CN109344237A - A kind of method and device of the information processing for human-computer interaction - Google Patents
A kind of method and device of the information processing for human-computer interaction Download PDFInfo
- Publication number
- CN109344237A CN109344237A CN201811074893.9A CN201811074893A CN109344237A CN 109344237 A CN109344237 A CN 109344237A CN 201811074893 A CN201811074893 A CN 201811074893A CN 109344237 A CN109344237 A CN 109344237A
- Authority
- CN
- China
- Prior art keywords
- sample
- asked
- standard
- user
- question sentence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000010365 information processing Effects 0.000 title claims abstract description 32
- 230000002452 interceptive effect Effects 0.000 claims description 32
- 238000005457 optimization Methods 0.000 claims description 21
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000005259 measurement Methods 0.000 claims description 7
- 238000009394 selective breeding Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 4
- 238000003672 processing method Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 description 9
- 208000037805 labour Diseases 0.000 description 7
- 238000013473 artificial intelligence Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The present invention relates to human-computer interaction technique field more particularly to a kind of method and devices for the information processing in human-computer interaction.The described method includes: providing model sample library, model sample library includes that sample standard asks and asks that corresponding sample extension is asked with each sample standard；Knowledge base is provided, the knowledge base includes that knowledge library standard asks and asks that corresponding knowledge base extension is asked and answer, the knowledge base are used to furnish an answer for user's question sentence with each knowledge library standard；It determines in model sample library and is asked with the presence or absence of the sample extension to match with user's question sentence in human-computer interaction log；If it exists, it is determined that the corresponding standard of user's question sentence described in the human-computer interaction log asks whether the corresponding sample standard asked with the extension of matched sample is asked identical；If not identical, optimize the knowledge base.The present invention also provides a kind of device and system of information processing corresponding with the method for above- mentioned information processing.
Description
The application be on August 23rd, 2016 the applying date, application No. is 201610710565.8, invention and created name is
The divisional application of " a kind of method and device of information processing ".
Technical field
The present invention relates to a kind of method of human-computer interaction technique field more particularly to information processing for human-computer interaction and
Device.
Background technique
Human-computer interaction is the science of the interactive relation between research system and user.System can be various machines
Device is also possible to the system and software of computerization.For example, various artificial intelligence systems, example may be implemented by human-computer interaction
Such as, intelligent customer service system, speech control system etc..
Artificial intelligence semantics recognition is the basis of human-computer interaction, can be identified to human language, to be converted into machine
Device it will be appreciated that language.In order to understand human language, artificial intelligence semantics recognition system needs a set of knowledge base.Magnanimity
Isomeric data is organized into knowledge by knowledge learning system, and is dissolved into existing knowledge hierarchy.
Various artificial intelligence systems are handled the original question sentence that user proposes using artificial intelligence semantics recognition technology,
Determine the corresponding standard question sentence of the original question sentence, then based on incidental some limited in the standard question sentence and original question sentence
Information provide corresponding answer, the place for each original question sentence is recorded in the form of log in artificial intelligence system
Manage situation, the information of each log includes: original question sentence (user's question sentence) that user proposes and is answered standard question sentence (standard is asked)
Case.
Knowledge base optimized, include two important steps: the interactive log optimized will be needed to pick out；For
Select log optimizes knowledge base.
In the prior art, when selecting interactive log, mainly by manually collect and sort out correct log library and
Meaningless log library, is then compared with daily interactive log, is filtered to the log content of exact matching.Each log
Artificial contrast is all needed, needs to put into a large amount of hand labors.Meanwhile when needing to optimize knowledge base, it is also desirable to professional
Knowledge operation maintenance personnel, which for every need to optimize log and carry out standard, asks and writes, and is costly and inefficient down.
Summary of the invention
The purpose of the present invention is to provide a kind of method and device of information processing, overcome present in traditional technology with
Lower problem: it needs to put into a large amount of hand labors and selects the interactive log that need to optimize.Meanwhile in information processing, system can be automatic
Proposed standard is asked, the investment of hand labor is further reduced, and improves the optimization efficiency of knowledge base.
According to above-mentioned purpose, the present invention provides a kind of method of information processing for human-computer interaction, comprising:
Model sample library is provided, model sample library includes that sample standard is asked and asked with each sample standard corresponding
Sample extension ask；
There is provided knowledge base, the knowledge base includes that knowledge library standard is asked and asked with each knowledge library standard and corresponding knows
The extension of knowledge library is asked and answer, and the knowledge base is used to furnish an answer for user's question sentence；
It determines in model sample library and expands with the presence or absence of the sample to match with user's question sentence in human-computer interaction log
Zhan Wen；
If it exists, it is determined that the corresponding standard of user's question sentence described in the human-computer interaction log is asked and matched sample
Whether the corresponding sample standard that extension is asked asks identical；
If not identical, optimize the knowledge base；
If there is no the sample to match with user's question sentence extensions to ask in model sample library, in knowledge base
Knowledge point corresponding with user's question sentence is created, the knowledge point includes: that knowledge library standard is asked, knowledge base extension is asked and answered
Case, and by the knowledge point created in knowledge base while being added to model sample library.
In one embodiment, the sample extension, which is asked, asks that the sample standard is asked including knowledge base including knowledge base extension
Standard is asked.
In one embodiment, it determines in model sample library and expands with the presence or absence of the sample to match with user's question sentence
Exhibition, which is asked, includes:
User's question sentence is asked with sample extension and executes Semantic Similarity Measurement to be in determination model sample library
The no sample extension for being greater than first threshold there are the semantic similarity of at least one and user's question sentence is asked.
In one embodiment, determine the corresponding standard of user's question sentence ask with matched sample extension ask corresponding to
Whether sample standard is asked identical includes:
The corresponding standard for comparing user's question sentence asks that the corresponding sample standard asked with the extension of matched sample asks text
Whether word is completely the same.
In one embodiment, it is greater than the first threshold with user's question semanteme similarity if it exists and is less than
100% sample extension asks, and the corresponding standard of user's question sentence ask with semantic similarity be greater than the first threshold and
It is identical less than the corresponding sample standard question sentence that the extension of 100% sample is asked, then by user's question sentence and user's question sentence
Corresponding standard ask and be added into model sample library in association.
In one embodiment, multiple matched sample extensions are asked if it exists, it is determined that the corresponding mark of user's question sentence
Whether standard is asked asks with the corresponding sample standard asked of matched sample extension and identical includes:
It is right with the institute of user's question sentence to determine whether that corresponding sample standard that a matched sample extension is asked is asked
Standard is answered to ask identical.
In one embodiment, include: to the optimization of the knowledge base
It is based on the Semantic Similarity Measurement as a result, recommending to be greater than the second threshold with the semantic similarity of user's question sentence
The corresponding sample standard that the sample extension of value is asked is asked；
The sample standard for asking that middle artificial selection goes out from the sample standard recommended is asked with user's question sentence in association
It is added into the knowledge base.
In one embodiment, the method also includes:
By it is described from the sample standard recommended ask middle artificial selection go out sample standard ask it is related to user's question sentence
It is added into model sample library to connection.
According to above-mentioned purpose, the present invention also provides a kind of devices of information processing for human-computer interaction, comprising:
First analysis module whether there is and user's question sentence phase in human-computer interaction log for determining in model sample library
Matched sample extension is asked；
Second analysis module, for being asked in response to there is the sample to match with user's question sentence extension, it is determined that institute
The corresponding standard for stating user's question sentence described in human-computer interaction log, which is asked, extends the corresponding sample standard asked with matched sample
It whether identical asks；And
Optimization module, for asking that the institute asked with the extension of matched sample is right in response to the corresponding standard of user's question sentence
It answers sample standard to ask not identical, then optimizes knowledge base；
If there is no the sample to match with user's question sentence extensions to ask in model sample library, the addition mould
Block creates knowledge point corresponding with user's question sentence in knowledge base, the knowledge point include: knowledge library standard ask, knowledge base
Extension is asked and answer；
The adding module also by the knowledge point created in knowledge base while being added to model sample library.
According to above-mentioned purpose, the present invention also provides a kind of systems of information processing for human-computer interaction, comprising:
The device of above-mentioned information processing；
Model sample library, model sample library include that sample standard asks and asks corresponding sample with each sample standard
Example extension is asked；
Knowledge base, the knowledge base include that knowledge library standard asks and asks corresponding knowledge base with each knowledge library standard
Extension is asked and answer, and the knowledge base is used to furnish an answer for user's question sentence.
The present invention carries out Automatic sieve by the model sample library set up first when human-computer interaction log need to be optimized by choosing
Choosing has filtered out largely existing knowledge content, has reduced the input amount of hand labor.Simultaneity factor can need to optimize people from trend
Machine interactive log proposed standard is asked, artificial only to be selected, and is further reduced hand labor, is improved knowledge base
Optimization efficiency.
More preferably understand to have to above-mentioned and other aspect of the invention, preferred embodiment is cited below particularly, and cooperates attached
Figure, is described in detail below:
Detailed description of the invention
Fig. 1 is knowledge base schematic diagram of the present invention；
Fig. 2 is model sample of the present invention library schematic diagram；
Fig. 3 is the schematic diagram for optimizing knowledge base process in the method flow of the information processing of one embodiment of the invention；
Fig. 4 is the schematic diagram of the method flow of the information processing of one embodiment of the invention；
Fig. 5 is the schematic diagram of the device of the information processing of one embodiment of the invention.
Specific embodiment
User with can generate interactive log in intelligent robot interactive process, every interactive log is by user's question sentence, right
The knowledge library standard answered is asked and answer three parts composition.Wherein user's question sentence is that acquisition is directly inputted by user, passes through question and answer
After engine is to the parsing identification of user's question sentence, corresponding knowledge library standard is called to ask about corresponding answer.In these interactive logs
It is middle that accuracy differentiation is replied with the answer that corresponding knowledge point is given by robot according to user's question sentence, user's question sentence content machine can be divided into
Device people do not give reply, correct answer is given by user's question sentence content robot, wrong answer is given by user's question sentence content robot.
Robot is caused not reply or give the reason of mistake replies mainly due to having lacked corresponding knowledge in robot knowledge base
Point or the way to put questions of existing knowledge point are not abundant enough.Therefore it by the analysis of the interactive log generated daily, extracts because knowledge point lacks
The log of the incorrect answer of robot caused by mistake or way to put questions be not abundant is a main path to knowledge base Continuous optimization.This
The method and apparatus that invention provides can greatly reduce the artificial input amount when extracting the human-computer interaction log for needing to optimize.This
It invents the user's question sentence being primarily upon in interactive log and standard is asked.
Fig. 1 and Fig. 2 are please referred to, figures 1 and 2 show that the partial objects of information processing of the present invention, knowledge base and model sample
Example library.
As shown in Figure 1, knowledge base 10 includes that at least one knowledge library standard asks 101 and asks phase with each knowledge library standard
1011 and answer are asked in corresponding knowledge base extension, wherein each knowledge library standard asks a corresponding answer, can there is multiple knowledge
Library extension asks that the extension of 1011- knowledge base asks 101n that a corresponding knowledge library standard asks 101.Since knowledge library standard is asked 101 with answering
Case is asked present invention is primarily concerned with knowledge library standard and is asked with each knowledge library standard corresponding there are one-to-one relationship
Knowledge base extends the treatment process asked.In general, can all have multiple knowledge library standards in knowledge base asks that knowledge library standard is asked
101- knowledge library standard asks 10n.In knowledge base include multiple knowledge points, each knowledge point include: a knowledge library standard ask,
Multiple knowledge base extensions are asked with an answer, i.e., different knowledge base extensions ask it is all the corresponding same answer, a knowledge base
Standard, which is asked, also corresponds to this answer.Usually from each knowledge point, corresponding multiple knowledge base extensions ask middle selection one expression
Clear knowledge base extension easy to maintain asks that the knowledge library standard as the knowledge point is asked, therefore knowledge library standard is asked and known with one
The extension of knowledge library is asked identical.It should be noted that each knowledge library standard asks that corresponding knowledge base extension asks that number can be identical,
It can also be different.
In human-computer interaction process, after receiving user's question sentence, it can be obtained from knowledge base by Semantic Similarity Measurement
With the semantic similarity highest of user's question sentence and the knowledge base extension that is higher than threshold value is asked, and asks knowledge base extension to corresponding answer
Case is sent to user, while asking corresponding knowledge library standard with asking relevance conduct by user's question sentence and with knowledge base extension
One interactive log.
As shown in Fig. 2, model sample library 20 includes that at least one sample standard asks 201 and corresponding one or more
A sample extension asks 2011, similar with knowledge base data structure, and a sample standard, which asks to extend with multiple samples, asks correspondence.
Usually from the extension of multiple samples ask it is middle select one expression clearly extension easy to maintain ask as with the multiple sample pair
The sample standard answered asks, thus sample standard ask asked with the extension of one of sample it is identical.Each sample standard asks corresponding sample
Example extension asks that number may be the same or different.
Fig. 3 is please referred to, the knowledge base Optimizing Flow 30 of one embodiment of the invention is shown comprising the steps of:
Step 301: starting.
Step 302: determining in model sample library with the presence or absence of the sample to match with user's question sentence in human-computer interaction log
Example extension is asked.
Step 303: if it exists, it is determined that the corresponding standard of user's question sentence described in the human-computer interaction log ask with
Whether the corresponding sample standard that the sample extension matched is asked asks identical.
Step 304: if not identical, optimizing the knowledge base.
In step 302, it has been looked for whether in model sample library first close with human-computer interaction log user's question semanteme
As sample extension ask, if there is approximate, then be referred to as match.If having matched, think that this user question sentence can quilt at this time
Model sample library determines.Then in step 303, if can be determined, it is determined that the corresponding standard of user's question sentence is asked and the sample
Example extension asks that whether identical corresponding standard asks, herein identical refers to that text is completely the same, then shows in knowledge base if they are the same
Include knowledge point corresponding with user's question sentence, has optimized knowledge base without using this user journal.If not identical, show
Question sentence not corresponding with the interactive log content, shows that this interactive log is new at this time in model sample library and knowledge base
Content, need using this interactive log Advance data quality knowledge base, that is, enter in step 304.At this point, due to handing over
User's question sentence in mutual log can be determined, can directly will be approximate with interactive log user's question semanteme in model sample library
The corresponding one or more sample standards of one or more sample question sentences, which are asked, recommends knowledge maintenance personnel, when for one, by
Knowledge maintenance personnel judge whether properly；When to be multiple, therefrom directly selected by knowledge maintenance personnel one it is most suitable i.e.
Can, most suitable sample standard that is finally that judgement is suitable or selecting is asked and user's question sentence is stored in knowledge base in association, from
And artificial investment only needs to carry out simple supervision and management, the knowledge maintenance personnel for the management that exercises supervision need to only recognize Chinese,
With normal logic judgment ability, certain knowledge edition experience is needed for needing to put into before manually in this way
For, it further reduced the requirement to personnel's threshold, and improve optimization efficiency.
The advantages of the method, also resides in, and judges whether that needing to optimize knowledge base is entirely to complete in local model sample library
, without the knowledge base using cloud.Arithmetic speed is not only improved in this way, but also saves the spending of cloud knowledge base.
In one embodiment, sample extension, which is asked, asks that sample standard is asked asks including knowledge library standard including knowledge base extension.More
Further, sample extension, which is asked, asks that sample standard is asked including the institute in knowledge base including all knowledge bases extension in knowledge base
There is knowledge library standard to ask.In this embodiment, model sample library includes that all knowledge library standards in knowledge base are asked and knowledge
Library extension is asked.Model sample library is further reduced what subsequent artefacts selected to whether the judgement that optimizes is more accurate at this time
Workload.
In one embodiment, in step 302, if judging result is, there is no ask with the user in model sample library
The sample extension that sentence matches is asked, then knowledge point corresponding with user's question sentence, the knowledge point packet are created in knowledge base
Include: knowledge library standard is asked, knowledge base extension is asked and answer.In this embodiment, it is believed that the interactive log can not be by model sample library
Determined, i.e., information not relevant to the interactive log in knowledge base, needs to optimize knowledge base using this interactive log.At this time
Due to the interactive log undecidable, a knowledge relevant to user's question sentence is actively only added by knowledge maintenance personnel
Point, that is, need to add a knowledge library standard ask, multiple knowledge bases extension ask with an answer, to complete the optimization of knowledge base.
In a preferred embodiment, whether be by semantic similarity measured, can set if being matched in step 302
One threshold value, when semantic similarity is greater than first threshold, it is believed that interactive log user question sentence asks matching with sample extension.When artificial
When input amount can guarantee, the first threshold can be set higher.Otherwise, then first threshold can be set ground
It is lower, so as to save human cost.
In one embodiment, whether there is and user's question sentence phase in human-computer interaction log in the determining model sample library
Matched sample extension is asked, is to be completed by semantic matching degree operation, is segmented comprising steps of asking sample extension, and
Calculate word and sentence vector value；User's question sentence is segmented, and calculates word and sentence vector value；Each sample is calculated to expand
The word asked and sentence vector value and the word of user's question sentence and the degree of correlation of sentence vector value are opened up, to obtain user's question sentence
The semantic similarity asked is extended with sample.There are many operation method of semantic matching degree, and method in the prior art can also be transported
It uses in the present invention.
Since the quality in model sample library is most important for the present invention, more preferably, in another embodiment, to model sample
Example library optimizes, including two ways: one, while optimizing to knowledge base, identical content being added into model
Sample library；Two, it is extended when in the presence of the sample with user's question semanteme similarity greater than the first threshold and less than 100%
It asks, and the corresponding standard of user's question sentence asks the sample with semantic similarity greater than the first threshold and less than 100%
It is identical to extend the corresponding sample standard question sentence asked, then asks the corresponding standard of user's question sentence and user's question sentence to phase
Associatedly it is added into model sample library.The first optimization is primarily to keep model sample library content with knowledge base content
Unanimously, and by newest question sentence and standard it asks and updates into model sample library, approximately handed over encountering the content with update in next time
It when mutual log, can directly filter out, optimize without artificial judgment through the invention.Under second of optimal way, due to
Correct answer can be provided for current user's question sentence from knowledge base, that is, find correct standard and ask, so as to not have to incite somebody to action
Interactive log optimizes into knowledge base, but optimizes to be conducive to for subsequent more interactive logs being included in model sample library and can determine that
In range, so as to directly handle related interactive log through the invention.
Fig. 4 is please referred to, is the schematic diagram of the information processing method process for human-computer interaction of one embodiment of the invention, phase
Than Fig. 2, method flow shown in Fig. 3 includes the optimization to model sample library.It specifically includes:
Step 401: starting.
Step 402: determining in model sample library with the presence or absence of the sample to match with user's question sentence in human-computer interaction log
Example extension is asked, is entered step 403 if it exists, is otherwise entered step 405.
Step 403: determining that the corresponding standard of user's question sentence described in the human-computer interaction log is asked and matched sample
Whether the corresponding sample standard that extension is asked asks identical.404 are entered step if they are the same, otherwise enter step 406.
Step 404: judging whether the semantic similarity that user's question sentence is asked with sample extension is greater than first threshold and is less than
100%, if then entering 407, otherwise enter 408.
Step 405: re-creating knowledge point, and with knowledge point optimization knowledge base and model sample library.
Step 406: selection creation of knowledge point, and with knowledge point optimization knowledge base and model sample library.
Step 407: using interactive log content, Optimized model sample library.
Step 408: terminating.
Wherein step 405 content includes: actively to add one by knowledge maintenance personnel user's question sentence is relevant knows to this
Know point, that is, need to add a knowledge library standard ask, multiple knowledge bases extension ask with an answer, to complete the excellent of knowledge base
Change, while utilizing identical knowledge point Optimized model sample library, only the optimization in model sample library has only been used in knowledge point
Question sentence and standard ask content.Step 406 includes: that one or more standards in recommended models sample library ask and give knowledge maintenance people
Member, the pairing that knowledge maintenance personnel are directly selected to form user's question sentence and standard is asked, then the pairing is added
Enter knowledge base, while the pairing is added into model sample library.In step 407, by interactive log user's question sentence and institute it is right
The standard answered, which is asked, to be added in model sample library, so that forming a pair of new sample extension asks the correspondence asked with sample standard.This
Invention also provides a kind of device 51 of information processing, please refers to Fig. 5.In one embodiment, described device includes the first analysis mould
Block 501, the second analysis module 502 and optimization module 503.Interactive log initially enters the first analysis module 501, the first analysis mould
Block 501 determines that the sample extension that whether there is in model sample library and match with user's question sentence in human-computer interaction log is asked, if
In the presence of, then enter the second analysis module 502, determine the corresponding standard of user's question sentence described in the human-computer interaction log ask with
Whether the corresponding sample standard that the extension of matched sample is asked asks identical, enters optimization module 503 if not identical and knows described
Know library to optimize.
In another embodiment, Fig. 5 is please referred to, the first analysis module 501 further includes Semantic Similarity Measurement module 5011,
The semantic similarity asked is extended for calculating user's question sentence in human-computer interaction log and sample, and then obtains matching degree.Second
Analysis module 502 includes comparison module 5021, is asked and the expansion of matched sample for the corresponding standard of user's question sentence
Open up the corresponding sample standard asked asks whether text is completely the same.Optimization module 503 further includes recommending module 5031, for being based on
Semantic Similarity Measurement module 5011 as a result, recommending the sample for being greater than second threshold with the semantic matching degree of user's question sentence
The corresponding sample standard that example extension is asked is asked.Optimization module 503 further includes adding module 5032, for will be from the sample recommended
Standard asks that the standard that middle artificial selection goes out is asked and is added into the knowledge base in association with user's question sentence, while will be above-mentioned interior
Hold optimization and is added into model sample library.
More preferably, while optimizing to knowledge base, model sample library 504 is optimized.Second analysis module 502 is also
Including adding module 5022, when whether the semantic similarity that user's question sentence is asked with sample extension is greater than first threshold and is less than
100%, and when corresponding standard asks identical, interactive log content optimization is entered into model sample library.Adding module 5032 is also used to
It asks that the standard of middle artificial selection out is asked for the sample standard recommended from recommending module 5031 to add in association with user's question sentence
Model sample library is added.
In another embodiment, the invalid data in interactive log is filtered first, can be picked according to preset filtering rule
Except the junk data in daily record data, such as: single English alphabet be repeated 5 times more than data.Naive Bayesian can be used later
Algorithm is analyzed, and calculates whether log content can determine that in range in analysis model.
The present invention also provides a kind of systems 52 of information processing for human-computer interaction, please refer to Fig. 5.Including described any
Information processing unit, while including knowledge base 504 and model sample library 505.
The present invention carries out Automatic sieve by the model sample library set up first when human-computer interaction log need to be optimized by choosing
Choosing has filtered out largely existing knowledge content, has reduced the input amount of hand labor.Simultaneity factor can need to optimize people from trend
Machine interactive log proposed standard is asked, artificial only to be selected, and is further reduced hand labor, is improved knowledge base
Optimization efficiency.
Offer is to make any person skilled in the art all and can make or use this public affairs to the previous description of the disclosure
It opens.The various modifications of the disclosure all will be apparent for a person skilled in the art, and as defined herein general
Suitable principle can be applied to other variants without departing from the spirit or scope of the disclosure.The disclosure is not intended to be limited as a result,
Due to example described herein and design, but should be awarded and principle disclosed herein and novel features phase one
The widest scope of cause.
Claims (10)
1. a kind of method of the information processing for human-computer interaction characterized by comprising
Model sample library is provided, model sample library includes that sample standard asks and asks corresponding sample with each sample standard
Example extension is asked；
Knowledge base is provided, the knowledge base includes that knowledge library standard asks and asks corresponding knowledge base with each knowledge library standard
Extension is asked and answer, and the knowledge base is used to furnish an answer for user's question sentence；
It determines in model sample library and is asked with the presence or absence of the sample extension to match with user's question sentence in human-computer interaction log；
If it exists, it is determined that the corresponding standard of user's question sentence described in the human-computer interaction log is asked to be extended with matched sample
Whether the corresponding sample standard asked asks identical；
If not identical, optimize the knowledge base；
If there is no the sample to match with user's question sentence extensions to ask in model sample library, created in knowledge base
Knowledge point corresponding with user's question sentence, the knowledge point include: that knowledge library standard is asked, knowledge base extension is asked and answer, and
By the knowledge point created in knowledge base while being added to model sample library.
2. the method for the information processing of human-computer interaction as described in claim 1, which is characterized in that the sample extension is asked
Ask that the sample standard is asked asks including knowledge library standard including knowledge base extension.
3. the method for the information processing of human-computer interaction as described in claim 1, which is characterized in that determine the model sample
It is asked in example library with the presence or absence of the sample extension to match with user's question sentence and includes:
User's question sentence is asked with sample extension and executes Semantic Similarity Measurement whether to deposit in determination model sample library
It is asked in the sample extension that the semantic similarity of at least one and user's question sentence is greater than first threshold.
4. the method for the information processing of human-computer interaction as described in claim 1, which is characterized in that determine that the user asks
Whether the corresponding standard of sentence is asked asks with the corresponding sample standard asked of matched sample extension and identical includes:
The corresponding standard for comparing user's question sentence asks that the corresponding sample standard asked with the extension of matched sample asks that text is
It is no completely the same.
5. as claimed in claim 4 for human-computer interaction information processing method, which is characterized in that if it exists with the use
Family question semanteme similarity is greater than the first threshold and the sample extension less than 100% is asked, and the institute of user's question sentence is right
It answers standard to ask to be greater than the first threshold with semantic similarity and ask less than the corresponding sample standard asked of 100% sample extension
Sentence is identical, then asks the corresponding standard of user's question sentence and user's question sentence and be added into the model sample in association
Library.
6. the method for the information processing of human-computer interaction as claimed in claim 4, which is characterized in that multiple matchings if it exists
Sample extension ask, it is determined that the corresponding standard of user's question sentence, which is asked, extends the corresponding sample mark asked with matched sample
Whether standard is asked identical includes:
Determine whether that corresponding sample standard that a matched sample extension is asked asks the corresponding mark with user's question sentence
Standard is asked identical.
7. the method for the information processing of human-computer interaction as claimed in claim 4, which is characterized in that the knowledge base
Optimization includes:
It is based on the Semantic Similarity Measurement as a result, recommending to be greater than second threshold with the semantic similarity of user's question sentence
The corresponding sample standard that sample extension is asked is asked；
It is added asking that the sample standard of middle artificial selection out is asked from the sample standard recommended in association with user's question sentence
Enter the knowledge base.
8. the method for the information processing of human-computer interaction as claimed in claim 7, which is characterized in that the method is also wrapped
It includes:
The sample standard for asking that middle artificial selection goes out from the sample standard recommended is asked with user's question sentence in association
It is added into model sample library.
9. a kind of device of the information processing for human-computer interaction characterized by comprising
First analysis module matches for determining to whether there is in model sample library with user's question sentence in human-computer interaction log
Sample extension ask；
Second analysis module, for being asked in response to there is the sample to match with user's question sentence extension, it is determined that the people
The corresponding standard of user's question sentence described in machine interactive log asks that the corresponding sample standard asked with the extension of matched sample is asked
It is no identical；And
Optimization module extends the corresponding sample asked with matched sample for asking in response to the corresponding standard of user's question sentence
Example standard is asked not identical, then optimizes knowledge base；
If there is no the sample to match with user's question sentence extensions to ask that the adding module exists in model sample library
Knowledge point corresponding with user's question sentence is created in knowledge base, the knowledge point includes: that knowledge library standard is asked, knowledge base extends
It asks and answer；
The adding module also by the knowledge point created in knowledge base while being added to model sample library.
10. a kind of system of the information processing for human-computer interaction, which is characterized in that the system comprises:
The device of information processing as claimed in claim 9；
Model sample library, model sample library include that sample standard asks and asks that corresponding sample expands with each sample standard
Zhan Wen；
Knowledge base, the knowledge base include that knowledge library standard asks and asks that corresponding knowledge base extends with each knowledge library standard
It asks and answer, the knowledge base is used to furnish an answer for user's question sentence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811074893.9A CN109344237B (en) | 2016-08-23 | 2016-08-23 | Information processing method and device for man-machine interaction |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811074893.9A CN109344237B (en) | 2016-08-23 | 2016-08-23 | Information processing method and device for man-machine interaction |
| CN201610710565.8A CN106295807B (en) | 2016-08-23 | 2016-08-23 | A kind of method and device of information processing |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610710565.8A Division CN106295807B (en) | 2016-08-23 | 2016-08-23 | A kind of method and device of information processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109344237A true CN109344237A (en) | 2019-02-15 |
| CN109344237B CN109344237B (en) | 2020-11-17 |
Family
ID=57615826
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610710565.8A Active CN106295807B (en) | 2016-08-23 | 2016-08-23 | A kind of method and device of information processing |
| CN201810620088.5A Active CN108764480B (en) | 2016-08-23 | 2016-08-23 | Information processing system |
| CN201811074893.9A Active CN109344237B (en) | 2016-08-23 | 2016-08-23 | Information processing method and device for man-machine interaction |
Family Applications Before (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610710565.8A Active CN106295807B (en) | 2016-08-23 | 2016-08-23 | A kind of method and device of information processing |
| CN201810620088.5A Active CN108764480B (en) | 2016-08-23 | 2016-08-23 | Information processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN106295807B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110362665A (en) * | 2019-06-12 | 2019-10-22 | 深圳追一科技有限公司 | A kind of question answering system and method based on semantic similarity |
| CN112936304A (en) * | 2021-02-02 | 2021-06-11 | 浙江大学 | Self-evolution type service robot system and learning method thereof |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106886820A (en) * | 2017-02-08 | 2017-06-23 | 深圳市科迈爱康科技有限公司 | Intelligent information processing method and system |
| CN109933777B (en) * | 2017-12-18 | 2024-02-06 | 上海智臻智能网络科技股份有限公司 | Knowledge base expanding device |
| CN109934347B (en) * | 2017-12-18 | 2024-02-02 | 上海智臻智能网络科技股份有限公司 | Device for expanding question-answer knowledge base |
| CN110019305B (en) * | 2017-12-18 | 2024-03-15 | 上海智臻智能网络科技股份有限公司 | Knowledge base expansion method, storage medium and terminal |
| CN110019304B (en) * | 2017-12-18 | 2024-01-05 | 上海智臻智能网络科技股份有限公司 | Method for expanding question-answering knowledge base, storage medium and terminal |
| CN108345644A (en) * | 2018-01-15 | 2018-07-31 | 阿里巴巴集团控股有限公司 | A kind of method and device of data processing |
| CN109325040B (en) * | 2018-07-13 | 2020-11-10 | 众安信息技术服务有限公司 | FAQ question-answer library generalization method, device and equipment |
| WO2020047779A1 (en) * | 2018-09-05 | 2020-03-12 | 西门子（中国）有限公司 | Fault analysis method and device and computer readable medium |
| CN109213847A (en) * | 2018-09-14 | 2019-01-15 | 广州神马移动信息科技有限公司 | Layered approach and its device, electronic equipment, the computer-readable medium of answer |
| CN109189912A (en) * | 2018-10-09 | 2019-01-11 | 阿里巴巴集团控股有限公司 | The update method and device of user's consulting statement library |
| CN111400458A (en) * | 2018-12-27 | 2020-07-10 | 上海智臻智能网络科技股份有限公司 | Automatic generalization method and device |
| CN111382235A (en) * | 2018-12-27 | 2020-07-07 | 上海智臻智能网络科技股份有限公司 | Question-answer knowledge base optimization method and device |
| CN111382239B (en) * | 2018-12-27 | 2023-06-23 | 上海智臻智能网络科技股份有限公司 | Interaction flow optimization method and device |
| CN109992675A (en) * | 2019-01-30 | 2019-07-09 | 阿里巴巴集团控股有限公司 | Information processing method and device |
| CN109829051B (en) * | 2019-01-30 | 2023-01-17 | 科大讯飞股份有限公司 | Method and device for screening similar sentences of database |
| CN109947651B (en) * | 2019-03-21 | 2022-08-02 | 上海智臻智能网络科技股份有限公司 | Artificial intelligence engine optimization method and device |
| CN110347807B (en) * | 2019-05-20 | 2023-08-08 | 平安科技（深圳）有限公司 | Problem information processing method and device |
| CN110928991A (en) * | 2019-11-20 | 2020-03-27 | 上海智臻智能网络科技股份有限公司 | Method and device for updating question-answer knowledge base |
| CN111125379B (en) * | 2019-12-26 | 2022-12-06 | 科大讯飞股份有限公司 | Knowledge base expansion method and device, electronic equipment and storage medium |
| CN111144098B (en) * | 2019-12-26 | 2023-05-30 | 支付宝(杭州)信息技术有限公司 | Recall method and device for extended question |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101178705A (en) * | 2007-12-13 | 2008-05-14 | 中国电信股份有限公司 | Free-running speech comprehend method and man-machine interactive intelligent system |
| US8504361B2 (en) * | 2008-02-07 | 2013-08-06 | Nec Laboratories America, Inc. | Deep neural networks and methods for using same |
| CN104199825A (en) * | 2014-07-23 | 2014-12-10 | 清华大学 | Information inquiry method and system |
| CN104360994A (en) * | 2014-12-04 | 2015-02-18 | 科大讯飞股份有限公司 | Natural language understanding method and natural language understanding system |
| CN104679815B (en) * | 2014-12-08 | 2018-02-23 | 北京云知声信息技术有限公司 | It is a kind of to screen question and answer pair and the method and system in real-time update question and answer storehouse |
| US20160196490A1 (en) * | 2015-01-02 | 2016-07-07 | International Business Machines Corporation | Method for Recommending Content to Ingest as Corpora Based on Interaction History in Natural Language Question and Answering Systems |
| CN105824797B (en) * | 2015-01-04 | 2019-11-12 | 华为技术有限公司 | A kind of methods, devices and systems for evaluating semantic similarity |
| CN105488185B (en) * | 2015-12-01 | 2018-07-24 | 上海智臻智能网络科技股份有限公司 | A kind of optimization method and device of knowledge base |
| CN105591882B (en) * | 2015-12-10 | 2018-03-06 | 北京中科汇联科技股份有限公司 | A kind of intelligence machine person to person mixes the method and system of customer service |
| CN105631022B (en) * | 2015-12-29 | 2019-03-05 | 上海智臻智能网络科技股份有限公司 | Information processing method and device |
| CN105677783A (en) * | 2015-12-31 | 2016-06-15 | 上海智臻智能网络科技股份有限公司 | Information processing method and device for intelligent question-answering system |
| CN105550361B (en) * | 2015-12-31 | 2018-11-09 | 上海智臻智能网络科技股份有限公司 | Log processing method and device and question and answer information processing method and device |
| CN105678324B (en) * | 2015-12-31 | 2019-03-26 | 上海智臻智能网络科技股份有限公司 | Method for building up, the apparatus and system of question and answer knowledge base based on similarity calculation |
-
2016
- 2016-08-23 CN CN201610710565.8A patent/CN106295807B/en active Active
- 2016-08-23 CN CN201810620088.5A patent/CN108764480B/en active Active
- 2016-08-23 CN CN201811074893.9A patent/CN109344237B/en active Active
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110362665A (en) * | 2019-06-12 | 2019-10-22 | 深圳追一科技有限公司 | A kind of question answering system and method based on semantic similarity |
| CN110362665B (en) * | 2019-06-12 | 2021-04-30 | 深圳追一科技有限公司 | Question-answering system and method based on semantic similarity |
| CN112936304A (en) * | 2021-02-02 | 2021-06-11 | 浙江大学 | Self-evolution type service robot system and learning method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108764480A (en) | 2018-11-06 |
| CN109344237B (en) | 2020-11-17 |
| CN106295807A (en) | 2017-01-04 |
| CN106295807B (en) | 2018-12-21 |
| CN108764480B (en) | 2020-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106295807B (en) | A kind of method and device of information processing | |
| CN107329967B (en) | Question answering system and method based on deep learning | |
| CN106649742A (en) | Database maintenance method and device | |
| CN109918489A (en) | A kind of knowledge question answering method and system of more strategy fusions | |
| CN109151218A (en) | Call voice quality detecting method, device, computer equipment and storage medium | |
| EP3096246A1 (en) | Method, system and storage medium for realizing intelligent answering of questions | |
| CN105868179B (en) | A kind of intelligent answer method and device | |
| CN110262273A (en) | A kind of home equipment control method, device, storage medium and smart home system | |
| CN106776832B (en) | Processing method, apparatus and system for question and answer interactive log | |
| CN107729468A (en) | Answer extracting method and system based on deep learning | |
| CN109857846B (en) | Method and device for matching user question and knowledge point | |
| CN110120001B (en) | Method and system for scoring based on combination of knowledge graph library and memory curve | |
| CN108388553B (en) | Method for eliminating ambiguity in conversation, electronic equipment and kitchen-oriented conversation system | |
| CN111026884B (en) | Dialog corpus generation method for improving quality and diversity of man-machine interaction dialog corpus | |
| CN109408821B (en) | Corpus generation method and device, computing equipment and storage medium | |
| CN110442700A (en) | Man-machine more wheel dialogue methods and system, smart machine for human-computer interaction | |
| CN115470338B (en) | Multi-scenario intelligent question answering method and system based on multi-path recall | |
| CN109885823A (en) | A kind of distributed semantic recognition methods of financial industry and system and device | |
| KR101916174B1 (en) | Method and apparatus for processing language based on machine learning | |
| CN104347071B (en) | Method and system for generating reference answers of spoken language test | |
| CN106202288A (en) | The optimization method of a kind of man-machine interactive system knowledge base and system | |
| CN113468296A (en) | Model self-iteration type intelligent customer service quality inspection system and method capable of configuring business logic | |
| CN112287082A (en) | Data processing method, device, equipment and storage medium combining RPA and AI | |
| US20020165716A1 (en) | Error corrective mechanisms for consensus decoding of speech | |
| CN109615009A (en) | A kind of learning Content recommended method and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A method and device for information processing in human-computer interaction Effective date of registration: 20231123 Granted publication date: 20201117 Pledgee: Bank of Jiangsu Co.,Ltd. Shanghai Jiading Sub branch Pledgor: SHANGHAI XIAOI ROBOT TECHNOLOGY Co.,Ltd. Registration number: Y2023980066939 |