Instruction processing method based on training system, training system, and storage medium

Abstract

The application relates to the technical field of training, and particularly discloses a command processing method based on a training system, the training system and a storage medium. The method comprises the following steps: receiving an input command of a user; identifying the intention of the user according to the input command and generating a target command corresponding to the identified intention; identifying and splitting the target command based on a classifier; extracting each command parameter and a corresponding execution interface from the splitting result; and calling each execution interface to execute the target command. The application can quickly and accurately pre-judge and identify the intention of the user for an incomplete or unclear input command, generate a target command corresponding to the identified intention, effectively improve the intelligent degree and self-adaptive capacity of the training system, effectively improve the processing efficiency of the target command, maintain a high response speed when the training system processes complex commands, and improve the overall use fluency and user experience of the training system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of training, in particular to a command processing method based on a training system, a training system and a storage medium. BACKGROUND

[0002] With the progress of science and technology, automated training systems have gradually become popular. Users can independently train through the training system. Specifically, users can input relevant commands in the training system to make the training system execute relevant actions.

[0003] However, when using a traditional training system, if the user's input command does not conform to the pre-set command inside the system, it is difficult to analyze the user's true intention and output the result the user wants. Therefore, the traditional training system has low intelligence and adaptability. SUMMARY

[0004] Therefore, it is necessary to provide a command processing method based on a training system, a training system and a computer readable storage medium to solve the above problems.

[0005] According to a first aspect of an embodiment of the present application, a command processing method based on a training system is provided, comprising:

[0006] receiving a user's input command;

[0007] identifying the user's intention according to the input command and generating a target command corresponding to the identified intention;

[0008] identifying and splitting the target command based on a classifier;

[0009] extracting each command parameter and the corresponding execution interface from the splitting result;

[0010] calling each execution interface to execute the target command.

[0011] In one embodiment, the step of identifying the user's intention according to the input command and generating a target command corresponding to the identified intention comprises:

[0012] When the input command is not clear, extracting a plurality of commands related to the intention of the input command from a pre-stored command set according to a pre-set intelligent model and outputting the plurality of commands;

[0013] receiving the user's selection command for the outputted plurality of commands;

[0014] determining the command selected by the user as the target command according to the user's selection command.

[0015] In one of the embodiments, the step of identifying the user's intention according to the input instruction and generating a target instruction corresponding to the identified intention further comprises:

[0016] When the input instruction is explicit, the input instruction is determined as the target instruction.

[0017] In one of the embodiments, before the step of identifying and splitting the target instruction based on the classifier, the instruction processing method based on the training system further comprises:

[0018] The classifier is pre-trained, and the pre-training comprises: constructing instruction sets of several functional domains in the training system, and dynamically generating a large number of instruction processing examples for each instruction in each instruction set in combination with an intelligent model and a classifier.

[0019] In one of the embodiments, the several functional domains include training management, course management, examination management, survey management, practice management, knowledge management, micro-lecture management, live broadcast management, decoration operation, student search, to-do list query, personal task query, and personal information query.

[0020] In one of the embodiments, the step of extracting each instruction parameter and the corresponding execution interface from the splitting result comprises:

[0021] When the initial extraction of each instruction parameter fails, the extraction of each instruction parameter is performed in combination with a preset intelligent model and each instruction processing example.

[0022] In one of the embodiments, after the step of extracting each instruction parameter and the corresponding execution interface from the splitting result, the instruction processing method based on the training system further comprises:

[0023] When the instruction parameter is a time parameter, the time parameter is parsed in combination with a pre-stored intelligent model to convert the time parameter into a date format.

[0024] In one of the embodiments, before the step of calling each execution interface to execute the target instruction, the instruction processing method based on the training system further comprises:

[0025] A secondary confirmation interface is provided for the user to receive feedback information of the user on each instruction parameter;

[0026] When a confirmation instruction of the user based on the secondary confirmation interface is received, the step of calling each execution interface to execute the target instruction is performed;

[0027] When a correction instruction of the user based on the secondary confirmation interface is received, each instruction parameter is corrected according to the correction instruction.

[0028] According to a second aspect of the embodiments of the present application, a training system is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above-mentioned instruction processing method based on the training system when executing the computer program.

[0029] According to a third aspect of the embodiments of the present application, a computer readable storage medium is provided, storing a computer program, and the computer program is executed by a processor to implement the above-mentioned instruction processing method based on the training system.

[0030] The instruction processing method based on the training system, the training system and the storage medium provided by the embodiments of the present application can recognize the intention of the user according to the input instruction of the user, generate a target instruction corresponding to the recognized intention, identify and split the target instruction based on the classifier, extract each instruction parameter and the corresponding execution interface from the splitting result, and finally call each execution interface to execute the target instruction to output the data required by the user. Compared with the prior art, in the scheme of the present application, the intention of the user can be quickly and accurately pre-identified for incomplete or unclear input instructions, and a target instruction corresponding to the identified intention is generated, which effectively improves the intelligent degree and adaptive ability of the training system. At the same time, the target instruction can be identified and split based on the classifier, and then each target parameter and the corresponding execution interface are extracted, and the execution interface is called to execute the target instruction, so that the processing efficiency of the target instruction can be effectively improved, and the training system can maintain a high response speed when processing complex instructions, thereby improving the overall use fluency and user experience of the training system. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 A flowchart of the instruction processing method based on the training system provided by an embodiment of the present application is shown;

[0032] Figure 2 A flowchart of the instruction processing method based on the training system provided by an embodiment of the present application is shown;

[0033] Figure 3 A flowchart of the instruction processing method based on the training system provided by an embodiment of the present application is shown;

[0034] Figure 4 A structural schematic diagram of the training system provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0035] For the purpose of clarity, the present application will be described below with reference to the attached drawings. The preferred embodiments of the present application are shown in the drawings. However, the present application can be realized in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and fully convey the scope of the present application to those skilled in the art.

[0036] In the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connecting", "fixing" and the like should be understood in a broad sense, for example, can be fixed connection, can also be detachable connection, or can be integrated; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through an intermediate medium, can be the internal communication of two elements or the interaction relationship between two elements, unless otherwise explicitly limited. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0037] The terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "multiple" is at least two, for example, two, three, etc., unless otherwise explicitly specified.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing the specific embodiments, and are not intended to limit the present application. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0039] As described in the background, the conventional training system lacks sufficient intelligence and adaptability in understanding user intent and executing specific instructions.

[0040] To solve the above problems, the embodiments of the present application provide a training system based instruction processing method, a training system and a computer readable storage medium.

[0041] In one embodiment, a training system based instruction processing method is provided, which can quickly and accurately identify the user's intent, thereby outputting the correct result, improving the overall satisfaction of the user, and improving the intelligence and adaptability of the training system.

[0042] Reference Figure 1 The training system based instruction processing method provided in the embodiment includes the following steps:

[0043] Step S100, receiving an input instruction of a user.

[0044] Firstly, when using the training system, the user can input an instruction in the user interface provided by the training system. In actual application, the input instruction of the user can be a complete instruction, or an incomplete instruction or an instruction with unclear intention.

[0045] Step S300, identifying the intention of the user according to the input instruction, and generating a target instruction corresponding to the identified intention.

[0046] When receiving the input instruction of the user, the intention of the user can be identified according to the input instruction, and a target instruction corresponding to the intention can be generated. As described above, the input instruction can not be a complete instruction or an instruction with clear intention. For such instructions, in the embodiment, the intention of the user can be identified according to the input instruction, which can be a pre-judgment of the intention of the user according to the input instruction of the user and the pre-stored instruction set, and a target instruction corresponding to the intention can be generated. In the embodiment, the intention of the user can also be pre-judged by other means according to the input instruction of the user, so as to generate a target instruction corresponding to the intention.

[0047] Step S500, identifying and splitting the target instruction based on the classifier.

[0048] After generating the target instruction, the target instruction can be parsed based on the classifier, and the target instruction can be identified and split, and the target instruction can be split into a plurality of instruction parameters for subsequent processing. For example, the target instruction is “query my courseware list”, and the target instruction can be split into two instruction parameters “my courseware” and “list” based on the classifier.

[0049] In the embodiment, the classifier can be pre-trained so as to be applicable to the rapid and accurate splitting of various target instructions.

[0050] Step S700, extracting each instruction parameter and the corresponding execution interface from the splitting result.

[0051] When the splitting of the target instruction is completed, each instruction parameter can be extracted from the splitting result, and the execution interface corresponding to each instruction parameter can also be extracted. As described in the foregoing example, two instruction parameters “my courseware” and “list” can be extracted, and the execution interfaces corresponding to “my courseware” and “list” can also be extracted. When each execution interface is called, the specific data corresponding to each instruction parameter can be obtained.

[0052] Step S900, calling each execution interface to execute the target instruction.

[0053] After determining the execution interface corresponding to each instruction parameter, each execution interface can be called to execute the target instruction, thereby outputting the data required by the user.

[0054] The instruction processing method based on the training system provided in the embodiment can identify the user's intention according to the input instruction of the user, generate a target instruction corresponding to the identified intention, identify and split the target instruction based on a classifier, extract each instruction parameter and the corresponding execution interface from the split result, and finally call each execution interface to execute the target instruction to output the data required by the user. Compared with the prior art, in the scheme of the present application, the intention of the user can be quickly and accurately pre-identified for incomplete or unclear input instructions, and a target instruction corresponding to the identified intention can be generated, thereby effectively improving the intelligent degree and adaptive ability of the training system. At the same time, the target instruction can be identified and split based on the classifier, and then each target parameter and the corresponding execution interface can be extracted, and the execution interface can be called to execute the target instruction, thereby effectively improving the processing efficiency of the target instruction. Even when the training system processes complex instructions, it can also maintain a high response speed, thereby improving the overall use fluency and user experience of the training system.

[0055] Reference Figure 2 In one of the embodiments, step S300, i.e., the step of identifying the user's intention according to the input instruction and generating a target instruction corresponding to the identified intention, includes:

[0056] Step S310, when the input instruction is unclear, extracting a plurality of instructions related to the intention of the input instruction from a pre-stored instruction set according to a preset intelligent model and outputting.

[0057] The unclear input instruction refers to the case that the input instruction is incomplete or the intention of the input instruction is unclear. For example, when the input instruction is "courseware", it is not a complete input instruction and the intention of the user is also unclear. When it is determined that the input instruction is unclear, a plurality of instructions related to the intention of the input instruction can be automatically extracted from a pre-stored instruction set according to a preset intelligent model, so that the user can select the instruction closest to the real intention. Returning to the above example, when the input instruction is "courseware", the instruction closest to "courseware" can be selected from the instruction set by using the intelligent model to expand the input instruction "courseware", for example, the input instruction "courseware" can be expanded to "query my courseware", "create new courseware process", "courseware management and update", and the like.

[0058] The number of the extracted instructions related to the intention of the input instruction can be at least three, thereby providing the user with a selection space and avoiding missing instructions reflecting the real intention of the user as much as possible.

[0059] The extracted instructions can be output to the human-computer interaction interface of the training system, so that the user can select them.

[0060] That is to say, when the input information of the user is limited, the potential needs of the user can be quickly captured and responded, thereby improving the efficiency and accuracy of instruction processing.

[0061] Step S320, receiving a selection instruction of the user on the output instructions.

[0062] When the instructions are output to the human-computer interaction interface of the training system, the user can select the instruction consistent with the needs of the user from the instructions through the human-computer interaction interface.

[0063] Step S330, determining the instruction selected by the user as the target instruction according to the selection instruction of the user.

[0064] When the user selects the instruction consistent with the needs of the user from the output instructions, the instruction selected by the user can be taken as the target instruction, that is, the instruction reflecting the real intention of the user. Thereby, subsequent data query and output can be performed according to the target instruction.

[0065] In one embodiment, step S300, that is, the step of identifying the intention of the user according to the input instruction and generating the target instruction corresponding to the identified intention, further comprises:

[0066] Step S310', when the input instruction is explicit, determining the input instruction as the target instruction.

[0067] When the input instruction of the user is an explicit instruction, for example, the input instruction of the user is "query my courseware", the input instruction is a complete instruction and the intention is clear. At this time, the input instruction does not need to be expanded and can be directly determined as the target instruction.

[0068] In one embodiment, before step S500, that is, the step of identifying and splitting the target instruction based on the classifier, the instruction processing method based on the training system provided in the embodiment further comprises:

[0069] The classifier is pre-trained, and the pre-training comprises: constructing instruction sets of a plurality of functional fields in the training system, and dynamically generating a large number of instruction processing examples for each instruction in each instruction set in combination with an intelligent model and the classifier.

[0070] Specifically, the instruction set can include instruction name, function description, target URL, required parameters, and invocation instances, etc. to ensure the comprehensiveness and accuracy of the instructions. Special emphasis is placed on the comprehensive coverage of professional terms, such as "micro course", "project", "courseware", "learning hours", and other key words specific to the training field are included in the instruction set. After the instruction set is constructed, a large number of instruction processing examples can be dynamically generated for each instruction in the instruction set by combining AI intelligent models and classifiers, which can incorporate a large number of professional scenario simulations, such as "query the learning hours of micro course <python basics>" and "upload courseware <data analysis case>", etc. to ensure that the intelligent model not only understands general instructions widely, but also accurately identifies and responds to complex instruction structures specific to the training system, so that when the user presents a demand related to "micro course management", "project progress tracking", "learning plan", etc., the system can provide efficient natural language processing support.

[0071] Among them, several functional areas can include training management, course management, examination management, survey management, practice management, knowledge management, micro course management, live broadcast management, decoration operation, student search, to-do list query, personal task query, and personal information query, etc. That is, each of the above core functional areas of the training system can be deeply trained so that the classifier can identify and process instructions related to each of the above core functional areas.

[0072] In step S500, the classifier can accurately distinguish whether the target instruction is a regular question exchange or a request containing a specific instruction, and if it is a request containing a specific instruction, it can be distinguished whether it comes from a management instruction or a query instruction, and then a corresponding special classifier is called for deep analysis. Under this framework, each classifier can be customized according to the source of the instruction, aiming to capture the subtle differences in instruction characteristics.

[0073] In one embodiment, step S700, i.e. the step of extracting each instruction parameter and the corresponding execution interface from the split result, includes:

[0074] When the initial extraction of each instruction parameter fails, the extraction of each instruction parameter is performed in combination with the pre-set intelligent model and each instruction processing example.

[0075] After the target instruction is identified and split by the classifier, each instruction parameter can be extracted from the split result, and the corresponding execution interface of each instruction parameter can also be extracted. In this step, if the initial extraction fails, the extraction can be performed with the help of the trained intelligent model and each instruction processing example. The intelligent model can deeply analyze the semantic relationship between the user instruction and the instruction processing example, not only accurately capturing key information fragments in the instruction, but also identifying elements that are crucial to the execution of the instruction in a complex language environment.

[0076] In one of the embodiments, after the step S700, i.e., the step of extracting each instruction parameter and the corresponding execution interface in the split result, the instruction processing method based on the training system further comprises:

[0077] When the instruction parameter is a time parameter, the time parameter is parsed in combination with a pre-stored intelligent model to convert the time parameter into a date format.

[0078] For example, when the extracted instruction parameter contains a time parameter, the time parameter can be parsed in combination with an intelligent model. Specifically, the time parameter can include "today", "tomorrow", "yesterday", "last year", and the like, which do not belong to machine-readable dates. Therefore, before executing the target instruction, the time parameter can be parsed and converted into a date format so that the machine can execute directly. For another example, the time parameter can also be a very irregular expression covering a complex time span, such as "past year". For such an expression, the relative relationship between the current date and the time span can be accurately captured by the reasoning and understanding ability of the intelligent model, and converted into an interval composed of explicit and calculable dates, thereby ensuring the accuracy of parameter extraction and the executability of the instruction.

[0079] In step S900, when the number of target instructions exceeds 1, each target instruction can be executed in turn. When each target instruction is executed, the corresponding API execution interface can be called to realize the docking of the natural language instruction and the training system. Meanwhile, after the target instruction is executed to obtain the corresponding data, the data can be format-converted and beautified, and then output and displayed to the man-machine interaction interface in the form of a card, thereby improving the intuitiveness and fluency of the interaction between the user and the training system.

[0080] Reference Figure 3 In one of the embodiments, before the step S900, i.e., the step of calling each execution interface to execute the target instruction, the instruction processing method based on the training system further comprises:

[0081] Step S910, providing a secondary confirmation interface for the user to receive feedback information of each instruction parameter of the user;

[0082] Step S920, when receiving a confirmation instruction of the user based on the secondary confirmation interface, executing the step of calling each execution interface to execute the target instruction;

[0083] Step S930, when receiving a correction instruction of the user based on the secondary confirmation interface, correcting each instruction parameter according to the correction instruction.

[0084] In other words, after successfully extracting each instruction parameter and its corresponding execution interface, further verification can be performed to ensure the accuracy of the operation. This step is a user interaction confirmation stage, providing the user with a secondary confirmation interface that displays the parsed instruction parameters. The user can confirm whether the parsed instruction parameters match their intention. If they match, the user can input a confirmation command, allowing the system to proceed to the next step. If they do not match, the user can directly correct the instruction parameters on the secondary confirmation interface, and the system will execute subsequent steps according to the corrected instruction parameters. This secondary confirmation process further ensures the smoothness of human-computer interaction and the convenience of correction.

[0085] In one embodiment, a training system is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps in the above method embodiments.

[0086] Figure 4 This is a schematic diagram of the structure of a training system provided in an embodiment of this application. The training system can be a server, and its internal structure diagram can be as follows: Figure 4 As shown, the training system includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores various types of data related to the instruction processing methods. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements an instruction processing method.

[0087] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the training system to which the present application is applied. A specific training system may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0088] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0089] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0090] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0091] Any combination of the technical features of the above-mentioned embodiments can be combined. In order to make the description simple, all possible combinations of the technical features in the above-mentioned embodiments are not described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0092] The above-mentioned embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the patent scope. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for processing instructions based on a training system, characterized in that, include: Receive user input commands; The system identifies the user's intent based on the input command and generates a target command corresponding to the identified intent. This includes: constructing instruction sets for several functional areas within the training system and dynamically generating numerous instruction processing examples for each instruction in each instruction set using an intelligent model and classifier. These examples incorporate numerous professional scenario simulations from training scenarios. The functional areas include training management, course management, exam management, survey management, practice management, knowledge management, micro-course management, live streaming management, setup operations, student search, to-do list query, personal task query, and personal information query. When the input command is unclear, the system extracts and outputs several instructions related to the intent of the input command from a pre-stored instruction set based on a preset intelligent model. These extracted instructions are all complete instructions expanded from the input command. The system receives the user's selection of one of the output instructions. Based on the user's selection, the selected instruction is determined as the target command. The classifier distinguishes whether the target instruction is a routine question or a request containing a specific instruction. If it is a request containing a specific instruction, it further determines whether the request originates from a management instruction or a query instruction, and calls the corresponding specialized classifier to identify and segment the target instruction. Extract the instruction parameters and their corresponding execution interfaces from the splitting results; Call each execution interface to execute the target instruction; Before calling each execution interface to execute the target instruction, a secondary confirmation interface is provided to the user to receive feedback information from the user on each instruction parameter; when a confirmation instruction is received from the user based on the secondary confirmation interface, the step of calling each execution interface to execute the target instruction is executed; when a correction instruction is received from the user based on the secondary confirmation interface, the instruction parameters are corrected according to the correction instruction.

2. The instruction processing method based on the training system according to claim 1, characterized in that, The step of recognizing the user's intent based on the input instruction and generating a target instruction corresponding to the recognized intent further includes: When the input instruction is explicit, the input instruction is determined as the target instruction.

3. The instruction processing method based on the training system according to claim 1, characterized in that, The steps for extracting each instruction parameter and its corresponding execution interface from the splitting results include: When the initial extraction of each instruction parameter fails, the extraction of each instruction parameter is performed by combining the preset intelligent model and the instruction processing examples.

4. The instruction processing method based on the training system according to claim 1, characterized in that, After the step of extracting each instruction parameter and its corresponding execution interface from the splitting result, the instruction processing method based on the training system further includes: When the instruction parameter is a time parameter, the time parameter is parsed using a pre-stored intelligent model to convert it into a date format.

5. A training system comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the instruction processing method based on the training system as described in any one of claims 1-4.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the instruction processing method based on the training system as described in any one of claims 1-4.

Images