CN108256123A - Service consultation self-learning method and device - Google Patents
Service consultation self-learning method and device Download PDFInfo
- Publication number
- CN108256123A CN108256123A CN201810156364.7A CN201810156364A CN108256123A CN 108256123 A CN108256123 A CN 108256123A CN 201810156364 A CN201810156364 A CN 201810156364A CN 108256123 A CN108256123 A CN 108256123A
- Authority
- CN
- China
- Prior art keywords
- consulting
- item
- instant
- reply
- sample database
- 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; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present invention provides a kind of service consultation self-learning method and device.The service consultation self-learning method includes：Receive Instant-Counseling problem；The Instant-Counseling problem is identified by identification model, with obtain with the Instant-Counseling problem matching degree be more than preset matching degree multinomial reply item and shown；When receiving user in the multinomial reply item and selecting an operation as target retro item, it is stored in the Instant-Counseling problem as the sample of standard advisory problem in the consulting sample database to update the consulting sample database, and correspondence is established with the target retro item.
Description
Technical field
The present invention relates to field of computer technology, in particular to a kind of service consultation self-learning method and device.
Background technology
Due to the development of e-commerce, lead to the also more and more of online consultation, the quantity of contact staff cannot be complete
Meet the demand for counseling of customer.Therefore, the prior art has by the way that robot is set to reply the problem of customer seeks advice from, to improve consulting
Efficiency.But robot cannot be identified and accurately be answered the problem of all completely.Therefore it also needs to further improve robot
It can identify the success rate of problem.
Invention content
In view of this, the embodiment of the present invention is designed to provide a kind of service consultation self-learning method and device.
A kind of service consultation self-learning method provided in an embodiment of the present invention, applied to electric terminal, the electric terminal
In be stored with consulting sample database, multinomial reply item is stored in the consulting sample database and standard corresponding with each reply item is consulted
Inquiry is inscribed, and each standard advisory problem corresponds to multiple standard advisory problem samples, and the service consultation self-learning method includes：
Receive Instant-Counseling problem；
The Instant-Counseling problem is identified by identification model, to obtain and the Instant-Counseling problem matching degree
More than preset matching degree multinomial reply item and shown, the identification model be using it is described consulting sample database as training sample
The identification model obtained using deep learning model training；
When receiving user in the multinomial reply item and selecting an operation as target retro item, by the reality
When ask questions in the sample deposit consulting sample database as standard advisory problem to update the consulting sample database, and with
The target retro item establishes correspondence.
The embodiment of the present invention also provides a kind of service consultation self study device, applied to electric terminal, the electric terminal
In be stored with consulting sample database, multinomial reply item is stored in the consulting sample database and standard corresponding with each reply item is consulted
Inquiry is inscribed, and each standard advisory problem corresponds to multiple samples, and the service consultation self study device includes：
Receiving module is seeked advice from, for receiving Instant-Counseling problem；
Enquiry module is identified the Instant-Counseling problem for passing through identification model, with obtain with it is described in real time
It asks questions multinomial reply item of the matching degree more than preset matching degree and is shown, the identification model is with the consulting sample
This library is the identification model that training sample is obtained using deep learning model training；
Memory module selects the behaviour as target retro item for that ought receive user in the multinomial reply item
When making, it is stored in the consulting sample database to update the official communication using the Instant-Counseling problem as the sample of standard advisory problem
Sample database is ask, and correspondence is established with the target retro item.
Compared with prior art, the service consultation self-learning method and device of the embodiment of the present invention.By that will identify
In the obtained Instant-Counseling problem write-in consulting sample database, enable the content in consulting sample database more perfect, make electricity
Sub- terminal recognition problem ability can be promoted well, so as to improve the successful recognition rate of electric terminal problem.
For the above objects, features and advantages of the present invention is enable to be clearer and more comprehensible, preferred embodiment cited below particularly, and coordinate
Appended attached drawing, is described in detail below.
Description of the drawings
It in order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range, for those of ordinary skill in the art, without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the schematic diagram that the electric terminal that present pre-ferred embodiments provide is interacted with consulting terminal.
Fig. 2 is the block diagram of electric terminal that present pre-ferred embodiments provide.
Fig. 3 is the flow chart of service consultation self-learning method that present pre-ferred embodiments provide.
Fig. 4 is the partial process view of service consultation self-learning method that another preferred embodiment of the present invention provides.
Fig. 5 is the partial process view of service consultation self-learning method that the another preferred embodiment of the present invention provides.
Fig. 6 is the high-level schematic functional block diagram of service consultation self study device that present pre-ferred embodiments provide.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Ground describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be configured to arrange and design with a variety of different herein.Cause
This, the detailed description of the embodiment of the present invention to providing in the accompanying drawings is not intended to limit claimed invention below
Range, but it is merely representative of the selected embodiment of the present invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Go out all other embodiments obtained under the premise of creative work, shall fall within the protection scope of the present invention.
It should be noted that：Similar label and letter represents similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need to that it is further defined and explained in subsequent attached drawing.Meanwhile the present invention's
In description, term " first ", " second " etc. are only used for distinguishing description, and it is not intended that instruction or hint relative importance.
As shown in Figure 1, it is that the electric terminal 100 that present pre-ferred embodiments provide is interacted with consulting terminal 200
Schematic diagram.The electric terminal 100 is communicatively coupled by network and one or more consulting terminal 200, to carry out data
Communication or interaction.The electric terminal 100 can be network server, database server, PC (personal
Computer, PC), tablet computer, smart mobile phone, personal digital assistant (personal digital assistant, PDA)
Deng.The consulting terminal 200 can be PC (personal computer, PC), tablet computer, smart mobile phone, individual
Digital assistants (personal digital assistant, PDA) etc..
In one embodiment, the electric terminal 100 is equipped with the serve end program of specified application, the official communication
The client-side program of specified application can be equipped with by asking terminal 200.The specified application can be Jingdone district, Taobao,
The sale class application programs such as poly- U.S.'s quality product.The specified application can also be that online doctor etc. services class application program.
In another embodiment, the electric terminal 100 is the robot being placed in service hall.The robot
It is asked questions by speech recognition acquisition.Then described ask questions is identified using machine learning, when can recognize
It is described when asking questions, it this is provided asks questions corresponding target retro item and asked questions with replying this.For example, language can be passed through
The form that sound is reported plays the target retro item, and the target retro item can also be included to the display screen in the robot
On.
Fig. 2 shows the block diagrams of electric terminal 100.The electric terminal includes service consultation self study device
110th, memory 111, storage control 112, processor 113, Peripheral Interface 114, input-output unit 115, display unit
116.Structure shown in Fig. 2 is only to illustrate, and the structure of electric terminal 100 is not caused to limit.For example, electric terminal 100
It may also include than shown in Fig. 2 more either less components or with the configuration different from shown in Fig. 2.
The memory 111, storage control 112, processor 113, Peripheral Interface 114, input-output unit 115 and aobvious
Show that 116 each element of unit is directly or indirectly electrically connected between each other, to realize the transmission of data or interaction.For example, these
Element can be realized by one or more communication bus or signal wire be electrically connected between each other.The service consultation self study dress
Putting 110 can be stored in the memory 111 or be solidificated in the form of software or firmware (firmware) including at least one
Software function module in the operating system (operating system, OS) of the electric terminal 100.The processor 113
For performing the executable module stored in memory, such as the software function that the service consultation self study device 110 includes
Module or computer program.
Wherein, the memory 111 may be, but not limited to, random access memory (Random Access
Memory, RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable
Read-Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only
Memory, EPROM), electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only
Memory, EEPROM) etc..Wherein, memory 111 is for storing program, the processor 113 after execute instruction is received,
Described program is performed, the method performed by electric terminal 100 that the process that any embodiment of the embodiment of the present invention discloses defines can
To be applied to realize in processor 113 or by processor 113.
The processor 113 may be a kind of IC chip, have the processing capacity of signal.Above-mentioned processor
113 can be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processes
Device (Network Processor, abbreviation NP) etc.；It can also be digital signal processor (DSP), application-specific integrated circuit
(ASIC), field programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components.It can realize or perform disclosed each method, step and the logic diagram in the embodiment of the present invention.It is general
Processor can be microprocessor or the processor can also be any conventional processor etc..
Various input/output devices are coupled to processor 113 and memory 111 by the Peripheral Interface 114.At some
In embodiment, Peripheral Interface 114, processor 113 and storage control 112 can be realized in one single chip.Other one
In a little examples, they can be realized by independent chip respectively.
The input-output unit 115 is used to be supplied to user input data.The input-output unit 115 can be,
But it is not limited to, mouse and keyboard etc..Audio unit provides a user audio interface, may include one or more microphones, one
A or multiple loud speakers and voicefrequency circuit.
The display unit 116 provided between the electric terminal 100 and user an interactive interface (such as user behaviour
Make interface) or for display image data give user reference.In the present embodiment, the display unit can be liquid crystal display
Or touch control display.Can be the capacitance type touch control screen or resistance for supporting single-point and multi-point touch operation if touch control display
Formula touch screen etc..Single-point and multi-point touch operation is supported to refer to that touch control display can sense on the touch control display one
Or the touch control operation generated simultaneously at multiple positions, and processor is transferred to be calculated and located the touch control operation that this is sensed
Reason.
Referring to Fig. 3, it is that the service applied to electric terminal 100 shown in Fig. 2 that present pre-ferred embodiments provide is consulted
Ask the flow chart of self-learning method.Idiographic flow shown in Fig. 3 will be described in detail below.
Step S101 receives Instant-Counseling problem.
In the present embodiment, the Instant-Counseling problem can be sent out by the consulting terminal communicated to connect with the electric terminal
That send asks questions；Can also be the speech message received by electric terminal, the official communication which is identified
Inquiry is inscribed.
Step S102 is identified the Instant-Counseling problem by identification model, to obtain and the Instant-Counseling
Problem matching degree is more than the multinomial reply item of preset matching degree and is shown.
In the present embodiment, the identification model can use deep learning mould as training sample using the consulting sample database
The identification model that type training obtains.
In the present embodiment, step S102 includes：The Instant-Counseling problem is identified by identification model, is found out
It is higher than multiple standard advisory problems of preset matching degree with the Instant-Counseling problem similarity；It is looked into the consulting sample database
It finds out multinomial reply item corresponding with the multiple standard advisory problem respectively and is shown.
In one embodiment, it is described consulting sample database in be stored with multinomial reply item and with it is each reply item it is corresponding
Standard advisory problem, each standard advisory problem correspond to multiple samples.For example, one replys item as " so-and-so express delivery ", the reply item
The sample of corresponding standard advisory problem can be " what express delivery sent out ", " what acquiescence is quickly " etc..When the Instant-Counseling is asked
When topic asks questions matching degree with " what express delivery sent out ", " acquiescence what is quickly " any standard and has been more than 60%, then reply is shown
Item " so-and-so express delivery ".When the matching degree of the Instant-Counseling problem and multinomial standard advisory problem has been above the preset matching
Degree then shows that the corresponding multinomial reply item of the multinomial standard advisory problem is selected for user.
Step S103 selects an operation as target retro item when receiving user in the multinomial reply item
When, it is stored in the consulting sample database to update the consulting using the Instant-Counseling problem as the sample of standard advisory problem
Sample database, and establish correspondence with the target retro item.
In the present embodiment, the standard advisory problem is the corresponding standard advisory problem of the target retro item.
In the present embodiment, the service consultation self-learning method further includes：The target retro item is sent to the official communication
Terminal is ask, so that the consulting terminal shows the target retro item.
For example, the electric terminal receives the user's operation of " so-and-so express delivery " as the target retro item by described in
When, the sample of the interim advisory message " so-and-so express delivery " corresponding standard advisory problem as described in is stored in the consulting sample
In this library, and correspondence is established with the reply item " so-and-so express delivery ".
Further, the electric terminal receives user and selects behaviour of the multinomial reply item as the target retro item
Make, then the Instant-Counseling problem is stored in the consulting sample database, correspondence is established with multinomial reply item.This reality
It applies in example, the user can be contact staff.
Method in the present embodiment in service process by receiving Instant-Counseling problem and user by being confirmed
The target retro item is obtained, the Instant-Counseling problem and the target retro item are associated, to realize the electricity
The self study process of sub- terminal can improve the consulting sample thereby using electric terminal during service consultation is provided
Library, preferably to identify the Instant-Counseling problem received.
In other embodiments, as shown in figure 4, the service consultation self-learning method may also include：Step S104 is extremely walked
Rapid S107.
Step S104 is identified the Instant-Counseling problem by identification model, finds out and the Instant-Counseling
Problem similarity is higher than multiple standard advisory problems of preset matching degree.
The multiple standard advisory problem is sent to the consulting terminal by step S105, so that the consulting terminal is shown
Show.
Step S106 receives the consulting item that the consulting terminal is sent in the selection of the multiple standard advisory problem.
Step S107 sends the corresponding reply item of the consulting item according to the consulting item to the consulting terminal, so that
The consulting terminal is shown.
By step S105 to S107, the confirmation that terminal is seeked advice from by reception seeks advice from item, consulting item is made more to meet the electricity
What the identification model of sub- terminal can be identified preferably asks questions, and the answer for replying to consulting terminal can be made more to disclosure satisfy that
The demand of consultant.
In other embodiments, it as shown in figure 5, the method further includes step S108 to step S1011, specifically describes such as
Under.
Step S108 receives user and inputs reply character string, returned the character string input by user as the target
The target retro item is replied the Instant-Counseling problem by multiple item.
It, can when the reply item of electric terminal generation does not meet answer needed for the Instant-Counseling problem in the present embodiment
The reply character string input by user received is sent to the consulting terminal as target retro item.
Step S109 obtains the advisory data received in specified time section.
In the present embodiment, the advisory data include in the specified time section Instant-Counseling problem that receives and with reality
When ask questions corresponding reply character string input by user.
Step S1010 obtains the target time that the reply character string frequency of occurrences in the advisory data is more than predetermined probabilities
Multiple character string.
Step S1011, using the target retro character string as replying, item write-in is described to seek advice from sample database, and by described in
The official communication is written as the corresponding standard advisory problem of the target retro character string in corresponding ask questions of target retro character string
It askes in sample database.
In the present embodiment, the predetermined probabilities can be pre-set probability, and step S109 is being performed a plurality of times to step
The probability can be used during S1011.The predetermined probabilities can also be every time perform step S108 to step S1011 with into
Receive user's input probability when row update consulting sample database.
The problem of can getting the problem of consultant compares concern by above-mentioned steps, can pay close attention to consultant, carries out
Storage, is workload with the user for reducing client, also can provide answer for consultant well.
In the present embodiment, the electric terminal can perform step S109 to S1011 to the official communication after specified time
Sample database is ask to be updated.The consulting sample database timing is updated to the habit that consulting sample database can be enable more to meet consultant
Idiom preferably can provide answer for consultant.
In the present embodiment, the service consultation self-learning method further includes：According to period specified time with updated institute
It states consulting sample database and obtains newer identification model using deep learning model training.
In the present embodiment, by constantly updating the sample database in the electric terminal, the more experiences of sample are with regard to more, in institute
The judgment method formd in electric terminal to language meaning is stated, identical meanings consulting is recognized not so as to draw inferences about other cases from one instance
Same expression way.The accumulation of the sample in method in through this embodiment, constantly in the real work of the electric terminal
Sample is accumulated, so as to improve this electric terminal recognition capability, so as to promote the accuracy rate of the identification of electric terminal.
The service consultation self-learning method of the embodiment of the present invention is written by the Instant-Counseling problem that will be identified
In the consulting sample database, enable the content in consulting sample database more perfect, electric terminal is enable to identify problem ability
It is promoted well, so as to improve the successful recognition rate of electric terminal problem.
Referring to Fig. 6, it is the work(for the service consultation self study device 110 shown in Fig. 2 that present pre-ferred embodiments provide
It can module diagram.The modules in service consultation self study device 110 in the present embodiment are real for performing the above method
Apply the step in example.The service consultation self study device 110 includes：It seeks advice from receiving module 1101, enquiry module 1102 and deposits
Store up module 1103.
The consulting receiving module 1101, for receiving Instant-Counseling problem.
The enquiry module 1102 is identified the Instant-Counseling problem for passing through identification model, with obtain with
The Instant-Counseling problem matching degree is more than the multinomial reply item of preset matching degree and is shown.
The memory module 1103 selects one to be returned as target for that ought receive user in the multinomial reply item
During the operation of multiple item, it is stored in the Instant-Counseling problem as the sample of standard advisory problem in the consulting sample database with more
The new consulting sample database, and establish correspondence with the target retro item.
In the present embodiment, the enquiry module 1102 includes：Problem matching unit and reply searching unit.
Described problem matching unit is identified the Instant-Counseling problem for passing through identification model, find out with
The Instant-Counseling problem similarity is higher than multiple standard advisory problems of preset matching degree.
The reply searching unit is asked for being found out in the consulting sample database with the multiple standard advisory respectively
It inscribes corresponding multinomial reply item and is shown.
In the present embodiment, the consulting receiving module 1101 is additionally operable to receive the real-time official communication that the consulting terminal is sent
Inquiry is inscribed；The service consultation self study device 110 further includes：Training module 1104, for training module 1104, for according to
Period specified time obtains newer identification model with the updated consulting sample database using deep learning model training.
The electric terminal and consulting terminal communication connection, referring to Fig. 6, the service consultation self study device is also
Including：Sending module 1105 and receiving module 1106.
The enquiry module 1102 is additionally operable to that the Instant-Counseling problem is identified by identification model, find out with
The Instant-Counseling problem similarity is higher than multiple standard advisory problems of preset matching degree.
The sending module 1105, for the multiple standard advisory problem to be sent to the consulting terminal, so that institute
Consulting terminal is stated to show.
The confirmation receiving module 1106 selects to send out for receiving the consulting terminal in the multiple standard advisory problem
The consulting item sent.
The memory module 1103 is additionally operable to send the consulting item correspondence to the consulting terminal according to the consulting item
Reply item so that it is described consulting terminal show.
In the present embodiment, the service consultation self study device 110, which further includes, replys receiving module 1107, acquisition module
1108th, module 1109 and update module 11010 are obtained.
The reply receiving module 1107 inputs reply character string for receiving user, the reply character string is sent
To the consulting terminal, so that the consulting terminal shows the target retro item；
The acquisition module 1108, for obtaining the advisory data received in specified time section, the advisory data packet
Include the Instant-Counseling problem received in the specified time section and reply word input by user corresponding with Instant-Counseling problem
Symbol string.
It is described to obtain module 1109, it is general more than default for obtaining the reply character string frequency of occurrences in the advisory data
The target retro character string of rate.
The update module 11010 is additionally operable to that the consulting sample is written using the target retro character string as item is replied
In library, and corresponding ask questions of the target retro character string is asked as the corresponding standard advisory of target retro character string
It inscribes in the consulting sample database.
The other details closed in this present embodiment can further refer to the description in above method embodiment, herein not
It repeats again.
The service consultation self study device of the embodiment of the present invention.It is written by the Instant-Counseling problem that will be identified
In the consulting sample database, enable the content in consulting sample database more perfect, electric terminal is enable to identify problem ability
It is promoted well, so as to improve the successful recognition rate of electric terminal problem.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flow chart or block diagram can represent the one of a module, program segment or code
Part, a part for the module, program segment or code include one or more and are used to implement holding for defined logic function
Row instruction.It should also be noted that at some as in the realization method replaced, the function that is marked in box can also be to be different from
The sequence marked in attached drawing occurs.For example, two continuous boxes can essentially perform substantially in parallel, they are sometimes
It can perform in the opposite order, this is depended on the functions involved.It is it is also noted that every in block diagram and/or flow chart
The combination of a box and the box in block diagram and/or flow chart can use function or the dedicated base of action as defined in performing
It realizes or can be realized with the combination of specialized hardware and computer instruction in the system of hardware.
In addition, each function module in each embodiment of the present invention can integrate to form an independent portion
Point or modules individualism, can also two or more modules be integrated to form an independent part.
If the function is realized in the form of software function module and is independent product sale or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme of the present invention is substantially in other words
The part contribute to the prior art or the part of the technical solution can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, is used including some instructions so that a computer equipment (can be
People's computer, server or network equipment etc.) perform all or part of the steps of the method according to each embodiment of the present invention.
And aforementioned storage medium includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic disc or CD.It needs
Illustrate, herein, relational terms such as first and second and the like be used merely to by an entity or operation with
Another entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this realities
The relationship or sequence on border.Moreover, term " comprising ", "comprising" or its any other variant are intended to the packet of nonexcludability
Contain so that process, method, article or equipment including a series of elements not only include those elements, but also including
It other elements that are not explicitly listed or further includes as elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, also there are other identical elements in article or equipment.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, that is made any repaiies
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should be noted that：Similar label and letter exists
Similar terms are represented in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and is explained.
The above description is merely a specific embodiment, but protection scope of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in change or replacement, should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (10)
1. a kind of service consultation self-learning method, which is characterized in that applied to electric terminal, official communication is stored in the electric terminal
Sample database is ask, multinomial reply item and standard advisory problem corresponding with each reply item are stored in the consulting sample database, often
A standard advisory problem corresponds to multiple samples, and the service consultation self-learning method includes：
Receive Instant-Counseling problem；
The Instant-Counseling problem is identified by identification model, to obtain being more than with the Instant-Counseling problem matching degree
The multinomial reply item of preset matching degree is simultaneously shown that the identification model is to be used using the consulting sample database as training sample
The identification model that deep learning model training obtains；
When receiving user in the multinomial reply item and selecting an operation as target retro item, by the real-time official communication
Inquiry topic as standard advisory problem sample deposit it is described seek advice from sample database to update the consulting sample database, and with it is described
Target retro item establishes correspondence.
2. service consultation self-learning method as described in claim 1, which is characterized in that by identification model to the real-time official communication
Inquiry topic be identified, with obtain with the Instant-Counseling problem matching degree be more than preset matching degree multinomial reply item and carry out
The step of display, includes：
The Instant-Counseling problem is identified by identification model, finds out and is higher than with the Instant-Counseling problem similarity
Multiple standard advisory problems of preset matching degree；
Multinomial reply item corresponding with the multiple standard advisory problem respectively is found out in the consulting sample database and is carried out
Display.
3. service consultation self-learning method as described in claim 1, which is characterized in that the electric terminal leads to consulting terminal
Letter connection, the method further include：
The Instant-Counseling problem is identified by identification model, finds out and is higher than with the Instant-Counseling problem similarity
Multiple standard advisory problems of preset matching degree；
The multiple standard advisory problem is sent to the consulting terminal, so that the consulting terminal is shown；
Receive the consulting item that the consulting terminal is sent in the selection of the multiple standard advisory problem；
The corresponding reply item of the consulting item is sent to the consulting terminal according to the consulting item, so that the consulting terminal is shown
Show.
4. service consultation self-learning method as described in claim 1, which is characterized in that the method further includes：
It receives user and inputs reply character string, using the character string input by user as the target retro item, by the target
The Instant-Counseling problem is replied in the answer that item is replied as the Instant-Counseling problem；
The advisory data received in specified time section is obtained, the advisory data includes what is received in specified time section
Instant-Counseling problem and reply character string input by user corresponding with Instant-Counseling problem；
Obtain the target retro character string that the reply character string frequency of occurrences in the advisory data is more than predetermined probabilities；
Using the target retro character string as replying in the item write-in consulting sample database, and by the target retro character string
It is corresponding to ask questions as in the corresponding standard advisory problem write-in consulting sample database of the target retro character string.
5. the service consultation self-learning method as described in claim 1-4 any one, which is characterized in that the method is also wrapped
It includes：
Newer knowledge is obtained using deep learning model training with the updated consulting sample database according to period specified time
Other model.
6. a kind of service consultation self study device, which is characterized in that applied to electric terminal, official communication is stored in the electric terminal
Sample database is ask, multinomial reply item and standard advisory problem corresponding with each reply item are stored in the consulting sample database, often
A standard advisory problem corresponds to multiple samples, and the service consultation self study device includes：
Receiving module is seeked advice from, for receiving Instant-Counseling problem；
Enquiry module is identified the Instant-Counseling problem for passing through identification model, to obtain and the Instant-Counseling
Problem matching degree is more than the multinomial reply item of preset matching degree and is shown, the identification model is with the consulting sample database
The identification model obtained for training sample using deep learning model training；
Memory module selects an operation as target retro item for that ought receive user in the multinomial reply item
When, it is stored in the consulting sample database to update the consulting using the Instant-Counseling problem as the sample of standard advisory problem
Sample database, and establish correspondence with the target retro item.
7. service consultation self study device as claimed in claim 6, which is characterized in that the enquiry module includes：
Problem matching unit is identified the Instant-Counseling problem for passing through identification model, find out with it is described in real time
Ask questions multiple standard advisory problems that similarity is higher than preset matching degree；
Searching unit is replied, it is corresponding with the multiple standard advisory problem respectively for being found out in the consulting sample database
Multinomial reply item is simultaneously shown.
8. service consultation self study device as claimed in claim 6, which is characterized in that the electric terminal leads to consulting terminal
Letter connection, described device further include：
The enquiry module is additionally operable to that the Instant-Counseling problem is identified by identification model, find out with it is described in real time
Ask questions multiple standard advisory problems that similarity is higher than preset matching degree；
Sending module, for the multiple standard advisory problem to be sent to the consulting terminal, so that the consulting terminal is shown
Show；
Receiving module is confirmed, for receiving the consulting item that the consulting terminal is sent in the selection of the multiple standard advisory problem；
The memory module is additionally operable to send the corresponding reply item of the consulting item to the consulting terminal according to the consulting item,
So that the consulting terminal is shown.
9. service consultation self study device as claimed in claim 6, which is characterized in that described device further includes：
Receiving module is replied, reply character string is inputted for receiving user, using the character string input by user as the mesh
Mark replys item, and the Instant-Counseling problem is replied using the target retro item as the answer of the Instant-Counseling problem；
Acquisition module, for obtaining the advisory data received in specified time section, when the advisory data includes described specified
Between the Instant-Counseling problem that receives in section and reply character string input by user corresponding with Instant-Counseling problem；
Module is obtained, for obtaining the target retro that the reply character string frequency of occurrences in the advisory data is more than predetermined probabilities
Character string；
Update module, for item write-in is described to seek advice from sample database, and by described in as replying using the target retro character string
The official communication is written as the corresponding standard advisory problem of the target retro character string in corresponding ask questions of target retro character string
It askes in sample database.
10. the service consultation self study device as described in claim 6-9 any one, which is characterized in that described device is also wrapped
It includes：Training module, for using deep learning model training according to period specified time with the updated consulting sample database
Obtain newer identification model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810156364.7A CN108256123A (en) | 2018-02-24 | 2018-02-24 | Service consultation self-learning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810156364.7A CN108256123A (en) | 2018-02-24 | 2018-02-24 | Service consultation self-learning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108256123A true CN108256123A (en) | 2018-07-06 |
Family
ID=62745171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810156364.7A Pending CN108256123A (en) | 2018-02-24 | 2018-02-24 | Service consultation self-learning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108256123A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110377712A (en) * | 2019-07-12 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of intelligence conversation switching method, device, equipment and storage medium |
| CN110505142A (en) * | 2019-08-06 | 2019-11-26 | 北京达佳互联信息技术有限公司 | Message informing method, device, electronic equipment and storage medium |
| CN115470325A (en) * | 2021-06-10 | 2022-12-13 | 腾讯科技（深圳）有限公司 | Message reply method, device and equipment |
| CN115470325B (en) * | 2021-06-10 | 2024-05-10 | 腾讯科技（深圳）有限公司 | Message reply method, device and equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104850539A (en) * | 2015-05-28 | 2015-08-19 | 宁波薄言信息技术有限公司 | Natural language understanding method and travel question-answering system based on same |
| CN105893391A (en) * | 2015-01-26 | 2016-08-24 | 阿里巴巴集团控股有限公司 | Intelligent answering method, apparatus and system, and electronic device |
| CN106789595A (en) * | 2017-01-17 | 2017-05-31 | 北京诸葛找房信息技术有限公司 | Information-pushing method and device |
-
2018
- 2018-02-24 CN CN201810156364.7A patent/CN108256123A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105893391A (en) * | 2015-01-26 | 2016-08-24 | 阿里巴巴集团控股有限公司 | Intelligent answering method, apparatus and system, and electronic device |
| CN104850539A (en) * | 2015-05-28 | 2015-08-19 | 宁波薄言信息技术有限公司 | Natural language understanding method and travel question-answering system based on same |
| CN106789595A (en) * | 2017-01-17 | 2017-05-31 | 北京诸葛找房信息技术有限公司 | Information-pushing method and device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110377712A (en) * | 2019-07-12 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of intelligence conversation switching method, device, equipment and storage medium |
| CN110377712B (en) * | 2019-07-12 | 2023-05-16 | 腾讯科技（深圳）有限公司 | Intelligent session switching method, device, equipment and storage medium |
| CN110505142A (en) * | 2019-08-06 | 2019-11-26 | 北京达佳互联信息技术有限公司 | Message informing method, device, electronic equipment and storage medium |
| CN115470325A (en) * | 2021-06-10 | 2022-12-13 | 腾讯科技（深圳）有限公司 | Message reply method, device and equipment |
| CN115470325B (en) * | 2021-06-10 | 2024-05-10 | 腾讯科技（深圳）有限公司 | Message reply method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11238228B2 (en) | Training systems for pseudo labeling natural language | |
| CN108415980A (en) | Question and answer data processing method, electronic device and storage medium | |
| US20170124184A1 (en) | Method and system for performing a probabilistic topic analysis of search queries for a customer support system | |
| US10841257B1 (en) | Determining engagement scores for sub-categories in a digital domain by a computing system | |
| CN107066537A (en) | Hot news generation method, equipment, electronic equipment | |
| US11704594B2 (en) | Machine learning system | |
| CN110825956A (en) | Information flow recommendation method and device, computer equipment and storage medium | |
| CN108073659A (en) | A kind of love and marriage object recommendation method and device | |
| CN108053105A (en) | Traveller's distribution method and device | |
| US9704168B2 (en) | Method and system for implementing profiles for an enterprise business application | |
| CN108510384A (en) | Loan product recommends method and device | |
| CN109543005A (en) | The dialogue state recognition methods of customer service robot and device, equipment, storage medium | |
| US20220294897A1 (en) | Systems and methods to manage models for call data | |
| CN109598404A (en) | Automatically to the method and apparatus for issuing the progress data processing of sales task list | |
| US20230020864A1 (en) | Social network for merchants | |
| US20150278907A1 (en) | User Inactivity Aware Recommendation System | |
| CN108256123A (en) | Service consultation self-learning method and device | |
| CN112749238A (en) | Search ranking method and device, electronic equipment and computer-readable storage medium | |
| CN111753203A (en) | Card number recommendation method, device, equipment and medium | |
| CN108198037A (en) | Account management method and device | |
| WO2023196456A1 (en) | Adaptive wellness collaborative media system | |
| CN110134872A (en) | Determination method, apparatus, server and the readable medium on information notice opportunity | |
| CN111859154B (en) | Application recommendation method and device | |
| CN109657073A (en) | Method and apparatus for generating information | |
| US11687591B2 (en) | Systems, methods, computing platforms, and storage media for comparing non-adjacent data subsets |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 610000 Huayang Street, Tianfu New District, Chengdu City, Sichuan Province, No. 1, No. 2, No. 19 Building, Unit 2, 1903 Applicant after: Chengdu Xiaoduo Technology Co., Ltd. Address before: 610000 846, southern section of Tianfu Avenue, Huayang street, Tianfu New District, Chengdu, Sichuan Applicant before: CHENGDU XIAODUO TECH CO., LTD. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180706 |