CN109635271A - A kind of user's intension recognizing method, customer service system, device and electronic equipment - Google Patents
A kind of user's intension recognizing method, customer service system, device and electronic equipment Download PDFInfo
- Publication number
- CN109635271A CN109635271A CN201811228093.8A CN201811228093A CN109635271A CN 109635271 A CN109635271 A CN 109635271A CN 201811228093 A CN201811228093 A CN 201811228093A CN 109635271 A CN109635271 A CN 109635271A
- Authority
- CN
- China
- Prior art keywords
- user
- textual
- customer service
- service
- model
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5166—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing in combination with interactive voice response systems or voice portals, e.g. as front-ends
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本说明书公开了一种用户意图识别方法、客服服务系统、装置及电子设备。该用户意图识别方法包括：获取用户的历史服务数据，包含服务过程中产生的文本数据和对用户进行标定的非文本因子；通过意图识别模型对获取到的历史服务数据进行意图识别，识别输出用户待咨询的参考问题；在客服务系统的客服对客户进行服务之前，将用户待咨询的参考问题推荐给客服，以使客服提前预知用户的咨询意图或者了解与用户咨询意图先关的内容，缩短客服与用户之间的沟通时间，从而解决现有技术中因客服沟通时间长导致的客服服务效率低的技术问题，进而提高客服服务效率。
This specification discloses a user intent identification method, a customer service system, an apparatus and an electronic device. The user intent identification method includes: acquiring historical service data of the user, including text data generated in the service process and non-text factors for calibrating the user; performing intent identification on the acquired historical service data through an intent identification model, identifying and outputting the user Reference questions to be consulted; before the customer service system of the customer service system serves the customer, the reference questions to be consulted by the user are recommended to the customer service, so that the customer service can predict the user's consultation intention in advance or understand the content related to the user's consultation intention, shorten the The communication time between the customer service and the user can solve the technical problem of low customer service efficiency caused by the long customer service communication time in the existing technology, thereby improving the customer service efficiency.
Description
Technical field
This specification is related to software technology field, in particular to a kind of user's intension recognizing method, customer service system, dress
It sets and electronic equipment.
Background technique
Customer service system includes: IVR (Interactive Voice Response, interactive voice answering system at present
System), artificial customer service workbench, that is, DT workbench.When user's manual service is sought help, initially enters IVR voice interactive system and retouch
Problem is stated, user is diverted to the contact staff on DT workbench by the problem of IVR is described according to user, after contact staff connects,
User and contact staff's replication problem describe, and are solved the problems, such as by contact staff or recorded problem.During existing customer service,
Contact staff can only be described by the replication problem of user come the problem of identifying user, the interaction duration of user and contact staff compared with
Long, efficiency of service is lower, needs the new method of one kind to improve customer service efficiency.
Summary of the invention
This specification embodiment provides a kind of user's intension recognizing method, customer service system, device and electronic equipment, uses
In solving the lower technical problem of customer service efficiency in the prior art, efficiency of service is improved.
In a first aspect, this specification embodiment provides a kind of user's intension recognizing method, it is applied to customer service system, packet
It includes:
Obtain the history service data of user, the history service data include in service process the text data that generates and
The non-textual factor that the user is demarcated；
Intention assessment is carried out to the history service data by intention assessment model, identification exports the user and waits seeking advice from
Reference problem；
Before the customer service of the objective service system services the user, user reference to be seeked advice from is asked
Topic recommends the customer service.
Second aspect, this specification embodiment provide a kind of customer service system, comprising:
Interactive voice answering system is described for receiving the problem of user inputs description information, and based on described problem
Information assigns the user to corresponding artificial customer service workbench；
The artificial customer service workbench, for establishing communication connection for the user and customer service；
Intention assessment model is carried out for obtaining the history service data of the user, and to the history service data
Intention assessment obtains user reference problem to be seeked advice from, will before the user and the customer service establish communication connection
It is described to give the customer service with reference to question recommending, wherein the history service data includes the text data generated in service process
With the non-textual factor demarcated to the user.
The third aspect, this specification embodiment provide a kind of user's intention assessment device, are applied to customer service system, packet
It includes:
Acquiring unit, for obtaining the history service data of user, the history service data includes to produce in service process
Raw text data and the non-textual factor that the user is demarcated；
Recognition unit, for carrying out intention assessment, identification output to the history service data by intention assessment model
User reference problem to be seeked advice from；
Recommendation unit, for before the customer service of the objective service system services the user, by the user
Reference question recommending to be seeked advice from gives the customer service.
Fourth aspect, this specification embodiment provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence, the program perform the steps of when being executed by processor
Obtain the history service data of user, the history service data include in service process the text data that generates and
The non-textual factor that the user is demarcated；
Intention assessment is carried out to the history service data by intention assessment model, identification exports the user and waits seeking advice from
Reference problem；
Before the customer service of the objective service system services the user, user reference to be seeked advice from is asked
Topic recommends the customer service.
5th aspect, this specification embodiment provide a kind of electronic equipment, include memory and one or one
Above program, one of them perhaps more than one program be stored in memory and be configured to by one or one with
It includes the instruction for performing the following operation that upper processor, which executes the one or more programs:
Obtain the history service data of user, the history service data include in service process the text data that generates and
The non-textual factor that the user is demarcated；
Intention assessment is carried out to the history service data by intention assessment model, identification exports the user and waits seeking advice from
Reference problem；
Before the customer service of the objective service system services the user, user reference to be seeked advice from is asked
Topic recommends the customer service.
Said one or multiple technical solutions in this specification embodiment, at least have the following technical effect that
This specification embodiment provides a kind of user's intension recognizing method, obtains the history service data of user, includes clothes
The text data generated during business and the non-textual factor that user is demarcated；By intention assessment model to getting
History service data carries out intention assessment, identification output user reference problem to be seeked advice from；Objective service system customer service to visitor
Before family is serviced, by user's reference question recommending to be seeked advice to customer service, so that the consulting meaning of user is predicted in customer service in advance
Figure understands the content first closed with user's consulting intention, shortens the time for communication between customer service and user, to solve existing
The low technical problem of customer service efficiency caused by being grown in technology because of customer service time for communication, and then improve customer service efficiency.
Detailed description of the invention
In order to illustrate more clearly of the technical solution in this specification embodiment, embodiment or the prior art will be retouched below
Attached drawing needed in stating is briefly described, it should be apparent that, the accompanying drawings in the following description is the one of this specification
A little embodiments for those of ordinary skill in the art without any creative labor, can also be according to this
A little attached drawings obtain other attached drawings.
Fig. 1 is a kind of schematic diagram for customer service system that this specification embodiment provides；
Fig. 2 is a kind of flow chart for user's intension recognizing method that this specification embodiment provides；
Fig. 3 is the identification process schematic diagram for the intention assessment model that this specification embodiment provides；
Fig. 4 is a kind of schematic diagram for user's intention assessment device that this specification embodiment provides；
Fig. 5 is the schematic diagram for a kind of electronic equipment that this specification embodiment provides.
Specific embodiment
To keep the purposes, technical schemes and advantages of this specification embodiment clearer, below in conjunction with this specification reality
The attached drawing in example is applied, the technical solution in this specification embodiment is clearly and completely described, it is clear that described reality
Applying example is this specification a part of the embodiment, instead of all the embodiments.The embodiment of base in this manual, this field are general
Logical technical staff every other embodiment obtained without creative efforts belongs to this specification protection
Range.
A kind of user's intension recognizing method, customer service system, device and electronic equipment are provided in this specification embodiment,
For solving the technical problem that customer service efficiency is lower in the prior art, efficiency of service is improved.
With reference to the accompanying drawing to the main realization principle of this specification embodiment technical solution, specific embodiment and its right
The beneficial effect that should be able to reach is explained in detail.
Embodiment
Referring to FIG. 1, the embodiment of the present application provides a kind of customer service system, comprising: interactive voice answering system
IVR, artificial customer service workbench, that is, DT workbench and intention assessment model.Wherein, interactive voice answering system is for connecing
The problem of receiving user's input description information, and corresponding artificial customer service work is assigned the user to based on problem description information
Platform；Artificial customer service workbench is used to establish communication connection for user and customer service；Intention assessment model is for obtaining user's
History service data, and intention assessment is carried out to history service data and obtains user's reference problem to be seeked advice from, in user and visitor
Clothes are established before communication connection, will be with reference to question recommending to customer service.
In use, user describes problem, interactive voice answering system to interactive voice answering system IVR
When IVR distributes DT workbench, the shunting of artificial canal is carried out: for example, IVR can be based on belonging to the problem of receiving description information
Type: user is transferred to DT workbench corresponding with the affiliated type of the problem by complaint, business consultation, troublshooting etc., by
Special customer service provides service for it；For another example IVR can also be according to the consulting amount of current each DT workbench, by user point
It is fitted on the few DT workbench of consulting amount, shortens user's waiting time, promotes user experience.
When describing the problem of interactive voice answering system IVR receives user or later, triggering intention assessment model is held
A kind of row user's intension recognizing method provided by the embodiments of the present application, referring to FIG. 2, this method comprises:
S210: obtaining the history service data of user, and the history service data includes the text generated in service process
Data and the non-textual factor that the user is demarcated；
S220: intention assessment is carried out to the history service data by intention assessment model, identification exports the user
Reference problem to be seeked advice from；
S230: before the customer service of the objective service system services the user, the user is to be seeked advice from
The customer service is given with reference to question recommending.
In the specific implementation process, each user records and saves user when seeking advice from by customer service system
Service data, including text data and the non-textual factor.Wherein, text data may include generated in service process it is as follows
One or more text datas: the problem of user, describes the problem of text, customer service record text, the name of user, affiliated area
Deng, the present embodiment W1, W2 ... Wn indicates text data.The non-textual factor is indicated using preset ID symbol, be may include
The following one or more factor:
The attribute status of user, for example gender, it is bundled with several bank cards, nearest 24 hours login failure numbers etc., it can
To indicate the attribute status of user with F1, F2 ... Fn；
Send a telegram here the problem of seeking advice from customer service M1 A before the switching track that user is demarcated by customer service, such as user, this comes
Electricity asks questions B at customer service M1 but the customer service can't resolve switching to customer service M2, then the switching track of user can be
From M1 to M2, switching track can be indicated with M1, M2, Mn；
The action trail of user adds a unique number to every single stepping of user, such as user's point button
A, then put button B, has visited again interface C etc., has been numbered to form a sequence to these operations, can with B_1, B_2 ...
B_n is indicated.
Service item track, i.e., the service seeked advice to user add a unique number, for example, user first seeked advice from " flower
When refund ", then the correlated knowledge point of service items such as " how flower amount improve " has been seeked advice from, record these service entries
Mesh track, can with S_1, S_2 ... S_n indicate.
By recording and saving history service data of these service datas as user, executed for the embodiment of the present application
S210 provides data source.When S210 obtains the history service data of user, user is last before available current point in time
The history service data generated using customer service system, also history service data before available user several times is anticipated
Figure identification.Wherein, the correlation that time closer history service data and user seek advice from is higher, it is intended that the accuracy of identification is got over
It is high.
After S210 gets the history service data of user, executes S220 and carry out user's intention assessment.Specifically, will
The history service data of user carries out intention assessment as characteristic input intention assessment model, is known by intention assessment model
It Shu Chu not user's reference problem to be seeked advice from.
Wherein, intention assessment model provided by the embodiments of the present application is mixed by textual classification model and non-textual disaggregated model
The network model formed is closed, semantic understanding, but also the history to user not only were done to the text data in the history service data of user
The personalized state that the non-textual factor in data is characterized does finer identification, has to the accuracy rate of intention assessment and significantly mentions
It rises.
The specific configuration of intention assessment model may include: textual classification model, the first non-textual disaggregated model and second
Textual classification model, textual classification model and the first non-textual disaggregated model be respectively used to text data and the non-textual factor into
Row category conversion exports the classification results such as vector of Unified Form, then, by the second non-textual disaggregated model to text classification mould
The classification results of type and the first non-textual disaggregated model carry out comprehensive identification, realize the knot of the identification of text and the non-textual factor
It closes, improves identification standard and go rate.When the history service data to user carries out intention assessment, it can specifically pass through text classification mould
Text data in history service data is carried out sorting code number by type, obtains primary vector；Pass through the first non-textual disaggregated model
The non-textual factor in history service data is subjected to sorting code number, obtains secondary vector；Primary vector and secondary vector are made
It is characterized data and inputs the second non-textual model, asked by the second non-textual disaggregated model identification output user reference to be seeked advice from
Topic.
Further, if comprising a plurality of types of text datas and/or a plurality of types of in the history service data of user
Multiple textual classification models or multiple non-textual disaggregated models can be accordingly arranged in being intended to identification model in the non-textual factor,
To carry out Classification and Identification to different types of text data or the non-textual factor respectively, then using all classification recognition results as
The non-textual disaggregated model of characteristic input second carries out intention assessment.For the text data of same type, in order to be promoted point
The accuracy of class identification, can also carry out Classification and Identification using different types of textual classification model, to obtain Classification and Identification
As a result.
Such as: the history service data of user include: text data W1, W2 ... Wn, the non-textual factor: the attribute of user
State F1, F2 ... Fn, by customer service demarcate switching track M1, M2, Mn, user behavior track B_1, B_2 ... B_n and service
Project track S_1, S_2 ... S_n, wherein the attribute status of user is same type with the switching track demarcated by customer service two
Data, that is, attribute factor, remaining be different types of data.Referring to FIG. 3, being directed to above-mentioned history service data, can construct
Intention assessment model includes: the convolutional neural networks CNN of a textual classification model, the depth of a non-textual disaggregated model are refreshing
Shot and long term memory network LSTM through network DNN and four non-textual disaggregated models.When carrying out intention assessment, by W1, W2 ...
Wn inputs CNN and first LSTM respectively as characteristic and obtains classification recognition result, and F1, F2 ... Fn and M1, M2, Mn are made
Be characterized data and input second LSTM and obtain classification recognition result, using B_1, B_2 ... B_n is as characteristic input third
A LSTM obtains classification recognition result, using S_1, S_2 ... S_n inputs the 4th LSTM acquisition Classification and Identification as characteristic
As a result, carrying out intention assessment finally by using all classification recognition results as characteristic input DNN, final meaning is exported
Figure recognition result refers to problem.
The mode that above-mentioned intention assessment model is mixed by using LSTM, CNN and DNN multiple network, to text data and
The non-textual factor carries out comprehensive identification, and the factor that user is calibrated not only is utilized, also uses the record problem of customer service, significantly
Improve the accuracy rate of user's intention assessment.
After S220 identifies reference problem of the output user wait seeking advice from by the above method, the present embodiment then executes S230
Before the customer service of objective service system services user, by user reference question recommending to be seeked advice to customer service, mention
Understand the problem of user may wish to consulting in advance for customer service, shortens time for communication the problem of between customer service and user, to mention
High customer service efficiency.
It is a in the specific implementation process, after customer service services completion to active user, problem is also further recorded, that is, is recorded
The problem of real consulting of the user or an open question, and it is saved in current service data as target problem.
After this, the embodiment of the present application also obtains the target problem recorded after the completion of customer service, which is fed back to meaning
Figure identification model, to correct the parameter of intention assessment model by target problem, to improve the accuracy of intention assessment model.
A kind of user's intension recognizing method provided based on the above embodiment, the present embodiment is also corresponding to provide a kind of user's meaning
Figure identification device, referring to FIG. 4, the device includes:
Acquiring unit 41, for obtaining the history service data of user, the history service data includes in service process
The text data of generation and the non-textual factor that the user is demarcated；
Recognition unit 42 identifies defeated for carrying out intention assessment to the history service data by intention assessment model
User reference problem to be seeked advice from out；
Recommendation unit 43, for before the customer service of the objective service system services the user, by the use
Family reference question recommending to be seeked advice from gives the customer service.
Wherein, the non-textual factor includes the attribute status of the user, the switching track demarcated by customer service, Yong Huhang
For track and/or service item track.
As an alternative embodiment, described device further include:
Updating unit 44, for obtaining institute after described the problem of seeking advice from user's generation recommends the customer service
State the target problem recorded after the completion of customer service；The target problem is fed back into the intention assessment model, to pass through
State the parameter that target problem corrects the intention assessment model.
As an alternative embodiment, the intention assessment model in recognition unit 42 includes: textual classification model,
One non-textual disaggregated model and the second textual classification model；
The recognition unit 42 is used for: by the textual classification model by the text in the history service data
Data carry out sorting code number, obtain primary vector；It will be in the history service data by the described first non-textual disaggregated model
The non-textual factor carry out sorting code number, obtain secondary vector；Using the primary vector and secondary vector as characteristic
According to the second non-textual model is inputted, user ginseng to be seeked advice from is exported by the described second non-textual disaggregated model identification
Examination topic.
About the device in above-described embodiment, wherein each unit executes the concrete mode of operation in method
It is described in detail in embodiment, no longer elaborates herein.
Referring to FIG. 5, being that a kind of electronics for realizing data query method shown according to an exemplary embodiment is set
Standby 700 block diagram.For example, electronic equipment 700 can be computer, database console, tablet device, personal digital assistant
Deng.
Referring to Fig. 5, electronic equipment 700 may include following one or more components: processing component 702, memory 704,
Power supply module 706, multimedia component 708, the interface 710 and communication component 712 of input/output (I/O).
The integrated operation of the usual controlling electronic devices 700 of processing component 702 is such as grasped with display, data communication, and record
Make associated operation.Processing element 702 may include one or more processors 720 to execute instruction, above-mentioned to complete
The all or part of the steps of method.In addition, processing component 702 may include one or more modules, it is convenient for 702 He of processing component
Interaction between other assemblies.
Memory 704 is configured as storing various types of data to support the operation in equipment 700.These data are shown
Example includes the instruction of any application or method for operating on electronic equipment 700, contact data, telephone directory number
According to, message, picture, video etc..Memory 704 can by any kind of volatibility or non-volatile memory device or they
Combination realize, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable
Programmable read only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, quick flashing
Memory, disk or CD.
Power supply module 706 provides electric power for the various assemblies of electronic equipment 700.Power supply module 706 may include power supply pipe
Reason system, one or more power supplys and other with for electronic equipment 700 generate, manage, and distribute the associated component of electric power.
I/O interface 710 provides interface between processing component 702 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Communication component 712 is configured to facilitate the communication of wired or wireless way between electronic equipment 700 and other equipment.
Electronic equipment 700 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.Show at one
In example property embodiment, communication component 712 receives broadcast singal or broadcast from external broadcasting management system via broadcast channel
Relevant information.In one exemplary embodiment, the communication component 712 further includes near-field communication (NFC) module, short to promote
Cheng Tongxin.For example, radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band can be based in NFC module
(UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, electronic equipment 700 can be by one or more application specific integrated circuit (ASIC), number
Word signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 704 of instruction, above-metioned instruction can be executed by the processor 720 of electronic equipment 700 to complete the above method.Example
Such as, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, soft
Disk and optical data storage devices etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of mobile terminal
When device executes, so that electronic equipment is able to carry out a kind of data query method, which comprises obtain the history service of user
Data, the history service data include the text data generated in service process and are demarcated to the user non-textual
The factor；Intention assessment is carried out to the history service data by intention assessment model, it is to be seeked advice from that identification exports the user
With reference to problem；Before the customer service of the objective service system services the user, by user reference to be seeked advice from
Question recommending gives the customer service.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is limited only by the attached claims
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (13)
1. a kind of user's intension recognizing method is applied to customer service system, comprising:
Obtain the history service data of user, the history service data includes the text data that generates and to institute in service process
State the non-textual factor that user is demarcated；
Intention assessment is carried out to the history service data by intention assessment model, identification exports user ginseng to be seeked advice from
Examination topic；
Before the customer service of the objective service system services the user, user reference problem to be seeked advice from is pushed away
It recommends to the customer service.
2. the method as described in claim 1, the non-textual factor includes the attribute status of the user, by customer service calibration
Switching track, user behavior track and/or service item track.
3. the method as described in claim 1, after described the problem of seeking advice from user's generation, recommends the customer service, institute
State method further include:
Obtain the target problem recorded after the completion of the customer service；
The target problem is fed back into the intention assessment model, to correct the intention assessment mould by the target problem
The parameter of type.
4. the method as described in claims 1 to 3 is any, the intention assessment model includes: textual classification model, the first non-text
This disaggregated model and the second textual classification model；
Described to carry out intention assessment to the history service data by intention assessment model, identification exports the user and waits seeking advice from
Reference problem, comprising:
The text data in the history service data is subjected to sorting code number by the textual classification model, obtains the
One vector；
The non-textual factor in the history service data is subjected to classification volume by the described first non-textual disaggregated model
Code obtains secondary vector；
The second non-textual model is inputted using the primary vector and secondary vector as characteristic, it is non-by described second
Textual classification model identification exports user reference problem to be seeked advice from.
5. a kind of customer service system, comprising:
Interactive voice answering system for receiving the problem of user inputs description information, and is based on described problem description information
Assign the user to corresponding artificial customer service workbench；
The artificial customer service workbench, for establishing communication connection for the user and customer service；
Intention assessment model is intended to for obtaining the history service data of the user, and to the history service data
Identification obtains user reference problem to be seeked advice from, will be described before the user and the customer service establish communication connection
The customer service is given with reference to question recommending, wherein the history service data includes the text data that generates and right in service process
The non-textual factor that the user is demarcated.
6. system as claimed in claim 5, the history service data includes the text data generated in service process and right
The non-textual factor that the user is demarcated.
7. system as claimed in claim 5, the intention assessment model includes: textual classification model, the first non-textual classification
Model and the second textual classification model；
The textual classification model is obtained for carrying out sorting code number to the text data in the history service data
Primary vector；
The first non-textual disaggregated model, for carrying out classification volume to the non-textual factor in the history service data
Code obtains secondary vector；
The second non-textual disaggregated model, for carrying out intention knowledge using the primary vector and secondary vector as characteristic
Not, identification exports user reference problem to be seeked advice from.
8. a kind of user's intention assessment device is applied to customer service system, comprising:
Acquiring unit, for obtaining the history service data of user, the history service data includes to generate in service process
Text data and the non-textual factor that the user is demarcated；
Recognition unit identifies described in output for carrying out intention assessment to the history service data by intention assessment model
User's reference problem to be seeked advice from；
Recommendation unit, for before the customer service of the objective service system services the user, the user being waited consulting
The reference question recommending of inquiry gives the customer service.
9. device as claimed in claim 8, the non-textual factor includes the attribute status of the user, by customer service calibration
Switching track, user behavior track and/or service item track.
10. device as claimed in claim 8, described device further include:
Updating unit, for obtaining the customer service after described the problem of seeking advice from user's generation recommends the customer service
The target problem recorded after the completion of service；The target problem is fed back into the intention assessment model, to pass through the target
Problem corrects the parameter of the intention assessment model.
11. the device as described in claim 8~10 is any, the intention assessment model includes: textual classification model, first non-
Textual classification model and the second textual classification model；
The recognition unit is specifically used for:
The text data in the history service data is subjected to sorting code number by the textual classification model, obtains the
One vector；
The non-textual factor in the history service data is subjected to classification volume by the described first non-textual disaggregated model
Code obtains secondary vector；
The second non-textual model is inputted using the primary vector and secondary vector as characteristic, it is non-by described second
Textual classification model identification exports user reference problem to be seeked advice from.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
It is performed the steps of when execution
Obtain the history service data of user, the history service data includes the text data that generates and to institute in service process
State the non-textual factor that user is demarcated；
Intention assessment is carried out to the history service data by intention assessment model, identification exports user ginseng to be seeked advice from
Examination topic；
Before the customer service of the objective service system services the user, user reference problem to be seeked advice from is pushed away
It recommends to the customer service.
13. a kind of electronic equipment, which is characterized in that include memory and one or more than one program, wherein one
A perhaps more than one program is stored in memory and is configured to execute described one by one or more than one processor
A or more than one program includes the instruction for performing the following operation:
Obtain the history service data of user, the history service data includes the text data that generates and to institute in service process
State the non-textual factor that user is demarcated；
Intention assessment is carried out to the history service data by intention assessment model, identification exports user ginseng to be seeked advice from
Examination topic；
Before the customer service of the objective service system services the user, user reference problem to be seeked advice from is pushed away
It recommends to the customer service.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811228093.8A CN109635271A (en) | 2018-10-22 | 2018-10-22 | A kind of user's intension recognizing method, customer service system, device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811228093.8A CN109635271A (en) | 2018-10-22 | 2018-10-22 | A kind of user's intension recognizing method, customer service system, device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109635271A true CN109635271A (en) | 2019-04-16 |
Family
ID=66066453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811228093.8A Pending CN109635271A (en) | 2018-10-22 | 2018-10-22 | A kind of user's intension recognizing method, customer service system, device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635271A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110225207A (en) * | 2019-04-29 | 2019-09-10 | 厦门快商通信息咨询有限公司 | A kind of anti-harassment method, system, terminal and storage medium merging semantic understanding |
| CN110390535A (en) * | 2019-06-25 | 2019-10-29 | 阿里巴巴集团控股有限公司 | Customer complaint object determines method, apparatus, electronic equipment and readable storage medium storing program for executing |
| CN110909148A (en) * | 2019-12-17 | 2020-03-24 | 中国银行股份有限公司 | Customer service assisting method and device |
| CN111292103A (en) * | 2020-04-24 | 2020-06-16 | 支付宝(杭州)信息技术有限公司 | Method and device for recommending customer service channel to user |
| CN111324206A (en) * | 2020-02-28 | 2020-06-23 | 重庆百事得大牛机器人有限公司 | Gesture interaction-based confirmation information identification system and method |
| CN112183953A (en) * | 2020-09-08 | 2021-01-05 | 北京达佳互联信息技术有限公司 | Method and device for allocating customer service resources, electronic equipment and storage medium |
| CN112836025A (en) * | 2019-11-22 | 2021-05-25 | 航天信息股份有限公司 | Intention identification method and device |
| CN112925888A (en) * | 2019-12-06 | 2021-06-08 | 上海大岂网络科技有限公司 | Method and device for training question-answer response and small sample text matching model |
| CN113886563A (en) * | 2021-10-25 | 2022-01-04 | 北京达佳互联信息技术有限公司 | Question recommendation method and device, electronic equipment and storage medium |
| CN115796333A (en) * | 2022-11-03 | 2023-03-14 | 平安银行股份有限公司 | User consultation intention prediction method and system and computer equipment |
| CN116204720A (en) * | 2023-03-09 | 2023-06-02 | 上海喜马拉雅科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104991887A (en) * | 2015-06-18 | 2015-10-21 | 北京京东尚科信息技术有限公司 | Information providing method and apparatus |
| CN105512153A (en) * | 2014-10-20 | 2016-04-20 | 中国电信股份有限公司 | Method and device for service provision of online customer service system, and system |
| CN107451199A (en) * | 2017-07-05 | 2017-12-08 | 阿里巴巴集团控股有限公司 | Method for recommending problem and device, equipment |
| 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 |
| CN107862005A (en) * | 2017-10-25 | 2018-03-30 | 阿里巴巴集团控股有限公司 | User view recognition methods and device |
| CN108537644A (en) * | 2018-04-23 | 2018-09-14 | 吉林亿联银行股份有限公司 | A kind of method and apparatus of customer service recommended products |
-
2018
- 2018-10-22 CN CN201811228093.8A patent/CN109635271A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512153A (en) * | 2014-10-20 | 2016-04-20 | 中国电信股份有限公司 | Method and device for service provision of online customer service system, and system |
| CN104991887A (en) * | 2015-06-18 | 2015-10-21 | 北京京东尚科信息技术有限公司 | Information providing method and apparatus |
| CN107451199A (en) * | 2017-07-05 | 2017-12-08 | 阿里巴巴集团控股有限公司 | Method for recommending problem and device, equipment |
| 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 |
| CN107862005A (en) * | 2017-10-25 | 2018-03-30 | 阿里巴巴集团控股有限公司 | User view recognition methods and device |
| CN108537644A (en) * | 2018-04-23 | 2018-09-14 | 吉林亿联银行股份有限公司 | A kind of method and apparatus of customer service recommended products |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110225207A (en) * | 2019-04-29 | 2019-09-10 | 厦门快商通信息咨询有限公司 | A kind of anti-harassment method, system, terminal and storage medium merging semantic understanding |
| CN110225207B (en) * | 2019-04-29 | 2021-08-06 | 厦门快商通信息咨询有限公司 | An anti-harassment method, system, terminal and storage medium integrating semantic understanding |
| CN110390535A (en) * | 2019-06-25 | 2019-10-29 | 阿里巴巴集团控股有限公司 | Customer complaint object determines method, apparatus, electronic equipment and readable storage medium storing program for executing |
| CN110390535B (en) * | 2019-06-25 | 2023-10-10 | 阿里巴巴集团控股有限公司 | Methods, devices, electronic equipment and readable storage media for determining customer complaint objects |
| CN112836025A (en) * | 2019-11-22 | 2021-05-25 | 航天信息股份有限公司 | Intention identification method and device |
| CN112925888A (en) * | 2019-12-06 | 2021-06-08 | 上海大岂网络科技有限公司 | Method and device for training question-answer response and small sample text matching model |
| CN110909148A (en) * | 2019-12-17 | 2020-03-24 | 中国银行股份有限公司 | Customer service assisting method and device |
| CN111324206B (en) * | 2020-02-28 | 2023-07-18 | 重庆百事得大牛机器人有限公司 | System and method for identifying confirmation information based on gesture interaction |
| CN111324206A (en) * | 2020-02-28 | 2020-06-23 | 重庆百事得大牛机器人有限公司 | Gesture interaction-based confirmation information identification system and method |
| CN111292103A (en) * | 2020-04-24 | 2020-06-16 | 支付宝(杭州)信息技术有限公司 | Method and device for recommending customer service channel to user |
| CN112183953A (en) * | 2020-09-08 | 2021-01-05 | 北京达佳互联信息技术有限公司 | Method and device for allocating customer service resources, electronic equipment and storage medium |
| CN113886563A (en) * | 2021-10-25 | 2022-01-04 | 北京达佳互联信息技术有限公司 | Question recommendation method and device, electronic equipment and storage medium |
| CN113886563B (en) * | 2021-10-25 | 2024-09-24 | 北京达佳互联信息技术有限公司 | Question recommending method and device, electronic equipment and storage medium |
| CN115796333A (en) * | 2022-11-03 | 2023-03-14 | 平安银行股份有限公司 | User consultation intention prediction method and system and computer equipment |
| CN116204720A (en) * | 2023-03-09 | 2023-06-02 | 上海喜马拉雅科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635271A (en) | A kind of user's intension recognizing method, customer service system, device and electronic equipment | |
| US11663607B2 (en) | Machine-learning based systems and methods for generating an ordered listing of objects for a particular user | |
| CN112052316B (en) | Model evaluation method and device, storage medium and electronic equipment | |
| CN110895940A (en) | Intelligent voice interaction method and device | |
| US20140255895A1 (en) | System and method for training agents of a contact center | |
| US12113934B1 (en) | Systems and methods for intelligent call agent evaluations | |
| CN112600982B (en) | Power supply service hotline interactive voice response method, system, equipment and medium | |
| CN109858702A (en) | Client upgrades prediction technique, device, equipment and the readable storage medium storing program for executing complained | |
| CN111028007B (en) | User portrait information prompting method, device and system | |
| CN112395366B (en) | Data processing and creation method, device and electronic equipment for distributed database | |
| CN106528759B (en) | Information processing method and device of intelligent question answering system | |
| CN112925888A (en) | Method and device for training question-answer response and small sample text matching model | |
| CN108109618A (en) | voice interactive method, system and terminal device | |
| CN109493866A (en) | Intelligent sound box and its operating method | |
| CN108132768A (en) | The processing method of phonetic entry, terminal and network server | |
| CN114186036A (en) | Dialogue processing method, device, computer equipment and storage medium | |
| CN107832941A (en) | Order processing method and device | |
| CN104052883A (en) | Method, device and system for obtaining menu information | |
| CN116127036B (en) | Dialogue processing method and device and electronic equipment | |
| CN117455430A (en) | Resume information processing method, device, equipment and storage medium based on AI | |
| CN120812178A (en) | Intelligent voice interaction method, system, electronic device, storage medium and program product | |
| CN111881270B (en) | Intelligent dialogue method and system | |
| CN111061855B (en) | Reply content generation method and device, online chat processing method and electronic equipment | |
| CN119204028A (en) | A method, device, storage medium and electronic device for recommending speech skills | |
| CN114663113A (en) | Intelligent auxiliary method and device for customer service system, storage medium and computer equipment |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200925 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200925 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |
|
| RJ01 | Rejection of invention patent application after publication |