CN114722266A

CN114722266A - Questionnaire pushing method and device, electronic equipment and readable storage medium

Info

Publication number: CN114722266A
Application number: CN202110001431.XA
Authority: CN
Inventors: 马燕; 黄志勇
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Communications Ltd Research Institute
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Communications Ltd Research Institute
Priority date: 2021-01-04
Filing date: 2021-01-04
Publication date: 2022-07-08

Abstract

The invention provides a questionnaire pushing method, a questionnaire pushing device, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring first question bank data of a user to be pushed, wherein the first question bank data comprises a plurality of question questions and historical answer information of the question questions, and a subject label of each question in the question questions is matched with a questionnaire subject; determining a recommended value of each question in the plurality of question questions aiming at the user to be pushed based on the historical answer information of the plurality of question questions; acquiring data of candidate problem topics in the first question bank data to generate second question bank data of the user to be pushed, wherein the candidate problem topics are problem topics of which recommended values for the user to be pushed are larger than a first threshold value, and the second question bank data comprise the candidate problem topics; and carrying out questionnaire pushing on the user to be pushed based on the second question bank data. The embodiment of the invention can improve the effect of pushing the questionnaire.

Description

Questionnaire pushing method and device, electronic equipment and readable storage medium

Technical Field

The embodiment of the invention relates to the technical field of data services, in particular to a questionnaire pushing method and device, electronic equipment and a readable storage medium.

Background

With the wide popularization of the internet, online questionnaire survey has become a main mode for subjective data acquisition of users in the technical field of data services. The online questionnaire survey is widely applied, and industries such as aviation, e-commerce, retail, communication, finance and internet can perform user satisfaction monitoring and product demand collection in the mode at present.

In the related art, the on-line questionnaire survey system generally uniformly pushes the whole set of questionnaires to all users, some questions in the pushed questionnaires may not be suitable for the users to answer, and the questionnaire pushing effect is poor.

Disclosure of Invention

The embodiment of the invention provides a questionnaire pushing method and device, electronic equipment and a readable storage medium, and aims to solve the problem that the questionnaire pushing effect is poor.

In order to solve the problems, the invention is realized as follows:

in a first aspect, an embodiment of the present invention provides a questionnaire pushing method, where the method includes:

acquiring first question bank data of a user to be pushed, wherein the first question bank data comprises a plurality of question questions and historical answer information of the question questions, and a subject label of each question in the question questions is matched with a questionnaire subject;

determining a recommended value of each question in the plurality of question questions aiming at the user to be pushed based on the historical answer information of the plurality of question questions;

acquiring data of candidate problem topics in the first question bank data to generate second question bank data of the user to be pushed, wherein the candidate problem topics are problem topics of which recommended values for the user to be pushed are larger than a first threshold value, and the second question bank data comprise the candidate problem topics;

and carrying out questionnaire pushing on the user to be pushed based on the second question bank data.

In the above scheme, the plurality of question questions include a first question, the historical answer information of the first question includes a historical answer user tag of the first question, and the first question is any question in the plurality of question questions;

the step of determining a recommended value of each question in the plurality of question questions for the user to be pushed based on the historical answer information of the plurality of question questions comprises:

acquiring the answer states of the first user corresponding to the historical answer user labels to the plurality of question questions from the historical answer information of the plurality of question questions;

determining the similarity between the user to be pushed and the first user;

and determining a recommended value of the first question for the user to be pushed based on the similarity and the answer states of the first user to the plurality of question questions.

In the foregoing solution, the second question bank data further includes question sequence numbers of the candidate question questions, the question sequence numbers are generated in descending order of recommended values of the candidate question questions for the user to be pushed, and the step of pushing a questionnaire to the user to be pushed based on the second question bank data includes:

based on the problem sequence numbers of the candidate problem questions, carrying out problem pushing to the user to be pushed one by one;

and under the condition that the number of the pushed questions is equal to a target number, performing termination judgment on the question pushing event to terminate the question pushing on the user to be pushed, wherein the target number is the number of the questionnaire answers of a second user aiming at the questionnaire theme, and the similarity between the second user and the user to be pushed is greater than a second threshold value.

In the foregoing solution, the second question bank data further includes question types of the candidate question questions, and the step of determining whether to terminate the question pushing event when the number of pushed questions is equal to the target number includes:

terminating the problem pushing to the user to be pushed under the condition that the pushed problem number is equal to the target number and the problem type of the second problem is a non-skip type;

terminating the problem pushing to the user to be pushed under the conditions that the number of pushed problems is equal to the target number, the problem type of a second problem question is a skip type and a problem pushing event meets a pushing termination condition, wherein the pushing termination condition is the completion of the pushing of candidate problem questions matched with answer information of the second problem question in the second question bank data;

and the second problem topic is the problem topic of which the push sequence number corresponds to the target number.

In the foregoing solution, the second question bank data further includes question types of the candidate question questions, and before the step of determining termination of the question pushing event when the number of pushed questions is equal to the target number, the method further includes:

under the condition that the problem type of a first candidate problem currently pushed is a skip type, acquiring answer information of the first candidate problem;

determining the number of second candidate question questions matched with answer information of the first candidate question questions in target question bank data, wherein the target question bank data comprises the candidate question questions except the pushed candidate question questions in the second question bank data;

and updating the question sequence numbers of the candidate question questions except the second candidate question questions in the target question bank data based on the quantity of the second candidate question questions.

In the foregoing solution, before the step of pushing the questionnaire to the user to be pushed based on the second question bank data, the method further includes:

under the condition that the current time interval is the historical answer time interval of the user to be pushed, target data of the user to be pushed are obtained, wherein the target data comprise terminal state data and/or terminal use behavior data;

predicting whether the current time interval is the optimal answer time interval of the user to be pushed or not based on the target data;

the step of pushing questionnaires to the user to be pushed based on the second question bank data comprises the following steps:

and when the current time interval is the optimal answer time interval of the user to be pushed, carrying out questionnaire pushing on the user to be pushed based on the second question bank data.

In a second aspect, an embodiment of the present invention further provides a questionnaire pushing apparatus, including:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring first question bank data of a user to be pushed, the first question bank data comprises a plurality of question questions and historical answer information of the question questions, and a topic tag of each question in the question questions is matched with a questionnaire topic;

the first determining module is used for determining a recommended value of each question in the plurality of question questions aiming at the user to be pushed based on the historical answer information of the plurality of question questions;

a second obtaining module, configured to obtain data of candidate problem topics in the first question bank data to generate second question bank data of the user to be pushed, where the candidate problem topics are problem topics, of the multiple problem topics, for which a recommended value of the user to be pushed is greater than a first threshold, and the second question bank data includes the candidate problem topics;

and the questionnaire pushing module is used for pushing questionnaires to the user to be pushed based on the second question bank data.

the first determining module includes:

the acquisition unit is used for acquiring the answer states of the plurality of question questions by a first user corresponding to the historical answer user tags from the historical answer information of the plurality of question questions;

the first determining unit is used for determining the similarity between the user to be pushed and the first user;

and the second determining unit is used for determining the recommended value of the first question to the user to be pushed based on the similarity and the answer states of the first user to the plurality of question questions.

In the foregoing solution, the second question bank data further includes question sequence numbers of the candidate question questions, the question sequence numbers are generated from large to small based on the candidate question questions in order of recommendation values of the user to be pushed, and the questionnaire pushing module includes:

the problem pushing unit is used for pushing the problems to the user to be pushed one by one based on the problem sequence numbers of the candidate problem problems;

and the termination judging unit is used for performing termination judgment on the problem pushing event to terminate the problem pushing on the user to be pushed under the condition that the number of pushed problems is equal to a target number, the target number is the number of questionnaire answers of a second user aiming at the questionnaire theme, and the similarity between the second user and the user to be pushed is greater than a second threshold value.

In the above solution, the second question bank data further includes a question type of the candidate question, and the termination determining unit is specifically configured to terminate the question pushing to the user to be pushed when the number of pushed questions is equal to the target number and the question type of the second question is a non-skip type; terminating the problem pushing to the user to be pushed under the conditions that the number of pushed problems is equal to the target number, the problem type of a second problem question is a skip type and a problem pushing event meets a pushing termination condition, wherein the pushing termination condition is the completion of the pushing of candidate problem questions matched with answer information of the second problem question in the second question bank data; and the second problem topic is the problem topic of which the push sequence number corresponds to the target number.

In the above solution, the second question bank data further includes question types of the candidate question questions, and the apparatus further includes:

the third obtaining module is used for obtaining answer information of the first candidate question under the condition that the question type of the first candidate question pushed currently is a skip type;

a second determining module, configured to determine the number of second candidate question questions that are matched with answer information of the first candidate question questions in target question bank data, where the target question bank data includes candidate question questions in the second question bank data except for pushed candidate question questions;

and the updating module is used for updating the problem sequence numbers of the candidate problem questions except the second candidate problem question in the target question bank data based on the quantity of the second candidate problem questions.

In the above scheme, the apparatus further comprises:

the fourth obtaining module is used for obtaining target data of the user to be pushed under the condition that the current time interval is the historical answer time interval of the user to be pushed, and the target data comprises terminal state data and/or terminal use behavior data;

the prediction module is used for predicting whether the current time interval is the optimal answer time interval of the user to be pushed or not based on the target data;

the questionnaire pushing module is specifically configured to, based on the second question bank data, push the questionnaire to the user to be pushed in the case that the current time period is the optimal answer time period of the user to be pushed.

In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes: a processor, a memory, a computer program stored on said memory and executable on said processor, said computer program implementing the steps of the method according to the first aspect when executed by said processor.

In a fourth aspect, the embodiment of the present invention further provides a readable storage medium for storing a program, where the program, when executed by a processor, implements the steps in the method according to the foregoing first aspect.

In the embodiment of the invention, the recommendation value of each question in a plurality of question questions aiming at the user to be pushed is determined based on the historical answer information of the plurality of question questions in the first question bank data; acquiring data of the problem questions of which the recommended values for the users to be pushed are larger than a first threshold value in the plurality of problem questions in the first question bank data to generate second question bank data of the users to be pushed; and then, based on the second question bank data, carrying out questionnaire pushing on the user to be pushed. Therefore, the questionnaire questions suitable for the user to be pushed can be intelligently generated according to the historical answer information of the question questions, and the questionnaire pushing effect can be improved.

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 of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.

Fig. 1 is a schematic flow chart of a questionnaire pushing method provided by an embodiment of the present invention;

FIG. 2 is a schematic diagram of a judgment rule of necessary dimensions;

FIG. 3 is a schematic diagram of a decision rule of sufficient dimension;

FIG. 4 is a schematic diagram of a judgment rule under a combination of essential dimension and sufficient dimension;

FIG. 5 is a schematic diagram of another decision rule under a combination of essential dimension and sufficient dimension;

FIG. 6 is a diagram of another judgment rule under a combination of essential dimension and sufficient dimension;

fig. 7 is a schematic overall flow chart of a questionnaire pushing method in an embodiment of the present invention;

FIG. 8 is a schematic structural diagram of a questionnaire pushing system in an embodiment of the present invention;

fig. 9 is a schematic structural diagram of a questionnaire pushing apparatus provided in an embodiment of the present invention;

fig. 10 is a schematic structural diagram of an electronic device 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 terms "first," "second," and the like in the embodiments of the present invention are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Further, as used herein, "and/or" means at least one of the connected objects, e.g., a and/or B and/or C, means 7 cases including a alone, B alone, C alone, and both a and B present, B and C present, both a and C present, and A, B and C present.

First, a questionnaire pushing method provided in an embodiment of the present invention will be described.

It should be noted that the questionnaire pushing method provided in the embodiment of the present invention can be executed by the questionnaire pushing apparatus in the embodiment of the present invention. The questionnaire pushing device of the embodiment of the invention can be configured in any electronic equipment to execute the questionnaire pushing method of the embodiment of the invention. The electronic device may be a server, and specifically may be a server of the intelligent research platform.

Referring to fig. 1, a schematic flow chart of a questionnaire pushing method provided by an embodiment of the present invention is shown. As shown in fig. 1, the method may include the steps of:

step 101, obtaining first question bank data of a user to be pushed, wherein the first question bank data comprises a plurality of question questions and historical answer information of the plurality of question questions, and a topic label of each question in the plurality of question questions is matched with a questionnaire topic.

The user to be pushed may be any user, or may be a user who has triggered the questionnaire pushing function, or may be a user screened by the questionnaire pushing device, which is not specifically limited herein.

The users to be pushed take the users screened by the questionnaire pushing device as an example, and the questionnaire pushing device can screen the users on the line to determine the users to be pushed.

Specifically, the questionnaire pushing device can generate a user attribute tag based on various attribute data such as basic attributes (including a user Identity (ID), a mobile phone number, a gender, an age, a region, an occupation, an industry, a family condition and the like) of a system registered user, terminal use attributes (including a brand, a model, system information, package information, a flow use condition and the like), consumption preference data (including an online shopping product, an offline shopping product, a consumption amount, a payment means and the like), and online behavior characteristics (including an application program (APP) use condition, online time, frequency, online social behaviors and the like) and the like; matching the questionnaire theme of the research with the user attribute tag, and screening out target type users meeting the research requirement to serve as users to be pushed to push questionnaires.

The first question bank data may be referred to as raw question bank data, and the raw question bank data may include a plurality of question questions whose topic tags match the topics of the questionnaire. The original question bank data can be obtained from the overall question bank data, the overall question bank data can include all pre-stored data of question questions, and the overall question bank data can include the subject labels of the question questions.

The keywords of the questionnaire theme researched this time can be matched with the topic tags of the question topics in the database data by using the existing or new matching algorithm, such as the extensive matching algorithm, and when the keywords of the questionnaire theme researched contain the keywords or synonyms of the topic tags of the question topics in the database data, the matching is successful, and the question topics can be stored in the original question database.

The original question bank data may include: questionnaire names, question questions and options, question sequence numbers, and historical answer information. The historical answer information may include the number of answer times of the question and the historical answer user tag, and the historical answer user tag may include the user ID and the mobile phone number that have filled in the question.

And 102, determining a recommended value of each question in the plurality of question questions for the user to be pushed based on the historical answer information of the plurality of question questions.

The method comprises the steps of determining a recommended value of each question in a plurality of question questions aiming at a user to be pushed based on historical answer information of the plurality of question questions in original question bank data so as to generate a customized question suitable for the user to be pushed.

The questionnaire pushing device determines a recommended value of the question questions to be pushed, wherein the recommended value can be different for the question questions in the original question bank data and the same question questions are for different pushing users, and therefore the recommended value is the recommended value for the users to be pushed. That is to say, the recommendation value can be used as a standard parameter for performing question pushing to a user to be pushed, and a question with a high recommendation value is preferentially pushed to the user to be pushed. And aiming at different pushing users, even if the questionnaire topics are the same, the question topics of the pushed questionnaire can be different, namely customized question pushing can be carried out for the users on the basis of the determined pushing value.

Before determining that each question in the plurality of question questions aims at the recommended value of the user to be pushed based on the historical answer information of the plurality of question questions, in order to avoid the problem that the user to be pushed has already answered before repeatedly pushing by the user to be pushed, the breadth of answering is improved, and the problem that the user to be pushed has already answered in the original question bank data can be eliminated according to the historical answer information of the user to be pushed. And then determining the recommended value of the problem questions left after being removed in the original question bank data aiming at the user to be pushed.

Step 103, obtaining data of candidate problem topics in the first question bank data to generate second question bank data of the user to be pushed, wherein the candidate problem topics are problem topics aiming at the recommended value of the user to be pushed and larger than a first threshold value in the plurality of problem topics, and the second question bank data comprises the candidate problem topics.

The problem questions with recommendation values within a certain threshold range can be screened from the original question bank data, in order to perform preferential push, the problem questions with the recommendation values larger than a first threshold for the user to be pushed can be obtained from the original question bank data to obtain candidate problem questions, data of the candidate problem questions can be obtained from the first question bank data to obtain second question bank data, and the second question bank data can be called as basic question bank data.

The second question bank data comprises question questions and options, question sequence numbers, question types and question answering times. The problem sequence numbers may be generated from a large value to a small value based on the recommended values of the candidate problem topics for the to-be-pushed users, that is, in a general case, the larger the recommended value for the to-be-pushed user is, the more front the problem sequence number of the candidate problem topic is, and the smaller the recommended value for the to-be-pushed user is, the more back the problem sequence number of the candidate problem topic is. The candidate problem topic component expression in the second topic database may be represented by the following formula (1).

W＝{P₁,P₂,P₃,...,P_n}P_n≥k(0＜k＜1) (1)

Wherein W represents a set of candidate problem topics, P_iAnd (i is more than or equal to 1 and less than or equal to n) represents a recommended value of the ith topic for the user to be pushed, and k represents a first threshold value, wherein the value of k is between 0 and 1.

The problem types can include two types, namely a jump type and a non-jump type, wherein the jump type can be identified by a value 1, and the non-jump type can be identified by a value 0.

And 104, carrying out questionnaire pushing on the user to be pushed based on the second question bank data.

In this step, the questionnaire pushing device may push the candidate question questions in the second question bank data to the user to be pushed, and may push the questionnaire according to the question sequence numbers of the candidate question questions in the second question bank data.

When the questionnaire is pushed, questionnaire data can be pushed to the user to be pushed at one time, and the questionnaire data can comprise candidate question questions and options with a plurality of question sequence numbers arranged in the front. The problem pushing may also be performed one by one according to a preset pushing rule based on the problem sequence numbers of the candidate problem questions, for example, the problem pushing is performed one by one according to the sequence from front to back of the arrangement of the problem sequence numbers of the candidate problem questions, the candidate problem questions and the options with the problem sequence number of 1 are pushed first, the candidate problem questions and the options with the problem sequence number of 2 are pushed second, and so on.

Of course, when performing question pushing, the questionnaire pushing device may determine the question type of the pushed candidate question, and perform next question pushing based on the question type of the candidate question. For example, if the problem type of the currently pushed candidate problem question is a non-skip type, the candidate problem questions are continuously pushed in sequence according to the problem sequence number in the second question bank data. For another example, if the question type of the currently pushed candidate question is a skip type, the question answer submitted by the user to be pushed may be obtained, and the next question is pushed based on the answer submitted by the user to be pushed, which will be described in detail below.

The number of candidate question questions pushed by the questionnaire pushing device may be preset, or the average question amount of the questionnaire of the type that the user of the same type as the user to be pushed answers the questionnaire topics may be counted, and the average question amount is used as the reference value of the number of the pushed candidate question questions, which is not specifically limited herein.

In the embodiment, a recommended value of each question in a plurality of question questions for the user to be pushed is determined based on historical answer information of the plurality of question questions in first question bank data; acquiring data of problem questions, of which recommended values for the users to be pushed are larger than a first threshold value, in the plurality of problem questions in the first question bank data to generate second question bank data of the users to be pushed; and then, based on the second question bank data, carrying out questionnaire pushing on the user to be pushed. Therefore, the questionnaire questions suitable for the user to be pushed can be intelligently generated according to the historical answer information of the question questions, and the questionnaire pushing effect can be improved. Moreover, intelligent and customized investigation is realized, and the investigation accuracy is improved.

Optionally, the plurality of question questions include a first question, the historical answer information of the first question includes a historical answer user tag of the first question, and the first question is any question in the plurality of question questions;

the step 102 comprises:

determining the similarity between the user to be pushed and the first user;

In this embodiment, taking the determination of the recommended value of the first question to the user to be pushed as an example, the process of determining the recommended value of each question in the plurality of question to the user to be pushed based on the historical answer information of the plurality of question is described in detail. The first question topic may be any question topic of the plurality of question topics in the first question bank data.

The historical answer information of the first question may include a historical answer user tag of the first question, and the historical answer user tag may include a user ID.

The answer states of the first user corresponding to the user ID for the multiple question questions may be obtained from the historical answer information of the multiple question questions. For example, for a question, if the first user answers the question, the first user may be identified by a value of 1, and if the first user does not answer the question, the first user may be identified by a value of 0.

And calling a user basic attribute label in a user label library through the user ID to acquire the attribute label of the first user, and calculating the similarity between the user to be pushed and the first user based on the attribute label of the first user and the attribute label of the user to be pushed. Specifically, let r_aiAnd r_biAnd respectively representing the n-dimensional vectors of the attribute labels of the user a to be pushed and the first user, and calculating the similarity of the user a to be pushed and the first user b by adopting a cosine similarity calculation formula, as shown in the following formula (2).

Then, a recommended value of the first question for the user to be pushed may be determined based on the similarity and the answer states of the first user on the plurality of question questions. Specifically, assume α_iRepresenting the similarity between the user to be pushed and the first user who has responded to the ith topic in the first topic database data, wherein the first topic database data can totally comprise t topics, and the recommended value P of the ith topic_iIt can be calculated according to the following formula (3).

Wherein, I_ijShowing the answer state of the first user who has answered the ith question to the jth question, and when the first user answers the jth question, then I_ijWhen the first user has not answered 1Topic of j, then I_ij＝0。

In the embodiment, by calculating the similarity between the user to be pushed and the first user who answers the question in the first question bank data and determining the recommended value of the question in the first question bank data according to the similarity of the users, the optimal question suitable for the user to be pushed can be calculated in real time based on the historical answer information of the question in the first question bank data, so that the generation aspect of the questionnaire is more flexible and intelligent, and the question generation is more accurate.

Optionally, the second question bank data further includes question sequence numbers of the candidate question questions, where the question sequence numbers are generated from large to small based on the recommendation values of the candidate question questions for the user to be pushed, and the step 104 specifically includes:

In this embodiment, the questions may be pushed to the user to be pushed one by one based on the question numbers of the candidate question questions.

Specifically, after the second question bank data is obtained, the question pushing may be performed according to a pushing rule 1, where the pushing rule 1 may be: and sequentially pushing according to the sequence of the problem sequence numbers from front to back, and pushing the candidate problem questions with the problem sequence number of 1 and the options in the second question bank data as the 1 st question to the terminal of the user to be pushed.

Starting from the candidate problem topic of the problem sequence number 2, the problem type of the candidate problem topic can be judged, when the problem type is a non-skip type, the problem is pushed by adopting a pushing rule 2, and when the problem type is a skip type, the problem is pushed by adopting a pushing rule 3.

The push rule 2 may be: and after the candidate question questions are answered by the user to be pushed, continuing to push the candidate question questions in sequence according to the question sequence numbers in the second question bank data.

The push rule 3 may be: after the user answers the currently pushed candidate question questions, the answers submitted by the user to be pushed are returned to the second question bank data, the answers are widely matched with the topic labels of the candidate question questions (the pushed candidate question questions can not be included) in the second question bank data, and the matched candidate question questions are pushed and then continuously pushed in sequence according to the question sequence numbers.

In the questionnaire pushing process, a pushing sequence number can be counted, wherein the pushing sequence number represents the number of problems pushed by a questionnaire pushing device, namely the number of the problems pushed to the user to be pushed, and based on the number of the pushed problems and the target number, a termination judgment is performed on the problem pushing event, namely whether the problem pushing to the user to be pushed needs to be terminated or not is determined. The question pushing event may be an event for pushing a question to the user to be pushed.

When the number of the pushed questions is equal to the target number, the questionnaire pushing device may terminate the question pushing to the user to be pushed, may further determine the question type of the currently pushed candidate question, and determine whether to terminate the question pushing to the user to be pushed based on the question type of the currently pushed candidate question.

The target number may be the number of questionnaire answers of a second user to the questionnaire topic, where the similarity between the second user and the user to be pushed is greater than a second threshold. That is, the target number may be an average number of questions that users of the same type as the user to be pushed have answered questionnaires of the same type as the questionnaire topic, and the average number of questions is used as the answer termination judgment of this time.

In this embodiment, the average question amount of the questionnaire of the same type as the questionnaire theme based on the user answer of the same type as the user to be pushed is used as the answer termination judgment of this time, so as to limit the number of questions to be pushed. In this way, the effect of questionnaire delivery can be further improved.

Optionally, the second question bank data further includes question types of the candidate question questions, and the step of determining termination of the question pushing event when the number of pushed questions is equal to the target number includes:

In this embodiment, when the number of pushed questions is equal to the target number, the terminal may perform terminal determination on the question pushing event, and make a decision to terminate answering.

Specifically, the termination answer decision may include two types, the first type may be a termination answer decision in which the problem type of the second problem question, that is, the reference value problem, is a non-skip type, and the second type may be a termination answer decision in which the problem type of the second problem question, that is, the reference value problem, is a skip type.

And under the condition that the problem type of the reference value problem is a non-skip type, the decision for terminating question answering can be that the problem pushing to the user to be pushed is terminated immediately after the user to be pushed answers the reference value problem.

In the case that the type of the reference-value question is a skip type, the decision to terminate answering may be to terminate the question pushing to the user to be pushed after the candidate question questions matched with the answer information of the reference-value question in the second question bank data are pushed.

In the embodiment, the average question amount of the questionnaire of the same type as the questionnaire theme based on the user answer of the same type as the user to be pushed is used as the answer termination judgment of the current question, and the answer termination decision is made based on the matching condition of the answer information of the pushed question of the last question so as to limit the number of the questions pushed by the current question. Therefore, the effect of questionnaire pushing can be further improved, and the flexibility of questionnaire pushing is improved.

Optionally, the second question bank data further includes question types of the candidate question questions, and before the step of determining termination of the question pushing event when the number of the pushed questions is equal to the target number, the method further includes:

In this embodiment, when the problem type of the currently pushed first candidate problem topic is a skip type, the pushing rule 3 may be adopted to push the problem.

In order to push the matched candidate problem questions in sequence according to the problem sequence numbers after the matched candidate problem questions are pushed, the problem sequence numbers of the candidate problem questions to be pushed need to be updated according to the number of the matched candidate problem questions.

Specifically, if the currently pushed first candidate problem topic only matches the previous second candidate problem topic in the target topic database data, the matched second candidate problem topic is pushed as the next topic, and the problem sequence numbers of the remaining candidate problem topics which are not pushed in the target topic database are sequentially shifted backwards by one bit. The target question bank data can be candidate question questions except the pushed candidate question questions in the second question bank data.

If the currently pushed first candidate question questions are matched with a plurality of second candidate question questions in the target question bank data, the times that the user answers the matched second candidate question questions in the second question bank data can be compared, the second candidate question questions are pushed according to the times in a sorting mode, and the question sequence numbers of the remaining undelivered candidate question questions in the target question bank data are sequentially shifted backwards by corresponding numbers, so that the current pushed first candidate question questions are pushed continuously according to the question sequence numbers after the pushing of the matched question is completed. The corresponding number may be the number of second candidate problem topics, for example, when the number of second candidate problem topics is 3 tracks, the second candidate problem topics may be sequentially shifted backward by three bits.

And if the question is not matched with any question in the second question bank data, continuing to push the questions of the jump type in sequence according to the question sequence number. Then, the questions and the user answers can be fed back to the overall question bank for manual updating, so that the overall question bank data is enriched.

In the embodiment, when the questions are pushed, customized questions most suitable for the users can be generated intelligently according to the real-time answer feedback of the answers of the users and pushed one by one, so that the questionnaire pushing effect can be further improved, and the investigation accuracy is improved.

Optionally, before the step 104, the method further includes:

the step 104 specifically includes:

In this embodiment, in order to improve the effectiveness of the questionnaire data, the success rate of questionnaire recovery, and the user answering experience, the questionnaire propelling device can finally determine the optimal answering time period of the user to be pushed according to the target data of the user to be pushed acquired in real time on the basis of the historical answering time period of the user to be pushed, and push the questionnaire in the optimal answering time period.

Specifically, the questionnaire pushing device can use the historical answer time period as the answer alternative time period of the user to be pushed according to the historical answer time period of the user to be pushed, and on the basis, the target data of the user to be pushed is collected to predict whether the current time period is the optimal answer time period of the user to be pushed. The target data may include terminal state data and/or terminal usage behavior data, and the following target data is described in detail by taking the terminal state data and the terminal usage behavior data as examples.

When the optimal answer time period is predicted, the target data can be divided into data with necessary dimension and data with sufficient dimension, when the data with necessary dimension accords with the optimal answer time period, the optimal answer time period is judged based on the data with sufficient dimension, and when the data with necessary dimension does not accord with the optimal answer time period, the non-optimal answer time period is directly judged.

Data of the necessary dimensions include, but are not limited to: signal intensity, screen state, call state, current time, terminal message reminding setting, user dynamic and static states and the like; data of sufficient dimensions include, but are not limited to: user location, APP usage type, APP switching rate, screen click or swipe frequency, and browse content type lights.

Firstly, the necessary dimensionality is judged, and whether the user to be pushed is in the non-optimal answering time period or not is judged. And if the user to be pushed is not in the non-optimal answering time period, combining the scenes with sufficient dimension on the basis to form various judgment rules based on different scenes, and finally predicting the optimal answering time period of the user to be pushed.

Referring to fig. 2, fig. 2 is a schematic diagram of a determination rule of necessary dimensions, and as shown in fig. 2, when a terminal is in a call, or a terminal signal is not good, or a user to be pushed is not in a static state, or a screen of the terminal of the user to be pushed is not lit, or the terminal of the user to be pushed has no message to remind, it is determined that a current time period is a non-optimal answer time period.

Referring to fig. 3, fig. 3 is a schematic diagram of a determination rule of sufficient dimensionality, and as shown in fig. 3, the determination may be performed based on a plurality of sufficient dimensionalities such as current time (whether the current APP is in a working period, a class period, a sleep period, and the like), a current APP usage type of a user (whether the current APP is in a working period, a game period, a video period, and the like), APP switching rate (whether the current APP stays in an APP for a long time or not), screen operation frequency, a browsing content type (whether related content such as a browsing work period, a search result, and the like is browsed), and a determination rule is generated based on different scenes, so as to finally obtain an optimal answer period of the user to be pushed.

Referring to fig. 4, fig. 4 is a schematic diagram of a judgment rule under the combination of the necessary dimension and the sufficient dimension, and as shown in fig. 4, in the case that the necessary dimension reaches the standard, the judgment of the optimal answer period can be performed according to the current time and the rationality of the screen operation frequency.

Referring to fig. 5, fig. 5 is a schematic diagram of another judgment rule under the combination of the necessary dimension and the sufficient dimension, and as shown in fig. 5, in the case that the necessary dimension reaches the standard, the judgment of the optimal answer time period can be performed according to the application APP type rationality.

Referring to fig. 6, fig. 6 is a schematic diagram of another judgment rule under the combination of the necessary dimension and the sufficient dimension, and as shown in fig. 6, when the necessary dimension reaches the standard, the optimal answer period can be judged according to the APP switching speed and the rationality of the browsed content.

And then, under the condition that the current time interval is determined to be the optimal answer time interval of the user to be pushed, the questionnaire can be pushed to the user to be pushed based on the second question bank data.

In the embodiment, the optimal answer time period of the user to be pushed is predicted by combining the historical answer time period of the user to be pushed, the terminal state, the signal intensity and the terminal using behavior data of the user to be pushed, which are collected in real time, and the questionnaire is pushed in the optimal answer time period, so that the effectiveness of the questionnaire data, the questionnaire recovery success rate and the user answering experience can be improved.

The various optional implementations described in the embodiments of the present invention may be implemented in combination with each other or implemented separately without conflict, and the embodiments of the present invention are not limited thereto.

For ease of understanding, examples are illustrated below:

referring to fig. 7, fig. 7 is a schematic overall flow chart of a questionnaire pushing method in an embodiment of the present invention, and as shown in fig. 7, the overall flow chart is as follows:

the questionnaire pushing of the questionnaire pushing device can comprise a plurality of stages, namely a target and time determining stage, a questionnaire information collecting and preprocessing stage and a questionnaire pushing stage for questionnaire pushing.

In the stage of determining the target and time for pushing the questionnaire, the target answering users can be screened based on the user database and the user terminal data to obtain the users to be pushed, and the optimal answering time period of the users is predicted.

In the questionnaire information collection and preprocessing stage, an original question bank can be screened from a questionnaire question bank, and an answer bank is formed according to a question generation rule to obtain a basic question bank.

In the questionnaire pushing stage, the questions can be pushed according to the pushing rules, the questions are pushed to the user to be pushed one by one, the answers submitted by the user to be pushed are obtained, whether answer answering is terminated or not is judged, if yes, the answer is finished, if not, whether the answers are in the basic question bank or not is judged, if yes, the questions matched with the answers in the basic question bank are continuously pushed, and if not, the answer is finished, and the total question bank is updated.

An embodiment of the present invention further provides a questionnaire pushing system, referring to fig. 8, fig. 8 is a schematic structural diagram of the questionnaire pushing system in the embodiment of the present invention, as shown in fig. 8, the questionnaire pushing device may include a terminal such as a mobile terminal and an intelligent research platform, the mobile terminal may include a terminal operation behavior acquisition module, a terminal use state acquisition module, a communication signal strength acquisition module, and an interaction module, the terminal operation behavior acquisition module, the terminal use state acquisition module, and the communication signal strength acquisition module are used for acquiring user terminal data, and the interaction module is used for reporting the acquired data to the intelligent research platform.

The intelligent investigation platform comprises a target user screening module, an optimal answer time period prediction module, an answer data acquisition module, a questionnaire library acquisition and processing module, a question pushing module and an answer state judgment module, wherein the target user screening module is used for screening users to be pushed according with the investigation based on data such as user basic attributes, terminal attributes, user consumption preferences, internet surfing behaviors, user labels and the like.

The optimal answer time period prediction module is used for pushing the optimal answer time period pushed to the user to be pushed, and the answer data acquisition module is used for acquiring answers reported by the terminal when the user answers. The questionnaire library acquisition and processing module is used for acquiring an original question library comprising a plurality of question questions matched with the questionnaire topics from the overall question library and acquiring a basic question library pushed by the questionnaire from the original question library based on the historical answer data of the user.

The basic question bank comprises a question sequence number, a question option, a question type and answer times, and the user historical answer data comprises a topic label, a question option, an answer module and answer duration.

The question pushing module is used for pushing questions one by one according to the question sequence numbers of the questions in the basic question bank, and the answer state judging module is used for judging the answer state of the terminal so as to push the next question.

The following describes a questionnaire pushing device provided in an embodiment of the present invention.

Referring to fig. 9, a schematic structural diagram of a questionnaire pushing apparatus provided by an embodiment of the present invention is shown. As shown in fig. 9, questionnaire pushing apparatus 900 includes:

a first obtaining module 901, configured to obtain first question bank data of a user to be pushed, where the first question bank data includes multiple question questions and historical answer information of the multiple question questions, and a topic tag of each of the multiple question questions is matched with a questionnaire topic;

a first determining module 902, configured to determine, based on historical answer information of the plurality of question questions, a recommended value of each question in the plurality of question questions for the user to be pushed;

a second obtaining module 903, configured to obtain data of a candidate problem topic in the first question library data to generate second question library data of the user to be pushed, where the candidate problem topic is a problem topic, in the multiple problem topics, for which a recommended value of the user to be pushed is greater than a first threshold, and the second question library data includes the candidate problem topic;

and the questionnaire pushing module 904 is configured to push questionnaires to the user to be pushed based on the second question bank data.

the first determining module 902 comprises:

Optionally, the second question bank data further includes question sequence numbers of the candidate question questions, the question sequence numbers are generated from large to small based on the recommendation values of the candidate question questions for the user to be pushed, and the questionnaire pushing module 904 includes:

and a termination judgment unit, configured to perform termination judgment on the problem pushing event to terminate the pushing of the problem to the user to be pushed when the number of pushed problems is equal to a target number, where the target number is the number of questionnaire answers of a second user to the questionnaire topic, and the similarity between the second user and the user to be pushed is greater than a second threshold.

Optionally, the second question bank data further includes a question type of the candidate question, and the termination determining unit is specifically configured to terminate the question pushing to the user to be pushed when the number of pushed questions is equal to the target number and the question type of the second question is a non-skip type; terminating the problem pushing to the user to be pushed under the conditions that the number of pushed problems is equal to the target number, the problem type of a second problem question is a skip type and a problem pushing event meets a pushing termination condition, wherein the pushing termination condition is the completion of the pushing of candidate problem questions matched with answer information of the second problem question in the second question bank data; and the second problem topic is the problem topic of which the push sequence number corresponds to the target number.

Optionally, the second question bank data further includes question types of the candidate question questions, and the apparatus further includes:

Optionally, the apparatus further comprises:

The questionnaire pushing apparatus 900 can implement each process implemented in the above method embodiments, and is not described here again to avoid repetition.

The following describes an electronic device provided in an embodiment of the present invention.

Referring to fig. 10, a schematic structural diagram of an electronic device provided in an embodiment of the present invention is shown. As shown in fig. 10, the electronic apparatus 1000 includes: a processor 1001, a memory 1002, a user interface 1003, and a bus interface 1004.

The processor 1001, configured to read the program in the memory 1002, executes the following processes:

In fig. 10, the bus architecture may include any number of interconnected buses and bridges, with one or more processors, represented by the processor 1001, and various circuits, represented by the memory 1002, being linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface 1004 provides an interface. The user interface 1003 may also be an interface capable of interfacing with a desired device for different user devices, including but not limited to a keypad, display, speaker, microphone, joystick, etc.

The processor 1001 is responsible for managing the bus architecture and general processing and may also provide various functions including timing, peripheral interface, voltage regulation, power management and other control functions, and optionally the processor 1001 may be a CPU, ASIC, FPGA or CPLD. And the memory 1002 may store data used by the processor 1001 in performing operations.

Optionally, the multiple question questions include a first question, the historical answer information of the first question includes a historical answer user tag of the first question, and the first question is any one of the multiple question questions; the processor 1001 is further configured to:

determining the similarity between the user to be pushed and the first user;

Optionally, the second question bank data further includes question sequence numbers of the candidate question questions, where the question sequence numbers are generated from large to small based on the candidate question questions in order of recommendation values of the user to be pushed, and the processor 1001 is further configured to:

Optionally, the second question bank data further includes question types of the candidate question questions, and the processor 1001 is further configured to:

determining the number of second candidate question questions matched with the answer information of the first candidate question questions in target question bank data, wherein the target question bank data comprises the candidate question questions except the pushed candidate question questions in the second question bank data;

Optionally, the processor 1001 is further configured to:

under the condition that the current time period is the historical answer time period of the user to be pushed, acquiring target data of the user to be pushed, wherein the target data comprises terminal state data and/or terminal use behavior data;

predicting whether the current time period is the optimal answer time period of the user to be pushed or not based on the target data;

the process 1001 is further configured to perform questionnaire pushing to the user to be pushed based on the second question bank data when the current time period is the optimal answer time period of the user to be pushed.

Preferably, an embodiment of the present invention further provides an electronic device, which includes a processor 1001, a memory 1002, and a computer program that is stored in the memory 1002 and can be run on the processor 1001, and when the computer program is executed by the processor 1001, the electronic device implements each process of the above embodiment of the questionnaire pushing method, and can achieve the same technical effect, and in order to avoid repetition, details are not described here again.

The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the above-mentioned questionnaire pushing method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A questionnaire pushing method, characterized in that the method comprises:

2. The method of claim 1, wherein the plurality of question questions comprises a first question, wherein the historical answer information for the first question comprises a historical answer user tag for the first question, and wherein the first question is any one of the plurality of question questions;

acquiring the answer states of the plurality of question questions by a first user corresponding to the historical answer user labels from the historical answer information of the plurality of question questions;

determining the similarity between the user to be pushed and the first user;

and determining a recommendation value of the first question to the user to be pushed based on the similarity and the answer state of the first user to the plurality of question questions.

3. The method according to claim 1, wherein the second question bank data further includes question sequence numbers of the candidate question questions, the question sequence numbers are generated based on the candidate question questions in order of a recommended value of the user to be pushed from large to small, and the step of performing questionnaire pushing to the user to be pushed based on the second question bank data includes:

4. The method according to claim 3, wherein the second question bank data further includes question types of the candidate question questions, and the step of determining termination of the question pushing event in the case that the number of pushed questions is equal to the target number comprises:

when the number of the pushed problems is equal to the target number and the problem type of the second problem is a non-skip type, terminating the problem pushing to the user to be pushed;

5. The method according to claim 3, wherein the second question bank data further includes question types of the candidate question questions, and the method further includes, before the step of performing termination judgment on the question pushing event in the case that the number of pushed questions is equal to the target number:

6. The method according to claim 1, wherein before the step of pushing a questionnaire to the user to be pushed based on the second question bank data, the method further comprises:

7. A questionnaire propelling device, characterized by comprising:

8. The apparatus of claim 7, wherein the plurality of question questions comprises a first question, wherein the historical answer information for the first question comprises a historical answer user tag for the first question, and wherein the first question is any one of the plurality of question questions;

the first determining module includes:

and the second determining unit is used for determining a recommended value of the first question for the user to be pushed based on the similarity and the answer states of the first user on the plurality of question questions.

9. The apparatus of claim 7, wherein the second question bank data further includes question sequence numbers of the candidate question questions, the question sequence numbers are generated based on the candidate question questions in order of big to small recommended values for the user to be pushed, and the questionnaire pushing module comprises:

10. The apparatus according to claim 9, wherein the second question bank data further includes question types of the candidate question questions, and the termination determining unit is specifically configured to terminate the question pushing to the user to be pushed if the number of pushed questions is equal to the target number and the question type of the second question is a non-skip type; terminating the problem pushing to the user to be pushed under the conditions that the number of pushed problems is equal to the target number, the problem type of a second problem question is a skip type and a problem pushing event meets a pushing termination condition, wherein the pushing termination condition is the completion of the pushing of candidate problem questions matched with answer information of the second problem question in the second question bank data; and the second problem topic is the problem topic of which the push sequence number corresponds to the target number.

11. The apparatus of claim 9, wherein the second question bank data further comprises question types for the candidate question questions, the apparatus further comprising:

a second determining module, configured to determine the number of second candidate question questions that are matched with answer information of the first candidate question questions in target question bank data, where the target question bank data includes candidate question questions other than the pushed candidate question questions in the second question bank data;

12. The apparatus of claim 7, further comprising:

the fourth acquisition module is used for acquiring target data of the user to be pushed under the condition that the current time period is the historical answer time period of the user to be pushed, wherein the target data comprises terminal state data and/or terminal use behavior data;

13. An electronic device, characterized in that the electronic device comprises: processor, memory, a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the questionnaire pushing method of any of claims 1 to 6.

14. A readable storage medium storing a program, wherein the program, when executed by a processor, implements the steps in the questionnaire pushing method according to any one of claims 1 to 6.