A method, device and medium for extracting a mathematical subjective question solving thought

Abstract

The present disclosure provides a mathematical subjective question solving method, device, equipment and medium, based on the first entity object information, the first entity attribute information and the first entity object relationship information of the stem text, the reference solving method corresponding to the stem text is obtained from the knowledge graph; based on the second entity object information, the second entity attribute information and the second entity object relationship information of the answer text corresponding to the stem text, the candidate solving method is obtained from the knowledge graph; based on the candidate solving method and the reference solving method corresponding to the stem text, the user solving method corresponding to the stem text is output. The present disclosure can realize the extraction of the stem text and the answer text corresponding to the stem text, and comprehensively obtain the knowledge mastery and application of the user when answering by using the knowledge graph.

Description

Technical Field

[0001] This invention relates to the field of education, and in particular to a method, apparatus, device, and medium for extracting problem-solving strategies for subjective mathematical questions. Background Technology

[0002] Extracting problem-solving strategies for subjective math questions has always been an important issue in education and teaching. Currently, there are some methods in related technologies for extracting student answers, such as image recognition technology based on computer vision and automatic scoring technology based on machine learning.

[0003] However, existing methods for extracting solutions to subjective math problems are based on matching the semantic features of the solution steps, reference standard answers, and answer content. This approach cannot reliably capture the user's solution process for subjective math problems, nor can it comprehensively assess the user's knowledge and application during the answer process. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, device, equipment, and medium for extracting problem-solving strategies for subjective mathematical questions in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for extracting problem-solving strategies for subjective mathematical questions, the method comprising:

[0006] Based on the first entity object information, first entity attribute information and first entity object relationship information of the question stem text, the reference problem-solving ideas corresponding to the question stem text are obtained from the knowledge graph.

[0007] Based on the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text, candidate problem-solving ideas are obtained from the knowledge graph.

[0008] Based on the candidate solutions and the reference solutions corresponding to the question text, the user's solution corresponding to the question text is output.

[0009] Secondly, this application provides a device for extracting problem-solving strategies for subjective mathematical questions, the device comprising:

[0010] The first acquisition module is used to acquire the reference problem-solving ideas corresponding to the question text from the knowledge graph based on the first entity object information, first entity attribute information and first entity object relationship information of the question text.

[0011] The second acquisition module is used to acquire candidate problem-solving ideas from the knowledge graph based on the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text.

[0012] The output module is used to output the user's solution to the question stem text based on the candidate solution ideas and the reference solution ideas corresponding to the question stem text.

[0013] Thirdly, this application provides an electronic device, including a processor; and a memory storing a program; wherein the program includes instructions that, when executed by the processor, cause the processor to perform the method.

[0014] Fourthly, this application provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method described thereon.

[0015] The aforementioned method, apparatus, equipment, and medium for extracting problem-solving strategies for subjective mathematical questions obtain reference problem-solving strategies corresponding to the question stem text from a knowledge graph based on the first entity object information, first entity attribute information, and first entity object relationship information of the question stem text; obtain candidate problem-solving strategies from the knowledge graph based on the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text; and output the user's problem-solving strategy corresponding to the question stem text based on the candidate problem-solving strategies and the reference problem-solving strategies corresponding to the question stem text. This embodiment first obtains the entity object information, entity attribute information, and entity object relationship information of the question stem text and the answer text, then obtains reference problem-solving strategies and candidate problem-solving strategies respectively through a knowledge graph, and finally supplements the candidate problem-solving strategies with the reference problem-solving strategies to obtain the user's problem-solving strategy. Therefore, this embodiment can comprehensively obtain the user's knowledge mastery and application during the answering process by extracting the question stem text and the answer text and utilizing a knowledge graph. Attached Figure Description

[0016] Further details, features, and advantages of this disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A flowchart is shown for a method of extracting problem-solving strategies for subjective mathematical questions according to an exemplary embodiment of the present disclosure;

[0018] Figure 2 A flowchart is shown for another method for extracting problem-solving strategies for subjective mathematical problems according to an exemplary embodiment of this disclosure;

[0019] Figure 3 A flowchart is shown for another method for extracting problem-solving strategies for subjective mathematical problems according to an exemplary embodiment of this disclosure;

[0020] Figure 4 A flowchart is shown for another method for extracting problem-solving strategies for subjective mathematical problems according to an exemplary embodiment of this disclosure;

[0021] Figure 5 A schematic block diagram of an apparatus for extracting problem-solving strategies for subjective mathematical questions according to an exemplary embodiment of the present disclosure is shown;

[0022] Figure 6 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0023] The following is a brief description of the implementation environment involved in the method for extracting problem-solving strategies for subjective mathematical questions provided in the embodiments of this application.

[0024] The method for extracting problem-solving strategies for subjective mathematical questions provided in this application can be executed by an electronic device, which can be a terminal or a server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, portable wearable devices, and medical electronic devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc., and portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. The server can be a standalone server or a server cluster composed of multiple servers.

[0025] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0026] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0027] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based 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". Definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc., used in this disclosure are only used to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0028] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0029] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0030] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0031] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0032] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device. It is understood that the above notification and user authorization process is merely illustrative and does not constitute a limitation on the implementation of this disclosure; other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0033] In one embodiment, such as Figure 1 As shown, a method for extracting problem-solving strategies for subjective mathematical questions is provided, including the following steps:

[0034] Step 101: Based on the first entity object information, first entity attribute information, and first entity object relationship information in the question stem text, obtain the reference solution ideas corresponding to the question stem text from the knowledge graph.

[0035] In one possible embodiment, the electronic device first acquires manually annotated question stem text and corresponding answer text, and preprocesses the manually annotated question stem text and corresponding answer text. The manually annotated content includes entity object information, entity attribute information, and entity object relationship information in the question stem text and corresponding answer text. For example, the preprocessing includes removing punctuation marks, and / or removing stop words, and / or word segmentation of the question stem text and corresponding answer text, which is not limited here. Then, an extraction model is trained through a deep learning model. The trained model can extract entity object information, entity attribute information, and entity object relationship information from the question stem text or the corresponding answer text. For example, the deep learning model can use a conditional random field model, or a recurrent neural network model, or a neural Turing machine model, or a self-attention generative adversarial network model, which is not limited here.

[0036] In one possible embodiment, the electronic device acquires the question stem text and then extracts the first entity object information, first entity attribute information, and first entity object relationship information from the question stem text using an extraction model. For example, the entity object information includes numbers, angles, triangles, quadrilaterals, fractions, line segments, unknowns, infinite repeating decimals, fractions, radicals, absolute values, equations, inequalities, addition / subtraction expressions, multiplication expressions, etc., from the text. Entity attribute information includes inherent attribute information and mathematical concept attribute information. Inherent attribute information refers to the attributes inherent to the entity itself; for example, a number entity has a numerical attribute; a fraction has numerator and denominator attributes; a triangle entity has attributes for each of its three vertices, etc. Mathematical concept attribute information describes the mathematical conceptual meaning attributes possessed by an entity; for example, a number entity has an algebraic attribute, and a triangle has attributes such as right angle / isosceles. The organizational structure relationships between entities mainly include: inheritance relationships, attribute relationships, and inclusion relationships. Logical relationships between entities include, but are not limited to: derivation relationship, application relationship, similarity relationship, equivalence relationship, extension relationship, generalization relationship, equivalence transformation relationship, dependency relationship, prerequisite relationship, union relationship, intersection relationship, mutual exclusion relationship, etc.

[0037] In one possible embodiment, after the electronic device obtains the first entity object information, first entity attribute information, and first entity object relationship information of the question stem text based on the extraction model, it inputs these information into a knowledge graph. The knowledge graph includes knowledge node data and the relationships between the knowledge node data, including conceptual node data, theorem node data, and formula node data. The knowledge graph matches the first entity object information, first entity attribute information, and first entity object relationship information of the question stem text with the knowledge node data and the relationships between the knowledge node data in the knowledge graph to generate at least one reference solution strategy corresponding to the question stem text.

[0038] It's important to note that a knowledge graph is a method for organizing and representing knowledge in the form of a graph. Concepts, theorems, formulas, etc., are abstracted into nodes, and the relationships between nodes are abstracted into edges, forming a graph structure composed of nodes and edges. Through a knowledge graph, the relationships between knowledge are represented, enabling knowledge matching based on the entity object information, entity attribute information, and entity object relationship information of the question stem text and its corresponding answer text. Once established, the knowledge graph can be continuously supplemented, updated, and improved from a large number of question stem texts and their corresponding answer texts.

[0039] In one possible implementation, a graph neural network is used to acquire a knowledge graph. First, mathematical concepts, theorems, and formulas are abstracted into nodes, and the relationships between nodes are abstracted into edges, forming a graph structure composed of nodes and edges. This graph structure is stored in the graph database of the graph neural network. Then, the graph structure is used as training data to train and generate a graph neural network knowledge base model. This model represents the relationships between mathematical knowledge and is used to match mathematical knowledge based on the entity object information, entity attribute information, and entity object relationship information of the question stem text and its corresponding answer text. After the graph neural network knowledge base model is established, it can be continuously supplemented, updated, and improved from a large number of question stem texts and their corresponding answer texts, enabling the model to better perform mathematical knowledge matching.

[0040] Step 102: Based on the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text, obtain candidate problem-solving ideas from the knowledge graph.

[0041] In one possible embodiment, the electronic device acquires the answer text corresponding to the question stem text, and extracts the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text through an extraction model. The electronic device inputs the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text into a knowledge graph. The knowledge graph matches the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text with the knowledge node data and the relationships between the knowledge node data in the knowledge graph to generate candidate problem-solving ideas.

[0042] Step 103: Based on the candidate solutions and the reference solutions corresponding to the question text, output the user's solution corresponding to the question text.

[0043] In one possible embodiment, the electronic device compares the overlap between the reference solution and the candidate solution corresponding to the obtained question text to obtain overlap information. Based on the overlap information, it selects a suitable reference solution to supplement the candidate solution, uses the supplemented candidate solution as the user solution corresponding to the question text, and outputs the user solution corresponding to the question text.

[0044] The aforementioned method, apparatus, equipment, and medium for extracting problem-solving strategies for subjective mathematical questions obtain reference problem-solving strategies corresponding to the question stem text from a knowledge graph based on the first entity object information, first entity attribute information, and first entity object relationship information of the question stem text; obtain candidate problem-solving strategies from the knowledge graph based on the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text; and output the user's problem-solving strategy corresponding to the question stem text based on the candidate problem-solving strategies and the reference problem-solving strategies corresponding to the question stem text. This embodiment first obtains the entity object information, entity attribute information, and entity object relationship information of the question stem text and the answer text, then obtains reference problem-solving strategies and candidate problem-solving strategies respectively through a knowledge graph, and finally supplements the candidate problem-solving strategies with the reference problem-solving strategies to obtain the user's problem-solving strategy. Therefore, this embodiment can comprehensively obtain the user's knowledge mastery and application during the answering process by extracting information from the question stem text and the answer text and utilizing a knowledge graph.

[0045] Based on the above embodiments, in another embodiment provided in this disclosure, such as Figure 2 As shown, step 101 above may further include the following steps:

[0046] Step 201: Obtain the first similarity information between the knowledge node data in the knowledge graph and the first entity object information in the question text, and obtain the second similarity information between the knowledge node data in the knowledge graph and the first entity attribute information in the question text.

[0047] In one possible embodiment, the electronic device performs similarity comparisons between the knowledge node data in the knowledge graph and the first entity object information and the first entity attribute information of the question stem text, respectively, and obtains first similarity information and second similarity information, which respectively characterize the similarity between the knowledge node data in the knowledge graph and the first entity object information and the first entity attribute information of the question stem text.

[0048] Step 202: Determine the target node in the knowledge graph based on the first similarity information and the second similarity information.

[0049] In one possible embodiment, after obtaining the first similarity information between the knowledge node data and the first entity object information of the question text and the second similarity information between the knowledge node data and the first entity attribute information of the question text in the knowledge graph, the knowledge node with the highest similarity to the first entity object information and the first entity attribute information of the question text in the knowledge graph is selected as the target node based on the first similarity information and the second similarity information.

[0050] Step 203: Obtain the third similarity information between the relationship information of the target node data in the knowledge graph and the first entity object relationship information in the question text, and determine the target relationship information based on the third similarity information.

[0051] In one possible embodiment, the electronic device compares the similarity between the relationship information between the target node data in the knowledge graph and the first entity object relationship information in the question text to obtain third similarity information, and selects the relationship information with the highest similarity to the first entity object relationship information in the question text as the target relationship information in the knowledge graph.

[0052] Step 204: Generate at least one reference solution based on the target node and target relationship information.

[0053] In one possible embodiment, target nodes are connected based on target relationship information in the knowledge graph to generate reference problem-solving approaches corresponding to the question stem text. It should be noted that there may be multiple target nodes and target relationship information in the knowledge graph, and multiple reference problem-solving approaches corresponding to the question stem text can be generated based on multiple target nodes and target relationship information in the knowledge graph.

[0054] In this embodiment, target nodes are determined in the knowledge graph by obtaining first and second similarity information. Then, the relationship information between the target node data in the knowledge graph and the first entity object relationship information of the question text are obtained as third similarity information. Target relationship information is determined based on the third similarity information. Finally, at least one reference solution for the question text is generated based on the target node and target relationship information. This embodiment obtains the reference solution for the question text through the similarity of each node and the similarity of each relationship information, making the method for extracting solution ideas for subjective mathematical questions more accurate and rigorous.

[0055] Based on the above embodiments, in another embodiment provided in this disclosure, such as Figure 3 As shown, step 102 above may further include the following steps:

[0056] Step 301: Obtain the fourth similarity information between the knowledge node data in the knowledge graph and the second entity object information of the answer text, and obtain the fifth similarity information between the knowledge node data in the knowledge graph and the second entity attribute information of the answer text.

[0057] In one possible embodiment, the electronic device performs similarity comparisons between the knowledge node data in the knowledge graph and the second entity object information and the second entity attribute information of the answer text, respectively, and obtains fourth similarity information and fifth similarity information, which respectively characterize the similarity between the knowledge node data in the knowledge graph and the second entity object information and the second entity attribute information of the answer text.

[0058] Step 302: Determine the target node in the knowledge graph based on the fourth and fifth similarity information.

[0059] In one possible embodiment, after obtaining the fourth similarity information between the knowledge node data and the second entity object information of the answer text and the fifth similarity information between the knowledge node data and the second entity attribute information of the answer text in the knowledge graph, the knowledge node with the highest similarity to the second entity object information and the second entity attribute information of the answer text is selected as the target node in the knowledge graph based on the fourth similarity information and the fifth similarity information.

[0060] Step 303: Obtain the sixth similarity information between the relationship information of the target node data in the knowledge graph and the second entity object relationship information of the answer text, and determine the target relationship information based on the sixth similarity information.

[0061] In one possible embodiment, the electronic device compares the similarity between the relationship information between the target node data in the knowledge graph and the relationship information of the second entity object in the answer text to obtain the sixth similarity information, and selects the relationship information with the highest similarity to the relationship information of the second entity object in the answer text as the target relationship information in the knowledge graph.

[0062] Step 304: Generate candidate solutions based on the target node and target relationship information.

[0063] In one possible embodiment, target nodes are connected based on target relationship information in the knowledge graph to generate candidate problem-solving ideas, which are used to represent the user's problem-solving ideas for subjective mathematical questions.

[0064] In this embodiment, the target node is determined in the knowledge graph based on the fourth and fifth similarity information, and the target relationship information is determined based on the sixth similarity information. Then, candidate problem-solving approaches are generated based on the target node and the target relationship information. This embodiment obtains the candidate problem-solving approaches corresponding to the answer text through the similarity of each node and the similarity of each relationship information. The obtained candidate problem-solving approaches more accurately reflect the user's problem-solving approach for subjective mathematical questions, thus improving the accuracy of the method for extracting problem-solving approaches for subjective mathematical questions.

[0065] Based on the above embodiments, in another embodiment provided in this disclosure, such as Figure 4 As shown, step 103 above may further include the following steps:

[0066] Step 401: Compare the overlap between the reference solution approach corresponding to the question stem text and the candidate solution approaches to obtain overlap information. Based on the overlap information, select the reference solution approach corresponding to the question stem text with the largest overlap with the candidate solution approach as the target reference solution approach.

[0067] The electronic device compares the overlap between the reference solution and the candidate solution corresponding to the obtained question text. By comparing the paths of the reference solution and the candidate solution, it obtains the overlap information. Based on the overlap information, it selects the reference solution corresponding to the question text with the largest overlap with the candidate solution as the target reference solution.

[0068] Step 402: If the overlap between the target reference solution and the candidate solution is greater than a preset threshold, then supplement the candidate solution based on the target reference solution, use the supplemented candidate solution as the user solution corresponding to the question text, and output the user solution corresponding to the question text.

[0069] The electronic device acquires overlap information. If the overlap between the target reference solution and the candidate solution is greater than a preset threshold, the complete path in the target reference solution is used to supplement the path in the candidate solution to make the candidate solution more complete. The supplemented candidate solution is then used as the user solution corresponding to the question text, and the user solution corresponding to the question text is output.

[0070] Step 403: If the overlap between the target reference solution and the candidate solution is less than a preset threshold, the candidate solution is taken as the user solution corresponding to the question text, and the user solution corresponding to the question text is output.

[0071] If the overlap between the target reference solution and the candidate solution is less than a preset threshold, it indicates that the logic of the candidate solution differs significantly from that of the target reference solution. The electronic device will then directly use the candidate solution as the user's solution corresponding to the question text and output the user's solution corresponding to the question text.

[0072] In this embodiment, the electronic device selects the reference solution that has the highest overlap with the candidate solution as the target reference solution. By judging the overlap between the target reference solution and the candidate solution, the electronic device finally outputs the user's solution corresponding to the question text. Considering the case where the logic of the user's solution differs greatly from that of the target reference solution, in order to restore the user's solution to subjective mathematical questions to the greatest extent, the electronic device directly outputs the candidate solution as the user's solution corresponding to the question text. This makes the extraction of the solution to subjective mathematical questions more rigorous and reliable, and more comprehensively and objectively obtains the user's knowledge mastery and application when answering the question.

[0073] In one embodiment, such as Figure 5 As shown, a device for extracting problem-solving strategies for subjective mathematical questions is provided. The device includes:

[0074] The first acquisition module 501 is used to acquire the reference problem-solving ideas corresponding to the question text from the knowledge graph based on the first entity object information, the first entity attribute information and the first entity object relationship information of the question text.

[0075] The second acquisition module 502 is used to acquire candidate problem-solving ideas from the knowledge graph based on the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text.

[0076] The output module 503 is used to output the user's solution to the question stem text based on the candidate solution ideas and the reference solution ideas corresponding to the question stem text.

[0077] Exemplary embodiments of this disclosure also provide an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the electronic device to perform a method according to an embodiment of this disclosure.

[0078] Exemplary embodiments of this disclosure also provide a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to embodiments of this disclosure.

[0079] refer to Figure 6 The present invention describes a structural block diagram of an electronic device 600 that can serve as a server or client of the present disclosure, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0080] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. The RAM 603 may also store various programs and data required for the operation of the device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0081] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, output unit 607, storage unit 608, and communication unit 609. Input unit 606 can be any type of device capable of inputting information to electronic device 600. Input unit 606 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of electronic device. Output unit 607 can be any type of device capable of presenting information and may include, but is not limited to, a display, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 604 may include, but is not limited to, disk and optical disk. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks 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™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0082] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose 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 601 performs the various methods and processes described above. For example, in some embodiments, method 101 may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 600 via ROM 602 and / or communication unit 609. In some embodiments, the computing unit 601 may be configured to perform the methods of the embodiments by any other suitable means (e.g., by means of firmware).

[0083] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This 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 when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0084] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0085] As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0086] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0087] The systems and technologies described herein can be implemented in computing systems that include back-end components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected via digital data communication (e.g., a communication network) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0088] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0089] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this disclosure are performed, in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a terminal, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center integrating one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video disc (DVD); or it can be a semiconductor medium, such as a solid-state drive (SSD).

[0090] Although this disclosure has been described in conjunction with specific features and embodiments, it will be apparent that various modifications and combinations can be made therein without departing from the spirit and scope of this disclosure. Accordingly, this specification and drawings are merely exemplary illustrations of the disclosure as defined by the appended claims and are to be considered as covering any and all modifications, variations, combinations, or equivalents within the scope of this disclosure. It is obvious that those skilled in the art can make various alterations and modifications to this disclosure without departing from its spirit and scope. Thus, this disclosure is also intended to include any such modifications and modifications that fall within the scope of the claims of this disclosure and their equivalents.

Claims

1. A method for extracting problem-solving strategies for subjective mathematical questions, characterized in that, The method includes: Based on the first entity object information, first entity attribute information, and first entity object relationship information of the question stem text, the reference problem-solving ideas corresponding to the question stem text are obtained from the knowledge graph; wherein, the knowledge graph includes knowledge node data and the relationship between knowledge node data, and the knowledge node data includes conceptual node data, theorem node data, and formula node data; Based on the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text, candidate problem-solving ideas are obtained from the knowledge graph. Based on the candidate solutions and the reference solutions corresponding to the question text, output the user's solution corresponding to the question text. The step of outputting the user's solution to the question stem text based on the candidate solution ideas and the reference solution ideas corresponding to the question stem text includes: The overlap between the reference solution approach corresponding to the question stem text and the candidate solution approach is compared to obtain the overlap information. Based on the overlap information, the reference solution that has the highest overlap with the candidate solution is selected as the target reference solution. If the overlap between the target reference solution and the candidate solution is greater than a preset threshold, then the candidate solution is supplemented based on the target reference solution, and the supplemented candidate solution is used as the user solution corresponding to the question text, and the user solution corresponding to the question text is output. If the overlap between the target reference solution and the candidate solution is less than a preset threshold, the candidate solution is taken as the user solution corresponding to the question text, and the user solution corresponding to the question text is output. The step of obtaining reference problem-solving strategies corresponding to the question stem text from the knowledge graph based on the first entity object information, first entity attribute information, and first entity object relationship information of the question stem text includes: The first entity object information, first entity attribute information, and first entity object relationship information of the question text are input into the knowledge graph; Obtain the first similarity information between the knowledge node data in the knowledge graph and the first entity object information in the question text; Obtain the second similarity information between the knowledge node data in the knowledge graph and the first entity attribute information of the question text; The target node is determined in the knowledge graph based on the first similarity information and the second similarity information; Obtain the third similarity information between the relationship information of the target node data in the knowledge graph and the first entity object relationship information of the question text, and determine the target relationship information based on the third similarity information; Generate at least one reference solution approach corresponding to the question stem text based on the target node and the target relationship information; The step of obtaining candidate problem-solving approaches from the knowledge graph based on the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text includes: The second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text are input into the knowledge graph; Obtain fourth similarity information between the knowledge node data in the knowledge graph and the second entity object information of the response text; Obtain the fifth similarity information between the knowledge node data in the knowledge graph and the second entity attribute information of the response text; The target node is determined in the knowledge graph based on the fourth similarity information and the fifth similarity information; Obtain the sixth similarity information between the relationship information of the target node data in the knowledge graph and the second entity object relationship information of the answer text, and determine the target relationship information based on the sixth similarity information; The candidate problem-solving approaches are generated based on the target node and the target relationship information.

2. The method according to claim 1, characterized in that, The first entity attribute information includes the inherent attribute information and mathematical concept attribute information of the question stem text; the first entity object relationship information includes the organizational structure relationship information and logical relationship information between entities in the question stem text; the second entity attribute information includes the inherent attribute information and mathematical concept attribute information of the answer text corresponding to the question stem text; the second entity object relationship information includes the organizational structure relationship information and logical relationship information between entities in the answer text corresponding to the question stem text.

3. A device for extracting problem-solving strategies for subjective mathematical questions, characterized in that, The device includes: The first acquisition module is used to acquire reference problem-solving ideas corresponding to the question stem text from the knowledge graph based on the first entity object information, first entity attribute information and first entity object relationship information of the question stem text; wherein, the knowledge graph includes knowledge node data and the relationship between knowledge node data, and the knowledge node data includes conceptual node data, theoretical node data and formula node data; The second acquisition module is used to acquire candidate problem-solving ideas from the knowledge graph based on the second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text. The output module is used to output the user's solution to the question stem text based on the candidate solution ideas and the reference solution ideas corresponding to the question stem text. The output module is further configured to: The overlap between the reference solution approach corresponding to the question stem text and the candidate solution approach is compared to obtain the overlap information. Based on the overlap information, the reference solution that has the highest overlap with the candidate solution is selected as the target reference solution. If the overlap between the target reference solution and the candidate solution is greater than a preset threshold, then the candidate solution is supplemented based on the target reference solution, and the supplemented candidate solution is used as the user solution corresponding to the question text, and the user solution corresponding to the question text is output. If the overlap between the target reference solution and the candidate solution is less than a preset threshold, the candidate solution is taken as the user solution corresponding to the question text, and the user solution corresponding to the question text is output. The first acquisition module is further configured to: The first entity object information, first entity attribute information, and first entity object relationship information of the question text are input into the knowledge graph; Obtain the first similarity information between the knowledge node data in the knowledge graph and the first entity object information in the question text; Obtain the second similarity information between the knowledge node data in the knowledge graph and the first entity attribute information of the question text; The target node is determined in the knowledge graph based on the first similarity information and the second similarity information; Obtain the third similarity information between the relationship information of the target node data in the knowledge graph and the first entity object relationship information of the question text, and determine the target relationship information based on the third similarity information; Generate at least one reference solution approach corresponding to the question stem text based on the target node and the target relationship information; The second acquisition module is further configured to: The second entity object information, second entity attribute information, and second entity object relationship information of the answer text corresponding to the question stem text are input into the knowledge graph; Obtain fourth similarity information between the knowledge node data in the knowledge graph and the second entity object information of the response text; Obtain the fifth similarity information between the knowledge node data in the knowledge graph and the second entity attribute information of the response text; The target node is determined in the knowledge graph based on the fourth similarity information and the fifth similarity information; Obtain the sixth similarity information between the relationship information of the target node data in the knowledge graph and the second entity object relationship information of the answer text, and determine the target relationship information based on the sixth similarity information; The candidate problem-solving approaches are generated based on the target node and the target relationship information.

4. An electronic device, characterized in that, include: processor; as well as, Memory for stored programs; The program includes instructions that, when executed by the processor, cause the processor to perform the method according to any one of claims 1-2.

5. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the method according to any one of claims 1-2.

Images