CN107807960A - Intelligent customer service method, electronic installation and computer-readable recording medium - Google Patents
Intelligent customer service method, electronic installation and computer-readable recording medium Download PDFInfo
- Publication number
- CN107807960A CN107807960A CN201710932603.9A CN201710932603A CN107807960A CN 107807960 A CN107807960 A CN 107807960A CN 201710932603 A CN201710932603 A CN 201710932603A CN 107807960 A CN107807960 A CN 107807960A
- Authority
- CN
- China
- Prior art keywords
- standard
- answer
- customer service
- word sequence
- typical problem
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of intelligent customer service method, belong to semantics recognition field.A kind of intelligent customer service method, comprises the following steps:S1, structure standard knowledge storehouse;S2, structure thesaurus;S3, the service conversation request for receiving client, and create the customer service conversation with the client;S4, the content to customer service conversation are analyzed, and obtain the analysis result of the user service session;S5, according to analysis result, the typical problem to match with the analysis result is found out from standard knowledge storehouse;The dimension where answer associated by S6, localization criteria problem, and push the answer that typical problem associates in the dimension.The present invention in knowledge base by increasing dimension, a typical problem is allowd to associate several different model answers on different dimensions, on this basis, realize area or the equipment used according to belonging to client is specific, provide the answer for meeting client's own situation, customer experience is improved, mitigates the pressure of human customer's customer service.
Description
Technical field
The present invention relates to semantics recognition field, is related to a kind of intelligent customer service method, electronic installation and computer-readable storage
Medium.
Background technology
With the rapid development of Internet, the raising of people's service awareness, network customer service has spread to all trades and professions, deep
Enter the links to everyday commerce service.
At present, common network client is generally made up of intelligent customer service robot and artificial customer service, wherein intelligent customer service machine
The problem of device people is by semantic analysis location client so that client talks as talking with natural person with robot, certainly
In right interaction specific area way to solve the problem is obtained by many forms.Compared to traditional customer service side
Formula, intelligent customer service can realize the 24-hour service with festivals or holidays round the clock, artificial customer service burden be shunted, so as to effectively reduce enterprise
The operation cost in customer service field.
Although intelligent customer service robot can quick response client to a certain extent demand, intelligent customer service robot
Thinking rely on knowledge base, only knowledge base maintenance improve and it is accurate, could make it that intelligent customer service robot is more clever, and
In order that accurate answer can be provided according to customer issue by obtaining intelligent customer service robot, and generally in knowledge base maintenance, a mark
The corresponding model answer of quasi- problem, and a typical problem can only be safeguarded once, in case intelligent robot is when selecting answer
It is at a loss as to what to do.
Therefore, existing enterprise, all can be suitable because of ground in formulation activity or product, each regional same campaign it is interior
Appearance may and differ, and for such case, knowledge base can not be safeguarded, and then cause intelligent customer service robot to face such a situation
Shi Wufa answers customer issue, can only rely on artificial customer service.
The content of the invention
The technical problem to be solved in the present invention be in order to overcome in the prior art intelligent customer service robot can not be directed to it is same
Individual problem provides the problem of different answers for meeting client institute possession, it is proposed that a kind of intelligent customer service method, electronic installation and meter
Calculation machine readable storage medium storing program for executing, by increasing dimension in knowledge base, so that intelligent customer service robot faces the client of different regions
Same problem when, can suitably provide different answers because of ground.
The present invention is that solve above-mentioned technical problem by following technical proposals:
A kind of intelligent customer service method, comprises the following steps:
S1, structure standard knowledge storehouse, are stored with some typical problems, the typical problem is closed in one or more dimensions
Join corresponding answer to form typical problem-answer set, and by typical problem be split as by some crucial phrases into word order
Row associate preservation with the typical problem;
S2, structure thesaurus, some clumps being made up of the near synonym of the standard word association standard words are stored with, it is described
Standard words are corresponding with the keyword in the typical problem;
S3, the service conversation request for receiving client, and create the customer service conversation with the client;
S4, the content to customer service conversation are analyzed, and obtain the analysis result of the user service session;
S5, according to analysis result, the standard to match with the analysis result is found out from the standard knowledge storehouse and is asked
Topic;
The dimension where answer associated by S6, localization criteria problem, and push what typical problem associated in the dimension
Answer.
Preferably, step S1 specifically include it is following step by step:
S11, collection simultaneously arrange problem and at least one answer to match with the problem;
S12, according to answer generate dimension;
S13, associate the answer corresponding with the dimension in one or more dimensions to problem, generation typical problem-
Answer set;
S14, typical problem split into by the word sequence being made up of several words by participle instrument;
S15, the stop words in word sequence removed, generate by some crucial phrases into word sequence and the typical problem close
UNPROFOR is deposited.
Preferably, step S2 specifically include it is following step by step:
Keyword in S21, extraction standard knowledge base in each typical problem;
S22, by all crucial phrases into keyword set be merged into row duplicate removal processing, obtain standard set of words;
S23, the successively standard words in extraction standard set of words, collect at least one nearly justice with the standard words similar import
Word, and the near synonym are associated to clump with the standard words and preserved.
Preferably, step S4 specifically include it is following step by step:
S41, participle, the content of customer service conversation is split into the word order being made up of several words using participle instrument
Row;
S42, extraction keyword, by removing the stop words in word sequence, generation only by crucial phrase into simplification word order
Row;
S43, synonym is replaced, judge to simplify the standard words whether keyword in word sequence belongs in thesaurus, if
It is not to replace the keyword with the standard words in thesaurus, generation only includes the standard word sequence of standard words;
S44, outputting standard word sequence.
Preferably, S43 specifically includes following sub-step step by step:
S431, obtain the keyword simplified in word sequence;
S432, the standard words in the keyword and thesaurus of acquisition are compared one by one;
S433, judge whether there is the standard words to match with the keyword in thesaurus, if then performing step
S435, if otherwise performing step S434;
S434, the keyword and the near synonym in thesaurus compared one by one, found out and the described keyword phase
Same synonym, and the standard words associated by the synonym are replaced into position of the keyword in word sequence is simplified;
S435, judge whether the keyword is last word in the simplified word sequence, if then performing step
S436, if otherwise performing step S431;
S436, generation only include the standard word sequence of standard words.
Preferably, step S5 specifically include it is following step by step:
S51, standard word sequence matched with the word sequence in standard knowledge storehouse, found out and the standard word sequence phase
The word sequence of matching;
S52, judge whether the quantity that the answer associated by the typical problem preserved is associated with the word sequence found out is more than 1,
If then performing step S6, step S6 is skipped and if directly exports the answer.
Preferably, step S6 specifically include it is following step by step:
S61, judge some answers of typical problem association where dimension whether can be obtained by automatic detection,
If then export dimension and perform step S64, if otherwise performing step S62;
S62, basis question closely rule to pushes customer problem to question closely the dimension where answer;
S63, the answer for receiving client, dimension is extracted from answer and is exported;
S64, the dimension according to output, push the answer that the typical problem associates in the dimension.
Preferably, the rule of questioning closely is specially:
When answer quantity is more than 3, using open enquirement;
When answer quantity is less than or equal to 3, putd question to using formula of enumerating.
A kind of electronic installation, including memory and processor, being stored with the memory can be by the computing device
Intelligent customer service system, the intelligent customer service system includes:
Standard knowledge storehouse, for storing some typical problems, the typical problem associates phase in one or more dimensions
Corresponding answer to form typical problem-answer set, and by typical problem be split as by some crucial phrases into word sequence with
Typical problem association preserves;
Thesaurus, for storing some clumps being made up of the near synonym of the standard word association standard words, the standard
Word is corresponding with the keyword in the typical problem;
Session connection module, the service conversation for receiving client is asked, and creates the customer service meeting with the client
Words;
Conversation analysis module, for analyzing the content of customer service conversation, obtain the user service session
Analysis result;
Matching module, for according to analysis result, being found out from the standard knowledge storehouse and the analysis result phase
The typical problem matched somebody with somebody;
Pushing module is positioned, for the dimension where the answer associated by localization criteria problem, and typical problem is pushed and exists
The answer associated in the dimension.
A kind of computer-readable recording medium, the computer-readable recording medium internal memory contain intelligent customer service system, institute
Stating intelligent customer service system can be performed by least one processor, so that at least one computing device is for example any one of foregoing
The step of described intelligent customer service method.
The positive effect of the present invention is:The present invention in knowledge base by increasing dimension so that a standard is asked
Topic can associate several different model answers on different dimensions, on this basis, realize specifically affiliated according to client
Area or the equipment used, provide the answer for meeting client's own situation, improve customer experience, mitigate human customer's customer service
Pressure.
Brief description of the drawings
Fig. 1 shows the hardware structure schematic diagram of the embodiment of electronic installation one of the present invention;
Fig. 2 shows the program module schematic diagram of the embodiment of intelligent customer service system one in electronic installation of the present invention;
Fig. 3 shows the flow chart of intelligent customer service method first embodiment of the present invention;
Fig. 4 shows the flow chart that standard knowledge storehouse is built in intelligent customer service method second embodiment of the present invention;
Fig. 5 shows the flow chart that thesaurus is built in intelligent customer service method 3rd embodiment of the present invention;
Fig. 6 shows the flow chart of conversation analysis in intelligent customer service method fourth embodiment of the present invention;
Fig. 7 shows the flow of the replacement synonym in conversation analysis in the embodiment of intelligent customer service method the 5th of the present invention
Figure;
Fig. 8 shows the flow chart matched in intelligent customer service method sixth embodiment of the present invention;
Fig. 9, which is shown, to be positioned in the embodiment of intelligent customer service method the 7th of the present invention and pushes the flow chart of answer.
Embodiment
The present invention is further illustrated below by the mode of embodiment, but does not therefore limit the present invention to described reality
Apply among a scope.
First, the present invention proposes a kind of electronic installation.
As shown in fig.1, it is the hardware structure schematic diagram of the embodiment of electronic installation one of the present invention.It is described in the present embodiment
Electronic installation 1 be it is a kind of can be automatic to carry out numerical computations and/or information processing according to the instruction for being previously set or storing
Equipment.For example, it may be smart mobile phone, tablet personal computer, notebook computer, desktop computer, rack-mount server, blade type take
It is engaged in device, tower server or Cabinet-type server (including independent server, or the server set that multiple servers are formed
Group) etc..As illustrated, the electronic installation 2 comprises at least, but it is not limited to, connection storage can be in communication with each other by system bus
Device 21, processor 22, network interface 23 and intelligent customer service system 20.Wherein:
The memory 21 comprises at least a type of computer-readable recording medium, and the readable storage medium storing program for executing includes
Flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memories etc.), random access storage device (RAM), it is static with
Machine access memory (SRAM), read-only storage (ROM), Electrically Erasable Read Only Memory (EEPROM), it is programmable only
Read memory (PROM), magnetic storage, disk, CD etc..In certain embodiments, the memory 21 can be the electricity
The internal storage unit of sub-device 2, such as the hard disk or internal memory of the electronic installation 2.In further embodiments, the memory
21 can also be the plug-in type hard disk being equipped with the External memory equipment of the electronic installation 2, such as the electronic installation 2, intelligence
Storage card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card)
Deng.Certainly, the memory 21 can also both include the internal storage unit of the electronic installation 2 or be set including its external storage
It is standby.In the present embodiment, the memory 21 is generally used for the operating system and types of applications that storage is installed on the electronic installation 2
Software, such as program code of the intelligent customer service system 20 etc..In addition, the memory 21 can be also used for temporarily storing
The Various types of data that has exported or will export.
The processor 22 can be in certain embodiments central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips.The processor 22 is generally used for controlling the electricity
The overall operation of sub-device 2, such as perform the control and processing related to the electronic installation 2 progress data interaction or communication
Deng.In the present embodiment, the processor 22 is used to run the program code stored in the memory 21 or processing data, example
Intelligent customer service system 20 as described in running.
The network interface 23 may include radio network interface or wired network interface, and the network interface 23 is generally used for
Communication connection is established between the electronic installation 2 and other electronic installations.For example, the network interface 23 is used to incite somebody to action by network
The electronic installation 2 is connected with exterior terminal, between the electronic installation 2 and exterior terminal establish data transmission channel and
Communication connection etc..The network can be intranet (Intranet), internet (Internet), global system for mobile telecommunications system
Unite (Global System of Mobile communication, GSM), WCDMA (Wideband Code
Division Multiple Access, WCDMA), 4G networks, 5G networks, bluetooth (Bluetooth), Wi-Fi etc. is wireless or has
Gauze network.
It is pointed out that Fig. 1 illustrate only the electronic installation 2 with component 21-23, it should be understood that not
It is required that implement all components shown, the more or less component of the implementation that can be substituted.
In the present embodiment, the intelligent customer service system 20 being stored in memory 21 can be divided into one or
Multiple program modules, one or more of program modules are stored in memory 11, and can be handled by one or more
Device (the present embodiment is processor 12) is performed, to complete the present invention.
For example, Fig. 2 shows the program module schematic diagram of the embodiment of intelligent customer service system 20 1, in the embodiment,
The intelligent customer service system 20 can be divided into standard knowledge storehouse 201, thesaurus 202, session connection module 203, session
Analysis module 204, matching module 205 and positioning pushing module 206.Wherein, the program module alleged by the present invention is to have referred to
Into the series of computation machine programmed instruction section of specific function, than program more suitable for describing the intelligent customer service system 20 described
Implementation procedure in electronic installation 1.Describe specifically to introduce the concrete function of the program module 201-206 below.
The standard knowledge storehouse 201, for storing some typical problems, the typical problem is in one or more dimensions
Corresponding answer is associated to form typical problem-answer set, and by typical problem be split as by some crucial phrases into word
Sequence associates preservation with the typical problem;
The thesaurus 202, for storing some clumps being made up of the near synonym of the standard word association standard words, institute
It is corresponding with the keyword in the typical problem to state standard words;
The session connection module 203, the service conversation for receiving client is asked, and creates the client with the client
Service conversation;
The conversation analysis module 204, for analyzing the content of customer service conversation, obtain the user service
The analysis result of session;
The matching module 205, for according to analysis result, finding out from the standard knowledge storehouse and being tied with the analysis
The typical problem that fruit matches;
The positioning pushing module 206, for the dimension where the answer associated by localization criteria problem, and pushes standard
The answer that problem associates in the dimension.
Intelligent customer service system described in the present embodiment 20 can by identifying the affiliated regional and used equipment of client,
Provide the answer for meeting client characteristics.Below with using the customer inquiries of Android mobile phone how by it is self-service handle participation certain activity
Exemplified by illustrated:
1st, the problem of service conversation being established by session connection module and client and receiving client;
2nd, by conversation analysis module, analyzed for the problem of client, by the problem be split as by crucial phrase into
Word sequence, and replaced with the standard words in thesaurus and the keywords of standard words be not belonging in word sequence, most client at last
Problem is expressed as the standard word sequence for only including standard words;
3rd, by matching module, find what word sequence matching in standard knowledge storehouse was associated according to standard word sequence
Typical problem;
4th, by positioning pushing module, the quantity of associated answer is more than 1 under first criterion problem, further sentences
It is Android system used in disconnected client, finally self-service handles flow to what is associated under pushes customer Android system dimension.
In the present embodiment, standard knowledge storehouse and thesaurus all to safeguard in systems, and can be according to actual feelings in advance
Condition makes corresponding modification, increase etc..
Secondly, the present invention proposes a kind of intelligent customer service method.
In the first embodiment, as shown in figure 3, described intelligent customer service method comprises the following steps:
S1, structure standard knowledge storehouse, are stored with some typical problems, the typical problem is closed in one or more dimensions
Join corresponding answer to form typical problem-answer set, and by typical problem be split as by some crucial phrases into word order
Row associate preservation with the typical problem;
S2, structure thesaurus, some clumps being made up of the near synonym of the standard word association standard words are stored with, it is described
Standard words are corresponding with the keyword in the typical problem;
S3, the service conversation request for receiving client, and create the customer service conversation with the client;
S4, the content to customer service conversation are analyzed, and obtain the analysis result of the user service session;
S5, according to analysis result, the standard to match with the analysis result is found out from the standard knowledge storehouse and is asked
Topic;
The dimension where answer associated by S6, localization criteria problem, and push what typical problem associated in the dimension
Answer.
It should be noted that the structure thesaurus built in standard knowledge storehouse and step S2 in step S1 is dimension in advance
In systems, without every time using all safeguarding once, as long as being safeguarded when content needs renewal, maintenance mode can be with for shield
It is that manual maintenance, system capture automatic safeguard or both after information and be combined maintenance automatically.
Based on above-mentioned first embodiment, in a second embodiment, as shown in figure 4, the step S1 specifically includes following point
Step:
S11, collection simultaneously arrange problem and at least one answer to match with the problem;
In the problem of collection, there may be the problem of a variety of question formulations to all point to identical answer, now needing will be multiple
A problem in problem is defined as typical problem and is stored in standard knowledge storehouse.
At least one answer referred herein, it is primarily referred to as, because system version is different, being related to some system process for using sides
The problem of face, has a different answers, or because from different places, the activity description of same campaign can difference, cause differently
Different answers is had during area's customer inquiries activity description.
S12, according to answer generate dimension;
Referring specifically to, an answer just corresponds to one dimension of generation, such as:System has three kinds of versions, respectively Android,
IOS and IE, then to generate tri- Android, IOS and IE dimensions.
S13, associate the answer corresponding with the dimension in one or more dimensions to problem, generation typical problem-
Answer set;
S12 explanation is connect, operating process corresponding in the association explanation under each dimension, that is, generates typical problem-answer
Collection.
S14, typical problem split into by the word sequence being made up of several words by participle instrument;
S15, the stop words in word sequence removed, generate by some crucial phrases into word sequence and the typical problem close
UNPROFOR is deposited.
Illustrated below by taking " old band is new " movable (i.e. frequent customer introduces new client's activity) as an example:
It is related to two typical problem-answer sets:
Typical problem one:What the movable present with New activity is always
Answer:1) A areas:Give 500 yuan of purchase cards;2) B areas:Give 300 yuan of telephone expenses.
Typical problem two:Self-service with New activity handles flow always
Answer:1) Android system:Click on the activity of this page lower right corner --- band is new always for selection ...;2) IOS systems:Click on
Band is new always for this page lower right corner activity --- selection ...;3) IE systems:Click on the activity in this page top menu --- choosing
It is new to select old band --- click on ....
For typical problem one, the maintenance process in standard knowledge storehouse is as follows:
1st, collect and arrange typical problem-answer set, i.e. typical problem:What the movable present with New activity is alwaysAnswer
Case:1) A areas:Give 500 yuan of purchase cards;2) B areas:Give 300 yuan of telephone expenses.
2nd, two dimensions, respectively A areas and B areas are generated according to answer.
3rd, answer " giving 500 yuan of purchase cards " is associated in the dimension of A areas, answer is associated in the dimension of B areas and " is given
300 yuan of telephone expenses ".
4th, typical problem one is split as " what the movable present with New activity is always ".
5th, generate word sequence " always with new present what " and associate preservation with the typical problem one.
For typical problem two, the maintenance process in standard knowledge storehouse is with typical problem one, and here is omitted.
Based on above-mentioned second embodiment, in the third embodiment, as shown in figure 5, the step S2 specifically includes following point
Step:
Keyword in S21, extraction standard knowledge base in each typical problem;
S22, by all crucial phrases into keyword set be merged into row duplicate removal processing, obtain standard set of words;
S23, the successively standard words in extraction standard set of words, collect at least one nearly justice with the standard words similar import
Word, and the near synonym are associated to clump with the standard words and preserved.
In the present embodiment, keyword in typical problem is defined as standard words, it is then some near to each standard word association
Adopted word, during so as to client according to respective word accustomed to using, non-standard words can be substituted for standard words by system, so by client
When problem matches typical problem, there can be more preferable matching effect, improve the accuracy of matching.
Example is connected, the maintenance process of thesaurus is as follows:
1st, " what the movable present with New activity is to extraction standard problem one always" in keyword it is " always assorted with new present
";" self-service with New activity handles flow to extraction standard problem two always" in keyword " old band new self-service handles flow ".
2nd, will " old band new " this keyword duplicate removal, obtaining standard set of words, " with new present, what self-service handles stream always
Journey ".
3rd, first collect always with new near synonym, can be " patron introduces new customer ", " frequent customer is with new client " etc., incite somebody to action
" old band is new " associates with the near synonym such as " patron introduces new customer ", " frequent customer is with new client " to save as always with new clump;Its
The composition of his keyword clump is the same as the composition always with new clump.
Based on above-mentioned 3rd embodiment, in the fourth embodiment, as shown in fig. 6, step S4 specifically include it is following step by step:
S41, participle, the content of customer service conversation is split into the word order being made up of several words using participle instrument
Row;
S42, extraction keyword, by removing the stop words in word sequence, generation only by crucial phrase into simplification word order
Row;
S43, synonym is replaced, judge to simplify the standard words whether keyword in word sequence belongs in thesaurus, if
It is not to replace the keyword with the standard words in thesaurus, generation only includes the standard word sequence of standard words;
S44, outputting standard word sequence.
Connect example, it is assumed that have client's inlet wire inquiry band New activity always, problem is " may I ask me to introduce my friend to participate in band always new
Activity, I can obtain any present", the flow of conversation analysis is illustrated as example:
1st, the problem of client, " may I ask me and introduces my the old band New activity of friend's participation, what prize I can obtain" tear open
It is divided into the word sequence of " may I ask me introduce my friend participate in old what present I can obtain with New activity ".
2nd, the keyword " old what new prize of band " in foregoing word sequence is extracted.
3rd, " prize " use " present " in aforementioned simplified word sequence is replaced, " old band newly gives anything to generation standard word sequence
Product ".
4th, outputting standard word sequence " old what new present of band ".
Based on above-mentioned fourth embodiment, in the 5th embodiment, as shown in fig. 7, S43 specifically includes following sub-step step by step
Suddenly:
S431, obtain the keyword simplified in word sequence;
S432, the standard words in the keyword and thesaurus of acquisition are compared one by one;
S433, judge whether there is the standard words to match with the keyword in thesaurus, if then performing step
S435, if otherwise performing step S434;
S434, the keyword and the near synonym in thesaurus compared one by one, found out and the described keyword phase
Same synonym, and the standard words associated by the synonym are replaced into position of the keyword in word sequence is simplified;
S435, judge whether the keyword is last word in the simplified word sequence, if then performing step
S436, if otherwise performing step S431;
S436, generation only include the standard word sequence of standard words.
Example is connected, was replaced by simplifying to illustrate exemplified by word sequence " old what new prize of band " is replaced synonym
Journey:
1st, first keyword " old band is new " simplified in word sequence " old what new prize of band " is obtained;
2nd, keyword " old band is new " is compared with the standard words in thesaurus, finds the same word " old band is new ";
3rd, it is not last word in simplified word sequence " old what new prize of band " to judge keyword " old band is new ";
4th, second keyword " what " simplified in word sequence " old what new prize of band " is obtained;
5th, keyword " what " is compared with the standard words in thesaurus, finds the same word " what ";
6th, it is not last word in simplified word sequence " old what new prize of band " to judge keyword " what ";
7th, the 3rd keyword " prize " simplified in word sequence " old what new prize of band " is obtained;
8th, keyword " prize " is compared with the standard words in thesaurus, does not find the same word;
9th, keyword " prize " is compared with the near synonym in thesaurus, finds the same word " prize ", word
The standard words " present " of " prize " association replace the keyword " prize " simplified in word sequence;
10th, it is last word in simplified word sequence " old what new prize of band " to judge keyword " prize ";
11st, standard word sequence " old what new present of band " is generated.
Based on above-mentioned 5th embodiment, in the sixth embodiment, as shown in figure 8, step S5 specifically include it is following step by step:
S51, standard word sequence matched with the word sequence in standard knowledge storehouse, found out and the standard word sequence phase
The word sequence of matching;
S52, judge whether the quantity that the answer associated by the typical problem preserved is associated with the word sequence found out is more than 1,
If then performing step S6, step S6 is skipped and if directly exports the answer.
Example is connected, standard word sequence " old what new present of band " is matched with the word sequence in standard knowledge storehouse;
1st, standard word sequence " old band new what present " and word sequence " always with new present what " phase in standard knowledge storehouse
Matching;
2nd, the associated typical problem of the word sequence in standard knowledge storehouse " always with new present what " is " always with New activity
What movable present is", judge that this typical problem is corresponding with two answers.
Based on above-mentioned sixth embodiment, in the 7th embodiment, as shown in figure 9, step S6 specifically include it is following step by step:
S61, judge some answers of typical problem association where dimension whether can be obtained by automatic detection,
If then export dimension and perform step S64, if otherwise performing step S62;
S62, basis question closely rule to pushes customer problem to question closely the dimension where answer;
S63, the answer for receiving client, dimension is extracted from answer and is exported;
S64, the dimension according to output, push the answer that the typical problem associates in the dimension.
Example is connected, so that " what the movable present with New activity is always to the pushes customer typical problem in A areas" answer
Exemplified by illustrate the flow that answer is positioned and pushed:
1st, the dimension of the typical problem is A areas and B areas, can not be obtained automatically by system;
2nd, to its possession of customer inquiries, because answer quantity is 2, it can use and enumerate formula enquirement, such as to client
" may I ask you is A areas or B areas for enquirement”
3rd, receive client and answer " I stays in A areas ", extract the keyword " A areas " during the client answers and export;
4th, to pushes customer typical problem, " what the movable present with New activity is always" answer in the dimension of A areas,
Push answer " giving 500 yuan of purchase cards ".
It should be noted that in the present embodiment, in order to allow client answer as far as possible with the keyword in model answer
Match, rule can be questioned closely using following:When answer quantity is more than 3, using open enquirement;When answer quantity is less than
Or during equal to 3, putd question to using formula of enumerating.Because the answer corresponding to upper example Plays problem only has 2, so recommending to adopt
Putd question to formula of enumerating.
In addition, a kind of computer-readable recording medium of the present invention, the computer-readable recording medium internal memory contain intelligent visitor
Dress system 20, when the intelligent customer service system 20 can be executed by one or more processors, realize above-mentioned intelligent customer service method or electricity
The operation of sub-device.
Although the embodiment of the present invention is the foregoing described, it will be appreciated by those of skill in the art that this is only
For example, protection scope of the present invention is to be defined by the appended claims.Those skilled in the art without departing substantially from
On the premise of the principle and essence of the present invention, various changes or modifications can be made to these embodiments, but these changes and
Modification each falls within protection scope of the present invention.
Claims (10)
- A kind of 1. intelligent customer service method, it is characterised in that comprise the following steps:S1, structure standard knowledge storehouse, are stored with some typical problems, the typical problem associates phase in one or more dimensions Corresponding answer to form typical problem-answer set, and by typical problem be split as by some crucial phrases into word sequence with Typical problem association preserves;S2, structure thesaurus, are stored with some clumps being made up of the near synonym of the standard word association standard words, the standard Word is corresponding with the keyword in the typical problem;S3, the service conversation request for receiving client, and create the customer service conversation with the client;S4, the content to customer service conversation are analyzed, and obtain the analysis result of the user service session;S5, according to analysis result, the typical problem to match with the analysis result is found out from the standard knowledge storehouse;The dimension where answer associated by S6, localization criteria problem, and push the answer that typical problem associates in the dimension.
- 2. intelligent customer service method according to claim 1, it is characterised in that step S1 specifically include it is following step by step:S11, collection simultaneously arrange problem and at least one answer to match with the problem;S12, according to answer generate dimension;S13, the answer corresponding with the dimension is associated in one or more dimensions to problem, generate typical problem-answer Collection;S14, typical problem split into by the word sequence being made up of several words by participle instrument;S15, by word sequence stop words remove, generate by some crucial phrases into word sequence associate guarantor with the typical problem Deposit.
- 3. intelligent customer service method according to claim 1, it is characterised in that step S2 specifically include it is following step by step:Keyword in S21, extraction standard knowledge base in each typical problem;S22, by all crucial phrases into keyword set be merged into row duplicate removal processing, obtain standard set of words;S23, the successively standard words in extraction standard set of words, at least one near synonym with the standard words similar import are collected, And the near synonym are associated to clump with the standard words and preserved.
- 4. intelligent customer service method according to claim 3, it is characterised in that step S4 specifically include it is following step by step:S41, participle, the content of customer service conversation is split into the word sequence being made up of several words using participle instrument;S42, extraction keyword, by removing the stop words in word sequence, generation only by crucial phrase into simplification word sequence;S43, synonym is replaced, judge to simplify the standard words whether keyword in word sequence belongs in thesaurus, if not The keyword then is replaced with the standard words in thesaurus, generation only includes the standard word sequence of standard words;S44, outputting standard word sequence.
- 5. intelligent customer service method according to claim 4, it is characterised in that S43 specifically includes following sub-step step by step:S431, obtain the keyword simplified in word sequence;S432, the standard words in the keyword and thesaurus of acquisition are compared one by one;S433, judge whether there is the standard words to match with the keyword in thesaurus, if then performing step S435, if Otherwise step S434 is performed;S434, the keyword and the near synonym in thesaurus compared one by one, found out and the described keyword identical Synonym, and the standard words associated by the synonym are replaced into position of the keyword in word sequence is simplified;S435, judge whether the keyword is last word in the simplified word sequence, if then performing step S436, if Otherwise step S431 is performed;S436, generation only include the standard word sequence of standard words.
- 6. intelligent customer service method according to claim 4, it is characterised in that step S5 specifically include it is following step by step:S51, standard word sequence matched with the word sequence in standard knowledge storehouse, find out and match with the standard word sequence Word sequence;S52, judge whether the quantity that the answer associated by the typical problem preserved is associated with the word sequence found out is more than 1, if Step S6 is then performed, step S6 is skipped and if directly exports the answer.
- 7. intelligent customer service method according to claim 6, it is characterised in that step S6 specifically include it is following step by step:S61, judge some answers of typical problem association where dimension whether can be obtained by automatic detection, if Then export dimension and perform step S64, if otherwise performing step S62;S62, basis question closely rule to pushes customer problem to question closely the dimension where answer;S63, the answer for receiving client, dimension is extracted from answer and is exported;S64, the dimension according to output, push the answer that the typical problem associates in the dimension.
- 8. intelligent customer service method according to claim 7, it is characterised in that the rule of questioning closely is specially:When answer quantity is more than 3, using open enquirement;When answer quantity is less than or equal to 3, putd question to using formula of enumerating.
- 9. a kind of electronic installation, including memory and processor, it is characterised in that being stored with the memory can be by the place The intelligent customer service system that device performs is managed, the intelligent customer service system includes:Standard knowledge storehouse, for storing some typical problems, the typical problem associates corresponding in one or more dimensions Answer to form typical problem-answer set, and by typical problem be split as by some crucial phrases into word sequence and the mark Quasi- problem association preserves;Thesaurus, for storing some clumps being made up of the near synonym of the standard word association standard words, the standard words with Keyword in the typical problem is corresponding;Session connection module, the service conversation for receiving client is asked, and creates the customer service conversation with the client;Conversation analysis module, for analyzing the content of customer service conversation, obtain the analysis of the user service session As a result;Matching module, for according to analysis result, finding out what is matched with the analysis result from the standard knowledge storehouse Typical problem;Pushing module is positioned, for the dimension where the answer associated by localization criteria problem, and pushes typical problem in the dimension The answer associated on degree.
- 10. a kind of computer-readable recording medium, it is characterised in that the computer-readable recording medium internal memory contains intelligent visitor Dress system, the intelligent customer service system can be performed by least one processors, so that at least one computing device is such as The step of intelligent customer service method any one of claim 1-8.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710932603.9A CN107807960B (en) | 2017-09-30 | 2017-09-30 | Intelligent customer service method, electronic device and computer readable storage medium |
PCT/CN2018/083081 WO2019062078A1 (en) | 2017-09-30 | 2018-04-13 | Smart customer service method, electronic apparatus and computer-readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710932603.9A CN107807960B (en) | 2017-09-30 | 2017-09-30 | Intelligent customer service method, electronic device and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107807960A true CN107807960A (en) | 2018-03-16 |
CN107807960B CN107807960B (en) | 2020-05-12 |
Family
ID=61584874
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710932603.9A Active CN107807960B (en) | 2017-09-30 | 2017-09-30 | Intelligent customer service method, electronic device and computer readable storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107807960B (en) |
WO (1) | WO2019062078A1 (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108197963A (en) * | 2018-03-28 | 2018-06-22 | 广州市菲玛尔咨询服务有限公司 | A kind of intelligent customer service manages system |
CN108984777A (en) * | 2018-07-25 | 2018-12-11 | 北京京东尚科信息技术有限公司 | Customer service method, apparatus and computer readable storage medium |
WO2019062078A1 (en) * | 2017-09-30 | 2019-04-04 | 平安科技(深圳)有限公司 | Smart customer service method, electronic apparatus and computer-readable storage medium |
CN109685628A (en) * | 2018-12-27 | 2019-04-26 | 北京百佑科技有限公司 | Information sharing apparatus and system |
CN109684461A (en) * | 2018-12-30 | 2019-04-26 | 联想(北京)有限公司 | A kind of data processing method and device |
CN110399469A (en) * | 2018-04-23 | 2019-11-01 | 中国电信股份有限公司 | Customer service robot understands performance detection fusion method and apparatus |
CN110472024A (en) * | 2019-07-11 | 2019-11-19 | 北京云迹科技有限公司 | For the configuration of the customized question and answer of robot, processing method and device, robot |
CN111078832A (en) * | 2019-11-08 | 2020-04-28 | 杭州九阳小家电有限公司 | Auxiliary response method and system for intelligent customer service |
CN111159372A (en) * | 2019-12-24 | 2020-05-15 | 合肥凌极西雅电子科技有限公司 | Question-answering system applied to pragmatic education |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130073277A1 (en) * | 2011-09-21 | 2013-03-21 | Pket Llc | Methods and systems for compiling communication fragments and creating effective communication |
CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
CN104731895A (en) * | 2015-03-18 | 2015-06-24 | 北京京东尚科信息技术有限公司 | Auto-answer method and device |
CN104933204A (en) * | 2015-07-15 | 2015-09-23 | 武汉杰宇天成文化咨询服务有限公司 | Intelligent network response method and device |
CN105117387A (en) * | 2015-09-21 | 2015-12-02 | 上海智臻智能网络科技股份有限公司 | Intelligent robot interaction system |
CN105893465A (en) * | 2016-03-28 | 2016-08-24 | 北京京东尚科信息技术有限公司 | Automatic question answering method and device |
CN106528759A (en) * | 2016-11-04 | 2017-03-22 | 上海智臻智能网络科技股份有限公司 | Information processing method and device for intelligent question-answering system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107807960B (en) * | 2017-09-30 | 2020-05-12 | 平安科技(深圳)有限公司 | Intelligent customer service method, electronic device and computer readable storage medium |
-
2017
- 2017-09-30 CN CN201710932603.9A patent/CN107807960B/en active Active
-
2018
- 2018-04-13 WO PCT/CN2018/083081 patent/WO2019062078A1/en active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130073277A1 (en) * | 2011-09-21 | 2013-03-21 | Pket Llc | Methods and systems for compiling communication fragments and creating effective communication |
CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
CN104731895A (en) * | 2015-03-18 | 2015-06-24 | 北京京东尚科信息技术有限公司 | Auto-answer method and device |
CN104933204A (en) * | 2015-07-15 | 2015-09-23 | 武汉杰宇天成文化咨询服务有限公司 | Intelligent network response method and device |
CN105117387A (en) * | 2015-09-21 | 2015-12-02 | 上海智臻智能网络科技股份有限公司 | Intelligent robot interaction system |
CN105893465A (en) * | 2016-03-28 | 2016-08-24 | 北京京东尚科信息技术有限公司 | Automatic question answering method and device |
CN106528759A (en) * | 2016-11-04 | 2017-03-22 | 上海智臻智能网络科技股份有限公司 | Information processing method and device for intelligent question-answering system |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019062078A1 (en) * | 2017-09-30 | 2019-04-04 | 平安科技(深圳)有限公司 | Smart customer service method, electronic apparatus and computer-readable storage medium |
CN108197963A (en) * | 2018-03-28 | 2018-06-22 | 广州市菲玛尔咨询服务有限公司 | A kind of intelligent customer service manages system |
CN110399469A (en) * | 2018-04-23 | 2019-11-01 | 中国电信股份有限公司 | Customer service robot understands performance detection fusion method and apparatus |
CN110399469B (en) * | 2018-04-23 | 2022-02-15 | 中国电信股份有限公司 | Customer service robot understanding performance detection fusion method and device |
CN108984777A (en) * | 2018-07-25 | 2018-12-11 | 北京京东尚科信息技术有限公司 | Customer service method, apparatus and computer readable storage medium |
CN108984777B (en) * | 2018-07-25 | 2021-04-30 | 北京京东尚科信息技术有限公司 | Customer service method, apparatus and computer-readable storage medium |
CN109685628A (en) * | 2018-12-27 | 2019-04-26 | 北京百佑科技有限公司 | Information sharing apparatus and system |
CN109684461A (en) * | 2018-12-30 | 2019-04-26 | 联想(北京)有限公司 | A kind of data processing method and device |
CN110472024A (en) * | 2019-07-11 | 2019-11-19 | 北京云迹科技有限公司 | For the configuration of the customized question and answer of robot, processing method and device, robot |
CN111078832A (en) * | 2019-11-08 | 2020-04-28 | 杭州九阳小家电有限公司 | Auxiliary response method and system for intelligent customer service |
CN111159372A (en) * | 2019-12-24 | 2020-05-15 | 合肥凌极西雅电子科技有限公司 | Question-answering system applied to pragmatic education |
Also Published As
Publication number | Publication date |
---|---|
CN107807960B (en) | 2020-05-12 |
WO2019062078A1 (en) | 2019-04-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107807960A (en) | Intelligent customer service method, electronic installation and computer-readable recording medium | |
CN107688667A (en) | Intelligent robot client service method, electronic installation and computer-readable recording medium | |
CN108509477B (en) | Method for recognizing semantics, electronic device and computer readable storage medium | |
CN104090886B (en) | The method that structure user draws a portrait in real time and device | |
CN107832291A (en) | Client service method, electronic installation and the storage medium of man-machine collaboration | |
CN106649742A (en) | Database maintenance method and device | |
CN109408811B (en) | Data processing method and server | |
CN108509476A (en) | Problem associates method for pushing, electronic device and computer readable storage medium | |
CN103400054A (en) | Computer-assisted psychological consulting automatic question-answering robot system | |
CN107679082A (en) | Question and answer searching method, device and electronic equipment | |
CN106970912A (en) | Chinese sentence similarity calculating method, computing device and computer-readable storage medium | |
CN110347724A (en) | Abnormal behaviour recognition methods, device, electronic equipment and medium | |
CN110795697B (en) | Method and device for acquiring logic expression, storage medium and electronic device | |
CN110348991A (en) | Assess the method, apparatus and electronic equipment of user's accrediting amount upper limit | |
CN109508367A (en) | Automatically extract the method, on-line intelligence customer service system and electronic equipment of question and answer corpus | |
CN109150585A (en) | A kind of network O&M failure solution, system, device and storage medium | |
CN114936727A (en) | Work order distribution system, method and computer equipment | |
CN110427453A (en) | Similarity calculating method, device, computer equipment and the storage medium of data | |
CN113486166B (en) | Construction method, device and equipment of intelligent customer service robot and storage medium | |
CN107527289A (en) | A kind of investment combination industry distribution method, apparatus, server and storage medium | |
CN111931503B (en) | Information extraction method and device, equipment and computer readable storage medium | |
CN110069686A (en) | User behavior analysis method, apparatus, computer installation and storage medium | |
CN109376287A (en) | House property map construction method, device, computer equipment and storage medium | |
CN110287290A (en) | Based on marketing clue extracting method, device and the computer readable storage medium for reading understanding | |
CN107832374A (en) | Construction method, electronic installation and the storage medium in standard knowledge storehouse |
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 |