CN107180029A - A kind of information processing method and device based on consultation service - Google Patents
A kind of information processing method and device based on consultation service Download PDFInfo
- Publication number
- CN107180029A CN107180029A CN201610131535.1A CN201610131535A CN107180029A CN 107180029 A CN107180029 A CN 107180029A CN 201610131535 A CN201610131535 A CN 201610131535A CN 107180029 A CN107180029 A CN 107180029A
- Authority
- CN
- China
- Prior art keywords
- text
- consulting
- initial
- result
- user
- 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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses a kind of information processing method and device based on consultation service, this method includes：Receive the problem of user inputs, text formatting processing is carried out to described problem, generate typical problem text, call all kinds of consulting engines having been turned on to handle the typical problem text, generate each initial consulting result, according to default confidence level rule, determine the confidence level of each initial consulting result, according to the confidence level for each initial consulting result determined, it is determined that the initial consulting result matched with the typical problem text, and it is shown as the consulting result of described problem.By this method, for the customer problem of diversification, it can be selected in a variety of consulting results and more conform to the desired answer of user, lift the accuracy replied.
Description
Technical field
The application is related to field of computer technology, more particularly to a kind of information processing method based on consultation service
And device.
Background technology
With the development of information technology, on-line system can provide the user increasingly abundanter business service.
In order to which user can successfully obtain the service provided by on-line system, and successfully solve obtaining industry
During business service the problem of meet, therefore on-line system would generally set customer service system, to be user
Business consultation service is provided.
At present, the customer service system in on-line system is typically a kind of artificial customer service system, but with on-line system
Visit capacity it is growing day by day, carry out business consultation user number be also continuously increased, this results in Traditional Man
Customer service system has produced certain service bottleneck due to being limited by customer service number, specifically, when obtaining
When the customer volume for taking business consultation to service is larger, the situation that certain customers wait as long for just occurs, it is clear that
Traditional artificial customer service system is difficult to the business consultation service for meeting a large number of users.
In the prior art, traditional artificial customer service system is gradually converted into automatic question answering formula by on-line system
Customer service system, so as to which corresponding business consultation service can be provided towards a large number of users.Specifically, user can be with
The there is provided business consultation interface by providing online, problem is proposed to customer service system, and by the customer service system
After the problem of being proposed to user is analyzed, corresponding consulting result is provided a user.
But, for the customer service system of automatic question answering formula in the prior art, generally asked only with single
Consultation is answered, so may result in customer service system can only handle consultation service according to single tupe,
And in practical application, the traffic issues that user is proposed may be complicated, changeable, it is clear that single question and answer are consulted
Inquiry pattern is not applied to simultaneously.
For example：Only with the question and answer technology based on keyword retrieval in some on-line systems, wherein, the technology
The main various keywords being to determine in problem sentence, using corresponding searching algorithm, for keyword in number
The answer matched according to carrying out retrieving in storehouse, and it is supplied to user.However, the technology is only to problem sentence
In keyword retrieved, but have ignored the grammer and the meaning of one's words in problem sentence.In other words, if user
The problem of input, does not include obvious keyword, or complex grammer has been used in problem, then,
User can not obtain effectively seeking advice from result.
The content of the invention
The embodiment of the present application provides a kind of customer service automatic question-answering method, to solve existing automatic question answering formula visitor
The problem of applicability that dress system is handled for consultation service is poor.
A kind of information processing method based on consultation service that the embodiment of the present application is provided, this method includes：
Receive the problem of user inputs；
Text formatting processing is carried out to described problem, typical problem text is generated；
Call all kinds of consulting engines having been turned on to handle the typical problem text, generate each initial official communication
Ask result；
According to default confidence level rule, the confidence level of each initial consulting result is determined；
According to the confidence level for each initial consulting result determined, it is determined that matching with the typical problem text
Initial consulting result, and be shown as the consulting result of described problem.
A kind of information processor based on consultation service that the embodiment of the present application is provided, the device includes：
Receiving module, for receiving the problem of user inputs；
Text processing module, for carrying out text formatting processing to described problem, generates typical problem text；
Processing module is called, all kinds of consulting engines being had been turned on for calling are carried out to the typical problem text
Processing, generates each initial consulting result；
Confidence level module, for according to default confidence level rule, determining putting for each initial consulting result
Reliability；
Seek advice from object module, for according to determine it is each it is initial consulting result confidence level, it is determined that with it is described
The initial consulting result that typical problem text matches, and be shown as the consulting result of described problem.
The embodiment of the present application provides a kind of information processing method and device based on consultation service, with it,
After the server that operation has automatic customer service system have received the problem of user inputs, the problem will be carried out
Text formatting processing, the fixed Sentence format of server is converted into by the Sentence format of the problem, that is,
Typical problem text is generated, and then, server will call a variety of consulting engines to carry out the typical problem text
Processing, each consulting engine all has different analyses, query function, so, is consulted by a variety of
After the processing for asking engine, a variety of initial consulting results will be obtained, in these initial consulting results, certain
A little initial consulting results are suitable as the answer for the problem of user proposes, and some initial consulting results are not
It is adapted to, in this case, server goes forward side by side one it is determined that confidence level of each initial consulting result
The confidence level according to each initial consulting result is walked, the consulting result matched the most with above mentioned problem is determined, makees
User is supplied to for the answer of problem.Unlike the prior art, it is exactly based on the side of a variety of consulting engines
The problem of formula, diversification that can be proposed for user, is handled, and obtains the consulting result of diversification, and
It is not existing single consultation, moreover, a variety of consulting knots obtained in a variety of consulting engine processing
On the basis of fruit, it can be selected in these consulting results and more conform to the desired answer of user, i.e. lifting
The accuracy replied.
Brief description of the drawings
Accompanying drawing described herein is used for providing further understanding of the present application, constitutes the part of the application,
The schematic description and description of the application is used to explain the application, does not constitute the improper limit to the application
It is fixed.In the accompanying drawings：
The information process based on consultation service that Fig. 1 provides for the embodiment of the present application；
The schematic diagram at the consulting interface that Fig. 2 provides for the embodiment of the present application；
The information processor structural representation based on consultation service that Fig. 3 provides for the embodiment of the present application.
Embodiment
It is specifically real below in conjunction with the application to make the purpose, technical scheme and advantage of the application clearer
Apply example and technical scheme is clearly and completely described corresponding accompanying drawing.Obviously, it is described
Embodiment is only some embodiments of the present application, rather than whole embodiments.Based on the implementation in the application
Example, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of the application protection.
Just it has been observed that existing automatic question answering formula customer service system (in order to be different from artificial customer service system, therefore
Hereinafter referred to as automatic customer service system) generally only with single consultation, so as to cause obtained by user
The consulting result arrived is also more single, so, and the problem of automatic customer service system can only be to some aspects is carried
For corresponding consulting result, its applicability is poor, in some actual scenes, and user even can not be by certainly
Dynamic customer service system obtains accurately seeking advice from result.This is accomplished by a kind of to handle the automatic visitor of diversification problem
Dress system, therefore, in the embodiment of the present application provides a kind of information processing method based on consultation service, in reality
In the application of border, the automatic customer service system based on this method passes through a variety of consulting engine (that is, advisory role lists
Member), provide different initial answers the problem of the diversification proposed to user, and initial answer different
On the basis of case, preferably going out to best suit the answer of customer problem, there is provided to user.
Furthermore, it is necessary to which explanation, for the automatic customer service system in the embodiment of the present application, can run
In the server on on-line system backstage, then, under the scene, user's input will be received by the server
The problem of.Certainly, automatic customer service system also may operate at terminal local used in user, under the scene,
Automatic customer service system will keep network connection with the database on on-line system backstage, so as to provide the user automatic
Catechetical counseling services.Two kinds of above-mentioned scenes do not constitute the restriction to the application.Under the application
State in content, the scene that server is operated in based on automatic customer service system is specifically described.
Specifically, as shown in figure 1, a kind of letter based on consultation service provided by the embodiment of the present application
Processing method is ceased, this method specifically includes following steps：
S101, receives the problem of user inputs.
When user obtains corresponding business service by on-line system to go wrong, or when user is for online
When the business service that system is provided has query, user just can use the automatic visitor that on-line system is provided
Dress system, that is, user is seeked advice from the problem of can inputting corresponding.So, operation has automatic customer service system
Server will just receive user the problem of input.
During practical application, the problem of user can input corresponding by terminal used in itself.Wherein, use
Terminal includes but is not limited to used in family：The mobile terminals such as mobile phone, tablet personal computer or terminal etc..
S102, text formatting processing is carried out to described problem, generates typical problem text.
The problem of user inputs is it is possible that colloquial sentence, the sentence not comprising any punctuation mark
Etc. the sentence of a variety of noncanonical formats.So it is possible to cause to a certain degree follow-up query analysis process
Influence, therefore, in the embodiment of the present application, in order to lifted subsequent query analyze process accuracy, therefore
By the way of text formatting is handled, the problem of user is inputted is converted into the typical problem text of cannonical format.
Here typical problem text, can meet server to carry out sentence required during query analysis, example
Such as：The problem of server can be proposed for user, is converted into the Sentence format of subject+predicate+object.
Certainly, in actual applications, typical problem text will according to defined in different server standard statement format
And it is different, the restriction to the application is not constituted here.
In addition, in the embodiment of the present application, text formatting processing can include：Participle, form error correction and/
Or word meaning conversion process etc., the restriction to the application is not constituted here.
S103, calls all kinds of consulting engines having been turned on to handle the typical problem text, and generation is each
Initial consulting result.
In the automatic customer service system run in the server, a variety of consulting engines are contained, are respectively used to perform
Different advisory roles, for example：Certain consulting engine is used to provide the conversation sentence under chat scenario, then,
When user's input problem is greets sentence " hello ", user " you just can be replied by the consulting engine
Good, what, which be may I ask, can help you" in another example：Certain consulting engine has service inquiry function, when
When including the phrase relevant with certain business in the problem of user inputs, then, the consulting engine just can basis
Corresponding service in phrase inquiry on-line system, and by the information of the corresponding service inquired (introduction to business,
The information such as application method) return to user.
It should be noted that a variety of consulting engines in the application can be started according to actual application scenarios or
(in some actual scenes, seeking advice from the startup or closing of engine can be controlled by operating personnel, here for closing
Not as the restriction to the application), therefore, the typical problem text obtained for aforementioned process, server
All consulting engines having been turned on will be called to be handled.
Exactly use above-mentioned a variety of consulting engines so that the problem of being proposed for user carries out comprehensive
Ground is analyzed and inquired about, and provides a user the consulting result of diversification, rather than official communication single in the prior art
Inquiry pattern.
But due to different types of function of seeking advice from engine and differ, so, provided for same problem
Consulting result be also typically inconsistent, some consulting results for being generated of consulting engines may be not appropriate for
The problem of user proposes, therefore in above-mentioned steps S103, given birth to after each consulting engine is handled
Into consulting result be used as initial consulting result.Further, it is necessary to selected from multiple initial consulting results
The consulting result of most suitable problem is selected out, that is, performing following step S104.
S104, according to default confidence level rule, determines the confidence level of each initial consulting result.
Confidence level rule in the embodiment of the present application can include many algorithms, be used as one in the embodiment of the present application
The mode of kind, confidence level rule can be configured according to different business scenarios, for example：For in on-line system
Added Business, the confidence level of the consulting engine for carrying out service concept inquiry can be heightened because
User would generally seek advice from Added Business some Back ground Informations on the Added Business.
As the another way in the embodiment of the present application, confidence level rule can be retrieved according to each consulting engine
To the frequency of sentence be configured, for example：The a certain problem proposed for user, two kinds of consulting engines
A and B carry out query and search in corresponding database, it is assumed that the official communication that consulting engine A is retrieved
Result a is ask, and seeks advice from the consulting result b that engine B is retrieved, it is further assumed that consulting result a exists
It is 1,000 times as the number of times of the answer of such problem in the historical data of data place record, similarly,
It is 200 times that result b, which is seeked advice from, as the number of times of the answer of such problem.So as to confidence level rule in this example
Can be：Seek advice from engine A confidence level of the confidence level higher than consulting engine B.
Certainly, in practical application scene, the computational methods of other confidence levels can also be used, here not
Constitute the restriction to the application.
By different certainty factor algebra'ss (that is, above-mentioned confidence level rule), just it can determine each first
Begin the consulting respective confidence level of result, on this basis, also just can be according to each initial confidence for seeking advice from result
Degree, to determine the consulting result for the problem of best suiting, that is, performing following step S105.
S105, according to determine it is each it is initial consulting result confidence level, it is determined that with the typical problem text
The initial consulting result matched, and be shown as the consulting result of described problem.
The confidence level of each initial consulting result, can be regarded as the initial consulting result and accords with customer problem
Credibility, it is clear that confidence level highest initially seeks advice from result and also just meets customer problem the most.So,
It is used as a kind of mode in the embodiment of the present application, it is possible to select confidence level most from each initial consulting result
High initial consulting result, the consulting result for the problem of being proposed as user shows user.Such one
Come, user just can obtain the problem of being provided by automatic customer service system and reply, and compared to prior art, face
The problem of above-mentioned consulting result is proposed with user in the problem of diversification that user is proposed, the application is more
Plus matching.
By above-mentioned steps, when the server that operation has automatic customer service system have received the problem of user inputs
Afterwards, text formatting processing will be carried out to the problem, the Sentence format of the problem is converted into server and determined
Sentence format, that is, generation typical problem text, and then, server will call it is a variety of consulting engines pair
The typical problem text is handled, and each consulting engine all has different analyses, query function, this
Sample one, after the processing of a variety of consulting engines, will obtain a variety of initial consulting results, at the beginning of these
In the consulting result of beginning, some initial consulting results are suitable as the answer of the problem of user proposes, and certain
A little initial consulting results are not appropriate for, in this case, and server is it is determined that each initial consulting knot
The confidence level of fruit, and further determined according to the confidence level of each initial consulting result with above mentioned problem the most
The consulting result of matching, user is supplied to as the answer of problem.Unlike the prior art, exactly lead to
Spending the problem of modes of a variety of consulting engines, diversification that can be proposed for user is handled, and obtains many
The consulting result of memberization, and it is not existing single consultation, moreover, at a variety of consulting engines
Manage on the basis of obtained a variety of consulting results, can be selected in these consulting results and more conform to user's institute's phase
The answer of prestige, i.e. improve the accuracy of answer.
For the process of user's input problem in foregoing teachings, the above method of the application supports different
Access way, specifically, under a kind of scene, user can pass through the net when accessing certain website A
Stand A automatic customer service system consulting interface, carry out business consultation；Under another scene, user can be with
From other websites associated with website A, into consulting circle of website A automatic customer service system
Face, carries out business consultation.In addition, user can also use the related application of operation on mobile terminals
(Application, App), into consulting interface, carries out business consultation.
Certainly, in business consultation interface, user except can in addition to input problem by the way of text,
Problem can also be inputted by the way of voice.If user inputs problem, automatic customer service by the way of voice
The voice of user can be converted into text message by system using corresponding speech recognition technology, not constituted here
Restriction to the application.
It is visible in from the discussion above, in the embodiment of the present application, the problem of user inputs is received, is specifically included：
User is received in interface is seeked advice from voice mode or the problem of inputted with text mode.Wherein, it is described to consult
Asking interface includes at least one of webpage, application interface.
Server have received the problem of user inputs, and will carry out text formatting processing, generate typical problem
Text, afterwards, server will call all kinds of consulting engines in comprehensive sonsultancy model, to typical problem text
This progress is handled.
Explanation is needed exist for, in the embodiment of the present application, described consulting engine includes but is not limited to：
Base search engine, question and answer search engine, chat engine, interactive engine.Specifically：
Base search engine
The engine is used to extract the keyword in described problem text, retrieval and the keyword in knowledge base
Corresponding existing business information, according to the existing initial consulting result of business information generation.
Wherein, knowledge base can be that the detailed descriptions of all kinds of business, setting procedure are stored in on-line system, is obtained
Take the database of the information such as flow, points for attention, FAQs.
For example：Assuming that it is " what is monthly payment plan " to handle obtained typical problem text by text formatting,
So, after server calls Base search engine, the Base search engine will be directed to the typical problem text,
Retrieved in knowledge base, and it is initial as one kind to retrieve relevant serial service description information
Seek advice from result.
Question and answer search engine
The engine is used for the history Question Log according to the user, determines that described problem text is asked with the history
The incidence relation of record is answered, according to the history Question Log with the question text with incidence relation, generation is just
Begin consulting result.
During practical application, user can input under problem, some scenes at any time in consulting interface, Yong Husuo
Have between the problem of the problem of input before user with inputting and necessarily associate, for example：User is at consulting interface
In have input problem " today, how is weather ", and obtained corresponding answer, now, it is assumed that user continues
Input " tomorrow ".Obviously, if the Second Problem proposed just for user is inquired about, it is impossible to
To effective answer.It was found from from the example, there is relevance between two problems that user is proposed：The
Two problems on the basis of first problem based on proposing.Therefore in the embodiment of the present application, question and answer search
Engine will determine question text and the incidence relation of history Question Log, that is, question and answer search engine will be analyzed
Context, so that according to this progress problem retrieval.
Chat engine
The engine is used for according to described problem text, searches for related to the question text to language in dictionary
Sentence, according to the conversation sentence, the initial consulting result of generation.
Wherein, the dictionary in the application, can be one or more sentence databases, for storing exchange pair
Talk about various sentences under scene.
During practical application, during user is seeked advice from consulting interface, user may seek advice from this
Process is considered a kind of communication process, then, the situation that user is seeked advice from the way of chatting just occurs,
Such as：User's input greeting, every-day language sentence etc., now, in order to what is matched to user feedback
Reply, the sentence that chat engine will be inputted according to user is inquired about in corresponding dictionary, to search
To the answer matched with the sentence that user inputs.It is believed that being chatted when being included in the sentence that user is inputted
During its conversation sentence, the chat engine in the application carries out the mode of " simulation " artificial customer service with user
Chat conversations.
Interactive engine
The engine is used to recognize the typical problem text, lacks industry when identifying in the typical problem text
During business conditional information, according to the interaction models of training in advance, generation professional qualification confirms sentence, and according to institute
State professional qualification and confirm the initial consulting result of sentence generation；And, when identifying the typical problem text institute
During corresponding business, the application programming interface API related to the business, the initial consulting knot of generation are called
Really.
For example：Tentative standard question text is " I wants to inquire about bill ", more it is apparent that the typical problem
Having lacked the bill time to be inquired about in text, (in this example, the bill time is exactly a kind of professional qualification letter
Breath), such as：The bill in January, 2016, or annual bill in 2015 etc..So, interactive mode is drawn
The typical problem text will be directed to by holding up, according to the interaction models of training in advance, question closely the user, be generated all
Such as " may I ask will specifically inquire about bill what time period " questions closely sentence, specific business bar for confirmation
Part.Certainly, the interaction models of described training in advance, can be by server previously according in artificial customer service system
The alternate statement related to business and scene training form, the restriction to the application is not constituted here.
In addition, when the business corresponding to interactive engine have identified typical problem text, it will call this
The API of business, to access the business, obtains corresponding business information.
For example：Tentative standard question text is " I will inquire about the bill in January, 2016 ", then, should
After the typical problem text is identified interactive engine, the API of bill inquiry business will be called, to visit
Bill inquiry business is asked, the bill information in 2016 that user to be inquired about year January is used as initial consulting
As a result.
It is visible with reference to the above, in the presence of above-mentioned a variety of consulting engines, it can be carried for user
The problem of diversification gone out, is handled, and returns to the answer of user's diversification.
Certainly, the consulting engine mentioned in the above, is the conventional engine in automatic customer service system,
During practical application, it can also not constituted here according to different consulting engines are added the need for practical application
Restriction to the application.
In the embodiment of the present application, each problem proposed for user, server can all be called and had been turned on
All kinds of consulting engines handled, each initial consulting result is generated, in order to from these initial consulting results
The consulting result matched with problem is determined, therefore in the embodiment of the present application, it is each initial according to what is determined
The confidence level of result is seeked advice from, it is determined that the initial consulting result matched with the typical problem text, specific bag
Include：In each initial consulting result, selection confidence level highest initially seeks advice from result, is defined as and the mark
The initial consulting result that quasi- question text matches.
And as a kind of mode in the embodiment of the present application, each initial consulting result can also be directed to, according to each
From confidence level carry out answer integration processing, that is, in this mode, not only picking out confidence level highest
An initial consulting result, but can be carried out for the less multiple initial consulting results of confidence level gap
Integrate, so as to regard the result after integration as the consulting result matched with problem.Here do not constitute to this
The restriction of application.
In addition, except foregoing teachings, following additional ways are also included in the present processes：
First way：
In view of certain user commonly using some of on-line system business, then, when these users use
Automatic customer service system, it is likely that want to be seeked advice from for its business being commonly used, therefore under scene, can
The problem of to recommend related to user.Specifically, it is above-mentioned as schemed before the problem of user inputs is received
Method shown in 1 also includes：The accounts information of user is determined, according to the accounts information, the account is inquired about
The type of service of the corresponding historical operational information of information, according to the type of service, selection belongs to the service class
The problem of type, frequency of occurrences highest, is recommended.
For example：For a certain user, after the accounts information of the user is obtained, it may be determined that the user institute
The type of service of the history service used is：Transferred account service.So, also it can just inquire about in transferred account service,
The one or more problems of frequency of occurrences highest, and the problem is recommended.
It should be noted that the accounts information to determine user, generally requires User logs in on-line system,
So as to be obtained with the historical operational information of user.And user for new registration or the use that is not logged in
For family, the historical operational information of these users can not be obtained, now, if these users have used automatically
Customer service system, then, can recommending hot issue to these users, (hot issue refers to entirely in linear system
In system, the most one or more problems of the frequency of occurrences).Certainly, the limit to the application is not constituted here
It is fixed.
The second way：
In view of in practical application, for on-line system, in fact it could happen that extraordinary maintenance, extensive communication
Interruption etc. emergency case, the business that these emergency cases may result in on-line system is run currently
Failure, now, automatic customer service system can typically each be seeked advice from by accessing the user of the on-line system, with consultation service
Failure or the disabled reason of business, in the case, one are also provided in the above method of the embodiment of the present application
Informing mechanism is planted, specifically, before the problem of user inputs is received, methods described also includes：Monitoring
The fault notification message related to business, after the fault notification message is monitored, by the failure notification
Message is shown.
Exactly employ the mode of above-mentioned fault notification message, it is possible to when user opens consulting interface,
Above-mentioned fault notification message is showed into user, so that when there is emergency case, being easy to user to obtain
Know corresponding notification message.
The third mode：
In actual applications, foregoing part consulting engine may be dependent on the number such as knowledge base, dictionary
According to storehouse, in other words, the data included in these databases will produce certain to the answer of customer problem
Influence, so, in order to ensure the accuracy and matching degree of the answer to customer problem, also it is accomplished by
Data in these databases are updated, i.e. methods described also includes：According to the setting time cycle pair
The knowledge base and dictionary are updated.
Certainly, for above-mentioned additional ways, in some embodiments in this application, server can be with
The accuracy for specifying the consulting result of automatic customer service system in the period is counted (such as：Server is directed to
The accuracy of the consulting result of intraday automatic customer service system is counted), to reflect different business
Under accuracy, or the accuracy under different dialogue scene, so as to help to improve each consulting engine.
In order to obtain the statistical result of the accuracy to seeking advice from result, one kind side in the embodiment of the present application is used as
Formula, can provide option in consulting interface, choose whether to solve relevant issues for user.As shown in Fig. 2
It is visible in fig. 2 for the consulting interface in practical application scene, when automatic customer service system asking for user
After topic is replied, above-mentioned option will be generated in consulting interface, if the answer of automatic customer service system is solved
The problem of user proposes, then, user just can click on the option with " solution " printed words；If with
Think the answer of automatic system and unsolved problem in family, then, user, which can click on, " not to be solved, and goes to
The option of artificial customer service " printed words, now, server will access artificial customer service for user.
By way of user clicks on above-mentioned option, server can be just counted for different problems, difference
The accuracy of consulting result under business scenario.Certainly, disclosure does not constitute the restriction to the application.
With reference to above content, in the embodiment of the present application, based on the automatic customer service system of the application above method,
Various modes in above content can be realized using different functional units (or, different engines).
Moreover, in actual applications, different business can enable different functional units and realize different modes,
Here the restriction to the application is not constituted.
Based on same thinking, the embodiment of the present application also provides a kind of information processor based on consultation service,
As shown in Figure 3.
In figure 3, the information processor based on consultation service includes：
Receiving module 301, for receiving the problem of user inputs.
Text processing module 302, for carrying out text formatting processing, generation typical problem text to described problem
This.
Processing module 303 is called, all kinds of consulting engines being had been turned on for calling are to the typical problem text
Handled, generate each initial consulting result.
Confidence level module 304, for according to default confidence level rule, determining each initial consulting result
Confidence level.
Object module 305 is seeked advice from, for the confidence level according to each initial consulting result determined, it is determined that with
The initial consulting result that the typical problem text matches, and carry out exhibition as the consulting result of described problem
Show.
In the embodiment of the present application, receiving module 301, specifically for receiving user in consulting interface with language
Sound mode or the problem of inputted with text mode.Wherein, the consulting interface includes webpage, application interface
At least one of.
In the embodiment of the present application, text processing module 302, specifically for described problem carry out participle,
Form error correction and/or word meaning conversion process.
It should be noted that for calling the consulting engine that processing module 303 is called, at least including：
Base search engine, question and answer search engine, chat engine, interactive engine.
Wherein, Base search engine, for extracting the keyword in the typical problem text, in knowledge base
The middle retrieval existing business information corresponding with the keyword, according to the existing initial official communication of business information generation
Ask result.
Question and answer search engine, for the history Question Log according to the user, determines described problem text and institute
The incidence relation of history Question Log is stated, according to the history Question Log with the question text with incidence relation,
The initial consulting result of generation.
Chat engine, for according to the typical problem text, searching for related to the question text in dictionary
Conversation sentence, according to the conversation sentence, the initial consulting result of generation.
Interactive engine, for recognizing the typical problem text, when identifying in the typical problem text
When lacking professional qualification information, according to the interaction models of training in advance, generation professional qualification confirms sentence, and
The initial consulting result of sentence generation is confirmed according to the professional qualification；And, when identifying the typical problem
During business corresponding to text, the application programming interface API related to the business is called, generation is initial
Seek advice from result.
Confidence level module 304, specifically in each initial consulting result, selection confidence level highest is initial
Result is seeked advice from, is defined as the initial consulting result matched with the typical problem text.
As a kind of mode in the embodiment of the present application, described device also includes：Recommending module 306, is used for
Before the problem of user inputs is received, the accounts information of user is determined, according to the accounts information, inquiry
The type of service of the corresponding historical operational information of account information, according to the type of service, selection belongs to this
The problem of type of service, frequency of occurrences highest, is recommended.
As a kind of mode in the embodiment of the present application, described device also includes：Notification module 307, is used for
Before the problem of user inputs is received, the fault notification message related to business is monitored, it is described when monitoring
After fault notification message, the fault notification message is shown.
As a kind of mode in the embodiment of the present application, described device also includes：Maintenance management module 308,
For being updated according to the setting time cycle to the knowledge base and dictionary.
In a typical configuration, computing device includes one or more processors (CPU), input/defeated
Outgoing interface, network interface and internal memory.
Internal memory potentially includes the volatile memory in computer-readable medium, random access memory
And/or the form, such as read-only storage (ROM) or flash memory (flash RAM) such as Nonvolatile memory (RAM).
Internal memory is the example of computer-readable medium.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by appointing
What method or technique realizes that information is stored.Information can be computer-readable instruction, data structure, program
Module or other data.The example of the storage medium of computer includes, but are not limited to phase transition internal memory
(PRAM), static RAM (SRAM), dynamic random access memory (DRAM), its
Random access memory (RAM), read-only storage (ROM), the electrically erasable of his type are read-only
Memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage
(CD-ROM), digital versatile disc (DVD) or other optical storages, magnetic cassette tape, tape magnetic
Disk storage or other magnetic storage apparatus or any other non-transmission medium, can be calculated available for storage
The information that equipment is accessed.Defined according to herein, computer-readable medium does not include temporary computer-readable matchmaker
The data-signal and carrier wave of body (transitory media), such as modulation.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to non-row
His property is included, so that process, method, commodity or equipment including a series of key elements not only include
Those key elements, but also other key elements including being not expressly set out, or also include for this process,
Method, commodity or the intrinsic key element of equipment.In the absence of more restrictions, by sentence " including
One ... " key element that limits, it is not excluded that in the process including the key element, method, commodity or set
Also there is other identical element in standby.
It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer journey
Sequence product.Therefore, the application can using complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the application can be used wherein includes calculating one or more
Machine usable program code computer-usable storage medium (include but is not limited to magnetic disk storage, CD-ROM,
Optical memory etc.) on the form of computer program product implemented.
Embodiments herein is the foregoing is only, the application is not limited to.For this area skill
For art personnel, the application can have various modifications and variations.All institutes within spirit herein and principle
Any modification, equivalent substitution and improvements of work etc., should be included within the scope of claims hereof.
Claims (16)
1. a kind of information processing method based on consultation service, it is characterised in that methods described includes：
Receive the problem of user inputs；
Text formatting processing is carried out to described problem, typical problem text is generated；
Call all kinds of consulting engines having been turned on to handle the typical problem text, generate each initial official communication
Ask result；
According to default confidence level rule, the confidence level of each initial consulting result is determined；
According to the confidence level for each initial consulting result determined, it is determined that matching with the typical problem text
Initial consulting result, and be shown as the consulting result of described problem.
2. the method as described in claim 1, it is characterised in that receive the problem of user inputs, specifically
Including：
User is received in interface is seeked advice from voice mode or the problem of inputted with text mode；
Wherein, the consulting interface includes at least one of webpage, application interface.
3. the method as described in claim 1, it is characterised in that carried out to described problem at text formatting
Reason, is specifically included：
Participle, form error correction and/or word meaning conversion process are carried out to described problem.
4. the method as described in claim 1, it is characterised in that the consulting engine includes Base search
At least one of engine, question and answer search engine, chat engine, interactive engine；
Wherein, the Base search engine, for extracting the keyword in the typical problem text, is knowing
Know and the existing business information corresponding with the keyword is retrieved in storehouse, according to the existing business information generation just
Begin consulting result；
The question and answer search engine, for the history Question Log according to the user, determines described problem text
With the incidence relation of the history Question Log, according to the history question and answer with the question text with incidence relation
Record, the initial consulting result of generation；
The chat engine, for according to the typical problem text, being searched for and the question text in dictionary
Related conversation sentence, according to the conversation sentence, the initial consulting result of generation；
The interactive engine, for recognizing the typical problem text, when identifying typical problem text
When lacking professional qualification information in this, according to the interaction models of training in advance, generation professional qualification confirms sentence,
And the initial consulting result of sentence generation is confirmed according to the professional qualification；And, when identifying that the standard asks
When inscribing the business corresponding to text, the application programming interface API related to the business is called, generation is just
Begin consulting result.
5. the method as described in claim 1, it is characterised in that each initial consulting according to determining is tied
The confidence level of fruit, it is determined that the initial consulting result matched with the typical problem text, is specifically included：
In each initial consulting result, selection confidence level highest initially seeks advice from result, is defined as and the mark
The initial consulting result that quasi- question text matches.
6. the method as described in claim 1, it is characterised in that before the problem of user inputs is received,
Methods described also includes：Determine the accounts information of user；
According to the accounts information, the type of service of the corresponding historical operational information of inquiry account information；
According to the type of service, the problem of selection belongs to the type of service, frequency of occurrences highest is pushed away
Recommend.
7. the method as described in claim 1, it is characterised in that before the problem of user inputs is received,
Methods described also includes：The monitoring fault notification message related to business；
After the fault notification message is monitored, the fault notification message is shown.
8. method as claimed in claim 4, it is characterised in that methods described also includes：
The knowledge base and dictionary are updated according to the setting time cycle.
9. a kind of information processor based on consultation service, it is characterised in that described device includes：
Receiving module, for receiving the problem of user inputs；
Text processing module, for carrying out text formatting processing to described problem, generates typical problem text；
Processing module is called, all kinds of consulting engines being had been turned on for calling are carried out to the typical problem text
Processing, generates each initial consulting result；
Confidence level module, for according to default confidence level rule, determining putting for each initial consulting result
Reliability；
Seek advice from object module, for according to determine it is each it is initial consulting result confidence level, it is determined that with it is described
The initial consulting result that typical problem text matches, and be shown as the consulting result of described problem.
10. device as claimed in claim 9, it is characterised in that the receiving module, specifically for connecing
User is received in interface is seeked advice from voice mode or the problem of inputted with text mode；
Wherein, the consulting interface includes at least one of webpage, application interface.
11. device as claimed in claim 9, it is characterised in that the text processing module, specific to use
In conversion process of being anticipated to described problem progress participle, form error correction and/or word.
12. device as claimed in claim 9, it is characterised in that the consulting engine includes Base search
At least one of engine, question and answer search engine, chat engine, interactive engine；
Wherein, the Base search engine, for extracting the keyword in the typical problem text, is knowing
Know and the existing business information corresponding with the keyword is retrieved in storehouse, according to the existing business information generation just
Begin consulting result；
The question and answer search engine, for the history Question Log according to the user, determines described problem text
With the incidence relation of the history Question Log, according to the history question and answer with the question text with incidence relation
Record, the initial consulting result of generation；
The chat engine, for according to the typical problem text, being searched for and the question text in dictionary
Related conversation sentence, according to the conversation sentence, the initial consulting result of generation；
The interactive engine, for recognizing the typical problem text, when identifying typical problem text
When lacking professional qualification information in this, according to the interaction models of training in advance, generation professional qualification confirms sentence,
And the initial consulting result of sentence generation is confirmed according to the professional qualification；And, when identifying that the standard asks
When inscribing the business corresponding to text, the application programming interface API related to the business is called, generation is just
Begin consulting result.
13. device as claimed in claim 9, it is characterised in that the confidence level module, specifically for
In each initial consulting result, selection confidence level highest initially seeks advice from result, is defined as asking with the standard
The initial consulting result that topic text matches.
14. device as claimed in claim 9, it is characterised in that described device also includes：Recommending module,
For before the problem of user inputs is received, determining the accounts information of user, according to the accounts information,
The type of service of the corresponding historical operational information of account information is inquired about, according to the type of service, selection category
Recommended the problem of the type of service, frequency of occurrences highest.
15. device as claimed in claim 9, it is characterised in that described device also includes：Notification module,
For before the problem of user inputs is received, monitoring the fault notification message related to business, when monitoring
After the fault notification message, the fault notification message is shown.
16. device as claimed in claim 12, it is characterised in that described device also includes：Safeguard pipe
Module is managed, for being updated according to the setting time cycle to the knowledge base and dictionary.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610131535.1A CN107180029A (en) | 2016-03-09 | 2016-03-09 | A kind of information processing method and device based on consultation service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610131535.1A CN107180029A (en) | 2016-03-09 | 2016-03-09 | A kind of information processing method and device based on consultation service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107180029A true CN107180029A (en) | 2017-09-19 |
Family
ID=59829510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610131535.1A Pending CN107180029A (en) | 2016-03-09 | 2016-03-09 | A kind of information processing method and device based on consultation service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107180029A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107479726A (en) * | 2017-09-27 | 2017-12-15 | 联想(北京)有限公司 | A kind of data inputting method and electronic equipment |
| CN107798116A (en) * | 2017-11-07 | 2018-03-13 | 盐城工学院 | Traffic rules answering method and device |
| CN109241252A (en) * | 2018-07-27 | 2019-01-18 | 北京小米移动软件有限公司 | Consulting replies method, apparatus, electronic equipment and storage medium |
| CN109241249A (en) * | 2018-07-16 | 2019-01-18 | 阿里巴巴集团控股有限公司 | A kind of method and device of determining bursting problem |
| CN109344392A (en) * | 2018-08-23 | 2019-02-15 | 广州市万隆证券咨询顾问有限公司 | A kind of smart message method for pushing, system and the device of security customer service consulting |
| CN109345282A (en) * | 2018-08-22 | 2019-02-15 | 中国平安人寿保险股份有限公司 | A kind of response method and equipment of business consultation |
| CN109460448A (en) * | 2018-08-31 | 2019-03-12 | 厦门快商通信息技术有限公司 | It is a kind of can autonomous configuration FAQ service framework |
| CN109614464A (en) * | 2018-10-31 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Method and device for traffic issues identification |
| CN109684364A (en) * | 2018-08-21 | 2019-04-26 | 平安普惠企业管理有限公司 | The problem of being drawn a portrait based on user processing method, device, equipment and storage medium |
| CN109739845A (en) * | 2018-12-26 | 2019-05-10 | 贵州商学院 | A kind of big data service system based on intensified learning |
| CN109840802A (en) * | 2018-12-29 | 2019-06-04 | 深圳道合信息科技有限公司 | Communication means and device, real estate system, computer and readable storage medium storing program for executing |
| CN110032628A (en) * | 2019-02-21 | 2019-07-19 | 北京奥鹏远程教育中心有限公司 | A kind of user's on-line consulting system and method |
| CN110309293A (en) * | 2018-02-13 | 2019-10-08 | 北京京东尚科信息技术有限公司 | Text recommended method and device |
| 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 |
| CN111782792A (en) * | 2020-08-05 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for information processing |
| CN111951020A (en) * | 2019-05-14 | 2020-11-17 | 阿里巴巴集团控股有限公司 | Method and device for providing service information |
| WO2020258654A1 (en) * | 2019-06-27 | 2020-12-30 | 深圳前海微众银行股份有限公司 | Answer acquisition method and device |
| CN112364149A (en) * | 2021-01-12 | 2021-02-12 | 广州云趣信息科技有限公司 | User question obtaining method and device and electronic equipment |
| CN112396444A (en) * | 2019-08-15 | 2021-02-23 | 阿里巴巴集团控股有限公司 | Intelligent robot response method and device |
| CN112633949A (en) * | 2021-01-06 | 2021-04-09 | 上海归程网络科技有限公司 | Strategy consultation system applied to financial economic activities |
| CN111507366B (en) * | 2019-11-07 | 2021-06-08 | 马上消费金融股份有限公司 | Training method of recommendation probability model, intelligent completion method and related device |
| CN113051389A (en) * | 2021-04-30 | 2021-06-29 | 中国银行股份有限公司 | Knowledge pushing method and device |
| CN113204635A (en) * | 2021-06-08 | 2021-08-03 | 重庆电子工程职业学院 | Intelligent consultation system for modern agricultural planting |
| CN114840653A (en) * | 2022-04-26 | 2022-08-02 | 北京百度网讯科技有限公司 | Dialogue processing method, device, equipment and storage medium |
| CN117349408A (en) * | 2023-12-04 | 2024-01-05 | 天津市品茗科技有限公司 | Man-machine interaction result generation method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198155A (en) * | 2013-04-27 | 2013-07-10 | 俞志晨 | Mobile terminal based smart question answering interaction system and method |
| CN104050256A (en) * | 2014-06-13 | 2014-09-17 | 西安蒜泥电子科技有限责任公司 | Initiative study-based questioning and answering method and questioning and answering system adopting initiative study-based questioning and answering method |
| CN104050224A (en) * | 2013-03-15 | 2014-09-17 | 国际商业机器公司 | Combining different type coercion components for deferred type evaluation |
| CN104424290A (en) * | 2013-09-02 | 2015-03-18 | 佳能株式会社 | Voice based question-answering system and method for interactive voice system |
| CN105159996A (en) * | 2015-09-07 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Deep question-and-answer service providing method and device based on artificial intelligence |
-
2016
- 2016-03-09 CN CN201610131535.1A patent/CN107180029A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050224A (en) * | 2013-03-15 | 2014-09-17 | 国际商业机器公司 | Combining different type coercion components for deferred type evaluation |
| CN103198155A (en) * | 2013-04-27 | 2013-07-10 | 俞志晨 | Mobile terminal based smart question answering interaction system and method |
| CN104424290A (en) * | 2013-09-02 | 2015-03-18 | 佳能株式会社 | Voice based question-answering system and method for interactive voice system |
| CN104050256A (en) * | 2014-06-13 | 2014-09-17 | 西安蒜泥电子科技有限责任公司 | Initiative study-based questioning and answering method and questioning and answering system adopting initiative study-based questioning and answering method |
| CN105159996A (en) * | 2015-09-07 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Deep question-and-answer service providing method and device based on artificial intelligence |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107479726A (en) * | 2017-09-27 | 2017-12-15 | 联想(北京)有限公司 | A kind of data inputting method and electronic equipment |
| CN107479726B (en) * | 2017-09-27 | 2021-08-17 | 联想(北京)有限公司 | Information input method and electronic equipment |
| CN107798116A (en) * | 2017-11-07 | 2018-03-13 | 盐城工学院 | Traffic rules answering method and device |
| CN110309293A (en) * | 2018-02-13 | 2019-10-08 | 北京京东尚科信息技术有限公司 | Text recommended method and device |
| CN109241249A (en) * | 2018-07-16 | 2019-01-18 | 阿里巴巴集团控股有限公司 | A kind of method and device of determining bursting problem |
| CN109241249B (en) * | 2018-07-16 | 2021-09-14 | 创新先进技术有限公司 | Method and device for determining burst problem |
| CN109241252A (en) * | 2018-07-27 | 2019-01-18 | 北京小米移动软件有限公司 | Consulting replies method, apparatus, electronic equipment and storage medium |
| CN109684364A (en) * | 2018-08-21 | 2019-04-26 | 平安普惠企业管理有限公司 | The problem of being drawn a portrait based on user processing method, device, equipment and storage medium |
| CN109684364B (en) * | 2018-08-21 | 2024-04-19 | 深圳市与米数字科技有限公司 | User portrait-based problem processing method, device, equipment and storage medium |
| CN109345282A (en) * | 2018-08-22 | 2019-02-15 | 中国平安人寿保险股份有限公司 | A kind of response method and equipment of business consultation |
| CN109344392A (en) * | 2018-08-23 | 2019-02-15 | 广州市万隆证券咨询顾问有限公司 | A kind of smart message method for pushing, system and the device of security customer service consulting |
| CN109460448A (en) * | 2018-08-31 | 2019-03-12 | 厦门快商通信息技术有限公司 | It is a kind of can autonomous configuration FAQ service framework |
| CN109614464A (en) * | 2018-10-31 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Method and device for traffic issues identification |
| CN109614464B (en) * | 2018-10-31 | 2023-10-27 | 创新先进技术有限公司 | Method and device for identifying business problems |
| CN109739845A (en) * | 2018-12-26 | 2019-05-10 | 贵州商学院 | A kind of big data service system based on intensified learning |
| CN109840802A (en) * | 2018-12-29 | 2019-06-04 | 深圳道合信息科技有限公司 | Communication means and device, real estate system, computer and readable storage medium storing program for executing |
| CN110032628A (en) * | 2019-02-21 | 2019-07-19 | 北京奥鹏远程教育中心有限公司 | A kind of user's on-line consulting system and method |
| CN111951020A (en) * | 2019-05-14 | 2020-11-17 | 阿里巴巴集团控股有限公司 | Method and device for providing service information |
| WO2020258654A1 (en) * | 2019-06-27 | 2020-12-30 | 深圳前海微众银行股份有限公司 | Answer acquisition method and device |
| 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 |
| CN112396444A (en) * | 2019-08-15 | 2021-02-23 | 阿里巴巴集团控股有限公司 | Intelligent robot response method and device |
| CN111507366B (en) * | 2019-11-07 | 2021-06-08 | 马上消费金融股份有限公司 | Training method of recommendation probability model, intelligent completion method and related device |
| CN111782792A (en) * | 2020-08-05 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for information processing |
| CN112633949A (en) * | 2021-01-06 | 2021-04-09 | 上海归程网络科技有限公司 | Strategy consultation system applied to financial economic activities |
| CN112364149B (en) * | 2021-01-12 | 2021-04-23 | 广州云趣信息科技有限公司 | User question obtaining method and device and electronic equipment |
| CN112364149A (en) * | 2021-01-12 | 2021-02-12 | 广州云趣信息科技有限公司 | User question obtaining method and device and electronic equipment |
| CN113051389A (en) * | 2021-04-30 | 2021-06-29 | 中国银行股份有限公司 | Knowledge pushing method and device |
| CN113051389B (en) * | 2021-04-30 | 2024-02-02 | 中国银行股份有限公司 | Knowledge pushing method and device |
| CN113204635A (en) * | 2021-06-08 | 2021-08-03 | 重庆电子工程职业学院 | Intelligent consultation system for modern agricultural planting |
| CN114840653A (en) * | 2022-04-26 | 2022-08-02 | 北京百度网讯科技有限公司 | Dialogue processing method, device, equipment and storage medium |
| CN114840653B (en) * | 2022-04-26 | 2023-08-01 | 北京百度网讯科技有限公司 | Dialogue processing method, device, equipment and storage medium |
| CN117349408A (en) * | 2023-12-04 | 2024-01-05 | 天津市品茗科技有限公司 | Man-machine interaction result generation method and system |
| CN117349408B (en) * | 2023-12-04 | 2024-02-13 | 天津市品茗科技有限公司 | Man-machine interaction result generation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107180029A (en) | A kind of information processing method and device based on consultation service | |
| US10891438B2 (en) | Deep learning techniques based multi-purpose conversational agents for processing natural language queries | |
| US10824814B2 (en) | Generalized phrases in automatic speech recognition systems | |
| US11238226B2 (en) | System and method for accelerating user agent chats | |
| US11645660B2 (en) | Computer systems and methods for efficient query resolution by customer representatives | |
| US20180316636A1 (en) | Context-aware conversational assistant | |
| US9621725B2 (en) | Method and apparatus for analyzing leakage from chat to voice | |
| US12010268B2 (en) | Partial automation of text chat conversations | |
| EP4187463A1 (en) | An artificial intelligence powered digital meeting assistant | |
| CN112925888A (en) | Method and device for training question-answer response and small sample text matching model | |
| CN113112282A (en) | Method, device, equipment and medium for processing consult problem based on client portrait | |
| US20230063713A1 (en) | Sentence level dialogue summaries using unsupervised machine learning for keyword selection and scoring | |
| CN113051389B (en) | Knowledge pushing method and device | |
| US11178284B2 (en) | Electronic communication system for providing expert information and method of using same | |
| US10972608B2 (en) | Asynchronous multi-dimensional platform for customer and tele-agent communications | |
| US20220101052A1 (en) | Answering questions with artificial intelligence using tabular data | |
| CN114239604A (en) | Online consultation processing method and device and computer equipment | |
| WO2021035245A1 (en) | Systems and methods for real-time processing of audio feedback | |
| US20240193190A1 (en) | Automated key-value extraction using natural language intents | |
| US20230259541A1 (en) | Intelligent Assistant System for Conversational Job Search | |
| US20230138741A1 (en) | Social network adapted response | |
| CN116320164A (en) | Call center service receipt creation method, device, equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201013 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: 20201013 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. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170919 |