CN109840277A - A kind of government affairs Intelligent Service answering method and system - Google Patents
A kind of government affairs Intelligent Service answering method and system Download PDFInfo
- Publication number
- CN109840277A CN109840277A CN201910127846.4A CN201910127846A CN109840277A CN 109840277 A CN109840277 A CN 109840277A CN 201910127846 A CN201910127846 A CN 201910127846A CN 109840277 A CN109840277 A CN 109840277A
- Authority
- CN
- China
- Prior art keywords
- similarity
- government affairs
- faqs
- library
- calculated
- 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
Abstract
The invention discloses a kind of government affairs Intelligent Service answering method and systems, which comprises step 1, obtains customer problem;Step 2, calculate the first similarity of the FAQs of customer problem and storage, and compare the first similarity for being calculated and the first similarity given threshold: thening follow the steps 3 when the first similarity being calculated is higher than the first similarity given threshold, it is no to then follow the steps 4;Step 3, the relevant information of FAQs is inquired;Step 4, calculate the second similarity of the government affairs service item of customer problem and storage, and compare the second similarity and the second similarity given threshold being calculated: executing step 5 when the second similarity being calculated is higher than the second similarity given threshold, it is no to then follow the steps 6;Step 5, the relevant information of government affairs service item is inquired;Step 6, record customer problem is as problem to be solved.The present invention facilitates user to quickly understand working item.
Description
Technical field
The present invention relates to computer science and technology field, especially a kind of government affairs Intelligent Service answering method and system.
Background technique
Government affairs field, which is handled affairs, at present compares dependence manually, not only heavy workload, but also repeatability is high.Therefore how accurately fixed
The specific working item in position returns to user related information, mitigates artificial question and answer pressure, increases work efficiency, facilitates user quick
Solution government affairs working item is very important.
Summary of the invention
The technical problems to be solved by the present invention are: in view of the above problems, a kind of government affairs Intelligent Service is provided and is asked
Method and system are answered, user is facilitated to quickly understand government affairs working item.
The technical solution adopted by the invention is as follows:
A kind of government affairs Intelligent Service answering method, includes the following steps:
Step 1, customer problem is obtained;
Step 2, the first similarity of the FAQs of customer problem and storage is calculated, and compares the first phase being calculated
Like degree and the first similarity given threshold: then being executed when the first similarity being calculated is higher than the first similarity given threshold
Step 3, no to then follow the steps 4;
Step 3, it inquires the relevant information of FAQs and feeds back to user;
Step 4, the second similarity of the government affairs service item of customer problem and storage is calculated, and compares the be calculated
Two similarities and the second similarity given threshold: it is held when the second similarity being calculated is higher than the second similarity given threshold
Row step 5, it is no to then follow the steps 6;
Step 5, it inquires the relevant information of government affairs service item and feeds back to user;
Step 6, record customer problem is as problem to be solved.
Further, the government affairs Intelligent Service answering method, further includes: step 7, manually to the problem to be solved of record into
Row is answered, and the problem to be solved after answer is stored into FAQs library.
Further, the first similarity given threshold and the second similarity given threshold are 0.7.
A kind of government affairs Intelligent Service question answering system, comprising: FAQs library, government affairs service item library, natural language processing
Layer, MySql inquire layer, and SPARQL inquires layer, service item library to be solved;
The FAQs library, for storing FAQs;
Government affairs service item library, for storing government affairs service item;
The natural language processing layer, including the semantic analysis unit for obtaining customer problem;And first analysis it is single
Member and the second analytical unit;First analytical unit is used to calculate the first similarity of customer problem and FAQs, and compares
The first similarity being relatively calculated is to the first similarity given threshold: when the first similarity being calculated is similar higher than first
Spend given threshold when, then by MySql inquire layer inquiry FAQs library in relevant information and feed back to user;Described second
Analytical unit, for when the first similarity being calculated be not higher than the first similarity given threshold when, calculate customer problem with
Second similarity of government affairs service item, and compare the second similarity and the second similarity given threshold being calculated: work as meter
When the second obtained similarity is higher than the second similarity given threshold, layer is inquired by the SPARQL and inquires government affairs service thing
The relevant information of item simultaneously feeds back to user;
The service item library to be solved, for setting threshold not higher than the second similarity when the second similarity being calculated
When value, customer problem is recorded as problem to be solved.
Further, the input of the semantic analysis unit is Chinese natural language, is exported to describe the data of natural language
Library or government affairs service item database query language.
Further, the SPARQL inquiry layer uses Fuseki.
Further, the FAQs library is provided with access frequency to the FAQs of storage, and before backward reference frequency
10 FAQs.
Further, government affairs service item library stores government affairs service item in the form of RDF triple data.
Further, the government affairs Intelligent Service question answering system, further includes: human assistance unit, for record wait solve
Certainly problem is answered, and the problem to be solved after answer is stored into FAQs library.
Further, the government affairs Intelligent Service question answering system, further includes: government affairs service item pushes library, for recording not
With frequency the problem of user, and the higher government affairs service item of frequency is pushed to user.
In conclusion by adopting the above-described technical solution, the beneficial effects of the present invention are:
FAQs library and government affairs service item library is arranged by natural language processing in the present invention, can satisfy difference
The working demand of user, facilitates user to quickly understand working item;And it can reduce the workload of artificial question and answer, improve and handle affairs
Efficiency.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the flow chart of a kind of government affairs Intelligent Service answering method of the present invention and system;
Fig. 2 is the structure chart of a kind of government affairs Intelligent Service answering method of the present invention and system.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention, i.e., described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is logical
The component for the embodiment of the present invention being often described and illustrated herein in the accompanying drawings can be arranged and be designed with a variety of different configurations.
Therefore, claimed invention is not intended to limit to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but be merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Feature and performance of the invention are described in further detail with reference to embodiments.
Embodiment 1
A kind of government affairs Intelligent Service answering method that present pre-ferred embodiments provide, includes the following steps:
Step 1, customer problem is obtained;
Step 2, the first similarity of the FAQs of customer problem and storage is calculated, and compares the first phase being calculated
Like degree and the first similarity given threshold: then being executed when the first similarity being calculated is higher than the first similarity given threshold
Step 3, no to then follow the steps 4;
Step 3, it inquires the relevant information of FAQs and feeds back to user;
Step 4, the second similarity of the government affairs service item of customer problem and storage is calculated, and compares the be calculated
Two similarities and the second similarity given threshold: it is held when the second similarity being calculated is higher than the second similarity given threshold
Row step 5, it is no to then follow the steps 6;
Step 5, it inquires the relevant information of government affairs service item and feeds back to user;
Step 6, record customer problem is as problem to be solved.Wherein, the first similarity given threshold and the second phase
0.7 is preferably arranged to like degree given threshold.
Step 7, manually the problem to be solved of record is answered, the problem to be solved storage after answer to FAQs
In library.
According to above-mentioned government affairs Intelligent Service answering method, the present embodiment also provides a kind of government affairs Intelligent Service question and answer system
System, comprising: FAQs library, government affairs service item library, natural language processing layer, MySql inquire layer, and SPARQL inquires layer, to
Solve service item library;
The FAQs library, for storing FAQs;The FAQs library is using relevant database.Institute
It states FAQs library and access frequency is provided with to the FAQs of storage, before access frequency 10 FAQs can be fed back to
User.
Government affairs service item library, for storing government affairs service item;Preferably, government affairs service item library uses
Be that Jena is used to store the component TDB of RDF, government affairs service item is stored in the form of RDF triple data.
The natural language processing layer, including the semantic analysis unit for obtaining customer problem;And first analysis it is single
Member and the second analytical unit.
The input of the semantic analysis unit is Chinese natural language, using participle tools such as Jieba participle, LTP participles
The Chinese natural language of input is segmented, the work such as part-of-speech tagging.Wherein, participle also needs to construct the field of government affairs service
Dictionary and customized attribute dictionary, domain lexicon includes government affairs field specifically working item title and abbreviation, customized
Attribute dictionary include attribute word relevant to specific working item.
First analytical unit is used to calculate the first similarity of customer problem and FAQs, and compares and be calculated
The first similarity and the first similarity given threshold: when the first similarity being calculated be higher than the first similarity given threshold
When, then by MySql inquire layer inquire FAQs library in relevant information and feed back to user;The MySql inquires layer
The MySql sentence finished writing in advance.
Second analytical unit works as calculating for carrying out entity link to customer problem and government affairs service item library
When the first obtained similarity is not higher than the first similarity given threshold, the second phase of customer problem and government affairs service item is calculated
Like degree, and compare the second similarity and the second similarity given threshold being calculated: when the second similarity being calculated is high
When the second similarity given threshold, the relevant information of layer inquiry government affairs service item is inquired by the SPARQL and is fed back to
User;When the relevant information of the SPARQL inquiry layer inquiry government affairs service item, need to carry out in advance to construct SPARQL template,
I.e. in advance by the relevant problem definition of government affairs service item are as follows: true class problem defines class problem, explains class problem, process class
Problem, for being born the government affairs service item of notarization:
True class problem: handle birth notarization and need to charge?
Define class problem: what is birth notarization?
According to class problem: why needing to handle raw notarization?
Does is process class problem: what the process of handling for notarization of being born?
Using Fuseki, (Fuseki is the SPARQL server that Jena is provided to the SPARQL inquiry layer, is used for SPARQL
The operation such as inquiry and SPARQL update), it needs using SPARQL query statement, therefore, it is necessary to pass through SPARQL template, by semanteme
The customer problem mapping of the RDF triple data mode of analysis module output generates SPARQL query statement, reuses SPARQL
Query statement inquiry government affairs service item library in relevant information and feed back to user.The calculation method of above-mentioned similarity is
TFIDF similarity calculating method.
The service item library to be solved, for setting threshold not higher than the second similarity when the second similarity being calculated
When value, customer problem is recorded as problem to be solved;It is asked at the same time it can also feed back similarity in FAQs library highest 2
Interrogation frequency highest 5 in topic, government affairs service item library similarity highest 3 related working items and FAQs library
Problem is to user.Further, the government affairs Intelligent Service question answering system, further includes: human assistance unit, for record
Problem to be solved is answered, and the problem to be solved after answer is stored into FAQs library, i.e., manually transfers problem to be solved,
Problem to be solved is answered, the problem to be solved after answer is stored into FAQs library, for later use family carries out political affairs
It is used when Intelligent Service question and answer of being engaged in.
Further, the government affairs Intelligent Service question answering system, further includes: government affairs service item pushes library, uses relationship type
Database, frequency the problem of for recording different user, and the higher government affairs service item of frequency is pushed to user.Record is different
The problem of mode of frequency was that problem table is established for different user, and every table records user the problem of user and troublesome frequencies.
And a total problem table is established, record all customer problems and its frequency.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (10)
1. a kind of government affairs Intelligent Service answering method, which comprises the steps of:
Step 1, customer problem is obtained;
Step 2, the first similarity of the FAQs of customer problem and storage is calculated, and compares the first similarity being calculated
With the first similarity given threshold: when the first similarity being calculated be higher than the first similarity given threshold when then follow the steps
3, it is no to then follow the steps 4;
Step 3, it inquires the relevant information of FAQs and feeds back to user;
Step 4, the second similarity of the government affairs service item of customer problem and storage is calculated, and compares the second phase being calculated
Like degree and the second similarity given threshold: executing step when the second similarity being calculated is higher than the second similarity given threshold
Rapid 5, it is no to then follow the steps 6;
Step 5, it inquires the relevant information of government affairs service item and feeds back to user;
Step 6, record customer problem is as problem to be solved.
2. government affairs Intelligent Service answering method as described in claim 1, which is characterized in that further include: step 7, manually to note
The problem to be solved of record is answered, and the problem to be solved after answer is stored into FAQs library.
3. government affairs Intelligent Service answering method as described in claim 1, which is characterized in that the first similarity given threshold
It is 0.7 with the second similarity given threshold.
4. a kind of government affairs Intelligent Service question answering system characterized by comprising FAQs library, government affairs service item library, nature
Language Processing layer, MySql inquire layer, and SPARQL inquires layer, service item library to be solved;
The FAQs library, for storing FAQs;
Government affairs service item library, for storing government affairs service item;
The natural language processing layer, including the semantic analysis unit for obtaining customer problem;And first analytical unit and
Second analytical unit;First analytical unit is used to calculate the first similarity of customer problem and FAQs, and compares meter
Obtained the first similarity and the first similarity given threshold: it is set when the first similarity being calculated is higher than the first similarity
When determining threshold value, then by MySql inquire layer inquire FAQs library in relevant information and feed back to user;Second analysis
Unit, for calculating customer problem and government affairs when the first similarity being calculated is not higher than the first similarity given threshold
Second similarity of service item, and compare the second similarity for being calculated and the second similarity given threshold: when calculating
When the second similarity arrived is higher than the second similarity given threshold, layer is inquired by the SPARQL and inquires government affairs service item
Relevant information simultaneously feeds back to user;
The service item library to be solved, for when the second similarity being calculated is not higher than the second similarity given threshold
When, customer problem is recorded as problem to be solved.
5. government affairs Intelligent Service question answering system as claimed in claim 4, which is characterized in that the input of the semantic analysis unit
For Chinese natural language, export to describe the database or government affairs service item database query language of natural language.
6. government affairs Intelligent Service question answering system as claimed in claim 4, which is characterized in that the SPARQL inquiry layer uses
Fuseki。
7. government affairs Intelligent Service question answering system as claimed in claim 4, which is characterized in that the FAQs library is to storage
FAQs is provided with access frequency, and before backward reference frequency 10 FAQs.
8. government affairs Intelligent Service question answering system as claimed in claim 4, which is characterized in that government affairs service item library with
The form of RDF triple data stores government affairs service item.
9. government affairs Intelligent Service question answering system as claimed in claim 4, which is characterized in that further include: human assistance unit is used
It is answered in the problem to be solved to record, the problem to be solved after answer is stored into FAQs library.
10. government affairs Intelligent Service question answering system as claimed in claim 4, which is characterized in that further include: government affairs service item pushes away
Library is sent, frequency the problem of for recording different user, and the higher government affairs service item of frequency is pushed to user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910127846.4A CN109840277A (en) | 2019-02-20 | 2019-02-20 | A kind of government affairs Intelligent Service answering method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910127846.4A CN109840277A (en) | 2019-02-20 | 2019-02-20 | A kind of government affairs Intelligent Service answering method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109840277A true CN109840277A (en) | 2019-06-04 |
Family
ID=66884636
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910127846.4A Pending CN109840277A (en) | 2019-02-20 | 2019-02-20 | A kind of government affairs Intelligent Service answering method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109840277A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111858899A (en) * | 2020-07-31 | 2020-10-30 | 中国工商银行股份有限公司 | Statement processing method, device, system and medium |
CN113626569A (en) * | 2021-08-02 | 2021-11-09 | 浪潮软件股份有限公司 | Convenient affair handling method and system based on government affair items and historical data |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103177108A (en) * | 2013-03-26 | 2013-06-26 | 中山大学 | Medical treatment automatic question answering method based on internet and system thereof |
CN103902652A (en) * | 2014-02-27 | 2014-07-02 | 深圳市智搜信息技术有限公司 | Automatic question-answering system |
CN105630938A (en) * | 2015-12-23 | 2016-06-01 | 深圳市智客网络科技有限公司 | Intelligent question-answering system |
CN106909930A (en) * | 2015-12-23 | 2017-06-30 | 神州数码信息系统有限公司 | A kind of model and method of the man-machine automatic switchover based on government affairs machine question answering system |
CN107910006A (en) * | 2017-12-06 | 2018-04-13 | 广州宝镜智能科技有限公司 | Audio recognition method, device and multiple source speech differentiation identifying system |
CN107993724A (en) * | 2017-11-09 | 2018-05-04 | 易保互联医疗信息科技(北京)有限公司 | A kind of method and device of medicine intelligent answer data processing |
CN109033318A (en) * | 2018-07-18 | 2018-12-18 | 北京市农林科学院 | Intelligent answer method and device |
CN109213910A (en) * | 2018-09-12 | 2019-01-15 | 杭州数梦工场科技有限公司 | A kind of government intelligence customer service method, system, electronic equipment and storage medium |
CN109325780A (en) * | 2018-08-24 | 2019-02-12 | 安徽讯飞智能科技有限公司 | A kind of exchange method of the intelligent customer service system in E-Governance Oriented field |
-
2019
- 2019-02-20 CN CN201910127846.4A patent/CN109840277A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103177108A (en) * | 2013-03-26 | 2013-06-26 | 中山大学 | Medical treatment automatic question answering method based on internet and system thereof |
CN103902652A (en) * | 2014-02-27 | 2014-07-02 | 深圳市智搜信息技术有限公司 | Automatic question-answering system |
CN105630938A (en) * | 2015-12-23 | 2016-06-01 | 深圳市智客网络科技有限公司 | Intelligent question-answering system |
CN106909930A (en) * | 2015-12-23 | 2017-06-30 | 神州数码信息系统有限公司 | A kind of model and method of the man-machine automatic switchover based on government affairs machine question answering system |
CN107993724A (en) * | 2017-11-09 | 2018-05-04 | 易保互联医疗信息科技(北京)有限公司 | A kind of method and device of medicine intelligent answer data processing |
CN107910006A (en) * | 2017-12-06 | 2018-04-13 | 广州宝镜智能科技有限公司 | Audio recognition method, device and multiple source speech differentiation identifying system |
CN109033318A (en) * | 2018-07-18 | 2018-12-18 | 北京市农林科学院 | Intelligent answer method and device |
CN109325780A (en) * | 2018-08-24 | 2019-02-12 | 安徽讯飞智能科技有限公司 | A kind of exchange method of the intelligent customer service system in E-Governance Oriented field |
CN109213910A (en) * | 2018-09-12 | 2019-01-15 | 杭州数梦工场科技有限公司 | A kind of government intelligence customer service method, system, electronic equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
陶永芹: "专业领域智能问答系统设计与实现", 《计算机应用与软件》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111858899A (en) * | 2020-07-31 | 2020-10-30 | 中国工商银行股份有限公司 | Statement processing method, device, system and medium |
CN111858899B (en) * | 2020-07-31 | 2023-09-15 | 中国工商银行股份有限公司 | Statement processing method, device, system and medium |
CN113626569A (en) * | 2021-08-02 | 2021-11-09 | 浪潮软件股份有限公司 | Convenient affair handling method and system based on government affair items and historical data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10698977B1 (en) | System and methods for processing fuzzy expressions in search engines and for information extraction | |
US9569506B2 (en) | Uniform search, navigation and combination of heterogeneous data | |
JP6118414B2 (en) | Context Blind Data Transformation Using Indexed String Matching | |
US7949654B2 (en) | Supporting unified querying over autonomous unstructured and structured databases | |
US8126892B2 (en) | Automatically linking documents with relevant structured information | |
US8156102B2 (en) | Inferring search category synonyms | |
US8019771B2 (en) | Method for dynamically finding relations between database tables | |
CN109815343B (en) | Method, apparatus, device and medium for obtaining data models in a knowledge graph | |
US20220222437A1 (en) | Systems and methods for structured phrase embedding and use thereof | |
US11829388B2 (en) | System and method for identifying questions of users of a data management system | |
US11487943B2 (en) | Automatic synonyms using word embedding and word similarity models | |
WO2012129152A2 (en) | Annotating schema elements based associating data instances with knowledge base entities | |
JP2023507286A (en) | Automatic creation of schema annotation files for converting natural language queries to structured query language | |
JP2019040598A5 (en) | ||
US20130117325A1 (en) | Semantic Related Objects | |
CN109840277A (en) | A kind of government affairs Intelligent Service answering method and system | |
US20040193567A1 (en) | Apparatus and method for using a predefined database operation as a data source for a different database operation | |
Schmidts et al. | Schema Matching with Frequent Changes on Semi-Structured Input Files: A Machine Learning Approach on Biological Product Data. | |
US10817554B2 (en) | Observation-based query interpretation model modification | |
EP3170101B1 (en) | Data model indexing for model queries | |
Iqbal et al. | A Negation Query Engine for Complex Query Transformations | |
US20170177670A1 (en) | Database querying apparatuses, methods for querying a database, and non-transitory tangible machine-readable media thereof | |
JP2022546228A (en) | Resolution of queries using structured and unstructured data | |
Iqbal et al. | Negation query handling engine for natural language interfaces to ontologies | |
US7925642B2 (en) | Apparatus and method for reducing size of intermediate results by analyzing having clause information during SQL processing |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190604 |