Problem solving step generation method and apparatus

Abstract

The present specification provides a problem solving step generation method and device, wherein the problem solving step generation method comprises: obtaining a user uploaded to-be-processed question; determining the question type corresponding to the to-be-processed question by recognizing the to-be-processed question; traversing the question tree structure corresponding to the to-be-processed question according to the question type to determine the target problem solving strategy corresponding to the to-be-processed question; processing the question tree structure according to the target problem solving strategy to obtain problem solving step information, and feeding back the problem solving step information to the user.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of computer, in particular to a problem solving step generation method and device. BACKGROUND

[0002] Expression simplification is widely used in elementary mathematics, is one of the important problem solving methods in middle school mathematics, and is a powerful tool for solving many mathematical problems. With the development of computer technology, more and more online learning applications are used. Through simple question catalog, the user can be fed back the corresponding answer of the question. However, this process does not give the related problem solving steps, so that the user can only find out the problem solving process by himself through the answer, and cannot achieve the purpose of effectively assisting the user to learn, so an effective solution is needed to solve the above problems. SUMMARY

[0003] Therefore, the embodiments of the present specification provide a problem solving step generation method. The present specification also relates to a problem solving step generation device, a computing device, and a computer readable storage medium to solve the technical defects in the prior art.

[0004] According to a first aspect of the embodiments of the present specification, a problem solving step generation method is provided, comprising:

[0005] obtaining a user uploaded to-be-processed question;

[0006] determining the question type corresponding to the to-be-processed question by recognizing the to-be-processed question;

[0007] According to the question type, the question tree structure corresponding to the to-be-processed question is traversed to determine the target problem solving strategy corresponding to the to-be-processed question;

[0008] According to the target problem solving strategy, the question tree structure is processed to obtain problem solving step information, and the user is fed back the problem solving step information.

[0009] Optionally, the determining the question type corresponding to the to-be-processed question by recognizing the to-be-processed question comprises:

[0010] inputting the to-be-processed question into a recognition model for processing to obtain a question type identifier corresponding to the to-be-processed question;

[0011] determining the question type corresponding to the to-be-processed question according to the question type identifier;

[0012] The question type includes at least one of the following: integral question type, fractional question type, root question type, and related question type.

[0013] Optionally, the traversing the question tree structure corresponding to the to-be-processed question according to the question type, and determining the target solving strategy corresponding to the to-be-processed question comprises:

[0014] determining the question tree structure corresponding to the to-be-processed question, and traversing the question tree structure according to the question type;

[0015] determining the question sub-type corresponding to the to-be-processed question according to the traversal result;

[0016] selecting the target solving strategy corresponding to the to-be-processed question from the solving strategy set corresponding to the question type according to the question sub-type.

[0017] Optionally, the processing the question tree structure according to the target solving strategy to obtain the solving step information comprises:

[0018] in the case where the question tree structure is an addition tree structure, determining the symbol operation priority corresponding to the to-be-processed question according to the target solving strategy;

[0019] converting the to-be-processed question according to the symbol operation priority to obtain a first subject question, wherein the first subject question is composed of a coefficient and a remainder;

[0020] integrating the first subject question according to the coefficient and the remainder, and constructing a first question tree structure according to the integration result;

[0021] generating the solving step information corresponding to the to-be-processed question according to the first question tree structure.

[0022] Optionally, in the case where the question tree structure is a multiplication tree structure, the method further comprises:

[0023] converting the to-be-processed question according to the symbol operation priority to obtain a second subject question, wherein the second subject question is composed of a base and an index;

[0024] integrating the second subject question according to the base and the index, and constructing a second question tree structure according to the integration result;

[0025] generating the solving step information corresponding to the to-be-processed question according to the second question tree structure.

[0026] Optionally, the processing the question tree structure according to the target solving strategy to obtain the solving step information comprises:

[0027] in the case where the question tree structure is a fraction tree structure, determining the numerator expression and the denominator expression corresponding to the to-be-processed question according to the target solving strategy;

[0028] An auxiliary expression is calculated according to the numerator expression and the denominator expression, and the to-be-processed question is integrated according to the auxiliary expression, to obtain a third question tree structure;

[0029] The solving step information corresponding to the to-be-processed question is generated according to the third question tree structure.

[0030] Optionally, the method further comprises:

[0031] The denominator expression is processed to obtain a target denominator expression;

[0032] A third question title is constructed according to the target denominator expression and the numerator expression, and a fourth question tree structure is constructed according to the third question title;

[0033] The solving step information corresponding to the to-be-processed question is generated according to the fourth question tree structure.

[0034] Optionally, the processing of the question tree structure according to the target solving strategy to obtain the solving step information comprises:

[0035] In a case where the question tree structure is a root form tree structure, a root form inner expression and a root form outer expression corresponding to the to-be-processed question are determined according to the target solving strategy;

[0036] An expression type corresponding to the root form inner expression is determined, and the root form inner expression is converted according to the expression type to obtain a target root form inner expression;

[0037] A fourth question title is constructed according to the target root form inner expression and the root form outer expression, and a fifth question tree structure is constructed according to the fourth question title;

[0038] The solving step information corresponding to the to-be-processed question is generated according to the fifth question tree structure.

[0039] Optionally, the method further comprises:

[0040] A question title tree structure corresponding to the to-be-processed question is constructed according to the solving step information;

[0041] A plurality of sub-expression tree structures are determined by traversing the question title tree structure;

[0042] In a case where a simplified expression tree structure exists in the plurality of sub-expression tree structures, sub-solving step information is generated according to the simplified expression tree structure;

[0043] update the problem solving step information as target problem solving step information according to the sub-problem solving step information, and feed back the target problem solving step information to the user.

[0044] According to a second aspect of the embodiments of the present specification, a problem solving step generation apparatus is provided, comprising:

[0045] An obtaining module configured to obtain a to-be-processed problem uploaded by a user;

[0046] An identifying module configured to determine a problem type corresponding to the to-be-processed problem by identifying the to-be-processed problem;

[0047] A traversing module configured to traverse a problem tree structure corresponding to the to-be-processed problem according to the problem type, and determine a target problem solving strategy corresponding to the to-be-processed problem;

[0048] A processing module configured to process the problem tree structure according to the target problem solving strategy to obtain problem solving step information, and feed back the problem solving step information to the user.

[0049] According to a third aspect of the embodiments of the present specification, a computing device is provided, comprising:

[0050] a memory and a processor;

[0051] The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement the steps of the problem solving step generation method.

[0052] According to a fourth aspect of the embodiments of the present specification, a computer readable storage medium is provided, which stores computer executable instructions, and the instructions are executed by a processor to implement the steps of the problem solving step generation method.

[0053] The problem solving step generation method provided by the present specification can achieve the purpose of assisting users in learning, and improve the explainability of answers. After obtaining the to-be-processed problem uploaded by the user, the problem type corresponding to the to-be-processed problem is determined by identifying the problem. Then, the target problem solving strategy corresponding to the to-be-processed problem is determined by traversing the problem tree structure corresponding to the to-be-processed problem according to the problem type. Finally, the problem solving step information fed back to the user is obtained by processing the problem tree structure according to the target problem solving strategy. The problem solving process related to the problem can be given when assisting the user, so that the user can fully learn the problem knowledge. At the same time, different strategies are selected to process different problems, which can effectively ensure the accuracy of the problem solving steps and further improve the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1is a flow chart of a first problem solving step generation method provided by an embodiment of the present specification;

[0055] Figure 2 is a schematic diagram corresponding to a problem solving step in the first problem solving step generation method provided by an embodiment of the present specification;

[0056] Figure 3 is a flow chart of a second problem solving step generation method provided by an embodiment of the present specification;

[0057] Figure 4 is a schematic diagram corresponding to a problem solving step in the second problem solving step generation method provided by an embodiment of the present specification;

[0058] Figure 5 is a flow chart of a third problem solving step generation method provided by an embodiment of the present specification;

[0059] Figure 6 is a schematic diagram corresponding to a problem solving step in the third problem solving step generation method provided by an embodiment of the present specification;

[0060] Figure 7 is a structural schematic diagram of a problem solving step generation device provided by an embodiment of the present specification;

[0061] Figure 8 is a structural block diagram of a computing device provided by an embodiment of the present specification. DETAILED DESCRIPTION

[0062] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present specification. However, the present specification can be practiced without the specific details, other than in the examples, and it is understood that the scope of the present specification is not limited to the details below.

[0063] The terminology used in one or more embodiments of the present specification is for the purpose of describing particular embodiments only and is not intended to be limiting of one or more embodiments of the present specification. As used in one or more embodiments of the present specification and the accompanying claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in one or more embodiments of the present specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0064] It should be understood that, although the terms first, second, etc. can be employed in describing various information in one or more embodiments of the present specification, the information should not be limited to such terms. These terms are only used to distinguish one piece of information from another piece of information of the same type. For example, without departing from the scope of one or more embodiments of the present specification, first can also be referred to as second, and similarly, second can also be referred to as first. Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon" or "in response to determining".

[0065] First, the noun terms related to one or more embodiments of the present specification are explained.

[0066] Expression simplification: performing various algebraic transformation operations on an expression, returning its simplest form.

[0067] Heuristic algorithm: an algorithm based on intuition or experience construction, which gives a feasible solution to each instance of the combinatorial optimization problem to be solved under acceptable cost (referring to computing time and space).

[0068] CAS: computer algebra system (English: computer algebra system). It is a computer software that performs symbolic operations.

[0069] Polynomial: in mathematics, an algebraic expression composed of several monomials added together is called a polynomial.

[0070] Fraction: generally, if A, B (B is not equal to zero) represents two integral expressions, then the expression A / B is called a fraction, where A is called the numerator and B is called the denominator.

[0071] Radical: radical is one of the basic concepts of mathematics, which is an algebraic expression containing square root (root) operation, that is, an expression containing a radical sign.

[0072] Rationalization of denominator: refers to the operation of removing the radical sign in the denominator of an algebraic expression by appropriate transformation.

[0073] In the present specification, a problem solving step generation method is provided, the present specification also relates to a problem solving step generation device, a computing device, and a computer readable storage medium, which are described in detail one by one in the following embodiments.

[0074] Figure 1 The flow chart of the first problem solving step generation method provided according to an embodiment of the present specification is shown, which specifically includes the following steps:

[0075] Step S102, obtaining the user uploaded problem to be processed.

[0076] Specifically, the problem solving step generation method provided in the embodiment can be applied to a client, which can be a mobile phone, a computer, a smart wearable device or the like held by a user, that is, the user can enter a to-be-processed problem through the client, and then subsequent problem solving processing operations can be completed; correspondingly, it can also be applied to a server, that is, after the user enters the to-be-processed problem through the client, the to-be-processed problem is sent to the server, and the problem solving step generation method provided in the embodiment is executed by the server to obtain problem solving step information, and then the client is fed back to achieve the purpose of problem solving. In specific implementation, the problem solving step generation method provided in the embodiment can set a running environment according to an actual application scenario, which is not limited here.

[0077] Correspondingly, the to-be-processed problem specifically refers to a problem that needs to be answered and generates a problem solving step, which is entered by the user through the client, and the entry mode includes but is not limited to manual input or image acquisition, and the to-be-processed problem belongs to a problem that needs to be simplified and solved.

[0078] The embodiment is described for convenience with the to-be-processed problem as a mathematical simplification problem, and the process of simplifying other types of problems can be seen from the same or corresponding description content of the embodiment, which is not described here.

[0079] Step S104, determining the problem type corresponding to the to-be-processed problem by recognizing the to-be-processed problem.

[0080] Specifically, after obtaining the to-be-processed problem uploaded by the user, further, considering that the to-be-processed problem entered by the user belongs to the same subject, but the to-be-processed problem under the same subject can include multiple problem types, and different problem types correspond to different problem solving methods, in order to ensure that the problem solving step information generated subsequently corresponds to the correct problem solving operation of the to-be-processed problem, the to-be-processed problem can be first identified by type, and then the subsequent processing can be performed according to the identification result to determine the problem type corresponding to the to-be-processed problem. The problem type specifically refers to the type corresponding to the to-be-processed problem, which includes but is not limited to: whole number problem type, fractional problem type, root problem type, related problem type, etc.

[0081] Further, in order to ensure the accuracy of identification and select the corresponding strategy for processing in the subsequent processing, the identification model can be used to complete the type identification of the to-be-processed problem, and the specific implementation manner in the embodiment is as follows:

[0082] The to-be-processed problem is input into the identification model for processing to obtain a problem title type identifier corresponding to the to-be-processed problem; and the problem type corresponding to the to-be-processed problem is determined according to the problem title type identifier.

[0083] Specifically, the identification model specifically refers to a model for identifying the type of the to-be-processed question. The model can complete type determination by identifying the symbol contained in the to-be-processed question. Correspondingly, the question type identifier specifically refers to a unique question type identifier corresponding to the to-be-processed question. The question type identifier can determine the type to which the to-be-processed question belongs.

[0084] Based on this, when the user uploads the to-be-processed question, in order to accurately process it, the question type identifier contained in the to-be-processed question can be identified by the identification model, so as to determine the question type corresponding to the to-be-processed question according to the question type identification result. This facilitates subsequent selection of a suitable strategy for processing the to-be-processed question to generate correct solving steps for feedback to the user.

[0085] That is, the question type identifier specifically refers to an identifier that can uniquely represent the to-be-processed question, which can be a mathematical symbol. For example, if the identification model determines that the question type identifier corresponding to the to-be-processed question is a radical sign, it can be determined that the to-be-processed question belongs to the radical type; or if the identification model determines that the question type identifier corresponding to the to-be-processed question is a semicolon, it can be determined that the to-be-processed question belongs to the fraction type; or if the identification model determines that the question type identifier corresponding to the to-be-processed question is an equal sign, it can be determined that the to-be-processed question belongs to the integer type; or if the identification model determines that the question type identifier corresponding to the to-be-processed question is empty, it can be determined that the to-be-processed question does not belong to the above three types, and it can be identified as a related question type.

[0086] In summary, by using the identification model to determine the question type, the identification accuracy can be improved, and the efficiency can be improved, so that accurate solving step information can be fed back to the user in a short time.

[0087] Step S106: According to the question type, the question tree structure corresponding to the to-be-processed question is traversed to determine the target solving strategy corresponding to the to-be-processed question.

[0088] Specifically, after determining the question type corresponding to the to-be-processed question, further considering that the question type may contain multiple question subtypes, such as the integer type which may involve addition and subtraction subtypes and multiplication and division subtypes, and different questions may affect the final result and the solving steps in the intermediate process due to different operation priorities, in order to ensure accurate solving, the question tree structure corresponding to the to-be-processed question can be traversed according to the question type to determine the sub-question type corresponding to the to-be-processed question according to the traversal result, and then the target solving strategy can be selected according to the finally determined type.

[0089] The question tree structure is a tree structure constructed based on the to-be-processed question, and the nodes in the tree structure are each item in the to-be-processed question. Correspondingly, the target solving strategy is a strategy for processing different question types. The implementation can accurately process the to-be-processed question, ensuring processing efficiency and accuracy.

[0090] Further, in determining the target solving strategy, in order to be able to select the strategy corresponding to the to-be-processed question, the tree structure of the to-be-processed question can be traversed first to determine the question sub-type corresponding to the to-be-processed question, and then selected. In this embodiment, the specific implementation is as follows:

[0091] The question tree structure corresponding to the to-be-processed question is determined, and the question tree structure is traversed according to the question type. The question sub-type corresponding to the to-be-processed question is determined according to the traversal result. The target solving strategy corresponding to the to-be-processed question is selected from the solving strategy set corresponding to the question type according to the question sub-type.

[0092] Specifically, traversal refers to traversing each node in the question tree structure corresponding to the to-be-processed question to search and integrate the question tree structure, so as to determine the question sub-type corresponding to the to-be-processed question according to the traversal result. Correspondingly, the solving strategy set is a set of all solving schemes under the integrated question type. Different question types correspond to different solving strategy sets, and the solving strategy set can be added / removed / modified according to the actual application scenario. This embodiment does not make any limitation here.

[0093] Based on this, the question tree structure corresponding to the to-be-processed question is first determined, then the DFS algorithm is used to traverse the question tree structure to determine the question sub-type corresponding to the to-be-processed question according to the traversal result, and finally the solving strategy set corresponding to the question type is queried according to the question sub-type. The target solving strategy corresponding to the to-be-processed question can be selected from the set to facilitate subsequent processing.

[0094] In summary, by using the traversal tree structure to determine the question sub-type, the type corresponding to the to-be-processed question can be determined with finer accuracy, so that the strategy corresponding to the type can be selected for subsequent use, effectively ensuring the accuracy.

[0095] Step S108, processing the question tree structure according to the target solving strategy to obtain solving step information, and feeding back the solving step information to the user.

[0096] Specifically, after determining the target problem-solving strategy corresponding to the to-be-processed question, further processing the question tree structure corresponding to the to-be-processed question according to the target problem-solving strategy can obtain the problem-solving step information corresponding to the to-be-processed question, so that the user can be fed back according to the problem-solving step information, and the user can learn the problem-solving idea of the to-be-processed question more conveniently.

[0097] In practical applications, considering that different questions need to be processed in different ways in different scenarios to obtain corresponding problem-solving step information, if the type of the to-be-processed question is determined in the processing process, the processing result of each layer of the tree structure can be determined by processing the question tree structure of the to-be-processed question, and then the problem-solving step tree structure can be constructed according to the final question simplification result and the processing result of each layer of the tree structure, and the generation of the problem-solving step information can be performed on this basis, so that the simplification process can be further ensured to be more clear and accurate.

[0098] Further, in the case where the question tree structure is an addition tree structure, the symbol operation priority corresponding to the to-be-processed question can be determined according to the target problem-solving strategy; the to-be-processed question is converted according to the symbol operation priority to obtain a first subject question, wherein the first subject question is composed of a coefficient and a remainder; the first subject question is integrated according to the coefficient and the remainder, and a first question tree structure is constructed according to the integration result; and the problem-solving step information corresponding to the to-be-processed question is generated according to the first question tree structure.

[0099] Specifically, the addition tree structure specifically refers to a tree structure of the to-be-processed question belonging to the integer addition question type; correspondingly, the symbol operation priority specifically refers to that the simplification of the to-be-processed question needs to be completed according to the operation priority, and the operation priority conforms to the basic logic of mathematical calculation; correspondingly, the first subject question specifically refers to a question obtained by preliminary simplification after conversion according to the symbol operation priority; and the first question tree structure specifically refers to a tree structure integrated based on the simplification process, that is, each node corresponds to an item in a problem-solving step.

[0100] Based on this, when it is determined that the question tree structure is an addition tree structure, it means that the to-be-processed question is of the integer addition question type, so at this time, the addition operation process can be followed, the symbol operation priority corresponding to the to-be-processed question is determined according to the target problem-solving strategy, then the to-be-processed question is converted according to the symbol operation priority to obtain a first subject question, then the first subject question is integrated according to the coefficient and the remainder, and a first question tree structure can be constructed according to the integration result; finally, the problem-solving step information corresponding to the to-be-processed question can be generated according to the first question tree structure.

[0101] That is, in the process of processing the whole formula addition problem type, if the to-be-processed problem contains an operator symbol with high priority, such as a parenthesis, the symbol removal needs to be performed according to the priority order first, and then the to-be-processed problem is converted into a form in which each term is written as a coefficient multiplied by a remainder. Then, the coefficients of the same remainder are added to obtain the first problem tree structure according to the addition structure, and finally the problem solving step information is generated according to the first problem tree structure.

[0102] In summary, by adopting the step-by-step simplification of the to-be-processed problem according to the operation priority, the simplification process can be more in line with the mathematical operation logic, thereby ensuring the accuracy of the problem solving step information.

[0103] In addition, in the case where the problem tree structure is a multiplication tree structure, the to-be-processed problem can be converted according to the symbol operation priority to obtain a second problem, wherein the second problem is composed of a base and an index; the second problem is integrated according to the base and the index, and a second problem tree structure is constructed according to the integration result; and the problem solving step information corresponding to the to-be-processed problem is generated according to the second problem tree structure.

[0104] Specifically, the multiplication tree structure specifically refers to a tree structure of the to-be-processed problem belonging to the whole formula multiplication problem type; correspondingly, the second problem specifically refers to a problem obtained after preliminary simplification by conversion according to the symbol operation priority; and correspondingly, the second problem tree structure specifically refers to a tree structure integrated based on the simplification process, and each node corresponds to an item in a problem solving step.

[0105] Based on this, in the case where the problem tree structure is a multiplication tree structure, it is indicated that the to-be-processed problem is of the whole formula multiplication problem type at this time, and therefore the multiplication operation process can be followed to convert the to-be-processed problem according to the symbol operation priority to obtain a second problem; then the second problem is integrated according to the base in the second problem and the index, and a second problem tree structure is constructed according to the integration result; and finally, the problem solving step information corresponding to the to-be-processed problem can be generated according to the second problem tree structure.

[0106] That is, in the process of processing the whole formula multiplication problem type, if the to-be-processed problem contains an operator symbol with high priority, such as a parenthesis, the symbol removal needs to be performed according to the priority order first, and then the to-be-processed problem is converted into a form in which each term is written as a coefficient multiplied by a remainder. Then, the coefficients of the same remainder are added to obtain the first problem tree structure according to the addition structure, and finally the problem solving step information is generated according to the first problem tree structure.

[0107] For example, when a user inputs Figure 2After the shown to-be-processed question, it can be determined that the to-be-processed question is an integer addition question type. First, the to-be-processed question can be debracketed to obtain expression 2x 2 -x 2 +3x-2x (for each item that needs to be changed in sign, change in sign according to the preset strategy), then merge the same type, the first item and the second item are written as 2*x 2 and -1*x 2 , the third item and the fourth item are written as 3*x and -2*x. By traversing, it is determined that the first item and the second item both have x 2 , the third item and the fourth item both have x, so the coefficients can be added to obtain x 2 +x, then generate the problem solving step information based on the simplification process, and feed back to the user.

[0108] In addition, when generating the problem solving step information, considering that the final simplification result may not necessarily be the simplest, it can also be updated by expanding the processing. In this embodiment, the specific implementation manner is as follows:

[0109] According to the problem solving step information, a question title question tree structure corresponding to the to-be-processed question is constructed. By traversing the question title question tree structure, a plurality of sub-expression tree structures are determined. In the case that there is a simplified expression tree structure in the plurality of sub-expression tree structures, sub-problem solving step information is generated according to the simplified expression tree structure. According to the sub-problem solving step information, the problem solving step information is updated to target problem solving step information, and the target problem solving step information is fed back to the user.

[0110] Specifically, the question title question tree structure specifically refers to a tree structure constructed based on all steps involved in the problem solving steps, for determining whether the problem solving step information reaches the simplest; correspondingly, the plurality of sub-expression tree structures specifically refer to the tree structure corresponding to the expression corresponding to each problem solving step in the problem solving step information; correspondingly, the simplified expression tree structure specifically refers to the tree structure corresponding to the expression that can be further simplified; correspondingly, the sub-problem solving step information specifically refers to the problem solving step obtained by simplifying the expression corresponding to the simplified expression tree structure; correspondingly, the target problem solving step information specifically refers to the problem solving step information that fuses the sub-problem solving step information.

[0111] Based on this, considering that the simplification process may not have reached the simplest, in order to avoid misleading the user, at this time, the title subject tree structure corresponding to the to-be-processed subject can be constructed according to the problem solving step information; then the multiple sub-expression tree structures are determined by traversing the title subject tree structure; when it is determined that there is a simplified expression tree structure in the sub-expression tree structure, it is indicated that the simplification operation can be further performed; at this time, the sub-problem solving step information can be generated according to the simplified expression tree structure; finally, the problem solving step information is updated to the target problem solving step information according to the sub-problem solving step information, and the target problem solving step information is fed back to the user.

[0112] In the above example, after simplifying the to-be-processed subject shown in Figure 2 , the result x(x+1) is obtained, the tree structure corresponding to the result is traversed, it is determined that the expression also includes parentheses, in order to achieve the simplest, it is also necessary to perform the parentheses removal processing, and x 2 + x is obtained according to the processing result; finally, the problem solving steps from x(x+1) to x 2 + x are also written into the problem solving step information corresponding to the to-be-processed subject, and the user is fed back.

[0113] That is, the expansion simplification can be applied to the multiplication distribution law, that is, a plurality of polynomials are expanded into a polynomial, and then the whole expression is simplified. Specifically, the DFS algorithm is used to traverse the whole expression tree structure, and each sub-expression tree is expanded from the bottom to the top. If the expansion is successful, the expanded expression is simplified; if the expansion is not successful, it is indicated that the simplest is reached, and no processing is performed.

[0114] In summary, by updating the problem solving step information through the expansion simplification, the problem solving step information fed back to the user is more accurate, and the expected calculation effect is achieved, so that the user can learn the problem solving process more accurately.

[0115] The problem solving step generation method provided in the specification can achieve the purpose of assisting the user to learn, and improve the explainability of the answer. After obtaining the to-be-processed subject uploaded by the user, the subject type corresponding to the subject is determined by recognizing the subject, then the target problem solving strategy corresponding to the to-be-processed subject is determined by traversing the subject tree structure corresponding to the to-be-processed subject according to the subject type, and finally the problem solving step information fed back to the user is obtained by processing the subject tree structure according to the target problem solving strategy. When assisting the user, the problem solving process related to the subject can be given, the user can fully learn the subject knowledge, different strategies are selected for different subjects, the accuracy of the problem solving step can be effectively guaranteed, and the user experience is further improved.

[0116] Figure 3A flowchart of a second problem solving step generation method according to an embodiment of the present specification is shown, and specifically includes the following steps:

[0117] In step S302, a user-uploaded to-be-processed problem is obtained.

[0118] In step S304, the to-be-processed problem is identified to determine the problem type corresponding to the to-be-processed problem.

[0119] In step S306, the to-be-processed problem corresponding problem tree structure is traversed according to the problem type to determine the target problem solving strategy corresponding to the to-be-processed problem.

[0120] The second problem solving step generation method provided in this embodiment is similar to the description of the first problem solving step generation method described above, and features not described in detail can be referred to the above embodiment. This embodiment will not be described in detail here.

[0121] In step S308, in the case where the problem tree structure is a fraction tree structure, the target problem solving strategy is used to determine the numerator expression and the denominator expression corresponding to the to-be-processed problem.

[0122] In step S310, an auxiliary expression is calculated according to the numerator expression and the denominator expression, and the to-be-processed problem is integrated according to the auxiliary expression to obtain a third problem tree structure.

[0123] In step S312, the problem solving step information corresponding to the to-be-processed problem is generated according to the third problem tree structure, and the problem solving step information is fed back to the user.

[0124] Specifically, the numerator expression specifically refers to the expression corresponding to the numerator part in the to-be-processed problem; correspondingly, the denominator expression specifically refers to the expression corresponding to the denominator part in the to-be-processed problem; correspondingly, the auxiliary expression specifically refers to the common factor; correspondingly, the third problem tree structure specifically refers to the tree structure generated according to the fraction expression simplification process.

[0125] Based on this, in the case where the problem tree structure is a fraction tree structure, it is indicated that the to-be-processed problem is a fraction expression. In order to be more accurate for fraction expression simplification, the expression reduction method can be selected to complete the simplification, that is, the numerator expression and the denominator expression contained in the to-be-processed problem can be determined according to the target problem solving strategy, then the auxiliary expression is calculated according to the numerator expression and the denominator expression, and the to-be-processed problem is integrated according to the auxiliary expression to obtain a third problem tree structure; finally, the problem solving step information corresponding to the to-be-processed problem is generated according to the third problem tree structure, and the problem solving step information is fed back to the user.

[0126] In other words, when simplifying an expression, the numerator and denominator of the expression to be processed are extracted first. To simplify the operation, nested fractions can be removed first. This process checks whether there are fractions in the numerator and denominator. If there are fractions, the outermost fraction is multiplied by the least common multiple of all the inner denominators to remove the inner fractions. If there are no fractions, simplification can be performed directly to find the common factor of the numerator and denominator. If a common factor exists and it is a single term, simplification can be performed directly. If the common factor is not a single term, the numerator and denominator can be factored first, and then simplified. After simplification, the simplified result can be obtained.

[0127] For example, user input such as Figure 4 After processing the problem shown in (a), it is determined that there are nested fractions in the expression. Therefore, we can first find the denominators: x-2, 2-x, x, and calculate the least common multiple (x-2)x. Then, multiply the outermost numerator and denominator by (x-2)x to remove the nested fractions. Next, we find the common factor of the numerator and denominator, which is (x+2)(x-2). Since it is not a single term, we need to factorize the numerator and denominator. Based on the target problem-solving strategy, we determine that the difference of squares formula can be used. Therefore, we can use the difference of squares formula to factor the x in the numerator. 2 Factorize -4 into (x+2)(x-2), and finally divide both the numerator and denominator by (x+2)(x-2) to simplify the fraction. Then, generate the solution steps based on the simplification process and feed them back to the user.

[0128] In summary, when processing fractions, the solution steps can be generated by simplifying fractions, making it clearer to users how each step of the simplification process is performed. This helps users learn how to simplify fractions and improves the user experience.

[0129] Furthermore, when processing fractions, a common denominator approach can be used, which involves processing the denominator expression to obtain a target denominator expression; constructing a third target problem based on the target denominator expression and the numerator expression; constructing a fourth problem tree structure based on the third target problem; and generating the solution steps information corresponding to the problem to be processed based on the fourth problem tree structure.

[0130] Specifically, the target denominator expression refers to the new denominator expression obtained after factorization; correspondingly, the third target problem refers to the problem that integrates the new denominator expression and the original numerator expression; correspondingly, the fourth problem tree structure refers to the problem tree structure that constructs the corresponding simplification steps based on the third target problem.

[0131] Therefore, when the problem to be processed is determined to be a fractional problem, it means that the problem is a fractional expression. In order to simplify the fractional expression more accurately, we can choose to simplify it by finding a common denominator. That is, we can first determine the numerator and denominator expressions contained in the problem to be processed according to the target problem-solving strategy, then process the denominator expression to obtain the target denominator expression, then construct the third target problem based on the target denominator expression and the numerator expression, and then construct the fourth problem tree structure based on the third target problem, and finally generate the problem-solving steps information corresponding to the problem to be processed based on the fourth problem tree structure.

[0132] In other words, when finding a common denominator for the expression, first extract the numerator and denominator for each term in the addition expression in the problem, factorize the denominator, find the least common multiple of all denominators, and record it as the denominator of the new expression. Then, divide the obtained least common multiple by each denominator and multiply it by each numerator, add them together, and record it as the numerator of the new expression. Reconstruct the expression using the new numerator and denominator, and finally perform a polynomial simplification. Polynomial simplification can be found in the same or corresponding descriptions in the above embodiments, and will not be elaborated on in this embodiment.

[0133] For example, user input such as Figure 4 After processing the problem shown in (b), first find all the denominators in the fraction and determine them as x-2. Then construct a new numerator and denominator with the denominator x-2 and the numerator (x-2) / (x-2)*(x+2)+(x-2) / 1*1, which is (x+2)+(x-2). Then use the new numerator and denominator to reconstruct the entire fraction. Finally, simplify the numerator and denominator to obtain the final answer. Then generate the solution steps based on the simplification process and feed them back to the user.

[0134] In summary, by using the method of finding a common denominator to process the problems, users can learn each step of fraction simplification from multiple perspectives, thereby assisting users in learning fraction simplification and improving the user experience.

[0135] The problem-solving step generation method provided in this manual aims to assist users in learning and improve the interpretability of answers. After receiving the problem uploaded by the user, the method identifies the problem type, traverses the corresponding problem tree structure based on the problem type, determines the target problem-solving strategy, and finally processes the problem tree structure according to the target strategy to obtain the problem-solving steps to be fed back to the user. This method provides the relevant solution process when assisting users, allowing them to fully learn the problem knowledge. Furthermore, by selecting different strategies for different problems, the accuracy of the problem-solving steps can be effectively guaranteed, further improving the user experience.

[0136] Figure 5 A flowchart of a third problem solving step generation method according to an embodiment of the present specification is shown, which specifically includes the following steps:

[0137] In step S502, a user uploaded to-be-processed problem is obtained.

[0138] In step S504, the to-be-processed problem is identified to determine the problem type corresponding to the to-be-processed problem.

[0139] In step S506, the to-be-processed problem corresponding to the problem tree structure is traversed according to the problem type to determine the target problem solving strategy corresponding to the to-be-processed problem.

[0140] The third problem solving step generation method provided in this embodiment is similar to the description of the first problem solving step generation method described above, and the features not described in detail can be referred to the above embodiment. This embodiment will not be described in detail here.

[0141] In step S508, in the case where the problem tree structure is a root formula tree structure, the root formula inner expression and the root formula outer expression corresponding to the to-be-processed problem are determined according to the target problem solving strategy.

[0142] In step S510, the expression type corresponding to the root formula inner expression is determined, and the root formula inner expression is converted according to the expression type to obtain a target root formula inner expression.

[0143] In step S512, a fourth problem is constructed according to the target root formula inner expression and the root formula outer expression, and a fifth problem tree structure is constructed according to the fourth problem.

[0144] In step S514, the problem solving step information corresponding to the to-be-processed problem is generated according to the fifth problem tree structure, and the problem solving step information is fed back to the user.

[0145] Specifically, the root formula inner expression specifically refers to the expression inside the root in the to-be-processed problem; correspondingly, the root formula outer expression specifically refers to the expression outside the root formula in the to-be-processed problem; correspondingly, the expression type specifically refers to the type corresponding to the root formula inner expression, which needs to be converted according to different strategies to obtain the target root formula inner expression; correspondingly, the fourth problem specifically refers to the problem integrated by the target root formula inner expression and the root formula outer expression.

[0146] Based on this, in the case that the question tree structure is a root tree structure, it is indicated that the to-be-processed question is a root expression, in order to be able to simplify the root expression more accurately, the root internal expression and the root external expression corresponding to the to-be-processed question can be determined according to the target solving strategy; secondly, the expression type corresponding to the root internal expression is determined, and the root internal expression is converted according to the expression type to obtain a target root internal expression; thirdly, a fourth target question is constructed according to the target root internal expression and the root external expression, and a fifth question tree structure is constructed according to the fourth target question; finally, the solving step information corresponding to the to-be-processed question is determined according to the fifth question tree structure, and the solving step information is fed back to the user.

[0147] That is, in the case that the to-be-processed question contains a root, all sub-expressions that can be taken the root need to be simplified. First, it can be checked whether there is a fraction in the root, if there is a fraction, the fraction is first simplified; then the root internal expression is factorized, if the root internal expression is multiplication, it is written in the form of taking the root first and then multiplying, that is, taking the root of each sub-expression in the multiplication. If the sub-expression is negative, the negative sign needs to be moved to the sub-expression with the variable, the root of each sub-expression is simplified, and all the sub-expressions are multiplied. If the root internal expression is a root or a power operation, if the root is an even root and the exponent in the root is even: the absolute value is added to the base, then the exponent is rewritten as the product of all exponents, and the expression is reconstructed according to the new base and the new exponent, and finally the expression is simplified by whole expression simplification. The whole expression simplification can refer to the same or corresponding description in the above embodiment, which will not be described in detail herein.

[0148] In addition, in order to achieve the simplest, for the expression with a root in the denominator, the denominator needs to be rationalized. First, the rationalization coefficient of the denominator needs to be found. For a denominator with a root, if it can be expressed as x (a / b) The rationalization coefficient of the denominator is x (1-(amodb) / b) For a multiplication denominator, the rationalization coefficient is the product of the rationalization coefficients of each multiplier; for a denominator with two roots added, the rationalization coefficient is the difference between the two roots. Then the numerator and the denominator are multiplied by the rationalization coefficient, and then expanded and simplified again to complete the rationalization of the denominator.

[0149] For example, after the user inputs the to-be-processed question shown in (a) of Figure 6 The root inside has been simplified to the simplest, and then it is written in the form of taking the root first and then multiplying. Here it is a fraction, that is, the numerator and the denominator are taken separately. For the root of the denominator, the inside is a power operation, the exponent is 2, which is even, so it is converted into the form of the absolute value added to the base.

[0150] Further, referring to Figure 6The denominator of the schematic diagram shown in (a) has an absolute value, and if this is solved, there will be multiple possibilities. In order to improve accuracy, the absolute value can be removed again. See Figure 6 The schematic diagram shown in (b). If there is an absolute value, the definition domain of the expression itself with respect to the variable needs to be solved first, and then the definition domain is combined with the absolute value range, and then discussed in different cases, and then simplified.

[0151] That is, solving the definition domain needs to scan the entire expression: if the sub-expression is an even root, the root bottom number needs to be greater than or equal to 0; if the sub-expression is division, the denominator cannot be equal to 0; if the sub-expression is a logarithmic operation, the base is greater than 0 and not equal to 1, and the true number is greater than 0. Then the range to be discussed needs to be discussed; for each absolute value item, combine the definition domain: if it is always positive or always negative, remove the absolute value directly; if its positive and negative are not determined, find its zero point. List all the zero points on the number line, find the interval; combine the interval and the definition domain to get the final discussion interval; after getting the interval to be discussed, under the restriction of each interval, the absolute value in the expression can be expressed in the form of always positive or always negative, that is, the absolute value in the expression can be eliminated. After eliminating the absolute value, simplify it again, and finally combine all the cases to get the final answer.

[0152] Further, see Figure 6 The schematic diagram shown in (b), the original expression is simplified by the root to get an expression with absolute value. Before removing the absolute value, the definition domain of the original expression is found, and for the root, the base needs to be greater than or equal to 0, and x can be solved to be less than or equal to -2. After finding the range of x, it can be discussed. Here, since x is always negative, the absolute value can be removed directly and written as -x. After removing the absolute value, the entire expression is simplified to get the final answer. Then, based on the simplification process, the problem solving step information is generated and fed back to the user.

[0153] The problem solving step generation method provided in the specification, in order to achieve the purpose of assisting users to learn, and improve the explainability of the answer, after obtaining the user uploaded to-be-processed question, the question is identified to determine its corresponding question type, then the to-be-processed question tree structure is traversed according to the question type, the target problem solving strategy corresponding to the to-be-processed question is determined, and finally the question tree structure is processed according to the target problem solving strategy to obtain the problem solving step information fed back to the user, which realizes that when assisting the user, the problem solving process related to the question can be given, the user can fully learn the question knowledge, and different strategies are selected for different questions to process them, which can effectively guarantee the accuracy of the problem solving steps and further improve the user experience.

[0154] Corresponding to the method embodiments described above, the specification also provides problem solving step generation device embodiments,Figure 7 A structural schematic diagram of a problem solving step generation device is shown. As shown in the figure, the device comprises: Figure 7

[0155] An obtaining module 702 is configured to obtain a to-be-processed problem uploaded by a user;

[0156] An identifying module 704 is configured to determine a problem type corresponding to the to-be-processed problem by identifying the to-be-processed problem;

[0157] A traversing module 706 is configured to traverse a problem tree structure corresponding to the to-be-processed problem according to the problem type, and determine a target problem solving strategy corresponding to the to-be-processed problem;

[0158] A processing module 708 is configured to process the problem tree structure according to the target problem solving strategy to obtain problem solving step information, and feed back the problem solving step information to the user.

[0159] In an optional embodiment, the identifying module 704 is further configured to:

[0160] input the to-be-processed problem into an identifying model for processing to obtain a problem title type identifier corresponding to the to-be-processed problem; and determine the problem type corresponding to the to-be-processed problem according to the problem title type identifier; wherein the problem type comprises at least one of the following: an integral problem type, a fractional problem type, a root problem type, and a correlation problem type.

[0161] In an optional embodiment, the traversing module 706 is further configured to:

[0162] determine a problem tree structure corresponding to the to-be-processed problem, and traverse the problem tree structure according to the problem type; determine a problem sub-type corresponding to the to-be-processed problem according to the traversal result; and select the target problem solving strategy corresponding to the to-be-processed problem from a problem solving strategy set corresponding to the problem type according to the problem sub-type.

[0163] In an optional embodiment, the processing module 708 is further configured to:

[0164] in a case where the problem tree structure is an addition tree structure, determine a symbol operation priority corresponding to the to-be-processed problem according to the target problem solving strategy; convert the to-be-processed problem according to the symbol operation priority to obtain a first problem title problem, wherein the first problem title problem is composed of a coefficient and a remainder; integrate the first problem title problem according to the coefficient and the remainder, and construct a first problem tree structure according to the integration result; and generate the problem solving step information corresponding to the to-be-processed problem according to the first problem tree structure.​

[0165] In an optional embodiment, when the question tree structure is a multiplication tree structure, the processing module 708 is further configured to:

[0166] convert the to-be-processed question according to the symbol operation priority, to obtain a second question, wherein the second question is composed of a base and an index; integrate the second question according to the base and the index, and construct a second question tree structure according to the integration result; and generate the question solving step information corresponding to the to-be-processed question according to the second question tree structure.

[0167] In an optional embodiment, the processing module 708 is further configured to:

[0168] when the question tree structure is a fraction tree structure, determine a numerator expression and a denominator expression corresponding to the to-be-processed question according to the target question solving strategy; calculate an auxiliary expression according to the numerator expression and the denominator expression, and integrate the to-be-processed question according to the auxiliary expression, to obtain a third question tree structure; and generate the question solving step information corresponding to the to-be-processed question according to the third question tree structure.

[0169] In an optional embodiment, the processing module 708 is further configured to:

[0170] process the denominator expression, to obtain a target denominator expression; construct a third question according to the target denominator expression and the numerator expression, and construct a fourth question tree structure according to the third question; and generate the question solving step information corresponding to the to-be-processed question according to the fourth question tree structure.

[0171] In an optional embodiment, the processing module 708 is further configured to:

[0172] when the question tree structure is a root tree structure, determine a root expression inside and a root expression outside corresponding to the to-be-processed question according to the target question solving strategy; determine an expression type corresponding to the root expression inside, and convert the root expression inside according to the expression type, to obtain a target root expression inside; construct a fourth question according to the target root expression inside and the root expression outside, and construct a fifth question tree structure according to the fourth question; and generate the question solving step information corresponding to the to-be-processed question according to the fifth question tree structure.

[0173] In an optional embodiment, the processing module 708 is further configured to:

[0174] According to the problem solving step information, a problem title problem tree structure corresponding to the to-be-processed problem is constructed; by traversing the problem title problem tree structure, a plurality of sub-expression tree structures are determined; in the case that a simplified expression tree structure exists in the plurality of sub-expression tree structures, sub-problem solving step information is generated according to the simplified expression tree structure; the problem solving step information is updated into target problem solving step information according to the sub-problem solving step information, and the target problem solving step information is fed back to the user.

[0175] The problem solving step generation device provided by the present specification can assist the user in learning and improve the explainability of the answer. After obtaining the to-be-processed problem uploaded by the user, the problem type corresponding to the problem is determined by recognizing the problem, and then the problem tree structure corresponding to the to-be-processed problem is traversed according to the problem type to determine the target problem solving strategy corresponding to the to-be-processed problem. Finally, the problem tree structure is processed according to the target problem solving strategy to obtain the problem solving step information fed back to the user, which can provide the user with the problem related problem solving process when assisting the user, so that the user can fully learn the problem knowledge. At the same time, different strategies are selected for different problems to process them, which can effectively ensure the accuracy of the problem solving steps and further improve the user experience.

[0176] The above is a schematic scheme of a problem solving step generation device according to an embodiment of the present specification. It should be noted that the technical scheme of the problem solving step generation device belongs to the same concept as the technical scheme of the problem solving step generation method described above. The technical scheme of the problem solving step generation device is not described in detail, and the details can be referred to the description of the technical scheme of the problem solving step generation method.

[0177] Figure 8 A structural block diagram of a computing device 800 according to an embodiment of the present specification is shown. The components of the computing device 800 include but are not limited to a memory 810 and a processor 820. The processor 820 is connected to the memory 810 through a bus 830, and a database 850 is used to save data.

[0178] The computing device 800 also includes an access device 840 that enables the computing device 800 to communicate via one or more networks 860. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or combinations of such networks, such as the Internet. The access device 840 can include one or more of any type of network interface (e.g., network interface cards (NICs)) such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a global microwave interconnection access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like, either wired or wireless.

[0179] In one embodiment of the present specification, the above-mentioned components of the computing device 800 and other components not shown in the above-mentioned components of the computing device 800 can be connected to each other, for example, through a bus. It should be understood that Figure 8 Figure 8 The computing device structure diagram shown is only for the purpose of example, and is not a limitation on the scope of the present specification. Other components can be added or replaced as needed by those skilled in the art.

[0180] The computing device 800 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. The computing device 800 can also be a mobile or stationary server. The processor 820 is used to execute computer executable instructions to implement the steps of the problem solving step generation method.

[0181] The above is a schematic scheme of a computing device of the present embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the problem solving step generation method described above belong to the same concept, and the details of the technical scheme of the computing device that are not described in detail can be referred to the description of the technical scheme of the problem solving step generation method.

[0182] The present embodiment of the present specification also provides a computer readable storage medium storing computer instructions, which are executed by a processor to implement the problem solving step generation method.

[0183] ​The above is a schematic solution of the computer readable storage medium of the embodiment. It should be noted that the technical solution of the storage medium and the technical solution of the problem solving step generation method described above belong to the same concept, and the technical solution of the storage medium which is not described in detail can be referred to the description of the technical solution of the problem solving step generation method.

[0184] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than the order in which they are recited in the embodiments and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or necessary.

[0185] The computer instructions include computer program code, which can be in the form of source code, object code, executable code, or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content contained in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, computer readable medium does not include electrical carrier signals and telecommunication signals.

[0186] It should be noted that for the foregoing method embodiments, in order to facilitate description, they are all expressed as a combination of a series of actions, but those skilled in the art should know that the present specification is not limited by the order of the described actions, because according to the present specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily all necessary for the present specification.

[0187] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments. The preferred embodiments disclosed above are only used to help explain the present specification. The alternative embodiments do not describe all the details and are not limited to the specific embodiments described. Obviously, according to the content of the present specification, many modifications and changes can be made. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present specification, so that those skilled in the art can well understand and utilize the present specification. The present specification is limited only by the claims and their full scope and equivalents.

Claims

1. A method for generating problem-solving steps, characterized in that, include: Retrieve user-uploaded questions to be processed; By identifying the questions to be processed, the question type corresponding to the questions to be processed is determined, wherein the question type is determined by the symbols contained in the questions to be processed; Determine the question tree structure corresponding to the question to be processed, and traverse the question tree structure according to the question type. Based on the traversal result, determine the question subtype corresponding to the question to be processed. According to the question subtype, select the target problem-solving strategy corresponding to the question to be processed from the problem-solving strategy set corresponding to the question type. The problem tree structure is processed according to the target problem-solving strategy to obtain problem-solving step information, and the problem-solving step information is fed back to the user. Construct the target question tree structure corresponding to the question to be processed based on the problem-solving step information; By traversing the target question tree structure, multiple sub-expression tree structures are determined; If a simplified expression tree structure exists among the multiple sub-expression tree structures, sub-solution step information is generated based on the simplified expression tree structure. The problem-solving step information is updated to target problem-solving step information based on the sub-problem-solving step information, and the target problem-solving step information is fed back to the user. The target problem-solving step information is problem-solving step information that integrates the sub-problem-solving step information.

2. The method according to claim 1, characterized in that, The step of identifying the question to be processed and determining the question type corresponding to the question to be processed includes: The question to be processed is input into the recognition model for processing to obtain the target question type identifier corresponding to the question to be processed. The question type corresponding to the question to be processed is determined based on the target question type identifier; The question types include at least one of the following: polynomial question type, fractional question type, radical question type, and relational question type.

3. The method according to any one of claims 1-2, characterized in that, The step of processing the problem tree structure according to the target problem-solving strategy to obtain problem-solving step information includes: When the problem tree structure is an addition tree structure, the symbolic operation priority corresponding to the problem to be processed is determined according to the target problem-solving strategy; The problem to be processed is transformed according to the symbolic operation priority to obtain a first target problem, wherein the first target problem consists of coefficients and remainder terms; The first target questions are integrated based on the coefficients and the remainders, and a first question tree structure is constructed based on the integration results. The solution steps information corresponding to the problem to be processed are generated based on the first problem tree structure.

4. The method according to claim 3, characterized in that, In the case where the problem tree structure is a multiplication tree structure, it also includes: The problem to be processed is transformed according to the symbolic operation priority to obtain a second target problem, wherein the second target problem consists of a base and an exponent; The second target questions are integrated based on the base and the index, and a second question tree structure is constructed based on the integration result. The solution steps information corresponding to the problem to be processed are generated based on the second problem tree structure.

5. The method according to any one of claims 1-2, characterized in that, The step of processing the problem tree structure according to the target problem-solving strategy to obtain problem-solving step information includes: When the problem tree structure is a fraction tree structure, the numerator and denominator expressions corresponding to the problem to be processed are determined according to the target problem-solving strategy. Calculate the auxiliary expression based on the numerator and denominator expressions, and integrate the questions to be processed according to the auxiliary expression to obtain a third question tree structure; The solution steps information corresponding to the problem to be processed are generated based on the third problem tree structure.

6. The method according to claim 5, characterized in that, Also includes: The denominator expression is processed to obtain the target denominator expression; Construct a third target problem based on the target denominator expression and the target numerator expression, and construct a fourth problem tree structure based on the third target problem; The solution steps information corresponding to the problem to be processed are generated based on the fourth problem tree structure.

7. The method according to any one of claims 1-2, characterized in that, The step of processing the problem tree structure according to the target problem-solving strategy to obtain problem-solving step information includes: When the problem tree structure is a radical tree structure, the radical expression inside the radical and the radical expression outside the radical corresponding to the problem to be processed are determined according to the target problem-solving strategy. Determine the expression type corresponding to the expression within the radical, and convert the expression within the radical according to the expression type to obtain the target expression within the radical; Construct a fourth target question based on the inner expression and outer expression of the target radical, and construct a fifth question tree structure based on the fourth target question; The solution steps information corresponding to the problem to be processed are generated based on the fifth problem tree structure.

8. A problem-solving step generation device, characterized in that, include: The acquisition module is configured to acquire user-uploaded questions to be processed. The identification module is configured to identify the question to be processed and determine the question type corresponding to the question to be processed, wherein the question type is determined by the symbols contained in the question to be processed; The traversal module is configured to determine the question tree structure corresponding to the question to be processed, traverse the question tree structure according to the question type, determine the question subtype corresponding to the question to be processed according to the traversal result, and select the target problem-solving strategy corresponding to the question to be processed from the problem-solving strategy set corresponding to the question type according to the question subtype. The processing module is configured to process the problem tree structure according to the target problem-solving strategy to obtain problem-solving step information, and to feed back the problem-solving step information to the user; to construct a target problem tree structure corresponding to the problem to be processed based on the problem-solving step information; to determine multiple sub-expression tree structures by traversing the target problem tree structure; to generate sub-problem-solving step information based on the simplified expression tree structure if a simplified expression tree structure exists among the multiple sub-expression tree structures; to update the problem-solving step information to target problem-solving step information based on the sub-problem-solving step information, and to feed back the target problem-solving step information to the user, wherein the target problem-solving step information is problem-solving step information that integrates the sub-problem-solving step information.

9. A computing device, characterized in that, It includes a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer instructions, characterized in that, When executed by the processor, this instruction implements the steps of the method according to any one of claims 1 to 7.

Images