Questionnaire survey methods, devices, electronic equipment, and storage media based on large models

Abstract

This application discloses a questionnaire survey method, apparatus, electronic device, and storage medium based on a large model, relating to the field of computer technology, particularly to artificial intelligence fields such as large models, natural language processing, and deep learning. The specific implementation scheme is as follows: First response information is obtained for the current question in the target questionnaire; wherein the current question has a related first slot; based on the attribute information of the first slot, information is extracted from the first response information to obtain key information, and the first slot is filled based on the key information; in response to the existence of an unfilled second slot in the first slot, a guiding question is generated based on the attribute information of the second slot and displayed; second response information for the guiding question is obtained; based on the attribute information of the second slot, information is extracted from the second response information to fill the second slot.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to the fields of artificial intelligence such as large models, natural language processing, and deep learning. Specifically, it relates to a questionnaire survey method, device, electronic device, and storage medium based on a large model. Background Technology

[0002] Questionnaire surveys are a common data collection method that gathers opinions by collecting respondents' answers to questions. Questionnaire surveys have wide applications in various fields, including marketing, social science research, and healthcare. Summary of the Invention

[0003] This application provides a questionnaire survey method, apparatus, electronic device, and storage medium based on a large model.

[0004] According to one aspect of this application, a questionnaire survey method based on a large model is provided, comprising:

[0005] Obtain the first response information for the current question in the target questionnaire; wherein, the current question has an associated first slot;

[0006] Based on the attribute information of the first slot, information is extracted from the first response information to obtain key information, and the first slot is filled with the key information.

[0007] In response to the existence of an unfilled second slot in the first slot, a guiding question is generated based on the attribute information of the second slot, and the guiding question is displayed.

[0008] Obtain the second response information for the guidance question;

[0009] Based on the attribute information of the second slot, information is extracted from the second response information to fill the second slot.

[0010] According to another aspect of this application, a questionnaire survey device based on a large model is provided, comprising:

[0011] The first acquisition module is used to acquire the first response information for the current question in the target questionnaire; wherein, the current question has an associated first slot;

[0012] The information extraction and filling module is used to extract key information from the first response information based on the attribute information of the first word slot; and to fill the first word slot based on the key information.

[0013] The question generation module is used to generate a guiding question based on the attribute information of the second slot in response to the existence of an unfilled second slot in the first slot.

[0014] The display module is used to display the aforementioned guidance questions;

[0015] The second acquisition module is used to acquire the second response information of the guidance question;

[0016] The information extraction and filling module is further configured to extract information from the second response information based on the attribute information of the second word slot, so as to fill the second word slot.

[0017] According to another aspect of this application, an electronic device is provided, comprising:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method described in the above embodiments.

[0021] According to another aspect of this application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to perform the method described in the above embodiments.

[0022] According to another aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in the above embodiments.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0024] The accompanying drawings are provided for a better understanding of this solution and do not constitute a limitation of this application. Wherein:

[0025] Figure 1 A flowchart illustrating a questionnaire survey method based on a large model provided in an embodiment of this application;

[0026] Figure 2 A flowchart illustrating a questionnaire survey method based on a large model, provided as another embodiment of this application;

[0027] Figure 3A flowchart illustrating a questionnaire survey method based on a large model, provided as another embodiment of this application;

[0028] Figure 4 A flowchart illustrating a questionnaire survey method based on a large model, provided as another embodiment of this application;

[0029] Figure 5 A flowchart illustrating a questionnaire survey provided in this application embodiment;

[0030] Figure 6 A schematic diagram of the structure of a questionnaire survey device based on a large model provided in an embodiment of this application;

[0031] Figure 7 This is a block diagram of an electronic device used to implement the questionnaire survey method based on a large model according to the embodiments of this application. Detailed Implementation

[0032] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0033] It should be noted that the acquisition, storage, use, and processing of data in this application comply with the relevant provisions of national laws and regulations and do not violate public order and good morals.

[0034] The following description, with reference to the accompanying drawings, describes a questionnaire survey method, apparatus, electronic device, and storage medium based on a large model according to embodiments of this application.

[0035] In some embodiments, a fixed set of questions and options can be provided during a questionnaire survey, from which users select a response. However, this static questionnaire method lacks flexibility.

[0036] Based on this, embodiments of this application provide a questionnaire survey method based on a large model. Figure 1 This is a flowchart illustrating a questionnaire survey method based on a large model, provided as an embodiment of this application.

[0037] The large-model-based questionnaire survey method of this application embodiment can be executed by the large-model-based questionnaire survey device of this application embodiment, which can be configured in an electronic device.

[0038] Among them, electronic devices can be any device with computing capabilities, such as personal computers, mobile terminals, servers, etc. Mobile terminals can be hardware devices with various operating systems, touch screens and / or displays, such as in-vehicle devices, mobile phones, tablets, personal digital assistants, wearable devices, etc.

[0039] like Figure 1 As shown, this questionnaire survey method based on a large model includes:

[0040] Step 101: Obtain the first response information for the current question in the target questionnaire.

[0041] In this application, the target questionnaire can be any questionnaire, and the target questionnaire can include at least one preset question. Slots can be set for each preset question in advance, that is, each preset question can be associated with one or more slots.

[0042] In this application, the current question in the target questionnaire can be displayed to the user, who can then input their response to the current question, i.e., the first response information. This allows the retrieval of the first response information for the current question. The current question has associated slots, i.e., the first slots. Furthermore, the number of first slots can be one or more, without limitation.

[0043] For example, users can input a response to a question via voice or text. If the response is in voice format, it can be converted into text through voice recognition.

[0044] Step 102: Extract information from the first response information based on the attribute information of the first slot to obtain key information, and fill the first slot with the key information.

[0045] The attribute information of the slots may include, but is not limited to, the slot's name, description, answer type, answer value range, and filling requirements. The description information guides the AI ​​(Artificial Intelligence) in its understanding, and the filling requirements indicate whether the slot must be filled.

[0046] For example, the attribute information of a slot is as follows:

[0047] {

[0048] "slot":"Image report uploaded"

[0049] "description": "You need to determine what kind of report is being uploaded. If the uploaded report is an 'Imaging Report' (such as CT scan, ultrasound, etc.), please fill in 'Yes' in the slot; only fill in 'Unwilling to Upload' if the user explicitly states that they cannot provide the report; otherwise, this slot does not need to be filled in."

[0050] "type":"enumeration type",

[0051] "answer_range":"["Yes","Unwilling to upload"]",

[0052] "optional":true

[0053] }

[0054] For example, the attribute information of another slot is as follows:

[0055] {

[0056] "slot":"age",

[0057] "description":"Collects user's age information",

[0058] "type":"Open-ended question and answer type",

[0059] "answer_range":"\"Age, such as 20 years old, 35 years old\"",

[0060] "optional":true

[0061] }

[0062] In the above example, "optional" indicates whether the slot is optional. A value of "true" for "optional" means the slot is not required to be filled, while a value of "false" means the slot is required to be filled. In the example, the "optional" attribute of the slot named "Age" is "true," meaning that the user can choose not to provide age information.

[0063] As one possible implementation, the first reply information can be segmented to obtain each segment contained in the first reply information. The attribute information of the first word slot can be matched with each segment to determine the segment that matches the first word slot from each segment. Based on the segment that matches the first word slot, the key information that matches the first segment can be obtained. Then, the key information can be used to fill the first word slot so that the word slot has slot information.

[0064] Step 103: In response to the existence of an unfilled second slot in the first slot, generate a guiding question based on the attribute information of the second slot and display the guiding question.

[0065] In this application, if there is an unfilled second slot in the first slot, in order to meet the needs of the questionnaire survey, a guiding question can be generated based on the attribute information of the second slot, and the guiding question can be displayed to the user for targeted follow-up questions.

[0066] The second slot can be some or all of the slots in the first slot, and there can be one or more second slots.

[0067] For example, the question is "How long and how frequently do you use this product each day?" The associated slots for this question are "daily usage time" and "daily usage frequency." If the user's response is "I use it for about two hours each day," the key information "two hours" that matches the slot "daily usage time" can be extracted from the question to fill in the slot "daily usage time." However, the slot "daily usage frequency" is not filled in, so a guiding question, "How many times do you use this product each day?" can be generated based on this slot to continue asking the user.

[0068] For example, if the question is "What is your name and how old are you?", the associated slots are "name" and "age". If the user's response is "Could you repeat that?", no key information is extracted from this response; neither "name" nor "age" is filled. Therefore, based on these two slots, the question can be refined to generate a guiding question, such as "I wanted to ask what your name is and how old you are." Thus, new questions can be generated for indirect responses, effectively handling unexpected answers.

[0069] Step 104: Obtain the second response information for the guiding question.

[0070] In this application, the user's response to the guidance question can be collected, that is, the second response information of the guidance question can be obtained.

[0071] Step 105: Extract information from the second response information based on the attribute information of the second slot to fill the second slot.

[0072] In this application, the method for extracting information from the second response information based on the attribute information of the second slot can be referred to the method for extracting information from the first response information based on the attribute information of the first slot, and will not be repeated here.

[0073] In this application, key information extracted from the second response information is used to fill the second slots. If there are still unfilled slots in the second slots, guiding questions can be generated based on these unfilled slots. Key information is then extracted from the responses to these guiding questions to fill the unfilled slots in the second slots, until all the first slots associated with the current question are filled. If all the second slots are filled, it means that all the first slots of the current question are filled. Here, the fact that all the first slots are filled indicates that all the first slots have slot information.

[0074] For example, after the first slot of the current question has been filled, the next question in the target questionnaire can be displayed, and the above method can be used to fill the slots associated with the next question until all slots associated with the questions in the target questionnaire have been filled, and the session ends.

[0075] In this embodiment, information is extracted from the response information of the current question based on the attribute information of the slots associated with the current question in the target questionnaire. The extracted key information is then used to fill the slots associated with the current question. If there are unfilled slots, a guiding question is generated using these unfilled slots. Information is then extracted from the response information of the guiding question based on the attribute information of the unfilled slots to fill them. Therefore, the natural language input by the user can be accurately parsed using the slots associated with the question. If unfilled slots exist, guiding questions are generated, thereby dynamically adjusting the subsequent question-and-answer process. This improves the flexibility of the questionnaire survey and the natural communicative feel of dynamic question-and-answer. Furthermore, generating guiding questions based on unfilled slots allows for targeted follow-up questions, improving questionnaire efficiency.

[0076] Figure 2 This is a flowchart illustrating a questionnaire survey method based on a large model, provided as another embodiment of this application.

[0077] like Figure 2 As shown, this large-model-based questionnaire survey method includes:

[0078] Step 201: Obtain the first response information for the current question in the target questionnaire.

[0079] In this application, step 201 can be implemented in any of the embodiments of this application, so it will not be described in detail here.

[0080] Optionally, the system can first obtain the attribute information of the current question. If the attribute information of the current question includes a skip condition and the skip condition is not met, then the current question is displayed to the user to obtain the user's response information for the current question. If the skip condition is met, the current question can be skipped, and the system can determine whether the next question meets the skip condition based on the attribute information of the next question, thereby determining whether to display the next question.

[0081] For example, the skipping conditions for a certain question are as follows:

[0082]

[0083] The skip condition means that if the slot information for the term "Image Report Uploaded" is "Yes", that is, if an image report has already been uploaded, then this question can be skipped.

[0084] Therefore, by setting skip conditions for questions, the number of interactions can be controlled, duplicate information collection can be avoided, and the efficiency of questionnaire surveys can be improved.

[0085] Step 202: Extract information from the first response information based on the attribute information of the first slot to obtain key information, and fill the first slot with the key information.

[0086] In this application, step 202 can be implemented in any of the embodiments of this application, so it will not be described in detail here.

[0087] For example, the information extraction task prompt template can be filled based on the attribute information of the first slot to obtain the second prompt information. The second prompt information is then input into the large model, which extracts information from the first response information based on the attribute information of the first slot to obtain key information. The extracted key information is then used to fill the first slot.

[0088] The second prompt can be used to prompt the large model to perform information extraction tasks based on the attribute information of the first slot.

[0089] Therefore, the large model uses the attribute information of the slots associated with the current question to extract information from the response information of the current question, which simplifies the task scope of the large model and allows it to focus on recognizing the content of a single slot, thereby improving the stability and response speed of the overall system.

[0090] Since the response information to the current question may contain slot information for slots other than those associated with the current question, for example, it is possible to identify the unfilled slots in the slot set corresponding to the target questionnaire. These unfilled slots may include those in the first slot set. Based on the attribute information of the unfilled slots in the slot set, information is extracted from the first response information to obtain key information. This extracted key information is then used to fill the unfilled slots in the slot set.

[0091] The slot set corresponding to the target questionnaire is the set of slots associated with each question in the target questionnaire; that is, the slot set is the set of slots associated with each question in the target questionnaire.

[0092] Therefore, by utilizing the currently unfilled slots in the target questionnaire to extract information from the responses to the current question, not only can the slots associated with the current question be filled, but also other slots can be filled when the responses contain information about other slots, thus improving the efficiency of the questionnaire survey.

[0093] Step 203: In response to the existence of an unfilled second slot in the first slot, generate a first prompt message based on the attribute information of the second slot, the current question, and the first reply information.

[0094] In this application, if there are unfilled second slots in the first slot, the question generation task prompt template can be filled based on the attribute information of the second slot, the current question, the first response information, etc., to obtain the first prompt information. This first prompt information can be used to prompt the large model to perform the question generation task.

[0095] The first prompt information may include, but is not limited to, the attribute information of the second slot, the current question, the first response information, the question generation task instruction statement, and the model output requirements. The question generation task instruction statement is a statement that instructs the large model to perform a task; for example, the question generation task instruction statement could be "Based on the above content, generate a question for the slot 'daily usage frequency'".

[0096] Step 204: Input the first prompt information into the large model, use the large model to generate a guiding question for the second slot, and display the guiding question.

[0097] In this application, a large model can be used to generate guiding questions for the second slot based on the first cue information. It is understood that the guiding questions are related to the second slot.

[0098] Step 205: Obtain the second response information for the guiding question.

[0099] Step 206: Extract information from the second response information based on the attribute information of the second slot to fill the second slot.

[0100] In this application, steps 205-206 can be implemented in any of the embodiments of this application, so they will not be described in detail here.

[0101] In this embodiment, based on the attribute information of the unfilled slots in the currently associated slots, the current question, and the response information to the current question, a first prompt is constructed. This first prompt is input into a large model, which then generates guiding questions for the unfilled slots. Based on the response information to these guiding questions, the unfilled slots in the currently associated slots are filled. Therefore, by utilizing a large model to generate guiding questions for the unfilled slots, the accuracy of the guiding questions is improved.

[0102] Figure 3 This is a flowchart illustrating a questionnaire survey method based on a large model, provided as another embodiment of this application.

[0103] like Figure 3 As shown, this large-model-based questionnaire survey method includes:

[0104] Step 301: Obtain the first response information for the current question in the target questionnaire.

[0105] Step 302: Extract information from the first response information based on the attribute information of the first slot to obtain key information, and fill the first slot with the key information.

[0106] In this application, steps 301-302 can be implemented in any of the embodiments of this application, so they will not be described in detail here.

[0107] Step 303: In response to the existence of an unfilled second slot in the first slot and the slot information type of the first slot being image type, determine the third slot associated with the second slot.

[0108] In this application, the attribute information of the slot may include the slot information type, such as image type, text type, etc.

[0109] For example, if the slot information of a word slot is of the image type, and the required information is extracted from the image by recognizing the image, then the word slot corresponding to the information to be extracted from the image is the word slot associated with the word slot whose slot information is of the image type.

[0110] For example, if the slot information type of the word slot "lab report" is an image type, the index values ​​of each test indicator can be obtained from the image by recognizing the image of "lab report". Then each test indicator is a slot associated with the word slot "lab report".

[0111] In this application, if there is an unfilled second slot in the first slot, it can be determined whether the attribute information of the second slot includes the slot information type of the second slot. If the attribute information of the second slot includes the slot information type of the second slot, and the slot information type of the second slot is an image type, the third slot associated with the second slot can be determined.

[0112] Step 304: Generate a guiding question based on the attribute information of the third slot and display the guiding question.

[0113] In this application, the task prompt template can be filled with the attribute information of the third slot to obtain the corresponding prompt information. The prompt information is then input into the large model, and the large model is used to generate guiding questions.

[0114] For example, if the slot is "lab report", when a user is unwilling or unable to provide a lab report, a guiding question can be generated based on the slots associated with "lab report", that is, each test indicator, to ask follow-up questions about the value of each test indicator.

[0115] Step 305: Obtain the second response information for the guiding question.

[0116] Step 306: Extract information from the second response information based on the attribute information of the second slot to fill the second slot.

[0117] In this application, steps 305-306 can be implemented in any of the embodiments of this application, so they will not be described in detail here.

[0118] In this embodiment of the application, the attribute information of the second slot includes the slot information type of the second slot. If the slot information type of the second slot is an image type, a guiding question can be generated based on the third slot associated with the second slot, thereby converting the acquisition of the image type slot information into information indirectly obtained through the image by directly querying, which improves the flexibility of data collection.

[0119] Figure 4 This is a flowchart illustrating a questionnaire survey method based on a large model, provided as another embodiment of this application.

[0120] like Figure 4 As shown, this large-model-based questionnaire survey method includes:

[0121] Step 401: Obtain the first response information for the current question in the target questionnaire.

[0122] Step 402: Extract information from the first response information based on the attribute information of the first slot to obtain key information, and fill the first slot with the key information.

[0123] In this application, steps 401-402 can be implemented in any of the embodiments of this application, so they will not be described in detail here.

[0124] Step 403: In response to the existence of an unfilled second slot in the first slot and the requirement that the second slot be filled is mandatory, generate a guiding question based on the attribute information of the second slot and display the guiding question.

[0125] For example, in the slots associated with each question in the questionnaire, some slot information may be mandatory, while others may be optional. Based on this, if there is an unfilled second slot in the first slot, it can be determined whether the attribute information of the second slot includes the requirement to fill it. If the attribute information of the second slot includes the requirement to fill it, and the requirement is mandatory, it indicates that the slot information of the second slot is necessary data. Therefore, guiding questions can be generated based on the attribute information of the second slot.

[0126] Step 404: Obtain the second response information for the guiding question.

[0127] Step 405: Extract information from the second response information based on the attribute information of the second slot to fill the second slot.

[0128] In this application, steps 404-405 can be implemented in any of the embodiments of this application, so they will not be described in detail here.

[0129] In this embodiment, if there is an unfilled second slot in the first slot, it is determined whether the attribute information of the second slot includes a filling requirement. If it does, and the requirement is mandatory, a guiding question is generated based on the attribute information of the second slot. Therefore, generating a guiding question based on the attribute information of the second slot when the slot information is mandatory can improve the efficiency of the questionnaire survey.

[0130] In one embodiment of this application, user responses can also be extracted based on all slots associated with each question in the questionnaire. After the slots are filled with responses to each question in the questionnaire, if there are unfilled slots, guiding questions can be generated based on these unfilled slots for targeted follow-up questions. The following is in conjunction with... Figure 5 To explain, Figure 5This is a flowchart illustrating a questionnaire survey provided in an embodiment of this application.

[0131] like Figure 5 As shown, the process includes:

[0132] Step 501: Initialize the questionnaire.

[0133] In this embodiment, the questionnaire can be initialized, and word slots can be assigned to each question in the questionnaire.

[0134] Step 502: Present the problem to the user.

[0135] Step 503: Receive user response.

[0136] Step 504: Parse the response and fill in the word slots.

[0137] In this embodiment, a large model can be used to parse the responses based on all the slots corresponding to the questionnaire, and the slots can be filled based on the extracted key information.

[0138] Step 505: Have all necessary items been collected?

[0139] The "necessary items" here can be understood as slots that are required to be filled. In this embodiment, it can be determined whether all necessary slots in the questionnaire have been filled.

[0140] Step 506: Generate a new boot question.

[0141] If there are unfilled words, the large model is used to generate new guiding questions based on the unfilled word slots and display them to the user to receive user responses, and then continue to fill the unfilled word slots.

[0142] Step 507: End the session.

[0143] The session ends when all necessary slots in the questionnaire are filled with information.

[0144] The questionnaire survey method based on a large model in this application can bring at least the following four beneficial effects:

[0145] Improve user experience: By allowing users to communicate in a more natural way, the sense of barrier in the traditional questionnaire filling process is reduced;

[0146] Enhanced information gathering capabilities: Effectively break down and extract information from responses containing multiple layers of data to ensure comprehensive and accurate acquisition of the required data;

[0147] Reduced costs and maintenance difficulty: It combines the advantages of static questionnaires (easy to manage) and dynamic Q&A (flexible interaction) while reducing the need to design complex dialogue logic separately for different business scenarios.

[0148] Improved efficiency and reliability: The task scope of large language models is simplified, focusing on performing simple but critical small tasks, namely recognizing information fragments in a specified format, thereby improving the overall system stability and response speed.

[0149] To achieve the above embodiments, this application also proposes a questionnaire survey device based on a large model. Figure 6 This is a schematic diagram of the structure of a questionnaire survey device based on a large model provided in an embodiment of this application.

[0150] like Figure 6 As shown, the large-scale model-based questionnaire survey device 600 includes:

[0151] The first acquisition module 610 is used to acquire the first response information for the current question in the target questionnaire; wherein the current question has an associated first slot.

[0152] The information extraction and filling module 620 is used to extract key information from the first response information based on the attribute information of the first word slot; and to fill the first word slot based on the key information.

[0153] The question generation module 630 is used to generate a guiding question based on the attribute information of the second slot in response to the existence of an unfilled second slot in the first slot.

[0154] Display module 640 is used to display the aforementioned guidance question;

[0155] The second acquisition module 650 is used to acquire the second response information of the guidance question;

[0156] The information extraction and filling module 620 is further configured to extract information from the second response information based on the attribute information of the second word slot, so as to fill the second word slot.

[0157] Optionally, the question generation module 630 is used for:

[0158] Based on the attribute information of the second slot, the current question, and the first response information, a first prompt message is generated; wherein, the first prompt message is used to prompt the large model to perform a question generation task;

[0159] The first prompt information is input into the large model, and the large model is used to generate the guiding question for the second slot.

[0160] Optionally, the attribute information of the second slot includes the slot information type of the second slot, and the question generation module 630 is used to:

[0161] In response to the slot information type being image type, a third slot associated with the second slot is determined;

[0162] The guiding question is generated based on the attribute information of the third slot.

[0163] Optionally, the question generation module 630 is used for:

[0164] In response to the existence of an unfilled second slot in the first slot, determine whether the attribute information of the second slot includes the filling requirement of the second slot;

[0165] In response to the fact that the attribute information of the second slot includes the filling requirement of the second slot and the filling requirement is mandatory, the guiding question is generated based on the attribute information of the second slot.

[0166] Optionally, the information extraction and filling module 620 is used for:

[0167] Based on the attribute information of the first slot, a second prompt message is generated; wherein, the second prompt message is used to prompt the large model to perform the information extraction task;

[0168] The second prompt information is input into the large model, and the large model is used to extract information from the first reply information to obtain the key information.

[0169] Optionally, the information extraction and filling module 620 is used for:

[0170] Identify the unfilled slots in the slot set corresponding to the target questionnaire; wherein, the slot set is the set of slots associated with each question in the target questionnaire, and the unfilled slots in the slot set include the unfilled slots in the first slot set;

[0171] Based on the attribute information of the unfilled slots in the slot set, information is extracted from the first response information to obtain the key information.

[0172] Optionally, the device may further include:

[0173] The third acquisition module is used to acquire the attribute information of the current problem;

[0174] The display module 640 is further configured to display the current problem in response to the current problem's attribute information including a skip condition and the skip condition not being met; and to skip the current problem in response to the skip condition being met, and to determine whether to display the next problem of the current problem based on the attribute information of the next problem of the current problem.

[0175] It should be noted that the explanation of the aforementioned questionnaire survey method embodiment based on large model also applies to the questionnaire survey device based on large model in this embodiment, so it will not be repeated here.

[0176] In this embodiment, information is extracted from the response information of the current question based on the attribute information of the slots associated with the current question in the target questionnaire. The extracted key information is then used to fill the slots associated with the current question. If there are unfilled slots, a guiding question is generated using these unfilled slots. Information is then extracted from the response information of the guiding question based on the attribute information of the unfilled slots to fill them. Therefore, the natural language input by the user can be accurately parsed using the slots associated with the question. If unfilled slots exist, guiding questions are generated, thereby dynamically adjusting the subsequent question-and-answer process. This improves the flexibility of the questionnaire survey and the natural communicative feel of dynamic question-and-answer. Furthermore, generating guiding questions based on unfilled slots allows for targeted follow-up questions, improving questionnaire efficiency.

[0177] According to embodiments of this application, this application also provides an electronic device, a readable storage medium, and a computer program product.

[0178] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of this application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0179] like Figure 7 As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 702 or a computer program loaded from storage unit 708 into RAM (Random Access Memory) 703. RAM 703 can also store various programs and data required for the operation of device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 704. I / O (Input / Output) interface 705 is also connected to bus 704.

[0180] Multiple components in device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of monitors, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0181] The computing unit 701 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as a large-model-based questionnaire survey method. For example, in some embodiments, the large-model-based questionnaire survey method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the large-model-based questionnaire survey method described above can be performed. Alternatively, in other embodiments, the computing unit 701 may be configured, by any other suitable means (e.g., by means of firmware), to perform a questionnaire survey method based on a large model.

[0182] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0183] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0184] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0185] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0186] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0187] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers integrated with blockchain technology.

[0188] According to embodiments of this application, this application also provides a computer program product that, when the instruction processor in the computer program product is executed, performs the questionnaire survey method based on a large model proposed in the above embodiments of this application.

[0189] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0190] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A questionnaire survey method based on a large model, characterized in that, include: Obtain the first response information for the current question in the target questionnaire; wherein, the current question has an associated first slot, and the number of the first slots is multiple; Based on the attribute information of the first slot, information is extracted from the first response information to obtain key information, and the first slot is filled with the key information. In response to the existence of an unfilled second slot in the first slot, a guiding question is generated based on the attribute information of the second slot, and the guiding question is displayed. Obtain the second response information for the guidance question; Based on the attribute information of the second slot, information is extracted from the second response information to fill the second slot; Wherein, in response to the existence of an unfilled second slot in the first slot, a guiding question is generated based on the attribute information of the second slot, including: Based on the attribute information of the second slot, the current question, and the first response information, a first prompt message is generated; wherein, the first prompt message is used to prompt the large model to perform a question generation task, and the first prompt message includes the attribute information of the second slot, the current question, and the first response information; The first prompt information is input into the large model, and the large model is used to generate the guiding question for the second slot.

2. The method as described in claim 1, wherein, The attribute information of the second slot includes the slot information type of the second slot. The step of generating a guiding question based on the attribute information of the second slot includes: In response to the slot information type being image type, a third slot associated with the second slot is determined; The guiding question is generated based on the attribute information of the third slot.

3. The method as described in claim 1, wherein, In response to the existence of an unfilled second slot in the first slot, a guiding question is generated based on the attribute information of the second slot, including: In response to the existence of an unfilled second slot in the first slot, determine whether the attribute information of the second slot includes the filling requirement of the second slot; In response to the fact that the attribute information of the second slot includes the filling requirement of the second slot and the filling requirement is mandatory, the guiding question is generated based on the attribute information of the second slot.

4. The method of claim 1, wherein, The step of extracting key information from the first response information based on the attribute information of the first slot includes: Based on the attribute information of the first slot, a second prompt message is generated; wherein, the second prompt message is used to prompt the large model to perform the information extraction task; The second prompt information is input into the large model, and the large model is used to extract information from the first reply information to obtain the key information.

5. The method of claim 1, wherein, The step of extracting key information from the first response information based on the attribute information of the first slot includes: Identify the unfilled slots in the slot set corresponding to the target questionnaire; wherein, the slot set is the set of slots associated with each question in the target questionnaire, and the unfilled slots in the slot set include the unfilled slots in the first slot set; Based on the attribute information of the unfilled slots in the slot set, information is extracted from the first response information to obtain the key information.

6. The method according to any one of claims 1-5, further comprising: Obtain the attribute information of the current problem; If the attribute information of the current problem includes a skip condition and the skip condition is not met, the current problem is displayed. In response to the fulfillment of the skip condition, the current question is skipped, and the next question is determined based on the attribute information of the next question for the current question.

7. A questionnaire survey device based on a large model, characterized in that, include: The first acquisition module is used to acquire the first response information for the current question in the target questionnaire; wherein, the current question has associated first slots, and the number of first slots is multiple; The information extraction and filling module is used to extract key information from the first response information based on the attribute information of the first word slot; and to fill the first word slot based on the key information. The question generation module is used to generate a guiding question based on the attribute information of the second slot in response to the existence of an unfilled second slot in the first slot. The display module is used to display the aforementioned guidance questions; The second acquisition module is used to acquire the second response information of the guidance question; The information extraction and filling module is further configured to extract information from the second response information based on the attribute information of the second slot, so as to fill the second slot; The question generation module is used for: Based on the attribute information of the second slot, the current question, and the first response information, a first prompt message is generated; wherein, the first prompt message is used to prompt the large model to perform a question generation task, and the first prompt message includes the attribute information of the second slot, the current question, and the first response information; The first prompt information is input into the large model, and the large model is used to generate the guiding question for the second slot.

8. The apparatus of claim 7, wherein, The attribute information of the second slot includes the slot information type of the second slot. The question generation module is used for: In response to the slot information type being image type, a third slot associated with the second slot is determined; The guiding question is generated based on the attribute information of the third slot.

9. The apparatus of claim 7, wherein, The question generation module is used for: In response to the existence of an unfilled second slot in the first slot, determine whether the attribute information of the second slot includes the filling requirement of the second slot; In response to the fact that the attribute information of the second slot includes the filling requirement of the second slot and the filling requirement is mandatory, the guiding question is generated based on the attribute information of the second slot.

10. The apparatus of claim 7, wherein, The information extraction and filling module is used for: Based on the attribute information of the first slot, a second prompt message is generated; wherein, the second prompt message is used to prompt the large model to perform the information extraction task; The second prompt information is input into the large model, and the large model is used to extract information from the first reply information to obtain the key information.

11. The apparatus of claim 7, wherein, The information extraction and filling module is used for: Identify the unfilled slots in the slot set corresponding to the target questionnaire; wherein, the slot set is the set of slots associated with each question in the target questionnaire, and the unfilled slots in the slot set include the unfilled slots in the first slot set; Based on the attribute information of the unfilled slots in the slot set, information is extracted from the first response information to obtain the key information.

12. The apparatus of any one of claims 7-11, further comprising: The third acquisition module is used to acquire the attribute information of the current problem; The display module is further configured to display the current question in response to the current question's attribute information including a skip condition and the skip condition not being met; and to skip the current question in response to the skip condition being met, and to determine whether to display the next question of the current question based on the attribute information of the next question of the current question.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

15. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-6.

Images