CN112100461A

CN112100461A - Questionnaire data processing method, device, server and medium based on data analysis

Info

Publication number: CN112100461A
Application number: CN202011249876.1A
Authority: CN
Inventors: 王震; 施伟豪; 罗电花; 李卓文; 罗东; 林勇; 刘丹
Original assignee: Ping An International Smart City Technology Co Ltd
Current assignee: Ping An International Smart City Technology Co Ltd
Priority date: 2020-11-11
Filing date: 2020-11-11
Publication date: 2020-12-18
Anticipated expiration: 2040-11-11
Also published as: CN112100461B

Abstract

The embodiment of the invention discloses a questionnaire data processing method, a device, a server and a medium based on data analysis, wherein the method comprises the following steps: the method includes the steps of obtaining scene information uploaded by a terminal, selecting at least one question from a question database according to the scene information, obtaining an questionnaire constructed based on the at least one question, sending the questionnaire to the terminal, receiving response information which is returned by the terminal and aims at a target question in the questionnaire, verifying the response information based on a preset questionnaire verification mode, uploading data corresponding to the questionnaire to a block chain if the verification is passed, and enabling the block chain to store the data corresponding to the questionnaire.

Description

Questionnaire data processing method, device, server and medium based on data analysis

Technical Field

The invention relates to the technical field of computers, in particular to a questionnaire data processing method, device, server and medium based on data analysis.

Background

The questionnaire refers to a method of creating a detailed and thorough questionnaire and requesting respondents to respond to the questionnaire to collect data. It is a common tool used by people to collect data in social investigation and research activities. By means of the tool, the investigator can accurately and specifically measure the social activity process, and can use the social statistical method to carry out quantity description and analysis to obtain the required investigation data.

At present, in the questionnaire survey process, questionnaire result collection is usually performed on site by adopting a paper form mode, specifically, a management department formulates an inspection standard in advance according to a work target, an inspection form is printed, a worker performing field inspection performs field data collection, after the paper forms are collected, the worker manually counts the inspection result, the rank of an inspected area and the like, and outputs the inspection result capable of supporting the management requirement. The mode of manually printing and manually collecting statistical results of the offline inspection table has low working efficiency, poor data accuracy and large difficulty in summary analysis, and greatly reduces the supporting effect of field inspection work on work propulsion.

Disclosure of Invention

The embodiment of the invention provides a questionnaire data processing method, a device, a server and a medium based on data analysis, which can automatically screen problems and automatically check the problems based on different scenes in the questionnaire research process, and improve the efficiency and intelligence of questionnaire data processing.

In one aspect, an embodiment of the present invention provides a questionnaire data processing method based on data analysis, where the method includes:

the method comprises the steps of obtaining scene information uploaded by a terminal, selecting at least one question from a question database according to the scene information, and obtaining a questionnaire constructed based on the at least one question;

sending the questionnaire to a terminal, and receiving response information for target questions in the questionnaire returned by the terminal, wherein the response information comprises answers and proof materials for the target questions in the questionnaire, and the target questions are any one or more questions in the questionnaire;

verifying the response information based on a preset questionnaire verification mode, wherein the preset questionnaire verification mode comprises at least one of verification based on a preset format, verification based on a certification material and verification based on historical response information aiming at similar questionnaires;

and if the verification is passed, uploading the data corresponding to the questionnaire to a block chain so that the block chain stores the data corresponding to the questionnaire, wherein the data corresponding to the questionnaire comprises at least one of target questions in the questionnaire, the answering information and the signature information of the terminal.

In one aspect, an embodiment of the present invention provides a device for processing questionnaire data based on data analysis, where the device includes:

the acquisition module is used for acquiring scene information uploaded by the terminal;

the selecting module is used for selecting at least one question from a question database according to the scene information to obtain a questionnaire constructed based on the at least one question;

the sending module is used for sending the questionnaire to a terminal;

the receiving module is used for receiving response information which is returned by the terminal and aims at target questions in a questionnaire, the response information comprises answers and proof materials aiming at the target questions in the questionnaire, and the target questions are any one or more questions in the questionnaire;

the verification module is used for verifying the answering information based on a preset questionnaire verification mode, wherein the preset questionnaire verification mode comprises at least one of verification based on a preset format, verification based on a certification material and verification based on historical answering information aiming at similar questionnaires;

and the uploading module is used for uploading the data corresponding to the questionnaire to a block chain if the verification is passed, so that the block chain stores the data corresponding to the questionnaire, and the data corresponding to the questionnaire comprises at least one of target questions in the questionnaire, the answering information and the signature information of the terminal.

In one aspect, an embodiment of the present invention provides a terminal, including a processor, an input interface, an output interface, and a memory, where the processor, the input interface, the output interface, and the memory are connected to each other, where the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the data analysis-based questionnaire data processing method.

In one aspect, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, where the computer program includes program instructions, and the program instructions, when executed by a processor, cause the processor to execute the data analysis-based questionnaire data processing method.

In the embodiment of the invention, the server acquires the scene information uploaded by the terminal, selects at least one question from the question database according to the scene information, obtains the questionnaire constructed based on the at least one question, sends the questionnaire to the terminal, receives response information which is returned by the terminal and aims at a target question in the questionnaire, verifies the response information based on a preset questionnaire verification mode, and uploads the data corresponding to the questionnaire to the block chain if the verification is passed, so that the block chain stores the data corresponding to the questionnaire.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flow chart of a questionnaire data processing method based on data analysis according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of another questionnaire data processing method based on data analysis according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of a questionnaire data processing apparatus based on data analysis according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of a server according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The questionnaire data processing method based on data analysis provided by the embodiment of the invention is realized on a terminal, and the terminal comprises electronic equipment such as a smart phone, a tablet personal computer, a digital audio and video player, an electronic reader, a handheld game machine or vehicle-mounted electronic equipment.

Fig. 1 is a schematic flow chart of a questionnaire data processing method based on data analysis in an embodiment of the present invention, and as shown in fig. 1, the flow of the questionnaire data processing method in the embodiment may include:

s101, the server obtains scene information uploaded by the terminal, at least one question is selected from a question database according to the scene information, and a questionnaire constructed based on the at least one question is obtained.

In the embodiment of the invention, after a user arrives at a place, the user can upload scene information corresponding to a scene of the user to the server through the terminal, and the server can acquire the scene information uploaded by the terminal, wherein the terminal can be a mobile phone, a computer, a tablet personal computer and the like used by the user, and can specifically interact with the server, the server can be specifically a background server of a questionnaire data processing system and is used for generating a questionnaire and checking the questionnaire, the scene information can comprise information used for describing the current scene of the user such as time, geographic position, weather condition and the like, and can specifically be uploaded based on built-in GPS information, uploaded shot images, uploaded text description and the like. After receiving the scene information uploaded by the terminal, the server can select at least one question from the question database according to the scene information to obtain a questionnaire constructed based on the at least one question, wherein the question database stores the at least one question, each question corresponds to the scene information, and the same scene information can correspond to a plurality of different questions. Specifically, each problem can correspond different applicable scenes, for example, the applicable scene that the problem "rubbish classification in water has what" corresponds is that river detects, and the use scene that the problem "whether dry rubbish classification is correct" corresponds is that the garbage bin detects, wherein, the scene also can be day, night, rainy day, and same scene can correspond a plurality of problems, and same problem also can correspond a plurality of scenes. Further, for a plurality of problems corresponding to each scene, each problem may also have a corresponding priority, where the priority may be preset by a developer, or determined based on the frequency of use of the problem, and the higher the frequency of use is, the higher the priority is. Alternatively, the determination is made based on user satisfaction, the higher the priority.

In one implementation mode, after a user arrives at a questionnaire data processing site, a text description corresponding to the current scene information can be uploaded to a server through a terminal, a background server finds out a problem matched with the scene information from a problem database based on the received scene information, and generates a questionnaire based on the matched problem and sends the questionnaire to the terminal. The matched questions can be a preset number of questions selected from the questions corresponding to the scene information, specifically, the questions can be questions with higher priority in the scene, or the matched questions can also be questions randomly selected from the questions corresponding to the scene information, and the user can also upload requirements for the questions, so that the server selects the questions corresponding to the scene information to generate corresponding questionnaires based on the requirements. Each question in the question database can be of different types, such as a choice question, a blank question and the like, and the questions of different types in the questionnaire correspond to different display modes, such as question single-page configuration, display according to a catalog index or a waterfall flow combined page classification mode, so that the questions are closer to the field inspection behavior of the user and convenient for the field data acquisition of the user.

In one implementation, the server may also select a corresponding question from the question database according to an image corresponding to the scene information uploaded by the user to construct a questionnaire, specifically, after the user arrives at the specified location, the user may capture the scene information around the specified location, the terminal uploads the captured image to the server, the server detects each object region in the image by using a pre-constructed detection model, identifies the type of the object in each object region in the image based on the pre-constructed identification model, and selects a corresponding question from the question database based on the identification result to send to the terminal, for example, the questionnaire is used for surveying the garbage classification condition, the image uploaded by the user is an image of the garbage in the garbage can, the garbage can includes a recyclable garbage can and a non-recyclable garbage can, if the server identifies that the recyclable garbage can includes non-recyclable garbage, then, questions can be added to the questionnaire, the reason that the community personnel do not correctly classify the garbage is analyzed, the user answers the questions, and the server can output specific questions aiming at other different recognition results.

In an implementation scenario, the solution is specifically used in a garbage classification detection scenario, a question database may be designed according to garbage classification field inspection requirements, and includes question type settings adapted to various indexes of field inspection, questions stored in the question database may include single choice questions, multiple choice questions, digital blank filling questions, text blank filling questions, self-adding choice questions, self-adding blank filling questions, and the like, each question type may implement intelligent setting of question content and options, flexible configuration of question scores, and may perform association setting between options and answers among different questions, if an answer to a first question is yes, an answer to a second question is no, and if an answer to a first question is no, an answer to a second question is yes, thereby implementing association between the first question and the second question.

S102, the server sends the questionnaire to the terminal and receives response information which is returned by the terminal and aims at the target question in the questionnaire.

In the embodiment of the present invention, the answer information includes answers and certification materials for each question in the questionnaire, specifically, after the server generates the questionnaire, the server may send the questionnaire to the terminal, so that the terminal answers the questions in the questionnaire, for each question in the questionnaire, the user may upload a text answer for the question and a certification material for the text answer through the terminal, the certification material may be, for example, an image, a video, an audio, or the like, and a format of the certification material for each question may be preset by a research and development staff. In the answering process, the server can detect whether the answering mode of the terminal for the target problem meets the preset condition, if not, the server sends guide information to the terminal and instructs the terminal to answer the target problem according to the preset answering mode. In an implementation manner, when a user uses the terminal to start answering, the terminal enters a guidance mode, and receives an instruction continuously sent by the server in the guidance mode, for example, the user is guided to shoot a picture at a specified position, and the shot picture is uploaded as an answer to the question, further, in order to make the picture more accurate, the user can be guided to perform multi-angle shooting, wide-angle shooting, macro-shooting and the like in the guidance mode, or the user can be guided to record, shoot a video and the like in the guidance mode, so that the answer uploaded by the user meets the format requirement of the question, and the user can upload the more accurate answer.

It should be noted that, during the answering process, the user can directly select or fill in the question of the questionnaire, and can upload the relevant certification material through the modes of photos, videos, sound recordings and the like. Specifically, the user can upload different types of answers according to different question types, when answering information is uploaded, the user can encrypt the answering information by using a private key of the user, and the server can decrypt and analyze the answering information by using a public key of the user. Optionally, a corresponding answer mode is set for each question in the questionnaire, and the user can answer according to the corresponding answer mode, for example, the answer mode may be to upload a recording condition in a time period in a preset address, or upload a preset address surrounding environment video and the like, and the user may collect answers according to the answer mode. After the user finishes answering the target questions, the terminal can be used for uploading answering information aiming at the target questions in the questionnaire, the server receives the answering information aiming at the target questions in the questionnaire returned by the terminal, and the target questions can be specifically any one or more questions in the questionnaire.

S103, the server verifies the answering information based on a preset questionnaire verification mode.

In the embodiment of the present invention, the preset questionnaire verification method includes at least one of verification based on a preset format, verification based on a certification material, and verification based on historical answer information for similar questionnaires, and the preset questionnaire verification method may specifically be a preset verification method corresponding to a target question.

In one implementation, the preset questionnaire checking mode includes checking based on a preset format, that is, checking whether the format of the answer information matches the preset format, and if so, determining that the answer information passes the checking, wherein the answer format includes a character font format, a paragraph format, whether the required material is uploaded, and the like. For example, whether the duration of the audio/video file meets the requirement or not is detected for the audio/video file, whether the size of the audio/video file meets the requirement or not is detected, whether the number of images meets the requirement or not is detected for the image file, whether the size of the images meets the requirement or not is detected for the image file, and the like.

In one implementation, the predetermined questionnaire verification manner includes performing verification based on certification material, and the certification material includes at least one of audio material, image material, and video material.

Wherein, the specific way of the server for checking based on the audio material can be that the server processes the audio material to obtain the audio information corresponding to the audio material, if the audio information is matched with the answer of the target question in the answer information, the answer information is determined to pass the checking, the audio information comprises the sound description of the answer of the target question, specifically, the audio information is specifically used for identifying the authenticity of the answer in the answer information, specifically, whether the keyword in the audio information is matched with the answer of the target question can be checked, if the target question is inquiring whether the cell has noise, the audio material is the voice interview material for the personnel in the cell, the server identifies the voice interview material, converts the voice interview material into corresponding characters, checks whether the identified characters are matched with the characters in the answer of the target question to determine whether the answer is correct, if the keyword in the audio information obtained based on the audio material analysis includes "cell, noisy", when the answer to the target question indicates that the cell is not noisy, it is determined that the audio information does not match the answer to the target question. Or, if the audio material is the environmental sound of the cell, the audio information may be a decibel value of the environmental sound, when the decibel value is smaller than a preset distribution value, it is determined that the cell has no noise, and when the decibel value is higher than the preset decibel value, it is determined that the cell has noise, and the answer to the target question is checked. If the answer uploaded to the question "whether the cell has noise" is "cell without noise", and the detected decibel value is 200, which is higher than the preset decibel value, the answer is determined to be wrong.

The specific mode of the server for checking based on the image material can be that the server processes the image material to obtain image information corresponding to the image material, if the image information is matched with an answer of a target question in answer information, the answer information is determined to pass the checking, and the image information comprises objects in the image and the relative relationship between the objects; specifically, the image material may be introduced into the image recognition model to obtain the objects in the image and the relative relationship between the objects, and check whether the identified objects are matched with the objects in the answer to the target question, where if the answer to the target question "whether the cell includes 4 types of trash cans" is "the cell includes 4 types of trash cans", and the image recognition result indicates that the cell includes only two types of trash cans, it is determined that the objects are not matched, or, if the answer to the question "whether the cell trash is correctly classified" is "correctly classified", and the image recognition result indicates that the positional relationship between the dry trash and the wet trash can is that the dry trash is stored in the wet trash can ", it is determined that the dry trash is stored in the wet trash can.

The specific way of the server for checking based on the video material can be that the server extracts an audio part and an image part in the video material, and if the audio information corresponding to the audio part and the image information corresponding to the image part are matched with answers of the target questions in the answering information, the answering information is determined to pass the checking. Specifically, the video material is analyzed to obtain a voice material and an image material, and the questions in the questionnaire are verified based on the voice material and the image material, respectively.

Alternatively, when the certification material includes the above-mentioned 3 kinds of materials, the response information may be verified based on a combination of the above-mentioned three ways.

In one implementation, the preset questionnaire checking mode comprises checking based on historical answering information aiming at similar questionnaires, specifically, the server acquires M pieces of historical questionnaires with the similarity higher than the preset similarity with the questionnaires and the historical answering information corresponding to each piece of historical questionnaire from the block chain, wherein, a plurality of historical questionnaires and answering information of each historical questionnaire are stored in the block chain, M historical questionnaires can be questionnaires under the same scene with the questionnaires, or, the questionnaires with similar questions in different scenes, the specific calculation mode of the similarity between the questionnaires can be the ratio of the number of the same questions to the total number of the questions in the questionnaires, or, the similarity is comprehensively determined by combining the questionnaire scenes and the same number of questions, for example, questionnaires with the same number of questions larger than the preset number in the same questionnaire scene are determined as similar questionnaires.

Further, the server calculates the similarity between each piece of historical response information and the response information to obtain M similarities, determines a similarity characteristic value based on the M similarities, and determines that the response information passes verification if the similarity characteristic value meets a preset condition, wherein the similarity characteristic value comprises at least one of a similarity mean value, a similarity variance and a similarity median of the M similarities. For example, the similarity characteristic value is a similarity average value of M similarities, and if the similarity average value is greater than the preset similarity, it is determined that the similarity characteristic value satisfies the preset condition, and the answer information passes the verification. Or, the similarity characteristic value is a similarity variance of the M similarities, and if the similarity variance is smaller than the preset variance, the similarity characteristic value is determined to meet the preset condition, and the answer information is verified to pass. Or, the similarity characteristic value is a similarity median of the M similarities, and if the similarity median is greater than the preset similarity, the similarity characteristic value is determined to meet the preset condition, and the answer information is verified to pass. The similarity is calculated in a mode that the server extracts a historical keyword set corresponding to the historical answering information and a keyword set corresponding to the answering information, and obtains a first number of the same keywords in the historical keyword set and the total number of the keywords in the keyword set; the server determines a ratio of the first number to the total number as a similarity between the historical response information and the response information. For example, if the keyword set corresponding to the response information is "garbage, correct, and stored", and the keyword set corresponding to the historical response information is "garbage, correct, and stored", the similarity is determined to be 66.7%.

In an implementation scenario, the target question is specifically a question set for a garbage classification scenario, the verification response information may specifically be to verify whether the content of a file uploaded by a user is accurate, and for a problem that the user uploads a text description and an image certification material, the server verifies the text material uploaded by the user based on an identification result obtained after image identification by using an image identification model, for example, if the problem in a questionnaire is that whether garbage is randomly classified in the cell, the text description uploaded by the user is none, but the situation that the recyclable garbage storage barrel contains unrecyclable garbage after the image is identified is found, and it is determined that a text answer uploaded by the user is not matched with the real situation. Or, aiming at the problems of the text materials uploaded by the user and the voice certification materials, the server verifies the text materials uploaded by the user based on the recognition results obtained after the voice recognition is carried out by the voice recognition model, for example, if the satisfaction degree of the cell user in the voice certification materials to the cell environment is unsatisfactory, and if the satisfaction degree of the cell user in the voice certification materials is satisfactory, the text answers uploaded by the user are determined to be not matched with the real situation. Furthermore, the server outputs a confidence coefficient for the whole questionnaire based on the verification result for each question in the questionnaire, the confidence coefficient can be a ratio of the number of questions passing verification in the questionnaire to the total number of questions, and by outputting the confidence coefficient, the questionnaire can be conveniently and manually reviewed by the reviewer.

And S104, if the verification is passed, the server uploads the data corresponding to the questionnaire to the block chain so that the data corresponding to the questionnaire are stored by the block chain.

In the embodiment of the present invention, after the server checks the answer information, the server may upload data corresponding to the questionnaire to the block chain, the uploading process may be to broadcast the data corresponding to the questionnaire in the block chain, each node in the block chain performs consensus check on the data, after the check is passed, the data is packaged into blocks and connected to the block chain, so that the block chain stores the data corresponding to the questionnaire, where the data corresponding to the questionnaire includes at least one of a target question, the answer information, and signature information of the terminal, the signature information of the terminal may be a private key of the terminal, and other nodes in the block chain may refer to or download the data corresponding to the questionnaire through a public key of the terminal, and determine a publisher of the data corresponding to the questionnaire in a public-private key decryption manner, to determine the authenticity thereof, and by storing the data in the blockchain, the corresponding data in the questionnaire can be made unchangeable and traceable.

Fig. 2 is a schematic flow chart of another questionnaire data processing method based on data analysis in the embodiment of the present invention, and as shown in fig. 2, the flow of the questionnaire data processing method in the embodiment may include:

s201, the server obtains scene information uploaded by the terminal, and selects at least one question from the question database according to the scene information to obtain a questionnaire constructed based on the at least one question.

In the embodiment of the invention, at least one question is stored in the question database, each question corresponds to scene information, and the same scene information can correspond to a plurality of different questions.

S202, the server sends a questionnaire to the terminal.

S203, the server detects whether the answering mode of the terminal aiming at the target problem meets the preset condition.

In the embodiment of the invention, after the server sends the questionnaire to the terminal, the answering condition of the user aiming at the questionnaire in the terminal can be monitored in real time, and specifically, whether the answering mode of the terminal aiming at the target question meets the preset condition or not can be detected, wherein the target question is any one or more questions in the questionnaire, the answering mode comprises an answering place, an answering time or an answering format, and the preset condition comprises that the answering place is in the range of the preset place, the answering time is in the range of the preset time and the answering format is in the preset format.

204. If not, the server sends the guiding information to the terminal.

In the embodiment of the invention, if the answering mode of the terminal aiming at the target problem does not meet the preset condition, the server sends the guiding information to the terminal, and the guiding information is used for indicating the terminal to answer the target problem according to the preset answering mode.

For example, when a user starts answering a target question in a questionnaire by using a terminal, and detects that an answering place of the user for the target question is not within a preset place range, the terminal enters a guidance mode, and receives an instruction continuously sent by a server in the guidance mode, for example, the user is guided to reach a designated position to take a picture, and the taken picture is uploaded to the server as answering information of the target question, further, in order to make the picture more accurate, the user can be guided to take multi-angle shooting, wide-angle shooting, macro-distance shooting and the like in the guidance mode, or the user can be guided to record a sound, shoot a video and the like in the guidance mode, so that an answer uploaded by the user meets the format requirement of the question, and the user can also upload more accurate answering information.

S205, the server receives response information which is returned by the terminal and aims at the target question in the questionnaire.

In the embodiment of the present invention, the answering information includes answers and certification material for each question in the questionnaire; specifically, after the server generates the questionnaire, the questionnaire may be sent to the terminal, so that the terminal answers questions in the questionnaire, and for each question in the questionnaire, the user may upload, through the terminal, a text answer for the question and a certification material for the text answer, such as an image, a video, an audio, and the like, and a format of the certification material for each question may be preset by a research and development staff.

S206, the server verifies the answering information based on a preset questionnaire verification mode.

In the embodiment of the present invention, the preset questionnaire verification method includes at least one of verification based on a preset format, verification based on a certification material, and verification based on historical answer information for similar questionnaires.

In one implementation, the preset questionnaire checking mode includes checking based on a preset format, that is, checking whether the format of the response information matches the preset format, and if so, determining that the response information passes the checking.

In one implementation, the preset questionnaire checking mode includes checking based on a certification material, where the certification material includes an audio material, an image material, and a video material, and specifically, the server extracts a voice in the audio material or the video material to obtain a text description in the voice, checks whether the text description matches an answer to a target question in answer information, and if so, identifies objects in the image material and the video material and a relative relationship between the objects, checks whether the identified relative relationship between the objects matches the relative relationship between the objects in the answer to the target question, and if so, determines that the checking is passed.

In one implementation manner, the preset questionnaire checking mode includes checking based on historical answer information for similar questionnaires, specifically, the server acquires M historical questionnaires with similarity higher than preset similarity with the questionnaires and historical answer information corresponding to each historical questionnaire from the block chain, calculates similarity between each piece of historical answer information and the answer information to obtain M similarities, determines a similarity characteristic value based on the M similarities, and determines that the answer information passes checking if the similarity characteristic value meets a preset condition.

In one implementation, the server first checks the response information based on a preset format, if the check is passed, the response information is checked based on the proof material, if the check is passed, the response information is checked based on the historical response information for similar questionnaires, if the check is passed, the response information is determined to have authenticity, and the response information can be further put into a block chain for storage.

And S207, if the verification fails, the server sends a verification problem to the terminal.

In an embodiment of the present invention, a similarity between a verification question and a target question in a questionnaire is higher than a preset similarity, wherein a standard answer of the verification question is associated with a standard answer of the target question, if the verification question can be a similar question to the target question in the questionnaire, that is, the similarity between the verification question and the target question is higher than the preset similarity, the standard answer of the verification question and the standard answer of the target question should be similar answers, or, the verification question can be an opposite question to the target question in the questionnaire, the standard answer of the verification question and the standard answer of the target question should be opposite answers, if the standard answer of the target question is no, the standard answer of the verification question is yes.

S208, the server receives the verification answers uploaded by the terminal aiming at the verification questions and obtains the answers of the target questions in the answering information.

In the embodiment of the invention, the verification answer is an answer which is uploaded by the user through the terminal and aims at the verification question, and the answer of the target question in the answering information is an answer which is uploaded by the terminal and aims at the target question.

S209, the server determines the confidence level of the answering information based on the similarity between the verification answers and the answers of the target questions, and uploads the data corresponding to the questionnaire to the block chain when the confidence level is higher than the preset confidence level.

In the embodiment of the invention, the confidence degree is specifically used for reflecting the credibility of the answering information, and the higher the confidence degree is, the higher the credibility degree of the answering information is.

In one implementation, the verification question and the target question are similar questions, if the verification question is a cell without noise, and if the target question is a cell with silence, the answer to the verification question and the target question should be the same, at this time, the server determines the similarity between the verification answer to the verification question and the answer to the target question as the confidence level of the answering information, the similarity is high, and the confidence level is high, optionally, the verification question and the target question are opposite questions, if the verification question is that whether the garbage in the cell is correctly stored, and the target question is that the cell is randomly lost, the verification answer and the answer to the target question should be opposite answers, and at this time, the reciprocal of the similarity between the verification answer to the verification question and the answer to the target question is determined as the confidence level of the answering information, that the similarity is higher, the confidence level is lower. By sending the verification questions, the fidelity of the terminal to the questionnaire answers can be detected, and the confidence of the questionnaire can be further determined.

When the server determines that the confidence level of the answer information is higher than the preset confidence level, the server may upload data corresponding to a questionnaire to the block chain, where the data corresponding to the questionnaire includes at least one of target questions in the questionnaire, the answer information, and signature information of the terminal.

S210, the server acquires data corresponding to at least one questionnaire aiming at scene information from the block chain.

In the embodiment of the present invention, a questionnaire may be filled in by a plurality of users, and the questionnaire after being filled in is uploaded to a block chain, and a server may obtain at least one piece of data corresponding to the questionnaire of scene information from the block chain, where the data corresponding to the questionnaire includes at least one of target questions, response information, and signature information of a terminal in the questionnaire.

S211, the server preprocesses data corresponding to at least one questionnaire aiming at the scene information to obtain data to be analyzed.

In an embodiment of the present invention, the preprocessing includes at least one of deduplication processing, normalization processing, and screening processing, after the server acquires data corresponding to questionnaires uploaded by different users under the scenario information, the server may perform preprocessing on the data corresponding to the questionnaire for the scenario information to obtain data to be analyzed, specifically, after the server acquires response information of multiple users on the questionnaires for the scenario information, the server may perform deduplication processing, normalization processing, and screening processing on the data corresponding to at least one questionnaire for the scenario information, where the deduplication processing may include removing multiple response information uploaded by the same user, or removing the same answer uploaded by the same user on the same question in the questionnaire, and the normalization processing includes performing normalization processing on a confidence level of each questionnaire, so that the confidence levels of each questionnaire can be compared with each other, and the filtering process includes filtering by time period, filtering by location, filtering by user, and the like.

S212, the server classifies and sorts the data to be analyzed to obtain a questionnaire survey result aiming at the scene information.

In the embodiment of the present invention, after the server acquires the data to be analyzed, the data to be analyzed may be classified and sorted, and specifically, the server may determine a mode of different answers to each question in the data to be analyzed as a target answer to each question, or count proportions of the different answers, compare differences of the data to be analyzed corresponding to different times, and obtain a questionnaire survey result for the scene information.

In the embodiment of the invention, a server acquires scene information uploaded by a terminal, selects at least one question from a question database according to the scene information, obtains a questionnaire constructed based on the at least one question, sends the questionnaire to the terminal, receives response information which is returned by the terminal and aims at a target question in the questionnaire, verifies the response information based on a preset questionnaire verification mode, uploads data corresponding to the questionnaire to a block chain if the verification is passed, so that the block chain stores the data corresponding to the questionnaire, and can obtain a questionnaire survey result aiming at a certain scene by downloading different questionnaires stored in the block chain under the same scene and classifying, sorting and automatically analyzing. By the mode, automatic screening of the questions, automatic examination and verification of the questions and intelligent classification and arrangement of the questionnaires based on different scenes can be achieved in the questionnaire investigation process, and the efficiency and the intelligence of questionnaire data processing are improved.

Based on the above description of the embodiment of the questionnaire data processing method based on data analysis, the embodiment of the invention also discloses a questionnaire data processing device based on data analysis. The questionnaire data processing apparatus based on data analysis may be a computer program (including program code) running in a server, or may be a physical apparatus included in the server. The questionnaire data processing apparatus based on data analysis may perform the methods shown in fig. 1-2. Referring to fig. 3, questionnaire data processing apparatus 30 based on data analysis includes: the device comprises an acquisition module 301, a selection module 302, a sending module 303, a receiving module 304, a verification module 305 and an uploading module 306.

An obtaining module 301, configured to obtain scene information uploaded by a terminal;

a selecting module 302, configured to select at least one question from a question database according to the scenario information, and obtain a questionnaire constructed based on the at least one question;

a sending module 303, configured to send the questionnaire to a terminal;

a receiving module 304, configured to receive response information for target questions in a questionnaire returned by the terminal, where the response information includes answers and proof materials for the target questions in the questionnaire, and the target questions are any one or more questions in the questionnaire;

a checking module 305, configured to check the response information based on a preset questionnaire checking manner, where the preset questionnaire checking manner includes at least one of checking based on a preset format, checking based on a certification material, and checking based on historical response information for similar questionnaires;

an uploading module 306, configured to upload data corresponding to the questionnaire to a block chain if the verification passes, so that the block chain stores the data corresponding to the questionnaire, where the data corresponding to the questionnaire includes at least one of a target question in the questionnaire, the answer information, and the signature information of the terminal.

In an implementation manner, the sending module 303 is specifically configured to:

detecting whether a response mode of the terminal for the target question in the questionnaire meets a preset condition, wherein the response mode comprises a response place, a response time or a response format;

and if not, sending guide information to the terminal, wherein the guide information is used for indicating the terminal to answer the target problem according to a preset answering mode.

In one implementation, the preset questionnaire verification method includes performing verification based on a certification material, where the certification material includes at least one of an audio material, an image material, and a video material, and the verification module 305 is specifically configured to:

processing the audio material to obtain audio information corresponding to the audio material, and if the audio information is matched with an answer of a target question in the answering information, determining that the answering information passes verification, wherein the audio information comprises sound description of the answer of the target question;

or processing the image material to obtain image information corresponding to the image material, and if the image information is matched with the answer of the target question in the answer information, determining that the answer information passes verification, wherein the image information comprises each object in the image and the relative relationship between the objects;

or extracting an audio part and an image part in the video material, and if the audio information corresponding to the audio part and the image information corresponding to the image part are matched with the answer of the target question in the answering information, determining that the answering information passes the verification.

In an implementation manner, the preset questionnaire checking manner includes checking based on historical response information for similar questionnaires, and the checking module 305 is specifically configured to:

acquiring M historical questionnaires with the similarity higher than the preset similarity between the questionnaires and the block chain and historical answering information corresponding to each historical questionnaire, wherein M is a positive integer;

calculating the similarity between each historical answering information and the answering information to obtain M similarities;

determining similarity feature values based on the M similarities, wherein the similarity feature values comprise at least one of a similarity mean, a similarity variance and a similarity median of the M similarities;

and if the similarity characteristic value meets a preset condition, determining that the response information passes verification.

In one implementation, the checking module 305 is specifically configured to:

extracting a history keyword set corresponding to the history answering information and a keyword set corresponding to the answering information;

acquiring a first number of the same keywords in the historical keyword set and the keyword set, and a total number of the keywords in the keyword set;

determining a ratio of the first number to the total number as a similarity between the historical response information and the response information.

In one implementation, the upload module 306 is further configured to:

if the verification is not passed, sending a verification question to the terminal, wherein the similarity between the verification question and the target question in the questionnaire is higher than the preset similarity;

receiving a verification answer uploaded by the terminal aiming at the verification question, and acquiring an answer of the target question in the answering information;

and determining the confidence level of the answering information based on the similarity between the checking answers and the answers of the target questions, and uploading data corresponding to the questionnaire to a block chain when the confidence level is higher than a preset confidence level.

In one implementation, the obtaining module 301 is specifically configured to:

acquiring data corresponding to at least one questionnaire aiming at the scene information from the block chain;

preprocessing the data corresponding to the at least one questionnaire aiming at the scene information to obtain data to be analyzed, wherein the preprocessing comprises at least one of de-emphasis processing, normalization processing and screening processing;

and classifying and sorting the data to be analyzed to obtain a questionnaire survey result aiming at the scene information.

In the embodiment of the present invention, an obtaining module 301 obtains scene information uploaded by a terminal, a selecting module 302 selects at least one question from a question database according to the scene information to obtain an questionnaire constructed based on the at least one question, a sending module 303 sends the questionnaire to the terminal, a receiving module 304 receives answer information for a target question in the questionnaire returned by the terminal, a checking module 305 checks the answer information based on a preset questionnaire checking mode, if the answer information passes the checking, an uploading module 306 uploads data corresponding to the questionnaire to a block chain so that the block chain stores the data corresponding to the questionnaire, and by the above mode, automatic screening of questions based on different scenes in a questionnaire research process and automatic examination and verification of questions can be realized, and efficiency and intelligence of questionnaire data processing are improved.

Fig. 4 is a schematic structural diagram of a server according to an embodiment of the present invention. As shown in fig. 4, the server includes: at least one processor 401, input devices 403, output devices 404, memory 405, at least one communication bus 402. Wherein a communication bus 402 is used to enable connective communication between these components. The memory 405 may be a high-speed RAM memory or a non-volatile memory (e.g., at least one disk memory). The memory 405 may alternatively be at least one storage device located remotely from the aforementioned processor 401. Wherein the processor 401 may be combined with the apparatus described in fig. 3, the memory 405 stores a set of program codes, and the processor 401, the input device 403, and the output device 404 call the program codes stored in the memory 405 to perform the following operations:

a processor 401, configured to obtain scene information uploaded by a terminal;

a processor 401, configured to select at least one question from a question database according to the scenario information, and obtain a questionnaire constructed based on the at least one question;

a processor 401 configured to send the questionnaire to a terminal;

a processor 401, configured to receive response information for a target question in a questionnaire returned by the terminal, where the response information includes an answer and a proof material for the target question in the questionnaire, and the target question is any one or more questions in the questionnaire;

a processor 401, configured to verify the response information based on a preset questionnaire verification manner, where the preset questionnaire verification manner includes at least one of verification based on a preset format, verification based on a certification material, and verification based on historical response information for similar questionnaires;

a processor 401, configured to upload data corresponding to the questionnaire to a block chain if the verification passes, so that the block chain stores the data corresponding to the questionnaire, where the data corresponding to the questionnaire includes at least one of a target question in the questionnaire, the answer information, and signature information of the terminal.

In one implementation, the processor 401 is specifically configured to:

In one implementation, the preset questionnaire verification method includes performing verification based on a certification material, where the certification material includes at least one of an audio material, an image material, and a video material, and the processor 401 is specifically configured to:

In an implementation manner, the processor 401, where the preset questionnaire checking manner includes checking based on historical answer information for similar questionnaires, specifically is configured to:

In one implementation, the processor 401 is specifically configured to:

In the embodiment of the invention, the processor 401 acquires scene information uploaded by the terminal, the processor 401 selects at least one question from the question database according to the scene information to obtain a questionnaire constructed based on the at least one question, the processor 401 sends the questionnaire to the terminal, the processor 401 receives answering information, returned by the terminal, for a target question in the questionnaire, the processor 401 verifies the answering information based on a preset questionnaire verification mode, if the verification is passed, the processor 401 uploads data corresponding to the questionnaire to the block chain so that the block chain stores the data corresponding to the questionnaire, and by the mode, automatic screening of questions based on different scenes in a questionnaire research process and automatic examination and verification of questions can be realized, and the efficiency and the intelligence of processing of questionnaire data are improved.

The module in the embodiment of the present invention may be implemented by a general-purpose Integrated Circuit, such as a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit).

It should be understood that, in the embodiments of the present invention, the Processor 401 may be a Central Processing Unit (CPU), and the Processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The bus 402 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like, and the bus 402 may be divided into a site bus, a data bus, a control bus, and the like, where fig. 4 only shows one thick line for convenience of illustration, but does not show only one bus or one type of bus.

It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The computer-readable storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.

Claims

1. A questionnaire data processing method based on data analysis, the method comprising:

2. The method of claim 1, wherein after sending the questionnaire to a terminal, the method further comprises:

3. The method according to claim 1, wherein the preset questionnaire verification method comprises verification based on a certification material, the certification material comprising at least one of an audio material, an image material and a video material, and the verification of the response information based on the preset questionnaire verification method comprises:

4. The method according to claim 1, wherein the preset questionnaire verification method comprises verification based on historical answering information for similar questionnaires, and the verification of the answering information based on the preset questionnaire verification method comprises:

5. The method of claim 4, wherein said calculating a similarity between said historical response information and said response information comprises:

6. The method according to claim 1, wherein after the response information is verified based on a preset questionnaire verification method, the method further comprises:

7. The method of claim 1, wherein after uploading data corresponding to the questionnaire into a blockchain, the method further comprises:

8. A questionnaire data processing method device based on data analysis is characterized in that the device comprises:

the sending module is used for sending the questionnaire to a terminal;

9. A server comprising a processor, an input interface, an output interface, and a memory, the processor, the input interface, the output interface, and the memory being interconnected, wherein the memory is configured to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of any of claims 1-7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to carry out the method according to any one of claims 1-7.