CN105512228A - Bidirectional question-answer data processing method and system based on intelligent robot - Google Patents
Bidirectional question-answer data processing method and system based on intelligent robot Download PDFInfo
- Publication number
- CN105512228A CN105512228A CN201510857525.1A CN201510857525A CN105512228A CN 105512228 A CN105512228 A CN 105512228A CN 201510857525 A CN201510857525 A CN 201510857525A CN 105512228 A CN105512228 A CN 105512228A
- Authority
- CN
- China
- Prior art keywords
- question
- user
- initiatively
- information
- module
- 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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/2423—Interactive query statement specification based on a database schema
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
Abstract
The invention discloses a bidirectional question-answer data processing method and system based on an intelligent robot; the method comprises the following steps: obtaining user question information and carrying out intention identification; generating a first answer result corresponding to the question information according to the user intention; entering an active question process when the question information is related to user parameters stored in a user information database; generating an active question corresponding to the question information according to a preset dialogue rule; outputting a first response result and the active question. The method and system can answer user questions, can design questions complying with user features, and can ask the user; the user can answer the active questions, and the results are returned to the bidirectional question-answer system, thus supplementing and improving user information database, and realizing intelligent training for the system.
Description
Technical field
The present invention relates to intelligent robot technology field, specifically, relate to a kind of two-way question and answer data processing method based on intelligent robot and two-way question answering system.
Background technology
Intelligent answer robot belongs to the crossing domain of artificial intelligence and natural language processing, can be exchanged with people by the mode of natural language and answer a question, answer user the problem proposed with natural language with accurate, succinct natural language, ensure people's obtaining information rapidly and accurately.
Current situation is carried out from current question and answer robot, current technology can process common-sense (height above sea level as Mountain Everest is how many), open (how mediating as felt blue), problem such as chat greeting (as you are preferably also OK), mandatory (as putting song) etc., brings great convenience and better services experience to user.
But current question and answer robot is only confined to user's one direction and asks a question.That is, robot is the passive enquirement accepting user before this, then provides the answer of problem for user.This unidirectional interrogation reply system causes the limitation in reciprocal process, once user stops puing question to, robot also initiatively can not initiate topic.Therefore cause the effect of man-machine communication bad, user experience is poor.
Therefore, need one badly and question and answer robot can be made initiatively to initiate to put question to, two-way answering method and system that user initiatively initiates enquirement can be accepted again.
Summary of the invention
An object of the present invention is to solve the technological deficiency that existing question and answer robot initiatively can not initiate enquirement.
First embodiments of the invention provide a kind of two-way question and answer data processing method based on intelligent robot, comprise the following steps:
Obtain user's question information and carry out intention assessment;
The first response result corresponding to described question information is generated according to user view;
When described question information and the customer parameter stored in user information database form associate time, enter flow process of initiatively asking a question;
Initiatively the ask a question problem corresponding with described question information is generated according to the session rules preset;
Export described first response result and described problem of initiatively asking a question.
In one embodiment, also comprise:
Receive the second response result for described problem feedback of initiatively asking a question;
In the second response result, extract the related information of customer parameter, and upgrade the customer parameter of user information database according to related information.
In one embodiment, also comprise:
According to described second response result, flow process of initiatively asking a question is trained, upgrade session rules and mate with the customer parameter after making the problem of initiatively asking a question of generation and upgrading.
In one embodiment, also comprise:
Extract the sight conjunctive word in described question information, according to the context identification dialogue scenarios of described sight conjunctive word and current session;
Comprise in described step of carrying out intention assessment:
Carry out semanteme according to domain model to described question information to resolve, in described dialogue scenarios, carry out intention assessment.
In one embodiment, generate initiatively the ask a question problem corresponding with described question information according to the session rules preset to comprise:
Extract at least one to be selected problem corresponding with question information;
From at least one problem to be selected described, select the problem the highest with customer parameter matching degree as problem of initiatively asking a question.
In one embodiment, also comprise:
When it fails to match at least one problem to be selected described and customer parameter, generate the problem of initiatively asking a question adapted to described customer parameter.
In one embodiment, also comprise:
Receive user's chat message;
According to the customer parameter design chat scenario upgraded in user information database;
The dialogue of talking in professional jargon meeting customer parameter is generated under described chat scenario.
Embodiments of the invention also provide a kind of two-way question answering system based on intelligent robot, comprising:
Intention assessment module, it is configured to obtain user's question information and carry out intention assessment;
Responder module, it is configured to according to first response result of user view generation corresponding to described question information;
Matching module, its be configured to when described question information and the customer parameter stored in user information database form associate time, enter flow process of initiatively asking a question;
Initiatively ask a question module, it is configured to generate initiatively the ask a question problem corresponding with described question information according to the session rules preset;
Output module, it is configured to export described first response result and described problem of initiatively asking a question.
In one embodiment, also comprise:
Receiver module, it is configured to receive the second response result for described problem feedback of initiatively asking a question;
Update module, it is configured to the related information extracting customer parameter in the second response result, and upgrades the customer parameter of user information database according to related information.
In one embodiment, also comprise:
Training module, it is configured to train flow process of initiatively asking a question according to the second response result, upgrades session rules and mates with the customer parameter after making the problem of initiatively asking a question of generation and upgrading.
In one embodiment, also comprise:
Sight identification module, it is configured to the sight conjunctive word extracted in described question information, according to the context identification dialogue scenarios of described sight conjunctive word and current session;
Described intention assessment module is also resolved for carrying out semanteme according to domain model to described question information, in described dialogue scenarios, carry out intention assessment.
In one embodiment, described module of initiatively asking a question comprises:
Extract submodule, it is for extracting at least one to be selected problem corresponding with question information;
Chooser module, it for selecting the problem the highest with customer parameter matching degree as problem of initiatively asking a question from least one problem to be selected described.
In one embodiment, described module of initiatively asking a question also comprises:
Generate submodule, it is for when it fails to match at least one problem to be selected described and customer parameter, generates and problem of initiatively asking a question that described customer parameter adapts to.
In one embodiment, also comprise:
Acquisition module, it is configured to the chat message obtaining user;
Scenario Design module, it is configured to the customer parameter design chat scenario according to upgrading in user information database;
Chat module, it is configured under described chat scenario, generate the dialogue of talking in professional jargon meeting customer parameter.
In an embodiment of the present invention, intelligent robot not only can answer user the problem proposed, and can also design the problem that conforms to user characteristics and put question to user, makes interested to interactive process of user.User can also feed back in two-way question answering system to the answer of problem of initiatively asking a question, on the one hand user information database is carried out supplementary and perfect, also intelligent training is carried out to system on the other hand, make system in question answering process subsequently, design the problem of feature of being more close to the users.
In addition, system not only can complete the question answering process with user, can also initiate the chat topic meeting user characteristics, can promote the experience of user, possess stronger practicality in the chat process of class of talking in professional jargon.These two processes that active is asked a question and initiation is chatted complement each other and promote.Initiatively the interaction point of question is more, more can form the customer parameter reacting user characteristics in more detail, thus in chat process, initiate user interested or meet the topic of user's application demand, forms more well interaction with user.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from instructions, or understand by implementing the present invention.Object of the present invention and other advantages realize by structure specifically noted in instructions, claims and accompanying drawing and obtain.
Accompanying drawing explanation
Accompanying drawing is used to provide a further understanding of the present invention, and forms a part for instructions, with embodiments of the invention jointly for explaining the present invention, is not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is the flow chart of steps of the two-way question and answer data processing method of the embodiment of the present invention one;
Fig. 2 is the process flow diagram of the process of initiatively asking a question of the embodiment of the present invention one;
Fig. 3 is the flow chart of steps of the two-way question and answer data processing method of the embodiment of the present invention two;
Fig. 4 is the flow chart of steps of the two-way chat data disposal route of the embodiment of the present invention three;
Fig. 5 is the structural representation of the two-way question answering system of the embodiment of the present invention four;
Fig. 6 is the structural representation of the module of initiatively asking a question of the embodiment of the present invention four;
Fig. 7 is the structural representation of the two-way question answering system of the embodiment of the present invention five;
Fig. 8 is the structural representation of the two-way chat system of the embodiment of the present invention six.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, the present invention is described in further detail.
Below in conjunction with Figure of description, embodiments of the invention are described, should be appreciated that preferred embodiment described herein is only for instruction and explanation of the present invention, is not intended to limit the present invention.And in not afoul situation, the feature in embodiments of the invention can be combined with each other.
Embodiments of the invention provide a kind of intelligent answer robot of personalization, particularly a kind of two-way question answering system of personalization meeting user characteristics, intelligent sound assistant, chat robots, the automatically intelligent service system such as customer service and expert system can be widely used in, initiatively can put question to user, or initiatively initiate some topics to user.Wherein, the personality preference of the problem proposed to user or topic and the user of initiation, age, sex and occupation etc. are relevant, and these problems are more mated with user characteristics.Thus the behavioural habits of user are analysed in depth by the two-way interactive of user and question and answer robot, and will react on the analysis result of user initiatively in question mechanism, form the degree of intelligence that benign cycle improves system.
Before carrying out active enquirement, needing to build the domain model for carrying out semantic parsing and/or semantic classification model, identifying the input information representation user view out of user.In a preferred example, intention assessment engine judges by domain model the intention that user is possible.Draw above-mentioned domain model by training every field data separately, it is a kind of classification model in essence, utilizes semantic subsumption algorithm the order that user inputs can be referred to different fields.As user's input " Spicy diced chicken with peanuts ", judge that user view may follow restaurant, menu and encyclopaedia to have relation by semantic subsumption algorithm.Described semantic subsumption algorithm is a Semantic Similarity Measurement mode by using the modes such as regular expression, syntactic analysis, grammatical analysis or keyword resolution to realize, and its data basis is then a large number of users, the FIELD Data of training domain model.
Before carrying out active enquirement, also need to build user information database and store the customer parameter relevant to the sex of user, age, occupation, hobby and trip mode etc.This user information database is the mutual topic in order to identify user in follow-up active question process.Such as, user profile comprises age, sex, birthday, hobby, constellation and local etc., also comprises between occupation, travel modal, WA, taste of diet and frequent activity venue etc.
Such as, the information of party A-subscriber is " 8 years old, man, October 1 birthday, Beijing, local ".If the question information that intelligent robot receives party A-subscriber's input is " where you are ", then system judges that mutual topic can be relevant to customer parameter " local ", namely using " Beijing, local " this information of party A-subscriber as reference information.The problem of the active question that system goes out has " I is Pekinese, and you are also Pekinese ", or " I is Shanghai people, and you are Pekinese "
System initiatively can also initiate topic within user's long-time sluggish time period.For the information of above-mentioned party A-subscriber, the topic that system is initiatively initiated is such as " place which Beijing has joyful " or " Safari Park, Beijing is joyful " etc.
Below in conjunction with specific embodiment, two-way question and answer data processing method and system are described in detail.
embodiment one
Fig. 1 is the flow chart of steps of two-way question and answer implementation method.
In step S101, build domain model as described above and/or semantic classification model.
In step s 102, the user information database storing user profile is built.This user information database stores initial customer parameter, and can carry out improving and upgrading to user information database in follow-up question answering process.
In step s 103, obtain user's question information and carry out intention assessment.
Specifically, first gather the command information of user's input, then command information is converted to normative text format information, and pre-service is carried out to text formatting information, thus obtain question information to be identified.Wherein, the command information of user's input can be at least one in phonetic order, text instruction or positioning instruction.
Pretreatment operation can comprise denoising, intelligent correction, word segmentation processing and named entity recognition etc.Wherein, denoising mainly filters out the insignificant words such as invalid word, stop-word, does not affect the intention of user's input after filtration; Correction process is, according to phonetic error correction, mode such as statistics error correction, semantic error correction etc., correction process is carried out in the input of user's erroneous input or speech recognition errors, draws relatively accurate input; Word segmentation processing and named entity recognition carry out participle by modes such as Hidden Markov Model (HMM) to user's input, and mark each part of speech, also marks accordingly for named entity simultaneously.
Such as user's input " going to Xizhimen how to walk ", then " go " and noun " Xizhimen " by obtaining taxis verb after participle, the named entity simultaneously obtaining " Xizhimen " is place name, and " how walking " represents that user's is intended that inquiry route.
In this step, semanteme parsing can be carried out based on the domain model built in advance and/or semantic classification model to input information and identify user view.If the input information of user is clear and definite asked questions, such as " today, weather how " " goes to Xizhimen how to walk " etc., then directly can recognize the intention of user from problem.
In addition, the sight conjunctive word in user's question information can also first be extracted, according to the context identification dialogue scenarios of described sight conjunctive word and current session.Carry out semanteme according to domain model to described question information again to resolve, in described dialogue scenarios, carry out intention assessment.Wherein, dialogue scenarios represents User Status and user's request etc., for accurately judging that user view is replied accurately to provide in follow-up answer process.In this course, mainly rely on the descriptor extracted in the context of current session and decide, the judging to resolve as semanteme of sight provide effective support, improves greatly semantic accuracy rate of resolving.
Such as, the information of party B-subscriber is " man, Shanghai, local, bank clerk, trip of driving ".And in the dialogue of party B-subscriber and robot system, once there is information such as " road of today blocks up very much, late again " " getting on the bus seldom in road ".If the question information of party B-subscriber is " going to Xizhimen how to walk ", then determine that " Xizhimen " is for sight conjunctive word, system identification is that party B-subscriber will drive to go to Xizhimen to current dialogue scenarios, recognizes being intended to " obtaining the jam situation of current location to Xizhimen " of party B-subscriber in this dialogue scenarios.
In step S104, generate the first response result corresponding to question information according to user view.Such as, the question information for user " goes to Xizhimen how to walk ", if system recognize user in step s 103 be intended that inquiry driving route, then the first response result provided is " drive route of the shortest path from current location to Xizhimen "; Or recognize being intended to " obtaining the jam situation of current location to Xizhimen " of user in step s 103, then the first response result provided is " obtain the jam situation of current location to Xizhimen, and provide rational bypass route ".
In step S105, question information is mated with the customer parameter stored in user information database, when the two forms association, perform following step S106, enter flow process of initiatively asking a question.If the two can not form association, be then back to step S103.
Such as, the information of above-mentioned party A-subscriber is " 8 years old, man, October 1 birthday, Beijing, local ", then customer parameter is " age ", " sex ", " birthday " or " local ".If the question information that system acceptance inputs to party A-subscriber is " near have what dining room ", then recognize being intended in " dining room of finding nearby " of user, now user view and customer parameter do not form and associate, and directly export the first response result to user view.Such as, the first response result of output is " 500 meters have Malus spectabilis dining room eastwards ".
If the question information that system receives party A-subscriber's input is " you this year how old ", then user view forms with customer parameter " age " and associates, and triggering is initiatively asked a question mechanism.In subsequent step, system is to providing the first response result, and generates the problem " I 5 years old this year, you have 8 years old " of question.
In step s 106, initiatively the ask a question problem corresponding with question information is generated according to the session rules preset.Described in last example, if the question information that system receives party A-subscriber's input is " you this year how old ", then the problem generating initiatively question is " you have 8 years old ".In step s 107, described first response result and described problem of initiatively asking a question is exported.
Fig. 2 is a preferred example of process of initiatively asking a question.System can calculate the problem of multiple possible active enquirement according to the question information of user.System also can offering question storehouse, for storing all problems that may put question to.The session rules preset can be the maximum matched rule initiatively between asked questions and customer parameter.
In fig. 2, extract at least one to be selected problem corresponding with question information first in step s 201, then, in step S202, calculate the matching degree of at least one problem to be selected described and customer parameter.Next, in step S203, select the problem the highest with customer parameter matching degree as problem of initiatively asking a question; And, when the matching degree calculated is too low, it fails to match to be then judged as at least one problem to be selected described and customer parameter, generates the problem of initiatively asking a question adapted to customer parameter in step S204, makes the problem of initiatively asking a question generated more meet user characteristics.
Such as, C user is the little girl of 6 years old, if system acceptance to C user put question to as " we play games OK together ", and in user information database, do not match the hobby of C user, then design the problem more meeting little girl's feature, system initiatively question is " good, to come together how to play Barbie doll ".
Such as, D user is 50 years old, if the D user that system receives puts question to as " having the game what is joyful ", and in user information database, does not match the hobby of D user, then designing the problem of initiatively puing question to is " how carrying out fighting landlord ".
In addition, if the problem to be selected calculating the highest corresponding matching degree in the result of acquisition in step S202 is not unique, then in step S203, carry out Stochastic choice, namely from the problem multiple to be selected of correspondence the highest matching degree Stochastic choice problem as problem of initiatively asking a question.
Such as, the information of above-mentioned party B-subscriber is " man, Shanghai, local, bank clerk, trip of driving, hobby music and outdoor exercises ".If system receives the enquirement of party B-subscriber for " it is movable what weekend has ", the problem to be selected then calculating the highest matching degree in step S202 has two, be " weekend goes to hear a concert " or " weekend goes to drift about " respectively, in step S203, Stochastic choice one exports as the problem of initiatively asking a question subsequently.This design considers in current user information database to determine most suitable problem of initiatively asking a question, and needs again to put question to get more, more detailed user profile to user.Therefore, Stochastic choice problem exports.
As can be seen from above-mentioned analysis, according to the two-way question and answer data processing method that the present embodiment provides, intelligent robot not only can answer user the problem proposed, and can also design the problem that conforms to user characteristics and put question to user, makes interested to interactive process of user.
embodiment two
Fig. 3 is the flow chart of steps of the two-way question and answer data processing method that the present embodiment provides.With embodiment one unlike, user can also feed back in two-way question answering system to the answer of problem of initiatively asking a question, on the one hand user information database is carried out supplementary and perfect, also intelligent training is carried out to system on the other hand, make system in question answering process subsequently, design the problem of feature of being more close to the users.
In figure 3, the identical symbol logo of the step identical with embodiment one, be mainly described in detail to the feedback procedure of the present embodiment and the training process of flow process of initiatively asking a question at this, other guide repeats no more.
In step S108, receive second response result of user for described problem feedback of initiatively asking a question.For above-mentioned party B-subscriber, if party B-subscriber puts question to " you how old " to intelligent robot, robot answers and initiatively puts question to " I have five years old, you ".Party B-subscriber is " I have 30 years old " to " you " this second response result that initiatively asked questions feeds back.
In step S109, in the second response result, extract the related information of customer parameter, and upgrade the customer parameter of user information database according to related information.That is, intelligent robot extracts the information associated by customer parameter " age " in the second response result is " 30 years old ".Then the user information database of party B-subscriber is upgraded, add " age is 30 years old " this information.
In step s 110, according to the second response result, flow process of initiatively asking a question is trained, mate with the customer parameter after making the problem of initiatively asking a question of generation and upgrading.Get back to step S105 and step S106 afterwards, generate the problem of initiatively question.Specifically, the process of training flow process of initiatively asking a question comprises the renewal of matching process and the renewal of dialogue criterion.Be embodied in after with the addition of new customer parameter in user information database or being revised as new customer parameter, the customer parameter after needing according to renewal mates, and determines whether there is association; Correspondingly, in subsequent step according to dialogue criterion select with upgrade after the highest problem of customer parameter matching degree.Like this, by carrying out intelligent training to system, make system in question answering process subsequently, design the problem of feature of being more close to the users.
Such as, if party B-subscriber puts question to " having good-looking film recently " in dialogue next time, it is calculate matching degree according to the parameter " 30 years old age " of question information and party B-subscriber and " sex is the male sex " that robot upgrades session rules, the first response result generated is " " trump secret service " is hunky-dory ", and the problem of the active question of generation is " you like seeing action movie ".
embodiment three
Fig. 4 is the flow chart of steps of the two-way chat data disposal route that the present embodiment provides.Compared with above two embodiments, the method for the present embodiment can not only realize nan-machine interrogation, can also initiate the chat topic meeting user characteristics, can promote the experience of user, possess stronger practicality in the chat process of class of talking in professional jargon.
Fig. 4 is the improvement made on the basis of Fig. 3, and the step identical with Fig. 3 repeats no more.
After step s 102, the chat message that step S111 receives user is performed.Subsequently, according to the customer parameter design chat scenario upgraded in user information database in step S112, and in step S113, under chat scenario, the dialogue of talking in professional jargon meeting customer parameter is generated.Perform the answer that step S108 receives user again.
Such as, first party B-subscriber initiates to chat " playing games; It rs boring really " everyday, robot is according to the parameter upgraded in party B-subscriber's information " 30 years old age ", design the scene of chat for " user is on furlough ", generate the conversation message of class of talking in professional jargon for " 30 years old also play games, not promising " everyday.
It should be noted that, these two processes that active is asked a question and initiation is chatted complement each other and promote.Initiatively the interaction point of question is more, more can form the customer parameter reacting user characteristics in more detail, thus in chat process, initiate user interested or meet the topic of user's application demand, forms more well interaction with user.
embodiment four
Fig. 5 is the structural representation of the two-way question answering system of the present embodiment.This system mainly comprises intention assessment module 503, responder module 504, matching module 505, initiatively to ask a question module 506 and output module 507.In addition, domain model storehouse 501 and user information database 502 is also provided with.
Field of storage module and/or semantic classification model in domain model storehouse 501, for completing intention assessment.Storing subscriber information in user information database 502, stores initial customer parameter at first, and can constantly carry out improving and upgrading by user information database 502 in follow-up question answering process.
Intention assessment module 503 is configured to obtain user's question information and carry out intention assessment.Specifically, first gather the command information of user's input, then command information is converted to normative text format information, and pre-service is carried out to text formatting information, thus obtain question information to be identified.Based on the domain model built in advance and/or semantic classification model, semanteme parsing is carried out to input information and identify user view.
Responder module 504 is configured to according to first response result of user view generation corresponding to question information.Matching module 505 be configured to when question information and the customer parameter stored in user information database form associate time, enter flow process of initiatively asking a question.Associate if question information can not be formed with the customer parameter stored in user information database, then trigger module 506 of initiatively asking a question, the problem that design is initiatively asked a question.
Module of initiatively asking a question 506 is configured to generate initiatively the ask a question problem corresponding with described question information according to the session rules preset.Output module 507 is configured to export described first response result and described problem of initiatively asking a question.
Fig. 6 is the preferred exemplary of concrete structure of module 506 of initiatively asking a question.Module of initiatively asking a question 506 can calculate the problem of multiple possible active enquirement according to the question information of user.System also can offering question storehouse, for storing all problems that may put question to.The session rules preset can be the maximum matched rule initiatively between asked questions and customer parameter.
As shown in Figure 6, module 506 of initiatively asking a question comprises to be extracted submodule 601, chooser module 602 and generates submodule 603.Extract submodule 601 for extracting at least one to be selected problem corresponding with question information.Chooser module 602, for calculating the matching degree of at least one problem to be selected described and customer parameter, therefrom selects the problem the highest with customer parameter matching degree as problem of initiatively asking a question.When the matching degree calculated is too low, then it fails to match at least one problem to be selected described and customer parameter.Generate submodule 603 and generate the problem of initiatively asking a question adapted to described customer parameter, make the problem of initiatively asking a question generated more meet user characteristics.
Further, if the problem to be selected of the highest corresponding matching degree is not unique in the result that obtains of chooser module 602, then carry out Stochastic choice, namely from the problem multiple to be selected of correspondence the highest matching degree Stochastic choice problem as problem of initiatively asking a question.
The two-way question answering system that the present embodiment provides not only can answer user the problem proposed, and can also design the problem that conforms to user characteristics and put question to user, makes interested to interactive process of user.
embodiment five
Fig. 7 is the structural representation of the two-way question answering system of the present embodiment.With embodiment four unlike, user can also feed back in two-way question answering system to the answer of problem of initiatively asking a question, on the one hand user information database is carried out supplementary and perfect, also intelligent training is carried out to system on the other hand, make system in question answering process subsequently, design the problem of feature of being more close to the users.In the figure 7, the identical symbol logo of the structure identical with embodiment four, be mainly described in detail to the feedback of the present embodiment and the structure of training design at this, other guide repeats no more.
The present embodiment also comprises receiver module 701, update module 702 and training module 703.Wherein, receiver module 701 is for receiving second response result of user for described problem feedback of initiatively asking a question.Update module 702 for extracting the related information of customer parameter in the second response result, and upgrades the customer parameter of user information database according to related information.Training module 703 is trained flow process of initiatively asking a question according to the second response result, mates with the customer parameter after making the problem of initiatively asking a question of generation and upgrading.
Specifically, the process of training flow process of initiatively asking a question comprises the renewal of matching process and the renewal of dialogue criterion.Training module 703 can also call matching module 505 and module 506 of initiatively asking a question.Be embodied in after with the addition of new customer parameter in user information database or being revised as new customer parameter, matching module 505 need according to upgrade after customer parameter mate, determine whether there is association; Correspondingly, module 506 of initiatively asking a question is according to talking with the criterion selection problem the highest with the customer parameter matching degree after renewal.Like this, by carrying out intelligent training to system, make system in question answering process subsequently, design the problem of feature of being more close to the users.
embodiment six
Fig. 8 is the structural representation of the two-way chat system of the present embodiment.Compared with above two embodiments, the system of the present embodiment can not only realize nan-machine interrogation, can also initiate the chat topic meeting user characteristics, can promote the experience of user, possess stronger practicality in the chat process of class of talking in professional jargon.
Fig. 8 is the improvement made on the basis of Fig. 7, and the structure identical with Fig. 7 repeats no more.
The two-way chat system of the present embodiment also comprises acquisition module 801, Scenario Design module 802 and chat module 803.Wherein, acquisition module 801 is for receiving the chat message of the class of talking in professional jargon of user.Scenario Design module 802 is for designing chat scenario according to the customer parameter upgraded in user information database, and chat module 803 for generating the dialogue of talking in professional jargon meeting customer parameter under chat scenario.
Wherein, receiver module 701 can also receive the dialogue of user in chat process, and upgrades user information database by update module 702, and simultaneous training module 703 carries out intellectuality training to active question process.
It should be noted that, these two processes that active is asked a question and initiation is chatted complement each other and promote.Initiatively the interaction point of question is more, more can form the customer parameter reacting user characteristics in more detail, thus in chat process, initiate user interested or meet the topic of user's application demand, forms more well interaction with user.
Although embodiment disclosed in this invention is as above, the embodiment that described content just adopts for the ease of understanding the present invention, and be not used to limit the present invention.Technician in any the technical field of the invention; under the prerequisite not departing from spirit and scope disclosed in this invention; any amendment and change can be done what implement in form and in details; but scope of patent protection of the present invention, the scope that still must define with appending claims is as the criterion.
Claims (14)
1., based on a two-way question and answer data processing method for intelligent robot, it is characterized in that, comprise the following steps:
Obtain user's question information and carry out intention assessment;
The first response result corresponding to described question information is generated according to user view;
When described question information and the customer parameter stored in user information database form associate time, enter flow process of initiatively asking a question;
Initiatively the ask a question problem corresponding with described question information is generated according to the session rules preset;
Export described first response result and described problem of initiatively asking a question.
2. two-way question and answer data processing method as claimed in claim 1, is characterized in that, also comprise:
Receive the second response result for described problem feedback of initiatively asking a question;
In the second response result, extract the related information of customer parameter, and upgrade the customer parameter of user information database according to related information.
3. two-way question and answer data processing method as claimed in claim 2, is characterized in that, also comprise:
According to described second response result, flow process of initiatively asking a question is trained, upgrade session rules and mate with the customer parameter after making the problem of initiatively asking a question of generation and upgrading.
4. two-way question and answer data processing method as claimed in claim 1, is characterized in that, also comprise:
Extract the sight conjunctive word in described question information, according to the context identification dialogue scenarios of described sight conjunctive word and current session;
Comprise in described step of carrying out intention assessment:
Carry out semanteme according to domain model to described question information to resolve, in described dialogue scenarios, carry out intention assessment.
5. the two-way question and answer data processing method according to any one of claim 1-4, is characterized in that, generates initiatively the ask a question problem corresponding with described question information comprise according to the session rules preset:
Extract at least one to be selected problem corresponding with question information;
From at least one problem to be selected described, select the problem the highest with customer parameter matching degree as problem of initiatively asking a question.
6. two-way question and answer data processing method as claimed in claim 5, is characterized in that, also comprise:
When it fails to match at least one problem to be selected described and customer parameter, generate the problem of initiatively asking a question adapted to described customer parameter.
7. two-way question and answer data processing method as claimed in claim 5, is characterized in that, also comprise:
Receive user's chat message;
According to the customer parameter design chat scenario upgraded in user information database;
The dialogue of talking in professional jargon meeting customer parameter is generated under described chat scenario.
8., based on a two-way question answering system for intelligent robot, it is characterized in that, comprising:
Intention assessment module, it is configured to obtain user's question information and carry out intention assessment;
Responder module, it is configured to according to first response result of user view generation corresponding to described question information;
Matching module, its be configured to when described question information and the customer parameter stored in user information database form associate time, enter flow process of initiatively asking a question;
Initiatively ask a question module, it is configured to generate initiatively the ask a question problem corresponding with described question information according to the session rules preset;
Output module, it is configured to export described first response result and described problem of initiatively asking a question.
9. two-way question answering system as claimed in claim 8, is characterized in that, also comprise:
Receiver module, it is configured to receive the second response result for described problem feedback of initiatively asking a question;
Update module, it is configured to the related information extracting customer parameter in the second response result, and upgrades the customer parameter of user information database according to related information.
10. two-way question answering system as claimed in claim 9, is characterized in that, also comprise:
Training module, it is configured to train flow process of initiatively asking a question according to the second response result, upgrades session rules and mates with the customer parameter after making the problem of initiatively asking a question of generation and upgrading.
11. two-way question answering systems as claimed in claim 8, is characterized in that, also comprise:
Sight identification module, it is configured to the sight conjunctive word extracted in described question information, according to the context identification dialogue scenarios of described sight conjunctive word and current session;
Described intention assessment module is also resolved for carrying out semanteme according to domain model to described question information, in described dialogue scenarios, carry out intention assessment.
12. two-way question answering systems according to any one of claim 8-11, it is characterized in that, described module of initiatively asking a question comprises:
Extract submodule, it is for extracting at least one to be selected problem corresponding with question information;
Chooser module, it for selecting the problem the highest with customer parameter matching degree as problem of initiatively asking a question from least one problem to be selected described.
13. two-way question answering systems as claimed in claim 12, is characterized in that, described module of initiatively asking a question also comprises:
Generate submodule, it is for when it fails to match at least one problem to be selected described and customer parameter, generates and problem of initiatively asking a question that described customer parameter adapts to.
14. two-way question answering systems as claimed in claim 12, is characterized in that, also comprise:
Acquisition module, it is configured to the chat message obtaining user;
Scenario Design module, it is configured to the customer parameter design chat scenario according to upgrading in user information database;
Chat module, it is configured under described chat scenario, generate the dialogue of talking in professional jargon meeting customer parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510857525.1A CN105512228B (en) | 2015-11-30 | 2015-11-30 | A kind of two-way question and answer data processing method and system based on intelligent robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510857525.1A CN105512228B (en) | 2015-11-30 | 2015-11-30 | A kind of two-way question and answer data processing method and system based on intelligent robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105512228A true CN105512228A (en) | 2016-04-20 |
| CN105512228B CN105512228B (en) | 2018-12-25 |
Family
ID=55720210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510857525.1A Active CN105512228B (en) | 2015-11-30 | 2015-11-30 | A kind of two-way question and answer data processing method and system based on intelligent robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105512228B (en) |
Cited By (58)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105798918A (en) * | 2016-04-29 | 2016-07-27 | 北京光年无限科技有限公司 | Interactive method and device for intelligent robot |
| CN105898487A (en) * | 2016-04-28 | 2016-08-24 | 北京光年无限科技有限公司 | Interaction method and device for intelligent robot |
| CN105912697A (en) * | 2016-04-25 | 2016-08-31 | 北京光年无限科技有限公司 | Optimization method and device of dialog system knowledge base |
| CN105945949A (en) * | 2016-06-01 | 2016-09-21 | 北京光年无限科技有限公司 | Information processing method and system for intelligent robot |
| CN106113054A (en) * | 2016-07-12 | 2016-11-16 | 上海木爷机器人技术有限公司 | service processing method based on robot |
| CN106372195A (en) * | 2016-08-31 | 2017-02-01 | 北京光年无限科技有限公司 | Human-computer interaction method and device for intelligent robot |
| CN106457046A (en) * | 2016-07-07 | 2017-02-22 | 深圳狗尾草智能科技有限公司 | Prop purchase method and system in game based on multi-modal input |
| CN106446141A (en) * | 2016-09-21 | 2017-02-22 | 北京光年无限科技有限公司 | Interaction data processing method for intelligent robot system and robot system |
| CN106462384A (en) * | 2016-06-29 | 2017-02-22 | 深圳狗尾草智能科技有限公司 | Multi-modal based intelligent robot interaction method and intelligent robot |
| CN106426203A (en) * | 2016-11-02 | 2017-02-22 | 旗瀚科技有限公司 | Communication system and method of active trigger robot |
| CN106528522A (en) * | 2016-08-26 | 2017-03-22 | 南京威卡尔软件有限公司 | Scenarized semantic comprehension and dialogue generation method and system |
| CN106559321A (en) * | 2016-12-01 | 2017-04-05 | 竹间智能科技（上海）有限公司 | The method and system of dynamic adjustment dialog strategy |
| CN106599124A (en) * | 2016-11-30 | 2017-04-26 | 竹间智能科技（上海）有限公司 | System and method for actively guiding user to perform continuous conversation |
| CN106649704A (en) * | 2016-12-20 | 2017-05-10 | 竹间智能科技（上海）有限公司 | Intelligent dialogue control method and intelligent dialogue control system |
| CN106716934A (en) * | 2016-12-23 | 2017-05-24 | 深圳前海达闼云端智能科技有限公司 | Chat interaction method and apparatus, and electronic device thereof |
| CN106776926A (en) * | 2016-12-01 | 2017-05-31 | 竹间智能科技（上海）有限公司 | Improve the method and system of responsibility when robot talks with |
| CN106777081A (en) * | 2016-12-13 | 2017-05-31 | 竹间智能科技（上海）有限公司 | Method and device for determining conversational system acknowledgment strategy |
| CN106960005A (en) * | 2017-02-20 | 2017-07-18 | 北京光年无限科技有限公司 | A kind of output intent and robot for artificial intelligence robot |
| CN107053208A (en) * | 2017-05-24 | 2017-08-18 | 北京无忧创新科技有限公司 | A kind of method of active dialog interaction robot system and the system active interlocution |
| CN107133349A (en) * | 2017-05-24 | 2017-09-05 | 北京无忧创新科技有限公司 | One kind dialogue robot system |
| CN107225579A (en) * | 2017-05-27 | 2017-10-03 | 众德云格机器人（苏州）有限公司 | The machine question answering system of rhetorical question formula |
| CN107278302A (en) * | 2017-03-02 | 2017-10-20 | 深圳前海达闼云端智能科技有限公司 | A kind of robot interactive method and interaction robot |
| CN107273487A (en) * | 2017-06-13 | 2017-10-20 | 北京百度网讯科技有限公司 | Generation method, device and the computer equipment of chat data based on artificial intelligence |
| CN107357787A (en) * | 2017-07-26 | 2017-11-17 | 微鲸科技有限公司 | Semantic interaction method, apparatus and electronic equipment |
| CN107480766A (en) * | 2017-07-18 | 2017-12-15 | 北京光年无限科技有限公司 | The method and system of the content generation of multi-modal virtual robot |
| WO2018001040A1 (en) * | 2016-06-27 | 2018-01-04 | 中兴通讯股份有限公司 | Method and device for providing service data, and computer storage medium |
| WO2018000205A1 (en) * | 2016-06-28 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | Question answering method and system based on multiple intents and multiple skill packets, and robot |
| CN107562788A (en) * | 2017-07-28 | 2018-01-09 | 深圳前海微众银行股份有限公司 | Exchange method, device and computer-readable recording medium |
| WO2018010635A1 (en) * | 2016-07-14 | 2018-01-18 | 腾讯科技（深圳）有限公司 | Method of generating random interactive data, network server, and smart conversation system |
| CN107861961A (en) * | 2016-11-14 | 2018-03-30 | 平安科技（深圳）有限公司 | Dialog information generation method and device |
| CN107885744A (en) * | 2016-09-29 | 2018-04-06 | 微软技术许可有限责任公司 | Conversational data analysis |
| CN107967308A (en) * | 2017-11-16 | 2018-04-27 | 百度在线网络技术（北京）有限公司 | A kind of processing method of intelligent interaction, device, equipment and computer-readable storage medium |
| CN108109689A (en) * | 2017-12-29 | 2018-06-01 | 李向坤 | Diagnosis and treatment session method and device, storage medium, electronic equipment |
| CN108114469A (en) * | 2018-01-29 | 2018-06-05 | 北京神州泰岳软件股份有限公司 | Game interaction method, apparatus, terminal and game interaction model based on dialogue |
| CN108319978A (en) * | 2018-02-01 | 2018-07-24 | 北京捷通华声科技股份有限公司 | A kind of semantic similarity calculation method and device |
| WO2018157695A1 (en) * | 2017-03-02 | 2018-09-07 | 腾讯科技（深圳）有限公司 | Method and apparatus for information exchange |
| CN108564833A (en) * | 2018-04-28 | 2018-09-21 | 北京比特智学科技有限公司 | Intelligent interaction dialog control method and device |
| CN109145096A (en) * | 2017-06-27 | 2019-01-04 | 中国海洋大学 | The daily robot automatically request-answering system of accompanying and attending to of personalization in rule-based library |
| CN109460451A (en) * | 2018-09-29 | 2019-03-12 | 厦门快商通信息技术有限公司 | Actively obtain method, the intelligent customer service method and system of user information |
| CN109473101A (en) * | 2018-12-20 | 2019-03-15 | 福州瑞芯微电子股份有限公司 | A kind of speech chip structures and methods of the random question and answer of differentiation |
| CN109787881A (en) * | 2018-12-26 | 2019-05-21 | 广州灵聚信息科技有限公司 | A kind of dialogue method and device with forecast function |
| CN109800430A (en) * | 2019-01-18 | 2019-05-24 | 广东小天才科技有限公司 | semantic understanding method and system |
| CN109863487A (en) * | 2016-10-07 | 2019-06-07 | 国立研究开发法人情报通信研究机构 | Non- fact type question answering system and method and the computer program for it |
| CN110019743A (en) * | 2017-11-14 | 2019-07-16 | 富士施乐株式会社 | Information processing unit and the computer-readable medium for storing program |
| CN110166640A (en) * | 2019-05-31 | 2019-08-23 | 重庆先特服务外包产业有限公司 | Call center's Common Information Model establishes system and method |
| CN110245218A (en) * | 2019-06-18 | 2019-09-17 | 广州智伴人工智能科技有限公司 | A kind of voice response exchange method |
| TWI676902B (en) * | 2018-01-31 | 2019-11-11 | 中華電信股份有限公司 | Method and system of analyzing conversation contents using chatting robot |
| CN110610705A (en) * | 2019-09-20 | 2019-12-24 | 上海数鸣人工智能科技有限公司 | Voice interaction prompter based on artificial intelligence |
| CN110730962A (en) * | 2017-04-20 | 2020-01-24 | 布瑞威利美国公司 | Crowdsourcing responses in a query processing system |
| CN110750626A (en) * | 2018-07-06 | 2020-02-04 | 中国移动通信有限公司研究院 | Scene-based task-driven multi-turn dialogue method and system |
| CN111400472A (en) * | 2020-03-16 | 2020-07-10 | 上海百事通信息技术股份有限公司 | Legal consultation intelligent question-answering method and system |
| CN111448533A (en) * | 2017-12-15 | 2020-07-24 | 国际商业机器公司 | Communication model for cognitive system |
| CN112000786A (en) * | 2020-06-30 | 2020-11-27 | 北京来也网络科技有限公司 | Dialogue robot problem processing method, device and equipment combining RPA and AI |
| CN112133147A (en) * | 2019-06-24 | 2020-12-25 | 武汉慧人信息科技有限公司 | Online automatic teaching and interaction system based on teaching plan and preset question bank |
| CN113741885A (en) * | 2020-05-29 | 2021-12-03 | 阿里巴巴集团控股有限公司 | Method, device, equipment and storage medium for training domain model |
| WO2022089546A1 (en) * | 2020-10-28 | 2022-05-05 | 华为云计算技术有限公司 | Label generation method and apparatus, and related device |
| CN114697280A (en) * | 2022-03-01 | 2022-07-01 | 西安博纳吉生物科技有限公司 | Instant messaging method for preset content |
| CN118093833A (en) * | 2024-04-19 | 2024-05-28 | 创意信息技术股份有限公司 | Multi-agent question-answering system and method based on large language model |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150074112A1 (en) * | 2012-05-14 | 2015-03-12 | Huawei Technologies Co., Ltd. | Multimedia Question Answering System and Method |
| CN104978360A (en) * | 2014-04-11 | 2015-10-14 | 俞志晨 | Realization method of question-answering system with account identity |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
-
2015
- 2015-11-30 CN CN201510857525.1A patent/CN105512228B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150074112A1 (en) * | 2012-05-14 | 2015-03-12 | Huawei Technologies Co., Ltd. | Multimedia Question Answering System and Method |
| CN104978360A (en) * | 2014-04-11 | 2015-10-14 | 俞志晨 | Realization method of question-answering system with account identity |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
Cited By (80)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105912697A (en) * | 2016-04-25 | 2016-08-31 | 北京光年无限科技有限公司 | Optimization method and device of dialog system knowledge base |
| CN105912697B (en) * | 2016-04-25 | 2019-08-27 | 北京光年无限科技有限公司 | A kind of optimization method and device of conversational system knowledge base |
| CN105898487A (en) * | 2016-04-28 | 2016-08-24 | 北京光年无限科技有限公司 | Interaction method and device for intelligent robot |
| CN105798918A (en) * | 2016-04-29 | 2016-07-27 | 北京光年无限科技有限公司 | Interactive method and device for intelligent robot |
| CN105798918B (en) * | 2016-04-29 | 2018-08-21 | 北京光年无限科技有限公司 | A kind of exchange method and device towards intelligent robot |
| CN105945949A (en) * | 2016-06-01 | 2016-09-21 | 北京光年无限科技有限公司 | Information processing method and system for intelligent robot |
| CN107547354A (en) * | 2016-06-27 | 2018-01-05 | 南京中兴软件有限责任公司 | Business datum provides method and device |
| WO2018001040A1 (en) * | 2016-06-27 | 2018-01-04 | 中兴通讯股份有限公司 | Method and device for providing service data, and computer storage medium |
| WO2018000205A1 (en) * | 2016-06-28 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | Question answering method and system based on multiple intents and multiple skill packets, and robot |
| CN106462384B (en) * | 2016-06-29 | 2019-05-31 | 深圳狗尾草智能科技有限公司 | Based on multi-modal intelligent robot exchange method and intelligent robot |
| CN106462384A (en) * | 2016-06-29 | 2017-02-22 | 深圳狗尾草智能科技有限公司 | Multi-modal based intelligent robot interaction method and intelligent robot |
| WO2018000280A1 (en) * | 2016-06-29 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | Multi-mode based intelligent robot interaction method and intelligent robot |
| CN106457046A (en) * | 2016-07-07 | 2017-02-22 | 深圳狗尾草智能科技有限公司 | Prop purchase method and system in game based on multi-modal input |
| CN106113054A (en) * | 2016-07-12 | 2016-11-16 | 上海木爷机器人技术有限公司 | service processing method based on robot |
| WO2018010635A1 (en) * | 2016-07-14 | 2018-01-18 | 腾讯科技（深圳）有限公司 | Method of generating random interactive data, network server, and smart conversation system |
| US11294962B2 (en) | 2016-07-14 | 2022-04-05 | Tencent Technology (Shenzhen) Company Limited | Method for processing random interaction data, network server and intelligent dialog system |
| CN106528522A (en) * | 2016-08-26 | 2017-03-22 | 南京威卡尔软件有限公司 | Scenarized semantic comprehension and dialogue generation method and system |
| CN106372195A (en) * | 2016-08-31 | 2017-02-01 | 北京光年无限科技有限公司 | Human-computer interaction method and device for intelligent robot |
| CN106446141A (en) * | 2016-09-21 | 2017-02-22 | 北京光年无限科技有限公司 | Interaction data processing method for intelligent robot system and robot system |
| CN107885744A (en) * | 2016-09-29 | 2018-04-06 | 微软技术许可有限责任公司 | Conversational data analysis |
| US11423229B2 (en) | 2016-09-29 | 2022-08-23 | Microsoft Technology Licensing, Llc | Conversational data analysis |
| CN109863487A (en) * | 2016-10-07 | 2019-06-07 | 国立研究开发法人情报通信研究机构 | Non- fact type question answering system and method and the computer program for it |
| CN106426203A (en) * | 2016-11-02 | 2017-02-22 | 旗瀚科技有限公司 | Communication system and method of active trigger robot |
| CN107861961A (en) * | 2016-11-14 | 2018-03-30 | 平安科技（深圳）有限公司 | Dialog information generation method and device |
| CN106599124A (en) * | 2016-11-30 | 2017-04-26 | 竹间智能科技（上海）有限公司 | System and method for actively guiding user to perform continuous conversation |
| CN106776926A (en) * | 2016-12-01 | 2017-05-31 | 竹间智能科技（上海）有限公司 | Improve the method and system of responsibility when robot talks with |
| CN106559321A (en) * | 2016-12-01 | 2017-04-05 | 竹间智能科技（上海）有限公司 | The method and system of dynamic adjustment dialog strategy |
| CN106777081A (en) * | 2016-12-13 | 2017-05-31 | 竹间智能科技（上海）有限公司 | Method and device for determining conversational system acknowledgment strategy |
| CN106649704A (en) * | 2016-12-20 | 2017-05-10 | 竹间智能科技（上海）有限公司 | Intelligent dialogue control method and intelligent dialogue control system |
| CN106716934B (en) * | 2016-12-23 | 2020-08-04 | 深圳前海达闼云端智能科技有限公司 | Chat interaction method and device and electronic equipment thereof |
| CN106716934A (en) * | 2016-12-23 | 2017-05-24 | 深圳前海达闼云端智能科技有限公司 | Chat interaction method and apparatus, and electronic device thereof |
| CN106960005A (en) * | 2017-02-20 | 2017-07-18 | 北京光年无限科技有限公司 | A kind of output intent and robot for artificial intelligence robot |
| CN107278302B (en) * | 2017-03-02 | 2020-08-07 | 深圳前海达闼云端智能科技有限公司 | Robot interaction method and interaction robot |
| CN107278302A (en) * | 2017-03-02 | 2017-10-20 | 深圳前海达闼云端智能科技有限公司 | A kind of robot interactive method and interaction robot |
| WO2018157695A1 (en) * | 2017-03-02 | 2018-09-07 | 腾讯科技（深圳）有限公司 | Method and apparatus for information exchange |
| CN110730962B (en) * | 2017-04-20 | 2024-05-14 | 布瑞威利美国公司 | Crowd-sourced responses in a query processing system |
| CN110730962A (en) * | 2017-04-20 | 2020-01-24 | 布瑞威利美国公司 | Crowdsourcing responses in a query processing system |
| CN107053208A (en) * | 2017-05-24 | 2017-08-18 | 北京无忧创新科技有限公司 | A kind of method of active dialog interaction robot system and the system active interlocution |
| CN107053208B (en) * | 2017-05-24 | 2018-06-01 | 北京无忧创新科技有限公司 | A kind of method of active dialog interaction robot system and the system active interlocution |
| CN107133349A (en) * | 2017-05-24 | 2017-09-05 | 北京无忧创新科技有限公司 | One kind dialogue robot system |
| CN107133349B (en) * | 2017-05-24 | 2018-02-23 | 北京无忧创新科技有限公司 | One kind dialogue robot system |
| CN107225579A (en) * | 2017-05-27 | 2017-10-03 | 众德云格机器人（苏州）有限公司 | The machine question answering system of rhetorical question formula |
| US10762305B2 (en) | 2017-06-13 | 2020-09-01 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method for generating chatting data based on artificial intelligence, computer device and computer-readable storage medium |
| CN107273487A (en) * | 2017-06-13 | 2017-10-20 | 北京百度网讯科技有限公司 | Generation method, device and the computer equipment of chat data based on artificial intelligence |
| CN109145096A (en) * | 2017-06-27 | 2019-01-04 | 中国海洋大学 | The daily robot automatically request-answering system of accompanying and attending to of personalization in rule-based library |
| CN107480766A (en) * | 2017-07-18 | 2017-12-15 | 北京光年无限科技有限公司 | The method and system of the content generation of multi-modal virtual robot |
| CN107357787B (en) * | 2017-07-26 | 2021-04-02 | 微鲸科技有限公司 | Semantic interaction method and device and electronic equipment |
| CN107357787A (en) * | 2017-07-26 | 2017-11-17 | 微鲸科技有限公司 | Semantic interaction method, apparatus and electronic equipment |
| CN107562788A (en) * | 2017-07-28 | 2018-01-09 | 深圳前海微众银行股份有限公司 | Exchange method, device and computer-readable recording medium |
| CN107562788B (en) * | 2017-07-28 | 2021-02-19 | 深圳前海微众银行股份有限公司 | Interaction method, interaction device and computer-readable storage medium |
| CN110019743A (en) * | 2017-11-14 | 2019-07-16 | 富士施乐株式会社 | Information processing unit and the computer-readable medium for storing program |
| US11308948B2 (en) | 2017-11-16 | 2022-04-19 | Baidu Online Network Technology (Beijing) Co., Ltd. | Intelligent interaction processing method and apparatus, device and computer storage medium |
| CN107967308A (en) * | 2017-11-16 | 2018-04-27 | 百度在线网络技术（北京）有限公司 | A kind of processing method of intelligent interaction, device, equipment and computer-readable storage medium |
| US11836592B2 (en) | 2017-12-15 | 2023-12-05 | International Business Machines Corporation | Communication model for cognitive systems |
| CN111448533B (en) * | 2017-12-15 | 2024-02-13 | 国际商业机器公司 | Communication model of cognitive system |
| CN111448533A (en) * | 2017-12-15 | 2020-07-24 | 国际商业机器公司 | Communication model for cognitive system |
| CN108109689A (en) * | 2017-12-29 | 2018-06-01 | 李向坤 | Diagnosis and treatment session method and device, storage medium, electronic equipment |
| CN108109689B (en) * | 2017-12-29 | 2023-09-29 | 李向坤 | Diagnosis and treatment session method and device, storage medium and electronic equipment |
| CN108114469A (en) * | 2018-01-29 | 2018-06-05 | 北京神州泰岳软件股份有限公司 | Game interaction method, apparatus, terminal and game interaction model based on dialogue |
| TWI676902B (en) * | 2018-01-31 | 2019-11-11 | 中華電信股份有限公司 | Method and system of analyzing conversation contents using chatting robot |
| CN108319978B (en) * | 2018-02-01 | 2021-01-22 | 北京捷通华声科技股份有限公司 | Semantic similarity calculation method and device |
| CN108319978A (en) * | 2018-02-01 | 2018-07-24 | 北京捷通华声科技股份有限公司 | A kind of semantic similarity calculation method and device |
| CN108564833A (en) * | 2018-04-28 | 2018-09-21 | 北京比特智学科技有限公司 | Intelligent interaction dialog control method and device |
| CN110750626A (en) * | 2018-07-06 | 2020-02-04 | 中国移动通信有限公司研究院 | Scene-based task-driven multi-turn dialogue method and system |
| CN110750626B (en) * | 2018-07-06 | 2022-05-06 | 中国移动通信有限公司研究院 | Scene-based task-driven multi-turn dialogue method and system |
| CN109460451A (en) * | 2018-09-29 | 2019-03-12 | 厦门快商通信息技术有限公司 | Actively obtain method, the intelligent customer service method and system of user information |
| CN109473101A (en) * | 2018-12-20 | 2019-03-15 | 福州瑞芯微电子股份有限公司 | A kind of speech chip structures and methods of the random question and answer of differentiation |
| CN109473101B (en) * | 2018-12-20 | 2021-08-20 | 瑞芯微电子股份有限公司 | Voice chip structure and method for differentiated random question answering |
| CN109787881A (en) * | 2018-12-26 | 2019-05-21 | 广州灵聚信息科技有限公司 | A kind of dialogue method and device with forecast function |
| CN109800430A (en) * | 2019-01-18 | 2019-05-24 | 广东小天才科技有限公司 | semantic understanding method and system |
| CN110166640A (en) * | 2019-05-31 | 2019-08-23 | 重庆先特服务外包产业有限公司 | Call center's Common Information Model establishes system and method |
| CN110245218A (en) * | 2019-06-18 | 2019-09-17 | 广州智伴人工智能科技有限公司 | A kind of voice response exchange method |
| CN112133147A (en) * | 2019-06-24 | 2020-12-25 | 武汉慧人信息科技有限公司 | Online automatic teaching and interaction system based on teaching plan and preset question bank |
| CN110610705A (en) * | 2019-09-20 | 2019-12-24 | 上海数鸣人工智能科技有限公司 | Voice interaction prompter based on artificial intelligence |
| CN111400472A (en) * | 2020-03-16 | 2020-07-10 | 上海百事通信息技术股份有限公司 | Legal consultation intelligent question-answering method and system |
| CN113741885A (en) * | 2020-05-29 | 2021-12-03 | 阿里巴巴集团控股有限公司 | Method, device, equipment and storage medium for training domain model |
| CN112000786A (en) * | 2020-06-30 | 2020-11-27 | 北京来也网络科技有限公司 | Dialogue robot problem processing method, device and equipment combining RPA and AI |
| WO2022089546A1 (en) * | 2020-10-28 | 2022-05-05 | 华为云计算技术有限公司 | Label generation method and apparatus, and related device |
| CN114697280A (en) * | 2022-03-01 | 2022-07-01 | 西安博纳吉生物科技有限公司 | Instant messaging method for preset content |
| CN118093833A (en) * | 2024-04-19 | 2024-05-28 | 创意信息技术股份有限公司 | Multi-agent question-answering system and method based on large language model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105512228B (en) | 2018-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105512228A (en) | Bidirectional question-answer data processing method and system based on intelligent robot | |
| CN111858877B (en) | Multi-type intelligent question answering method, system, equipment and readable storage medium | |
| CN109616108B (en) | Multi-turn dialogue interaction processing method and device, electronic equipment and storage medium | |
| CN107943998B (en) | Man-machine conversation control system and method based on knowledge graph | |
| CA2929018C (en) | Natural expression processing method, processing and response method, device and system | |
| US20180174585A1 (en) | Interaction assistant | |
| CN111177359A (en) | Multi-turn dialogue method and device | |
| WO2015096564A1 (en) | On-line voice translation method and device | |
| CN105895103A (en) | Speech recognition method and device | |
| US20170270921A1 (en) | Dialog management system | |
| CN101567189A (en) | Device, method and system for correcting voice recognition result | |
| CN110019688A (en) | The method that robot is trained | |
| US11615787B2 (en) | Dialogue system and method of controlling the same | |
| CN111324708A (en) | Natural language processing system based on human-computer interaction | |
| CN110517668B (en) | Chinese and English mixed speech recognition system and method | |
| CN114238607B (en) | Deep interactive AI intelligent job-searching consultant method, system and storage medium | |
| CN106952648A (en) | A kind of output intent and robot for robot | |
| CN111178081B (en) | Semantic recognition method, server, electronic device and computer storage medium | |
| CN111191450A (en) | Corpus cleaning method, corpus entry device and computer-readable storage medium | |
| CN111159364A (en) | Dialogue system, dialogue device, dialogue method, and storage medium | |
| CN110059166A (en) | Natural expression processing method, response method, equipment and the system of natural intelligence | |
| CN110059168A (en) | The method that man-machine interactive system based on natural intelligence is trained | |
| CN110046232A (en) | Natural expression processing method, response method, equipment and the system of natural intelligence | |
| CN111259124A (en) | Dialogue management method, device, system and storage medium | |
| CN117453871A (en) | Interaction method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |