CN106383872A - Artificial intelligence-based information processing method and apparatus - Google Patents
Artificial intelligence-based information processing method and apparatus Download PDFInfo
- Publication number
- CN106383872A CN106383872A CN201610806534.2A CN201610806534A CN106383872A CN 106383872 A CN106383872 A CN 106383872A CN 201610806534 A CN201610806534 A CN 201610806534A CN 106383872 A CN106383872 A CN 106383872A
- Authority
- CN
- China
- Prior art keywords
- information
- natural language
- operational order
- text message
- current state
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/53—Processing of non-Latin text
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Machine Translation (AREA)
Abstract
The invention provides an artificial intelligence-based information processing method and apparatus. The method comprises the steps of identifying natural language information input by a user to obtain corresponding text information; analyzing an operation instruction corresponding to the text information according to a preset information library set; updating a current state according to a current state of the user and the operation instruction; and generating natural language feedback information according to the operation instruction and the updated current state. According to the technical scheme, the natural language information input by the user can be processed in a self-help service, and the natural language feedback information is further generated, so that process interaction can be performed according to the natural language; and the problem that the process interaction is performed only by adopting a solidification instruction in the prior art can be avoided, so that information interaction modes are enriched, the flexibility of information interaction is improved, and the error rate of the information interaction can be reduced.
Description
【Technical field】
The present invention relates to natural language processing technique field, more particularly, to a kind of information processing method based on artificial intelligence
And device.
【Background technology】
Artificial intelligence (Artificial Intelligence), english abbreviation is AI.It is research, be developed for simulation,
Extend and extend the theory of intelligence of people, new science of technology of method, technology and application system.Artificial intelligence is to calculate
One branch of machine science, it attempts to understand essence of intelligence, and produce a kind of new can be in the way of human intelligence be similar
The intelligent machine made a response, the research in this field includes robot, language identification, image recognition, natural language processing and specially
Family's system etc..
With the development of electronics technology, the emerging in large numbers of various intelligent electronic devices, user can be by self-service intelligence
Various Self-Services can be realized by electronic equipment, such as user can realize Self-help ordering by self-help meal ordering machine, can also pass through
Self-service sale device selects self-service purchase etc..
The self-service electronic equipment of prior art during providing the user self-help service, by need according to pre-
The instruction user of the solidification first arranging interacts, the finger that the self-service electronic equipment that only can accept to set is capable of identify that
Order, otherwise will not be identified by self-service electronic equipment.For example a kind of self-service equipment of ordering, its user interface prompt user is permissible
Select " set meal ", " No. two set meals " or " No. three set meals ", user only can by the species of set meal of interface display and
Including content, select one of which set meal, realize sending the instruction of corresponding set meal to self-service electronic equipment, so self-service
The electronic equipment of formula can recognize the set meal species of user's selection, then requires the user also must be according to stream set in advance
Journey selects to place an order and submit, once user does not place an order according to default flow process or submits, such as after user selects a kind of set meal, and
Modification set meal is wanted to select to check another kind of set meal content, it will to lead to mistake of ordering, user needs by frequent trial and error ability
Find flow process of correctly ordering.
Therefore, only flow process interaction can be carried out using the instruction of solidification in self-service electronic equipment in prior art, lead
Information interaction approach is caused to be attributed to inflexible.
【Content of the invention】
The invention provides a kind of information processing method based on artificial intelligence and device, for enriching self-service electronics
Carry out the motility of information exchange in equipment.
The present invention provides a kind of information processing method based on artificial intelligence, and methods described includes:
The natural language information of user input is identified, obtains corresponding text message;
According to default information bank set, parse the corresponding operational order of described text message;
Current state according to described user and described operational order, update described current state;
According to the described current state after described operational order and renewal, generate natural language feedback information.
Still optionally further, in method described above, according to default information bank set, parse described text message pair
The operational order answered, specifically includes:
The corresponding operational order of described text message is obtained from default command library set.
Still optionally further, in method described above, from default command library set, obtain described text message pair
Before the operational order answered, methods described also includes:
Judge to whether there is the corresponding operational order of described text message in described default command library set;
Determine in described default command library set there is the corresponding operational order of described text message;
Further, when there is not the corresponding operational order of described text message in described default command library set,
Methods described also includes:
According to default dictionary, the content information of extraction tank position from described text message, described default dictionary
Include multiple groove positions;
According to the content information of described groove position, generate the corresponding operational order of described text message.
Still optionally further, in method described above, according to default information bank set, parse described text message pair
The operational order answered, specifically includes:
According to default dictionary, the content information of extraction tank position from described text message, described default dictionary
Include multiple groove positions;
According to the content information of described groove position, generate the corresponding operational order of described text message.
Still optionally further, in method described above, according to the described current state after described operational order and renewal,
After generating natural language feedback information, methods described also includes:
Store described current state, described text message and described natural language feedback information, to generate conversation content.
Still optionally further, in method described above, according to the described current state after described operational order and renewal,
After generating natural language feedback information, methods described also includes:
Described natural language feedback information is play with natural language.
Still optionally further, in method described above, the natural language information of user input is identified, it is right to obtain
Before the text message answered, methods described also includes:
Receive the described natural language information of described user input.
Still optionally further, in method described above, described current state includes:SBR, tapeout state, confirmation
Order status or pay status.
Still optionally further, in method described above, when the described current state after updating is pay status, described
Method also includes:
According to the corresponding described operational order of the described state that confirms an order, obtain payment information;
Show described payment information, so that described user pays;
After described user pays success, described current state is updated to pay status;
The process that places an order is carried out according to the corresponding operational order of the described state that confirms an order.
The present invention also provides a kind of information processor based on artificial intelligence, and described device includes:
Natural language recognition module, for being identified to the natural language information of user input, obtains corresponding text
Information;
Natural language understanding module, for according to default information bank set, parsing the corresponding operation of described text message
Instruction;
Processing module, for the current state according to described user and described operational order, updates described current state;
Spatial term module, according to the described current state after described operational order and renewal, generates natural language
Feedback information.
Still optionally further, in device described above, described natural language understanding module, specifically for from default life
Make in the set of storehouse and obtain the corresponding operational order of described text message.
Still optionally further, in device described above, described natural language understanding module, specifically it is additionally operable to judgement described
Whether there is the corresponding operational order of described text message in default command library set;Determine described default command library set
In there is the corresponding operational order of described text message;
Further, described natural language understanding module, is specifically additionally operable to when not depositing in described default command library set
In the corresponding operational order of described text message, according to default dictionary, in extraction tank position from described text message
Appearance information, described default dictionary includes multiple groove positions;According to the content information of described groove position, generate described text message
Corresponding operational order.
Still optionally further, in device described above, described natural language understanding module, specifically for according to default
Dictionary, the content information of extraction tank position from described text message, described default dictionary includes multiple groove positions;According to
The content information of described groove position, generates the corresponding operational order of described text message.
Still optionally further, in device described above, also include:
Dialog information memory module, anti-for storing described current state, described text message and described natural language
Feedforward information, to generate conversation content.
Still optionally further, in device described above, also include:
Playing module, for playing described natural language feedback information with natural language.
Still optionally further, in device described above, also include:
Receiver module, for receiving the described natural language information of described user input.
Still optionally further, in device described above, described current state includes:SBR, tapeout state, confirmation
Order status or pay status.
Still optionally further, in device described above, also include display module:
Described processing module, when being additionally operable to the described current state after updating for pay status, orders according to described confirmation
The corresponding described operational order of single state, obtains payment information;
Described display module, for showing described payment information, so that described user pays;
Described processing module, is additionally operable to, after described user pays success, described current state is updated to pay
State;
Described processing module, is additionally operable to carry out, according to the corresponding operational order of the described state that confirms an order, the process that places an order.
The information processing method based on artificial intelligence of the present invention and device, by the natural language information to user input
It is identified, obtain corresponding text message;According to default information bank set, parse the corresponding operational order of text message;
Current state according to user and operational order, update current state;According to the current state after operational order and renewal, generate
Natural language feedback information, realizes in self-help service, the natural language information according to user input carries out information processing, from
And generate natural language feedback information further it is achieved that flow process interaction is carried out according to natural language.Technical scheme,
Can avoid only can carrying out flow process interaction using the instruction of solidification in prior art, thus enriching the mode of information exchange,
Increased the motility of information exchange, and the spirit due to being interacted using natural language information in technical scheme
Activity is higher, such that it is able to reduce the error rate of information exchange.
【Brief description】
Fig. 1 is the flow chart of the information processing method embodiment based on artificial intelligence of the present invention.
Fig. 2 is the operation principle schematic diagram of FSM.
Fig. 3 is the structure chart of the information processor embodiment one based on artificial intelligence of the present invention.
Fig. 4 is the structure chart of the information processor embodiment two based on artificial intelligence of the present invention.
【Specific embodiment】
In order that the object, technical solutions and advantages of the present invention are clearer, below in conjunction with the accompanying drawings with specific embodiment pair
The present invention is described in detail.
Fig. 1 is the flow chart of the information processing method embodiment based on artificial intelligence of the present invention.As shown in figure 1, this reality
Apply the information processing method based on artificial intelligence of example, specifically may include steps of:
100th, the natural language information of user input is identified, obtains corresponding text message;
101st, according to default information bank set, parse the corresponding operational order of text message;
102nd, the current state according to user and operational order, updates current state;
103rd, according to the current state after operational order and renewal, generate natural language feedback information.
The executive agent of the information processing method based on artificial intelligence of the present embodiment can be the letter based on artificial intelligence
Breath processing meanss, should can apply in self-service electronic equipment the information processor based on artificial intelligence, be used to help
User carry out self-service order or do shopping when carry out information processing.In the present embodiment, user is in self-help service, permissible
Directly interacted using natural language.The natural language of the present embodiment refers to the language naturally developing with culture, for example
Can be English, Chinese or Japanese etc. language, or even can also be certain local dialect.
In the present embodiment based in the information processing method of artificial intelligence, the natural language information of user input is voice
Form, such as, in self-service electronic equipment, be provided with corresponding mike, can gather the natural language of the speech form of user
Speech information.I.e. alternatively, the natural language information of receiving user's input can also before step 100, be included.By this Mike
Wind can gather the natural language information of simultaneously receiving user's input, then the natural language information of user input is identified,
The process of text message will be identified as by voice messaging, this step can by the information processor based on artificial intelligence from
So language identification module is realized.Then according to default information bank set, parse the corresponding operational order of text message, it is right to realize
The understanding process of text message, thus according to default information bank set, the natural language information obtaining user input is corresponding
Operational order, so, is just achieved to be converted into natural language information and is capable of identify that based on the information processor of artificial intelligence
Computer language, this step can be by the natural language understanding (Natural in the information processor based on artificial intelligence
Language Understanding;NLU) module is completing.Then by the information processor based on artificial intelligence
Reason module (Processor), according to the current state of user and operational order, updates current state;This Processor module
It is properly termed as automatic interaction dialog process module, realize User Status are redirected condition criterion and state transition.This Processor
State transition in major control user interaction flow, and in order to be described to the interaction flow of user, this Processor can
With using finite state machine (finite state machine;FSM) model.The current state of the user of the present embodiment can be
SBR, tapeout state, the state that confirms an order or pay status, specifically, can also include point in each state
The sub- state in stage, such as can also include new tapeout state and modification order status etc. state in tapeout state.Based on people
The information processor of work intelligence, in holding state, when that is, self-service electronic equipment waits user to use, is constantly in preparation
State.Finally natural language feedback information can be generated according to the current state after operational order and renewal.Specifically, operate
Instruction is the demand statement of the natural-sounding information representing user, and the current state after updating is the demand representing according to user
Statement, the state next entering, the state that then demand according to user is stated and entered, predict the feedback to user
Content, generates the feedback information of natural language, to respond the natural language information of user, the natural language of generation in the present embodiment
Feedback information can be textual form.According to the current state after operational order and renewal in the present embodiment, generate nature
The process of verbal feedback information specifically can spatial term in the information processor based on artificial intelligence
(Natural Language Generate;NLG) module is realizing.
It should be noted that the various current states of the present embodiment be not limited in above-described embodiment SBR, place an order
State, the state that confirms an order or pay status, specifically, can go out various working as according to the type evolution of various self-help services
Front state.For example, the various current states of self-service booking and the self-service various current states hired a car etc. are various self-service
The various states of formula service.The logical order of the current state of the present embodiment and various current state is daily according to user
Operating specification in life and set, meet user's use demand.
And be taking a current state as a example to describe technical scheme in the present embodiment, self-service in practical application
The operation that formula service procedure can include multiple current states is formed by stacking, the operation of each current state, may each comprise as
Upper step 100-103.
Fig. 2 is the operation principle schematic diagram of FSM.For example so that user self-help is ordered as a example.When the current state of user is a little
Meal state corresponds to each state node State, and the demand statement of user to be operational order then correspond to each state transfer
Condition (State transition condition), and pass through the current state of user and the demand statement of user, thus really
Determine the process of User Status renewal, then correspond to state transfer (transition) process, this model can be extremely relevantly right
Automatic interaction flow process of ordering is described, and it is also possible to easily be encoded with State for granularity on framework is realized
Realize, realize simple (only need to consider current State), extension is convenient (to only need to increase state, by itself and related state relation
Get up), at theoretical and actual two aspects, all serve very important effect.Give an example below:
User currently has selected for some set meals, and have expressed " not having other needs, confirm an order ", now uses
Current state State at family is " set meal selection ", and State transition condition is " confirming an order ", and
Transition process is then from " set meal selection " by State, is updated to " the confirmation set meal " of the state of confirming an order, and new
State on, give user certain feedback, that is, generate natural language feedback information.
Still optionally further, after step 103, can also include:Natural language feedback information is play with natural language.
Information processor for example based on artificial intelligence specifically can be play by the speaker of self-service electronic equipment with certainly
So feedback information of this natural language of soundplay.So, the natural language information of user not only can be processed, generate
Natural language feedback information, can also play the feedback information of natural language simultaneously, anti-to inform the natural language that user generates
Feedforward information, is easy to the operation that the feedback information further according to natural language for the user carries out next step.
The information processing method based on artificial intelligence of the present embodiment, by carrying out to the natural language information of user input
Identification, obtains corresponding text message;According to default information bank set, parse the corresponding operational order of text message;According to
The current state of user and operational order, update current state;According to the current state after operational order and renewal, generate nature
Verbal feedback information, realizes in self-help service, the natural language information according to user input carries out information processing, thus entering
One step generates natural language feedback information it is achieved that carrying out flow process interaction according to natural language.The technical scheme of the present embodiment, can
To avoid only to carry out flow process interaction using the instruction of solidification in prior art, thus enriching the mode of information exchange, increase
Add the motility of information exchange, and the motility due to being interacted using natural language information in the present embodiment be higher,
Such that it is able to reduce the error rate of information exchange.
Still optionally further, the step 101 " root on the basis of the technical scheme of above-described embodiment, in above-described embodiment
According to default information bank set, parse the corresponding operational order of text message " in default information bank set be specifically as follows
Default command library set and/or default dictionary.
The a plurality of order pre-setting can be included, order therein is specifically as follows in wherein default command library set
The corresponding text of one natural language information of user, such as taking the service of ordering as a example, " I wants an a set meal ", the words
Both can be as the text message of a natural language it is also possible to be provided in an order in command library.According to similar side
Formula, can be provided with a plurality of similar order in default command library, be provided with each corresponding operational order of order simultaneously,
If " I wants an a set meal " corresponding operational order can be " an a set meal ".From the foregoing, default order
The parsing that the parsing to the corresponding text message of natural language is based on accurately mate is gathered in storehouse.
Now corresponding step 101 specifically can include obtaining the corresponding behaviour of text message from default command library set
Instruct.
It is predicted by the content that expectation user under the current state to user is inputted based on the parsing accurately joined,
Include basic interaction statement, when the corresponding text message of the natural language information of user hits in the set of this pre-set commands storehouse
The statement of order when, can be quick, be accurately performed the identification of user view and the extraction of associated groove position, put in order to obtain height
The analysis result of reliability.
As:When user is in " confirming an order " state it is desirable to user carries out " modification of order ", " cancellation of order ",
Or enter " pay status ", then in this condition, if user expresses above-mentioned three class related needs, can accurately hit time
Choosing statement, goes to next corresponding state.
Multiple groove positions can be included in wherein default dictionary.For example or taking order as a example, on a user interface, certainly
Help and can show multiple set meals on the interface of electronic equipment of formula, such as " set meal ", " No. two set meals ", " No. three set meals " with
And various optional beverage or snack etc..These information can be used as the groove position of default dictionary.In addition, it is true in order
Recognize in state, " confirmation " in " cancellation ", " confirming an order " in " cancelling an order ", " there is no other main points, please place an order
" in " please place an order " can serve as groove position.Groove position in the present embodiment does not limit several ways above, in practical application,
The state of the type according to self-help service and different users can have the groove position of multiple various kinds.Default in the present embodiment
Dictionary is to differ with the match pattern in pre-set commands storehouse, and the set of pre-set commands storehouse is it is necessary to order completely based on accurately mate
Middle just cry hit.And presetting in dictionary is multiple groove position, it is easy to go to extract natural language according to the groove position in default dictionary
Groove position information in the text message of information.For example when the natural language information of user is long, now natural language information pair
The probability that the text message answered hits pre-set commands storehouse is very little, directly can extract groove position therein using default dictionary
Information.Now corresponding step 101 specifically may include steps of:
(a1) according to default dictionary, the content information of extraction tank position from text message;
(a2) content information according to groove position, generates the corresponding operational order of text message.
For example, text message is that " I wants this set meal a, and two portions of that No. two set meals, in addition, I feels
I also needs to have another one can happy two chicken wing ", the groove position that wherein default dictionary includes have " set meal ", " two
Number set meal ", " laughable ", " chicken wing ".The content of the groove position information extracted from text message is " an a set meal, portion two
Number set meal, one glass of cola, two portions of chicken wing ", and corresponding generate operational order be " select an a set meal, No. two set meals of portion, one
Cup is laughable, two portions of chicken wing ".
The process of the text message parsing natural language information according to default dictionary of the present embodiment can be based on
The parsing of dictionary pattern matching, the longest match pattern of dictionary pattern matching is passed through in this parsing, extracts the associated groove position of the current expression of user, and
By the post processing to groove position content, obtain multiple real needs of different intentions, can widely cover the multiformity of user
Statement, the understandability that lift system is expressed to user.
For example:User is under the state of ordering, and describes " I wants one No. two and three No. one ", at this time, it may be necessary to
It is capable of identify that " No. two " and " No. " expressed by user, actually refer to " set meal " and " No. two set meals ", and
The quantity of its association is respectively " 1 " and " 3 ".
In above-described embodiment, it is to parse text message using default command library set and default dictionary respectively.Enter
One step alternatively, can be combined with default command library set and default dictionary realized parsing text message jointly.For example,
Now step 101 specifically may include steps of:
(b1) judge to whether there is the corresponding operational order of text message in default command library set;When it is present, hold
Row step (b2);Otherwise execution step (b3);
(b2) obtain the corresponding operational order of text message from default command library set;
(b3) according to default dictionary, the content information of extraction tank position from text message;
(b4) content information according to groove position, generates the corresponding operational order of text message.
Still optionally further, on the basis of the technical scheme of above-described embodiment, step 103 is " according to operational order with more
Current state after new, generates natural language feedback information " after, also include:Storage current state, text message and nature
Verbal feedback information, to generate conversation content.
Specifically, can store all successively according to each current state in use of user, in order
The corresponding text message of natural language receiving under current state, current state and generation volume natural language feedback information, this
Sample, just obtains all conversation content during all of whole self-help service.Processor module can also be according to dialogue
Current state in content and text message, go to update current state.NLG module can also be according to each in conversation content
Current state after the text message of current state and corresponding renewal, generates natural language feedback information.As such, it is possible to more
It is accurately determined the demand statement of user, thus generating more accurate natural language feedback information.
Still optionally further, on the basis of the technical scheme of above-described embodiment, current state after updating is to pay
During state, the information processing method based on artificial intelligence of the present embodiment can also comprise the steps:
(c1) according to the corresponding operational order of state that confirms an order, obtain payment information;
(c2) show payment information, so that user pays;
(c3) after user pays success, current state is updated to pay status;
(c4) process that places an order is carried out according to the corresponding operational order of state that confirms an order.
Specifically, in actual applications, when user confirms an order, can be according to the operational order of the confirmation of user and right
The current state acknowledgement of orders state answered, current state is updated to pay status by acknowledgement of orders state.Now, based on artificial
The information processor of intelligence can be according to the corresponding operational order of the state of confirming an order, and that is, user confirms to buy which is specifically interior
Hold, calculate the payment of the content that user confirms to buy, and generate payment information.And this disbursement letter is shown by user interface
Breath, for example, can show a Quick Response Code, so that user realizes entering by the payment client terminal of terminal by scanning this Quick Response Code
Row pays.After user pays success, the information processor based on artificial intelligence needs first according to the state pair that confirms an order
The operational order answered carries out the process that places an order, for example, specifically can send, to the server of ordering on backstage, the corresponding operation that confirms an order
Instruction, such as " X user selects an a set meal, a No. two set meals, one glass of cola, two portions of chicken wing ", thus what realization was ordered
Process, X user can be the serial number of the self-service some day of electronic equipment.It is simultaneously based on the information processing of artificial intelligence
Current state is updated to pay success status by device, and according to the successful information of this payment and pays success status, generates certainly
So verbal feedback information such as " you have paid successfully, please arrive pick-up platform waiting pick-up " etc..
The information processing method based on artificial intelligence of above-described embodiment, by adopting technique scheme, it is possible to achieve
Flow process interaction is carried out according to natural language, can avoid only can carrying out flow process interaction using the instruction of solidification in prior art,
Thus enriching the mode of information exchange, increased the motility of information exchange, and due to being carried out using natural language information
The motility of interaction is higher, such that it is able to reduce the error rate of information exchange.
Fig. 3 is the structure chart of the information processor embodiment one based on artificial intelligence of the present invention.As shown in figure 3, this
The information processor based on artificial intelligence of embodiment, specifically includes:Natural language recognition module 10, natural language understanding mould
Block 11, processing module 12 and spatial term module 13.
Wherein natural language recognition module 10 is used for the natural language information of user input is identified, and obtains corresponding
Text message;Natural language understanding module 11 is used for according to default information bank set, parses natural language recognition module 10 and knows
The corresponding operational order of other text message;Processing module 12 is used for current state and natural language understanding module according to user
The operational order of 11 understandings, updates current state;Spatial term module 13 understands according to natural language understanding module 11
Current state after the renewal of operational order and processing module 12 process, generates natural language feedback information.
The information processor based on artificial intelligence of the present embodiment, by realizing the reality of information processing using above-mentioned module
Existing mode and above-mentioned related method embodiment realize principle and technique effect is identical, may be referred to above-mentioned correlation technique in detail
The record of embodiment, will not be described here.
Fig. 4 is the structure chart of the information processor embodiment two based on artificial intelligence of the present invention.As shown in figure 4, this
The information processor based on artificial intelligence of embodiment, on the basis of the technical scheme of above-mentioned embodiment illustrated in fig. 3, enters one
Step introduces technical scheme in further detail.
For example, in the information processor based on artificial intelligence of the present embodiment, natural language understanding module 11 is specifically used
In the acquisition corresponding operational order of text message from default command library set.
Still optionally further, in the information processor based on artificial intelligence of the present embodiment, natural language understanding module
11 are specifically additionally operable to judge to whether there is the corresponding operational order of text message in default command library set;Determine default life
Make in the set of storehouse and there is the corresponding operational order of text message;
Still optionally further, in the information processor based on artificial intelligence of the present embodiment, natural language understanding module
11 are specifically additionally operable to when there is not the corresponding operational order of text message in default command library set, according to default dictionary
Storehouse, the content information of extraction tank position from text message, default dictionary includes multiple groove positions;Content letter according to groove position
Breath, generates the corresponding operational order of text message.
Still optionally further, in the information processor based on artificial intelligence of the present embodiment, natural language understanding module
11 specifically for according to default dictionary, the content information of extraction tank position from text message, and default dictionary includes
Multiple groove positions;According to the content information of groove position, generate the corresponding operational order of text message.
Still optionally further, as shown in figure 4, in the information processor based on artificial intelligence of the present embodiment, also including:
Dialog information memory module 14.Dialog information memory module 14 is used for storing current state, natural language recognition module 10 identifies
Text message and spatial term module 13 generate natural language feedback information, to generate conversation content.Wherein deposit
The current state of storage includes the current state of processing module 12 renewal.
Still optionally further, as shown in figure 4, in the information processor based on artificial intelligence of the present embodiment, also including
Playing module 15 is used for playing spatial term module 13 generation natural language feedback information with natural language.
Still optionally further, as shown in figure 4, in the information processor based on artificial intelligence of the present embodiment, also including
Receiver module 16, this receiver module 16 is used for the natural language information of receiving user's input.Such as this receiver module can be wheat
Gram wind.Natural language recognition module 10 is specifically for knowing to the natural language information of the user input that receiver module 16 receives
, do not obtain corresponding text message
Still optionally further, in the information processor based on artificial intelligence of the present embodiment, current state includes:Prepare
State, tapeout state, the state that confirms an order or pay status.
Still optionally further, as shown in figure 4, in the information processor based on artificial intelligence of the present embodiment, also including
Display module 17.
When wherein processing module 12 is additionally operable to the current state after updating for pay status, according to the state of confirming an order pair
The operational order answered, obtains payment information;Display module 17 is used for the payment information that Display processing module 12 obtains, for user
Pay;Processing module 12 is additionally operable to, after user pays success, current state is updated to pay status;Processing module 12
It is additionally operable to carry out, according to the corresponding operational order of state that confirms an order, the process that places an order.
The information processor based on artificial intelligence of the present embodiment, by realizing the reality of information processing using above-mentioned module
Existing mode and above-mentioned related method embodiment realize principle and technique effect is identical, may be referred to above-mentioned correlation technique in detail
The record of embodiment, will not be described here.
Below taking independently order as a example, technical scheme is discussed in detail.Self-service electricity in following embodiments
Sub- equipment is used for realizing user self-help ordering, the information processing based on artificial intelligence being wherein located in self-service electronic equipment
Device is used for realizing interacting using natural language with user, realizes ordering.For example specifically may include steps of:
(1) self-service electronic equipment is in SBR, and user comes and can input before self-service electronic equipment
Natural language information " you are good, and I wants to order ";
(2) this natural language information is received based on the information processor of artificial intelligence, and be identified as " you of textual form
Good, I wants to order ";And in dialog information memory module real-time storage textual form " you are good, and I wants to order ";
(3), according to the set of pre-set commands storehouse and default dictionary, parsing should for the information processor based on artificial intelligence
The operational order of " you are good, and I wants to order ", be resolved in pre-set commands storehouse have to should bar order, and corresponding operational order is
" preparation is ordered ";
(4) information processor based on artificial intelligence " prepares point according to order state and operational order of current preparation
Meal ", renewal current state to " state of ordering ";And the current state after record updates in dialog information memory module;Certainly,
" SBR " before also record has in dialog information memory module;
(5) information processor based on artificial intelligence can be according to current after operational order " preparation is ordered " and renewal
State " state of ordering ", generates natural language feedback information " may I ask what you need to order ";And in dialog information memory module
The natural language feedback information " may I ask what you need to order " that record generates;
(6) information processor based on artificial intelligence is play natural language feedback information in the form of natural language and " is asked
Ask what you need to order ";
(7) user hears " may I ask what you need to order ", just determines that self-service electronic equipment has been turned on and inlet point meal
State, can order.Now user can input natural language information " I wants a No. five set meals, three glasss of colas, then plus two
Individual drumstickss, a No. two pickles, then plus two portions of No. three set meals ";
(8) natural language information of the information processor receiving user's input based on artificial intelligence, and it is identified as text
" I wants a No. five set meals, three glasss of colas, then plus two drumstickss, a No. two pickles, then plus two portions of No. three set meals ";
(9), according to the set of pre-set commands storehouse and default dictionary, parsing should for the information processor based on artificial intelligence
" I wants a No. five set meals, three glasss of colas, then plus two drumstickss, a No. two pickles, then plus two portions of No. three set meals "
Operational order, after through default dictionary extraction tank position information, generate corresponding operational order be " select two portions of No. three set meals,
A No. five set meals, three glasss of colas, a No. two pickles, two drumstickss ";
(10) information processor based on artificial intelligence is according to current order state and operational order " point two parts No. three
Set meal, a No. five set meals, three glasss of colas, a No. two pickles, two drumstickss " are it is contemplated that next step needs to confirm an order, therefore
Update current state to " confirm an order state ";And the current state after record updates in dialog information memory module;
(11) information processor based on artificial intelligence " can select two parts of No. three set meals, Yi Fenwu according to operational order
Number set meal, three glasss of colas, a No. two pickles, two drumstickss ", and the current state " confirm an order state " after updating, generate
Natural language feedback information " PLSCONFM you select be two portions of No. three set meals, a No. five set meals, three glasss of colas, a No. two little
Dish, two drumstickss ";And record this natural language feedback information of generation in dialog information memory module;
(12) information processor based on artificial intelligence is play natural language feedback information in the form of natural language and " is asked
Confirm that you select is two portions of No. three set meals, a No. five set meals, three glasss of colas, a No. two pickles, two drumstickss ".
(13), after user hears natural language feedback information, find that point is wrong, now can send natural language information
" sorry, point is wrong, and I needs to change order ";
(14) information processor based on artificial intelligence by natural language information be identified as text " sorry, point wrong, I
Need to change order ", and store in dialog information memory module;
(15), according to the set of pre-set commands storehouse and default dictionary, parsing should for the information processor based on artificial intelligence
The operational order of " sorry, point is wrong, and I needs to change order ", being resolved in default dictionary has the groove position of " modification order ",
Generating corresponding operational order is " modification order ";
(16) information processor based on artificial intelligence confirms an order state according to current preparation and operational order " is repaiied
Change list ", renewal current state to " modification order status ";And the current shape after record updates in dialog information memory module
State;
(17) information processor based on artificial intelligence can be according to working as after operational order " modification order " and renewal
Front state " modification order status ", generates natural language feedback information " may I ask which you change ";And store mould in dialog information
This natural language feedback information is stored in block;
(18) information processor based on artificial intelligence is play natural language feedback information in the form of natural language and " is asked
Ask which you change ";
(19), after user hears, natural language feedback information can be inputted and " two portions of No. three set meals please be revised as two
No. two set meals of part ";
(20) receive the natural language information of user input based on the information processor of artificial intelligence, and be identified as literary composition
This " two portions of No. three set meals please be revised as two portions of No. two set meals ", and be stored in dialog information memory module;
(21), according to the set of pre-set commands storehouse and default dictionary, parsing should for the information processor based on artificial intelligence
The operational order of " two portions of No. three set meals please be revised as two portions of No. two set meals ", after through default dictionary extraction tank position letter
Breath, determines that two portions of No. three set meals are revised as two portions of No. two set meals, and generates corresponding operational order;
(22) information processor based on artificial intelligence is according to current state " modification order status " and operational order " two
Portion No. three set meals are revised as two portions of No. two set meals ", determine that next step needs to confirm an order, update current state to " confirming an order
State ";And the current state after record updates in dialog information memory module;
(23) according to operational order, " two portions of No. three set meals are revised as two parts No. two to the information processor based on artificial intelligence
Current state " confirm an order state " after set meal " and renewal, " PLSCONFM is by two parts No. three to generate natural language feedback information
Set meal is revised as two portions of No. two set meals?What so you selected is two portions of No. two set meals, a No. five set meals, three glasss of colas, portions two
Number pickles, two drumstickss ";And record this natural language feedback information of generation in dialog information memory module;
(24) information processor based on artificial intelligence is play natural language feedback information in the form of natural language and " is asked
Confirmation is that two portions of No. three set meals are revised as two portions of No. two set meals?What so you selected be two portions of No. two set meals, a No. five set meals,
Three glasss of colas, a No. two pickles, two drumstickss ";
(25), after user hears natural language feedback information, find to have no problem, natural language information can be inputted
" confirming an order ";
(26) natural language information is identified as text " confirming an order " by the information processor based on artificial intelligence, and
Store in dialog information memory module;
(27), according to the set of pre-set commands storehouse and default dictionary, parsing should for the information processor based on artificial intelligence
The operational order of " confirming an order ", is resolved to corresponding order in the set of pre-set commands storehouse, and gets corresponding operational order
" confirming an order ";
(27) information processor based on artificial intelligence confirms an order state and operational order " really according to current preparation
Recognize order ", renewal current state to " pay status ";And the current state after record updates in dialog information memory module;
(28) information processor based on artificial intelligence can be according to working as after operational order " confirming an order " and renewal
Front state " pay status ", generates natural language feedback information " order has confirmed that, woulds you please pay ";And store mould in dialog information
Store this natural language feedback information in block, and store this natural language feedback information in dialog information memory module;And
Calculate payment and generate payment information according to the content of ordering that the middle user that confirms an order confirms simultaneously.And pass through user interface
Show this payment information, can be such as Quick Response Code;
(29) information processor based on artificial intelligence is play natural language feedback information in the form of natural language and " is ordered
Singly have confirmed that, would you please pay ";
(30) user passes through to scan the Quick Response Code of user interface, completes to pay, the now information processing based on artificial intelligence
Device detects user's payment and completes;Two portions of No. two set meals, portion five " are selected according to the corresponding operational order of the state of confirming an order
Set meal, three glasss of colas, a No. two pickles, two drumstickss " carry out the process that places an order, for example specifically can be to the service of ordering on backstage
Device sends the corresponding operational order that confirms an order, and realizes ordering;The information processor being simultaneously based on artificial intelligence is always according to inspection
The payment successful information of the user measuring and current state " pay status ", current state is updated to " pay status ";
(31) information processor based on artificial intelligence according to the payment successful information of user and pays success status, raw
Become natural language feedback information such as " you have paid successfully, please arrive pick-up platform waiting pick-up ", so complete once self-service ordering.
Wherein be stored with dialog information memory module all dialogues during ordering, and can transfer for during use, or can root
Update default command library set and default dictionary according to conversation content.
In above-described embodiment, tapeout state is refined as " state of ordering " and " modification order status ", other self-help services
Practical application in, other states can also be designed, are advisable with actual scene demand in a word, meet reality according to the actual requirements
The logical sum laws of use of border application, here is no longer illustrated one by one and is reviewed.
It should be understood that disclosed system, apparatus and method, Ke Yitong in several embodiment provided by the present invention
Cross other modes to realize.For example, device embodiment described above is only schematically, for example, the drawing of described unit
Point, only a kind of division of logic function, actual can have other dividing mode when realizing.
The described unit illustrating as separating component can be or may not be physically separate, show as unit
The part showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.The mesh to realize this embodiment scheme for some or all of unit therein can be selected according to the actual needs
's.
In addition, can be integrated in a processing unit in each functional unit in each embodiment of the present invention it is also possible to
It is that unit is individually physically present it is also possible to two or more units are integrated in a unit.Above-mentioned integrated list
Unit both can be to be realized in the form of hardware, it would however also be possible to employ the form that hardware adds SFU software functional unit is realized.
The above-mentioned integrated unit realized in the form of SFU software functional unit, can be stored in an embodied on computer readable and deposit
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions with so that a computer
Equipment (can be personal computer, server, or network equipment etc.) or processor (processor) execution the present invention each
The part steps of embodiment methods described.And aforesaid storage medium includes:USB flash disk, portable hard drive, read only memory (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disc or CD etc. various
Can be with the medium of store program codes.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all essences in the present invention
Within god and principle, any modification, equivalent substitution and improvement done etc., should be included within the scope of protection of the invention.
Claims (18)
1. a kind of information processing method based on artificial intelligence is it is characterised in that methods described includes:
The natural language information of user input is identified, obtains corresponding text message;
According to default information bank set, parse the corresponding operational order of described text message;
Current state according to described user and described operational order, update described current state;
According to the described current state after described operational order and renewal, generate natural language feedback information.
2. method according to claim 1 is it is characterised in that according to default information bank set, parse described text envelope
Cease corresponding operational order, specifically include:
The corresponding operational order of described text message is obtained from default command library set.
3. method according to claim 2 is it is characterised in that obtain described text message from default command library set
Before corresponding operational order, methods described also includes:
Judge to whether there is the corresponding operational order of described text message in described default command library set;
Determine in described default command library set there is the corresponding operational order of described text message;
Further, when there is not the corresponding operational order of described text message in described default command library set, described
Method also includes:
According to default dictionary, the content information of extraction tank position from described text message, wraps in described default dictionary
Include multiple groove positions;
According to the content information of described groove position, generate the corresponding operational order of described text message.
4. method according to claim 1 is it is characterised in that according to default information bank set, parse described text envelope
Cease corresponding operational order, specifically include:
According to default dictionary, the content information of extraction tank position from described text message, wraps in described default dictionary
Include multiple groove positions;
According to the content information of described groove position, generate the corresponding operational order of described text message.
5. according to the arbitrary described method of claim 1-4 it is characterised in that according to described operational order and update after described in
Current state, after generating natural language feedback information, methods described also includes:
Store described current state, described text message and described natural language feedback information, to generate conversation content.
6. according to the arbitrary described method of claim 1-4 it is characterised in that according to described operational order and update after described in
Current state, after generating natural language feedback information, methods described also includes:
Described natural language feedback information is play with natural language.
7. according to the arbitrary described method of claim 1-4 it is characterised in that knowing to the natural language information of user input
, before not obtaining corresponding text message, methods described also includes:
Receive the described natural language information of described user input.
8. according to the arbitrary described method of claim 1-4 it is characterised in that described current state includes:SBR, place an order
State, the state that confirms an order or pay status.
9. method according to claim 8 it is characterised in that when update after described current state be pay status when,
Methods described also includes:
According to the corresponding described operational order of the described state that confirms an order, obtain payment information;
Show described payment information, so that described user pays;
After described user pays success, described current state is updated to pay status;
The process that places an order is carried out according to the corresponding operational order of the described state that confirms an order.
10. a kind of information processor based on artificial intelligence is it is characterised in that described device includes:
Natural language recognition module, for being identified to the natural language information of user input, obtains corresponding text message;
Natural language understanding module, for according to default information bank set, parsing the corresponding operational order of described text message;
Processing module, for the current state according to described user and described operational order, updates described current state;
Spatial term module, according to the described current state after described operational order and renewal, generates natural language feedback
Information.
11. devices according to claim 10 it is characterised in that described natural language understanding module, specifically for from pre-
If command library set in obtain the corresponding operational order of described text message.
12. devices according to claim 11, it is characterised in that described natural language understanding module, are specifically additionally operable to sentence
Whether there is the corresponding operational order of described text message in disconnected described default command library set;Determine described default order
There is the corresponding operational order of described text message in the set of storehouse;
Further, described natural language understanding module, is specifically additionally operable to when there is not institute in described default command library set
When stating the corresponding operational order of text message, according to default dictionary, the content letter of extraction tank position from described text message
Breath, described default dictionary includes multiple groove positions;According to the content information of described groove position, generate described text message and correspond to
Operational order.
13. devices according to claim 10 it is characterised in that described natural language understanding module, specifically for basis
Default dictionary, the content information of extraction tank position from described text message, described default dictionary includes multiple grooves
Position;According to the content information of described groove position, generate the corresponding operational order of described text message.
14. according to the arbitrary described device of claim 10-13 it is characterised in that described device also includes:
Dialog information memory module, for storing described current state, described text message and described natural language feedback letter
Breath, to generate conversation content.
15. according to the arbitrary described device of claim 10-13 it is characterised in that described device also includes:
Playing module, for playing described natural language feedback information with natural language.
16. according to the arbitrary described device of claim 10-13 it is characterised in that described device also includes:
Receiver module, for receiving the described natural language information of described user input.
17. according to the arbitrary described device of claim 10-13 it is characterised in that described current state includes:SBR,
Tapeout state, the state that confirms an order or pay status.
18. devices according to claim 17 are it is characterised in that described device also includes display module:
Described processing module, when being additionally operable to the described current state after updating for pay status, according to the described shape that confirms an order
The corresponding described operational order of state, obtains payment information;
Described display module, for showing described payment information, so that described user pays;
Described processing module, is additionally operable to, after described user pays success, described current state is updated to pay status;
Described processing module, is additionally operable to carry out, according to the corresponding operational order of the described state that confirms an order, the process that places an order.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610806534.2A CN106383872A (en) | 2016-09-06 | 2016-09-06 | Artificial intelligence-based information processing method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610806534.2A CN106383872A (en) | 2016-09-06 | 2016-09-06 | Artificial intelligence-based information processing method and apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106383872A true CN106383872A (en) | 2017-02-08 |
Family
ID=57938056
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610806534.2A Pending CN106383872A (en) | 2016-09-06 | 2016-09-06 | Artificial intelligence-based information processing method and apparatus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106383872A (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846959A (en) * | 2017-04-20 | 2017-06-13 | 成都景中教育软件有限公司 | Voice command and operation teaching aid in the method and device of software |
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 |
CN107180105A (en) * | 2017-06-01 | 2017-09-19 | 北京果毅科技有限公司 | A kind of update method, device and the electronic equipment of the knowledge base of intelligent assistant |
CN107291867A (en) * | 2017-06-13 | 2017-10-24 | 北京百度网讯科技有限公司 | Dialog process method, device, equipment and computer-readable recording medium based on artificial intelligence |
CN107391456A (en) * | 2017-07-19 | 2017-11-24 | 李适真 | A kind of information processing method and device |
CN108804536A (en) * | 2018-05-04 | 2018-11-13 | 科沃斯商用机器人有限公司 | Human-computer dialogue and strategy-generating method, equipment, system and storage medium |
CN108920232A (en) * | 2018-06-20 | 2018-11-30 | 维沃移动通信有限公司 | A kind of processing method and terminal device of target object |
CN109101545A (en) * | 2018-06-29 | 2018-12-28 | 北京百度网讯科技有限公司 | Natural language processing method, apparatus, equipment and medium based on human-computer interaction |
CN109949805A (en) * | 2019-02-21 | 2019-06-28 | 江苏苏宁银行股份有限公司 | Intelligent collection robot and collection method based on intention assessment and finite-state automata |
CN110168535A (en) * | 2017-10-31 | 2019-08-23 | 腾讯科技(深圳)有限公司 | A kind of information processing method and terminal, computer storage medium |
CN110597967A (en) * | 2018-05-23 | 2019-12-20 | 阿里巴巴集团控股有限公司 | Order positioning method and equipment |
CN110599192A (en) * | 2018-05-23 | 2019-12-20 | 阿里巴巴集团控股有限公司 | User order positioning method, device and system |
CN110618944A (en) * | 2019-09-20 | 2019-12-27 | 百度在线网络技术(北京)有限公司 | Device simulation method, device, electronic device and storage medium |
WO2020052370A1 (en) * | 2018-09-10 | 2020-03-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for using self-service, and electronic device |
CN111522933A (en) * | 2020-04-23 | 2020-08-11 | 深圳追一科技有限公司 | Conversation process control method, device, equipment and medium |
CN111581919A (en) * | 2020-04-02 | 2020-08-25 | 联想(北京)有限公司 | Task processing method and device |
CN111652694A (en) * | 2020-06-10 | 2020-09-11 | 北京字节跳动网络技术有限公司 | Order processing method and device and electronic equipment |
WO2020232617A1 (en) * | 2019-05-20 | 2020-11-26 | 深圳市欢太科技有限公司 | Voice information processing method and apparatus, and electronic device and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102880649A (en) * | 2012-08-27 | 2013-01-16 | 北京搜狗信息服务有限公司 | Individualized information processing method and system |
CN104123650A (en) * | 2013-04-26 | 2014-10-29 | 腾讯科技(深圳)有限公司 | Text operation instruction recognition processing method for network transaction system and system thereof |
CN104281565A (en) * | 2014-09-30 | 2015-01-14 | 百度在线网络技术(北京)有限公司 | Semantic dictionary constructing method and device |
CN104484377A (en) * | 2014-12-09 | 2015-04-01 | 百度在线网络技术(北京)有限公司 | Generating method and device of substitute dictionaries |
CN105183850A (en) * | 2015-09-07 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Information querying method and device based on artificial intelligence |
CN105894405A (en) * | 2016-04-25 | 2016-08-24 | 百度在线网络技术(北京)有限公司 | Ordering interactive system and method based on artificial intelligence |
-
2016
- 2016-09-06 CN CN201610806534.2A patent/CN106383872A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102880649A (en) * | 2012-08-27 | 2013-01-16 | 北京搜狗信息服务有限公司 | Individualized information processing method and system |
CN104123650A (en) * | 2013-04-26 | 2014-10-29 | 腾讯科技(深圳)有限公司 | Text operation instruction recognition processing method for network transaction system and system thereof |
CN104281565A (en) * | 2014-09-30 | 2015-01-14 | 百度在线网络技术(北京)有限公司 | Semantic dictionary constructing method and device |
CN104484377A (en) * | 2014-12-09 | 2015-04-01 | 百度在线网络技术(北京)有限公司 | Generating method and device of substitute dictionaries |
CN105183850A (en) * | 2015-09-07 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Information querying method and device based on artificial intelligence |
CN105894405A (en) * | 2016-04-25 | 2016-08-24 | 百度在线网络技术(北京)有限公司 | Ordering interactive system and method based on artificial intelligence |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN106846959A (en) * | 2017-04-20 | 2017-06-13 | 成都景中教育软件有限公司 | Voice command and operation teaching aid in the method and device of software |
CN107180105A (en) * | 2017-06-01 | 2017-09-19 | 北京果毅科技有限公司 | A kind of update method, device and the electronic equipment of the knowledge base of intelligent assistant |
CN107291867A (en) * | 2017-06-13 | 2017-10-24 | 北京百度网讯科技有限公司 | Dialog process method, device, equipment and computer-readable recording medium based on artificial intelligence |
CN107391456A (en) * | 2017-07-19 | 2017-11-24 | 李适真 | A kind of information processing method and device |
US11645517B2 (en) | 2017-10-31 | 2023-05-09 | Tencent Technology (Shenzhen) Company Limited | Information processing method and terminal, and computer storage medium |
CN110168535A (en) * | 2017-10-31 | 2019-08-23 | 腾讯科技(深圳)有限公司 | A kind of information processing method and terminal, computer storage medium |
CN110168535B (en) * | 2017-10-31 | 2021-07-09 | 腾讯科技(深圳)有限公司 | Information processing method and terminal, computer storage medium |
CN108804536A (en) * | 2018-05-04 | 2018-11-13 | 科沃斯商用机器人有限公司 | Human-computer dialogue and strategy-generating method, equipment, system and storage medium |
CN110597967A (en) * | 2018-05-23 | 2019-12-20 | 阿里巴巴集团控股有限公司 | Order positioning method and equipment |
CN110599192A (en) * | 2018-05-23 | 2019-12-20 | 阿里巴巴集团控股有限公司 | User order positioning method, device and system |
CN110597967B (en) * | 2018-05-23 | 2023-04-18 | 阿里巴巴集团控股有限公司 | Order positioning method and equipment |
CN108920232A (en) * | 2018-06-20 | 2018-11-30 | 维沃移动通信有限公司 | A kind of processing method and terminal device of target object |
CN108920232B (en) * | 2018-06-20 | 2021-06-22 | 维沃移动通信有限公司 | Target object processing method and terminal equipment |
CN109101545A (en) * | 2018-06-29 | 2018-12-28 | 北京百度网讯科技有限公司 | Natural language processing method, apparatus, equipment and medium based on human-computer interaction |
WO2020052370A1 (en) * | 2018-09-10 | 2020-03-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for using self-service, and electronic device |
CN109949805B (en) * | 2019-02-21 | 2021-03-23 | 江苏苏宁银行股份有限公司 | Intelligent collection urging robot based on intention recognition and finite state automaton and collection urging method |
CN109949805A (en) * | 2019-02-21 | 2019-06-28 | 江苏苏宁银行股份有限公司 | Intelligent collection robot and collection method based on intention assessment and finite-state automata |
WO2020232617A1 (en) * | 2019-05-20 | 2020-11-26 | 深圳市欢太科技有限公司 | Voice information processing method and apparatus, and electronic device and storage medium |
CN110618944A (en) * | 2019-09-20 | 2019-12-27 | 百度在线网络技术(北京)有限公司 | Device simulation method, device, electronic device and storage medium |
CN111581919A (en) * | 2020-04-02 | 2020-08-25 | 联想(北京)有限公司 | Task processing method and device |
CN111581919B (en) * | 2020-04-02 | 2023-07-21 | 联想(北京)有限公司 | Task processing method and device |
CN111522933A (en) * | 2020-04-23 | 2020-08-11 | 深圳追一科技有限公司 | Conversation process control method, device, equipment and medium |
CN111652694A (en) * | 2020-06-10 | 2020-09-11 | 北京字节跳动网络技术有限公司 | Order processing method and device and electronic equipment |
CN111652694B (en) * | 2020-06-10 | 2023-04-07 | 北京字节跳动网络技术有限公司 | Order processing method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106383872A (en) | Artificial intelligence-based information processing method and apparatus | |
US7386440B2 (en) | Method, system, and apparatus for natural language mixed-initiative dialogue processing | |
US20190130912A1 (en) | Generic virtual personal assistant platform | |
CN110838288B (en) | Voice interaction method and system and dialogue equipment | |
CN105723362B (en) | Naturally processing method, processing and response method, equipment and system are expressed | |
US8001469B2 (en) | Automatic generation of interactive systems from a formalized description language | |
CN110069789A (en) | The method, system and computer program product that data processing equipment is implemented | |
US8155959B2 (en) | Dialog system for human agent to correct abnormal output | |
CN109101545A (en) | Natural language processing method, apparatus, equipment and medium based on human-computer interaction | |
CN109002501A (en) | For handling method, apparatus, electronic equipment and the computer readable storage medium of natural language dialogue | |
CN109543010A (en) | The interactive method and system of fused data library inquiry | |
CN109902957A (en) | A kind of data processing method and device | |
CN107291867A (en) | Dialog process method, device, equipment and computer-readable recording medium based on artificial intelligence | |
AU2011274318A1 (en) | System and method of providing a computer-generated response | |
CN109325091A (en) | Update method, device, equipment and the medium of points of interest attribute information | |
CN110059166A (en) | Natural expression processing method, response method, equipment and the system of natural intelligence | |
CN109739605A (en) | The method and apparatus for generating information | |
CN108628908A (en) | The method, apparatus and electronic equipment of sorted users challenge-response boundary | |
CN106558309A (en) | A kind of spoken dialog strategy-generating method and spoken dialog method | |
CN116562807A (en) | Robot flow automation method, device, electronic equipment and storage medium | |
CN112947902A (en) | System development management platform | |
CN110059167A (en) | Natural expression processing method, response method, equipment and the system of natural intelligence | |
CN110008317A (en) | Natural expression processing method, response method, equipment and the system of natural intelligence | |
CN114490994B (en) | Conversation management method and device | |
CN112487817A (en) | Named entity recognition model training method, sample labeling method, device and equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170208 |
|
RJ01 | Rejection of invention patent application after publication |