CN106227740A - A kind of data processing method towards conversational system and device - Google Patents
A kind of data processing method towards conversational system and device Download PDFInfo
- Publication number
- CN106227740A CN106227740A CN201610547396.0A CN201610547396A CN106227740A CN 106227740 A CN106227740 A CN 106227740A CN 201610547396 A CN201610547396 A CN 201610547396A CN 106227740 A CN106227740 A CN 106227740A
- Authority
- CN
- China
- Prior art keywords
- feedback information
- conversation group
- information
- candidate
- knowledge base
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
A kind of data processing method towards conversational system and device, wherein, the method includes: step one, the dialogue interactive information of acquisition user's input；Step 2, according to dialogue interactive information and context interaction data, generate corresponding characteristic vector, utilize characteristic vector retrieval to preset the conversation group of storage in knowledge base, obtain the feedback information corresponding to conversation group of coupling；Step 3, feedback information corresponding to conversation group according to coupling, generate the feedback information for dialogue interactive information.The method no longer only rely only on as existing method single sentence carry out knowledge base retrieval generate feedback information, but the content that combination dialogue both sides refer in dialog procedure before this is to carry out the retrieval of knowledge base, therefore compared to existing method, the method and device can be prevented effectively from the problem that the dialogue interactive information of feedback information and the user's input finally given does not matches that, are so favorably improved the Consumer's Experience of conversational system.
Description
Technical field
The present invention relates to robotics, specifically, relate to a kind of data processing method towards conversational system
And device.
Background technology
In traditional interactive process, the order of oneself is transmitted by user typically by the peripheral hardware such as keyboard or mouse
To robot.And this man-computer mode operates complexity, inefficiency, for not using the user of experience, this tradition
Man-machine interaction mode become the obstacle that user and robot carry out linking up.
Along with voice technology and the development of natural language processing technique, conversational system based on interactive voice is increasingly becoming use
Family and intelligent robot carry out the indispensable system of man-machine interaction.But for existing conversational system, its working method is led to
Being often that user initiates a chat, the content that then user is inputted by conversational system is answered, such question-response, thus real
Existing man-machine interaction.Therefore, the answer of conversational system is accomplished by relevant to Client-initiated chat main body, so could attract user
Continue to chat with conversational system with regard to same problem, be the most also the formation of dialogue.
But, existing conversational system, during interacting with user, the most only can be come by searching database
To the constructed answers of the content that user is inputted, so easily cause logical miss or the problem given an irrelevant answer.
Summary of the invention
For solving the problems referred to above, the invention provides a kind of data processing method towards conversational system, comprising:
Step one, the dialogue interactive information of acquisition user's input；
Step 2, according to described dialogue interactive information and context interaction data, generate corresponding characteristic vector, utilize institute
State characteristic vector retrieval and preset the conversation group of storage in knowledge base, obtain the feedback information corresponding to conversation group of coupling；
Step 3, according to feedback information corresponding to the conversation group of described coupling, generate for described dialogue interactive information
Feedback information.
According to one embodiment of present invention, the conversation group in described default knowledge base stores with vector mode.
According to one embodiment of present invention, in described step 2,
Utilize this feature vector index to preset knowledge base, choose the predetermined number the highest with described characteristic vector similarity
Conversation group is as the conversation group of coupling；
Obtain the feedback information corresponding to the conversation group of described coupling and form candidate's feedback information set；
In described step 3, according to described candidate's feedback information set, generate for described dialogue interactive information is anti-
Feedforward information.
According to one embodiment of present invention, in described step 2, cosine similarity algorithm is utilized to calculate described presetting
The similarity with this feature vector of each conversation group in knowledge base.
According to one embodiment of present invention, in described step 3,
Calculate the phase of each candidate's feedback information and described dialogue interactive information in described candidate's feedback information set respectively
Guan Du, selects for institute from described candidate's feedback information set according to the degree of association value of each candidate's feedback information described
State the feedback information of dialogue interactive information.
Present invention also offers a kind of data processing equipment towards conversational system, comprising:
Interactive information acquisition module, it is for obtaining the dialogue interactive information of user's input；
Information searching module, it, for according to described dialogue interactive information and context interaction data, generates corresponding special
Levy vector, utilize the retrieval of described characteristic vector to preset the conversation group of storage in knowledge base, obtain corresponding to the conversation group of coupling
Feedback information；
Feedback information generation module, it generates for institute for the feedback information corresponding according to the conversation group of described coupling
State the feedback information of dialogue interactive information.
According to one embodiment of present invention, the conversation group in described default knowledge base stores with vector mode.
According to one embodiment of present invention, described information searching module is configured to utilize the retrieval of described characteristic vector to preset
Knowledge base, chooses the conversation group of the predetermined number the highest with described characteristic vector similarity as the conversation group mated, acquisition institute
State the feedback information corresponding to the conversation group of coupling and form candidate's feedback information set；
Feedback information generation module is configured to, according to described candidate's feedback information set, generate and believe alternately for described dialogue
The feedback information of breath.
According to one embodiment of present invention, described information searching module is configured to utilize cosine similarity algorithm to calculate institute
State the similarity with this feature vector of each conversation group in default knowledge base.
According to one embodiment of present invention, described feedback information generation module is configured to calculate described candidate feedback respectively
Each candidate's feedback information and the degree of association of described dialogue interactive information in information aggregate, according to each candidate's feedback information described
Degree of association value from described candidate's feedback information set, select the feedback information for described dialogue interactive information.
Data processing method towards conversational system provided by the present invention and device no longer as existing method only
Rely on single sentence to carry out knowledge base retrieval and generate feedback information, but combine dialogue both sides (i.e. user and conversational system) and exist
The content referred in dialog procedure before this is to carry out the retrieval of knowledge base, therefore compared to existing method, and the method and device energy
Enough it is prevented effectively from the problem that the dialogue interactive information of feedback information and the user's input finally given does not matches that, so contributes to
Improve the Consumer's Experience of conversational system.
Other features and advantages of the present invention will illustrate in the following description, and, partly become from description
Obtain it is clear that or understand by implementing the present invention.The purpose of the present invention and other advantages can be by description, rights
Structure specifically noted in claim and accompanying drawing realizes and obtains.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, required accompanying drawing does and simply introduces:
Fig. 1 is according to an embodiment of the invention towards the flowchart of data processing method of conversational system；
Fig. 2 is in accordance with another embodiment of the present invention towards the flowchart of data processing method of conversational system；
Fig. 3 is according to an embodiment of the invention towards the structural representation of data processing equipment of conversational system.
Detailed description of the invention
Describe embodiments of the present invention in detail below with reference to drawings and Examples, whereby how the present invention is applied
Technological means solves technical problem, and the process that realizes reaching technique effect can fully understand and implement according to this.Need explanation
As long as not constituting conflict, each embodiment in the present invention and each feature in each embodiment can be combined with each other,
The technical scheme formed is all within protection scope of the present invention.
Meanwhile, in the following description, many details are elaborated for illustrative purposes, to provide real to the present invention
Execute the thorough understanding of example.It will be apparent, however, to one skilled in the art, that the present invention can tool here
Body details or described ad hoc fashion are implemented.
It addition, can be in the department of computer science of such as one group of computer executable instructions in the step shown in the flow chart of accompanying drawing
System performs, and, although show logical order in flow charts, but in some cases, can be to be different from herein
Order perform shown or described by step.
Existing conversational system is generally retrieved two parts by knowledge base and problem and is constituted, when user inputs a new request
After information, this solicited message can be input in knowledge base retrieve by conversational system, and the reply letter that retrieval is matched
Breath returns to user, thus realize between user and conversational system mutual.But, found by research, existing dialogue system
System is utilizing knowledge base to retrieve when, and it only relies only on the information of single sentence, not in view of dialogue both sides (i.e.
User and conversational system) content referred in dialog procedure before.This also results in existing conversational system easily occurs
Logical miss, situation about giving an irrelevant answer.
For the problems referred to above existing for existing conversational system, the invention provides a kind of new number towards conversational system
According to processing method.The method with the addition of the support to many wheel dialogues on the basis of tradition conversational system data processing method, from
And make to finally return that and can take into full account interactive context of co-text to the feedback information of user, it is right the most also to allow for
Telephone system seems more intelligent and hommization.
In order to clearly illustrate the data processing method towards conversational system provided by the present invention realize principle,
Realize process and advantage, below in conjunction with different embodiments, the method is further described.
Embodiment one:
Fig. 1 shows the flowchart of the data processing method towards conversational system that the present embodiment provided.
As it is shown in figure 1, in the present embodiment, first the method obtains the dialogue of user's input in step S101 and believes alternately
Breath.
It should be noted that according to actual needs, the method dialogue interactive information accessed by step S101 was both
Can be the text message that inputs of user, it is also possible to be the voice messaging that inputs of user, the invention is not restricted to this.
After obtaining dialogue interactive information, the method is mutual according to this dialogue interactive information and context in step s 102
Data, generate corresponding characteristic vector.After obtaining this feature vector, the method utilizes this feature vector in step s 103
The conversation group stored in knowledge base is preset in retrieval, thus gets the conversation group matched with this feature vector, and then obtains
Feedback information corresponding to these conversation group.
Owing to the content of current session generally all relies on the content that both sides had talked, the content of current session is obvious
Not being independently of linguistic context, the dialogue interactive information that the method that therefore the present embodiment is provided inputs according to active user is with upper and lower
Literary composition interaction data generates finally for the feedback information talking with interactive information.
Such as, there is following dialog procedure:
The thinnest point of A: face is all right
B: do not stab my sore spot
A: my comparison of speaking is direct, my mistake, elder sister
B: I am just kidding, get used to
For existing conversational system, only consider nearest conversation content (i.e. " I am just kidding, practises due to it
Be used to "), the content therefore fed back to the user as B as the conversational system of A be likely to " this custom can be bad " or
Person is " frightening me ", and this feedback content cannot embody the linguistic context of above-mentioned dialogue.
As can be seen here, traditional conversational system knowledge base is all the mode number using simple " problem-answer "
According to storage, the most also allow for a problem corresponding with an answer.Such as, the data in the knowledge base of existing conversational system
Storage mode is typically:
Problem: I am just kidding, get used to answer: this custom can be bad
Or, problem: I am just kidding, get used to answer: fat z z z the most lovely
But for the method that the present embodiment is provided, the data phase that it is stored in the knowledge base of conversational system
More information can be comprised compared with existing method, the problem (i.e. talking with interactive information) of its storage no longer simply a word, and
Further comprises relevant context data.
Such as, in the present embodiment, the data storage method in the knowledge base of conversational system may is that
As can be seen here, this knowledge base not only store dialogue interactive information " I am just kidding, get used to ", but deposit
Having stored up the context data relevant to this dialogue interactive information, the feedback information so enabling to obtain can reflect currently
Mutual linguistic context so that interaction is more lively and hommization.
After obtaining the feedback information corresponding to conversation group of coupling, the method conversation group according to coupling in step S104
Corresponding feedback information, generates the feedback information for dialogue interactive information.In the present embodiment, the method institute in step s 103
Obtain may comprise multiple conversation group with the dialogue conversation group that matches of interactive information, is obtaining these and dialogue interactive information
After the conversation group of coupling, the method obtains the feedback information corresponding to these conversation group these feedback informations are anti-as candidate
Feedforward information, thus obtain candidate's feedback information set.In step S104, the method is chosen according to candidate's feedback information collection is incompatible
Go out the feedback information for dialogue interactive information, and the feedback information selected is exported to user.
Embodiment two:
Fig. 2 shows the flowchart of the data processing method towards conversational system that the present embodiment provided.
As in figure 2 it is shown, in the present embodiment, the method obtains the dialogue of user's input the most in step s 201 and believes alternately
Breath, and generate corresponding characteristic vector according to dialogue interactive information and context interaction data in step S202.Obtaining
After this feature vector, the method just can utilize this feature vector index to preset knowledge base in step S203, and select with
The conversation group of the predetermined number that characteristic vector similarity is the highest is as the conversation group of coupling.
Owing to dialogue interactive information itself cannot be carried out mathematical operation, two sections of therefore given dialogues the most just cannot be sentenced
Breaking, they are similar, the most just cannot weigh the similarity degree between them how high.Therefore, the present embodiment is provided
Dialogue interactive information and context data are converted into corresponding characteristic vector in step S202 by method, due to default knowledge base
In conversation group be to store in the way of vector equally, the most just can be by calculating the similarity between two vectors
Obtain the similarity between two sections of dialogues.
In the present embodiment, the method be preferably by step S202 neutral net come according to dialogue interactive information and on
Context data generates corresponding characteristic vector, is preferably by cosine similarity algorithm to calculate default knowledge in step S203
The similarity of the characteristic vector that each conversation group is obtained with step S202 in storehouse.It is pointed out that at its of the present invention
In his embodiment, it is also possible to use other reasonable manners to calculate the similarity between characteristic vector and/or two groups of dialogues, originally
Invention is not limited to this.
Simultaneously it may also be noted that in different embodiments of the invention, coupling selected in step S203
The quantity of conversation group can be set according to actual needs, and the present invention is similarly not so limited to.
As in figure 2 it is shown, after the conversation group obtaining coupling, the method obtains the conversation group of these couplings in step S204
Corresponding feedback information, thus form candidate's feedback information set.
After obtaining feedback information set, the method in step S205 according to candidate's feedback information set, generate for
The feedback information of above-mentioned dialogue interactive information.Specifically, in the present embodiment, it is anti-that the method calculates candidate in step S205 respectively
Each candidate's feedback information degree of association to above-mentioned dialogue interactive information in feedforward information set, and according to each candidate's feedback information
Corresponding degree of association value selects final feedback information from candidate's feedback information set.
In the present embodiment, preferably using candidate's feedback information maximum for degree of association value as final for above-mentioned dialogue
The feedback information of interactive information exports to user.Certainly, in other embodiments of the invention, it is also possible to use other reasonable
Mode from candidate's feedback information set, select required feedback information export to user, the invention is not restricted to
This.
From foregoing description it can be seen that the data processing method towards conversational system that provided of the present embodiment no longer as
Existing method the most only relies only on single sentence and carries out knowledge base retrieval and generate feedback information, but combines dialogue both sides (i.e.
User and conversational system) content referred in dialog procedure before this is to carry out the retrieval of knowledge base, therefore compared to existing side
Method, what this method can be prevented effectively from that the dialogue interactive information that the feedback information that finally gives and user input do not matches that asks
Topic, is so favorably improved the Consumer's Experience of conversational system.
Present invention also offers a kind of data processing equipment towards conversational system, Fig. 3 shows this dress in the present embodiment
The structural representation put.
As it is shown on figure 3, the data processing equipment that the present embodiment is provided preferably includes: interactive information acquisition module 301,
Information searching module 302 and feedback information generation module 303.Wherein, to be used for obtaining user defeated for interactive information acquisition module 301
The dialogue interactive information entered.
It should be noted that according to actual needs, the dialogue interactive information accessed by interactive information acquisition module 301 was both
Can be the text message of the user's input obtained by equipment such as keyboards, it is also possible to be by audio sensor (such as Mike
Wind) etc. equipment obtain user input voice messaging, the invention is not restricted to this.
After obtaining dialogue interactive information, this dialogue interactive information can be transferred to information by interactive information acquisition module 301
Retrieval module 302, with by information searching module 302 according to this dialogue interactive information and context interaction data, generate corresponding
Characteristic vector.After obtaining this feature vector, information searching module 302 also can utilize this feature vector to retrieve default knowledge base
Middle stored conversation group, thus get the conversation group matched with this feature vector, and then it is right to obtain these conversation group institutes
The feedback information answered.
In the present embodiment, information searching module 302 can be by the transmission of feedback information corresponding to the conversation group of the coupling obtained
To feedback information generation module 303.Feedback information generation module 303 can be raw according to the feedback information of these conversation group mated
Become the feedback information for dialogue interactive information and export to user.
It is pointed out that in the present embodiment, interactive information acquisition module 301, information searching module 302 and feedback letter
Breath generation module 303 realize its each the concrete principle of function and process with step S101 in above-described embodiment one to step
In S104 and embodiment two, step S201 is similar to step S205 to involved content, therefore at this no longer to above-mentioned module such as
What realize its each function repeat.
From foregoing description it can be seen that with above-mentioned as the data processing method of conversational system, the present embodiment institute
There is provided the data processing equipment towards conversational system the most only rely only on single sentence carry out knowledge base retrieval generate
Feedback information, but the content that combination dialogue both sides (i.e. user and conversational system) is referred in dialog procedure before this is known
Knowing the retrieval in storehouse, therefore this device can be prevented effectively from the feedback information finally given equally and believes alternately with the dialogue that user inputs
The problem that breath does not matches that, is so favorably improved the Consumer's Experience of conversational system.
It should be understood that disclosed embodiment of this invention is not limited to ad hoc structure disclosed herein or processes step
Suddenly, the equivalent that should extend to these features that those of ordinary skill in the related art are understood substitutes.It should also be understood that
It is that term as used herein is only used for describing the purpose of specific embodiment, and is not intended to limit.
" embodiment " mentioned in description or " embodiment " mean special characteristic, the structure in conjunction with the embodiments described
Or characteristic is included at least one embodiment of the present invention.Therefore, the phrase " reality that description various places throughout occurs
Execute example " or " embodiment " same embodiment might not be referred both to.
Although above-mentioned example is for illustrating present invention principle in one or more application, but for the technology of this area
For personnel, in the case of without departing substantially from the principle of the present invention and thought, hence it is evident that can in form, usage and the details of enforcement
Above various modifications may be made and need not pay creative work.Therefore, the present invention is defined by the appended claims.
Claims (10)
1. the data processing method towards conversational system, it is characterised in that including:
Step one, the dialogue interactive information of acquisition user's input；
Step 2, according to described dialogue interactive information and context interaction data, generate corresponding characteristic vector, utilize described spy
Levy vector index and preset the conversation group of storage in knowledge base, obtain the feedback information corresponding to conversation group of coupling；
Step 3, according to the feedback information corresponding to the conversation group of described coupling, generate for described dialogue interactive information is anti-
Feedforward information.
2. the method for claim 1, it is characterised in that the conversation group in described default knowledge base is deposited with vector mode
Storage.
3. method as claimed in claim 1 or 2, it is characterised in that in described step 2,
Utilize characteristic vector retrieval to preset knowledge base, choose the conversation group of the predetermined number the highest with described characteristic vector similarity
Conversation group as coupling；
Obtain the feedback information corresponding to the conversation group of described coupling, form candidate's feedback information set；
In described step 3, according to described candidate's feedback information set, generate the feedback letter for described dialogue interactive information
Breath.
4. method as claimed in claim 3, it is characterised in that in described step 2, utilize cosine similarity algorithm to calculate
The similarity that in described default knowledge base, each conversation group is vectorial with this feature.
5. method as claimed in claim 3, it is characterised in that in described step 3,
Calculate each candidate's feedback information and the degree of association of described dialogue interactive information in described candidate's feedback information set respectively,
Degree of association value according to each candidate's feedback information described selects for described right from described candidate's feedback information set
The feedback information of words interactive information.
6. the data processing equipment towards conversational system, it is characterised in that including:
Interactive information acquisition module, it is for obtaining the dialogue interactive information of user's input；
Information searching module, it is for according to described dialogue interactive information and context interaction data, generate corresponding feature to
Amount, utilizes the retrieval of described characteristic vector to preset the conversation group of storage in knowledge base, obtains the feedback corresponding to conversation group of coupling
Information；
Feedback information generation module, it, for according to the feedback information corresponding to the conversation group of described coupling, generates for described
The feedback information of dialogue interactive information.
7. device as claimed in claim 6, it is characterised in that the conversation group in described default knowledge base is deposited with vector mode
Storage.
Device the most as claimed in claims 6 or 7, it is characterised in that described information searching module is configured that
Utilize characteristic vector retrieval to preset knowledge base, choose the conversation group of the predetermined number the highest with described characteristic vector similarity
Conversation group as coupling；
Obtain the feedback information corresponding to the conversation group of described coupling and form candidate's feedback information set；
In described step 3, according to described candidate's feedback information set, generate the feedback letter for described dialogue interactive information
Breath.
9. device as claimed in claim 8, it is characterised in that described information searching module is configured to utilize cosine similarity to calculate
Method calculates the similarity that in described default knowledge base, each conversation group is vectorial with this feature.
10. device as claimed in claim 8, it is characterised in that described feedback information generation module is configured to calculate institute respectively
State each candidate's feedback information and the degree of association of described dialogue interactive information in candidate's feedback information set, wait according to described each
It is anti-that the degree of association value selecting feedback information selects for described dialogue interactive information from described candidate's feedback information set
Feedforward information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610547396.0A CN106227740A (en) | 2016-07-12 | 2016-07-12 | A kind of data processing method towards conversational system and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610547396.0A CN106227740A (en) | 2016-07-12 | 2016-07-12 | A kind of data processing method towards conversational system and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106227740A true CN106227740A (en) | 2016-12-14 |
Family
ID=57519832
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610547396.0A Pending CN106227740A (en) | 2016-07-12 | 2016-07-12 | A kind of data processing method towards conversational system and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106227740A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106776578A (en) * | 2017-01-03 | 2017-05-31 | 竹间智能科技（上海）有限公司 | Talk with the method and device of performance for lifting conversational system |
| CN106909677A (en) * | 2017-03-02 | 2017-06-30 | 腾讯科技（深圳）有限公司 | It is a kind of to generate the method and device putd question to |
| CN108170764A (en) * | 2017-12-25 | 2018-06-15 | 上海大学 | A kind of man-machine more wheel dialog model construction methods based on scene context |
| CN108376144A (en) * | 2018-01-12 | 2018-08-07 | 上海大学 | Man-machine more wheel dialogue methods that scene based on deep neural network automatically switches |
| CN109145099A (en) * | 2018-08-17 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Answering method and device based on artificial intelligence |
| CN109408619A (en) * | 2018-10-10 | 2019-03-01 | 桂林电子科技大学 | A method of question sentence and answer similitude are calculated towards question and answer field dynamic |
| CN109710503A (en) * | 2018-12-28 | 2019-05-03 | 浙江百应科技有限公司 | A kind of method of Intelligent voice dialog data OA operation analysis |
| WO2019085697A1 (en) * | 2017-10-31 | 2019-05-09 | 科沃斯商用机器人有限公司 | Man-machine interaction method and system |
| CN109814831A (en) * | 2019-01-16 | 2019-05-28 | 平安普惠企业管理有限公司 | Intelligent dialogue method, electronic device and storage medium |
| CN110096567A (en) * | 2019-03-14 | 2019-08-06 | 中国科学院自动化研究所 | Selection method, system are replied in more wheels dialogue based on QA Analysis of Knowledge Bases Reasoning |
| CN110209897A (en) * | 2018-02-12 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Intelligent dialogue method, apparatus, storage medium and equipment |
| CN111048074A (en) * | 2019-12-25 | 2020-04-21 | 出门问问信息科技有限公司 | Context information generation method and device for assisting speech recognition |
| CN114125043A (en) * | 2020-09-01 | 2022-03-01 | 上海智臻智能网络科技股份有限公司 | Information pushing method and information pushing device |
| CN117556061A (en) * | 2023-11-20 | 2024-02-13 | 曾昭涵 | Text output method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368246A (en) * | 2011-09-15 | 2012-03-07 | 张德长 | Automatic-answer robot system |
| CN103744836A (en) * | 2014-01-08 | 2014-04-23 | 苏州思必驰信息科技有限公司 | Man-machine conversation method and device |
| US20140258322A1 (en) * | 2013-03-06 | 2014-09-11 | Electronics And Telecommunications Research Institute | Semantic-based search system and search method thereof |
| CN104050256A (en) * | 2014-06-13 | 2014-09-17 | 西安蒜泥电子科技有限责任公司 | Initiative study-based questioning and answering method and questioning and answering system adopting initiative study-based questioning and answering method |
| CN104809103A (en) * | 2015-04-29 | 2015-07-29 | 北京京东尚科信息技术有限公司 | Man-machine interactive semantic analysis method and system |
| CN105159996A (en) * | 2015-09-07 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Deep question-and-answer service providing method and device based on artificial intelligence |
| CN105183848A (en) * | 2015-09-07 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Human-computer chatting method and device based on artificial intelligence |
| CN105704013A (en) * | 2016-03-18 | 2016-06-22 | 北京光年无限科技有限公司 | Context-based topic updating data processing method and apparatus |
-
2016
- 2016-07-12 CN CN201610547396.0A patent/CN106227740A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368246A (en) * | 2011-09-15 | 2012-03-07 | 张德长 | Automatic-answer robot system |
| US20140258322A1 (en) * | 2013-03-06 | 2014-09-11 | Electronics And Telecommunications Research Institute | Semantic-based search system and search method thereof |
| CN103744836A (en) * | 2014-01-08 | 2014-04-23 | 苏州思必驰信息科技有限公司 | Man-machine conversation method and device |
| CN104050256A (en) * | 2014-06-13 | 2014-09-17 | 西安蒜泥电子科技有限责任公司 | Initiative study-based questioning and answering method and questioning and answering system adopting initiative study-based questioning and answering method |
| CN104809103A (en) * | 2015-04-29 | 2015-07-29 | 北京京东尚科信息技术有限公司 | Man-machine interactive semantic analysis method and system |
| CN105159996A (en) * | 2015-09-07 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Deep question-and-answer service providing method and device based on artificial intelligence |
| CN105183848A (en) * | 2015-09-07 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Human-computer chatting method and device based on artificial intelligence |
| CN105704013A (en) * | 2016-03-18 | 2016-06-22 | 北京光年无限科技有限公司 | Context-based topic updating data processing method and apparatus |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106776578A (en) * | 2017-01-03 | 2017-05-31 | 竹间智能科技（上海）有限公司 | Talk with the method and device of performance for lifting conversational system |
| CN106909677A (en) * | 2017-03-02 | 2017-06-30 | 腾讯科技（深圳）有限公司 | It is a kind of to generate the method and device putd question to |
| CN106909677B (en) * | 2017-03-02 | 2020-09-08 | 腾讯科技（深圳）有限公司 | Method and device for generating question |
| WO2019085697A1 (en) * | 2017-10-31 | 2019-05-09 | 科沃斯商用机器人有限公司 | Man-machine interaction method and system |
| CN108170764A (en) * | 2017-12-25 | 2018-06-15 | 上海大学 | A kind of man-machine more wheel dialog model construction methods based on scene context |
| CN108170764B (en) * | 2017-12-25 | 2022-06-14 | 上海大学 | Man-machine multi-turn dialogue model construction method based on scene context |
| CN108376144A (en) * | 2018-01-12 | 2018-08-07 | 上海大学 | Man-machine more wheel dialogue methods that scene based on deep neural network automatically switches |
| CN108376144B (en) * | 2018-01-12 | 2021-10-12 | 上海大学 | Man-machine multi-round conversation method for automatic scene switching based on deep neural network |
| CN110209897A (en) * | 2018-02-12 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Intelligent dialogue method, apparatus, storage medium and equipment |
| CN110209897B (en) * | 2018-02-12 | 2023-09-01 | 腾讯科技（深圳）有限公司 | Intelligent dialogue method, device, storage medium and equipment |
| CN109145099A (en) * | 2018-08-17 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Answering method and device based on artificial intelligence |
| CN109408619B (en) * | 2018-10-10 | 2021-09-07 | 桂林电子科技大学 | Method for dynamically calculating similarity between question and answer in question-answering field |
| CN109408619A (en) * | 2018-10-10 | 2019-03-01 | 桂林电子科技大学 | A method of question sentence and answer similitude are calculated towards question and answer field dynamic |
| CN109710503A (en) * | 2018-12-28 | 2019-05-03 | 浙江百应科技有限公司 | A kind of method of Intelligent voice dialog data OA operation analysis |
| CN109814831A (en) * | 2019-01-16 | 2019-05-28 | 平安普惠企业管理有限公司 | Intelligent dialogue method, electronic device and storage medium |
| CN110096567A (en) * | 2019-03-14 | 2019-08-06 | 中国科学院自动化研究所 | Selection method, system are replied in more wheels dialogue based on QA Analysis of Knowledge Bases Reasoning |
| CN110096567B (en) * | 2019-03-14 | 2020-12-25 | 中国科学院自动化研究所 | QA knowledge base reasoning-based multi-round dialogue reply selection method and system |
| CN111048074A (en) * | 2019-12-25 | 2020-04-21 | 出门问问信息科技有限公司 | Context information generation method and device for assisting speech recognition |
| CN114125043A (en) * | 2020-09-01 | 2022-03-01 | 上海智臻智能网络科技股份有限公司 | Information pushing method and information pushing device |
| CN117556061A (en) * | 2023-11-20 | 2024-02-13 | 曾昭涵 | Text output method and device, electronic equipment and storage medium |
| CN117556061B (en) * | 2023-11-20 | 2024-05-24 | 曾昭涵 | Text output method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106227740A (en) | A kind of data processing method towards conversational system and device | |
| Mehri et al. | Structured fusion networks for dialog | |
| US20180090141A1 (en) | Conversational interactions using superbots | |
| CN106202301A (en) | A kind of intelligent response system based on degree of depth study | |
| CN109658928A (en) | A kind of home-services robot cloud multi-modal dialog method, apparatus and system | |
| CN102955781B (en) | A kind of personage's searching method and device | |
| CN109325132A (en) | Expertise recommended method, device, computer equipment and storage medium | |
| CN108733713A (en) | Data query method and device in data warehouse | |
| CN111914179B (en) | Semantic-based fuzzy search method and device, storage medium and electronic equipment | |
| CN105960674A (en) | Information processing device | |
| CN110249595A (en) | System and method for communication request to be routed to dedicated proxies | |
| CN110110049A (en) | Service consultation method, device, system, service robot and storage medium | |
| CN103970791B (en) | A kind of method, apparatus for recommending video from video library | |
| US9720982B2 (en) | Method and apparatus for natural language search for variables | |
| CN117573834B (en) | Multi-robot dialogue method and system for software-oriented instant service platform | |
| CN112069830B (en) | Intelligent session method and device | |
| Li et al. | Using granule to search privacy preserving voice in home IoT systems | |
| CN107506426A (en) | A kind of implementation method of intelligent television automated intelligent response robot | |
| RU2703980C1 (en) | Question-and-answer interface based on contextual information | |
| US20240135176A1 (en) | Training method and apparatus for neural network model, and data processing method and apparatus | |
| Oliver et al. | Toward the construction of a profession’s boundaries: Creating a networking agenda | |
| CN117407498A (en) | Large language model reply method, system, terminal and medium capable of automatically adjusting prompt words | |
| CN112328776A (en) | Dialog generation method and device, electronic equipment and storage medium | |
| CN116521832A (en) | Dialogue interaction method, device and system, electronic equipment and storage medium | |
| CN117312982A (en) | Method for detecting true person in man-machine conversation process based on large model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161214 |