Questionnaire generation method, questionnaire generation device, electronic device, storage medium

Abstract

The embodiment of the application provides a questionnaire generation method, a questionnaire generation device, an electronic equipment and a storage medium, and belongs to the field of AI and financial technology. The method comprises the following steps: obtaining configuration data from a configuration platform, the configuration data comprising question examples, reference answer data and behavior data; obtaining a questionnaire generation request sent by a client, the questionnaire generation request comprising target identification information and role information, the role information being a role of the behavior data; extracting a target question from the question examples according to the role information; extracting target behavior details from the behavior data according to the target identification information; obtaining a target answer from the reference answer data or the target behavior details according to the target question, the target answer being a correct answer and a candidate answer being an incorrect answer; and generating a target questionnaire according to the candidate answer, the target question and the target answer, the target questionnaire being matched with the role information and being matched with the candidate answer as an interference option, so that the questionnaire is more reasonable and matched with the role, and the effect of follow-up or diagnosis of the questionnaire is improved.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and financial technology, and in particular to a questionnaire generation method, a questionnaire generation device, an electronic device, and a storage medium. Background Technology

[0002] In fields such as fintech and healthcare, it's common to conduct user follow-ups through questionnaires, questionnaire revisits, or video revisits. For example, in the insurance sector, video revisits are used, such as AI-powered video tellers verifying user identities during high-risk account renewals. To save manpower, video revisits are used, with the main flow controlled by the questionnaire stream (sending questions to the user and the user's response). Similarly, in digital healthcare, there are intelligent consultations or pre-consultations before formal medical visits. The diagnostic results of these consultations are controlled by the questionnaire stream (sending questions to the person seeking consultation and the person's response). Questionnaires significantly impact the effectiveness of follow-ups and consultations; therefore, developing reasonable and universally applicable questionnaires is a pressing issue. Summary of the Invention

[0003] The main objective of this application is to provide a questionnaire generation method, a questionnaire generation device, an electronic device, and a storage medium, which aim to generate reasonable questionnaires to improve the follow-up effect or the diagnostic effect of the questionnaire.

[0004] To achieve the above objectives, a first aspect of this application proposes a questionnaire generation method, the method comprising:

[0005] The configuration data is obtained from the configuration platform; wherein, the configuration data includes problem examples, reference answer data, and target object behavior data, the behavior data includes behavior roles, and the behavior data is at least one of the following: medical visit data or insurance data;

[0006] Obtain a questionnaire generation request sent by the client; wherein, the questionnaire generation request includes target identification information and role information, and the role information is the role of the behavioral data;

[0007] Extract the target question from the question example based on the role information;

[0008] Target behavior details are extracted from the behavior data based on the target identification information;

[0009] The target answer is obtained from the reference answer data or the target behavior details based on the target question; wherein, the target answer is the correct answer;

[0010] A target questionnaire is generated based on preset candidate answers, the target question, and the target answer; wherein, the candidate answers are incorrect answers.

[0011] In some embodiments, the question example includes candidate questions and a role field for the candidate questions, the role field being used to characterize the category of the candidate questions, and the step of extracting the target question from the question example based on the role information includes:

[0012] The target field is determined from the role field based on the role information;

[0013] The target question is selected from the candidate questions based on the target field.

[0014] In some embodiments, the step of filtering the target question from the candidate questions based on the target field includes:

[0015] The number of questions and the order of roles are determined based on the target fields.

[0016] The target number of questions is selected from the candidate questions according to the order of the roles.

[0017] In some embodiments, the role field includes a non-target field, and the step of filtering the target number of questions from the candidate questions according to the role order includes:

[0018] Using the target field as the first priority, a first number of first questions are selected from the candidate questions;

[0019] The non-target field is used as the second priority to filter out a second number of second questions from the candidate questions; wherein the first number is greater than or equal to the second number, and the first number plus the second number equals the number of questions;

[0020] The first problem and the second problem are combined to obtain the target problem.

[0021] In some embodiments, obtaining the target answer from the reference answer data or the target behavior details based on the target question includes:

[0022] Determine the type of the target problem to obtain the problem type;

[0023] The target question is determined to be either a general question or a specific question based on the question type; wherein the reference answer data is the answer to the general question;

[0024] If the target question is the general question, then the target answer is obtained from the reference answer data based on the target question;

[0025] If the target question is the specific question, then the target answer is extracted from the target behavior details based on the target question.

[0026] In some embodiments, the behavioral data further includes object information, and the method further includes obtaining the candidate answers, specifically including:

[0027] The information type is determined based on the object information;

[0028] The answer generation rules are determined based on the information type.

[0029] Based on the answer generation rules and the object information, generate distracting answer data;

[0030] The candidate answer is extracted from the interference answer data based on the target question.

[0031] In some embodiments, the target questionnaire is a multiple-choice question, and generating the target questionnaire based on preset candidate answers, the target question, and the target answer includes:

[0032] Obtain at least two of the aforementioned candidate answers;

[0033] The target questionnaire is generated by using the target answer and the at least two candidate answers as options for the multiple-choice question, the target question as the stem of the multiple-choice question, and the target answer as the answer to the multiple-choice question.

[0034] To achieve the above objectives, a second aspect of this application provides a questionnaire generation apparatus, the apparatus comprising:

[0035] The configuration data acquisition module is used to acquire configuration data from the configuration platform; wherein, the configuration data includes problem examples, reference answer data, and target object behavior data, the behavior data includes behavior roles, and the behavior data is at least one of the following: medical visit data or insurance data;

[0036] The questionnaire generation request acquisition module is used to acquire questionnaire generation requests sent by the client; wherein, the questionnaire generation request includes target identification information and role information, and the role information is the role of the behavioral data;

[0037] The target question extraction module is used to extract the target question from the question examples based on the role information;

[0038] The target behavior details extraction module is used to extract target behavior details from the behavior data based on the target identification information.

[0039] The target answer acquisition module is used to acquire a target answer from the reference answer data or the target behavior details based on the target question; wherein, the target answer is the correct answer;

[0040] The target questionnaire generation module is used to generate a target questionnaire based on preset candidate answers, the target question, and the target answer; wherein the candidate answers are incorrect answers.

[0041] To achieve the above objectives, a third aspect of the present application provides an electronic device, the electronic device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method described in the first aspect.

[0042] To achieve the above objectives, a fourth aspect of the present application provides a storage medium, which is a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0043] The questionnaire generation method, device, electronic device, and storage medium proposed in this application obtain configuration data from a configuration platform, receive a questionnaire generation request sent by a client, extract a target question from question examples based on role information, extract target behavior details from behavioral data based on target identification information, and then obtain a target answer from reference answer data or target behavior details based on the target question. This generates a target questionnaire based on preset candidate answers, target questions, and target answers. The target questionnaire matches the role information and includes candidate answers as distractors, making it more reasonable and role-matched, thus improving the follow-up or diagnostic effectiveness of the questionnaire. Attached Figure Description

[0044] Figure 1 This is a flowchart of the questionnaire generation method provided in the embodiments of this application;

[0045] Figure 2 This is an application scenario diagram of the questionnaire generation method provided in the embodiments of this application;

[0046] Figure 3 yes Figure 1 The flowchart for step 103 in the text;

[0047] Figure 4 yes Figure 3 The flowchart for step 302 in the document;

[0048] Figure 5 yes Figure 4 The flowchart for step 402 in the document;

[0049] Figure 6 yes Figure 1 The flowchart for step 104 in the document;

[0050] Figure 7 yes Figure 1 The flowchart for step 105 in the document;

[0051] Figure 8 This is another flowchart of the questionnaire generation method provided in the embodiments of this application;

[0052] Figure 9 yes Figure 1 The flowchart for step 106 in the document;

[0053] Figure 10 This is a schematic diagram of the questionnaire generation device provided in the embodiments of this application;

[0054] Figure 11 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0058] First, let's analyze some of the terms used in this application:

[0059] Artificial intelligence (AI) is a new branch of computer science that studies, develops, and applies theories, methods, technologies, and systems to simulate, extend, and expand human intelligence. It aims to understand the essence of intelligence and produce intelligent machines that can react in a way similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thought. Furthermore, AI utilizes digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceiving the environment, acquiring knowledge, and using that knowledge to achieve optimal results.

[0060] Natural Language Processing (NLP): NLP uses computers to process, understand, and utilize human language (such as Chinese and English). NLP is a branch of artificial intelligence and an interdisciplinary field of computer science and linguistics, often referred to as computational linguistics. NLP includes syntactic analysis, semantic analysis, and discourse understanding. It is commonly used in machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, intent recognition, information extraction and filtering, text classification and clustering, sentiment analysis, and opinion mining. It involves data mining, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, and linguistic research related to language computation.

[0061] In fields such as fintech and healthcare, it's common to conduct user follow-ups through questionnaires, questionnaire revisits, or video revisits. For example, in the insurance sector, video revisits are used, such as AI-powered video tellers verifying user identities during high-risk account renewals. To save manpower, video revisits are used, with the main flow controlled by the questionnaire stream (sending questions to the user and the user's response). Similarly, in digital healthcare, there are intelligent consultations or pre-consultations before formal medical visits. The diagnostic results of these consultations are controlled by the questionnaire stream (sending questions to the person seeking consultation and the person's response). Questionnaires significantly impact the effectiveness of follow-ups and consultations; therefore, developing reasonable and universally applicable questionnaires is a pressing issue.

[0062] Based on this, embodiments of this application provide a questionnaire generation method, a questionnaire generation device, an electronic device, and a storage medium, aiming to achieve intelligent generation of reasonable questionnaires to improve the effectiveness of questionnaire questions.

[0063] The questionnaire generation method, questionnaire generation device, electronic device, and storage medium provided in this application are specifically described through the following embodiments. First, the questionnaire generation method in this application embodiment is described.

[0064] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0065] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0066] The questionnaire generation method provided in this application relates to the field of artificial intelligence technology. The questionnaire generation method provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the questionnaire generation method, but is not limited to the above forms.

[0067] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0068] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user audio, personal information, user behavior, historical data, and user attribute information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive user personal information, separate permission or consent from the user is obtained through pop-ups or redirects to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0069] Figure 1 This is an optional flowchart of the questionnaire generation method provided in the embodiments of this application. This method is applied on the server side. Figure 1 The method may include, but is not limited to, steps 101 to 106.

[0070] Step 101: Obtain configuration data from the configuration platform; wherein, the configuration data includes problem examples, reference answer data, and target object behavior data, and the behavior data includes behavior roles, and the behavior data is at least one of the following: medical visit data or insurance data;

[0071] Step 102: Obtain the questionnaire generation request sent by the client; wherein, the questionnaire generation request includes target identification information and role information; wherein, the role information is the role of the behavioral data;

[0072] Step 103: Extract the target question from the question examples based on the role information;

[0073] Step 104: Extract target behavior details from the behavior data based on the target recognition information;

[0074] Step 105: Obtain the target answer from the reference answer data or target behavior details based on the target question; whereby the target answer is the correct answer.

[0075] Step 106: Generate a target questionnaire based on the preset candidate answers, target questions, and target answers; where candidate answers are incorrect answers.

[0076] Steps 101 to 106 as illustrated in this application embodiment involve obtaining configuration data from the configuration platform, obtaining the questionnaire generation request sent by the client, extracting the target question from the question examples based on the role information, extracting the target behavior details from the behavior data based on the target identification information, and then obtaining the target answer from the reference answer data or the target behavior details based on the target question. This generates a target questionnaire based on preset candidate answers, target questions, and target answers. The target questionnaire matches the role information and is equipped with candidate answers as interference options, making it more reasonable and matching the role, thereby improving the follow-up effect or the diagnostic effect of the questionnaire.

[0077] In some embodiments, the server can be an AI video server. In step 101 of an application scenario, the AI ​​video server first initializes, during which it pulls configuration data from the configuration platform to its local cache. Once the configuration data on the configuration platform changes, the configuration platform notifies the AI ​​video server to refresh its local cache. Upon receiving the data refresh notification from the configuration platform, the AI ​​video server refreshes its data, thereby updating the configuration data in its local cache.

[0078] The target question is determined to be either a general question or a specific question based on the answer type; wherein, the reference answer data is the answer to the general question;

[0079] Taking fintech scenarios as an example, the configuration data is used in the insurance field. The target object can be the insured, that is, the policyholder. The behavioral data is the policyholder's insurance data. The configuration data includes questions and examples in the insurance field, reference answer data, and the policyholder's policy data. The behavioral role is the policy role, which can be the policyholder, the insured, the beneficiary, etc.

[0080] Taking digital healthcare scenarios as an example, configuration data is used for intelligent consultation. The target object can be the patient, i.e., the patient. The behavioral data is the patient's consultation data. The configuration data includes question examples, reference answer data, and patient's consultation data in the digital healthcare field. The behavioral role is the consultation role, which can be the patient or the patient's family members.

[0081] In some embodiments, the example question can be an example of a general question or an example of a specific question. A general question is a question that is not related to behavioral data, such as "What is 1+1?". A specific question is a question that is related to behavioral data. For example, in a financial scenario, a specific question could be "What is the policyholder's date of birth?" or "What insurance product has the insured purchased?". In a medical scenario, a specific question could be "What is the name of the patient?"

[0082] The configuration platform pre-configures configuration data, which includes question examples, reference answer data, and behavioral data of the target audience. In one application scenario, the configuration data includes question examples, a unique identifier (ID) for each question example, reference answer data, and behavioral data. The question examples are descriptions of the questionnaire template, including question types marked by a role field. The behavioral data includes role information, which represents associated roles, such as insured individuals, policyholders, or death beneficiaries in the insurance field, or patients in the digital healthcare field.

[0083] In one application scenario, configuration data can support placeholders and dynamically replace variables. For example, the first n digits of the policy number ({placeholder a}) represent the insured amount, and the placeholder can dynamically replace the policy number. The configuration data is configured by a configuration platform, supports hot refresh, and can be edited and applied in real time; it can also be configured with fixed answers. Compared to existing technologies, this approach allows for dynamic replacement of policy numbers using placeholders, and the configuration data supports hot refresh and real-time editing.

[0084] In step 102 of some embodiments, the target object can trigger a questionnaire generation request through the client's APP, and the client sends the questionnaire generation request to the AI ​​video server. For example, in the insurance field, for new insurance policies, in order to confirm that the policyholder understands the insurance contract's coverage and related rights such as the cooling-off period, the insurance company needs to conduct a follow-up visit for life insurance business with a contract term of more than one year. This follow-up visit is a process of reviewing the insurance rights in the insurance contract, which is related to the vital interests of consumers (policyholders). If consumers encounter any content they do not understand about the insurance, they can consult the insurance company in a timely manner. If they find that the purchased insurance is indeed inconsistent with their needs, they can cancel the policy within the cooling-off period. The questionnaire in this application embodiment can be the questionnaire in the above-mentioned insurance follow-up visit.

[0085] The questionnaire generation request carries target identification information and role information. The target identification information corresponds one-to-one with the target pair and is used to uniquely identify the target object. Each target object has only unique target identification information. For example, in a financial scenario, the target identification information is the policy number, and in the medical field, the target identification information is the doctor's number.

[0086] Please see Figure 2 , Figure 2 This is a schematic diagram illustrating an application scenario of the questionnaire generation method provided in this application. In this scenario, the client 201 communicates and transmits data with the server 202 via a network. The client 201 can send a questionnaire generation request to the server 202. The configuration platform 203 communicates and transmits data with the server 202 via a network. The server 202 can obtain configuration data from the configuration platform 203 and store it locally. When the configuration data of the configuration platform 203 changes, the configuration platform 203 will notify the server 202 to refresh its local cache. After receiving the data refresh notification from the configuration platform 203, the server 202 can obtain the latest configuration data from the configuration platform 203 to refresh the data, thereby updating the configuration data in its local cache. In some embodiments, the client 201 can be a portable device, a tablet device, etc., such as a mobile phone or a tablet computer. The server 202 is a server, and the configuration platform 203 can also be a server.

[0087] In one embodiment, the example question includes a candidate question and a role field for the candidate question, the role field being used to characterize the category of the candidate question; see [link to relevant documentation]. Figure 3 In some embodiments, step 103 may include, but is not limited to, steps 301 to 302.

[0088] Step 301: Determine the target field from the role field based on the role information;

[0089] Step 302: Filter the target question from the candidate questions based on the target field.

[0090] In some embodiments, the role field corresponds to the role of the target object, and different role fields correspond to different roles of the target object. For different roles, the questions obtained are different, and the answers are also different. Thus, the questions are classified by role, and the target questions obtained are classified based on roles. It is understood that some questions are suitable for all roles. Therefore, for different roles, there will be some common questions. For example, the general question "What is 1+1 equal to?" described in the above embodiments can be used as questions for different roles. Through step 301, the field of the role corresponding to the target object (i.e., the target field) is determined according to the role information of the target object. Then, through step 302, the target questions suitable for the target object are filtered from the candidate questions based on the target field.

[0091] Please see Figure 4 In some embodiments, step 302 may include, but is not limited to, steps 401 to 402.

[0092] Step 401: Determine the number of questions and the order of roles based on the target field;

[0093] Step 402: Filter the target number of questions from the candidate questions according to the role order.

[0094] In some embodiments, the role field corresponds to the role of the target object, and different role fields correspond to different roles of the target object; for different roles, the questions obtained are different, and the answers are also different. In one application scenario, the number of questions, sum, is determined based on the target field, and the role order is determined. For example, the role order is: first role, second role, third role, first get question 1 of the first role, then get question 2 of the second role, then get question 3 of the third role, then get question 4 of the first role, question 5 of the second role, question 6 of the third role, and so on, specifying to get the sum-th question, which can be from the first role, the second role, or the third role.

[0095] Steps 401 to 402 can be used to filter out the target number of questions. For example, in a financial scenario, the target number of questions for the policyholder is 12, and the target number of questions for the insured is 10.

[0096] Please see Figure 5 In some embodiments, step 402 may include, but is not limited to, steps 501 to 503.

[0097] Step 501: Prioritize the target field and select the first number of first questions from the candidate questions;

[0098] Step 502: Use non-target fields as the second priority to filter out a second number of second questions from the candidate questions; wherein the first number is greater than or equal to the second number, and the first number plus the second number equals the number of questions;

[0099] Step 503: Combine the first problem and the second problem to obtain the target problem.

[0100] In step 501 of some embodiments, the role corresponding to the target field is a first role, and the first role is used as the first priority to filter a first number of first questions from the candidate questions. In step 502 of some embodiments, the role corresponding to the non-target field is a second role, and the second role is used as the second priority to filter a second number of second questions from the candidate questions. If the number of questions, sum, is even, then the first number = the second number = sum / 2. If the number of questions, sum, is odd, then the first number is greater than the second number, and the first number - the second number = 1, and the first number + the second number = sum. In other application scenarios, the first number and the second number can be randomly selected, as long as the first number + the second number = sum.

[0101] In step 503 of some embodiments, the first problem and the second problem are merged and summarized to obtain the target number of problems.

[0102] In step 104 of some embodiments, target behavior details can be extracted from policy data based on target identification information. Taking a financial scenario as an example, the target identification information is the policy number, and the target behavior details are the policy details, which include the policyholder's name, ID number, application date, type of insurance, insured amount, and payment date. Taking a medical scenario as an example, the target identification information is the patient's visit number, and the target behavior details are the visit details, which include the patient's name, ID number, visit date, department, and cost.

[0103] Please see Figure 6 In some embodiments, step 104 may include, but is not limited to, steps 601 to 606.

[0104] Step 601: Extract name information from behavioral data based on target recognition information to obtain the object's name;

[0105] Step 602: Extract identity information from behavioral data based on target recognition information to obtain object identity data;

[0106] Step 603: Extract the date of birth from the behavioral data based on the target recognition information to obtain the object's birthday data;

[0107] Step 604: Extract communication information from the behavioral data based on the target identification information to obtain object communication data; wherein, the object communication data includes communication number and communication address;

[0108] Step 605: Extract behavior from the behavior data based on the target recognition information to obtain behavior information; wherein, behavior information includes behavior time, behavior type, behavior duration, etc.

[0109] Step 606: Merge the data based on the object's name, identity data, birthday data, communication data, and insurance data to obtain the target behavior details.

[0110] In step 601 of some embodiments, the name can be extracted from the behavioral data based on the target identification information to obtain the object's name, such as the name of the insured or the person being insured, or the name of the person seeking medical treatment.

[0111] In step 602 of some embodiments, identity information can be extracted from behavioral data based on target identification information to obtain object identity data, such as the ID card number of the insured or the ID card number of the person seeking medical treatment.

[0112] In step 603 of some embodiments, the date of birth can be extracted from the behavioral data based on the target identification information to obtain the object's birthday data. For example, it can be the date of birth of the insured or the person seeking medical treatment.

[0113] In step 604 of some embodiments, communication information can be extracted from behavioral data based on target identification information to obtain object communication data, such as the birth date of the insured or the insured person, or the birth date of the patient.

[0114] In step 605 of some embodiments, behavioral data can be extracted based on target identification information to obtain behavioral information. For example, insurance purchase behavior can be extracted, and the obtained insurance purchase data includes insurance purchase time, insurance type, insurance amount, payment time, etc. Or medical treatment behavior can be extracted, and the obtained medical treatment data includes medical treatment time, medical treatment department, medical treatment cost, medical treatment time, etc.

[0115] In step 606 of some embodiments, data can be merged based on the object's name, object's identity data, object's birth date data, object's communication data, and behavioral information to obtain target behavioral details. For example, data can be merged based on the policyholder's name, policyholder's ID number, policyholder's date of birth, policyholder's contact number and address, and insurance data to obtain policy details. Or, data can be merged based on the patient's name, patient's ID number, patient's date of birth, patient's contact number and address, and medical data to obtain medical details.

[0116] Through steps 601 to 606, the policy details of the policyholder, the policy details of the insured, or the medical treatment details of the patient are obtained.

[0117] Please see Figure 7 In some embodiments, step 105 may include, but is not limited to, steps 701 to 704.

[0118] Step 701: Determine the type of the target problem to obtain the problem type;

[0119] Step 702: Determine whether the target problem is a general problem or a specific problem based on the problem type; whereby the reference answer data is the answer to the general problem;

[0120] Step 703: If the target question is a general question, then obtain the target answer from the reference answer data based on the target question;

[0121] Step 704: If the target question is a specific question, then extract the target answer from the target behavior details based on the target question.

[0122] In steps 701 to 702 of some embodiments, the type of the target question is determined, resulting in a question type. This question type is used to determine whether the target question is a general question or a specific question. A general question refers to a question unrelated to behavioral data, such as "What is 1+1?". A specific question refers to a question related to behavioral data. For example, in a financial scenario, a specific question could be "What is the policyholder's date of birth?" or "What insurance product did the insured purchase?". In a medical scenario, a specific question could be "What is the patient's name?". The reference answer data is the answer to the general question, for example, the answer to the general question "What is 1+1?" is 2.

[0123] In step 703 of some embodiments, if the target question is determined to be a general question, the target answer is obtained from the reference answer data based on the target question; in the embodiments of this application, the answer to the general question can be a pre-set fixed answer, which can be directly obtained from the reference answer data to obtain the target answer.

[0124] In step 704 of some embodiments, if the target question is determined to be a specific question, the target answer is extracted from the target behavior details based on the target question. In this embodiment of the application, the answer to the specific question needs to be extracted from the target behavior details to obtain the target answer.

[0125] Through steps 701 to 704, different answer acquisition methods can be adopted according to the type of the target question. If the target question is a general question, the target answer is obtained from the reference answer data; or, if the target question is a specific question, the target answer is extracted from the target behavior details.

[0126] Policy data also includes object information; please refer to [link / reference]. Figure 8 In some embodiments, the questionnaire generation method further includes obtaining candidate answers, which may include, but is not limited to, steps 801 to 804:

[0127] Step 801: Determine the information type based on the object information;

[0128] Step 802: Determine the answer generation rules based on the information type;

[0129] Step 803: Generate distractor answer data based on the answer generation rules and object information;

[0130] Step 804: Extract candidate answers from the interference answer data based on the target question.

[0131] In step 801 of some embodiments, the information type is determined based on the object information. In an application scenario, the information type may include, but is not limited to, name, relationship, birthday, mobile phone number, address, last six digits of telephone number, last six digits of ID card, insurance information, medical information, medical expenses, premium amount, payment month, zodiac sign, and last four digits of mobile phone number.

[0132] In step 802 of some embodiments, if the information type is a name, the answer generation rule is: based on the standard answer, using the same surname, randomly select a word from a pre-collected word library to construct the full name. If the information type is a mobile phone number, the answer generation rule is: based on the standard answer, the first three digits are the same, the middle is filled with the following characters: ****, and the last four digits are randomly selected from 1-9999, taking half of each digit. If the information type is a birthday, the answer generation rule is: based on the standard answer, generate random dates from the month preceding and following the birthday. If the information type is a relationship, the answer generation rule is: randomly select other options from a pre-configured set of relationship roles, including: self, spouse, parents, children, others, etc.

[0133] Furthermore, if the information type is a birthday, the dates before or after can be used as candidate answers; if the information type is a zodiac animal, candidate answers can be randomly selected from the twelve zodiac animals. The above answer generation rules are for illustrative purposes only and do not constitute a limitation on answer generation rules. These answer generation rules support multiple rule extensions and can be continuously expanded and improved to accommodate various business needs.

[0134] In step 803 of some embodiments, if the information type is a name and the surname in the object information is "Wang", then the surname "Wang" is taken, and a word "Xiao Er" is randomly selected from the word library, resulting in the candidate answer "Wang Xiao Er". If the information type is a mobile phone number and the first three digits of the reserved mobile phone number in the object information are 171, then four characters "*" are taken from the middle four digits, resulting in the final candidate answer 171****6578. If the information type is a relationship and the relationship in the object information is spouse, then the candidate answer can be "self", "parents", "children", or "other".

[0135] In step 804 of some embodiments, if the target question is the name of the policyholder (and the real name of the policyholder is Wang Laoqi), then according to the above embodiments, the candidate answer is "Wang Xiaoer".

[0136] Through steps 801 to 804, answer generation rules can be determined based on the type of object information, and candidate answers can be generated based on the answer generation rules as interference options.

[0137] Please see Figure 9 In some embodiments, step 106 may include, but is not limited to, steps 901 to 902:

[0138] Step 901: Obtain at least two candidate answers;

[0139] Step 902: Use the target answer and at least two candidate answers as options for the multiple-choice question, use the target question as the stem of the multiple-choice question, and use the target answer as the answer to the multiple-choice question to generate the target questionnaire.

[0140] In some embodiments, the target questionnaire is a multiple-choice question, which can be a single-choice question, a multiple-selection question, or an indeterminate-choice question; at least two candidate answers are obtained as distractors in step 901. In step 902 of an application scenario, the answer options can be set to at least four options, with the target answer being the correct answer and at least three candidate answers as distractors. The target question is used as the stem of the multiple-choice question to generate the target questionnaire.

[0141] In one application scenario, steps 901 and 902 can generate a multiple-choice questionnaire, with at least two candidate answers serving as distractors for the multiple-choice questions.

[0142] The target questionnaire generated in this application supports diverse combinations, takes effect in real time, and can be flexibly applied to various scenarios, such as AI video teller follow-up in fintech and questionnaire generation for intelligent online medical consultations. This application allows configuration of relevant questionnaire templates, storing template questions in a configuration platform. Question examples can include placeholders, such as replacements for similar terms in the digital healthcare field (doctor, nurse, etc.). Role information can be configured with consultation type, consultation platform, disease terminology, etc. The answers required in this application can be dynamically generated or directly entered. Dynamically generated answers, as described in the above embodiments, can be determined by associating role information (question category), question type (general or specific question), etc., ensuring both controllable questionnaire scope and randomness, thereby improving the follow-up or consultation effectiveness of the questionnaire.

[0143] The questionnaire generation method provided in this application obtains configuration data from a configuration platform and a questionnaire generation request sent by a client. It extracts a target question from question examples based on role information and extracts target behavior details from behavioral data based on target identification information. Then, it obtains a target answer from reference answer data or target behavior details based on the target question. The target questionnaire is generated based on preset candidate answers, target questions, and target answers. The target questionnaire matches the role information and is equipped with candidate answers as interference options, making it more reasonable and matching the role, thus improving the follow-up effect or the diagnostic effect of the questionnaire.

[0144] Please see Figure 10 This application also provides a questionnaire generation apparatus that can implement the above-described questionnaire generation method. The apparatus includes:

[0145] The configuration data acquisition module is used to acquire configuration data from the configuration platform. The configuration data includes problem examples, reference answer data, and target object behavior data. The behavior data includes behavior roles and is at least one of the following: medical visit data or insurance data.

[0146] The questionnaire generation request acquisition module is used to acquire questionnaire generation requests sent by the client; the questionnaire generation request includes target identification information and role information, where the role information is the role of the behavioral data.

[0147] The target question extraction module is used to extract the target question from the question examples based on role information.

[0148] The target behavior details extraction module is used to extract target behavior details from behavior data based on target identification information.

[0149] The target answer retrieval module is used to obtain the target answer from the reference answer data or target behavior details based on the target question; whereby the target answer is the correct answer.

[0150] The target questionnaire generation module is used to generate a target questionnaire based on preset candidate answers, target questions, and target answers; among them, candidate answers are incorrect answers.

[0151] In some embodiments, the target problem extraction module can specifically be used to implement:

[0152] Determine the target field from the role field based on the role information;

[0153] Filter the target questions from the candidate questions based on the target field.

[0154] Specifically, the target problem extraction module can be used to implement steps 301 to 302 above, which will not be described in detail here.

[0155] In some embodiments, the target question extraction module is used to implement "filtering target questions from candidate questions based on target fields", specifically including:

[0156] The number of questions and the order of roles are determined based on the target fields.

[0157] The target number of questions is selected from the candidate questions based on the order of roles.

[0158] Specifically, the target problem extraction module can be used to implement steps 401 to 402 above, which will not be described in detail here.

[0159] In some embodiments, the target question extraction module is used to "select a target number of questions from candidate questions according to role order", specifically including:

[0160] Prioritize the target field and select the first number of first questions from the candidate questions;

[0161] Non-target fields are given second priority, and a second number of second questions are selected from the candidate questions; wherein the first number is greater than or equal to the second number, and the first number plus the second number equals the number of questions.

[0162] By merging the first and second problems, we obtain the target problem.

[0163] Specifically, the target problem extraction module can be used to implement steps 501 to 503 above, which will not be described in detail here.

[0164] In some embodiments, the target behavior details extraction module can be specifically used to implement:

[0165] The name information is extracted from the behavioral data based on the target recognition information to obtain the object's name;

[0166] Based on the target recognition information, identity information is extracted from the behavioral data to obtain the object's identity data;

[0167] The birth date is extracted from the behavioral data based on the target recognition information to obtain the object's birthday data;

[0168] Based on the target identification information, communication information is extracted from the behavioral data to obtain the object communication data; the object communication data includes the communication number and communication address.

[0169] Behavior information is obtained by extracting behavior from behavioral data based on target recognition information; behavioral information includes behavior time, behavior type, behavior duration, etc.

[0170] Data is merged based on the target's name, identity data, date of birth data, communication data, and insurance data to obtain details of the target's behavior.

[0171] In some embodiments, the target behavior details extraction module can be used to implement steps 601 to 606 as described above, and will not be repeated here.

[0172] In some embodiments, the target answer acquisition module can be specifically used to implement:

[0173] Determine the type of the target problem to obtain the problem type;

[0174] The target question is determined as either a general question or a specific question based on the question type; the reference answer data is the answer to the general question.

[0175] If the target question is a general question, then obtain the target answer from the reference answer data based on the target question;

[0176] If the target question is a specific question, then the target answer is extracted from the target behavior details based on the target question.

[0177] In some embodiments, the target answer acquisition module can be used to implement steps 701 to 704 above, which will not be described again here.

[0178] In some embodiments, the questionnaire generation device can also be used to achieve:

[0179] Determine the information type based on the object information;

[0180] The answer generation rules are determined based on the type of information.

[0181] Generate distractor answer data based on answer generation rules and object information;

[0182] Extract candidate answers from the distractor answer data based on the target question.

[0183] In some embodiments, the questionnaire generation device can be used to implement steps 801 to 804 as described above, which will not be repeated here.

[0184] In some embodiments, the target questionnaire generation module can be specifically used to implement:

[0185] Get at least two candidate answers;

[0186] The target answer and at least two candidate answers are used as options for multiple-choice questions, the target question is used as the stem of multiple-choice questions, and the answers to the target answer multiple-choice questions are used to generate a target questionnaire.

[0187] In some embodiments, the questionnaire generation device can be used to implement steps 901 to 902 as described above, which will not be repeated here.

[0188] The specific implementation of the questionnaire generation device is basically the same as the specific implementation of the questionnaire generation method described above, and will not be repeated here.

[0189] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the questionnaire generation method described above. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0190] Please see Figure 11 , Figure 11 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0191] The processor 1101 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0192] The memory 1102 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1102 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1102 and is called and executed by the processor 1101 using the questionnaire generation method of the embodiments of this application.

[0193] Input / output interface 1103 is used to implement information input and output;

[0194] The communication interface 1104 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0195] Bus 1105 transmits information between various components of the device (e.g., processor 1101, memory 1102, input / output interface 1103, and communication interface 1104);

[0196] The processor 1101, memory 1102, input / output interface 1103 and communication interface 1104 are connected to each other within the device via bus 1105.

[0197] This application embodiment also provides a storage medium, which is a computer-readable storage medium, storing a computer program that, when executed by a processor, implements the above-described questionnaire generation method.

[0198] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0199] The questionnaire generation method, device, electronic device, and storage medium provided in this application obtain configuration data from a configuration platform and a questionnaire generation request sent by a client. Based on role information, they extract target questions from question examples and target behavior details from behavioral data based on target identification information. Then, they obtain target answers from reference answer data or target behavior details based on the target questions. Based on preset candidate answers, target questions, and target answers, they generate target questionnaires. These target questionnaires are matched with role information and include candidate answers as distractors, making them more reasonable and role-matched, thus improving the follow-up or diagnostic effects of the questionnaires.

[0200] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0201] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0202] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0203] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0204] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0205] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0206] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0207] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0208] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0209] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0210] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A questionnaire generation method, applied on a server side, characterized in that, The method includes: Configuration data is obtained from the configuration platform; wherein, the configuration data includes question examples, reference answer data, and target object behavior data, the behavior data includes behavior roles, and the behavior data is at least one of the following: medical visit data or insurance data; the question examples include candidate questions and role fields of the candidate questions, the role fields are used to characterize the category of the candidate questions, and the role fields include target fields and non-target fields; Obtain a questionnaire generation request sent by the client; wherein, the questionnaire generation request includes target identification information and role information, and the role information is the role of the behavioral data; Extract the target question from the question example based on the role information; Target behavior details are extracted from the behavior data based on the target identification information; The target answer is obtained from the reference answer data or the target behavior details based on the target question; wherein, the target answer is the correct answer; A target questionnaire is generated based on preset candidate answers, the target question, and the target answer; wherein, the candidate answers are incorrect answers. The step of extracting the target question from the question example based on the role information includes: filtering the target question from the candidate questions based on the target field; The step of filtering the target question from the candidate questions based on the target field includes: filtering the target number of questions from the candidate questions according to role order; specifically including: Using the target field as the first priority, a first number of first questions are selected from the candidate questions; The non-target field is used as the second priority to filter out a second number of second questions from the candidate questions; wherein the first number is greater than or equal to the second number, and the first number plus the second number equals the number of questions; The first problem and the second problem are combined to obtain the target problem; The step of obtaining the target answer from the reference answer data or the target behavior details based on the target question includes: Determine the type of the target problem to obtain the problem type; The target question is determined to be either a general question or a specific question based on the question type; wherein the reference answer data is the answer to the general question; If the target question is the general question, then the target answer is obtained from the reference answer data based on the target question; If the target question is the specific question, then the target answer is extracted from the target behavior details based on the target question.

2. The method according to claim 1, characterized in that, The step of extracting the target question from the question example based on the role information also includes: The target field is determined from the role field based on the role information.

3. The method according to claim 2, characterized in that, The step of filtering the target question from the candidate questions based on the target field further includes: The number of questions and the order of roles are determined based on the target field.

4. The method according to claim 3, characterized in that, The behavioral data also includes object information, and the method further includes obtaining the candidate answers, specifically including: The information type is determined based on the object information; The answer generation rules are determined based on the information type. Based on the answer generation rules and the object information, generate distracting answer data; The candidate answer is extracted from the interference answer data based on the target question.

5. The method according to claim 3, characterized in that, The target questionnaire consists of multiple-choice questions. Generating the target questionnaire based on preset candidate answers, the target questions, and the target answers includes: Obtain at least two of the aforementioned candidate answers; The target questionnaire is generated by using the target answer and the at least two candidate answers as options for the multiple-choice question, the target question as the stem of the multiple-choice question, and the target answer as the answer to the multiple-choice question.

6. A questionnaire generation device, applied on a server side, characterized in that, The apparatus is used to implement the method according to any one of claims 1 to 5, the apparatus comprising: The configuration data acquisition module is used to acquire configuration data from the configuration platform; wherein, the configuration data includes problem examples, reference answer data, and target object behavior data, the behavior data includes behavior roles, and the behavior data is at least one of the following: medical visit data or insurance data; The questionnaire generation request acquisition module is used to acquire questionnaire generation requests sent by the client; wherein, the questionnaire generation request includes target identification information and role information, and the role information is the role of the behavioral data; The target question extraction module is used to extract the target question from the question examples based on the role information; The target behavior details extraction module is used to extract target behavior details from the behavior data based on the target identification information. The target answer acquisition module is used to acquire a target answer from the reference answer data or the target behavior details based on the target question; wherein, the target answer is the correct answer; The target questionnaire generation module is used to generate a target questionnaire based on preset candidate answers, the target question, and the target answer; wherein the candidate answers are incorrect answers.

7. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 5.

Images