CN116484836B - Questionnaire generation system and method based on NLP model, electronic equipment and medium - Google Patents
Questionnaire generation system and method based on NLP model, electronic equipment and medium Download PDFInfo
- Publication number
- CN116484836B CN116484836B CN202310398053.2A CN202310398053A CN116484836B CN 116484836 B CN116484836 B CN 116484836B CN 202310398053 A CN202310398053 A CN 202310398053A CN 116484836 B CN116484836 B CN 116484836B
- Authority
- CN
- China
- Prior art keywords
- questionnaire
- data
- delivery
- user
- nlp model
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000003058 natural language processing Methods 0.000 description 40
- 238000011160 research Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 3
- 230000007115 recruitment Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000002453 shampoo Substances 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Library & Information Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a questionnaire generating system, a method, electronic equipment and a medium based on an NLP model, wherein the questionnaire generating method based on the NLP model comprises the following steps: acquiring a questionnaire, and acquiring data to be tested based on the questionnaire; inputting data to be tested into an NLP model to obtain a related idea set; populating a questionnaire based on the set of related ideas; the questionnaire is put in, and first user answer data of the questionnaire is obtained; generating a PK questionnaire based on the first user answer data; and putting the PK questionnaire, and acquiring second user answer data of the PK questionnaire. The questionnaire generation method based on the NLP model solves the problems that manual assistance is needed for generating questionnaires in the prior art, and the questionnaire generation method is time-consuming, tedious and low in efficiency.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a questionnaire generation system, a questionnaire generation method, electronic equipment and a questionnaire generation medium based on an NLP model.
Background
In the market research, the ideas of products, marketing and contents (similar to the human concentrated thinking and the public interests) are involved, then the generated ideas are subjected to data acquisition and analysis in a research mode, and a great deal of time is required to carry out manual conception, data analysis and other works on marketing contents before the market research, so that the time is consumed, the complexity is increased, and the efficiency is low.
And most enterprises do not have the capability of market research, and it is not clear how the market research should be performed.
Disclosure of Invention
The embodiment of the invention aims to provide a questionnaire generation system, a method, electronic equipment and a medium based on an NLP model, which are used for solving the problems that manual assistance is needed, time consumption is complex and efficiency is low in the generation of questionnaires in the prior art.
In order to achieve the above object, an embodiment of the present invention provides a questionnaire generating method based on an NLP model, which specifically includes:
acquiring a questionnaire, and acquiring data to be tested based on the questionnaire;
inputting data to be tested into an NLP model to obtain a related idea set;
populating a questionnaire based on the set of related ideas;
the questionnaire is put in, first user answer data of the questionnaire are obtained, and a PK questionnaire is generated based on the first user answer data;
and putting the PK questionnaire, and acquiring second user answer data of the PK questionnaire.
Based on the technical scheme, the invention can also be improved as follows:
further, the inputting the data to be tested into the NLP model to obtain the related idea set includes:
comparing and screening the data to be tested with the data in the historical database, and determining the matching degree of the data to be tested and the data in the historical database;
and extracting all relevant data in the historical database based on the matching degree to obtain a relevant idea set.
Further, the filling of the questionnaire based on the set of related ideas includes:
pre-constructing a customized API interface between the NLP model and the questionnaire system;
and establishing network connection between the NLP model and a questionnaire system based on the customized API interface.
Further, the step of putting the questionnaire and acquiring first user answer data of the questionnaire includes:
and determining a release mode based on the questionnaire, wherein the setting of the release mode comprises setting at least one of personalized release, release frequency and release time of a user.
Further, the step of delivering the PK questionnaire and obtaining second user answer data of the PK questionnaire includes:
and checking the content capable of generating the concept card based on the user question and answer data, and automatically generating the PK questionnaire based on the checked content.
Further, the step of delivering the PK questionnaire, and obtaining second user answer data of the PK questionnaire, further comprises:
determining a delivery mode based on the PK questionnaire, wherein the setting of the delivery mode comprises setting at least one of personalized delivery, delivery frequency and delivery time of a user;
a user net recommendation value is calculated based on the second user answer data.
A questionnaire generation system based on an NLP model, comprising:
the first acquisition module is used for acquiring a questionnaire and acquiring data to be tested based on the questionnaire;
the NLP model is used for receiving the data to be tested and obtaining a related idea set;
a filling module for filling a questionnaire based on the set of related ideas;
the releasing module is used for releasing the questionnaires and the PK questionnaires;
and the second acquisition module is used for acquiring first user answer data of the questionnaire, generating a PK questionnaire based on the first user answer data, and acquiring second user answer data of the PK questionnaire.
Further, the NLP model includes ChatGPT, AIGC and Bard.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method when the computer program is executed.
A non-transitory computer readable medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method.
The embodiment of the invention has the following advantages:
according to the questionnaire generation method based on the NLP model, a questionnaire is acquired, and data to be tested are acquired based on the questionnaire; inputting data to be tested into an NLP model to obtain a related idea set; populating a questionnaire based on the set of related ideas; the questionnaire is put in, first user answer data of the questionnaire are obtained, and a PK questionnaire is generated based on the first user answer data; the PK questionnaire is put in, and second user answer data of the PK questionnaire is obtained; the method solves the problems that manual assistance is needed for generating the questionnaire in the prior art, and the method is time-consuming, tedious and low in efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those skilled in the art from this disclosure that the drawings described below are merely exemplary and that other embodiments may be derived from the drawings provided without undue effort.
The structures, proportions, sizes, etc. shown in the present specification are shown only for the purposes of illustration and description, and are not intended to limit the scope of the invention, which is defined by the claims, but rather by the claims.
FIG. 1 is a flow chart of a questionnaire generation method based on NLP model of the present invention;
FIG. 2 is a block diagram of an NLP model-based questionnaire generation system of the present invention;
fig. 3 is a schematic diagram of an entity structure of an electronic device according to the present invention.
Wherein the reference numerals are as follows:
a first acquisition module 10, an nlp model 20, a filling module 30, a delivery module 40, a second acquisition module 50, an electronic device 60, a processor 601, a memory 602, a bus 603.
Detailed Description
Other advantages and advantages of the present invention will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples
Fig. 1 is a flowchart of an embodiment of a questionnaire generating method based on an NLP model, and as shown in fig. 1, the questionnaire generating method based on an NLP model provided by the embodiment of the invention includes the following steps:
s101, acquiring a questionnaire, and acquiring data to be tested based on the questionnaire;
specifically, obtaining data to be tested in a questionnaire;
for example: the data to be tested are obtained from the questionnaire as follows: please write out ten scenes you will pay special attention to the shampoo.
S102, inputting data to be tested into an NLP model to obtain a related idea set;
specifically, the NLP (Natural Language Processing) model is a natural language processing model, and the NLP model 20 is a branch subject in the fields of artificial intelligence and linguistics, and can mine information and knowledge contained in natural language text. Common applications include:
text classification: the method is suitable for scenes such as news tag marking, emotion analysis, text content anti-spam, commodity evaluation classification and the like.
Text matching: the method is suitable for scenes such as question-answer matching, sentence similarity matching, natural language reasoning, dialogue retrieval and the like.
Text generation: the method is suitable for scenes such as news headline generation, news abstract generation, content abstract generation, poetry creation, intelligent auxiliary creation and the like.
Sequence labeling: the method is suitable for scenes such as NER recognition and emotion word extraction of named entities.
Feature extraction: the extracted text features may be subjected to subsequent operations in the text field or in combination with other fields (e.g., computer vision).
In this embodiment:
comparing and screening the data to be tested with the data in the historical database, and determining the matching degree of the data to be tested and the data in the historical database;
and extracting all relevant data in the historical database based on the matching degree to obtain a relevant idea set.
For example: based on please write out ten scenes you will pay special attention to washing the hair;
obtaining a related idea set, wherein the related idea set is as follows:
1. preparing to participate in important occasions such as weddings, parties, dinner parties and the like;
2. preparing a bench performance, publishing a lecture and the like;
3. preparing to take part in annual end examination, professional authentication examination and the like;
4. working face test;
5. when a passenger takes an airplane, sits on a train and travels by taking a car;
6. preparing important steps such as submitting important files, applying and the like;
7. preparing to participate in an important meeting;
8. taking an examination;
9. preparing for application work or school recruitment examination;
10. preparing for affinity.
S103, filling a questionnaire based on the related ideas set;
in particular, the API (Application Programming Interface ) is a number of predefined functions that are intended to provide the application and developer the ability to access a set of routines based on certain software or hardware without having to access source code or understand the details of the internal operating mechanisms. An API refers to an application program interface, and also refers to an API description document, which is also called a help document.
Pre-building a custom API interface between the NLP model 20 and a questionnaire system;
a network connection between the NLP model 20 and a questionnaire system is established based on the custom API interface.
Set of related ideas: 1. preparing to participate in important occasions such as weddings, parties, dinner parties and the like; 2. preparing a bench performance, publishing a lecture and the like; 3. preparing to take part in annual end examination, professional authentication examination and the like; 4. working face test; 5. when a passenger takes an airplane, sits on a train and travels by taking a car; 6. preparing important steps such as submitting important files, applying and the like; 7. preparing to participate in an important meeting; 8. taking an examination; 9. preparing for application work or school recruitment examination; 10. the relatives are prepared and filled into the questionnaire.
S104, putting in a questionnaire, acquiring first user response data of the questionnaire, and generating a PK questionnaire based on the first user response data;
specifically, a delivery mode is determined based on the questionnaire, and setting of the delivery mode includes setting at least one of personalized delivery, delivery frequency and delivery time of a user.
And checking the content capable of generating the concept card based on the user question and answer data, and automatically generating the PK questionnaire based on the checked content.
The throwing crowd comprises: the whole-network crowd, young villages, white collar of cities, blue collar of cities and middle-aged and elderly villages;
preferably; preparing to participate in important occasions such as weddings, parties, dinner parties and the like based on the user question-answer data from 1; 2. preparing a bench performance, publishing a lecture and the like; 3. preparing to take part in annual end examination, professional authentication examination and the like; 4. working face test; 5. when a passenger takes an airplane, sits on a train and travels by taking a car; 6. preparing important steps such as submitting important files, applying and the like; 7. preparing to participate in an important meeting; 8. taking an examination; 9. preparing for application work or school recruitment examination; 10. preparing a relatives review to generate the content of the concept card to obtain 1. Preparing important occasions such as weddings, parties, dinner parties and the like; 2. preparing a bench performance, publishing a lecture and the like; 3. three pieces of checking content such as annual end examination, professional authentication examination and the like are prepared to be participated in, and a PK questionnaire is generated based on the checking content.
The PK questionnaire is put in, and first user answer data of the PK questionnaire is obtained;
s105, the PK questionnaire is put in, and second user response data of the PK questionnaire is obtained.
A net user recommendation value is calculated based on the first user answer data.
According to the questionnaire generating method based on the NLP model, a questionnaire is acquired, and data to be tested are acquired based on the questionnaire; inputting data to be tested into the NLP model 20 to obtain a related idea set; populating a questionnaire based on the set of related ideas; the questionnaire is put in, first user answer data of the questionnaire are obtained, and a PK questionnaire is generated based on the first user answer data; and putting the PK questionnaire, and acquiring second user answer data of the PK questionnaire. The method solves the problems that manual assistance is needed for generating the questionnaire in the prior art, and the method is time-consuming, tedious and low in efficiency.
The invention relates to a method for generating various related ideas on products, marketing and contents through conversations by using AI such as ChatGPT and the like, then importing the various related ideas generated by AI into a questionnaire system through API, wherein part or all of the related ideas can be selected in the questionnaire system, and the selected related ideas can be automatically filled into questions or options of the questionnaire, so that the related ideas can be immediately used for market research. The patent is an innovative technology, is helpful for improving the questionnaire generation efficiency, and can provide more originals and ideas to support market research.
Various ideas related to product and marketing are generated using Natural Language Processing (NLP) models, such as ChatGPT. The generated ideas are integrated into the questionnaire system through the API as questions or options. The questionnaire system may be used for market research and the like. Integrating the generated ideas into a questionnaire system allows more efficient and automatic marketing research and data collection.
FIG. 2 is a flowchart of an embodiment of a NLP model-based questionnaire generation system of the present invention; as shown in fig. 2, the questionnaire generating system based on the NLP model provided by the embodiment of the invention includes the following steps:
a first acquisition module 10 for acquiring a questionnaire and acquiring data to be tested based on the questionnaire;
the NLP model 20 is used for receiving the data to be tested and obtaining a related idea set;
a filling module 30 for filling a questionnaire based on the set of related ideas;
a delivery module 40 for delivering the questionnaire and PK questionnaire;
a second obtaining module 50, configured to obtain first user answer data of the questionnaire, generate a PK questionnaire based on the first user answer data, and obtain second user answer data of the PK questionnaire.
The NLP model 20 includes ChatGPT, AIGC and Bard.
The NLP model 20 is also used to:
comparing and screening the data to be tested with the data in the historical database, and determining the matching degree of the data to be tested and the data in the historical database;
and extracting all relevant data in the historical database based on the matching degree to obtain a relevant idea set.
The filling module 30 is further configured to:
pre-building a custom API interface between the NLP model 20 and a questionnaire system;
a network connection between the NLP model 20 and a questionnaire system is established based on the custom API interface.
The delivery module 40 is further configured to:
and determining a release mode based on the questionnaire, wherein the setting of the release mode comprises setting at least one of personalized release, release frequency and release time of a user.
The second acquisition module 50 is further configured to:
and checking the content capable of generating the concept card based on the user question and answer data, and automatically generating the PK questionnaire based on the checked content.
The delivery module 40 is further configured to:
releasing the PK questionnaire; determining a delivery mode based on the PK questionnaire, wherein the setting of the delivery mode comprises setting at least one of personalized delivery, delivery frequency and delivery time of a user;
the second acquisition module 50 is further configured to:
a user net recommendation value is calculated based on the second user answer data.
According to the questionnaire generating system based on the NLP model, a first acquisition module 10 acquires a questionnaire, and acquires data to be tested based on the questionnaire; receiving the data to be tested through the NLP model 20 to obtain a related idea set; populating, by a populating module 30, a questionnaire based on the set of related ideas; the questionnaire and PK questionnaire are launched by launch module 40; first user answer data of the questionnaire is acquired by a second acquisition module 50, a PK questionnaire is generated based on the first user answer data, and second user answer data of the PK questionnaire is acquired. The questionnaire generation method based on the NLP model solves the problems that manual assistance is needed for generating questionnaires in the prior art, and the questionnaire generation method is time-consuming, tedious and low in efficiency.
Fig. 3 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention, as shown in fig. 3, an electronic device 60 includes: a processor 601 (processor), a memory 602 (memory), and a bus 603;
wherein, the processor 601 and the memory 602 complete communication with each other through the bus 603;
the processor 601 is configured to invoke program instructions in the memory 602 to perform the methods provided by the method embodiments described above, including, for example: acquiring a questionnaire, and acquiring data to be tested based on the questionnaire; inputting data to be tested into the NLP model 20 to obtain a related idea set; populating a questionnaire based on the set of related ideas; the questionnaire is put in, first user answer data of the questionnaire are obtained, and a PK questionnaire is generated based on the first user answer data; and putting the PK questionnaire, and acquiring second user answer data of the PK questionnaire.
The present embodiment provides a non-transitory computer readable medium storing computer instructions that cause a computer to perform the methods provided by the above-described method embodiments, for example, including: acquiring a questionnaire, and acquiring data to be tested based on the questionnaire; inputting data to be tested into the NLP model 20 to obtain a related idea set; populating a questionnaire based on the set of related ideas; the questionnaire is put in, first user answer data of the questionnaire are obtained, and a PK questionnaire is generated based on the first user answer data; and putting the PK questionnaire, and acquiring second user answer data of the PK questionnaire.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable medium, where the program when executed performs steps including the above method embodiments; and the aforementioned medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable medium such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the embodiments or the methods of some parts of the embodiments.
While the invention has been described in detail in the foregoing general description and specific examples, it will be apparent to those skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (4)
1. The questionnaire generation method based on the NLP model is characterized by comprising the following steps of:
acquiring a questionnaire, and acquiring data to be tested based on the questionnaire;
inputting data to be tested into an NLP model to obtain a related idea set; wherein the NLP model comprises ChatGPT, AIGC and Bard;
comparing and screening the data to be tested with the data in the historical database, and determining the matching degree of the data to be tested and the data in the historical database;
extracting all relevant data in the historical database based on the matching degree to obtain a relevant idea set;
populating a questionnaire based on the set of related ideas;
pre-constructing a customized AP I interface between the NLP model and a questionnaire system;
establishing a network connection between the NLP model and a questionnaire system based on the customized API interface;
the questionnaire is put in, first user answer data of the questionnaire are obtained, and a PK questionnaire is generated based on the first user answer data;
determining a delivery mode based on the questionnaire, wherein the setting of the delivery mode comprises setting at least one of personalized delivery, delivery frequency and delivery time of a user;
the PK questionnaire is put in, and second user answer data of the PK questionnaire is obtained;
selecting the content of the generated concept card based on the second user question and answer data, and automatically generating a PK questionnaire based on the selected content;
determining a delivery mode based on the PK questionnaire, wherein the setting of the delivery mode comprises setting at least one of personalized delivery, delivery frequency and delivery time of a user;
a user net recommendation value is calculated based on the second user answer data.
2. A questionnaire generation system based on an NLP model, comprising:
the first acquisition module is used for acquiring a questionnaire and acquiring data to be tested based on the questionnaire;
the NLP model is used for receiving the data to be tested to obtain a related idea set, wherein the NLP model comprises ChatGPT, AIGC and Bard;
the NLP model is also used to:
comparing and screening the data to be tested with the data in the historical database, and determining the matching degree of the data to be tested and the data in the historical database;
extracting all relevant data in the historical database based on the matching degree to obtain a relevant idea set;
a filling module for filling a questionnaire based on the set of related ideas;
the filling module is also for:
pre-constructing a customized AP I interface between the NLP model and a questionnaire system;
establishing network connection between the NLP model and a questionnaire system based on the customized AP I interface;
the releasing module is used for releasing the questionnaires and the PK questionnaires;
the delivery module is also used for:
determining a delivery mode based on the questionnaire, wherein the setting of the delivery mode comprises setting at least one of personalized delivery, delivery frequency and delivery time of a user;
the second acquisition module is used for acquiring first user answer data of the questionnaire, generating a PK questionnaire based on the first user answer data, and acquiring second user answer data of the PK questionnaire;
the second acquisition module is further configured to:
selecting the content of the generated concept card based on the second user question and answer data, and automatically generating a PK questionnaire based on the selected content;
determining a delivery mode based on the PK questionnaire, wherein the setting of the delivery mode comprises setting at least one of personalized delivery, delivery frequency and delivery time of a user;
a user net recommendation value is calculated based on the second user answer data.
3. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method as claimed in claim 1 when executing the computer program.
4. A non-transitory computer readable medium, on which a computer program is stored, which when executed by a processor implements the steps of the method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310398053.2A CN116484836B (en) | 2023-04-14 | 2023-04-14 | Questionnaire generation system and method based on NLP model, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310398053.2A CN116484836B (en) | 2023-04-14 | 2023-04-14 | Questionnaire generation system and method based on NLP model, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116484836A CN116484836A (en) | 2023-07-25 |
| CN116484836B true CN116484836B (en) | 2023-11-24 |
Family
ID=87222519
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310398053.2A Active CN116484836B (en) | 2023-04-14 | 2023-04-14 | Questionnaire generation system and method based on NLP model, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116484836B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117667979B (en) * | 2023-12-08 | 2024-07-05 | 暨南大学 | Data mining method, device, equipment and medium based on large language model |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011028517A (en) * | 2009-07-24 | 2011-02-10 | Nomura Research Institute Ltd | Questionnaire survey conducting apparatus and method |
| CN108428152A (en) * | 2018-03-12 | 2018-08-21 | 平安科技（深圳）有限公司 | questionnaire generation method, server and computer readable storage medium |
| CN115511556A (en) * | 2022-08-22 | 2022-12-23 | 网易（杭州）网络有限公司 | Questionnaire processing method and device, electronic equipment and storage medium |
| CN115526659A (en) * | 2022-09-22 | 2022-12-27 | 中国平安财产保险股份有限公司 | Data analysis method, device, equipment and storage medium based on questionnaire |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140229199A1 (en) * | 2011-06-20 | 2014-08-14 | Timewyse Corporation | System and method for dynamic and customized questionnaire generation |
-
2023
- 2023-04-14 CN CN202310398053.2A patent/CN116484836B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011028517A (en) * | 2009-07-24 | 2011-02-10 | Nomura Research Institute Ltd | Questionnaire survey conducting apparatus and method |
| CN108428152A (en) * | 2018-03-12 | 2018-08-21 | 平安科技（深圳）有限公司 | questionnaire generation method, server and computer readable storage medium |
| CN115511556A (en) * | 2022-08-22 | 2022-12-23 | 网易（杭州）网络有限公司 | Questionnaire processing method and device, electronic equipment and storage medium |
| CN115526659A (en) * | 2022-09-22 | 2022-12-27 | 中国平安财产保险股份有限公司 | Data analysis method, device, equipment and storage medium based on questionnaire |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116484836A (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10878197B2 (en) | Self-learning user interface with image-processed QA-pair corpus | |
| CN109034069B (en) | Method and apparatus for generating information | |
| CN111652232A (en) | Bill identification method and device, electronic equipment and computer readable storage medium | |
| CN113705733A (en) | Medical bill image processing method and device, electronic device and storage medium | |
| CN116484836B (en) | Questionnaire generation system and method based on NLP model, electronic equipment and medium | |
| CN110765256A (en) | Method and equipment for generating online legal consultation automatic reply | |
| CN109101956B (en) | Method and apparatus for processing image | |
| CN117995373A (en) | Hospital ward record generation method and device, electronic equipment and storage medium | |
| CN116992847A (en) | Financial report processing method, device, system and medium | |
| CN110929519B (en) | Entity attribute extraction method and device | |
| CN112328812B (en) | Domain knowledge extraction method and system based on self-adjusting parameters and electronic equipment | |
| CN115934904A (en) | Text processing method and device | |
| CN111882419B (en) | Method and device for quality inspection of files and server | |
| CN113901793A (en) | Event extraction method and device combining RPA and AI | |
| CN111723188A (en) | Sentence display method and electronic equipment based on artificial intelligence for question-answering system | |
| CN112131379A (en) | Method, device, electronic equipment and storage medium for identifying problem category | |
| CN113361282A (en) | Information processing method and device | |
| CN111553168A (en) | Bilingual short text matching method | |
| CN110443202A (en) | Paper font carefully and neatly spends instant analysis platform, method and storage medium | |
| CN117667979B (en) | Data mining method, device, equipment and medium based on large language model | |
| CN118071310B (en) | Business processing method and system based on flow engine | |
| CN117522485B (en) | Advertisement recommendation method, device, equipment and computer readable storage medium | |
| CN114328870A (en) | Reply message generation method, system and device | |
| AlBar et al. | Business process modeling notation for MEASUR's Semantic Analysis | |
| CN116842930A (en) | Automatic processing method, device, system and medium for banking data |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |