CN109684455A - The implementation method and device of intelligent customer service system, equipment, readable storage medium storing program for executing - Google Patents
The implementation method and device of intelligent customer service system, equipment, readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109684455A CN109684455A CN201811611196.2A CN201811611196A CN109684455A CN 109684455 A CN109684455 A CN 109684455A CN 201811611196 A CN201811611196 A CN 201811611196A CN 109684455 A CN109684455 A CN 109684455A
- Authority
- CN
- China
- Prior art keywords
- customer service
- user
- response message
- information
- intensity value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 230000004044 response Effects 0.000 claims abstract description 179
- 230000036651 mood Effects 0.000 claims abstract description 85
- 230000004927 fusion Effects 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 20
- 230000005540 biological transmission Effects 0.000 claims abstract description 19
- 238000012790 confirmation Methods 0.000 claims abstract description 14
- 230000008451 emotion Effects 0.000 claims description 192
- 230000002996 emotional effect Effects 0.000 claims description 101
- 238000011156 evaluation Methods 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 22
- 230000009191 jumping Effects 0.000 claims description 5
- 238000012546 transfer Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 12
- 238000000605 extraction Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000007812 deficiency Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 210000001367 artery Anatomy 0.000 description 2
- 230000001427 coherent effect Effects 0.000 description 2
- 230000008909 emotion recognition Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 229910052709 silver Inorganic materials 0.000 description 2
- 239000004332 silver Substances 0.000 description 2
- 210000003462 vein Anatomy 0.000 description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 230000001314 paroxysmal effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of implementation method of intelligent customer service system, the described method comprises the following steps: when carrying out current sessions, inputting information according to the user that user terminal is sent, generates standard response message and mood response message；The standard response message is merged with the mood response message, generates fusion response message；By the fusion response message and presets artificial customer service entrance option and be sent to user terminal；When the selection confirmation instruction for the default artificial customer service entrance option for receiving user terminal transmission, artificial customer service module is jumped to, to carry out manual answering's processing.The present invention also provides realization device, equipment, the readable storage medium storing program for executing of a kind of intelligent customer service system.The present invention solve the problems, such as existing intelligent customer service system there is technical issues that robot customer service soothing effect it is limited, can not be really.
Description
Technical field
The present invention relates to the implementation method and device of intelligent customer service technical field more particularly to a kind of intelligent customer service system,
Equipment, readable storage medium storing program for executing.
Background technique
With the continuous growth of mobile Internet userbase, more and more online intelligent customer service systems of enterprise pass through
The combination of robot customer service and artificial customer service improves working efficiency, promotes user service experience.Compared with artificial customer service, machine
People's customer service have have a good memory, knowledge point is easy to expand, response rapidly, the advantages such as continuous service in 24 hours, but to having
Particularity, paroxysmal customer problem cannot be handled well；Compared with robot customer service, artificial customer service has personalized, essence
The advantages such as quasi- service, but response speed is compared with slow, energy is limited.
Emotion identification has been applied to intelligent customer service field.Currently, after most of robot customer services identify user emotion,
Mechanical, dull, the duplicate answer of robot customer service can be targetedly changed, warmer, warm answer is suitably provided, reduces
The negative emotions of user.Intelligent customer service system still has the application of Emotion identification at present pacify if art is limited, Wu Fada
Level, the deficiency that can not really solve the problems, such as to artificial customer service.How to solve existing for existing intelligent customer service system it is above-mentioned not
Foot place, and the actual effect that user emotion is pacified is improved, have become a significant concern point in intelligent customer service field.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of implementation method of intelligent customer service system and device, equipment, readable deposit
Storage media, it is intended to solve the problems, such as existing intelligent customer service system there are robot customer service soothing effects it is limited, can not really solve
Technical problem.
To achieve the above object, the present invention provides a kind of implementation method of intelligent customer service system, and the method includes following
Step:
When carrying out current sessions, information is inputted according to the user that user terminal is sent, generates standard response message and mood
Response message；
The standard response message is merged with the mood response message, generates fusion response message；
By the fusion response message and presets artificial customer service entrance option and be sent to user terminal；
When the selection confirmation instruction for the default artificial customer service entrance option for receiving user terminal transmission, artificial visitor is jumped to
Module is taken, to carry out manual answering's processing.
Preferably, the user sent according to user terminal inputs information, generates standard response message and mood response letter
The step of breath, specifically includes:
Information is inputted according to the user that user terminal is sent, generates standard response message；
Identify user emotion type；
If user emotion type is negative emotions, information is inputted according to the user, determines the concrete kind of user emotion
Other and emotional intensity value；
According to the specific category of user emotion and emotional intensity value, the mood response message is generated.
It is preferably, described when the selection confirmation instruction for the default artificial customer service entrance option for receiving user terminal transmission,
After the step of jumping to artificial customer service module, further includes:
Preset kind information relevant to user emotion is extracted, and the preset kind information is sent to artificial customer service mould
The default secondary page of block, to show the preset kind information in the secondary page；
Wherein, the preset kind information includes at least the specific category and emotional intensity value, current sessions of user emotion
Session information.
Preferably, described to jump to artificial customer service module, so as to also be wrapped after the step of artificial customer service carries out reply process
It includes:
It obtains to the specific category of the user emotion and the artificial evaluation data of emotional intensity value；
According to the artificial evaluation data, judge whether the specific category of the user emotion and emotional intensity value accord with respectively
Close default precise conditions；
If it is not, then obtaining the nominal data of the concrete type and emotional intensity value to the user emotion respectively；
According to the nominal data, the concrete type and emotional intensity value of the user emotion are demarcated and updated respectively.
Preferably, described according to the nominal data, the concrete type and feelings of the user emotion are demarcated and updated respectively
After the step of thread intensity value, further includes:
Concrete type and the mood for saving the session information of current sessions and the user emotion of updated current sessions are strong
Angle value is into default tranining database.
In addition, to achieve the above object, the present invention also provides a kind of realization device of intelligent customer service system, described device packets
It includes:
Response message generation unit inputs information according to the user that user terminal is sent, generates mark when carrying out current sessions
Quasi- response message and mood response message；
Response message integrated unit, it is raw for merging the standard response message with the mood response message
At fusion response message；
Transmission unit, for by the fusion response message and presetting artificial customer service entrance option and being sent to user terminal；
Jump-transfer unit, for the selection confirmation instruction when the default artificial customer service entrance option for receiving user terminal transmission
When, artificial customer service module is jumped to, to carry out manual answering's processing.
Preferably, the response message generation unit includes:
Standard response message subelement, the user for being sent according to user terminal input information, generate standard response message；
Type of emotion identifies subelement, for identification user emotion type；
Mood response message subelement, for being inputted and being believed according to the user when user emotion type is negative emotions
Breath, determines the specific category and emotional intensity value of user emotion；According to the specific category of user emotion and emotional intensity value, generate
The mood response message.
Preferably, described device further includes information extracting unit；
The information extracting unit, for extracting relevant to user emotion preset kind information, and by the default class
Type information is sent to the default secondary page of artificial customer service module, to show the preset kind information in the secondary page；
Wherein, the preset kind information includes at least the specific category and emotional intensity value, current sessions of user emotion
Session information.
Preferably, described device further includes calibration unit；
The calibration unit, for obtaining the artificial review number of specific category and emotional intensity value to the user emotion
According to；According to the artificial evaluation data, it is pre- to judge whether the specific category of the user emotion and emotional intensity value meet respectively
If precise conditions；If it is not, then obtaining the nominal data of the concrete type and emotional intensity value to the user emotion respectively；According to
The concrete type and emotional intensity value of the user emotion are demarcated respectively and updated to the nominal data.
Preferably, described device further includes storage unit；
The storage unit, for saving the session information of current sessions and the user emotion of updated current sessions
Concrete type and emotional intensity value are into default tranining database.
In addition, to achieve the above object, the present invention also provides a kind of terminal device, the terminal device include: memory,
Processor and the realization program for being stored in the intelligent customer service system that can be run on the memory and on the processor, it is described
The realization program of intelligent customer service system realizes the implementation method of intelligent customer service system as described above when being executed by the processor
The step of.
In addition, to achieve the above object, the present invention also provides a kind of readable storage medium storing program for executing, being deposited on the readable storage medium storing program for executing
The realization program of intelligent customer service system is contained, the realization program of the intelligent customer service system realizes institute as above when being executed by processor
The step of implementation method for the intelligent customer service system stated.
The embodiment of the present invention proposes the implementation method and device, equipment, readable storage medium storing program for executing of a kind of intelligent customer service system, first
Reply process is carried out by robot customer service module, information is inputted according to user, generates standard response message；In identification user emotion
When type is negative emotions, corresponding mood response message is further generated, and by mood response message and standard response message
It is merged, the fusion response message of generation is used as response message.In this way, helping to improve reply process efficiency and reducing artificial
It relies on.Offer is preset artificial customer service entrance option and is selected to user simultaneously, needs artificial customer service manually to be answered in user
When answering processing, the selection option based on user jumps to the artificial customer service module of intelligent customer service system, to carry out at manual answering
Reason.To while making robot customer service reply process, increase after judging user emotion type for negative emotions
The user of manual answering's processing selects option, can take into account the efficiency of reply process, also avoid the robot customer service of duration
Response facilitates the negative emotions for alleviating user, to improve the actual effect that user emotion is pacified.
Detailed description of the invention
Fig. 1 is the device structure schematic diagram for the hardware running environment that the realization equipment of intelligent customer service system of the present invention is related to；
Fig. 2 is the flow diagram of the implementation method first embodiment of intelligent customer service system of the present invention；
Fig. 3 is the refinement step process of the step S10 in the implementation method first embodiment of intelligent customer service system of the present invention
Schematic diagram；
Fig. 4 is the flow diagram of the implementation method second embodiment of intelligent customer service system of the present invention；
Fig. 5 is the flow diagram of the implementation method 3rd embodiment of intelligent customer service system of the present invention；
Fig. 6 is the realization schematic diagram of the implementation method of intelligent customer service system of the present invention；
Fig. 7 is that the functional unit of the realization device first embodiment of intelligent customer service of the present invention dress forms schematic diagram；
Fig. 8 is that the functional unit of the realization device second embodiment of intelligent customer service of the present invention dress forms schematic diagram；
Fig. 9 is that the functional unit of the realization device 3rd embodiment of intelligent customer service of the present invention dress forms schematic diagram.
The object of the invention is realized, the embodiments will be further described with reference to the accompanying drawings for functional characteristics and advantage.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, Fig. 1 is the device structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to.
The realization equipment of intelligent customer service system of the embodiment of the present invention can be PC machine or server.
As shown in Figure 1, the equipment may include: processor 1001, such as CPU, network interface 1004, user interface
1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing the connection communication between these components.
User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard), optional user interface
1003 can also include standard wireline interface and wireless interface.Network interface 1004 optionally may include that the wired of standard connects
Mouth, wireless interface (such as WI-FI interface).Memory 1005 can be high speed RAM memory, be also possible to stable memory
(non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned processor
1001 storage device.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of terminal structure shown in Fig. 1, can wrap
It includes than illustrating more or fewer components, perhaps combines certain components or different component layouts.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage medium
Believe the realization program of module, Subscriber Interface Module SIM and intelligent customer service system.
In terminal shown in Fig. 1, network interface 1004 is mainly used for connecting background server, carries out with background server
Data communication；User interface 1003 is mainly used for connecting client (user terminal), carries out data communication with client；And processor
1001 can be used for calling the realization program of the intelligent customer service system stored in memory 1005, and execute following intelligent customer service systems
Operation in the implementation method embodiment of system.
Based on above-mentioned hardware configuration, the implementation method embodiment of intelligent customer service system of the present invention is proposed.
The present invention provides a kind of implementation method of intelligent customer service system.
Fig. 2 is referred to, Fig. 2 is the flow diagram of the first embodiment of the implementation method of intelligent customer service system of the present invention.
In the present embodiment, it the described method comprises the following steps:
Step S10 inputs information according to the user that user terminal is sent, generates standard response letter when carrying out current sessions
Breath and mood response message；
In the specific implementation, user terminal refers to when carrying out current sessions with intelligent customer service system, end used by a user
Jaws equipment/software, such as page end or operate in application program on mobile terminal (such as mobile phone, tablet computer).Carry out
When current sessions, user inputs related session information in user terminal, and concrete form can be text, voice or other types
Information.Intelligent customer service system mainly includes robot customer service module and artificial customer service module.
It is same can to input information according to user after receiving the user that user terminal is sent and inputting information for robot customer service module
Shi Shengcheng standard response message and mood response message.In the present embodiment, as shown in figure 3, providing a kind of preferred embodiment party
Formula specifically includes:
Step S11 inputs information according to the user that user terminal is sent, generates standard response message；
Information is inputted according to the user that user terminal is sent, the implementation for generating standard response message is the prior art, example
Information can be such as inputted to user carries out sentence segmentation, keyword extraction, semantic analysis processing；By keyword and/or semanteme
Analysis result is matched with the model answer data of standard database, to be exactly matched or the highest mark of matching degree
Quasi- answer data, and then standard response message is generated according to model answer data.
Standard response message can be considered the standardization return information that information is inputted to a certain user, be mainly used for user
Real demand/intention/problem carry out response.
In a specific implementation, different " problem " can be matched with corresponding " standard response message " in advance, and
Construct corresponding standard reply data library.After analyzing demand/intention/problem of user, the demand of user/is intended to/to ask
Topic is standardized input, carries out matching inquiry in standard reply data library, is asked with finding out and the demand of user/intention/
Inscribe matched standard response.After successful search goes out matched standard response, extracts the standard response and generate standard response letter
Breath.
For example, user inputs that information is " you can handle loan transaction at bank's several points? ", then keyword " silver is extracted
Row ", " several points ", " handling ", " loan ", and then analyze the user and need to inquire that loan transaction is handled in the local site of this bank
Time.The demand of user is standardized input, is carrying out matching inquiry in standard reply data library, with find out with
" handling the loan transaction time in the local site of this bank " matched standard response, such as " handle loan in the local site of this bank
The money business hours is 9:00 to 16:00 ".
Step S12 identifies user emotion type；
After generation standard response message, information is inputted according to user, identifies the type of emotion of active user.Wherein,
Type of emotion may include: positive mood, neutral mood, negative emotions.Information, which is inputted, according to user identifies active user's
The specific implementation of type of emotion can be according to different modes, such as can first obtain sensitive word, language that user inputs in information
Gas auxiliary word, punctuation mark and/or user input the transmission frequency of information, and then according to sensitive word, auxiliary words of mood, punctuation mark
And/or user inputs the transmission frequency of information and one or more of works as and to carry out type of emotion analysis, to identify user's feelings
Thread type.
For example, for user input information be " you can handle loan transaction at bank's several points? ", include based on the information
Sensitive word, auxiliary words of mood, punctuation mark and/or user input the transmission frequency of information, analysis user emotion type is neutrality
Mood.For user input information be " several points can handle loan transaction actually for your this bank??? ", it is based on the packet
The sensitive word (as " actually ") that contains, auxiliary words of mood, punctuation mark (as "??? ") and/or user input information transmission frequency, point
Analysis user emotion type is negative emotions.
Step S13 inputs information according to the user, determines user emotion if user emotion type is negative emotions
Specific category and emotional intensity value；
Specifically, when determine active user type of emotion be negative emotions when, based on it is pre-establishing, comprising mood know
User is inputted information input into prediction model, and carries out relevant data processing and inversion by the prediction model of other algorithm, into
And determine the specific category and emotional intensity value of user emotion.Wherein, Emotion identification algorithm can be set according to actual needs
It sets.
The specific category of user emotion refers to the refinement of user emotion, specifics, situational integration type.For example, negative
The specific category " querying Related product or service " of face mood, " dissatisfied attitude ", user indicate to lose to product or service
Prestige ", " reference controversial issue ", " customer complaint ", " angry user ", " user urges progress " etc..
The emotional intensity value of user emotion refers to the intensity of user emotion specific category, such as the mood of " dissatisfied "
Intensity value includes 1 to 3 grade, is respectively indicated slight dissatisfied, general dissatisfied, very dissatisfied.
Step S14 generates the mood response message according to the specific category of user emotion and emotional intensity value.
Further, by above-mentioned prediction model by the specific category of user emotion and emotional intensity value with it is existing all kinds of
Pacifying property language is matched；Based on pacifying property language is matched, corresponding mood response message is generated.In the present embodiment,
Mood response message is corresponding with the negative emotions state that user is presently in, specifically can be with for pacifying user
Language comprising all kinds of pacifying property.
For example, if it is " your attitude is friendly a little just more preferable " that user, which inputs information, judge user
The specific category of mood is " dissatisfied attitude ", and emotional intensity value is 1 grade (corresponding slight dissatisfied), then prediction model
The specific category of user emotion and emotional intensity value are matched with existing all kinds of pacifying property language, matched pacifying property words
Language include " yes ", " thanks " " you ", " close friend ", " it is recommended that "；And then by matched pacifying property language according to preset conjunction
And rule merges, and generates mood response message and " yes, thanks to your friendly suggestion." also the rest may be inferred for remaining situation.
For example, it is that " your attitude is somewhat poor, it is also necessary to improve that user, which inputs information,！", then judge user's feelings
The specific category of thread is " dissatisfied attitude ", and emotional intensity value is 2 grades (corresponding general dissatisfied), then generates mood
Response message " yes, thanks your valuable to suggest very much."
If it is that " your attitude is too disappointing, and it is so poor not see, I will complain you that user, which inputs information,
", then the specific category of user emotion is judged for " dissatisfied attitude ", and emotional intensity value is 3 grades (corresponding very discontented
Meaning), then it generates mood response message and " woulds you please the more forgive, we centainly will do it improvement, thank very much to your valuable advices
And suggestion."
Step S20 merges the standard response message with the mood response message, generates fusion response letter
Breath；
It is merged in standard response message with mood response message, it can be directly by standard response message, mood response
Information is merged respectively as independent part, obtains fusion response message.
For example, customer complaint loan examination & approval speed is excessively slow, standard response message is " through verifying, at your loan examination & approval
In creditor's identity information Qualify Phase, we will pay close attention to your business progress."；Its mood response message be " it is sorry,
It keeps you waiting！", " would you please bear with, thank your support and cooperation！".Accordingly, fusion response message be " it is sorry, allow
You wait so long！Through verifying, your loan examination & approval are in creditor's identity information Qualify Phase, we will pay close attention to your business
Progress.Would you please bear with, thanks your support and cooperation！"
Further, it is also possible to be carried out respectively to standard response message, mood response message according to preset subordinate sentence rule respectively
Subordinate sentence, and each section after subordinate sentence is merged according to preset merging rule, obtain fusion response message.Preset subordinate sentence
Regular, the preset rule that merges can be set according to conventional sentence knowledge and actual needs, to ensure to merge response letter
Breath sentence is clear and coherent, the meaning of one's words is clearly advisable.
For example, quote example, the fusion response message of generation be " it is sorry, keep you waiting！Through verifying, your loan is examined
It criticizes and is in creditor's identity information Qualify Phase, would you please bear with！We will pay close attention to your business progress, thank you
It supports and cooperates！"
Step S30 by the fusion response message and presets artificial customer service entrance option and is sent to user terminal；
That is, the fusion response message of generation is believed comprising standard response when identifying that user is currently at negative emotions
Breath and mood response message.Standard response message is mainly used for the demand for user/problem and proposes corresponding disposal method, feelings
Thread response message is mainly used for carrying out user pacifying for common grade routinely.Then, by the fusion response message together with
It presets artificial customer service entrance option and is sent to user terminal, so that user checks and selects.
Wherein, the access triggering option for the artificial customer service module that artificial customer service entrance option is intelligent customer service system is preset,
It includes at least confirmation access option and/or does not access option.If user needs to access artificial customer service, confirmation access choosing is selected
, the instruction of triggering selection confirmation at this time is to intelligent customer service system, so that the execution master of the current sessions of intelligent customer service system
Body becomes artificial customer service module and artificial customer service from robot customer service module.If user does not need to access artificial customer service, not into
Row selection operation or selection do not access option, and user terminal default does not execute operation at this time.
Step S40 is jumped when the selection confirmation instruction for the default artificial customer service entrance option for receiving user terminal transmission
To artificial customer service module, so that artificial customer service carries out reply process.
Specifically, it is true to receive the selection by robot module's (or background program of the system) of intelligent customer service system
When recognizing instruction, the execution module of current sessions is jumped into artificial customer service module by robot customer service module.In this way, artificial customer service
The working interface and user provided by artificial customer service module continues current session.
In the present embodiment, reply process is first carried out by robot customer service module, information is inputted according to user, generates standard
Response message；When identifying user emotion type is negative emotions, corresponding mood response message is further generated, and by mood
Response message is merged with standard response message, and the fusion response message of generation is used as response message.In this way, helping to improve
Reply process efficiency and the artificial dependence of reduction.Offer is preset artificial customer service entrance option and is selected to user simultaneously, in user
When artificial customer service being needed to carry out manual answering's processing, the selection option based on user jumps to the artificial customer service of intelligent customer service system
Module, to carry out manual answering's processing.To make robot visitor after judging user emotion type for negative emotions
While taking reply process, the user for increasing manual answering's processing selects option, can take into account the efficiency of reply process, also avoid
The robot customer service response of duration facilitates the negative emotions for alleviating user, to improve the reality that user emotion is pacified
Effect.
Further, on the basis of the implementation method first embodiment of intelligent customer service system of the present invention, propose that second is real
Apply example.As shown in figure 4, in the present embodiment, after above-mentioned steps S40, further includes:
Step S50 extracts preset kind information relevant to user emotion, and the preset kind information is sent to people
The default secondary page of work customer service module, to show the preset kind information in the secondary page.
Wherein, the preset kind information includes at least the specific category and emotional intensity value, current sessions of user emotion
Session information.
When jumping to artificial customer service module, the extraction of preset kind information is carried out.Wherein, robot customer service module is based on
User inputs after specific category and the emotional intensity value that information determines user emotion, can be by the tool of identified user emotion
Body classification and emotional intensity value are buffered in default storage region.When executing the extraction of preset kind information, directly from default
The specific category and emotional intensity value of storage region reading user emotion.
In addition, the session information of current sessions refers to before the extraction step for carrying out preset kind information, user and machine
Session context information between device people's customer service.When executing the extraction of preset kind information, directly from the data of current sessions
Buffer area is read.
Preset kind information is sent to the default secondary page of artificial customer service module and is shown.Wherein, auxiliary is preset
The page can be artificial customer service in the working page for carrying out manual answering；Default secondary page can also be on the working page
Another page that layer generates, can specifically be realized by plug-in code.
In the present embodiment, the specific category and emotional intensity value, current sessions of user emotion are included at least by extracting
Session information preset kind information, and preset kind information is shown into the secondary page in artificial customer service module, so that people
Work customer service views the preset kind information before carrying out manual answering's processing, to know user's current predictive emotional information
And the contextual information of current sessions, help artificial customer service preferably judge user current emotional situation and session come it is imperial
Arteries and veins is removed, the reply process effect of artificial customer service is helped to improve.
Further, on the basis of the implementation method first embodiment of intelligent customer service system of the present invention, propose that third is real
Apply example.As shown in figure 5, in the present embodiment, after above-mentioned steps S40, further includes:
Step S60 is obtained to the specific category of the user emotion and the artificial evaluation data of emotional intensity value；
After current sessions, it is responsible for the user emotion that the artificial customer service of current sessions response determines robot module
Specific category and emotional intensity value manually evaluated；Correspondingly, the artificial evaluation data of artificial customer service are uploaded to intelligent visitor
Dress system.Artificial evaluation data specifically can be to the specific category of user emotion determined by robot module (or mood
Intensity value) evaluation data, such as divide different grades: it is excellent, good, in, it is poor, or carry out assign point.
Step S61 judges the specific category and emotional intensity of the user emotion according to the artificial evaluation data respectively
Whether value meets default precise conditions；
The artificial evaluation data be used to carry out the specific category and emotional intensity value of the user emotion accuracy (or
Person's accuracy) evaluation.Specific category and emotional intensity value for the user emotion, can set correspondence according to actual needs
Default precise conditions.
For example, be directed to the specific category of the user emotion, artificial customer service is needed according to " excellent, good, in, poor " four grades
It is evaluated；For the emotional intensity value of the user emotion, artificial customer service needs to carry out according to 1~10 point to assign a point evaluation.It is right
The default precise conditions answered are as follows: when the user emotion specific category opinion rating be " excellent " or " good ", and work as the use
The tax of the emotional intensity value of family mood is divided into 6~10 points.If the opinion rating of the specific category of the user emotion is described
The tax of the emotional intensity value of user emotion point mismatches the default precise conditions, is considered as the specific category and feelings of the user emotion
Thread intensity value does not meet default precise conditions.
Step S62, if it is not, then obtaining the calibration number of the concrete type and emotional intensity value to the user emotion respectively
According to；
When the specific category and emotional intensity value for judging the user emotion do not meet default precise conditions, in artificial visitor
Calibration information is shown in working interface used in taking, to indirect labor's customer service respectively to the tool of the user emotion of current sessions
Body type and emotional intensity value are manually demarcated.After artificial calibration, nominal data is uploaded to intelligent customer service system automatically, and holds
Row step S63.
Step S63, according to the nominal data, demarcate respectively and update the user emotion concrete type and mood it is strong
Angle value.
Corresponding nominal data is manually demarcated according to artificial customer service, is demarcating respectively from the background and is updating the user
The concrete type and emotional intensity value of mood, to realize to the concrete type of user emotion and the artificial evaluation of emotional intensity value
It is demarcated with artificial, to correct (adjustment) robot customer service module in the concrete type of user emotion and the determination of emotional intensity value
Deficiency existing for aspect, so that the concrete type of the user emotion determined under each session and emotional intensity value more accurately may be used
It leans on.
Further, after step S63, further includes:
Step S70 saves the concrete type of the session information of current sessions and the user emotion of updated current sessions
And emotional intensity value is into default tranining database, to make subsequent training data.
Understandably, it to improve the accuracy that robot customer service module carries out user emotion identification, needs constantly to machine
Prediction model used by people's customer service module is trained and optimizes.
The concrete type and mood of the user emotion of session information, updated current sessions that each session is generated are strong
Angle value save, and then the above-mentioned data of preservation are trained as the prediction model and optimize use training data or
Assess data.In addition, the position saved can be local data base or cloud database.In this way, realizing to robot customer service
The feedback and optimization of prediction model used by module help to improve the standard that robot customer service module carries out user emotion identification
True property, the user emotion recognition capability of further hoisting machine people customer service module.
In the following, being illustrated in conjunction with Fig. 6.Fig. 6 is the customer service of the implementation method based on intelligent customer service system of the present invention
Talk with realization process, robot customer service accessing user end, and obtains the input information of user.Then, standard response message is generated；
At this point, inputting information according to user judges whether user emotion type is negative emotions.If it is not, then using standard response message as
Standard reply is sent to user terminal.
If so, generating mood response message, and mood response message is merged with standard response message, generates fusion and answer
Answer information.It merges response message to reply as standard, user terminal is sent to together with artificial customer service entrance option, so that user looks into
It sees and selects.
Further obtain the lower whorl return information of user terminal, if user does not select artificial customer service entrance option, continue by
The response of robot customer service progress current session.
If user selects artificial customer service entrance option, turn the artificial customer service of intelligent customer service system at this time.At this point, intelligent customer service
User emotion specific category, emotional intensity value, current sessions information are sent to artificial customer service by the robot customer service module of system
Secondary page, so that artificial customer service is checked, and by the response of artificial customer service continuation current session, pacified with continuing artificial customer service,
Service user.After conversation end, user emotion specific category that artificial customer service generates robot customer service, emotional intensity value are carried out
Evaluation；When needed, user emotion specific category, emotional intensity value are manually demarcated again by artificial customer service, thus school
Then quasi- robot predicting is as a result, terminate this session.
In addition, the present invention also provides a kind of realization devices of intelligent customer service system.
Fig. 7 is referred to, is schemed, 7 be the functional unit group of the first embodiment of the realization device of intelligent customer service system of the present invention
At schematic diagram.Wherein, described device includes:
Response message generation unit 10 inputs information according to the user that user terminal is sent, generates when carrying out current sessions
Standard response message and mood response message；
In the specific implementation, user terminal refers to when carrying out current sessions with intelligent customer service system, end used by a user
Jaws equipment/software, such as page end or operate in application program on mobile terminal (such as mobile phone, tablet computer).Carry out
When current sessions, user inputs related session information in user terminal, and concrete form can be text, voice or other types
Information.Intelligent customer service system mainly includes robot customer service module and artificial customer service module.
It is same can to input information according to user after receiving the user that user terminal is sent and inputting information for robot customer service module
Shi Shengcheng standard response message and mood response message.
Specifically, as shown in fig. 7, response message generation unit 10 includes:
Standard response message subelement 110, the user for being sent according to user terminal input information, generate standard response letter
Breath；
Information is inputted according to the user that user terminal is sent, the implementation for generating standard response message is the prior art, example
Information can be such as inputted to user carries out sentence segmentation, keyword extraction, semantic analysis processing；By keyword and/or semanteme
Analysis result is matched with the model answer data of standard database, to be exactly matched or the highest mark of matching degree
Quasi- answer data, and then standard response message is generated according to model answer data.
Standard response message can be considered the standardization return information that information is inputted to a certain user, be mainly used for user
Real demand/intention/problem carry out response.
In a specific implementation, different " problem " can be matched with corresponding " standard response message " in advance, and
Construct corresponding standard reply data library.After analyzing demand/intention/problem of user, the demand of user/is intended to/to ask
Topic is standardized input, carries out matching inquiry in standard reply data library, is asked with finding out and the demand of user/intention/
Inscribe matched standard response.After successful search goes out matched standard response, extracts the standard response and generate standard response letter
Breath.
For example, user inputs that information is " you can handle loan transaction at bank's several points? ", then keyword " silver is extracted
Row ", " several points ", " handling ", " loan ", and then analyze the user and need to inquire that loan transaction is handled in the local site of this bank
Time.The demand of user is standardized input, is carrying out matching inquiry in standard reply data library, with find out with
" handling the loan transaction time in the local site of this bank " matched standard response, such as " handle loan in the local site of this bank
The money business hours is 9:00 to 16:00 ".
Type of emotion identifies subelement 120, for identification user emotion type；
After generation standard response message, information is inputted according to user, identifies the type of emotion of active user.Wherein,
Type of emotion may include: positive mood, neutral mood, negative emotions.Information, which is inputted, according to user identifies active user's
The specific implementation of type of emotion can be according to different modes, such as can first obtain sensitive word, language that user inputs in information
Gas auxiliary word, punctuation mark and/or user input the transmission frequency of information, and then according to sensitive word, auxiliary words of mood, punctuation mark
And/or user inputs the transmission frequency of information and one or more of works as and to carry out type of emotion analysis, to identify user's feelings
Thread type.
For example, for user input information be " you can handle loan transaction at bank's several points? ", include based on the information
Sensitive word, auxiliary words of mood, punctuation mark and/or user input the transmission frequency of information, analysis user emotion type is neutrality
Mood.For user input information be " several points can handle loan transaction actually for your this bank??? ", it is based on the packet
The sensitive word (as " actually ") that contains, auxiliary words of mood, punctuation mark (as "??? ") and/or user input information transmission frequency, point
Analysis user emotion type is negative emotions.
Mood response message subelement 130, for being inputted according to the user when user emotion type is negative emotions
Information determines the specific category and emotional intensity value of user emotion；It is raw according to the specific category of user emotion and emotional intensity value
At the mood response message.
Specifically, when determine active user type of emotion be negative emotions when, based on it is pre-establishing, comprising mood know
User is inputted information input into prediction model, and carries out relevant data processing and inversion by the prediction model of other algorithm, into
And determine the specific category and emotional intensity value of user emotion.Wherein, Emotion identification algorithm can be set according to actual needs
It sets.
The specific category of user emotion refers to the refinement of user emotion, specifics, situational integration type.For example, negative
The specific category " querying Related product or service " of face mood, " dissatisfied attitude ", user indicate to lose to product or service
Prestige ", " reference controversial issue ", " customer complaint ", " angry user ", " user urges progress " etc..
The emotional intensity value of user emotion refers to the intensity of user emotion specific category, such as the mood of " dissatisfied "
Intensity value includes 1 to 3 grade, is respectively indicated slight dissatisfied, general dissatisfied, very dissatisfied.
Further, by above-mentioned prediction model by the specific category of user emotion and emotional intensity value with it is existing all kinds of
Pacifying property language is matched；Based on pacifying property language is matched, corresponding mood response message is generated.In the present embodiment,
Mood response message is corresponding with the negative emotions state that user is presently in, specifically can be with for pacifying user
Language comprising all kinds of pacifying property.
For example, if it is " your attitude is friendly a little just more preferable " that user, which inputs information, judge user
The specific category of mood is " dissatisfied attitude ", and emotional intensity value is 1 grade (corresponding slight dissatisfied), then prediction model
The specific category of user emotion and emotional intensity value are matched with existing all kinds of pacifying property language, matched pacifying property words
Language include " yes ", " thanks " " you ", " close friend ", " it is recommended that "；And then by matched pacifying property language according to preset conjunction
And rule merges, and generates mood response message and " yes, thanks to your friendly suggestion." also the rest may be inferred for remaining situation.
For example, it is that " your attitude is somewhat poor, it is also necessary to improve that user, which inputs information,！", then judge user's feelings
The specific category of thread is " dissatisfied attitude ", and emotional intensity value is 2 grades (corresponding general dissatisfied), then generates mood
Response message " yes, thanks your valuable to suggest very much."
If it is that " your attitude is too disappointing, and it is so poor not see, I will complain you that user, which inputs information,
", then the specific category of user emotion is judged for " dissatisfied attitude ", and emotional intensity value is 3 grades (corresponding very discontented
Meaning), then it generates mood response message and " woulds you please the more forgive, we centainly will do it improvement, thank very much to your valuable advices
And suggestion."
Response message integrated unit 20, for the standard response message to be merged with the mood response message,
Generate fusion response message；
It is merged in standard response message with mood response message, it can be directly by standard response message, mood response
Information is merged respectively as independent part, obtains fusion response message.
For example, customer complaint loan examination & approval speed is excessively slow, standard response message is " through verifying, at your loan examination & approval
In creditor's identity information Qualify Phase, we will pay close attention to your business progress."；Its mood response message be " it is sorry,
It keeps you waiting！", " would you please bear with, thank your support and cooperation！".Accordingly, fusion response message be " it is sorry, allow
You wait so long！Through verifying, your loan examination & approval are in creditor's identity information Qualify Phase, we will pay close attention to your business
Progress.Would you please bear with, thanks your support and cooperation！"
Further, it is also possible to be carried out respectively to standard response message, mood response message according to preset subordinate sentence rule respectively
Subordinate sentence, and each section after subordinate sentence is merged according to preset merging rule, obtain fusion response message.Preset subordinate sentence
Regular, the preset rule that merges can be set according to conventional sentence knowledge and actual needs, to ensure to merge response letter
Breath sentence is clear and coherent, the meaning of one's words is clearly advisable.
For example, quote example, the fusion response message of generation be " it is sorry, keep you waiting！Through verifying, your loan is examined
It criticizes and is in creditor's identity information Qualify Phase, would you please bear with！We will pay close attention to your business progress, thank you
It supports and cooperates！"
Transmission unit 30, for by the fusion response message and presetting artificial customer service entrance option and being sent to user terminal；
That is, the fusion response message of generation is believed comprising standard response when identifying that user is currently at negative emotions
Breath and mood response message.Standard response message is mainly used for the demand for user/problem and proposes corresponding disposal method, feelings
Thread response message is mainly used for carrying out user pacifying for common grade routinely.Then, by the fusion response message together with
It presets artificial customer service entrance option and is sent to user terminal, so that user checks and selects.
Wherein, the access triggering option for the artificial customer service module that artificial customer service entrance option is intelligent customer service system is preset,
It includes at least confirmation access option and/or does not access option.If user needs to access artificial customer service, confirmation access choosing is selected
, the instruction of triggering selection confirmation at this time is to intelligent customer service system, so that the execution master of the current sessions of intelligent customer service system
Body becomes artificial customer service module and artificial customer service from robot customer service module.If user does not need to access artificial customer service, not into
Row selection operation or selection do not access option, and user terminal default does not execute operation at this time.
Jump-transfer unit 40, for the selection confirmation instruction when the default artificial customer service entrance option for receiving user terminal transmission
When, artificial customer service module is jumped to, to carry out manual answering's processing.
Specifically, it is true to receive the selection by robot module's (or background program of the system) of intelligent customer service system
When recognizing instruction, the execution module of current sessions is jumped into artificial customer service module by robot customer service module.In this way, artificial customer service
The working interface and user provided by artificial customer service module continues current session.
In the present embodiment, reply process is first carried out by robot customer service module, information is inputted according to user, generates standard
Response message；When identifying user emotion type is negative emotions, corresponding mood response message is further generated, and by mood
Response message is merged with standard response message, and the fusion response message of generation is used as response message.In this way, helping to improve
Reply process efficiency and the artificial dependence of reduction.Offer is preset artificial customer service entrance option and is selected to user simultaneously, in user
When artificial customer service being needed to carry out manual answering's processing, the selection option based on user jumps to the artificial customer service of intelligent customer service system
Module, to carry out manual answering's processing.To make robot visitor after judging user emotion type for negative emotions
While taking reply process, the user for increasing manual answering's processing selects option, can take into account the efficiency of reply process, also avoid
The robot customer service response of duration facilitates the negative emotions for alleviating user, to improve the reality that user emotion is pacified
Effect.
Further, on the basis of the realization device first embodiment of intelligent customer service system of the present invention, propose that second is real
Apply example.As shown in figure 8, the realization device of the intelligent customer service system further include:
Extracting unit 50, for extracting relevant to user emotion preset kind information, and by the preset kind information
It is sent to the default secondary page of artificial customer service module, to show the preset kind information in the secondary page.
Wherein, the preset kind information includes at least the specific category and emotional intensity value, current sessions of user emotion
Session information.
When jumping to artificial customer service module, the extraction of preset kind information is carried out.Wherein, robot customer service module is based on
User inputs after specific category and the emotional intensity value that information determines user emotion, can be by the tool of identified user emotion
Body classification and emotional intensity value are buffered in default storage region.When executing the extraction of preset kind information, directly from default
The specific category and emotional intensity value of storage region reading user emotion.
In addition, the session information of current sessions refers to before the extraction step for carrying out preset kind information, user and machine
Session context information between device people's customer service.When executing the extraction of preset kind information, directly from the data of current sessions
Buffer area is read.
Preset kind information is sent to the default secondary page of artificial customer service module and is shown.Wherein, auxiliary is preset
The page can be artificial customer service in the working page for carrying out manual answering；Default secondary page can also be on the working page
Another page that layer generates, can specifically be realized by plug-in code.
In the present embodiment, the specific category and emotional intensity value, current sessions of user emotion are included at least by extracting
Session information preset kind information, and preset kind information is shown into the secondary page in artificial customer service module, so that people
Work customer service views the preset kind information before carrying out manual answering's processing, to know user's current predictive emotional information
And the contextual information of current sessions, help artificial customer service preferably judge user current emotional situation and session come it is imperial
Arteries and veins is removed, the reply process effect of artificial customer service is helped to improve.
Further, on the basis of the realization device first embodiment of intelligent customer service system of the present invention, propose that third is real
Apply example.As shown in figure 9, the realization device of the intelligent customer service system further includes calibration unit 60；
The calibration unit 60, for obtaining the artificial evaluation of specific category and emotional intensity value to the user emotion
Data；
After current sessions, it is responsible for the user emotion that the artificial customer service of current sessions response determines robot module
Specific category and emotional intensity value manually evaluated；Correspondingly, the artificial evaluation data of artificial customer service are uploaded to intelligent visitor
Dress system.Artificial evaluation data specifically can be to the specific category of user emotion determined by robot module (or mood
Intensity value) evaluation data, such as divide different grades: it is excellent, good, in, it is poor, or carry out assign point.
The calibration unit 60, for judging the concrete kind of the user emotion respectively according to the artificial evaluation data
Not and whether emotional intensity value meets default precise conditions；
The artificial evaluation data be used to carry out the specific category and emotional intensity value of the user emotion accuracy (or
Person's accuracy) evaluation.Specific category and emotional intensity value for the user emotion, can set correspondence according to actual needs
Default precise conditions.
For example, be directed to the specific category of the user emotion, artificial customer service is needed according to " excellent, good, in, poor " four grades
It is evaluated；For the emotional intensity value of the user emotion, artificial customer service needs to carry out according to 1~10 point to assign a point evaluation.It is right
The default precise conditions answered are as follows: when the user emotion specific category opinion rating be " excellent " or " good ", and work as the use
The tax of the emotional intensity value of family mood is divided into 6~10 points.If the opinion rating of the specific category of the user emotion is described
The tax of the emotional intensity value of user emotion point mismatches the default precise conditions, is considered as the specific category and feelings of the user emotion
Thread intensity value does not meet default precise conditions.
The calibration unit 60 is preset accurately if the specific category and emotional intensity value for the user emotion are not met
Condition then obtains the nominal data of the concrete type and emotional intensity value to the user emotion respectively；
When the specific category and emotional intensity value for judging the user emotion do not meet default precise conditions, in artificial visitor
Calibration information is shown in working interface used in taking, to indirect labor's customer service respectively to the tool of the user emotion of current sessions
Body type and emotional intensity value are manually demarcated.After artificial calibration, nominal data is uploaded to intelligent customer service system automatically.
The calibration unit 60, for demarcating respectively and updating the specific of the user emotion according to the nominal data
Type and emotional intensity value.
Corresponding nominal data is manually demarcated according to artificial customer service, is demarcating respectively from the background and is updating the user
The concrete type and emotional intensity value of mood, to realize to the concrete type of user emotion and the artificial evaluation of emotional intensity value
It is demarcated with artificial, to correct (adjustment) robot customer service module in the concrete type of user emotion and the determination of emotional intensity value
Deficiency existing for aspect, so that the concrete type of the user emotion determined under each session and emotional intensity value more accurately may be used
It leans on.
Further, described device further includes storage unit 70:
The storage unit 70, for saving the session information of current sessions and the user emotion of updated current sessions
Concrete type and emotional intensity value into default tranining database, to make subsequent training data.
Understandably, it to improve the accuracy that robot customer service module carries out user emotion identification, needs constantly to machine
Prediction model used by people's customer service module is trained and optimizes.
The concrete type and mood of the user emotion of session information, updated current sessions that each session is generated are strong
Angle value save, and then the above-mentioned data of preservation are trained as the prediction model and optimize use training data or
Assess data.In addition, the position saved can be local data base or cloud database.In this way, realizing to robot customer service
The feedback and optimization of prediction model used by module help to improve the standard that robot customer service module carries out user emotion identification
True property, the user emotion recognition capability of further hoisting machine people customer service module.
In addition, the realization of the intelligent customer service system is set the present invention also provides a kind of realization equipment of intelligent customer service system
It is standby to include: memory, processor and be stored in the intelligent customer service system that run on the memory and on the processor
Realization program, intelligence visitor as described above is realized when the realization program of the intelligent customer service system is executed by the processor
The step of implementation method of dress system.
Wherein, the realization program of the intelligent customer service system run on the processor is performed realized method can
Referring to each embodiment of implementation method of intelligent customer service system of the present invention, details are not described herein again.
In addition, being stored with intelligent customer service system on the readable storage medium storing program for executing the present invention also provides a kind of readable storage medium storing program for executing
The realization program of the realization program of system, the intelligent customer service system realizes intelligent customer service as described above when being executed by processor
The step of each embodiment of the implementation method of system.
Wherein, the realization program of the intelligent customer service system run on the processor is performed realized method can
Referring to each embodiment of implementation method of intelligent customer service system of the present invention, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the device that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or device.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form, all of these belong to the protection of the present invention.
Claims (12)
1. a kind of implementation method of intelligent customer service system, which is characterized in that the described method comprises the following steps:
When carrying out current sessions, information is inputted according to the user that user terminal is sent, generates standard response message and mood response
Information；
The standard response message is merged with the mood response message, generates fusion response message；
By the fusion response message and presets artificial customer service entrance option and be sent to user terminal；
When the selection confirmation instruction for the default artificial customer service entrance option for receiving user terminal transmission, artificial customer service mould is jumped to
Block, to carry out manual answering's processing.
2. the implementation method of intelligent customer service system as described in claim 1, which is characterized in that it is described according to user terminal send
The step of user inputs information, generates standard response message and mood response message, specifically includes:
Information is inputted according to the user that user terminal is sent, generates standard response message；
Identify user emotion type；
If user emotion type be negative emotions, according to the user input information, determine user emotion specific category and
Emotional intensity value；
According to the specific category of user emotion and emotional intensity value, the mood response message is generated.
3. the implementation method of intelligent customer service system as claimed in claim 2, which is characterized in that described to receive user terminal hair
When the selection of the default artificial customer service entrance option sent confirms instruction, after the step of jumping to artificial customer service module, further includes:
Preset kind information relevant to user emotion is extracted, and the preset kind information is sent to artificial customer service module
Default secondary page, to show the preset kind information in the secondary page；
Wherein, the preset kind information includes at least the specific category of user emotion and the meeting of emotional intensity value, current sessions
Talk about information.
4. the implementation method of intelligent customer service system as described in claim 1, which is characterized in that described to jump to artificial customer service mould
Block, so that after the step of artificial customer service carries out reply process, further includes:
It obtains to the specific category of the user emotion and the artificial evaluation data of emotional intensity value；
According to the artificial evaluation data, it is pre- to judge whether the specific category of the user emotion and emotional intensity value meet respectively
If precise conditions；
If it is not, then obtaining the nominal data of the concrete type and emotional intensity value to the user emotion respectively；
According to the nominal data, the concrete type and emotional intensity value of the user emotion are demarcated and updated respectively.
5. the implementation method of intelligent customer service system as claimed in claim 4, which is characterized in that described according to the calibration number
According to after the step of demarcating respectively and updating the concrete type and emotional intensity value of the user emotion, further includes:
Save the concrete type and emotional intensity value of the session information of current sessions and the user emotion of updated current sessions
Into default tranining database.
6. a kind of realization device of intelligent customer service system, which is characterized in that described device includes:
Response message generation unit inputs information according to the user that user terminal is sent, generation standard is answered when carrying out current sessions
Answer information and mood response message；
Response message integrated unit, for merging the standard response message with the mood response message, generation is melted
Close response message；
Transmission unit, for by the fusion response message and presetting artificial customer service entrance option and being sent to user terminal；
Jump-transfer unit, for jumping when the selection confirmation instruction for the default artificial customer service entrance option for receiving user terminal transmission
Artificial customer service module is gone to, to carry out manual answering's processing.
7. the realization device of intelligent customer service system as claimed in claim 6, which is characterized in that the response message generation unit
Include:
Standard response message subelement, the user for being sent according to user terminal input information, generate standard response message；
Type of emotion identifies subelement, for identification user emotion type；
Mood response message subelement, for inputting information according to the user, really when user emotion type is negative emotions
Determine the specific category and emotional intensity value of user emotion；According to the specific category of user emotion and emotional intensity value, described in generation
Mood response message.
8. the realization device of intelligent customer service system as claimed in claim 7, which is characterized in that described device further includes that information is taken out
Take unit；
The information extracting unit for extracting preset kind information relevant to user emotion, and the preset kind is believed
Breath is sent to the default secondary page of artificial customer service module, to show the preset kind information in the secondary page；
Wherein, the preset kind information includes at least the specific category of user emotion and the meeting of emotional intensity value, current sessions
Talk about information.
9. the realization device of intelligent customer service system as claimed in claim 6, which is characterized in that described device further includes that calibration is single
Member；
The calibration unit, for obtaining the artificial evaluation data of specific category and emotional intensity value to the user emotion；
According to the artificial evaluation data, judge whether the specific category of the user emotion and emotional intensity value meet default standard respectively
True condition；If it is not, then obtaining the nominal data of the concrete type and emotional intensity value to the user emotion respectively；According to described
The concrete type and emotional intensity value of the user emotion are demarcated respectively and updated to nominal data.
10. the realization device of intelligent customer service system as claimed in claim 9, which is characterized in that described device further includes saving
Unit；
The storage unit, for saving the specific of the session information of current sessions and the user emotion of updated current sessions
Type and emotional intensity value are into default tranining database.
11. a kind of realization equipment of intelligent customer service system, which is characterized in that the realization equipment of the intelligent customer service system includes:
Memory, processor and the realization journey for being stored in the intelligent customer service system that can be run on the memory and on the processor
It is realized as described in any one of claims 1 to 5 when the realization program of sequence, the intelligent customer service system is executed by the processor
Intelligent customer service system implementation method the step of.
12. a kind of readable storage medium storing program for executing, which is characterized in that be stored with the realization of intelligent customer service system on the readable storage medium storing program for executing
It is realized as described in any one of claims 1 to 5 when the realization program of program, the intelligent customer service system is executed by processor
The step of implementation method of intelligent customer service system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811611196.2A CN109684455A (en) | 2018-12-27 | 2018-12-27 | The implementation method and device of intelligent customer service system, equipment, readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811611196.2A CN109684455A (en) | 2018-12-27 | 2018-12-27 | The implementation method and device of intelligent customer service system, equipment, readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109684455A true CN109684455A (en) | 2019-04-26 |
Family
ID=66190523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811611196.2A Pending CN109684455A (en) | 2018-12-27 | 2018-12-27 | The implementation method and device of intelligent customer service system, equipment, readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109684455A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428267A (en) * | 2019-07-31 | 2019-11-08 | 联想(北京)有限公司 | Content processing method and device, computer system and readable storage medium storing program for executing |
| CN110866764A (en) * | 2019-11-20 | 2020-03-06 | 冠杰消防工程师教育服务(深圳)有限公司 | Customer service method and device |
| CN110991178A (en) * | 2019-11-08 | 2020-04-10 | 苏宁金融科技(南京)有限公司 | Intelligent customer service and artificial customer service switching method and device and computer equipment |
| CN111063370A (en) * | 2019-12-31 | 2020-04-24 | 中国银行股份有限公司 | Voice processing method and device |
| CN111540358A (en) * | 2020-04-26 | 2020-08-14 | 云知声智能科技股份有限公司 | Man-machine interaction method, device, equipment and storage medium |
| CN112748980A (en) * | 2021-01-29 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Message pushing method, device, equipment and computer readable storage medium |
| CN112866493A (en) * | 2020-12-16 | 2021-05-28 | 华人运通(上海)云计算科技有限公司 | Intelligent vehicle customer service auxiliary system and method |
| CN113435999A (en) * | 2021-06-24 | 2021-09-24 | 中国工商银行股份有限公司 | Service processing method, device and system |
| CN116739235A (en) * | 2023-05-06 | 2023-09-12 | 广州圈量网络信息科技有限公司 | Intelligent community service management system based on big data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016062077A (en) * | 2014-09-22 | 2016-04-25 | シャープ株式会社 | Interactive device, interactive system, interactive program, server, control method for server, and server control program |
| CN106899625A (en) * | 2015-12-18 | 2017-06-27 | 北京奇虎科技有限公司 | A kind of method and device according to user mood state adjusting device environment configuration information |
| CN107679234A (en) * | 2017-10-24 | 2018-02-09 | 上海携程国际旅行社有限公司 | Customer service information providing method, device, electronic equipment, storage medium |
| CN107688667A (en) * | 2017-09-30 | 2018-02-13 | 平安科技（深圳）有限公司 | Intelligent robot client service method, electronic installation and computer-readable recording medium |
| CN108090174A (en) * | 2017-12-14 | 2018-05-29 | 北京邮电大学 | A kind of robot answer method and device based on system function syntax |
| CN108197251A (en) * | 2017-12-29 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | A kind of big data operation and maintenance analysis method, device and server |
| US20180239481A1 (en) * | 2017-02-22 | 2018-08-23 | International Business Machines Corporation | Providing force input to an application |
-
2018
- 2018-12-27 CN CN201811611196.2A patent/CN109684455A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016062077A (en) * | 2014-09-22 | 2016-04-25 | シャープ株式会社 | Interactive device, interactive system, interactive program, server, control method for server, and server control program |
| CN106899625A (en) * | 2015-12-18 | 2017-06-27 | 北京奇虎科技有限公司 | A kind of method and device according to user mood state adjusting device environment configuration information |
| US20180239481A1 (en) * | 2017-02-22 | 2018-08-23 | International Business Machines Corporation | Providing force input to an application |
| CN107688667A (en) * | 2017-09-30 | 2018-02-13 | 平安科技（深圳）有限公司 | Intelligent robot client service method, electronic installation and computer-readable recording medium |
| CN107679234A (en) * | 2017-10-24 | 2018-02-09 | 上海携程国际旅行社有限公司 | Customer service information providing method, device, electronic equipment, storage medium |
| CN108090174A (en) * | 2017-12-14 | 2018-05-29 | 北京邮电大学 | A kind of robot answer method and device based on system function syntax |
| CN108197251A (en) * | 2017-12-29 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | A kind of big data operation and maintenance analysis method, device and server |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428267A (en) * | 2019-07-31 | 2019-11-08 | 联想(北京)有限公司 | Content processing method and device, computer system and readable storage medium storing program for executing |
| CN110428267B (en) * | 2019-07-31 | 2023-01-06 | 联想(北京)有限公司 | Content processing method and device, computer system and readable storage medium |
| CN110991178A (en) * | 2019-11-08 | 2020-04-10 | 苏宁金融科技(南京)有限公司 | Intelligent customer service and artificial customer service switching method and device and computer equipment |
| CN110866764A (en) * | 2019-11-20 | 2020-03-06 | 冠杰消防工程师教育服务(深圳)有限公司 | Customer service method and device |
| CN111063370A (en) * | 2019-12-31 | 2020-04-24 | 中国银行股份有限公司 | Voice processing method and device |
| CN111063370B (en) * | 2019-12-31 | 2022-06-03 | 中国银行股份有限公司 | Voice processing method and device |
| CN111540358A (en) * | 2020-04-26 | 2020-08-14 | 云知声智能科技股份有限公司 | Man-machine interaction method, device, equipment and storage medium |
| CN112866493A (en) * | 2020-12-16 | 2021-05-28 | 华人运通(上海)云计算科技有限公司 | Intelligent vehicle customer service auxiliary system and method |
| CN112748980A (en) * | 2021-01-29 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Message pushing method, device, equipment and computer readable storage medium |
| CN113435999A (en) * | 2021-06-24 | 2021-09-24 | 中国工商银行股份有限公司 | Service processing method, device and system |
| CN116739235A (en) * | 2023-05-06 | 2023-09-12 | 广州圈量网络信息科技有限公司 | Intelligent community service management system based on big data |
| CN116739235B (en) * | 2023-05-06 | 2024-03-22 | 广州圈量网络信息科技有限公司 | Intelligent community service management system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109684455A (en) | The implementation method and device of intelligent customer service system, equipment, readable storage medium storing program for executing | |
| CN108205627A (en) | Have ready conditions offer of the interactive assistant module to access | |
| CN106407178A (en) | Session abstract generation method and device | |
| CN106104517A (en) | Identification mission in the message | |
| CN108156824A (en) | Association centre's virtual assistant | |
| CN105657129A (en) | Call information obtaining method and device | |
| JP2017152948A (en) | Information provision method, information provision program, and information provision system | |
| CN111798118B (en) | Enterprise operation risk monitoring method and device | |
| CN107341157B (en) | Customer service conversation clustering method and device | |
| CN115169906A (en) | Customer service distribution method and device, computer equipment and storage medium | |
| US20040148165A1 (en) | Pattern processing system specific to a user group | |
| CN115017289A (en) | Method and device for serving customers based on knowledge base | |
| KR20090076318A (en) | Realtime conversational service system and method thereof | |
| CN110929014B (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN110740212B (en) | Call answering method and device based on intelligent voice technology and electronic equipment | |
| KR102222637B1 (en) | Apparatus for analysis of emotion between users, interactive agent system using the same, terminal apparatus for analysis of emotion between users and method of the same | |
| KR20180089242A (en) | Method, system and non-transitory computer-readable recording medium for generating dialogue contents according to output type for same at chatbot | |
| JP7237381B1 (en) | Program, information processing system and information processing method | |
| CN113573029B (en) | Multi-party audio and video interaction method and system based on IOT | |
| CN115118820A (en) | Call processing method and device, computer equipment and storage medium | |
| CN112307186A (en) | Question-answering service method, system, terminal device and medium based on emotion recognition | |
| CN111046151B (en) | Message processing method and device | |
| KR101890704B1 (en) | Simple message output device using speech recognition and language modeling and Method | |
| CN112651526A (en) | Method, device, equipment and storage medium for reserving target service | |
| CN112632241A (en) | Method, device, equipment and computer readable medium for intelligent conversation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190426 |
|
| RJ01 | Rejection of invention patent application after publication |