CN117540034A - Test question model generation method and device and computer equipment - Google Patents

Abstract

The application relates to a test question model generation method, a test question model generation device, a test question model generation computer device, a test question model generation program and a test question model generation program. The method comprises the following steps: acquiring a test question set and current test question feature information, wherein the current test question feature information is used for representing the relation between different test questions in the test question set; performing iterative optimization on the current test question feature information by adopting an alternative recommendation algorithm to obtain target test question feature information; constructing a target knowledge graph according to the characteristic information of the target test questions; responding to a test question generation request, and selecting test questions in the test question set according to the target knowledge graph so as to generate a test question model. By adopting the method, the examination questions can be flexibly generated so as to meet different examination scenes.

Description

Test question model generation method, device and computer equipment

Technical field

The present application relates to the field of artificial intelligence technology, and in particular to a test question model generation method, device, computer equipment, storage medium and computer program product.

Background technique

With the continuous development of the power system, at this stage, refined modeling methods and simulation models of distributed photovoltaic clusters suitable for large power grid stability analysis have been carried out at home and abroad, as well as multi-scale power grids in high-penetration distributed photovoltaic access scenarios. Relevant research on coordinated control system architecture and key strategies for operational control. However, research on training simulation systems in new power system environments has not yet been carried out.

At present, the dispatcher training model is still the traditional "old and new". Dispatcher training is not systematic enough. Training and assessment evaluation lack the support of professional information systems. Training does not have a high-quality interactive environment. The operation level of relevant systems can only rely on subjective evaluation. , lack of objective and quantitative assessment methods.

In related technologies, preset test questions are usually used to assess relevant personnel, and the preset test questions cannot meet different assessment scenarios.

Contents of the invention

Based on this, it is necessary to address the above technical problems and provide a test question model generation method, device, computer equipment, computer readable storage medium and computer program product that can meet different assessment scenarios.

In the first aspect, this application provides a test question model generation method, including:

Obtain the test question set and the current test question feature information, where the current test question feature information is used to characterize the relationship between different test questions in the test question set;

Using an alternating recommendation algorithm to iteratively optimize the feature information of the current test question to obtain the feature information of the target test question;

Construct a target knowledge graph based on the characteristic information of the target test questions;

In response to the test question generation request, test questions in the test question set are selected according to the target knowledge graph to generate a test question model.

In one embodiment, the current test question feature information includes test question keywords and current test question relationship data; the use of an alternating recommendation algorithm to iteratively optimize the current test question feature information to obtain the target test question feature information includes:

Using an alternating recommendation algorithm, iteratively optimize the test question feature information according to the current test question relationship data to obtain target test question relationship data;

Target test question feature information is generated according to the test question keywords and the target test question relationship data.

In one embodiment, constructing the target knowledge graph based on the target test question feature information includes:

Generate a basic knowledge map based on the test question keywords;

The basic knowledge graph is updated according to the characteristic information of the target test question to obtain the target knowledge graph.

In one embodiment, in response to a question generation request, selecting questions from the question set according to the target knowledge graph to generate a question model includes:

In response to the test question generation request, select test questions from the test question set according to the target knowledge graph to obtain simulated test question data;

Check the simulated test question data according to the test question keywords;

If the test passes, a test question model is generated based on the simulated test question data.

In one embodiment, the test question set is obtained step by step according to the operating steps of the distributed energy system.

In one embodiment, the method is used for operational assessment of nonlinear systems.

In the second aspect, this application also provides a test question model generation device, including:

An information acquisition module, used to obtain the test question set and current test question feature information, wherein the current test question feature information is used to characterize the connection between different test questions in the test question set;

An iterative optimization module for iteratively optimizing the current test question feature information using an alternating recommendation algorithm to obtain the target test question feature information;

A graph generation module, configured to construct a target knowledge graph based on the characteristic information of the target test questions;

A test question generation module, configured to respond to a test question generation request and select test questions from the test question set according to the target knowledge graph to generate a test question model.

In a third aspect, this application also provides a computer device, including a memory and a processor. The memory stores a computer program. When the processor executes the computer program, it implements the following steps:

Obtain the test question set and the current test question feature information, where the current test question feature information is used to characterize the relationship between different test questions in the test question set;

Using an alternating recommendation algorithm to iteratively optimize the feature information of the current test question to obtain the feature information of the target test question;

Construct a target knowledge graph based on the characteristic information of the target test questions;

In response to the test question generation request, test questions in the test question set are selected according to the target knowledge graph to generate a test question model.

In a fourth aspect, the application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

Obtain the test question set and the current test question feature information, where the current test question feature information is used to characterize the relationship between different test questions in the test question set;

Using an alternating recommendation algorithm to iteratively optimize the feature information of the current test question to obtain the feature information of the target test question;

Construct a target knowledge graph based on the characteristic information of the target test questions;

In response to the test question generation request, test questions in the test question set are selected according to the target knowledge graph to generate a test question model.

In a fifth aspect, this application also provides a computer program product, including a computer program that implements the following steps when executed by a processor:

Obtain the test question set and the current test question feature information, where the current test question feature information is used to characterize the relationship between different test questions in the test question set;

Using an alternating recommendation algorithm to iteratively optimize the feature information of the current test question to obtain the feature information of the target test question;

Construct a target knowledge graph based on the characteristic information of the target test questions;

In response to the test question generation request, test questions in the test question set are selected according to the target knowledge graph to generate a test question model.

The above-mentioned test question model generation method, device, computer equipment, storage medium and computer program product obtain the test question set and the current test question characteristic information to obtain the current existing test question subjects and the connections between different questions in the test question set, using an alternating recommendation algorithm Iteratively optimize the characteristic information of the current test question to obtain the characteristic information of the target test question, and then build the target knowledge graph based on the characteristic information of the target test question. In response to the test question generation request, test questions in the test question set are selected according to the target knowledge graph to generate a test question model. The alternating recommendation algorithm is a universal, end-to-end in-depth recommendation framework that aims to use knowledge graph embedding to assist in recommendation tasks, so that assessment questions can be flexibly generated to meet different assessment scenarios.

Description of drawings

In order to more clearly explain the technical solutions in the embodiments of the present application or related technologies, the drawings needed to be used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings in the following description are only for the purpose of describing the embodiments or related technologies. For some embodiments of the application, those of ordinary skill in the art can also obtain other drawings based on these drawings without exerting creative efforts.

Figure 1 is an application environment diagram of a test question model generation method in one embodiment;

Figure 2 is a schematic flowchart of a test question model generation method in one embodiment;

Figure 3 is a schematic flowchart of steps S204 to S206 in the test question model generation method in one embodiment;

Figure 4 is a structural block diagram of a test question model generating device in one embodiment;

Figure 5 is an internal structure diagram of a computer device in one embodiment;

Figure 6 is an internal structure diagram of a computer device in another embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.

The test question model generation method provided by the embodiment of the present application can be applied in the application environment as shown in Figure 1. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system may store data that server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The data storage system is used to store test question sets and current test question feature information, as well as cached data in the iterative optimization process. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. . Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented as an independent server or a server cluster composed of multiple servers.

In an exemplary embodiment, as shown in Figure 2, a test question model generation method is provided. This method is explained by taking the method applied to the server 104 in Figure 1 as an example, including the following steps S202 to S208. in:

Step S202: Obtain the test question set and current test question feature information.

Among them, the current test question feature information is used to represent the connection between different test questions in the test question set.

For example, this method can be used for operational assessment of nonlinear systems. The server 104 can first establish a power system model based on the Hammerstein model. The established power system model is composed of static nonlinear links and dynamic linear links connected in series, which can highly approximate the dynamic characteristics of the nonlinear system. Its dynamic links and static links can be modeled separately, which has The simulation calculation amount is small and can simplify the nonlinear control design. And the server 104 executes this method to establish a test question model based on the dispatcher's operation points, where the dispatcher's operation points are the dispatcher's operation points in the power system scenario.

Among them, the Hammerstein model is a mathematical model that describes nonlinear systems. It consists of two parts connected in series: a static nonlinear part and a dynamic linear part. Together these two parts form the overall model of the nonlinear system. The static nonlinear part describes the nonlinear relationship between input and output, usually represented by a static nonlinear function. The output of this function depends on the input but is not affected by the dynamics of the system. The dynamic linear part describes the dynamic behavior of the system, that is, the linear relationship between input and output. It is usually expressed through difference equations or differential equations, which contain the dynamic characteristics of the system. This section is typically used to describe the delay, inertia, and dynamic response of the system.

For example, the server 104 may obtain the test question set step by step according to the operating steps of the distributed energy system, and may record the operation rank corresponding to each test question when acquiring the test question set.

Step S204: Use an alternating recommendation algorithm to iteratively optimize the feature information of the current test question to obtain the feature information of the target test question.

Among them, the alternating recommendation algorithm is a technology used in recommendation systems, mainly used to optimize the representation of users and items to improve the accuracy of recommendations. This type of algorithm optimizes user and item representations through alternating iterations to better capture the underlying relationships between them. These algorithms often fall into the category of collaborative filtering, where user and item representations are learned by mining user behavior data. For example, the alternating recommendation algorithm may be the MKR algorithm (Multi-task Learning forKG enhanced Recommendation). The MKR algorithm is a recommendation algorithm based on the knowledge graph, which uses the information in the knowledge graph to enhance the performance of the recommendation system. MKR mainly focuses on two tasks: automatic generation task (AutomaticTask) and automatic rating task (Rating Prediction Task). These two tasks are independent of each other, but are related to each other through entity relationships in the knowledge graph.

For example, the server 104 can establish a test question library including a test question keyword index without establishing a test question library containing a test question keyword index to collect statistics on current test question feature information; In the case of a test question bank, the existing test question information is recorded into the test question bank including a test question keyword index to collect statistics on the current test question feature information. Then the alternating recommendation algorithm is used to iteratively optimize the feature information of the current test question to obtain the feature information of the target test question.

Step S206: Construct a target knowledge graph based on the characteristic information of the target test questions.

Among them, in the above-mentioned MKR algorithm, the knowledge graph (Knowledge Graph) is a graphical structure used to represent the relationships and attributes between entities. In recommendation systems, knowledge graphs usually contain information related to the recommendation task such as entities (such as users, items), relationships (such as users' preferences for items), attributes (such as characteristics of items), and other information. Specifically, the knowledge graph in the MKR algorithm includes entities, relationships, attributes, triples and other elements: Entities include entities related to the recommendation task, such as users and items. Each entity has a unique identifier. Relations describe the relationships between entities. These relationships can be user preferences for items, attribute relationships of items, etc. Relationships are usually represented by directed edges, connecting two entities. Attributes are characteristics or attribute information that describe entities or relationships. In a recommendation system, the attributes of items may include categories, tags, ratings, etc., while the attributes of users may include historical behaviors, preferences, etc. In addition, the information in the knowledge graph is stored in the form of triples, namely (entity 1, relationship, entity 2). This representation helps organize and retrieve information in the knowledge graph. The triplet may include the test question content, the test question attribute category, and the relationship between different test questions.

In MKR, the purpose of the knowledge graph is to provide enhanced information for recommendation tasks by learning the relationships between entities. Entity relationships in knowledge graphs can be used to generate task-specific representations, thereby improving the performance of recommendation systems. The MKR algorithm alternately optimizes recommendation tasks and automatically generated tasks in the knowledge graph, so that task-specific representation and knowledge graph information promote each other to improve the recommendation effect.

Step S208: In response to the test question generation request, test questions in the test question set are selected according to the target knowledge graph to generate a test question model.

The test question generation request is issued by the terminal 102 and is used to instruct the server 104 to generate request instruction information for simulated test questions. For example, the test question generation request may be issued by the terminal 102 according to the input instructions received from the examiner.

For example, the server 104 can parse the test question information carried in the test question generation request according to the test question generation request issued by the terminal 102, and analyze the corresponding part of the target knowledge graph according to the test question information, thereby selecting the test questions in the test question set, and will select the test question. The test questions are combined and packaged according to the order of the test questions to form a test question model.

In the above test question model generation method, by obtaining the test question set and the current test question feature information, the current existing test question body and the relationship between different questions in the test question set are obtained, and the alternating recommendation algorithm is used to iteratively optimize the current test question feature information to obtain Target test question feature information, and then build a target knowledge graph based on the target test question feature information. In response to the test question generation request, test questions in the test question set are selected according to the target knowledge graph to generate a test question model. The alternating recommendation algorithm is a general, end-to-end deep recommendation framework designed to utilize knowledge graph embeddings to assist recommendation tasks. The two tasks are the automatic generation task and the automatic scoring task. The two tasks are independent of each other, but they are highly related because the items in the embedding layer RS and the entities in the embedding layer KG are interconnected. The entire framework can be trained by alternately optimizing two tasks, giving MKR a high degree of flexibility and adaptability in real recommendation scenarios, so that it can flexibly generate assessment questions.

In an exemplary embodiment, as shown in FIG. 3 , step S204 includes steps S302 to step S306, and correspondingly, step S206 includes steps S306 to step S308. in:

Step S302: Use an alternating recommendation algorithm to iteratively optimize the test question feature information based on the current test question relationship data to obtain target test question relationship data.

Among them, the current test question feature information includes test question keywords and current test question relationship data. The test question keywords are used to represent the characteristics of the current test question, and the current test question relationship data is used to represent the correlation information between different test questions, such as the degree of correlation, the difficulty of the test question, the proportion of the difficulty of the test question, etc.

For example, the server 104 can use an alternating recommendation algorithm to iteratively optimize the test question feature information according to the current test question relationship data, thereby filling some gaps in the current test question relationship data, and making the test question relationship data closer to actual requirements, thereby obtaining the target test question relationship. data.

Step S304: Generate target test question feature information based on test question keywords and target test question relationship data.

For example, the server 104 can make a one-to-one correspondence between the newly generated target test question relationship data and the test question keywords, and map the target test question relationship data to a set corresponding to the test question keywords by searching to form new target test question feature information. .

Step S306: Generate a basic knowledge map according to the test question keywords.

Among them, the basis can be a static prior knowledge constructed based on the test question keywords.

Step S308: Update the basic knowledge graph according to the characteristic information of the target test question to obtain the target knowledge graph.

For example, the server 104 can use the basic knowledge graph and target test question feature information to obtain the target knowledge graph, and use the MKR algorithm as the optimization objective function to learn the representation of users and items (or other entities), which includes prediction targets and knowledge regularization terms. Furthermore, in the optimization objective function, the knowledge regularization term is introduced. This item converts the relationships in the initial knowledge graph into constraints on the model representation to ensure that the learned representation conforms to the relationships defined in the knowledge graph as much as possible.

In an exemplary embodiment, step S208 includes responding to the test question generation request, selecting test questions from the test question set according to the target knowledge graph, and obtaining simulated test question data; checking the simulated test question data according to the test question keywords; if the test passes , generate a test question model based on simulated test question data.

For example, the server 104 can gradually select the test questions from the test question set according to the target knowledge graph according to the operation sequence of the power system, and then gradually verify the test questions in the test question model, thereby generating the final test question model.

In another embodiment, the server 104 first establishes a power system model composed of static nonlinear links and dynamic linear links in series based on the Hammerstein model. The server 104 executes this method to establish a test question model based on the dispatcher's operating points, where the dispatcher The operator operation points are the operation points of the dispatcher in the power system scenario. The server 104 obtains the test question set under the power system model, gradually obtains the test questions according to the operating steps of the distributed energy system to form a test question set, and records the operation position and test question characteristic information corresponding to each test question when acquiring the test question set.

Next, when the server 104 has not established a test question bank including a test question keyword index, it establishes the test question bank including a test question keyword index to collect statistics on the current test question feature information; when a test question bank including a test question keyword index has been established In the case of , the existing test question information is recorded into the test question database containing the test question keyword index to collect statistics on the current test question feature information. Then the alternating recommendation algorithm is used to iteratively optimize the current test question feature information and establish a target knowledge graph to obtain the target test question feature information.

During use, the server 104 parses the test question information carried in the test question generation request according to the test question generation request sent by the terminal 102, and analyzes the corresponding part of the target knowledge graph according to the test question information, thereby selecting the test questions in the test question set, and will The test questions are combined and packaged according to the order of the test questions to form a test question model.

It should be understood that although the steps in the flowcharts involved in the above-mentioned embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments may include multiple steps or stages. These steps or stages are not necessarily executed at the same time, but may be completed at different times. The execution order of these steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

Based on the same inventive concept, embodiments of the present application also provide a test question model generation device for implementing the above-mentioned test question model generation method. The problem-solving solution provided by this device is similar to the solution recorded in the above method. Therefore, the specific limitations in one or more test question model generation device embodiments provided below can be found in the test question model generation method mentioned above. Limitations will not be repeated here.

In an exemplary embodiment, as shown in Figure 4, a test question model generation device is provided, including: an information acquisition module 402, an iterative optimization module 404, a graph generation module 406, and a test question generation module 408, wherein:

The information acquisition module 402 is used to obtain the test question set and the current test question feature information, where the current test question feature information is used to represent the connection between different questions in the test question set;

The iterative optimization module 404 is used to iteratively optimize the current test question feature information using an alternating recommendation algorithm to obtain the target test question feature information;

The graph generation module 406 is used to construct a target knowledge graph based on the characteristic information of the target test questions;

The test question generation module 408 is configured to respond to the test question generation request and select test questions from the test question set according to the target knowledge graph to generate a test question model.

In one embodiment, the current test question feature information includes test question keywords and current test question relationship data; the iterative optimization module 404 includes:

The data optimization unit is used to use the alternating recommendation algorithm to iteratively optimize the test question feature information based on the current test question relationship data to obtain the target test question relationship data;

An information generation unit is used to generate target test question characteristic information based on test question keywords and target test question relationship data.

In one embodiment, the map generation module 406 includes:

The map initialization unit is used to generate a basic knowledge map based on test question keywords;

The map update unit is used to update the basic knowledge map according to the characteristic information of the target test question to obtain the target knowledge map.

In one embodiment, the test question generation module 408 includes:

Test questions are upgraded into units, which are used to respond to the test question generation request, select test questions from the test question set according to the target knowledge graph, and obtain simulated test question data;

The test question verification unit is used to check the simulated test question data based on the test question keywords;

The model generation unit is used to generate a test question model based on the simulated test question data when the test is passed.

In one embodiment, the test question set is obtained step by step according to the operating steps of the distributed energy system.

In one embodiment, the method is used for operational assessment of nonlinear systems.

Each module in the above-mentioned test question model generation device can be realized in whole or in part by software, hardware and combinations thereof. Each of the above modules may be embedded in or independent of the processor of the computer device in the form of hardware, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be shown in Figure 5 . The computer device includes a processor, a memory, an input/output interface (Input/Output, referred to as I/O), and a communication interface. Among them, the processor, memory and input/output interface are connected through the system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage medium stores operating systems, computer programs and databases. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media. The database of the computer device is used to store test question sets and current test question feature information, as well as cached data in the iterative optimization process. The input/output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. The computer program implements a test question model generating method when executed by the processor.

In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. 6 . The computer device includes a processor, memory, input/output interface, communication interface, display unit and input device. Among them, the processor, memory and input/output interface are connected through the system bus, and the communication interface, display unit and input device are connected to the system bus through the input/output interface. Wherein, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage medium stores operating systems and computer programs. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals. The wireless mode can be implemented through WIFI, mobile cellular network, NFC (Near Field Communication) or other technologies. The computer program implements a test question model generating method when executed by the processor. The display unit of the computer equipment is used to form a visually visible picture, and may be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display or an electronic ink display. The input device of the computer device can be a touch layer covered on the display screen, or it can be a button, trackball or touch pad provided on the computer device casing, or it can be External keyboard, trackpad or mouse, etc.

Those skilled in the art can understand that the structure shown in Figure 6 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Specific computer equipment can May include more or fewer parts than shown, or combine certain parts, or have a different arrangement of parts.

In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, it implements the following steps: obtaining a test question set and current test question characteristic information, wherein , the characteristic information of the current test question is used to characterize the connection between different questions in the test question set; the alternating recommendation algorithm is used to iteratively optimize the characteristic information of the current test question to obtain the characteristic information of the target test question; the target knowledge graph is constructed based on the characteristic information of the target test question; in response to the test question Generate a request and select test questions from the test question set based on the target knowledge graph to generate a test question model.

In one embodiment, the processor also implements the following steps when executing the computer program: using an alternating recommendation algorithm, iteratively optimizing the test question feature information according to the current test question relationship data to obtain the target test question relationship data; according to the test question keywords and the target test question relationship The data generates target test question feature information.

In one embodiment, when the processor executes the computer program, it also implements the following steps: generating a basic knowledge graph according to the test question keywords; updating the basic knowledge graph according to the target test question feature information to obtain the target knowledge graph.

In one embodiment, the processor also implements the following steps when executing the computer program: in response to the test question generation request, selects test questions from the test question set according to the target knowledge graph to obtain simulated test question data; checks the simulated test question data according to the test question keywords; If the test passes, a test question model is generated based on the simulated test question data.

In one embodiment, a computer-readable storage medium is provided, with a computer program stored thereon. When the computer program is executed by a processor, the following steps are implemented: obtaining a test question set and current test question feature information, where the current test question feature information is To represent the connection between different questions in the test question set; use the alternating recommendation algorithm to iteratively optimize the feature information of the current test question to obtain the feature information of the target question; build the target knowledge graph based on the feature information of the target question; respond to the question generation request, according to the target knowledge The graph selects test questions from the test question set to generate a test question model.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: using an alternating recommendation algorithm, iteratively optimizing the test question feature information according to the current test question relationship data to obtain the target test question relationship data; according to the test question keywords and the target test question Relational data generates target test question feature information.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: generating a basic knowledge graph according to the test question keywords; updating the basic knowledge graph according to the target test question feature information to obtain the target knowledge graph.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: in response to the test question generation request, select the test questions in the test question set according to the target knowledge graph, and obtain the simulated test question data; check the simulated test question data according to the test question keywords; If the test passes, a test question model is generated based on the simulated test question data.

In one embodiment, a computer program product is provided, including a computer program. When executed by a processor, the computer program implements the following steps: obtaining a test question set and current test question feature information, wherein the current test question feature information is used to characterize the test question set. The connection between different test questions; use the alternating recommendation algorithm to iteratively optimize the feature information of the current test question to obtain the feature information of the target test question; build the target knowledge graph based on the feature information of the target test question; respond to the question generation request, select the test question set based on the target knowledge graph test questions to generate test question models.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: using an alternating recommendation algorithm, iteratively optimizing the test question feature information according to the current test question relationship data to obtain the target test question relationship data; according to the test question keywords and the target test question Relational data generates target test question feature information.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: generating a basic knowledge graph according to the test question keywords; updating the basic knowledge graph according to the target test question feature information to obtain the target knowledge graph.

In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: in response to the test question generation request, select the test questions in the test question set according to the target knowledge graph, and obtain the simulated test question data; check the simulated test question data according to the test question keywords; If the test passes, a test question model is generated based on the simulated test question data.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage. In the media, when executed, the computer program may include the processes of the above method embodiments. Any reference to memory, database or other media used in the embodiments provided in this application may 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, optical memory, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetic variable memory (Magnetoresistive Random) Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene memory, etc. Volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include blockchain-based distributed databases, etc., but are not limited thereto. The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to this.

The technical features of the above embodiments can be combined in any way. To simplify the description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, all possible combinations should be used. It is considered to be within the scope of this manual.

The above-described embodiments only express several implementation modes of the present application, and their descriptions are relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all fall within the protection scope of the present application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims (10)

1. The test question model generation method is characterized by comprising the following steps:

acquiring a test question set and current test question feature information, wherein the current test question feature information is used for representing the relation between different test questions in the test question set;

performing iterative optimization on the current test question feature information by adopting an alternative recommendation algorithm to obtain target test question feature information;

constructing a target knowledge graph according to the characteristic information of the target test questions;

responding to a test question generation request, and selecting test questions in the test question set according to the target knowledge graph so as to generate a test question model.

2. The method according to claim 1, wherein the current test question feature information comprises test question keywords and current test question relation data; the step of performing iterative optimization on the current test question feature information by adopting an alternative recommendation algorithm to obtain target test question feature information comprises the following steps:

adopting an alternate recommendation algorithm, and carrying out iterative optimization on the test question feature information according to the current test question relation data so as to obtain target test question relation data;

and generating target test question feature information according to the test question keywords and the target test question relation data.

3. The method of claim 2, wherein constructing a target knowledge-graph from the target test question feature information comprises:

generating a basic knowledge graph according to the test question keywords;

and updating the basic knowledge graph according to the characteristic information of the target test questions to obtain a target knowledge graph.

4. The method of claim 2, wherein the selecting the questions in the set of questions according to the target knowledge-graph in response to the question generation request to generate the question model comprises:

responding to a test question generation request, and selecting test questions in the test question set according to the target knowledge graph to obtain simulated test question data;

checking the simulated test question data according to the test question keywords;

and generating a test question model according to the simulated test question data under the condition that the test passes.

5. The method of claim 1, wherein the test question sets are obtained step by step according to the operating steps of the distributed energy system.

6. The method according to any one of claims 1 to 5, wherein the method is used for operational assessment of a nonlinear system.

7. A test question model generation device, characterized in that the device comprises:

the information acquisition module is used for acquiring a test question set and current test question feature information, wherein the current test question feature information is used for representing the relation between different test questions in the test question set;

the iterative optimization module is used for carrying out iterative optimization on the current test question feature information by adopting an alternative recommendation algorithm so as to obtain target test question feature information;

the map generation module is used for constructing a target knowledge map according to the target test question characteristic information;

and the test question generation module is used for responding to a test question generation request, selecting test questions in the test question set according to the target knowledge graph so as to generate a test question model.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.