the two types of computation are similar. Based on this, the candidate solving method in this embodiment may be a solving method corresponding to the target calculation type, and may also be a solving method corresponding to the reference calculation type similar to the target calculation type.

At least one target solution method is determined from at least two candidate solution methods. In this embodiment, a better target solution method may be determined from among candidate solution methods. Many mathematical topics exist with one problem solving, and thus, the candidate problem solving method and the target problem solving method in this embodiment may be one or more.

Under classification at the same granularity level, there may be two or more candidate solution methods that can solve the current computational topic, which is common in the topic of the exquisite class. In the case where there are a plurality of candidate solving methods, the present embodiment can perform the optimization of the solving method by the following two schemes.

Scheme one is a learning order priority method. The embodiment comprises the following steps: acquiring a learning arrangement sequence marked in advance by a candidate solving method; and determining at least one candidate solution method arranged before the specified sequence as a target solution method according to the learning arrangement sequence from front to back.

In a specific embodiment, the learning arrangement sequence of each question solving method can be marked in advance according to the knowledge points, the grades, the chapters and the like included in the question solving method, and the learning arrangement sequence can embody the learning sequence of teaching outline, grades, chapters, knowledge points and the like and accords with the teaching progress and knowledge grasping stage. After obtaining a candidate solving method, obtaining a learning arrangement sequence of the candidate solving method; in order to avoid providing the user with the superclass solution, the present embodiment may select at least one candidate solution method with a top learning arrangement order as the target solution method. The solution is optimized based on the learning arrangement sequence of the solution methods, so that the selected target solution method can be better ensured to be within the learning capacity range of the user, and the solution methods with superclass are reduced.

Scheme two is the least-cost method of calculation. The embodiment comprises the following steps: evaluating the calculation cost of the rest steps of each candidate solving method; and selecting at least one target solving method with minimum calculation cost from the candidate solving methods.

In a specific embodiment, when solving the computational problem by using each candidate problem solving method, one or more problem solving steps are required to complete the solving process to obtain a final result. Based on this, for each candidate solving method, each time one solving step is solved, the calculation cost of the remaining steps is evaluated, and the calculation cost may include, for example: the number of solving steps, the size of calculated amount, the adopted operation rules, the number of operation rules, the priority among different operation rules and the like. By evaluating the calculation cost of the rest steps of each candidate solution method and comparing the calculation cost, the first n (n is more than or equal to 1) candidate solution methods with the minimum calculation cost can be selected as the preferred target solution method corresponding to the current calculation problem. The computational cost of the smart algorithm is typically significantly reduced compared to conventional solution methods, and thus, by evaluating and comparing the computational cost of the remaining steps of different candidate solution methods through the present embodiment, the smart algorithm may be selected as the optimal solution for the computational problem.

The two schemes for determining the target solving method can realize one-question multi-solution, provide flexible and various solving methods for users, better inspire and guide the users to solve and answer the same calculation question by adopting different solving methods from different angles and different ideas.

Further, after determining the target solving method corresponding to the target computing type, the method provided in this embodiment may further include: and generating an explanation sequence corresponding to the calculated question based on the target question solving method.

In this embodiment, the calculation questions are solved based on the internal data structure according to the target question solving method, so as to obtain the question solving step information in the solving process. The complete problem solving process of the calculation problem can comprise one or more steps of problem solving step information which is used for representing the formula item corresponding to the problem solving step, the first type attribute, the sub formula and the second type attribute thereof, the operation rule, the priority of the operation rule, the knowledge point and the like.

And generating a problem solving action stream corresponding to the problem solving step information based on the front-end display data structure. In the process of gradually obtaining the solving step information in the solving process, the embodiment can simultaneously generate the solving action streams respectively corresponding to the solving step information of each step.

In this embodiment, the solving of the computational problem may be implemented by a program using an internal data structure, and the generating of the problem solving action stream may be implemented using a front-end presentation data structure. The design that the internal data structure and the front-end display data structure are separated is adopted, the internal data structure is deeply embedded into the logic for solving the calculation problem, and when the problem solving step information is generated, information related to the step can be transmitted as much as possible, so that the frequency of possibly changing the problem solving logic code is reduced. The front-end display data structure is mainly used for displaying the front-end problem solving action flow.

In this embodiment, by adopting a design that the internal data structure and the front-end display data structure are separated, on one hand, when the data structure required by the front-end is changed, only the converted part of the internal data structure and the front-end data structure needs to be modified, and no complex solving process needs to be changed. On the other hand, the solving process may include a plurality of problem solving actions at the front end, and the separated data structure can reduce the complexity of the solving subject logic. The front-end display data structure comprises information such as the type of the front-end solving action, explanation text, relevant position information of an action formula, step knowledge points, relevant sub-calculation and the like, the complexity of the front-end obtaining relevant information and the error probability are greatly reduced, the action animation type and sequence can be conveniently changed in a predefined action range and specification, and the front-end data and solving action are decoupled.

Acquiring an explanation text template preset by an explanation action flow, and filling the explanation text template according to the explanation step information to generate a target explanation text; and generating an explanation sequence based on the target explanation text and the explanation action stream.

After the problem-solving action flow is generated, the explanation text template in the problem-solving action flow can be rapidly extracted by utilizing the advantages of the rear end, and the problem-solving step information is added into the explanation text template to obtain the target explanation text. And then, converting the target explanation Text into target explanation voice by calling TTS (Text To Speech) concurrently, and fusing the target explanation voice into an explanation action stream To generate an explanation sequence.

And sending the explanation sequence to the front end, and gradually explaining the calculation questions according to the target question solving method by the front end through analyzing the explanation actions in the predefined question solving action flow.

Fig. 3 is a block diagram illustrating a structure of an explanation device for calculating a topic according to an embodiment of the present disclosure. The device can be used for realizing the explanation method of the calculation problem, and can be realized in a software and/or hardware mode. As shown in fig. 3, the explanation device 300 for calculating the subject includes the following modules:

the title acquisition module 302 is configured to acquire a calculation title to be explained;

the topic analysis module 304 is configured to analyze the calculation topic into a formula term and a sub-formula, and determine a first type attribute of the formula term and a second type attribute of the sub-formula;

the classification module 306 is configured to classify the calculation type of the calculation question under different granularities based on the formula term and the first type attribute, the sub-formula and the second type attribute, so as to obtain a target calculation type of the calculation question;

the solving module 308 is configured to determine a target solving method corresponding to the target computing type according to a preset matching relationship between the computing type and the solving method.

The device provided in this embodiment has the same implementation principle and technical effects as those of the foregoing method embodiment, and for brevity, reference may be made to the corresponding content of the foregoing method embodiment where the device embodiment is not mentioned.

The exemplary embodiments of the present disclosure also provide an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor. The memory stores a computer program executable by the at least one processor for causing the electronic device to perform a method according to embodiments of the present disclosure when executed by the at least one processor.

The present disclosure also provides a computer program product comprising a computer program, wherein the computer program, when executed by a processor of a computer, is for causing the computer to perform a method according to embodiments of the disclosure.

Referring to fig. 4, a block diagram of an electronic device 400 that may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 4, the electronic device 400 includes a computing unit 401 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 402 or a computer program loaded from a storage unit 408 into a Random Access Memory (RAM) 403. In RAM 403, various programs and data required for the operation of device 400 may also be stored. The computing unit 401, ROM 402, and RAM 403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.

Various components in electronic device 400 are connected to I/O interface 405, including: an input unit 406, an output unit 407, a storage unit 408, and a communication unit 409. The input unit 406 may be any type of device capable of inputting information to the electronic device 400, and the input unit 406 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device. The output unit 407 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, video/audio output terminals, vibrators, and/or printers. Storage unit 408 may include, but is not limited to, magnetic disks, optical disks. The communication unit 409 allows the electronic device 400 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth (TM) devices, wiFi devices, wiMax devices, cellular communication devices, and/or the like.

The computing unit 401 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 401 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the respective methods and processes described above. For example, in some embodiments, the teachings of the computational questions may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 400 via the ROM 402 and/or the communication unit 409. In some embodiments, computing unit 401 may be configured to perform the explanation of the computational problem in any other suitable manner (e.g., by means of firmware).

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

The foregoing is merely a specific embodiment of the disclosure to enable one skilled in the art to understand or practice the disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown and described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of teaching a computational topic, comprising:

acquiring a calculation question to be explained;

2. The method of claim 1, wherein said parsing the computational title into formula terms and sub-formulas and determining a first type of attribute of the formula terms and a second type of attribute of the sub-formulas comprises:

analyzing the element entity with the semantic meaning in the calculation question to obtain a formula term and a first type attribute of the formula term; wherein the element entity comprises: formula connectors, operators, and algebraic signs representing numerical values;

dividing the calculation subject into a plurality of sub formulas consisting of at least one formula term according to the formula term;

and determining the second type attribute of the sub-formula according to the first type attribute of each formula term in the sub-formula.

3. The method of claim 1, wherein classifying the calculation types of the calculation questions at different granularities based on the formula term and the first type attribute, the sub-formula and the second type attribute to obtain the target calculation types of the calculation questions comprises:

determining the formula term containing the term to be filled and the sub formula as unknown terms;

acquiring a formula connector in the formula term;

performing coarse-grained classification on the calculation type of the calculation question according to the first type attribute corresponding to the formula connector and the unknown item to obtain a first calculation type;

according to the operation relation between the first type attribute of each formula term in the sub-formula and the formula term, medium granularity classification is carried out on the calculation type of the calculation subject under the first calculation type, and a second calculation type is obtained;

according to the first type attribute of the formula item, carrying out fine granularity classification on the calculation type of the calculation problem under the second calculation type to obtain a third calculation type;

and taking the first calculation type, the second calculation type or the third calculation type as a target calculation type of the calculation questions.

4. The method according to claim 1, wherein the determining the target solution method corresponding to the target calculation type according to the preset matching relationship between the calculation type and the solution method includes:

determining at least two candidate solving methods corresponding to the target computing type according to a preset matching relation between the computing type and the solving methods;

at least one target solution method is determined from at least two candidate solution methods.

5. The method of claim 4, wherein said determining at least one target solution from at least two of said candidate solution methods comprises:

acquiring a learning arrangement sequence marked in advance by the candidate solving method;

and determining at least one candidate solving method arranged before the designated sequence as a target solving method according to the learning arrangement sequence from front to back.

6. The method of claim 4, wherein said determining at least one target solution from at least two of said candidate solution methods comprises:

evaluating the calculation cost of the rest steps of each candidate problem solving method;

and selecting at least one target solving method with the minimum calculation cost from the candidate solving methods.

7. The method according to claim 1, wherein the method further comprises:

and generating an explanation sequence corresponding to the calculation question based on the target question solving method.

8. The method of claim 1, wherein generating the interpretation sequence corresponding to the calculated topic based on the target solution method comprises:

solving the calculation questions based on an internal data structure and according to the target question solving method to obtain question solving step information in the solving process;

generating a problem solving action stream corresponding to the problem solving step information based on a front-end display data structure;

acquiring an explanation text template preset by the explanation action flow, and filling the explanation text template according to the explanation step information to generate a target explanation text;

and generating an explanation sequence based on the target explanation text and the explanation action stream.

9. An explanation device for calculating a subject, comprising:

10. An electronic device, the electronic device comprising:

a processor;

a memory for storing the processor-executable instructions;

the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method of any of the preceding claims 1-8.

11. A non-transitory computer readable storage medium storing computer instructions which, when executed on a terminal device, cause the terminal device to implement the method of any of claims 1-8.