CN113626575A - Intelligent recommendation method based on user question answering - Google Patents
Intelligent recommendation method based on user question answering Download PDFInfo
- Publication number
- CN113626575A CN113626575A CN202111022627.3A CN202111022627A CN113626575A CN 113626575 A CN113626575 A CN 113626575A CN 202111022627 A CN202111022627 A CN 202111022627A CN 113626575 A CN113626575 A CN 113626575A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- method based
- current
- recommendation method
- 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 20
- 230000011218 segmentation Effects 0.000 claims abstract description 25
- 230000008451 emotion Effects 0.000 claims description 7
- 230000003542 behavioural effect Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 10
- 230000002996 emotional effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013499 data model 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/268—Morphological analysis
-
- 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
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Mathematical Physics (AREA)
- Remote Sensing (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an intelligent recommendation method based on user question answering, which comprises the following steps: step one, a user terminal obtains a question and answer of a user by providing an input box; secondly, the back-end service system analyzes the data of the current user through NLP word segmentation and a data buried point interface; step three, judging whether the part of speech, the data tag and the content of the knowledge base of the current word are matched and hit; if yes, acquiring recommended content from the recommended resource pool according to the algorithm capacity of the big data in the matching resource pool, and returning the recommended content to the user side in cooperation with the content of the knowledge base; if not, directly returning the question-answer knowledge base of the user to the user side. The method has the advantage that the recommendation is accurate.
Description
Technical Field
The invention relates to an intelligent recommendation method based on user question answering.
Background
In the current travel scene, the intelligent recommendation of users of the online system is mostly based on the behavior data and the favorite label data of the users as an important data model of the user recommendation system. The behavior data of the user is collected, stored and analyzed through a point burying technology in the service system, the actual service of the online system is combined, the data content helpful to the user is recommended online through the existing capacity of big data, and the user can perceive the information of the system to be intelligent.
However, such approaches have drawbacks: on one hand, intelligent recommendation completely depends on online behaviors of users, including events such as clicking, browsing and the like, and when a large data field needs to store a large enough data volume, a bottom layer data algorithm can accurately recommend according to user behavior data. On the other hand, the real-time performance and the accuracy of the intelligent recommendation cannot be applied to each public user, different users can generate the recommendation according to own behavior data, and a bottom-layer algorithm model is not universal to a certain extent. Considering the reason of combining the two aspects, the current intelligent recommendation has a great improvement space to a certain extent so as to promote the system recommendation to be more accurate.
Disclosure of Invention
The invention aims to provide an intelligent recommendation method based on user question answering, which aims to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
an intelligent recommendation method based on user question answering comprises the following steps:
step one, a user terminal obtains a question and answer of a user by providing an input box;
secondly, the back-end service system analyzes the data of the current user through NLP word segmentation and a data buried point interface;
step three, judging whether the part of speech, the data tag and the content of the knowledge base of the current word are matched and hit;
if yes, acquiring recommended content from the recommended resource pool according to the algorithm capacity of the big data in the matching resource pool, and returning the recommended content to the user side in cooperation with the content of the knowledge base;
if not, directly returning the question-answer knowledge base of the user to the user side.
As a further scheme of the invention: in the second step, the back-end service system carries out multi-dimensional splitting according to the current user terminal input data.
As a further scheme of the invention: the multi-dimensional splitting of the user input data comprises: NLP word segmentation, SLB geographic position identification, data embedding point and tag data matching.
As a further scheme of the invention: segmenting words of a current user question and answer sentence through an NLP word segmentation tool, acquiring the part of speech of a consultation sentence of a user for system resources at present, and sensing the emotion and the final core word of the current user according to the part of speech
As a further scheme of the invention: when a user opens a software terminal to ask and answer, the real-time longitude and latitude of the current user are obtained, the geographic position of the user is obtained through the electronic fence of the system and a public service API (application program interface) based on the map SLB, and meanwhile, whether the current user is in a scenic spot or not is judged according to the data of the electronic fence.
As a further scheme of the invention: in addition to the guest's question and answer data, the system's data site will also collect guest behavior data.
As a further scheme of the invention: collecting the guest behavior data includes: dwell time, user equipment and system.
As a further scheme of the invention: and presetting a resource tag by a management end system in advance, matching and collecting the tag system and the content word segmentation of the question and answer of the user, and finally entering a tag resource pool.
As a further scheme of the invention: the dimension data obtained by splitting comprises the following steps: user segmentation, emotion part of speech, SLB geographic location, user equipment, behavioral data, and tag matching data.
As a further scheme of the invention: in the third step, the step of providing a decision for the recommendation algorithm according to whether the part of speech, the data tag and the knowledge base content of the current participle are matched and hit or not is carried out, and the step comprises the following steps:
step 3.1, finally, determining the data boundary of the system resource library through word segmentation and the resource library label, and selecting out the resource content conforming to the recommendation;
step 3.2, analyzing the dimensionality through the buried point data and the equipment data of the user to analyze the favorite category of the current user, and combining the favorite category with the recommended resources obtained in the step 3.1;
and 3.3, judging the current geographical position of the user, and finally providing recommended resources with the maximum probability according with the user preference to the user by combining the label dimension data of the data resources.
Compared with the prior art, the invention has the beneficial effects that: the recommendation is accurate.
And providing accurate real-time content recommendation for the user by combining a user question-answer word segmentation technology and a data point burying technology and combining an SLB geographical position label.
By adding the user semantic input module, the bottom layer carries out word segmentation through NLP (non-line language) semantics, and the accuracy of the recommendation system is comprehensively provided based on the emotional part of speech of the current user and the geographic information of the user.
Drawings
Fig. 1 is a flowchart of an intelligent recommendation method based on user question answering according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, in the embodiment of the present invention, an intelligent recommendation method based on user question answering includes the following steps:
step one, a user terminal obtains a question and answer of a user by providing an input box;
secondly, the back-end service system analyzes the data of the current user through NLP word segmentation and a data buried point interface;
step three, judging whether the part of speech, the data tag and the content of the knowledge base of the current word are matched and hit;
if yes, acquiring recommended content from the recommended resource pool according to the algorithm capacity of the big data in the matching resource pool, and returning the recommended content to the user side in cooperation with the content of the knowledge base;
if not, directly returning the question-answer knowledge base of the user to the user side.
Specifically, the back-end service system analyzes the emotion part of speech, the geographic position, the data label and other dimension data of the current user.
As a specific implementation manner, in step two, the backend service system performs multidimensional splitting according to the current data input by the user terminal. The multi-dimensional splitting of the user input data comprises: NLP word segmentation, SLB geographic position identification, data embedding point and tag data matching.
NLP word segmentation: through an NLP word segmentation tool, word segmentation is carried out on a current question and answer sentence of a user, the part of speech of a consultation sentence of the user for system resources at present is obtained, and the emotion and the final core word of the current user can be sensed according to the part of speech.
SLB geographical location identification: when a user opens a software terminal to ask and answer, the real-time longitude and latitude of the current user are obtained, the geographic position of the user is obtained through an electronic fence of the system and a public service AP I interface based on a map SLB, and meanwhile, important dimension data such as whether the current user is in a scenic spot or not is judged according to electronic fence data.
Data embedding: in addition to the guest's question and answer data, the system's data site will also collect guest behavior data. Collecting the guest behavior data includes: residence time, user equipment and system, etc.
Matching label data: and presetting a resource tag by a management end system in advance, matching and collecting the tag system and the content word segmentation of the question and answer of the user, and finally entering a tag resource pool.
In a preferred embodiment, in step three, through the previous multidimensional data splitting, the system has accumulated the dimensional data of multiple parties, and the dimensional data obtained by splitting includes: user segmentation, emotional part-of-speech, SLB geographic location, user equipment, behavioral data, and tag matching data, among others. And finally providing a decision for a recommendation algorithm according to the data.
In the third step, the step of providing a decision for the recommendation algorithm according to whether the part of speech, the data tag and the knowledge base content of the current participle are matched and hit or not is carried out, and the step comprises the following steps:
step 3.1, finally, determining the data boundary of the system resource library through word segmentation and the resource library label, and selecting out the resource content conforming to the recommendation;
step 3.2, analyzing the dimensionality through the buried point data and the equipment data of the user to analyze the favorite category of the current user, and combining the favorite category with the recommended resources obtained in the step 3.1;
and 3.3, judging the current geographical position of the user, and finally providing recommended resources with the maximum probability according with the user preference to the user by combining the label dimension data of the data resources.
The method comprises the steps of obtaining a question of a current user through question and answer input, obtaining a real-time longitude and latitude geographic position of the current user by combining the capacity of terminal equipment, and finally obtaining an emotion part of speech for problem NLP word segmentation of the user through collecting and analyzing behavior data of the user by a bottom layer data service. And triggering the recommended content matched with the resource library by combining the geographical position information of the current user, and comprehensively returning the recommended content to the user terminal by combining the answers of the knowledge library. Dynamic combination of question answering and recommendation is achieved.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (10)
1. An intelligent recommendation method based on user question answering is characterized by comprising the following steps:
step one, a user terminal obtains a question and answer of a user by providing an input box;
secondly, the back-end service system analyzes the data of the current user through NLP word segmentation and a data buried point interface;
step three, judging whether the part of speech, the data tag and the content of the knowledge base of the current word are matched and hit;
if yes, acquiring recommended content from the recommended resource pool according to the algorithm capacity of the big data in the matching resource pool, and returning the recommended content to the user side in cooperation with the content of the knowledge base;
if not, directly returning the question-answer knowledge base of the user to the user side.
2. The intelligent recommendation method based on user question answering of claim 1,
in the second step, the back-end service system carries out multi-dimensional splitting according to the current user terminal input data.
3. The intelligent recommendation method based on user question answering according to claim 2,
the multi-dimensional splitting of the user input data comprises: NLP word segmentation, SLB geographic position identification, data embedding point and tag data matching.
4. The intelligent recommendation method based on user question answering according to claim 3,
through an NLP word segmentation tool, word segmentation is carried out on a current question and answer sentence of a user, the part of speech of a consultation sentence of the user for system resources at present is obtained, and the emotion and the final core word of the current user can be sensed according to the part of speech.
5. The intelligent recommendation method based on user question answering according to claim 3,
when a user opens a software terminal to ask and answer, the real-time longitude and latitude of the current user are obtained, the geographic position of the user is obtained through the electronic fence of the system and a public service API (application program interface) based on the map SLB, and meanwhile, whether the current user is in a scenic spot or not is judged according to the data of the electronic fence.
6. The intelligent recommendation method based on user question answering according to claim 3,
in addition to the guest's question and answer data, the system's data site will also collect guest behavior data.
7. The intelligent recommendation method based on user question answering according to claim 6,
collecting the guest behavior data includes: dwell time, user equipment and system.
8. The intelligent recommendation method based on user question answering according to claim 3,
and presetting a resource tag by a management end system in advance, matching and collecting the tag system and the content word segmentation of the question and answer of the user, and finally entering a tag resource pool.
9. The intelligent recommendation method based on user question answering according to claim 2,
the dimension data obtained by splitting comprises the following steps: user segmentation, emotion part of speech, SLB geographic location, user equipment, behavioral data, and tag matching data.
10. The intelligent recommendation method based on user question answering according to claim 1,
in the third step, the step of providing a decision for the recommendation algorithm according to whether the part of speech, the data tag and the knowledge base content of the current participle are matched and hit or not is carried out, and the step comprises the following steps:
step 3.1, finally, determining the data boundary of the system resource library through word segmentation and the resource library label, and selecting out the resource content conforming to the recommendation;
step 3.2, analyzing the dimensionality through the buried point data and the equipment data of the user to analyze the favorite category of the current user, and combining the favorite category with the recommended resources obtained in the step 3.1;
and 3.3, judging the current geographical position of the user, and finally providing recommended resources with the maximum probability according with the user preference to the user by combining the label dimension data of the data resources.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111022627.3A CN113626575A (en) | 2021-09-01 | 2021-09-01 | Intelligent recommendation method based on user question answering |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111022627.3A CN113626575A (en) | 2021-09-01 | 2021-09-01 | Intelligent recommendation method based on user question answering |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113626575A true CN113626575A (en) | 2021-11-09 |
Family
ID=78388754
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111022627.3A Pending CN113626575A (en) | 2021-09-01 | 2021-09-01 | Intelligent recommendation method based on user question answering |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113626575A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102722558A (en) * | 2012-05-29 | 2012-10-10 | 百度在线网络技术(北京)有限公司 | User question recommending method and device |
CN107862553A (en) * | 2017-11-15 | 2018-03-30 | 平安科技(深圳)有限公司 | Advertisement real-time recommendation method, device, terminal device and storage medium |
WO2019019554A1 (en) * | 2017-07-26 | 2019-01-31 | 北京三快在线科技有限公司 | Method and apparatus for obtaining recommendation information, and electronic device |
CN109508426A (en) * | 2018-12-21 | 2019-03-22 | 深圳市智搜信息技术有限公司 | A kind of intelligent recommendation method and its system and storage medium based on physical environment |
CN109885672A (en) * | 2019-03-04 | 2019-06-14 | 中国科学院软件研究所 | A kind of question and answer mode intelligent retrieval system and method towards online education |
CN110992215A (en) * | 2019-12-10 | 2020-04-10 | 浙江力石科技股份有限公司 | Semantic analysis-based travel service recommendation system, database and recommendation method |
CN112506975A (en) * | 2020-11-30 | 2021-03-16 | 橙脑教育科技(上海)有限公司 | Information recommendation method, device and system |
-
2021
- 2021-09-01 CN CN202111022627.3A patent/CN113626575A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102722558A (en) * | 2012-05-29 | 2012-10-10 | 百度在线网络技术(北京)有限公司 | User question recommending method and device |
WO2019019554A1 (en) * | 2017-07-26 | 2019-01-31 | 北京三快在线科技有限公司 | Method and apparatus for obtaining recommendation information, and electronic device |
CN107862553A (en) * | 2017-11-15 | 2018-03-30 | 平安科技(深圳)有限公司 | Advertisement real-time recommendation method, device, terminal device and storage medium |
CN109508426A (en) * | 2018-12-21 | 2019-03-22 | 深圳市智搜信息技术有限公司 | A kind of intelligent recommendation method and its system and storage medium based on physical environment |
CN109885672A (en) * | 2019-03-04 | 2019-06-14 | 中国科学院软件研究所 | A kind of question and answer mode intelligent retrieval system and method towards online education |
CN110992215A (en) * | 2019-12-10 | 2020-04-10 | 浙江力石科技股份有限公司 | Semantic analysis-based travel service recommendation system, database and recommendation method |
CN112506975A (en) * | 2020-11-30 | 2021-03-16 | 橙脑教育科技(上海)有限公司 | Information recommendation method, device and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109145204B (en) | Portrait label generation and use method and system | |
CN110472066B (en) | Construction method of urban geographic semantic knowledge map | |
CN111694965B (en) | Image scene retrieval system and method based on multi-mode knowledge graph | |
CN111640436B (en) | Method for providing dynamic customer portraits of conversation objects to agents | |
CN110781280A (en) | Knowledge graph-based voice assisting method and device | |
CN110399448A (en) | Chinese Place Names address searching matching process, terminal, computer readable storage medium | |
CN110990651B (en) | Address data processing method and device, electronic equipment and computer readable medium | |
CN113468300B (en) | Intelligent message processing system and method based on WeChat interaction | |
CN115827882A (en) | Knowledge graph construction method based on multi-mode tourism big data | |
CN111916110B (en) | Voice quality inspection method and device | |
CN110895587A (en) | Method and device for determining target user | |
CN113626575A (en) | Intelligent recommendation method based on user question answering | |
CN113590771A (en) | Data mining method, device, equipment and storage medium | |
CN111933133A (en) | Intelligent customer service response method and device, electronic equipment and storage medium | |
CN110516236B (en) | Social short text fine-grained emotion acquisition method | |
KR101110026B1 (en) | Apparatus and method for searching local information | |
CN111092764A (en) | Real-time dynamic intimacy relationship analysis method and system | |
CN111177494A (en) | Semantic analysis method in voice interaction based on weather | |
CN112685618A (en) | User feature identification method and device, computing equipment and computer storage medium | |
CN111949781B (en) | Intelligent interaction method and device based on natural sentence syntactic analysis | |
CN112330387A (en) | Virtual broker applied to house-watching software | |
CN113468306A (en) | Voice conversation method, device, electronic equipment and storage medium | |
CN113011919B (en) | Method and device for identifying object of interest, recommendation method, medium and electronic equipment | |
CN106157651B (en) | A kind of traffic radio traffic information broadcasting system based on voice semantic understanding | |
CN116992111B (en) | Data processing method, device, electronic equipment and computer 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 |