CN109213910B - A kind of government intelligence customer service method, system, electronic equipment and storage medium - Google Patents
A kind of government intelligence customer service method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109213910B CN109213910B CN201811063047.7A CN201811063047A CN109213910B CN 109213910 B CN109213910 B CN 109213910B CN 201811063047 A CN201811063047 A CN 201811063047A CN 109213910 B CN109213910 B CN 109213910B
- Authority
- CN
- China
- Prior art keywords
- government affairs
- industry
- government
- data
- customer service
- 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
Classifications
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Abstract
The embodiment of the invention discloses a kind of government intelligence customer service method, system, electronic equipment and storage mediums, this method comprises: obtaining government affairs industry data, establish government affairs sector database;Obtain the solicited message of target user's input;The identification of reference content business is carried out to solicited message;According to the solicited message identified, the corresponding answer feedback in government affairs sector database is transferred to target user.It is obtained by the acquisition to government affairs industry data, establish the dedicated database about government affairs industry, when user is serviced by government intelligence customer service, identify the solicited message that user issues, then corresponding government affairs business answer is transferred to user, the semantic understandability of the problem of intelligent customer service seeks advice from government affairs industry user is substantially increased, the intelligence of government intelligence customer service is improved, user is facilitated quickly to obtain accurate answer.
Description
Technical field
The present invention relates to intelligent customer service technical fields, more particularly to a kind of government intelligence customer service method, system, electricity
Sub- equipment and storage medium.
Background technique
It is more preferably serviced to be provided for client, the customer service of more and more industry distributions.Traditional customer service uses
Artificial mode provides service, and there is hardly possible of recruiting, training cost height, mobility using contact staff, manageability etc. lacks greatly and not
Point.With advances in technology, intelligent customer service has obtained rapid popularization, wherein intelligent customer service robot is using customer knowledge
Enterprise is helped to improve the decision-making capability of optimization customer relationship and the software assembly of whole operation ability, it can be with 24 hourly worker of whole day
Make, moreover it is possible to constantly be learnt by the feedback of real time data, enterprise has enough power customer services robot to replace a part artificial
Customer service.
Intelligent customer service is that the Industry-oriented to grow up on the basis of extensive knowledge processing is applied, and is used big
Scale Knowledge Processing Technology, natural language understanding technology, Knowledge Management Technology, automatically request-answering system, inference technology etc. are advanced
Artificial intelligence technology has industry universal.Currently, intelligent customer service is mainly used in financial industry, such as security, bank, insurance
Equal subdivisions field.In real life and work, there are also many fields to need using intelligent customer service, especially government affairs field,
People's lives and work are be unable to do without and the information exchange of functional government departments, still, government intelligence customer service currently on the market
General-purpose platform, that is, the platform being transformed from marketing intelligent customer service are generally used, since the dictionary of general-purpose platform is business
Dictionary, therefore, the problem of intelligent customer service seeks advice from government affairs industry user semantic understanding ability it is poor, it is accurate often to provide
Answer.
Therefore, the intelligence of government intelligence customer service how is improved, to improve the reason for the problem of seeking advice from government affairs industry user
Solution ability is a technical problem that technical personnel in the field need to solve at present so that user quickly obtains accurate answer.
Summary of the invention
The object of the present invention is to provide a kind of government intelligence customer service method, system, electronic equipment and storage mediums, can
To improve the intelligence of government intelligence customer service, while the understandability for the problem of seeking advice from government affairs industry user is improved, to use
Family quickly obtains accurate answer.
In order to solve the above technical problems, the present invention provides the following technical scheme that
A kind of government intelligence customer service method, comprising:
Government affairs industry data is obtained, government affairs sector database is established;
Obtain the solicited message of target user's input;
The identification of reference content business is carried out to the solicited message;
According to the solicited message identified, the corresponding answer feedback in the government affairs sector database is transferred to described
Target user.
Preferably, the acquisition government affairs industry data, establishes government affairs sector database, comprising:
Crawl the government affairs industry data in network;
Historical data of the calling and obtaining user when accessing the government intelligence customer service;
According to the government affairs industry data crawled and the historical data transferred, government affairs sector database is constructed.
Preferably, the government affairs industry data and the historical data transferred that the basis crawls, construct government affairs row
Industry database, comprising:
According to the government affairs industry data crawled and the historical data transferred, corresponding unstructured number is filtered out
According to the unstructured data includes: business words art, professional hot word, business rule and the history interactive log of government affairs industry;
The unstructured data is handled by preset data processing model, constructs government affairs industry dictionary;
The high frequency words in the government affairs industry dictionary are filtered out, term clustering is carried out to the high frequency words and syntactic structure parses
This candidate pronouns, general term for nouns, numerals and measure words is obtained, industry ontology dictionary is constructed according to the business rule and this described candidate pronouns, general term for nouns, numerals and measure words, is the industry sheet
Each corresponding government affairs information of ontology word association in pronouns, general term for nouns, numerals and measure words library constructs government affairs industry knowledge base;
Business rule analysis is associated to each pronouns, general term for nouns, numerals and measure words in the industry ontology dictionary by preset algorithm, is established
Government affairs industry dialog model.
Preferably, the method for servicing further include:
Log analysis and quality testing are carried out to the historical data;
Judge whether there is neologisms;
If so, being associated with the neologisms and the government affairs sector database, the government affairs sector database is dynamically updated.
It is preferably, described that the identification of reference content business is carried out to the solicited message, comprising:
Text information identification and error correction are carried out to the solicited message;
Semantic parsing is carried out to the text information after error correction, obtains corresponding this pronouns, general term for nouns, numerals and measure words of target and association reference content word
It converges.
Preferably, the solicited message that the basis identifies transfers mutually replying in the government affairs sector database
Case feeds back to the target user, comprising:
According to described this pronouns, general term for nouns, numerals and measure words of target and reference content vocabulary, corresponding problem is matched in the government affairs sector database
Answer;
Described problem answer feedback is transferred to the target user.
Preferably, the method for servicing further include:
Manage the government affairs industry knowledge base;
Individual cultivation is provided;
The role of each user is defined, and configures corresponding permission;
According to the access data of user, corresponding statistical information is generated, counts high frequency problem, temporally dimension quantity of service
Statistics.
A kind of government intelligence customer service system, comprising:
Database module establishes government affairs sector database for obtaining government affairs industry data;
Request module, for obtaining the solicited message of target user's input;
Identification module, for carrying out the identification of reference content business to the solicited message;
Feedback module, for transferring corresponding in the government affairs sector database according to the solicited message identified
Answer feedback gives the target user.
Preferably, the database module includes:
Data crawl unit, for crawling the government affairs industry data in network;
Data transfer unit, for historical data of the calling and obtaining user when accessing the government intelligence customer service;
Library unit is built, for constructing government affairs according to the government affairs industry data crawled and the historical data transferred
Sector database.
Preferably, the library unit of building includes:
Subelement is screened, for filtering out according to the government affairs industry data crawled and the historical data transferred
Corresponding unstructured data, the unstructured data include: business words art, the professional hot word, business rule of government affairs industry
With history interactive log;
Dictionary creation subelement, for constructing government affairs industry dictionary by preset data processing model;
Ontology dictionary constructs subelement, for filtering out the high frequency words in the government affairs industry dictionary, to the high frequency words
It carries out term clustering and syntactic structure parses to obtain this candidate pronouns, general term for nouns, numerals and measure words, according to the business rule and candidate this pronouns, general term for nouns, numerals and measure words building row
Industry ontology dictionary is each corresponding government affairs information of ontology word association in the industry ontology dictionary, constructs government affairs domain knowledge
Library;
Dialog model construct subelement, for by preset algorithm to each pronouns, general term for nouns, numerals and measure words in the industry ontology dictionary into
Row associated services rule analysis establishes government affairs industry dialog model.
Preferably, further includes:
Analysis module, for carrying out log analysis and quality testing to the historical data;
Judgment module, for judging whether there is neologisms;
Database update module, for determining there are when neologisms, being associated with the neologisms and the government affairs sector database,
Dynamic updates the government affairs sector database.
Preferably, the identification module includes:
Error correction unit, for carrying out text information identification and error correction to the solicited message;
Resolution unit, for carrying out semantic parsing to the text information after error correction, obtain corresponding this pronouns, general term for nouns, numerals and measure words of target and
It is associated with reference content vocabulary.
Preferably, the feedback module includes:
Matching unit is used for according to described this pronouns, general term for nouns, numerals and measure words of target and reference content vocabulary, in the government affairs sector database
Match corresponding problem answers;
Feedback unit, for transferring described problem answer feedback to the target user.
Preferably, further includes:
Database management module, for managing the government affairs industry knowledge base;
Robot management module, for providing individual cultivation;
User management module for defining the role of each user, and configures corresponding permission;
Statistical analysis module generates corresponding statistical information for the access data according to user, counts high frequency problem,
Temporally dimension quantity of service counts.
A kind of electronic equipment for government intelligence customer service, comprising:
Memory, for storing computer program;
Processor realizes government intelligence customer service as described in any one of the above embodiments when for executing the computer program
The step of method.
A kind of computer readable storage medium is stored with computer program on the computer readable storage medium, described
It is realized when computer program is executed by processor as described in any of the above-described the step of government intelligence customer service method.
Compared with prior art, above-mentioned technical proposal has the advantage that
A kind of government intelligence customer service method provided by the embodiment of the present invention, comprising: obtain government affairs industry data, build
Vertical government affairs sector database;Obtain the solicited message of target user's input;The identification of reference content business is carried out to solicited message;Root
According to the solicited message identified, the corresponding answer feedback in government affairs sector database is transferred to target user.By to government affairs row
The acquisition of industry data obtains, and the dedicated database about government affairs industry is established, when user is taken by government intelligence customer service
When business, identifies the solicited message that user issues, then transfer corresponding government affairs business answer to user, substantially increase intelligence
The semantic understandability of the problem of government affairs industry user is seeked advice from customer service, improves the intelligence of government intelligence customer service, convenient
User quickly obtains accurate answer.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is government intelligence customer service method flow diagram provided by a kind of specific embodiment of the present invention;
Fig. 2 is government intelligence customer service robot system schematic provided by a kind of specific embodiment of the present invention;
Fig. 3 is government intelligence customer service system schematic provided by a kind of specific embodiment of the present invention.
Specific embodiment
Core of the invention is to provide a kind of government intelligence customer service method, system, electronic equipment and storage medium, can
To improve the intelligence of government intelligence customer service, while the understandability for the problem of seeking advice from government affairs industry user is improved, to use
Family quickly obtains accurate answer.
It is understandable in order to enable the above objects, features and advantages of the present invention to become apparent, with reference to the accompanying drawing to this hair
Bright specific embodiment is described in detail.
Detail is elaborated in the following description to fully understand the present invention.But the present invention can with it is a variety of not
Other way described herein is same as to implement, those skilled in the art can do class without violating the connotation of the present invention
Like popularization.Therefore the present invention is not limited to the specific embodiments disclosed below.
Referring to FIG. 1, Fig. 1 is government intelligence customer service method flow provided by a kind of specific embodiment of the present invention
Figure.
One embodiment of the present invention provides a kind of government intelligence customer service method, comprising:
S11: government affairs industry data is obtained, government affairs sector database is established.
In one embodiment of the invention, government affairs are obtained by way of crawling the government affairs industry data in network
Industry data further can obtain government affairs industry with historical data of the calling and obtaining user when accessing government intelligence customer service
Data, so-called historical data are that conversation activity of the user in application government intelligence customer service records data.
Wherein, the process for establishing government affairs sector database includes: government affairs industry data according to acquisition, is filtered out corresponding
Unstructured data, unstructured data include: business words art, professional hot word, business rule and the history interaction of government affairs industry
Log;Unstructured data is handled by preset data processing model, constructs government affairs industry dictionary;Filter out government affairs
High frequency words in industry dictionary carry out term clustering to high frequency words and syntactic structure parse to obtain this candidate pronouns, general term for nouns, numerals and measure words, advised according to business
Industry ontology dictionary then is constructed with this candidate pronouns, general term for nouns, numerals and measure words, is each corresponding government affairs information of ontology word association in industry ontology dictionary,
Construct government affairs industry knowledge base;Business rule point is associated to each pronouns, general term for nouns, numerals and measure words in industry ontology dictionary by preset algorithm
Analysis, establishes government affairs industry dialog model.
In the present embodiment, the business of existing government affairs industry can be talked about by art by data intelligence processing engine
The unstructured datas such as (some specific terms explain reply) in industry, professional hot word, business rule, history interactive log into
Row arranges, and forms government affairs industry dictionary, industry ontology dictionary, government affairs industry knowledge base, Task Tree and business rule.
Wherein, industry dictionary are used for when analyzing user session, are carried out analysis and understanding to user's sentence, are eliminated discrimination
Justice is easy to misread user's intention without industry dictionary.Government affairs industry dictionary are the industry dictionary about government affairs industry.Industry word
Allusion quotation can be recorded, based on artificial dictionary with history archive, supplemented by internet related fields document, and using Hidden Markov, most
The preset data processing models such as big entropy are constructed.Artificial dictionary and internet related fields document can be used as corpus,
Using the methods of participle, cluster, industry dictionary are obtained.
Business rule can be provided by industry specialists and be defined, for example definition " carry xxx and remove xx " can be defined as one
Business rule.By this business rule, this pronouns, general term for nouns, numerals and measure words found in industry dictionary can be convenient, for example entrained " xxx " is just
It certainly is this pronouns, general term for nouns, numerals and measure words.
When constructing industry ontology dictionary by data intelligence processing engine, for example " identity card " of government affairs industry is ontology
Word may include several problems around this pronouns, general term for nouns, numerals and measure words, such as how to handle identity card, how to make up identity card, how to report the loss.Row
The construction method of industry ontology dictionary is used with the high frequency words triggering in government affairs industry dictionary, is parsed using term clustering, syntactic structure
Etc. technologies obtain this candidate pronouns, general term for nouns, numerals and measure words, recycle business rule to be constructed.
And so-called Task Tree is exactly a kind of method of industry dialog model, building Task Tree is exactly to construct industry dialogue mould
Type.It can make Association Rule Analysis of some preset algorithms, for example put question to " where identity card is handled " and " identity card is handled
Required material ", " identity card handles the time " these problems are usually continuously to put question to together, may be sequentially different, but base
It is putd question to together in sheet, therefore this is it can be assumed that be an industry dialog model of government affairs industry.
Relative to currently used simple string matching mode, need human configuration entry that could use.And this
Government affairs industry data is obtained by crawling the government affairs industry data in network and transferring historical data in embodiment, significantly
The difficulty for reducing entry configuration, reduces the labor workload of configuration.And it is established according to the method in above embodiment
Government affairs sector database, realize the specialization of government affairs sector database, especially government affairs industry dictionary, industry this pronouns, general term for nouns, numerals and measure words
The building in library, government affairs industry knowledge base and government affairs industry dialog model, substantially increases the consulting to user for government affairs industry
The problem of sentence understandability, can be with disambiguation, so that government intelligence customer service is more intelligent, to provide for user
More accurate answer.
S12: the solicited message of target user's input is obtained.
By the acquisition target user's input of the information input equipments such as intelligent customer service robot client for government affairs industry
The solicited messages such as the traffic issues seeked advice from.
S13: the identification of reference content business is carried out to solicited message.
It in one embodiment of the invention, include: that text information knowledge is carried out to solicited message to solicited message identification
Other and error correction;Semantic parsing is carried out to the text information after error correction, obtains corresponding this pronouns, general term for nouns, numerals and measure words of target and association reference content
Vocabulary.
During intelligent customer service is customer service, either single-wheel dialogue or more wheel dialogues, in order to better understand
The intention of user, to reply correct option, this step realizes intelligent correction and the identification of main body word.When being asked questions to user
Solicited message carries out sentence Rationality Assessment, and then the wrong word in sentence is identified and corrected, guarantees the correct of data
Property, sentence modeling can be carried out by depth language model to realize identification and correct wrong word.And main body word identification be to
The identification of the family reference content scope of business, realizes the coarseness classification of user's request, identifies sentence by syntactic structure parsing
Main component then can match industry ontology dictionary and government affairs industry knowledge base.
S14: according to the solicited message identified, the corresponding answer feedback transferred in government affairs sector database is used to target
Family.
In one embodiment of the invention, it according to the solicited message identified, transfers in government affairs sector database
Corresponding answer feedback is to target user, comprising: according to this pronouns, general term for nouns, numerals and measure words of target and reference content vocabulary, in government affairs sector database
With corresponding problem answers;It transfers problem answers and feeds back to target user.
In one embodiment of the invention, government intelligence customer service method further include: historical data is carried out
Log analysis and quality testing;Judge whether there is neologisms;If so, association neologisms and government affairs sector database, dynamic updates
Government affairs sector database.
Wherein, quality testing, which refers to, detects interactive quality, and the mood of user is predominantly detected for dialogue
The accuracy answered with robot.
In the present embodiment, the reflux data that intelligent customer service is talked with are analyzed by intellectual analysis engine, such as
Log analysis and quality testing etc. construct the function of industry data to realize enhancing model training.According to user's history interaction number
According to find new word or nickname etc., based on original dictionary, not using the discovery of the models such as Hidden Markov, maximum entropy
Word in current government affairs sector database, and the connection of foundation and the government affairs sector database, realize the dynamic of database more
Newly.
Method of servicing further include: management government affairs industry knowledge base is used with providing the knowledge in corresponding field for each algorithm service
In answer user propose the problem of;Individual cultivation, for example intelligent customer service robot configuration head portrait, greeting etc. are provided;
The role of each user is defined, and configures corresponding permission, so that the system uses the operational administrative of based role, completes user's power
The management and page authorization of limit;According to the access data of user, corresponding statistical information is generated, counts high frequency problem, temporally
Dimension quantity of service statistics.
In one embodiment of the present invention, a kind of system, government intelligence customer service robot is additionally provided based on the above method
System, as shown in Fig. 2, the government intelligence customer service robot system includes: network data base 21, historical data base 22, government affairs industry
Database 23, intelligent customer service intelligent algorithm module 24, intelligent customer service robot client 25 and intelligent customer service robot backstage mould
Block 26.
Wherein, network data base 21 is used to store the government affairs industry data in crawled network;Historical data base 22 is used
Record data in each user of storage when using the government intelligence customer service robot system with the conversation activity of the system.
Intelligent customer service intelligent algorithm module 24 specifically includes that intellectual analysis engine, data intelligence processing engine, intelligent session
Engine and algorithm interface module.
Intelligent customer service intelligent algorithm module 24 is based on network data base 21 and historical data base 22, using data intelligence processing
Engine and intellectual analysis engine form government affairs sector database.By intelligent session engine, intelligent customer service robot system is from calculation
Method interface module calls corresponding interface, to understand the intention of customer problem, and reads government affairs from government affairs sector database 23
The problem of corresponding contents in industry knowledge base are user furnishes an answer.
Data intelligence processing engine, by the way that existing business is talked about art, professional hot word, business rule, history interactive log etc.
Unstructured data is arranged, and government affairs industry dictionary, ontology library, knowledge base, Task Tree, business rule etc. are formed.Intelligent number
Facilitate sentence comprehension, disambiguation according to the government affairs industry dictionary that processing engine establishes professional domain, government affairs industry dictionary are to go through
Based on history paper trail, artificial dictionary, supplemented by internet related fields document, the models such as Hidden Markov, maximum entropy can be used
Building.Data intelligence processing engine constructs this pronouns, general term for nouns, numerals and measure words of industry, for example " identity card " of government affairs industry is main pronouns, general term for nouns, numerals and measure words, surrounds the main body
Word problem includes: to handle identity card, how to make up, how to report the loss, and the construction method of industry ontology dictionary is used with profession
Dictionary medium-high frequency word sets out, and obtains this candidate pronouns, general term for nouns, numerals and measure words using technologies such as term clustering, syntactic structure parsings, recycles business rule structure
It builds.
Wherein, intellectual analysis engine mainly handles the analysis of the reflux data of intelligent customer service dialogue, carries out log analysis, matter
Enhancing model training, the function of constructing industry data may be implemented in the functions such as amount detection.Wherein, new word discovery is that its is important
One Xiang Gongneng.New word discovery is to find new word, nickname etc. according to user's history interaction data, can based on original dictionary
The word not in dictionary is found using models such as Hidden Markov, maximum entropies, and is established and the connection in original dictionary, realization word
The dynamic in library updates.
Wherein, intelligent session engine is real in the single-wheel dialogue and/or more wheel dialog procedures that intelligent customer service is customer service
Existing intelligent answer can better understand user's intention, reply correct option.In dialog procedure, intelligent correction, main body word are known
It is not its important function.Intelligent correction carries out sentence Rationality Assessment to the sentence that user seeks advice from, then in sentence
Wrong word identified and corrected, guarantee the correctness of data, realization principle is to carry out sentence by depth language model
Modeling, identifies and corrects wrong word.The identification of main body word is the identification to user's reference content scope of business, realizes user's request
Coarseness classification.Its realization principle is to identify then the main component of sentence matches ontology dictionary by syntactic structure parsing.
Intelligent customer service robot client 25 is responsible for customer service robot front end and shows logic, for being interacted with user,
The problem of obtaining user's input, is transmitted to intelligent customer service intelligent algorithm module 24 for the problem of user, while matching government affairs industry
Database 23, and the answer that intelligent customer service intelligent algorithm module 24 provides is presented to user.
Intelligent customer service robot background module 26 includes: database management module, for managing government affairs industry knowledge base, with
The knowledge in corresponding field is provided for each algorithm service, for answering the problem of user proposes;Robot management module, for providing
Individual cultivation, for example intelligent customer service robot configure head portrait, greeting etc.;User management module, for defining each use
The role at family, and corresponding permission is configured, so that the system uses the operational administrative of based role, complete the management of user right
With page authorization;Statistical analysis module generates corresponding statistical information for the access data according to user, and statistics high frequency is asked
Topic, temporally dimension quantity of service counts.
Government intelligence customer service method provided by the present invention, it is pre- by carrying out data to the government affairs industry data of acquisition
Processing establishes government affairs industry dictionary, government affairs industry knowledge base and government affairs industry dialog model etc. with government affairs industry characteristic
Core data, instead of the mode of pure human configuration service database used by general universal intelligent platform, so that manually
Maintenance workload substantially reduces.Dynamic updates government affairs sector database and passes through intelligent calculation that is, according to the advisory data of government affairs industry
Method is iterated study, expands the database of government affairs industry, more more intelligent and accurate than the answer of general intelligent customer service, significantly
The semantic understandability of the problem of intelligent customer service seeks advice from government affairs industry user is improved, the intelligence of government intelligence customer service is improved
Energyization facilitates user quickly to obtain accurate answer.
Referring to FIG. 3, Fig. 3 is government intelligence customer service system signal provided by a kind of specific embodiment of the present invention
Figure.
Correspondingly, one embodiment of the present invention additionally provides a kind of government intelligence customer service system, comprising: database
Module 31 establishes government affairs sector database for obtaining government affairs industry data;Request module 32 is used for obtaining target
The solicited message of family input;Identification module 33, for carrying out the identification of reference content business to solicited message;Feedback module 34 is used
According to the solicited message identified, the corresponding answer feedback in government affairs sector database is transferred to target user.
Wherein, preference data library module 31 includes: that data crawl unit, for crawling the government affairs industry data in network;
Data transfer unit, for historical data of the calling and obtaining user when accessing government intelligence customer service;Library unit is built, is crawled for basis
Government affairs industry data and the historical data transferred, construct government affairs sector database.
Further, building library unit includes: screening subelement, for being gone through according to the government affairs industry data crawled with what is transferred
History data, filter out corresponding unstructured data, unstructured data include: the business words art of government affairs industry, professional hot word,
Business rule and history interactive log;Dictionary creation subelement, for constructing government affairs industry by preset data processing model
Dictionary;Ontology dictionary construct subelement, for filtering out the high frequency words in government affairs industry dictionary, to high frequency words carry out term clustering and
Syntactic structure parses to obtain this candidate pronouns, general term for nouns, numerals and measure words, constructs industry ontology dictionary according to business rule and this candidate pronouns, general term for nouns, numerals and measure words, is industry sheet
Each corresponding government affairs information of ontology word association in pronouns, general term for nouns, numerals and measure words library constructs government affairs industry knowledge base;Dialog model constructs subelement, uses
In being associated business rule analysis to each pronouns, general term for nouns, numerals and measure words in industry ontology dictionary by preset algorithm, government affairs industry pair is established
Talk about model.
It is obtained by the acquisition to government affairs industry data, establishes the dedicated database about government affairs industry, when user is logical
When crossing government intelligence customer service and being serviced, identifies the solicited message that user issues, then transfer corresponding government affairs business answer
To user, the semantic understandability of the problem of intelligent customer service seeks advice from government affairs industry user is substantially increased, government affairs are improved
The intelligence of intelligent customer service facilitates user quickly to obtain accurate answer.
In one embodiment of the invention, the government intelligence customer service system further include: analysis module, for pair
Historical data carries out log analysis and quality testing;Judgment module, for judging whether there is neologisms;Database update module,
For determining that dynamic updates government affairs sector database there are neologisms and government affairs sector database when neologisms, is associated with.
In the present embodiment, the reflux data that intelligent customer service is talked with are analyzed by intellectual analysis engine, such as
Log analysis and quality testing etc. construct the function of industry data to realize enhancing model training.According to user's history interaction number
According to find new word or nickname etc., based on original dictionary, not using the discovery of the models such as Hidden Markov, maximum entropy
Word in current government affairs sector database, and the connection of foundation and the government affairs sector database, realize the dynamic of database more
Newly.
On the basis of any of the above-described embodiment, identification module includes: error correction unit, for carrying out text to solicited message
The identification of this information and error correction;Resolution unit obtains corresponding target sheet for carrying out semantic parsing to the text information after error correction
Pronouns, general term for nouns, numerals and measure words and association reference content vocabulary.
Feedback module includes: matching unit, is used for according to this pronouns, general term for nouns, numerals and measure words of target and reference content vocabulary, in government affairs industry data
Corresponding problem answers are matched in library;Feedback unit feeds back to target user for transferring problem answers.
During intelligent customer service is customer service, either single-wheel dialogue or more wheel dialogues, in order to better understand
The intention of user, to reply correct option, this step realizes intelligent correction and the identification of main body word.When being asked questions to user
Solicited message carries out sentence Rationality Assessment, and then the wrong word in sentence is identified and corrected, guarantees the correct of data
Property, sentence modeling can be carried out by depth language model to realize identification and correct wrong word.And main body word identification be to
The identification of the family reference content scope of business, realizes the coarseness classification of user's request, identifies sentence by syntactic structure parsing
Main component then can match industry ontology dictionary and government affairs industry knowledge base.
In one embodiment of the invention, the government intelligence customer service system further include: database management module,
For managing government affairs industry knowledge base, to provide the knowledge in corresponding field for each algorithm service, for answering asking for user's proposition
Topic;Robot management module, for providing individual cultivation, for example intelligent customer service robot configuration head portrait, greeting etc.;
User management module for defining the role of each user, and configures corresponding permission, so that the system uses the behaviour of based role
It manages, completes the management and page authorization of user right;Statistical analysis module is generated for the access data according to user
Corresponding statistical information counts high frequency problem, and temporally dimension quantity of service counts.
Government intelligence customer service system provided by the present invention, it is pre- by carrying out data to the government affairs industry data of acquisition
Processing establishes government affairs industry dictionary, government affairs industry knowledge base and government affairs industry dialog model etc. with government affairs industry characteristic
Core data, instead of the mode of pure human configuration service database used by general universal intelligent platform, so that manually
Maintenance workload substantially reduces.Dynamic updates government affairs sector database and passes through intelligent calculation that is, according to the advisory data of government affairs industry
Method is iterated study, expands the database of government affairs industry, more more intelligent and accurate than the answer of general intelligent customer service, significantly
The semantic understandability of the problem of intelligent customer service seeks advice from government affairs industry user is improved, the intelligence of government intelligence customer service is improved
Energyization facilitates user quickly to obtain accurate answer.
Correspondingly, one embodiment of the present invention additionally provides a kind of electronic equipment for government intelligence customer service, comprising:
Memory, for storing computer program;Processor is realized when for executing computer program such as above-mentioned any embodiment institute
The step of government intelligence customer service method of offer.
One embodiment of the present invention additionally provides a kind of computer readable storage medium, on computer readable storage medium
It is stored with computer program, the government affairs intelligence as provided by above-mentioned any embodiment is realized when computer program is executed by processor
The step of energy customer service method.
For the electronic equipment of government intelligence customer service and computer-readable storage provided by above embodiment of the present invention
Medium, by storing computer program, so that processor may be implemented when executing the computer program to government affairs industry number
According to acquisition obtain, establish dedicated database about government affairs industry, when user is serviced by government intelligence customer service,
It identifies the solicited message that user issues, then transfers corresponding government affairs business answer to user, substantially increase intelligent customer service
The semantic understandability of the problem of seeking advice from for government affairs industry user, improves the intelligence of government intelligence customer service, facilitates user
Quickly obtain accurate answer.
Above to a kind of government intelligence customer service method provided by the present invention, system, electronic equipment and storage medium
It is described in detail.Used herein a specific example illustrates the principle and implementation of the invention, the above reality
The explanation for applying example is merely used to help understand method and its core concept of the invention.It should be pointed out that for the art
For those of ordinary skill, without departing from the principle of the present invention, can with several improvements and modifications are made to the present invention,
These improvements and modifications also fall within the scope of protection of the claims of the present invention.
Claims (8)
1. a kind of government intelligence customer service method characterized by comprising
Government affairs industry data is obtained, government affairs sector database is established;
Obtain the solicited message of target user's input;
The identification of reference content business is carried out to the solicited message;
According to the solicited message identified, the corresponding answer feedback in the government affairs sector database is transferred to the target
User;
Wherein, the acquisition government affairs industry data, establishes government affairs sector database, comprising:
Crawl the government affairs industry data in network;
Historical data of the calling and obtaining user when accessing the government intelligence customer service;
According to the government affairs industry data crawled and the historical data transferred, government affairs sector database is constructed;
Wherein, the government affairs industry data and the historical data transferred that the basis crawls, construct government affairs industry data
Library, comprising:
According to the government affairs industry data crawled and the historical data transferred, corresponding unstructured data is filtered out,
The unstructured data includes: business words art, professional hot word, business rule and the history interactive log of government affairs industry;
The unstructured data is handled by preset data processing model, constructs government affairs industry dictionary;
The high frequency words in the government affairs industry dictionary are filtered out, term clustering is carried out to the high frequency words and syntactic structure parses to obtain
This candidate pronouns, general term for nouns, numerals and measure words constructs industry ontology dictionary according to the business rule and this described candidate pronouns, general term for nouns, numerals and measure words, is described this pronouns, general term for nouns, numerals and measure words of industry
Each corresponding government affairs information of ontology word association in library constructs government affairs industry knowledge base;
Business rule analysis is associated to each pronouns, general term for nouns, numerals and measure words in the industry ontology dictionary by preset algorithm, establishes government affairs
Industry dialog model.
2. method of servicing according to claim 1, which is characterized in that the method for servicing further include:
Log analysis and quality testing are carried out to the historical data;
Judge whether there is neologisms;
If so, being associated with the neologisms and the government affairs sector database, the government affairs sector database is dynamically updated.
3. according to claim 1 to 2 described in any item method of servicing, which is characterized in that described to be carried out to the solicited message
The identification of reference content business, comprising:
Text information identification and error correction are carried out to the solicited message;
Semantic parsing is carried out to the text information after error correction, obtains corresponding this pronouns, general term for nouns, numerals and measure words of target and association reference content vocabulary.
4. method of servicing according to claim 3, which is characterized in that the solicited message that the basis identifies is adjusted
Take the corresponding answer feedback in the government affairs sector database to the target user, comprising:
According to described this pronouns, general term for nouns, numerals and measure words of target and reference content vocabulary, corresponding problem is matched in the government affairs sector database and is answered
Case;
Described problem answer feedback is transferred to the target user.
5. method of servicing according to claim 4, which is characterized in that the method for servicing further include:
Manage the government affairs industry knowledge base;
Individual cultivation is provided;
The role of each user is defined, and configures corresponding permission;
According to the access data of user, corresponding statistical information is generated, counts high frequency problem, temporally dimension quantity of service is united
Meter.
6. a kind of government intelligence customer service system characterized by comprising
Database module establishes government affairs sector database for obtaining government affairs industry data;
Request module, for obtaining the solicited message of target user's input;
Identification module, for carrying out the identification of reference content business to the solicited message;
Feedback module, for transferring the corresponding answer in the government affairs sector database according to the solicited message identified
Feed back to the target user;
Wherein, the database module includes:
Data crawl unit, for crawling the government affairs industry data in network;
Data transfer unit, for historical data of the calling and obtaining user when accessing the government intelligence customer service;
Library unit is built, for constructing government affairs industry according to the government affairs industry data crawled and the historical data transferred
Database;
Wherein, the library unit of building includes:
Subelement is screened, for filtering out corresponding according to the government affairs industry data crawled and the historical data transferred
Unstructured data, the unstructured data includes: the business words art of government affairs industry, professional hot word, business rule and goes through
History interactive log;
Dictionary creation subelement is constructed for being handled by preset data processing model the unstructured data
Government affairs industry dictionary;
Ontology dictionary constructs subelement, for filtering out the high frequency words in the government affairs industry dictionary, carries out to the high frequency words
Term clustering and syntactic structure parse to obtain this candidate pronouns, general term for nouns, numerals and measure words, construct industry sheet according to the business rule and this described candidate pronouns, general term for nouns, numerals and measure words
Pronouns, general term for nouns, numerals and measure words library is each corresponding government affairs information of ontology word association in the industry ontology dictionary, constructs government affairs industry knowledge base;
Dialog model constructs subelement, for being closed by preset algorithm to each pronouns, general term for nouns, numerals and measure words in the industry ontology dictionary
Join business rule analysis, establishes government affairs industry dialog model.
7. a kind of electronic equipment for government intelligence customer service characterized by comprising
Memory, for storing computer program;
Processor realizes such as government intelligence customer service described in any one of claim 1 to 5 when for executing the computer program
The step of method of servicing.
8. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the government intelligence customer service as described in any one of claim 1 to 5 when the computer program is executed by processor
The step of method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811063047.7A CN109213910B (en) | 2018-09-12 | 2018-09-12 | A kind of government intelligence customer service method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811063047.7A CN109213910B (en) | 2018-09-12 | 2018-09-12 | A kind of government intelligence customer service method, system, electronic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109213910A CN109213910A (en) | 2019-01-15 |
CN109213910B true CN109213910B (en) | 2019-08-02 |
Family
ID=64983690
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811063047.7A Active CN109213910B (en) | 2018-09-12 | 2018-09-12 | A kind of government intelligence customer service method, system, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109213910B (en) |
Families Citing this family (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110110039A (en) * | 2019-01-10 | 2019-08-09 | 浙江百应科技有限公司 | A kind of method that the visualization of intelligent sound robot is built |
CN109840277A (en) * | 2019-02-20 | 2019-06-04 | 西南科技大学 | A kind of government affairs Intelligent Service answering method and system |
CN110019755A (en) * | 2019-02-27 | 2019-07-16 | 杭州简简科技有限公司 | Digital people's livelihood system and construction method based on artificial intelligence big data |
CN111626452B (en) * | 2019-02-28 | 2023-08-04 | 百度在线网络技术(北京)有限公司 | Intelligent government affair processing method, device, terminal and medium |
CN110083694A (en) * | 2019-04-30 | 2019-08-02 | 广东电网有限责任公司 | A kind of electrical network business integrated approach, device and memory based on webhook |
CN111914059A (en) * | 2019-05-09 | 2020-11-10 | 中智关爱通(上海)科技股份有限公司 | Employee welfare complaint processing method, system, storage medium and electronic equipment |
CN110377752A (en) * | 2019-06-26 | 2019-10-25 | 广东鼎义互联科技股份有限公司 | A kind of knowledge base system applied to the operation of government affairs hall |
CN112445946A (en) * | 2019-08-29 | 2021-03-05 | 上海卓繁信息技术股份有限公司 | Multi-turn dialogue method and system based on government affair field knowledge map |
CN110533390A (en) * | 2019-08-30 | 2019-12-03 | 广东鼎义互联科技股份有限公司 | A kind of secretary's formula business householder method |
CN111259120A (en) * | 2020-01-13 | 2020-06-09 | 大汉软件股份有限公司 | Interactive intelligent customer service engine based on relevant feedback algorithm |
CN111382256B (en) * | 2020-03-20 | 2024-04-09 | 北京百度网讯科技有限公司 | Information recommendation method and device |
CN111400474B (en) * | 2020-03-20 | 2023-02-03 | 腾讯云计算(北京)有限责任公司 | Intelligent customer service question and answer method and device for government affair service |
CN111753075A (en) * | 2020-08-12 | 2020-10-09 | 腾讯科技(深圳)有限公司 | Method and device for creating question and answer data of customer service robot and computer equipment |
CN112507063A (en) * | 2020-10-29 | 2021-03-16 | 福建拓尔通软件有限公司 | Automatic information combing method and system for office guide file |
CN112287092A (en) * | 2020-11-30 | 2021-01-29 | 珠海采筑电子商务有限公司 | Intelligent elevator service query method and related products |
CN113420130A (en) * | 2021-05-12 | 2021-09-21 | 同方知网数字出版技术股份有限公司 | Intention recognition algorithm based on government affair question-answering system |
CN113438515A (en) * | 2021-06-17 | 2021-09-24 | 重庆大牛认知科技有限公司 | IPTV terminal government affair consultation method and system based on intelligent interaction |
CN114979723B (en) * | 2022-02-14 | 2023-08-29 | 杭州脸脸会网络技术有限公司 | Virtual intelligent customer service method, device, electronic device and storage medium |
CN116307663B (en) * | 2023-02-16 | 2023-09-08 | 广州力麒智能科技有限公司 | Intelligent self-service government affair service system, government affair service general method and terminal |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106919563A (en) * | 2015-12-24 | 2017-07-04 | 神州数码信息系统有限公司 | A kind of cross-border issue of government affairs machine question answering system is classified, distributes automatically, the method for response |
CN107133323A (en) * | 2017-05-04 | 2017-09-05 | 山东浪潮云服务信息科技有限公司 | Data model construction method, the implementation method of government affairs service business and device |
CN107368548A (en) * | 2017-06-30 | 2017-11-21 | 华中科技大学鄂州工业技术研究院 | Intelligent government affairs service interaction method and system |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7080063B2 (en) * | 2002-05-10 | 2006-07-18 | Oracle International Corporation | Probabilistic model generation |
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 |
CN106230701A (en) * | 2016-08-25 | 2016-12-14 | 青岛亿联信息科技股份有限公司 | Instant communicating system based on governmental affairs hot-line and method |
CN106447346A (en) * | 2016-08-29 | 2017-02-22 | 北京中电普华信息技术有限公司 | Method and system for construction of intelligent electric power customer service system |
-
2018
- 2018-09-12 CN CN201811063047.7A patent/CN109213910B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106919563A (en) * | 2015-12-24 | 2017-07-04 | 神州数码信息系统有限公司 | A kind of cross-border issue of government affairs machine question answering system is classified, distributes automatically, the method for response |
CN107133323A (en) * | 2017-05-04 | 2017-09-05 | 山东浪潮云服务信息科技有限公司 | Data model construction method, the implementation method of government affairs service business and device |
CN107368548A (en) * | 2017-06-30 | 2017-11-21 | 华中科技大学鄂州工业技术研究院 | Intelligent government affairs service interaction method and system |
Non-Patent Citations (1)
Title |
---|
基于本体的文本挖掘结果的存储与表现;张庆;《中国优秀硕士学位论文全文数据库 信息科技辑》;20091115;正文第7页第2段至第8页第1段,图1 |
Also Published As
Publication number | Publication date |
---|---|
CN109213910A (en) | 2019-01-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109213910B (en) | A kind of government intelligence customer service method, system, electronic equipment and storage medium | |
Kalla et al. | Study and analysis of chat GPT and its impact on different fields of study | |
CN107329967B (en) | Question answering system and method based on deep learning | |
CN108764937A (en) | It can iteration intelligent customer service system | |
US11223723B2 (en) | Call center system having reduced communication latency | |
CN105072173A (en) | Customer service method and system for automatically switching between automatic customer service and artificial customer service | |
CN110175229B (en) | Method and system for on-line training based on natural language | |
CN109740928A (en) | Electric power consultation service treating method and apparatus | |
CN110232573A (en) | Based on interactive intelligent response system | |
US11615463B2 (en) | Artificial intelligence based digital leasing assistant | |
Rosenkranz et al. | Language quality in requirements development: tracing communication in the process of information systems development | |
US20200066259A1 (en) | Intelligence-driven virtual assistant for automated idea documentation | |
CN105868179A (en) | Intelligent asking-answering method and device | |
CN111400453A (en) | Intelligent interaction system and method based on legal consultation | |
CN109299865A (en) | Psychological assessment system and method, information data processing terminal based on semantic analysis | |
CN111198969A (en) | Economic information consultation system and method based on network big data | |
CN110738511A (en) | Intelligent customer service method and device | |
CN112785347A (en) | Intelligent customer service question and answer recommendation method and system based on knowledge graph | |
CN112287082A (en) | Data processing method, device, equipment and storage medium combining RPA and AI | |
CN110321414B (en) | Artificial intelligence consultation service method and system based on deep learning | |
CN110287305B (en) | Intelligent question-answering management system based on natural language processing | |
CN116611471A (en) | Multi-party sharing system and method for deep learning large model | |
CN114186040A (en) | Operation method of intelligent robot customer service | |
CN110399473A (en) | The method and apparatus for determining answer for customer problem | |
Zhang et al. | Understanding citizens’ satisfaction with the government response during the COVID-19 pandemic in China: comprehensive analysis of the government hotline |
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 |