CN110309284A - A kind of automatic answer method and device based on Bayesian Network Inference - Google Patents
A kind of automatic answer method and device based on Bayesian Network Inference Download PDFInfo
- Publication number
- CN110309284A CN110309284A CN201910579120.4A CN201910579120A CN110309284A CN 110309284 A CN110309284 A CN 110309284A CN 201910579120 A CN201910579120 A CN 201910579120A CN 110309284 A CN110309284 A CN 110309284A
- Authority
- CN
- China
- Prior art keywords
- answer
- probability
- answer probability
- reasonable
- bayesian network
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Abstract
The automatic answer method based on Bayesian Network Inference that the invention discloses a kind of, obtain communicating data of the user in dialogue map, and practical dialogue data is extracted from communicating data, then the answer probability of each words art node of practical dialogue data is predicted by dialogue map, obtain the first answer probability, reasonable analysis is carried out to practical dialogue data again, it generates and answers correctly record, and correctly record will be answered and summarized for reasonable communicating data, words art node statistics are carried out to reasonable communicating data according to knowledge base response mapping table, obtain Bayesian network distribution, and predict the answer probability of each words art node of reasonable communicating data, obtain the second answer probability, judge the reasonability of the first answer probability and the second answer probability, it generates the answer probability after reasonability judges and therefrom exports art node if answer probability maximum , dynamic can be made to original dialogue map prediction data and is judged, so that whole dialogue is more acurrate, more intelligent.
Description
Technical field
The present invention relates to field of artificial intelligence more particularly to a kind of automatic answer sides based on Bayesian Network Inference
Method and device.
Background technique
The automatic answer system constructed at present integrates mostly is intended to analysis, sentiment analysis, more wheel sessions and knowledge question etc.
Submodule is deduced and is managed according to artificial well-designed dialogue map, and a practical dialogue all is completed.
But since dialogue map needs are pre-designed, and increase with the scale of words art node, this design
Workload also will increase dramatically, while be also easy to hide more design irrationality.In addition, knowledge question has often corresponded to greatly
Amount words art, often there are tight associations for these knowledge contents.Current question answering system often ignores this part, so that
Whole dialogue seems not reasonable, stiff, not humanized enough.
Summary of the invention
The purpose of the embodiment of the present invention is that a kind of automatic answer method based on Bayesian Network Inference is provided, it can be to original
Some dialogue map prediction data make dynamic judgement and amendment, so that whole dialogue is more acurrate, more intelligent.
To achieve the above object, the embodiment of the invention provides a kind of automatic answer side based on Bayesian Network Inference
Method, comprising the following steps:
Communicating data of the user in dialogue map is obtained, and extracts practical dialogue data from the communicating data；
The answer probability for predicting each words art node of the practical dialogue data by talking with map, obtains the first response
Probability；
Reasonable analysis is carried out to the practical dialogue data, correctly record is answered in generation, and is answered described correctly
Record summarizes for reasonable communicating data；
Words art node statistics are carried out to the reasonable communicating data according to knowledge base response mapping table, obtain Bayesian network
Distribution, and predict the answer probability of each words art node of the reasonable communicating data, obtain the second answer probability；
Judge the reasonability of first answer probability and second answer probability, the response after generating reasonability judgement
Probability；
Art node if output answer probability is maximum from the answer probability after reasonability judgement.
Further, it in the reasonability of judgement first answer probability and second answer probability, generates and closes
After answer probability after rational judgment, further includes:
When, there are when reasonable answer probability, reasonably being answered in first answer probability and second answer probability
It answers probability and is modified processing, generate revised answer probability；
After the completion of to be modified, adjustment is normalized to the revised answer probability, the response after being adjusted is general
Rate.
Further, when answer probability is greater than 0.5, it is determined as reasonable answer probability.
Further, art section if output answer probability is maximum in the answer probability after the judgement from the reasonability
Point, specifically:
If maximum response is general after output adjustment there are reasonable answer probability in the answer probability after reasonability judgement
Art node if rate；
If reasonable answer probability is not present in the answer probability after the reasonability judgement, it is general to export second response
Art node if maximum probability in rate.
The embodiment of the invention also provides a kind of automatic answer device based on Bayesian Network Inference, comprising: data obtain
Modulus block, the first answer probability generation module, reasonable analysis module, the second answer probability generation module, judgment module and defeated
Module out；
The data acquisition module, for obtaining communicating data of the user in dialogue map, and from the communicating data
In extract practical dialogue data；
The first answer probability generation module, for predicting each words of the practical dialogue data by talking with map
The answer probability of art node obtains the first answer probability；
The reasonable analysis module is generated to answer and correctly be recorded for carrying out reasonable analysis to the practical dialogue data
Record, and correctly record summarizes for reasonable communicating data by the answer；
The second answer probability generation module, for according to knowledge base response mapping table to the reasonable communicating data into
Jargon art node statistics obtain Bayesian network distribution, and predict the response of each words art node of the reasonable communicating data
Probability obtains the second answer probability；
The judgment module is generated for judging the reasonability of first answer probability and second answer probability
Answer probability after reasonability judgement；
The output module, the art for the output answer probability maximum from the answer probability after reasonability judgement
Node.
Further, the automatic answer device based on Bayesian Network Inference, further includes: probability correction module and general
Rate adjusts module；
The probability correction module, for reasonable when existing in first answer probability and second answer probability
When answer probability, reasonable answer probability is modified processing, generates revised answer probability；
The association adjusts module, and after the completion of to be modified, tune is normalized to the revised answer probability
It is whole, the answer probability after being adjusted.
Further, when answer probability is greater than 0.5, it is determined as reasonable answer probability.
Further, the output module includes reasonable output unit and unreasonable output unit；
The reasonable output unit, if for there are reasonable response is general in the answer probability after reasonability judgement
Rate, art node if maximum answer probability after output adjustment；
The unreasonable output unit, if for reasonable response to be not present in the answer probability after reasonability judgement
Probability exports in second answer probability art node if maximum probability.
As the preferred embodiment of the present invention, the automatic answer based on Bayesian Network Inference that the present invention also provides a kind of
Equipment including processor, memory and stores in the memory and is configured as the calculating executed by the processor
Machine program is realized when the processor executes the computer program and is pushed away described in foregoing invention embodiment based on Bayesian network
The automatic answer method of reason.
Another embodiment of the present invention provides a kind of storage medium, the computer readable storage medium includes the meter of storage
Calculation machine program, wherein control equipment where the computer readable storage medium in computer program operation and execute
State the automatic answer method described in inventive embodiments based on Bayesian Network Inference.
Compared with prior art, it has the following beneficial effects:
Automatic answer method provided in an embodiment of the present invention based on Bayesian Network Inference obtains user in dialogue map
In communicating data, and extract practical dialogue data from communicating data, practical number of sessions then predicted by dialogue map
According to each words art node answer probability, obtain the first answer probability, then reasonable analysis is carried out to practical dialogue data, generate
Correctly record is answered, and correctly record will be answered and summarized for reasonable communicating data, according to knowledge base response mapping table pairing
Reason communicating data carries out words art node statistics, obtains Bayesian network distribution, and predict each words art section of reasonable communicating data
The answer probability of point, obtains the second answer probability, judges the reasonability of the first answer probability and the second answer probability, and it is reasonable to generate
Property judgement after answer probability and art node if therefrom output answer probability is maximum, can be to original dialogue map prediction number
Judge according to dynamic is made, so that whole dialogue is more acurrate, more intelligent.
Detailed description of the invention
Fig. 1 is that the process of one embodiment of the automatic answer method provided by the invention based on Bayesian Network Inference is shown
It is intended to；
Fig. 2 is that the structure of one embodiment of the automatic answer device provided by the invention based on Bayesian Network Inference is shown
It is intended to.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
It is one embodiment of the automatic answer method provided by the invention based on Bayesian Network Inference referring to Fig. 1, Fig. 1
Flow diagram；The embodiment of the present invention provides a kind of automatic answer method based on Bayesian Network Inference, including step S1-
S6；
S1 obtains communicating data of the user in dialogue map, and extracts practical number of sessions from the communicating data
According to.
S2, the answer probability for predicting each words art node of the practical dialogue data by talking with map, obtains first
Answer probability.
It should be noted that based on artificial preset dialogue map, including corresponding for user feeling analysis (such as certainly/
Negative) the knowledge question that jumps, may cover jump, some abnormality processings (such as interrupt/without reply) jump.
Wherein, the prediction data based on dialogue map is general to the response of all arts that should answer present in dialogue map
The prediction of rate exports.
S3 carries out reasonable analysis to the practical dialogue data, and correctly record is answered in generation, and is answered described correctly
Record summarize for reasonable communicating data.
In the present embodiment, it by being checked to session log and practical dialogic voice, identifies response and correctly records, lead to
The arrangement for crossing these records summarizes for reasonable practical communicating data.
S4 carries out words art node statistics to the reasonable communicating data according to knowledge base response mapping table, obtains Bayes
Network distribution, and predict the answer probability of each words art node of the reasonable communicating data, obtain the second answer probability.
Wherein, the same knowledge in the knowledge base response mapping table might have a variety of responses, so needing to pass through words
Art node statistics obtain Bayesian network distribution.
It should be noted that when practical application, it is contemplated that storage and speed, we, which only count, retains PBayes(at|(at-1,
at-2)), wherein a be words art node, shown herein as be for upper two-wheeled call words art node current answer probability.
S5 judges the reasonability of first answer probability and second answer probability, after generating reasonability judgement
Answer probability.
In embodiments of the present invention, after step S5 further include: when first answer probability and second response are general
There are when reasonable answer probability in rate, reasonable answer probability is modified processing, generates revised answer probability；To
After the completion of amendment, adjustment is normalized to the revised answer probability, the answer probability after being adjusted.
In the present embodiment, when answer probability is greater than 0.5, it is determined as reasonable answer probability.
It should be noted that correcting process formula is PAmendment=POutput*PBayes；Normalization adjustment formula are as follows: P 'Amendment=ep/∑
(ep)。
S6, art node if output answer probability is maximum from the answer probability after reasonability judgement.
Wherein, step S6 specifically: if the reasonability judgement after answer probability in there are reasonable answer probability, it is defeated
Art node if maximum answer probability after adjusting out；If reasonable response is not present in the answer probability after the reasonability judgement
Probability exports in second answer probability art node if maximum probability.
Assuming that upper two-wheeled words art node is a respectively1And a2,PBayes(a3|(a1,a2)) > 0 and P 'Amendment(a3|(a1,a2)) it is 0.4
It is maximum value, then a3The art node as last output；
Assuming that upper two-wheeled words art node is a respectively1And a2,PBayes(a3 | (a1, a2))=0 and P 'Amendment(a3|(a1,a2)) be
0.4 is maximum value, but threshold value is set as 0.5, at this time maximum PBayes(a4|(a1,a2)) it is 0.3, then a4As what is finally exported
Talk about art node.
Automatic answer method provided in an embodiment of the present invention based on Bayesian Network Inference is being talked with by obtaining user
Communicating data in map, and practical dialogue data is extracted from communicating data, it is then practical right by dialogue map prediction
The answer probability for talking about each words art node of data obtains the first answer probability, then carries out reasonable analysis to practical dialogue data,
It generates and answers correctly record, and correctly record will be answered and summarized for reasonable communicating data, according to knowledge base response mapping table
Words art node statistics are carried out to reasonable communicating data, obtain Bayesian network distribution, and predict each words of reasonable communicating data
The answer probability of art node obtains the second answer probability, judges the reasonability of the first answer probability and the second answer probability, generates
Reasonability judgement after answer probability and therefrom output answer probability maximum if art node.Embodiment provided by the invention is in original
On conversational system of some based on dialogue map, one layer of Bayesian Network Inference judgement built based on priori knowledge is added,
Have the advantages that implementation is simple, effect is good, and dynamic judgement can be made to original dialogue map prediction data and corrected,
So that whole dialogue is more acurrate, more intelligent.
As preferred embodiment provided by the invention, Fig. 2 is referred to, Fig. 2 is provided by the invention based on Bayesian network
The structural schematic diagram of one embodiment of the automatic answer device of reasoning, comprising: data acquisition module, the first answer probability generate
Module, reasonable analysis module, the second answer probability generation module, judgment module and output module；
The data acquisition module, for obtaining communicating data of the user in dialogue map, and from the communicating data
In extract practical dialogue data；The first answer probability generation module, for predicting that the reality is right by dialogue map
The answer probability for talking about each words art node of data, obtains the first answer probability；The reasonable analysis module, for the reality
Border dialogue data carries out reasonable analysis, generates answer correctly record, and the answer is correctly noted down and is summarized rationally to lead to
Talk about data；The second answer probability generation module, for according to knowledge base response mapping table to the reasonable communicating data into
Jargon art node statistics obtain Bayesian network distribution, and predict the response of each words art node of the reasonable communicating data
Probability obtains the second answer probability；The judgment module, for judging first answer probability and second answer probability
Reasonability, generate reasonability judgement after answer probability；The output module, for the response after judging from the reasonability
Art node if output answer probability is maximum in probability.
It should be noted that being determined as reasonable answer probability when answer probability is greater than 0.5.
In embodiments of the present invention, the automatic answer device based on Bayesian Network Inference further include: probability amendment
Module and probability adjust module；
The probability correction module, for reasonable when existing in first answer probability and second answer probability
When answer probability, reasonable answer probability is modified processing, generates revised answer probability；The association adjusts mould
After the completion of to be modified adjustment is normalized to the revised answer probability, the response after being adjusted is general in block
Rate.
Preferably, the output module includes reasonable output unit and unreasonable output unit；
The reasonable output unit, if for there are reasonable response is general in the answer probability after reasonability judgement
Rate, art node if maximum answer probability after output adjustment；The unreasonable output unit, if after for reasonability judgement
Answer probability in reasonable answer probability is not present, export in second answer probability art node if maximum probability.
Therefore a kind of automatic answer device based on Bayesian Network Inference provided in an embodiment of the present invention, pass through
Data acquisition module obtains communicating data of the user in dialogue map, and practical number of sessions is extracted from the communicating data
According to, the first answer probability generation module by talk with map predict the practical dialogue data each words art node response it is general
Rate, obtains the first answer probability, and reasonable analysis module carries out reasonable analysis to the practical dialogue data, generates and answer correctly
Record, and correctly record summarizes for reasonable communicating data by the answer, the second answer probability generation module is according to knowledge base
Response mapping table carries out words art node statistics to the reasonable communicating data, obtains Bayesian network distribution, and predict the conjunction
The answer probability for managing each words art node of communicating data, obtains the second answer probability, judgment module judges first response
The reasonability of probability and second answer probability, generate reasonability judgement after answer probability, output module from it is described rationally
Property judgement after answer probability in output answer probability it is maximum if art node.Embodiment provided by the invention is based on original
On the conversational system for talking with map, one layer of Bayesian Network Inference judgement built based on priori knowledge is added, has and implements
Simply, the good advantage of effect, and dynamic judgement and amendment can be made to original dialogue map prediction data, so that whole
Talk with more acurrate, more intelligent.
The automatic answer equipment based on Bayesian Network Inference that the embodiment of the invention also provides a kind of.The equipment includes:
Processor, memory and storage are in the memory and the computer program that can run on the processor.The place
Reason device is realized in above-mentioned each automatic answer embodiment of the method based on Bayesian Network Inference when executing the computer program
The step of, such as step S1 to S6 shown in FIG. 1.
Alleged processor can be central processing unit (Central Processing Unit, CPU), can also be it
His general processor, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng, the processor is the control centre of the automatic answer equipment based on Bayesian Network Inference, using various interfaces and
The various pieces of the entire automatic answer equipment based on Bayesian Network Inference of connection.
The memory can be used for storing the computer program and/or module, and the processor is by operation or executes
Computer program in the memory and/or module are stored, and calls the data being stored in memory, described in realization
The various functions of automatic answer equipment based on Bayesian Network Inference.The memory can mainly include storing program area and deposit
Store up data field, wherein storing program area can application program needed for storage program area, at least one function (for example sound is broadcast
Playing function, image player function etc.) etc.；Storage data area, which can be stored, uses created data (such as audio according to mobile phone
Data, phone directory etc.) etc..In addition, memory may include high-speed random access memory, it can also include non-volatile memories
Device, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or other volatibility are solid
State memory device.
Wherein, if module/unit of the automatic answer integration of equipments based on Bayesian Network Inference is with software function
Can the form of unit realize and when sold or used as an independent product, can store in computer-readable storage Jie
In matter.Based on this understanding, the present invention realizes all or part of the process in above-described embodiment method, can also pass through calculating
Machine program is completed to instruct relevant hardware, and the computer program can be stored in a computer readable storage medium,
The computer program is when being executed by processor, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer journey
Sequence includes computer program code, and the computer program code can be source code form, object identification code form, executable text
Part or certain intermediate forms etc..The computer-readable medium may include: that can carry appointing for the computer program code
What entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunications letter
Number and software distribution medium etc..
It should be noted that the apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
It needs that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.In addition, device provided by the invention
In embodiment attached drawing, the connection relationship between module indicate between them have communication connection, specifically can be implemented as one or
A plurality of communication bus or signal wire.Those of ordinary skill in the art are without creative efforts, it can understand
And implement.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (10)
1. a kind of automatic answer method based on Bayesian Network Inference, which comprises the following steps:
Communicating data of the user in dialogue map is obtained, and extracts practical dialogue data from the communicating data；
The answer probability for predicting each words art node of the practical dialogue data by talking with map, it is general to obtain the first response
Rate；
Reasonable analysis is carried out to the practical dialogue data, generates answer correctly record, and the answer is correctly noted down
Summarize for reasonable communicating data；
Words art node statistics are carried out to the reasonable communicating data according to knowledge base response mapping table, obtain Bayesian network point
Cloth, and predict the answer probability of each words art node of the reasonable communicating data, obtain the second answer probability；
Judge the reasonability of first answer probability and second answer probability, the response after generating reasonability judgement is general
Rate；
Art node if output answer probability is maximum from the answer probability after reasonability judgement.
2. the automatic answer method based on Bayesian Network Inference as described in claim 1, which is characterized in that in the judgement
The reasonability of first answer probability and second answer probability, after generating the answer probability after reasonability judges, also
Include:
When in first answer probability and second answer probability there are when reasonable answer probability, reasonable response is general
Rate is modified processing, generates revised answer probability；
After the completion of to be modified, adjustment is normalized to the revised answer probability, the answer probability after being adjusted.
3. the automatic answer method based on Bayesian Network Inference as claimed in claim 2, which is characterized in that work as answer probability
When greater than 0.5, it is determined as reasonable answer probability.
4. the automatic answer method based on Bayesian Network Inference as claimed in claim 3, which is characterized in that described from described
Art node if output answer probability is maximum in answer probability after reasonability judgement, specifically:
If there are reasonable answer probability in the answer probability after reasonability judgement, maximum answer probability after output adjustment
Talk about art node；
If reasonable answer probability is not present in the answer probability after the reasonability judgement, export in second answer probability
Art node if maximum probability.
5. a kind of automatic answer device based on Bayesian Network Inference characterized by comprising data acquisition module, first
Answer probability generation module, reasonable analysis module, the second answer probability generation module, judgment module and output module；
The data acquisition module for obtaining communicating data of the user in dialogue map, and is mentioned from the communicating data
Take out practical dialogue data；
The first answer probability generation module, for predicting each words art section of the practical dialogue data by talking with map
The answer probability of point, obtains the first answer probability；
The reasonable analysis module generates for carrying out reasonable analysis to the practical dialogue data and answers correctly record, and
By the answer, correctly record summarizes for reasonable communicating data；
The second answer probability generation module, for being talked about according to knowledge base response mapping table to the reasonable communicating data
Art node statistics obtain Bayesian network distribution, and predict the answer probability of each words art node of the reasonable communicating data,
Obtain the second answer probability；
The judgment module, for judging the reasonability of first answer probability and second answer probability, it is reasonable to generate
Property judgement after answer probability；
The output module, the art section for the output answer probability maximum from the answer probability after reasonability judgement
Point.
6. the automatic answer device based on Bayesian Network Inference as claimed in claim 5, which is characterized in that further include: probability
Correction module and probability adjust module；
The probability correction module, for when there are reasonable responses in first answer probability and second answer probability
When probability, reasonable answer probability is modified processing, generates revised answer probability；
The association adjusts module, after the completion of to be modified, adjustment is normalized to the revised answer probability, obtains
To answer probability adjusted.
7. the automatic answer device based on Bayesian Network Inference as claimed in claim 6, which is characterized in that when answer probability is big
When 0.5, it is determined as reasonable answer probability.
8. the automatic answer device based on Bayesian Network Inference as claimed in claim 7, which is characterized in that the output module
Including reasonable output unit and unreasonable output unit；
The reasonable output unit, if for the reasonability judgement after answer probability in there are reasonable answer probability, it is defeated
Art node if maximum answer probability after adjusting out；
The unreasonable output unit, if for there is no reasonable response is general in the answer probability after reasonability judgement
Rate exports in second answer probability art node if maximum probability.
9. a kind of automatic answer equipment based on Bayesian Network Inference, which is characterized in that including processor, memory and deposit
The computer program executed by the processor is stored up in the memory and is configured as, the processor executes the calculating
The automatic answer method based on Bayesian Network Inference as described in any one of Claims 1-4 is realized when machine program.
10. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium includes the calculating of storage
Machine program, wherein equipment where controlling the computer readable storage medium in computer program operation is executed as weighed
Benefit require any one of 1 to 4 described in the automatic answer method based on Bayesian Network Inference.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910579120.4A CN110309284B (en) | 2019-06-28 | 2019-06-28 | Automatic answer method and device based on Bayesian network reasoning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910579120.4A CN110309284B (en) | 2019-06-28 | 2019-06-28 | Automatic answer method and device based on Bayesian network reasoning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110309284A true CN110309284A (en) | 2019-10-08 |
| CN110309284B CN110309284B (en) | 2021-08-06 |
Family
ID=68077893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910579120.4A Active CN110309284B (en) | 2019-06-28 | 2019-06-28 | Automatic answer method and device based on Bayesian network reasoning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110309284B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111930905A (en) * | 2020-07-13 | 2020-11-13 | 上海明略人工智能(集团)有限公司 | Method, apparatus, system and computer-readable storage medium for question and answer training |
| EP3855323A1 (en) * | 2020-09-18 | 2021-07-28 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for generating conversation, electronic device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180032890A1 (en) * | 2016-07-27 | 2018-02-01 | Intuit Inc. | Method and system for improving content searching in a question and answer customer support system by using a crowd-machine learning hybrid predictive model |
| CN107807968A (en) * | 2017-10-13 | 2018-03-16 | 上海壹账通金融科技有限公司 | Question and answer system, method and storage medium based on Bayesian network |
| CN108596800A (en) * | 2018-04-13 | 2018-09-28 | 北京交通大学 | Bayes-based open answer decision method |
| CN109582778A (en) * | 2018-12-12 | 2019-04-05 | 东软集团股份有限公司 | A kind of intelligent answer method, apparatus, equipment and medium |
-
2019
- 2019-06-28 CN CN201910579120.4A patent/CN110309284B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180032890A1 (en) * | 2016-07-27 | 2018-02-01 | Intuit Inc. | Method and system for improving content searching in a question and answer customer support system by using a crowd-machine learning hybrid predictive model |
| CN107807968A (en) * | 2017-10-13 | 2018-03-16 | 上海壹账通金融科技有限公司 | Question and answer system, method and storage medium based on Bayesian network |
| CN108596800A (en) * | 2018-04-13 | 2018-09-28 | 北京交通大学 | Bayes-based open answer decision method |
| CN109582778A (en) * | 2018-12-12 | 2019-04-05 | 东软集团股份有限公司 | A kind of intelligent answer method, apparatus, equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 王玮等: "客服运维智能人机对话系统设计 ", 《烟台职业学院学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111930905A (en) * | 2020-07-13 | 2020-11-13 | 上海明略人工智能(集团)有限公司 | Method, apparatus, system and computer-readable storage medium for question and answer training |
| EP3855323A1 (en) * | 2020-09-18 | 2021-07-28 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for generating conversation, electronic device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110309284B (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10453472B2 (en) | Parameter prediction device and parameter prediction method for acoustic signal processing | |
| CN109842565A (en) | Interface current-limiting method, device, electronic equipment and storage medium | |
| CN108076226A (en) | A kind of method, mobile terminal and the storage medium of speech quality adjustment | |
| CN107734126B (en) | Voice adjusting method, device, terminal and storage medium | |
| WO2019042180A1 (en) | Resource allocation method and related product | |
| CN110309284A (en) | A kind of automatic answer method and device based on Bayesian Network Inference | |
| CN111953772B (en) | Request processing method, device, server and storage medium | |
| CN111198759B (en) | Memory optimization method, system, terminal equipment and readable storage medium | |
| CN110060696B (en) | Sound mixing method and device, terminal and readable storage medium | |
| CN109962893B (en) | Intelligent calling method and related equipment thereof | |
| CN105208221B (en) | A kind of method and device automatically adjusting call voice | |
| CN111031181B (en) | Method, system and server for deploying and scheduling home-based line of outgoing call of telephone | |
| CN107846435A (en) | Business realizing system and method | |
| CN109348434A (en) | A kind of sending method of scene information, sending device and terminal device | |
| CN109451527B (en) | A kind of mobile communication subscriber is lost day granularity prediction technique and device | |
| CN109600470B (en) | Mobile terminal and sound production control method thereof | |
| US11366688B2 (en) | Do-not-disturb processing method and apparatus, and storage medium | |
| CN105959466B (en) | The treating method and apparatus of audio data | |
| CN110096250B (en) | Audio data processing method and device, electronic equipment and storage medium | |
| WO2023071616A1 (en) | Service processing method and apparatus, electronic device, and medium | |
| CN115481114A (en) | Data cleaning method and device, computer equipment and storage medium | |
| CN109788373A (en) | A kind of method and system of lossless adjustment OTN protection business | |
| CN111918174A (en) | Method and device for balancing volume gain, electronic device and vehicle | |
| US7031440B1 (en) | Interactive voice response systems with general-purpose blocks | |
| WO2022089321A1 (en) | Method and apparatus for scheduling access point, and server 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |