Questionnaire generation method and device, computer equipment, storage medium and program product

Abstract

The invention relates to a questionnaire generation method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: receiving questionnaire description information about a to-be-generated target questionnaire input by a user, and obtaining type information corresponding to the target questionnaire based on the questionnaire description information; performing information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire; and inputting the questionnaire description information, the type information and the questionnaire design prompt information into a target large language model to obtain the target questionnaire output by the target large language model. By adopting the method, the flexibility of questionnaire generation can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a questionnaire generation method, apparatus, computer equipment, storage medium and computer program product. Background Art

[0002] Questionnaires are a tool used to collect data in social research. Researchers can use questionnaires to accurately and specifically measure the process of social activities, and apply sociological statistical methods to conduct quantitative description and analysis.

[0003] In the prior art, a template is usually used to generate the required questionnaire. However, this questionnaire generation method makes the flexibility of questionnaire generation poor. Summary of the invention

[0004] Based on this, it is necessary to provide a questionnaire generation method, device, computer equipment, computer-readable storage medium and computer program product with high flexibility to address the above technical issues.

[0005] In a first aspect, the present application provides a questionnaire generation method, comprising:

[0006] Receive questionnaire description information about a target questionnaire to be generated input by a user, and obtain type information corresponding to the target questionnaire based on the questionnaire description information; perform information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire; input the questionnaire description information, the type information and the questionnaire design prompt information into a target large language model to obtain the target questionnaire output by the target large language model.

[0007] In one embodiment, the questionnaire description information is subjected to information expansion processing to obtain questionnaire design prompt information corresponding to the target questionnaire, including: inputting the questionnaire description information into an intelligent agent selector to obtain the questionnaire design prompt information output by the intelligent agent selector after performing information expansion processing on the questionnaire description information.

[0008] In one embodiment, the questionnaire description information is input into the intelligent agent selector to obtain the questionnaire design prompt information output after the intelligent agent selector performs information expansion processing on the questionnaire description information, including: inputting the questionnaire description information into the intelligent agent selector, so that the intelligent agent selector determines the target thinking chain from multiple thinking chains according to the questionnaire description information, and performs information expansion processing on the questionnaire description information according to the target thinking chain to obtain the questionnaire design prompt information.

[0009] In one embodiment, the obtaining of the type information corresponding to the target questionnaire based on the questionnaire description information includes: inputting the questionnaire description information into a questionnaire classifier to obtain the type information output by the questionnaire classifier.

[0010] In one of the embodiments, the type information includes questionnaire type information and questionnaire content type information, wherein the questionnaire type information is used to indicate the type of the target questionnaire, and the questionnaire content type information is used to indicate the type of questionnaire content involved in the target questionnaire.

[0011] In one embodiment, the questionnaire description information is input into a questionnaire classifier to obtain the type information output by the questionnaire classifier, including: inputting the questionnaire description information into the questionnaire classifier, so that the questionnaire classifier determines the first similarity information between the target questionnaire and each type of questionnaire in a questionnaire type library, and the second similarity information between the target questionnaire and each type of questionnaire in a questionnaire content type library based on a vector matching algorithm and the questionnaire description information, and outputs the questionnaire type information and the questionnaire content type information according to the first similarity information and the second similarity information.

[0012] In one embodiment, the questionnaire description information is a description text or a description file.

[0013] In a second aspect, the present application also provides a questionnaire generating device, comprising:

[0014] A receiving module receives questionnaire description information about a target questionnaire to be generated input by a user, and obtains type information corresponding to the target questionnaire based on the questionnaire description information;

[0015] The first execution module is used to perform information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire;

[0016] The second execution module is used to input the questionnaire description information, the type information and the questionnaire design prompt information into the target large language model to obtain the target questionnaire output by the target large language model.

[0017] In one embodiment, the first execution module is specifically used to: input the questionnaire description information into the agent selector to obtain the questionnaire design prompt information output by the agent selector after performing information expansion processing on the questionnaire description information.

[0018] In one embodiment, the first execution module is specifically used to: input the questionnaire description information into the intelligent agent selector, so that the intelligent agent selector determines the target thinking chain from multiple thinking chains according to the questionnaire description information, and performs information expansion processing on the questionnaire description information according to the target thinking chain to obtain the questionnaire design prompt information.

[0019] In one embodiment, the receiving module is specifically used to: input the questionnaire description information into a questionnaire classifier to obtain the type information output by the questionnaire classifier.

[0020] In one embodiment, the type information includes questionnaire type information and questionnaire content type information, wherein the questionnaire type information is used to indicate the type of the target questionnaire, and the questionnaire content type information is used to indicate the type of questionnaire content involved in the target questionnaire.

[0021] In one embodiment, the receiving module is specifically used to: input the questionnaire description information into the questionnaire classifier, so that the questionnaire classifier determines the first similarity information between the target questionnaire and each type of questionnaire in the questionnaire type library, and the second similarity information between the target questionnaire and each type of questionnaire in the questionnaire content type library based on the vector matching algorithm and the questionnaire description information, and outputs the questionnaire type information and the questionnaire content type information according to the first similarity information and the second similarity information.

[0022] In one embodiment, the questionnaire description information is a description text or a description file.

[0023] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any of the steps described in the first aspect is implemented.

[0024] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the computer program implements any of the steps described in the first aspect.

[0025] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements any of the steps described in the first aspect.

[0026] The above-mentioned questionnaire generation method, device, computer equipment, storage medium and computer program product receive the questionnaire description information of the target questionnaire to be generated input by the user, and obtain the type information corresponding to the target questionnaire based on the questionnaire description information; perform information expansion processing on the questionnaire description information to obtain the questionnaire design prompt information corresponding to the target questionnaire; input the questionnaire description information, the type information and the questionnaire design prompt information into the target large language model to obtain the target questionnaire output by the target large language model. The questionnaire generation method provided in the present application determines the type information of the target questionnaire according to the questionnaire description information input by the user, and determines the questionnaire design prompt information according to the questionnaire description information, and finally inputs the questionnaire description information, the type information and the questionnaire design prompt information into the target large language model to obtain the target questionnaire. The questionnaire generation method provided in the present application can not only generate the corresponding questionnaire according to the user's needs, but also solve the problem that the questions of the generated questionnaire are too fixed due to the template-based questionnaire generation method in the prior art. The questionnaire generation method provided in the present application can effectively improve the flexibility of questionnaire generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 A flowchart of a questionnaire generation method in one embodiment;

[0029] Figure 2 is a flowchart of a questionnaire generation method in another embodiment;

[0030] Figure 3 is a structural block diagram of a questionnaire generating device in one embodiment;

[0031] Figure 4 is an internal structure diagram of a computer device in one embodiment;

[0032] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0034] Questionnaires are a tool used to collect data in social research. Researchers can use questionnaires to accurately and specifically measure the process of social activities, and apply sociological statistical methods to conduct quantitative description and analysis.

[0035] In the prior art, a template is usually used to generate the required questionnaire. However, this questionnaire generation method makes the flexibility of questionnaire generation poor.

[0036] In view of this, the present application provides a questionnaire generation method, which can effectively improve the flexibility of questionnaire generation.

[0037] The questionnaire generation method provided in the embodiment of the present application may be executed by a computer device, which may be a server or a terminal.

[0038] In an exemplary embodiment, Figure 1 As shown, a questionnaire generation method is provided, the method comprising the following steps:

[0039] Step 101: Receive questionnaire description information about a target questionnaire to be generated input by a user, and obtain type information corresponding to the target questionnaire based on the questionnaire description information.

[0040] Optionally, the questionnaire description information is used to represent the research topic and research purpose of the questionnaire.

[0041] In one possible implementation, the questionnaire description information may be zero-sample information, that is, the user only inputs the research topic and research purpose, for example, "Research topic: shared bicycles, research purpose: user satisfaction", "Research topic: company Mid-Autumn Festival activities, research purpose: employee satisfaction".

[0042] In another possible implementation, the questionnaire description information can also be a small amount of sample information, that is, the questionnaire description information entered by the user is a text content, for example, "The theme of my survey is to understand the satisfaction with the shared bicycle experience. The purpose of the survey is to understand the user's satisfaction with the overall experience, unlocking process, riding process and vehicle changing process."

[0043] In an optional embodiment of the present application, the questionnaire description information is a description text or a description file.

[0044] In a possible implementation, if the questionnaire description information is a description text, the user can input the description text based on a text box, and the questionnaire description information can be obtained based on the description text.

[0045] In another possible implementation, if the questionnaire description information is a description file, the user can upload the description file, and the questionnaire description information can be obtained based on the description file.

[0046] Optionally, the type information may be used to characterize the type information of the target questionnaire or the type of questionnaire content involved in the target questionnaire.

[0047] In a possible implementation manner, the type information corresponding to the target questionnaire may be determined based on a questionnaire classifier and the questionnaire description information.

[0048] In another possible implementation manner, the type information corresponding to the target questionnaire may also be determined based on a keyword algorithm and the questionnaire description information.

[0049] Step 102: perform information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire.

[0050] Optionally, the information expansion processing refers to further supplementing and expanding the questionnaire description information to obtain more comprehensive, accurate or useful information.

[0051] In one possible implementation, information technology may be used to perform information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire.

[0052] In another possible implementation, the questionnaire description information may be expanded based on data processing technology to obtain questionnaire design prompt information corresponding to the target questionnaire.

[0053] In another possible implementation, the questionnaire description information may be expanded based on the agent selector to obtain questionnaire design prompt information corresponding to the target questionnaire.

[0054] As described above, the questionnaire description information may be zero sample information, or may be a small amount of sample information.

[0055] In one possible implementation, if the questionnaire description information is zero-sample information, for example, the questionnaire description information is "research topic: company Mid-Autumn Festival activities, research purpose: employee satisfaction", then the questionnaire description information is expanded to obtain the questionnaire design prompt information corresponding to the target questionnaire, which can be "atmosphere and interaction during the Mid-Autumn Festival activities", "content and program arrangements of the Mid-Autumn Festival activities", or "food and beverages provided for the Mid-Autumn Festival activities"; if the questionnaire description information is a small amount of sample information, for example, the questionnaire description information is "the theme of my research is to understand the satisfaction with the shared bicycle experience, and the research purpose is to understand users' overall experience and unlocking process. If the questionnaire description information is zero sample information, then when the information expansion processing is performed on the questionnaire description information, the scope of expansion is relatively large; if the questionnaire description information is a small amount of sample information, then when the information expansion processing is performed on the questionnaire description information, the scope of expansion is relatively small, and it needs to be associated with the information in the questionnaire description information.

[0056] Step 103: input the questionnaire description information, the type information and the questionnaire design prompt information into the target large language model to obtain the target questionnaire output by the target large language model.

[0057] Optionally, the target large language model is a large language model pre-trained by technical personnel according to actual needs. The target large language model can be a GPT model, a BERT model, an XLNet model, or a T5 model.

[0058] In one possible implementation, the questionnaire description information, type information, and questionnaire design prompt information can be input into the target large language model to obtain the target questionnaire output by the target large language model. For example, the questionnaire description information is "The theme of my survey is to understand the satisfaction with the shared bicycle experience. The purpose of the survey is to understand the user's satisfaction with the overall experience, unlocking process, riding process, and changing process." Based on the above steps, after determining the type information and questionnaire design prompt information according to the questionnaire description information, all this information is input into the target large language model. The target questionnaire obtained can be "1. What is your satisfaction rating for the overall experience of this bicycle ride? 2. How satisfied are you with the bicycle scanning and unlocking process? ? 3. During the scanning code unlocking process, what is the reason for your dissatisfaction? Not knowing how to scan the code to unlock, being disturbed by ads / pop-ups during the scanning process, slow unlocking speed, unlocking failure, others. 4. How satisfied are you with the bicycle riding process? 5. During the riding process, what is the reason for your dissatisfaction? After unlocking, the vehicle was found to be faulty, the seat height adjustment was inconvenient, the seat was uncomfortable, the riding posture was uncomfortable, riding was laborious, the brakes were not sensitive or too sensitive, others. 6. How satisfied are you with the bicycle locking / returning process? 7. During the locking / returning process, what is the reason for your dissatisfaction? Unable to return the bicycle successfully at the parking spot in one go, the locking and returning methods were complicated, and the return operation process was cumbersome, others. 8. What improvements do you hope to make to shared bicycles in the future? ".

[0059] The above-mentioned questionnaire generation method receives the questionnaire description information about the target questionnaire to be generated input by the user, and obtains the type information corresponding to the target questionnaire based on the questionnaire description information; performs information expansion processing on the questionnaire description information to obtain the questionnaire design prompt information corresponding to the target questionnaire; inputs the questionnaire description information, the type information and the questionnaire design prompt information into the target large language model to obtain the target questionnaire output by the target large language model. The questionnaire generation method provided in the present application determines the type information of the target questionnaire according to the questionnaire description information input by the user, and determines the questionnaire design prompt information according to the questionnaire description information, and finally inputs the questionnaire description information, the type information and the questionnaire design prompt information into the target large language model to obtain the target questionnaire. The questionnaire generation method provided in the present application can not only generate the corresponding questionnaire according to the needs of the user, but also solve the problem that the questions of the generated questionnaire are too fixed due to the template-based questionnaire generation method in the prior art. The questionnaire generation method provided in the present application can effectively improve the flexibility of questionnaire generation.

[0060] In an exemplary embodiment, the questionnaire description information is subjected to information expansion processing to obtain questionnaire design prompt information corresponding to the target questionnaire, including: inputting the questionnaire description information into an intelligent agent selector to obtain the questionnaire design prompt information output by the intelligent agent selector after performing information expansion processing on the questionnaire description information.

[0061] Optionally, the agent selector is also called Agent selector, which refers to a mechanism that can select a suitable agent program or entity from multiple robots or intelligent assistants to handle specific tasks or requests. It can select the best one from the available agents to perform corresponding operations according to different conditions and requirements.

[0062] In an exemplary embodiment, the questionnaire description information is input into the intelligent agent selector to obtain the questionnaire design prompt information output by the intelligent agent selector after performing information expansion processing on the questionnaire description information, including: inputting the questionnaire description information into the intelligent agent selector, so that the intelligent agent selector determines a target thinking chain from multiple thinking chains according to the questionnaire description information, and performs information expansion processing on the questionnaire description information according to the target thinking chain to obtain the questionnaire design prompt information.

[0063] Optionally, the thought chain can be understood as a series of connected and associated information processing processes or algorithm models. The thought chain can be used to simulate human thinking and reasoning processes, and can play a role in organizing, integrating and expanding information.

[0064] In one possible implementation, the multiple thought chains are stored in the Agent knowledge base. The multiple thought chains may include a research expert thought chain, a user research expert thought chain, an operation expert thought chain, and a statistics expert thought chain. The thought chain is equivalent to the agent described above.

[0065] As described above, the agent selector can determine the target thinking chain from multiple thinking chains based on the questionnaire description information.

[0066] In one possible implementation, the agent selector can determine its needs based on the questionnaire description information, and evaluate the performance, reliability, functions and characteristics of multiple thinking chains in the Agent knowledge base based on the needs to determine the target thinking chain from the multiple thinking chains, and output the questionnaire design prompt information after performing information expansion processing on the questionnaire description information based on the target thinking chain.

[0067] The above method inputs the questionnaire description information into the intelligent agent selector, so that the intelligent agent selector determines the target thinking chain from multiple thinking chains according to the questionnaire description information, and performs information expansion processing on the questionnaire description information according to the target thinking chain to obtain the questionnaire design prompt information. The target thinking chain can be determined according to the questionnaire description information to improve the reliability and accuracy of the questionnaire design prompt information, thereby effectively improving the reliability and accuracy of questionnaire generation.

[0068] In an exemplary embodiment, the obtaining of the type information corresponding to the target questionnaire based on the questionnaire description information includes: inputting the questionnaire description information into a questionnaire classifier to obtain the type information output by the questionnaire classifier.

[0069] In an optional embodiment, the type information includes questionnaire type information and questionnaire content type information.

[0070] The questionnaire type information is used to indicate the type of the target questionnaire, and the questionnaire content type information is used to indicate the type of questionnaire content involved in the target questionnaire.

[0071] In one possible implementation, the questionnaire type information may include a common questionnaire and an examination questionnaire. The common questionnaire may be a satisfaction questionnaire. The questionnaire content type information may include the industry type, user experience type and examination training type. Specifically, it may be determined based on the questionnaire description information.

[0072] In an exemplary embodiment, the questionnaire description information is input into a questionnaire classifier to obtain the type information output by the questionnaire classifier, including: inputting the questionnaire description information into the questionnaire classifier, so that the questionnaire classifier determines, based on a vector matching algorithm and the questionnaire description information, first similarity information between the target questionnaire and each type of questionnaire in a questionnaire type library, and second similarity information between the target questionnaire and each type of questionnaire in a questionnaire content type library, and outputs the questionnaire type information and the questionnaire content type information according to the first similarity information and the second similarity information.

[0073] In one possible implementation, assuming that there are two types of questionnaire templates in the questionnaire type library, namely Type A and Type B, then the similarities between the volume description information and the two types of questionnaires are determined based on the vector matching algorithm. Assuming that the similarity with Type A is greater than the similarity with Type B, then Type A is determined to be the questionnaire type information. Assuming that there are three types of questionnaire content types in the questionnaire content type library, namely Type C, Type D and Type E, then the similarities between the volume description information and the three types of questionnaire content types are determined based on the vector matching algorithm. Assuming that the similarity with Type C is the greatest, then Type C is determined to be the questionnaire content type information.

[0074] In an exemplary embodiment, Figure 2 As shown, another questionnaire generation method is provided, the method comprising the following steps:

[0075] Step 201: receive questionnaire description information about the target questionnaire to be generated input by the user, input the questionnaire description information into the questionnaire classifier, so that the questionnaire classifier determines the first similarity information between the target questionnaire and each type of questionnaire in the questionnaire type library, and the second similarity information between the target questionnaire and each type of questionnaire in the questionnaire content type library based on the vector matching algorithm and the questionnaire description information, and outputs the questionnaire type information and the questionnaire content type information according to the first similarity information and the second similarity information.

[0076] Step 202: input the questionnaire description information into the intelligent agent selector, so that the intelligent agent selector determines the target thinking chain from multiple thinking chains according to the questionnaire description information, and outputs the questionnaire design prompt information after performing information expansion processing on the questionnaire description information according to the target thinking chain.

[0077] Step 203: input the questionnaire description information, the type information and the questionnaire design prompt information into the target large language model to obtain the target questionnaire output by the target large language model.

[0078] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0079] Based on the same inventive concept, the embodiment of the present application also provides a questionnaire generation device for implementing the questionnaire generation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more questionnaire generation device embodiments provided below can refer to the limitations on the questionnaire generation method above, and will not be repeated here.

[0080] In an exemplary embodiment, Figure 3 As shown, a questionnaire generating device 300 is provided, comprising: a receiving module 301, a first executing module 302 and a second executing module 303, wherein:

[0081] The receiving module 301 receives the questionnaire description information about the target questionnaire to be generated input by the user, and obtains the type information corresponding to the target questionnaire based on the questionnaire description information;

[0082] The first execution module 302 is used to perform information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire;

[0083] The second execution module 303 is used to input the questionnaire description information, the type information and the questionnaire design prompt information into the target large language model to obtain the target questionnaire output by the target large language model.

[0084] In one embodiment, the first execution module 302 is specifically used to: input the questionnaire description information into the agent selector to obtain the questionnaire design prompt information output by the agent selector after performing information expansion processing on the questionnaire description information.

[0085] In one embodiment, the first execution module 302 is specifically used to: input the questionnaire description information into the agent selector, so that the agent selector determines the target thinking chain from multiple thinking chains according to the questionnaire description information, and performs information expansion processing on the questionnaire description information according to the target thinking chain to obtain the questionnaire design prompt information.

[0086] In one embodiment, the receiving module 301 is specifically used to: input the questionnaire description information into a questionnaire classifier to obtain the type information output by the questionnaire classifier.

[0087] In one embodiment, the type information includes questionnaire type information and questionnaire content type information, wherein the questionnaire type information is used to indicate the type of the target questionnaire, and the questionnaire content type information is used to indicate the type of questionnaire content involved in the target questionnaire.

[0088] In one embodiment, the receiving module 301 is specifically used to: input the questionnaire description information into the questionnaire classifier, so that the questionnaire classifier determines the first similarity information between the target questionnaire and each type of questionnaire in the questionnaire type library, and the second similarity information between the target questionnaire and each type of questionnaire in the questionnaire content type library based on the vector matching algorithm and the questionnaire description information, and outputs the questionnaire type information and the questionnaire content type information according to the first similarity information and the second similarity information.

[0089] In one embodiment, the questionnaire description information is a description text or a description file.

[0090] Each module in the questionnaire generation device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0091] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a questionnaire generation method is implemented.

[0092] 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. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a questionnaire generation method is implemented.

[0093] Those skilled in the art will understand that Figure 4 and Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0094] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0095] Receive questionnaire description information about a target questionnaire to be generated input by a user, and obtain type information corresponding to the target questionnaire based on the questionnaire description information; perform information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire; input the questionnaire description information, the type information and the questionnaire design prompt information into a target large language model to obtain the target questionnaire output by the target large language model.

[0096] In one embodiment, the questionnaire description information is subjected to information expansion processing to obtain questionnaire design prompt information corresponding to the target questionnaire. When the processor executes the computer program, the following steps are also implemented: the questionnaire description information is input into the intelligent agent selector to obtain the questionnaire design prompt information output by the intelligent agent selector after the questionnaire description information is subjected to information expansion processing.

[0097] In one embodiment, the questionnaire description information is input into the intelligent agent selector to obtain the questionnaire design prompt information output by the intelligent agent selector after performing information expansion processing on the questionnaire description information. When the processor executes the computer program, the following steps are also implemented: the questionnaire description information is input into the intelligent agent selector, so that the intelligent agent selector determines the target thinking chain from multiple thinking chains according to the questionnaire description information, and performs information expansion processing on the questionnaire description information according to the target thinking chain to obtain the questionnaire design prompt information.

[0098] In one embodiment, the type information corresponding to the target questionnaire is obtained based on the questionnaire description information, and the processor also implements the following steps when executing the computer program: inputting the questionnaire description information into a questionnaire classifier to obtain the type information output by the questionnaire classifier.

[0099] In one embodiment, the type information includes questionnaire type information and questionnaire content type information, wherein the questionnaire type information is used to indicate the type of the target questionnaire, and the questionnaire content type information is used to indicate the type of questionnaire content involved in the target questionnaire.

[0100] In one embodiment, the questionnaire description information is input into a questionnaire classifier to obtain the type information output by the questionnaire classifier. When the processor executes the computer program, the following steps are also implemented: the questionnaire description information is input into the questionnaire classifier, so that the questionnaire classifier determines the first similarity information between the target questionnaire and each type of questionnaire in the questionnaire type library, and the second similarity information between the target questionnaire and each type of questionnaire in the questionnaire content type library based on a vector matching algorithm and the questionnaire description information, and outputs the questionnaire type information and the questionnaire content type information according to the first similarity information and the second similarity information.

[0101] In one embodiment, the questionnaire description information is a description text or a description file.

[0102] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0103] Receive questionnaire description information about a target questionnaire to be generated input by a user, and obtain type information corresponding to the target questionnaire based on the questionnaire description information; perform information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire; input the questionnaire description information, the type information and the questionnaire design prompt information into a target large language model to obtain the target questionnaire output by the target large language model.

[0104] In one embodiment, the questionnaire description information is subjected to information expansion processing to obtain questionnaire design prompt information corresponding to the target questionnaire. When the computer program is executed by the processor, the following steps are also implemented: the questionnaire description information is input into the intelligent agent selector to obtain the questionnaire design prompt information output by the intelligent agent selector after the questionnaire description information is subjected to information expansion processing.

[0105] In one embodiment, the questionnaire description information is input into the intelligent agent selector to obtain the questionnaire design prompt information output by the intelligent agent selector after performing information expansion processing on the questionnaire description information. When the computer program is executed by the processor, the following steps are also implemented: the questionnaire description information is input into the intelligent agent selector, so that the intelligent agent selector determines the target thinking chain from multiple thinking chains according to the questionnaire description information, and performs information expansion processing on the questionnaire description information according to the target thinking chain to obtain the questionnaire design prompt information.

[0106] In one embodiment, the type information corresponding to the target questionnaire is obtained based on the questionnaire description information, and the computer program also implements the following steps when executed by the processor: input the questionnaire description information into the questionnaire classifier to obtain the type information output by the questionnaire classifier.

[0107] In one embodiment, the type information includes questionnaire type information and questionnaire content type information, wherein the questionnaire type information is used to indicate the type of the target questionnaire, and the questionnaire content type information is used to indicate the type of questionnaire content involved in the target questionnaire.

[0108] In one embodiment, the questionnaire description information is input into a questionnaire classifier to obtain the type information output by the questionnaire classifier. When the computer program is executed by a processor, the following steps are also implemented: the questionnaire description information is input into the questionnaire classifier, so that the questionnaire classifier determines the first similarity information between the target questionnaire and each type of questionnaire in the questionnaire type library, and the second similarity information between the target questionnaire and each type of questionnaire in the questionnaire content type library based on a vector matching algorithm and the questionnaire description information, and outputs the questionnaire type information and the questionnaire content type information according to the first similarity information and the second similarity information.

[0109] In one embodiment, the questionnaire description information is a description text or a description file.

[0110] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0111] Receive questionnaire description information about a target questionnaire to be generated input by a user, and obtain type information corresponding to the target questionnaire based on the questionnaire description information; perform information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire; input the questionnaire description information, the type information and the questionnaire design prompt information into a target large language model to obtain the target questionnaire output by the target large language model.

[0112] In one embodiment, the questionnaire description information is subjected to information expansion processing to obtain questionnaire design prompt information corresponding to the target questionnaire. When the computer program is executed by the processor, the following steps are also implemented: the questionnaire description information is input into the intelligent agent selector to obtain the questionnaire design prompt information output by the intelligent agent selector after the questionnaire description information is subjected to information expansion processing.

[0113] In one embodiment, the questionnaire description information is input into the intelligent agent selector to obtain the questionnaire design prompt information output by the intelligent agent selector after performing information expansion processing on the questionnaire description information. When the computer program is executed by the processor, the following steps are also implemented: the questionnaire description information is input into the intelligent agent selector, so that the intelligent agent selector determines the target thinking chain from multiple thinking chains according to the questionnaire description information, and performs information expansion processing on the questionnaire description information according to the target thinking chain to obtain the questionnaire design prompt information.

[0114] In one embodiment, the type information corresponding to the target questionnaire is obtained based on the questionnaire description information, and the computer program also implements the following steps when executed by the processor: input the questionnaire description information into the questionnaire classifier to obtain the type information output by the questionnaire classifier.

[0115] In one embodiment, the type information includes questionnaire type information and questionnaire content type information, wherein the questionnaire type information is used to indicate the type of the target questionnaire, and the questionnaire content type information is used to indicate the type of questionnaire content involved in the target questionnaire.

[0116] In one embodiment, the questionnaire description information is input into a questionnaire classifier to obtain the type information output by the questionnaire classifier. When the computer program is executed by a processor, the following steps are also implemented: the questionnaire description information is input into the questionnaire classifier, so that the questionnaire classifier determines the first similarity information between the target questionnaire and each type of questionnaire in the questionnaire type library, and the second similarity information between the target questionnaire and each type of questionnaire in the questionnaire content type library based on a vector matching algorithm and the questionnaire description information, and outputs the questionnaire type information and the questionnaire content type information according to the first similarity information and the second similarity information.

[0117] In one embodiment, the questionnaire description information is a description text or a description file.

[0118] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0119] 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, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, 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, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0120] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0121] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A questionnaire generation method, characterized in that: The method comprises: Receiving questionnaire description information about a target questionnaire to be generated input by a user, and acquiring type information corresponding to the target questionnaire based on the questionnaire description information; Performing information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire; The questionnaire description information, the type information and the questionnaire design prompt information are input into a target large language model to obtain the target questionnaire output by the target large language model.

2. The method according to claim 1, characterized in that The step of performing information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire includes: The questionnaire description information is input into the agent selector to obtain the questionnaire design prompt information output by the agent selector after performing information expansion processing on the questionnaire description information.

3. The method according to claim 2, characterized in that The step of inputting the questionnaire description information into the agent selector to obtain the questionnaire design prompt information output by the agent selector after performing information expansion processing on the questionnaire description information includes: The questionnaire description information is input into the agent selector, so that the agent selector determines the target thinking chain from multiple thinking chains according to the questionnaire description information, and performs information expansion processing on the questionnaire description information according to the target thinking chain to obtain the questionnaire design prompt information.

4. The method according to any one of claims 1 to 3, characterized in that: The acquiring type information corresponding to the target questionnaire based on the questionnaire description information includes: The questionnaire description information is input into a questionnaire classifier to obtain the type information output by the questionnaire classifier.

5. The method according to claim 4, characterized in that The type information includes questionnaire type information and questionnaire content type information, wherein the questionnaire type information is used to indicate the type of the target questionnaire, and the questionnaire content type information is used to indicate the type of questionnaire content involved in the target questionnaire.

6. The method according to claim 5, characterized in that The step of inputting the questionnaire description information into a questionnaire classifier to obtain the type information output by the questionnaire classifier includes: The questionnaire description information is input into the questionnaire classifier, so that the questionnaire classifier determines the first similarity information between the target questionnaire and each type of questionnaire in the questionnaire type library, and the second similarity information between the target questionnaire and each type of questionnaire in the questionnaire content type library based on the vector matching algorithm and the questionnaire description information, and outputs the questionnaire type information and the questionnaire content type information according to the first similarity information and the second similarity information.

7. The method according to any one of claims 1 to 3, characterized in that: The questionnaire description information is a description text or a description file.

8. A questionnaire generating device, characterized in that: The device comprises: A receiving module receives questionnaire description information about a target questionnaire to be generated input by a user, and acquires type information corresponding to the target questionnaire based on the questionnaire description information; A first execution module is used to perform information expansion processing on the questionnaire description information to obtain questionnaire design prompt information corresponding to the target questionnaire; The second execution module is used to input the questionnaire description information, the type information and the questionnaire design prompt information into the target large language model to obtain the target questionnaire output by the target large language model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images