CN113190660A - Questionnaire survey method and device - Google Patents
Questionnaire survey method and device Download PDFInfo
- Publication number
- CN113190660A CN113190660A CN202010038197.3A CN202010038197A CN113190660A CN 113190660 A CN113190660 A CN 113190660A CN 202010038197 A CN202010038197 A CN 202010038197A CN 113190660 A CN113190660 A CN 113190660A
- Authority
- CN
- China
- Prior art keywords
- question
- user
- questionnaire
- current
- survey
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012545 processing Methods 0.000 claims description 38
- 238000011835 investigation Methods 0.000 claims description 12
- 230000009191 jumping Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000005352 clarification Methods 0.000 description 7
- 230000003993 interaction Effects 0.000 description 5
- 238000013145 classification model Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 241001122315 Polites Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a questionnaire survey method and device. The method comprises the following steps: outputting a questionnaire to a user, wherein the questionnaire comprises at least one question, the questions in the questionnaire comprise question content and question types, receiving user dialogues of each question in the questionnaire input by the user, determining a survey result of each question according to the question type of each question and the user dialogues of each question, the survey result of each question comprises the user dialogues of each question and/or answers of the questionnaire corresponding to the user dialogues of each question, outputting the survey result of each question, and storing the survey content of the questionnaire, wherein the survey content comprises survey identifications, and the user dialogues and the survey results of each question in the questionnaire. Therefore, the intelligent customer service can complete questionnaire services, and the labor cost is saved.
Description
Technical Field
The invention relates to the technical field of information, in particular to a questionnaire survey method and device.
Background
In recent years, with the development of artificial intelligence, customer service has been gradually advancing toward intellectualization. Compared with manual customer service, the intelligent customer service can better reduce the customer service pressure, reduce the operation cost, improve the marketing ability, standardize the industry knowledge base, establish the service image and improve the satisfaction degree.
The man-machine interaction mode of the intelligent customer service mainly adopts a conversation mode, the intelligent customer obtains the user intention in the user speaking art, and then the intelligent customer service decides how to interact with the user according to the user intention, such as: solving a certain question, executing a certain instruction, guiding a user to complete a certain flow, and the like.
However, for the questionnaire services such as satisfaction survey, questionnaire, return visit, etc., it is necessary to summarize the user's dialect into an effective questionnaire, and thus the existing intelligent customer service cannot fulfill the requirements of the questionnaire services.
Disclosure of Invention
The invention provides a questionnaire survey method and device, which are used for solving the problem that the existing intelligent customer service cannot complete questionnaire services.
In a first aspect, the present invention provides a method of questionnaire survey, comprising:
outputting a questionnaire to a user, wherein the questionnaire comprises at least one question; the questions in the questionnaire comprise question content and question types;
receiving a user utterance for each question in the questionnaire input by the user;
determining a survey result of each question according to the question type of each question and the user dialect of each question, wherein the survey result of each question comprises the user dialect of each question and/or a questionnaire answer corresponding to the user dialect of each question;
outputting the investigation result of each question;
and saving the survey content of the questionnaire, wherein the survey content comprises survey identification, user dialect of each question in the questionnaire and survey results.
Optionally, the determining the investigation result of each question according to the question type of each question and the user dialect of each question includes:
and when the question type of the current question is a selected question, matching the user dialect of the current question with a first sample answer library to obtain a questionnaire answer corresponding to the user dialect of the current question, wherein the first sample answer library comprises questionnaire answers of all options of the selected question.
Optionally, the determining the investigation result of each question according to the question type of each question and the user dialect of each question includes:
when the question type of the current question is a time question or a place question, matching the user dialect of the current question with a second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is the answer of the questionnaire of the current question; alternatively, the first and second electrodes may be,
matching the user dialect of the current question with a preset time regular expression or a preset place regular expression, if the matching is successful, obtaining the time or the place corresponding to the current question, and if the matching is unsuccessful, matching the user dialect of the current question with the second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is the answer of the questionnaire of the current question;
and the second sample answer library comprises preset answers of the time question and answer questions or the place question and answer questions.
Optionally, the determining the investigation result of each question according to the question type of each question and the user dialect of each question includes:
when the question type of the current question is a general question and answer question, taking the user's dialect of the current question as a survey result of the current question; or, performing similarity matching on the user dialect of the current question and a third sample answer library to obtain a score of the user dialect of the current question, where the scores of the user dialect and the user dialect of the current question are answers to the questionnaire of the current question, and the third sample answer library includes keywords or standard templates of answers to the general questionnaire.
Optionally, the method further includes:
receiving a retrieval condition;
according to the retrieval conditions, inquiring the stored survey contents of the questionnaires to obtain the survey contents of the target questionnaire meeting the retrieval conditions;
and determining a retrieval result according to the survey content of the target questionnaire, and outputting the retrieval result.
Optionally, after the receiving the user utterance of each question in the questionnaire input by the user, the method further includes:
identifying a user intraoperative intent of a current problem;
when the user's speech of the current question includes a second intention except the intention pointed by the current question, jumping to a processing scene corresponding to the second intention;
receiving user dialogues input by the user in the processing scene corresponding to the second intention;
receiving an end instruction, and ending the processing scene corresponding to the second intention according to the end instruction;
and after the processing scene corresponding to the second intention is finished, continuing to process the current problem.
In a second aspect, the present invention provides an apparatus for questionnaire survey, comprising:
the system comprises an output module, a query module and a query module, wherein the output module is used for outputting a questionnaire to a user, and the questionnaire comprises at least one question; the questions in the questionnaire comprise question content and question types;
a receiving module for receiving a user's dialect of each question in the questionnaire input by the user;
a determining module, configured to determine a survey result of each question according to the question type of each question and the user's dialect of each question, where the survey result of each question includes the user's dialect of each question and/or a questionnaire answer corresponding to the user's dialect of each question;
the output module is also used for outputting the investigation result of each question;
and the storage module is used for storing the survey content of the questionnaire, wherein the survey content comprises survey identification, and the user dialect and the survey result of each question in the questionnaire.
Optionally, the determining module is specifically configured to:
and when the question type of the current question is a selected question, matching the user dialect of the current question with a first sample answer library to obtain a questionnaire answer corresponding to the user dialect of the current question, wherein the first sample answer library comprises questionnaire answers of all options of the selected question.
Optionally, the determining module is specifically configured to:
when the question type of the current question is a time question or a place question, matching the user dialect of the current question with a second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is the answer of the questionnaire of the current question; alternatively, the first and second electrodes may be,
matching the user dialect of the current question with a preset time regular expression or a preset place regular expression, if the matching is successful, obtaining the time or the place corresponding to the current question, and if the matching is unsuccessful, matching the user dialect of the current question with the second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is the answer of the questionnaire of the current question;
and the second sample answer library comprises preset answers of the time question and answer questions or the place question and answer questions.
Optionally, the determining module is specifically configured to:
when the question type of the current question is a general question and answer question, taking the user's dialect of the current question as a survey result of the current question; or, performing similarity matching on the user dialect of the current question and a third sample answer library to obtain a score of the user dialect of the current question, where the scores of the user dialect and the user dialect of the current question are answers to the questionnaire of the current question, and the third sample answer library includes keywords or standard templates of answers to the general questionnaire.
Optionally, the apparatus further comprises:
the receiving module is also used for receiving the retrieval condition;
the query module is used for querying the stored survey contents of the questionnaires according to the retrieval conditions to obtain the survey contents of the target questionnaire meeting the retrieval conditions;
and the determining module is also used for determining a retrieval result according to the survey content of the target questionnaire and outputting the retrieval result.
Optionally, the apparatus further comprises:
an identification module for identifying a user's intraoperative intent of a current question;
the skipping module is used for skipping to a processing scene corresponding to a second intention when the user's dialect of the current question comprises the second intention except the intention pointed by the current question;
the receiving module is further used for receiving user dialogues input by the user in the processing scene corresponding to the second intention; receiving an end instruction, and ending the processing scene corresponding to the second intention according to the end instruction;
and the skipping module is further used for continuing to process the current problem after the processing scene corresponding to the second intention is finished.
In a third aspect, the present invention provides an apparatus for questionnaire survey, comprising:
a memory for storing processor-executable instructions;
a processor for executing instructions of the method of questionnaire survey as described above in the first aspect when the computer program is executed.
In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon computer-executable instructions for implementing the method of questionnaire survey as described in the first aspect above when the computer-executable instructions are executed by a processor.
The questionnaire survey method and device provided by the invention output questionnaires to users, wherein the questionnaires comprise at least one question, the questions in the questionnaires comprise question content and question types, user dialogs of each question in the questionnaires input by the users are received, survey results of each question are determined according to the question types of each question and the user dialogs of each question, the survey results of each question comprise the user dialogs of each question and/or questionnaire answers corresponding to the user dialogs of each question, the survey results of each question are output, the survey contents of the questionnaires are stored, the survey contents comprise survey identifications, the user dialogs of each question in the questionnaires and the survey results, and therefore intelligent customer service can be realized to complete questionnaire services, and labor cost is saved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a schematic diagram of a questionnaire survey system provided in the present invention;
FIG. 2 is a schematic flow chart of a method for questionnaire survey provided by the present invention;
FIG. 3 is a schematic diagram of a questionnaire;
FIG. 4 is a schematic flow chart of another method for questionnaire survey provided by the present invention;
FIG. 5 is a schematic flow chart of another questionnaire method provided by the present invention;
FIG. 6 is a schematic structural diagram of a questionnaire survey device provided by the present invention;
fig. 7 is a schematic structural diagram of a questionnaire survey device provided by the invention.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The terms to which the present invention relates will be explained first:
questionnaires: the method refers to a series of problems designed for collecting information such as attitude, value, viewpoint or belief of a user to a specific problem.
Fig. 1 is a schematic structural diagram of a questionnaire survey system provided by the present invention, and as shown in fig. 1, the system provided by this embodiment includes a terminal device 101 and a server 102. The terminal device 101 may be a mobile phone, a tablet, a vehicle-mounted terminal, a child story machine, or the like. The implementation manner of the terminal device 101 is not particularly limited in this embodiment, as long as the terminal device 101 can interact with the user through voice, text, or the like.
The intelligent customer service is equipment capable of interacting with people, so that manual work is replaced, and customer service work is completed. Server 102 is a device capable of intelligent customer service functionality.
In a questionnaire scenario such as a satisfaction survey, a questionnaire, a return visit, etc., it is necessary to collect answers of a user to a questionnaire containing at least one question. A questionnaire is set on the server 102, the questionnaire including: at least one question and the question type of each question, wherein the questions in the questionnaire can be directly set or can be obtained through a question database, the question database comprises at least one question, and the question can be selected from the questions in the question database when different questionnaires are set. For example, some common questions, such as "please score our services", may be set in the question database, and therefore the question may be set in the question database, and the question may be directly called when different questionnaires are set, and the question does not need to be set repeatedly, which may improve the efficiency of setting questionnaires. Accordingly, the questions in the question database also include a question type for the question, the question type for the question being one of the following types: types of choice questions, time question-answering questions, place question-answering questions, general question-answering questions, and the like.
After the questionnaire is set, the user to be faced by the current questionnaire needs to be selected from the user database, and the server 102 sends a voice or text interaction request to the terminal device 101 of the user to be faced by the questionnaire, for example, the questionnaire survey can be requested to be performed by sending a voice call, a short message or a voice or text message to the client in the terminal device 101. The user receives the request through the terminal device 101, for example, the server 102 can make a voice call with the terminal device and ask "ask if you can make a short return visit? After the user answers the dialects of "ok" or "good", etc., the server 102 outputs a questionnaire to the user through the terminal device 101, and receives the user dialects of each question in the questionnaire input by the user through the terminal device 101, the server 102 determines the survey result of each question according to the question type of each question and the user dialects of each question, wherein the survey result of each question comprises the user dialects of each question and/or the answers of the questionnaire corresponding to the user dialects of each question, the server 102 outputs the survey result of each question, and the survey content of the questionnaire is stored, and the survey content comprises survey identification, the user dialects of each question in the questionnaire and the survey results.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Fig. 2 is a schematic flow chart of a method for questionnaire survey provided by the present invention, as shown in fig. 2, the method of the present embodiment is executed by a server, and the method of the present embodiment is as follows:
s201, outputting a questionnaire to a user, wherein the questionnaire comprises at least one question, and the questions in the questionnaire comprise question contents and question types.
In this embodiment, a preset questionnaire may be output to a user in a voice or text manner, and fig. 3 is a schematic diagram of the questionnaire, as shown in fig. 3, the questionnaire includes 4 questions, and each question in the questionnaire includes a question content and a question type. The question types may include, among others: the choice question, the time short answer question, the place short answer question, the general short answer question, etc., the time short answer question is a short answer question for a time question, the place short answer question is a short answer question for a place question, the general short answer question is a short answer question other than a question for time and place, for example, the question type of the first question 302 is the choice question. Questionnaire name 301 may also be included in the questionnaire.
S202, receiving user dialects of each question in the questionnaire input by the user.
Questions in the questionnaire can be output to the user one by one, one question is output first, and after receiving the user's utterance input for the question, the next question is output. All questions in the questionnaire may also be output to the user, and the user's dialect for each question in the questionnaire input by the user may be received. Wherein the user utterance is a voice or text when the user answers a question.
S203, determining the investigation result of each question according to the question type of each question and the user dialect of each question.
The survey result of each question comprises the user dialect of each question and/or the answer of the questionnaire corresponding to the user dialect of each question.
When the question type of the current question is a choice question, in one possible implementation, when outputting the question to the user, an option of the choice question may be simultaneously output, where the option is a preset user's word that may appear for the question, for example, the options in the first question 302 in fig. 3 are "a is found" and "B is not found".
If the option of the selected question is output, the user's dialect may be "a" or "finding" as an example, and the user's dialect may be matched with the preset option to obtain the answer "a" of the questionnaire corresponding to the user's dialect of the current question.
In another possible implementation manner, when a question is output, the option of the selected question is not output, and the user dialect of the current question is matched with the first sample answer library to obtain the answer of the questionnaire corresponding to the user dialect of the current question.
For example, the option a of the first question 302 in fig. 3 is defined as representing a positive answer, so that the answer to the questionnaire of the option a in the first sample answer library is a user's dialect representing a positive answer to the first question 302, and may include preset "in-search", "yes", "in-search work", and the like. Alternatively, one or more classification sample sets may be preset, each classification sample set contains a class of user dialogs representing similar meanings, and when the answer to the questionnaire of each option of the choice question in the first sample answer library is set, the classification sample set may be directly used, for example, it may be set that the answer to the questionnaire of choice a in the first sample answer library of the first question 302 in fig. 3 includes "yes", and the like, and through the setting of the classification sample set, there is no need to repeat the setting of the answer to the questionnaire already existing in the classification sample set when the questionnaire is set, thereby improving the efficiency of setting the first sample answer library of the choice questions in the questionnaire.
Matching the user dialect of the current question with the first sample answer library, obtaining the matching degree of each option of the user dialect and the current question through a pre-trained classification model, and selecting the option with the highest matching degree as a questionnaire answer corresponding to the user dialect of the question, wherein the classification model is obtained by training the first sample answer library, and the user dialect can be classified as one option of the current question through the modes of calculating distance and the like.
Optionally, the first sample answer library may be modified, for example, after the questionnaire survey is actually performed, the questionnaire answers are added to the first sample answer library by analyzing the user's dialect, and the questionnaire answers in the unsuitable first sample answer library may also be reduced, so as to improve the ability of understanding the user's dialect.
When the question type of the current question is a time question or a place question, matching the user dialect of the current question with the second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is the answer of the questionnaire of the current question; alternatively, the first and second electrodes may be,
and matching the user dialect of the current question with a preset time regular expression or a preset place regular expression, if the matching is successful, obtaining the time or the place corresponding to the current question, and if the matching is unsuccessful, matching the user dialect of the current question with a second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is the answer of the questionnaire of the current question.
The second sample answer library is preset and can also be called as a time dictionary or a place dictionary, and the second sample answer library comprises preset answers of time questions or place questions. The time regular expression may be a regular expression at a certain day in a certain month in a certain year, or a regular expression at a certain minute in a certain second in a certain time, and the like, which is not limited to the present invention. The place regular expression may be a regular expression of a city or a district, and the invention is not limited thereto.
When a time regular expression or a place regular expression is preset, the user's speech of the current question can be matched with the preset time regular expression or place regular expression, if the matching is successful, the time or the place corresponding to the current question is output, if the matching is unsuccessful, the user's speech of the current question can be matched with a second sample answer library, the time or the place corresponding to the current question is the answer of the questionnaire of the current question, for example, the format of the corresponding time obtained by the time questionnaire question can be 'year-month-day: minute-second (yyyyy-MM-hh: MM: ss)'.
For example, when the question type of the current question is a time short answer question, and the user's utterance of the current question is "tomorrow", the "tomorrow" may be matched with a preset time regular expression, and if the matching fails, the "tomorrow" may be matched with the second sample answer library, and the "tomorrow" is matched in the second sample answer library, and the system may determine a specific day of the tomorrow according to the current time, and obtain a time corresponding to the current question as a questionnaire answer to the current question.
Optionally, if the matching between the user dialect of the current question and the second sample answer library is unsuccessful, outputting the clarification dialect of the current question, receiving the user dialect, performing the matching between the user dialect corresponding to the current clarification dialect, and stopping the output of the clarification dialect in a possible implementation manner, until the user dialect corresponding to the current clarification dialect is successfully matched in the manner, ending the output of the clarification dialect; a threshold value of the number of output clarifying utterances may also be set, and the output clarifying utterances are ended when the number of output clarifying utterances reaches the threshold value. The clarification dialog is preset for querying again, for example, the clarification dialog may be set as "i don't hear clearly, you can say once more", etc., and the present invention is not limited thereto.
Optionally, the second sample answer library may be modified, for example, after the questionnaire survey is actually performed, the questionnaire answers are added to the second sample answer library by analyzing the user's dialect, and the questionnaire answers in the unsuitable second sample answer library may also be reduced, so as to improve the ability of understanding the user's dialect.
When the question type of the current question is a general question and answer question, taking the user's dialect of the current question as the survey result of the current question; or, performing similarity matching on the user dialect of the current question and the third sample answer library to obtain the score of the user dialect of the current question, wherein the score of the user dialect and the user dialect of the current question are the questionnaire answers of the current question.
The third sample answer library is preset, and the third sample answer library comprises keywords of answers of general questions or standard templates. In a possible implementation manner, the third sample answer library includes at least one keyword of an answer to a general question-answer question, the keyword is extracted from the user's dialect of the current question, and then the keyword is matched with the keyword in the answer, for example, a score threshold may be preset, where the score threshold is a total score of the current question, in order to check whether the user will use a polite call, the keyword of the answer may be set to "you", and when "you" appears in the user's dialect, the score needs to be reduced by 3 points. And extracting a keyword 'you' from the user dialect, and if the keyword 'you' appears in the user dialect is extracted, subtracting 3 points according to a score threshold value when calculating the score of the user dialect of the current problem.
In another possible implementation manner, the third sample answer library includes a standard template of answers to general questions, similarity matching is performed between the user dialect of the current question and the standard template, a matching degree is calculated, a score threshold value, that is, a total score of the current question and a conversion formula of the matching degree and the score of the user dialect of the current question, may be preset, so as to obtain the score of the user dialect of the current question.
Optionally, the third sample answer library may be modified, for example, after the questionnaire survey is actually performed, the questionnaire answers are added to the third sample answer library by analyzing the user's dialect, and the questionnaire answers in the third sample answer library that are not suitable may also be reduced, or the questionnaire answers in the third sample answer library may be modified, so as to improve the ability of understanding the user's dialect.
And S204, outputting the investigation result of each question.
S205, saving the survey content of the questionnaire, wherein the survey content comprises a survey identifier, a user' S dialect of each question in the questionnaire and a survey result.
The survey contents of the file are stored, wherein the survey mark is a mark capable of uniquely identifying the questionnaire survey, and may be, for example, a mobile phone number of the user, an identification number of the generated unique questionnaire survey, or the like.
Optionally, the user's dialect of each question in the questionnaire may be saved in real time in a snapshot manner, and if the questionnaire is adjusted in a later stage, the adjusted survey result of the question may be retrieved according to the saved user's dialect. Adjusting the questionnaire may be a change to the questions in the questionnaire; the question in the questionnaire may be an option, or may be an adjustment of an option. For example, in fig. 3, the first question 302 is adjusted to be a not found, and B is found, so that the investigation result of the question is obviously inaccurate before the first question is found, and therefore, the investigation result needs to be output again according to the saved user's dialect, the adjusted question and the selected type.
In the embodiment, a questionnaire is output to a user, wherein the questionnaire comprises at least one question, the questions in the questionnaire comprise question content and question types, a user utterance of each question in the questionnaire input by the user is received, a survey result of each question is determined according to the question type of each question and the user utterance of each question, the survey result of each question comprises the user utterance of each question and/or a questionnaire answer corresponding to the user utterance of each question, the survey result of each question is output, the survey content of the questionnaire is stored, the survey content comprises a survey identifier, and the user utterance and the survey result of each question in the questionnaire are stored, so that intelligent customer service can complete questionnaire services, and labor cost is saved.
Fig. 4 is a schematic flow chart of another questionnaire survey method provided by the present invention, and fig. 4 is a flowchart of the embodiment shown in fig. 2, further, as shown in fig. 4, after S205, the present embodiment further includes:
s206, receiving the search condition.
The search condition is a limit condition for searching different dimensions of the survey content of the stored questionnaire, and the data to be displayed can be displayed according to the search result, so that the corresponding statistics of the search data can be carried out. The retrieval with different dimensions means that retrieval can be performed on user dialects corresponding to different problems, or retrieval can be performed on investigation results of different problems.
And S207, inquiring the stored survey contents of the plurality of questionnaires according to the search condition to obtain the survey contents of the target questionnaire meeting the search condition.
And S208, determining a search result according to the survey content of the target questionnaire, and outputting the search result.
For example, as shown in the questionnaire in fig. 3, if it is necessary to search for how many people currently want to find the job of customer service, the number of questionnaires whose search result is a for the first question 302 may be set as the search condition, and the search may be performed in the stored survey contents of the plurality of questionnaires to obtain the number of survey marks whose search result is a for the first question 302, so as to determine the search result, and output the search result, thereby counting how many people are finding the job of customer service.
In this embodiment, by receiving the search condition, a query is made among the stored survey contents of the plurality of questionnaires according to the search condition, the survey contents of the target questionnaire satisfying the search condition are obtained, the search result is determined according to the survey contents of the target questionnaire, and the search result is output. And corresponding data can be counted according to the set retrieval conditions with different dimensions.
Fig. 5 is a schematic flow chart of another questionnaire survey method provided by the present invention, where fig. 5 is based on the embodiment shown in fig. 2 or fig. 4, and further, as shown in fig. 5, this embodiment further includes, after S202:
s501, recognizing the intention of the user in the current question in the art.
In some scenarios, the intelligent customer service divides the service by scenarios, each scenario has several intentions, and the user's speech triggers an intention to perform human-computer interaction, for example, in a broadband renewal scenario, the included intentions are: introducing package intention, moving intention, repairing intention, no-time-charge intention, order placing intention, payment intention, network Taika intention, charging intention, package screening intention and the like. There is no correlation between these intentions, and they are performed independently.
In the scenes of questionnaire survey and the like, the questionnaire intentions are dominant intentions, the questionnaire intentions are associated to one questionnaire, and after the user's utterance of the current question is received, the intention of the user's utterance of the current question is identified.
And S502, when the user utterance of the current question comprises a second intention except the intention pointed by the current question, jumping to a processing scene corresponding to the second intention.
And when the user's intention in the operation of the current question under the questionnaire intention is recognized to be a second intention except the intention pointed by the current question, namely the second intention is not the questionnaire intention, jumping to a processing scene corresponding to the second intention for processing.
And S503, receiving the user dialect input by the user in the processing scene corresponding to the second intention.
And receiving user dialogues input by the user in the processing scene corresponding to the second intention, and interacting with the user according to a preset interaction strategy in the processing scene corresponding to the second intention.
And S504, receiving an end instruction, and ending the processing scene corresponding to the second intention according to the end instruction.
The ending indication may be, for example, a user's talk, or an ending flag in a processing scenario corresponding to the set second intention,
and S505, after the processing scene corresponding to the second intention is finished, continuing to process the current problem.
After the processing scene corresponding to the second intention is finished, the user needs to return to the questionnaire intention and continue to process the questionnaire under the questionnaire intention, that is, continue to process the current question.
Illustratively, in a broadband questionnaire scenario, questionnaire intents are included, and a second intention is included that is one or more of: employee intent, complaint employee intent, activity introduction intent, user uncooperative intent, cybercard intent, warranty intent, and the like. The questionnaire intentions are dominant intentions in a questionnaire scene, the questionnaire intentions need to be associated with one questionnaire, ask a user for a question and receive the user's utterance, and the second intentions have no relevance and are executed independently, but the second intentions are all associated with the questionnaire intentions. For example, after a question is output to a user under the questionnaire intention, if a user has a web card-related word in the word, the user jumps from the questionnaire intention to the web card intention, and a message of "please try to plug and unplug the router, and if the web card is still too large, the user logs in to an official website to know a more detailed solution can be output. At this time, receiving a word meaning "good" of the user or a word meaning "thank you" or the like, namely an end instruction of the processing scene corresponding to the network Ethernet card intention, ending the processing scene corresponding to the network Ethernet card intention, returning to the questionnaire intention, and continuing to process the current question.
In the embodiment, by identifying the intention in the user's speech of the current question, when the user's speech of the current question includes a second intention except the intention indicated by the current question, jumping to the processing scene corresponding to the second intention, receiving the user's speech input by the user in the processing scene corresponding to the second intention, receiving an end instruction, ending the processing scene corresponding to the second intention according to the end instruction, and after the processing scene corresponding to the second intention is ended, continuing to process the current question, so that the user is interacted with the questionnaire intention under the processing scene corresponding to the second intention according to the second intention indicated by the user's speech of the current question, the interaction with the user is more intelligent, and the user experience is improved.
Fig. 6 is a schematic structural diagram of an apparatus for questionnaire survey provided by the present invention, and as shown in fig. 6, the apparatus provided in this embodiment includes:
an output module 601, configured to output a questionnaire to a user, where the questionnaire includes at least one question; questions in the questionnaire include question content and question type;
an output module 602, configured to receive a user utterance of each question in the questionnaire input by the user;
an output module 603, configured to determine a survey result of each question according to the question type and the user utterance of each question, where the survey result of each question includes the user utterance of each question and/or a questionnaire answer corresponding to the user utterance of each question;
the output module 601 is further configured to output a survey result of each question;
the output module 604 is configured to store the survey content of the questionnaire, where the survey content includes a survey identifier, a user's dialect for each question in the questionnaire, and a survey result.
Optionally, the output module 603 is specifically configured to:
and when the question type of the current question is a selected question, matching the user dialect of the current question with a first sample answer library to obtain a questionnaire answer corresponding to the user dialect of the current question, wherein the first sample answer library comprises questionnaire answers of all options of the selected question.
Optionally, the output module 603 is specifically configured to:
when the question type of the current question is a time question or a place question, matching the user dialect of the current question with the second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is the answer of the questionnaire of the current question; alternatively, the first and second electrodes may be,
matching the user dialect of the current question with a preset time regular expression or a preset place regular expression, if the matching is successful, obtaining the time or the place corresponding to the current question, and if the matching is unsuccessful, matching the user dialect of the current question with a second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is a questionnaire answer of the current question;
and the second sample answer library comprises preset answers of time questions or place questions.
Optionally, the output module 603 is specifically configured to:
when the question type of the current question is a general question and answer question, taking the user's dialect of the current question as the survey result of the current question; or, performing similarity matching on the user dialect of the current question and a third sample answer library to obtain a score of the user dialect of the current question, wherein the score of the user dialect and the user dialect of the current question are answers to the questionnaire of the current question, and the third sample answer library comprises keywords of answers to general questions or standard templates.
Optionally, the apparatus further comprises:
an output module 602, further configured to receive a retrieval condition;
the query module is used for querying the stored survey contents of the questionnaires according to the retrieval conditions to obtain the survey contents of the target questionnaire meeting the retrieval conditions;
the output module 603 is further configured to determine a search result according to the survey content of the target questionnaire, and output the search result.
Optionally, the apparatus further comprises:
an identification module for identifying a user's intraoperative intent of a current question;
the skipping module is used for skipping to a processing scene corresponding to a second intention when the user dialect of the current question comprises the second intention except the intention indicated by the current question;
the output module 602 is further configured to receive a user utterance input by the user in a processing scenario corresponding to the second intention; receiving an end instruction, and ending the processing scene corresponding to the second intention according to the end instruction;
and the skipping module is also used for continuously processing the current problem after the processing scene corresponding to the second intention is finished.
The apparatus of the foregoing embodiment may be configured to implement the technical solution of the foregoing method embodiment, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 7 is a schematic structural diagram of an apparatus for questionnaire survey provided by the present invention, and as shown in fig. 7, the apparatus provided in this embodiment includes:
a memory 701, a memory 701 for storing instructions executable by the processor 702;
a processor 702 for executing instructions of the method of questionnaire survey of any of the above embodiments when the computer program is executed.
The present invention provides a computer-readable storage medium having stored thereon computer-executable instructions for implementing a method of questionnaire survey as in any one of the above embodiments when executed by a processor. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (14)
1. A method of questionnaire survey, comprising:
outputting a questionnaire to a user, wherein the questionnaire comprises at least one question; the questions in the questionnaire comprise question content and question types;
receiving a user utterance for each question in the questionnaire input by the user;
determining a survey result of each question according to the question type of each question and the user dialect of each question, wherein the survey result of each question comprises the user dialect of each question and/or a questionnaire answer corresponding to the user dialect of each question;
outputting the investigation result of each question;
and saving the survey content of the questionnaire, wherein the survey content comprises survey identification, user dialect of each question in the questionnaire and survey results.
2. The method of claim 1, wherein determining the survey results for each question based on the question type for each question and the user's interpretation of each question comprises:
and when the question type of the current question is a selected question, matching the user dialect of the current question with a first sample answer library to obtain a questionnaire answer corresponding to the user dialect of the current question, wherein the first sample answer library comprises questionnaire answers of all options of the selected question.
3. The method of claim 1, wherein determining the survey results for each question based on the question type for each question and the user's interpretation of each question comprises:
when the question type of the current question is a time question or a place question, matching the user dialect of the current question with a second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is the answer of the questionnaire of the current question; alternatively, the first and second electrodes may be,
matching the user dialect of the current question with a preset time regular expression or a preset place regular expression, if the matching is successful, obtaining the time or the place corresponding to the current question, and if the matching is unsuccessful, matching the user dialect of the current question with the second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is the answer of the questionnaire of the current question;
and the second sample answer library comprises preset answers of the time question and answer questions or the place question and answer questions.
4. The method of claim 1, wherein determining the survey results for each question based on the question type for each question and the user's interpretation of each question comprises:
when the question type of the current question is a general question and answer question, taking the user's dialect of the current question as a survey result of the current question; or, performing similarity matching on the user dialect of the current question and a third sample answer library to obtain a score of the user dialect of the current question, where the scores of the user dialect and the user dialect of the current question are answers to the questionnaire of the current question, and the third sample answer library includes keywords or standard templates of answers to the general questionnaire.
5. The method according to any one of claims 1-4, further comprising:
receiving a retrieval condition;
according to the retrieval conditions, inquiring the stored survey contents of the questionnaires to obtain the survey contents of the target questionnaire meeting the retrieval conditions;
and determining a retrieval result according to the survey content of the target questionnaire, and outputting the retrieval result.
6. The method of any of claims 1-4, wherein the receiving the user input after the user utterance of each question in the questionnaire further comprises:
identifying a user intraoperative intent of a current problem;
when the user's speech of the current question includes a second intention except the intention pointed by the current question, jumping to a processing scene corresponding to the second intention;
receiving user dialogues input by the user in the processing scene corresponding to the second intention;
receiving an end instruction, and ending the processing scene corresponding to the second intention according to the end instruction;
and after the processing scene corresponding to the second intention is finished, continuing to process the current problem.
7. An apparatus for questionnaire survey, comprising:
the system comprises an output module, a query module and a query module, wherein the output module is used for outputting a questionnaire to a user, and the questionnaire comprises at least one question; the questions in the questionnaire comprise question content and question types;
a receiving module for receiving a user's dialect of each question in the questionnaire input by the user;
a determining module, configured to determine a survey result of each question according to the question type of each question and the user's dialect of each question, where the survey result of each question includes the user's dialect of each question and/or a questionnaire answer corresponding to the user's dialect of each question;
the output module is also used for outputting the investigation result of each question;
and the storage module is used for storing the survey content of the questionnaire, wherein the survey content comprises survey identification, and the user dialect and the survey result of each question in the questionnaire.
8. The apparatus of claim 7, wherein the determining module is specifically configured to:
and when the question type of the current question is a selected question, matching the user dialect of the current question with a first sample answer library to obtain a questionnaire answer corresponding to the user dialect of the current question, wherein the first sample answer library comprises questionnaire answers of all options of the selected question.
9. The apparatus of claim 7, wherein the determining module is specifically configured to:
when the question type of the current question is a time question or a place question, matching the user dialect of the current question with a second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is the answer of the questionnaire of the current question; alternatively, the first and second electrodes may be,
matching the user dialect of the current question with a preset time regular expression or a preset place regular expression, if the matching is successful, obtaining the time or the place corresponding to the current question, and if the matching is unsuccessful, matching the user dialect of the current question with the second sample answer library to obtain the time or the place corresponding to the current question, wherein the time or the place corresponding to the current question is the answer of the questionnaire of the current question;
and the second sample answer library comprises preset answers of the time question and answer questions or the place question and answer questions.
10. The apparatus of claim 7, wherein the determining module is specifically configured to:
when the question type of the current question is a general question and answer question, taking the user's dialect of the current question as a survey result of the current question; or, performing similarity matching on the user dialect of the current question and a third sample answer library to obtain a score of the user dialect of the current question, where the scores of the user dialect and the user dialect of the current question are answers to the questionnaire of the current question, and the third sample answer library includes keywords or standard templates of answers to the general questionnaire.
11. The apparatus of any one of claims 7-10, further comprising:
the receiving module is also used for receiving the retrieval condition;
the query module is used for querying the stored survey contents of the questionnaires according to the retrieval conditions to obtain the survey contents of the target questionnaire meeting the retrieval conditions;
and the determining module is also used for determining a retrieval result according to the survey content of the target questionnaire and outputting the retrieval result.
12. The apparatus of any one of claims 7-10, further comprising:
an identification module for identifying a user's intraoperative intent of a current question;
the skipping module is used for skipping to a processing scene corresponding to a second intention when the user's dialect of the current question comprises the second intention except the intention pointed by the current question;
the receiving module is further used for receiving user dialogues input by the user in the processing scene corresponding to the second intention; receiving an end instruction, and ending the processing scene corresponding to the second intention according to the end instruction;
and the skipping module is further used for continuing to process the current problem after the processing scene corresponding to the second intention is finished.
13. An apparatus for questionnaire survey, comprising:
a memory for storing processor-executable instructions;
a processor for executing instructions of the method of questionnaire survey according to any one of the preceding claims 1 to 6 when the computer program is executed.
14. A computer-readable storage medium having stored thereon computer-executable instructions for implementing the method of questionnaire survey of any of claims 1-6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010038197.3A CN113190660A (en) | 2020-01-14 | 2020-01-14 | Questionnaire survey method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010038197.3A CN113190660A (en) | 2020-01-14 | 2020-01-14 | Questionnaire survey method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113190660A true CN113190660A (en) | 2021-07-30 |
Family
ID=76972935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010038197.3A Pending CN113190660A (en) | 2020-01-14 | 2020-01-14 | Questionnaire survey method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113190660A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115292458A (en) * | 2022-06-29 | 2022-11-04 | 北京梦天门科技股份有限公司 | Investigation information input method and system and electronic equipment |
| CN117373583A (en) * | 2023-10-10 | 2024-01-09 | 中国医学科学院肿瘤医院 | Intelligent medical treatment and big data medical treatment cloud platform based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108563384A (en) * | 2018-04-17 | 2018-09-21 | 泰康保险集团股份有限公司 | A kind of exchange method and relevant device based on questionnaire |
| CN109255697A (en) * | 2018-08-15 | 2019-01-22 | 普信恒业科技发展（北京）有限公司 | A kind of automatic credit estimation method and system based on artificial intelligence |
| CN110070333A (en) * | 2019-03-19 | 2019-07-30 | 平安普惠企业管理有限公司 | Intelligent questionnaire method, device, computer equipment and storage medium |
| CN110543550A (en) * | 2019-09-04 | 2019-12-06 | 上海智臻智能网络科技股份有限公司 | Method and device for automatically generating test questions |
-
2020
- 2020-01-14 CN CN202010038197.3A patent/CN113190660A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108563384A (en) * | 2018-04-17 | 2018-09-21 | 泰康保险集团股份有限公司 | A kind of exchange method and relevant device based on questionnaire |
| CN109255697A (en) * | 2018-08-15 | 2019-01-22 | 普信恒业科技发展（北京）有限公司 | A kind of automatic credit estimation method and system based on artificial intelligence |
| CN110070333A (en) * | 2019-03-19 | 2019-07-30 | 平安普惠企业管理有限公司 | Intelligent questionnaire method, device, computer equipment and storage medium |
| CN110543550A (en) * | 2019-09-04 | 2019-12-06 | 上海智臻智能网络科技股份有限公司 | Method and device for automatically generating test questions |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115292458A (en) * | 2022-06-29 | 2022-11-04 | 北京梦天门科技股份有限公司 | Investigation information input method and system and electronic equipment |
| CN117373583A (en) * | 2023-10-10 | 2024-01-09 | 中国医学科学院肿瘤医院 | Intelligent medical treatment and big data medical treatment cloud platform based on big data |
| CN117373583B (en) * | 2023-10-10 | 2024-05-07 | 中国医学科学院肿瘤医院 | Intelligent medical treatment and big data medical treatment cloud platform based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107038220B (en) | Method, intelligent robot and system for generating memorandum | |
| CN107798032B (en) | Method and device for processing response message in self-service voice conversation | |
| US9582757B1 (en) | Scalable curation system | |
| CN112492111B (en) | Intelligent voice outbound method, device, computer equipment and storage medium | |
| CN111177359A (en) | Multi-turn dialogue method and device | |
| CN110990685B (en) | Voiceprint-based voice searching method, voiceprint-based voice searching equipment, storage medium and storage device | |
| CN110135879B (en) | Customer service quality automatic scoring method based on natural language processing | |
| CN112037799A (en) | Voice interrupt processing method and device, computer equipment and storage medium | |
| CN111276148A (en) | Return visit method, system and storage medium based on convolutional neural network | |
| CN110781280A (en) | Knowledge graph-based voice assisting method and device | |
| CN111178081B (en) | Semantic recognition method, server, electronic device and computer storage medium | |
| CN113190660A (en) | Questionnaire survey method and device | |
| CN113297365A (en) | User intention determination method, device, equipment and storage medium | |
| CN112686051A (en) | Semantic recognition model training method, recognition method, electronic device, and storage medium | |
| CN116821290A (en) | Multitasking dialogue-oriented large language model training method and interaction method | |
| CN115509485A (en) | Filling-in method and device of business form, electronic equipment and storage medium | |
| CN111651554A (en) | Insurance question-answer method and device based on natural language understanding and processing | |
| CN117828057A (en) | Knowledge question-answering method, device, equipment and storage medium | |
| CN109684357B (en) | Information processing method and device, storage medium and terminal | |
| CN111723559A (en) | Real-time information extraction method and device | |
| CN114372476B (en) | Semantic truncation detection method, device, equipment and computer readable storage medium | |
| CN111970311B (en) | Session segmentation method, electronic device and computer readable medium | |
| CN114528851A (en) | Reply statement determination method and device, electronic equipment and storage medium | |
| CN114254088A (en) | Method for constructing automatic response model and automatic response method | |
| CN113868271A (en) | Method and device for updating knowledge base of intelligent customer service, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |