CN108491394A - A kind of semantic analysis, device, computer equipment and storage medium - Google Patents
A kind of semantic analysis, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN108491394A CN108491394A CN201810677959.7A CN201810677959A CN108491394A CN 108491394 A CN108491394 A CN 108491394A CN 201810677959 A CN201810677959 A CN 201810677959A CN 108491394 A CN108491394 A CN 108491394A
- Authority
- CN
- China
- Prior art keywords
- machine people
- regulation engine
- semantic
- described problem
- answer
- 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
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The embodiment of the invention discloses a kind of semantic analysis, device, computer equipment and storage medium, the method includes：The problem of user puts question to is obtained, described problem is sent to the semantic machine people of the application server；The semantic machine people classifies to described problem；And classification results and described problem are sent to the regulation engine of the application server；The regulation engine analyzes described problem according to the classification results, to determine problem types, and is fed back to the semantic machine people according to described problem type；The semantic machine people or the regulation engine export matched answer according to described problem type.The technical solution of the embodiment of the present invention realizes the question and answer service for providing differentiation, to improve reasonability and the accuracy of output answer, and then promotes user experience.
Description
Technical field
The present embodiments relate to natural language understanding technology field more particularly to a kind of semantic analysis, device, meters
Calculate machine equipment and storage medium.
Background technology
Semantic machine people has human-computer dialogue ability, is capable of providing the services such as semantic understanding, intelligent answer, task dialogue,
It is widely applied to various fields.
Inventor in the implementation of the present invention, it is found that there are following defects by existing semantic machine people：
Existing semantic machine people usually intelligently answers for common question, i.e., is provided for certain a kind of problem general
Answer, and general answer is also stereotyped, can not be directed to concrete scene or particular user is treated with a certain discrimination.Therefore, existing
Semantic machine people cannot achieve customization.For example, the user arrived involved in electric business system at this stage seeks advice from order return question,
For different scenes, different orders and different order status, different reimbursement modes and reimbursement channel are actually corresponded to.It is existing
Some semantic machine people can not accomplish to provide personalized answer for concrete scene or order status etc..
Invention content
A kind of semantic analysis of offer of the embodiment of the present invention, device, computer equipment and storage medium realize that offer is poor
The question and answer service of alienation to improve reasonability and the accuracy of output answer, and then promotes user experience.
In a first aspect, an embodiment of the present invention provides a kind of semantic analysis, it is applied to application server, the method
Including：
The problem of user puts question to is obtained, described problem is sent to the semantic machine people of the application server；
The semantic machine people classifies to described problem；And classification results and described problem are sent to the application
The regulation engine of server；
The regulation engine analyzes described problem according to the classification results, to determine problem types, and foundation
Described problem type is fed back to the semantic machine people；
The semantic machine people or the regulation engine export matched answer according to described problem type.
Second aspect, the embodiment of the present invention additionally provide a kind of semantic analysis device, are configured at application server, the dress
Set including：
Described problem is sent to the application server by problem acquisition module for obtaining the problem of user puts question to
Semantic machine people；
Semantic machine people, for classifying to described problem；And classification results and described problem are sent to described answer
With the regulation engine of server；
Regulation engine, for being analyzed described problem according to the classification results, to determine problem types, and foundation
Described problem type is fed back to the semantic machine people；
The semantic machine people or the regulation engine are additionally operable to export matched answer according to described problem type.
The third aspect, the embodiment of the present invention additionally provide a kind of computer equipment, and the computer equipment includes：
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors so that one or more of processing
Device realizes the semantic analysis that any embodiment of the present invention is provided.
Fourth aspect, the embodiment of the present invention additionally provide a kind of computer storage media, are stored thereon with computer program,
The semantic analysis that any embodiment of the present invention is provided is realized when the program is executed by processor.
The problem of embodiment of the present invention is by obtaining user's enquirement and the semantic machine people for being sent to application server, so that
Semantic machine people classifies to problem.Then, classification results and problem are uniformly sent to application server by semantic machine people
Regulation engine, regulation engine can be analyzed under different classification results for each problem, so that it is determined that specifically
Problem types, regulation engine are selectively fed back to semantic machine people according to different problems type；Finally by semantic machine
Device people or regulation engine export matched answer according to problem types, and common question can only be directed to by solving existing semantic machine people
The problem of being answered realizes the question and answer service for providing differentiation, to improve reasonability and the accuracy of output answer, in turn
Promote user experience.
Description of the drawings
Fig. 1 is a kind of flow chart for semantic analysis that the embodiment of the present invention one provides；
Fig. 2 a are a kind of flow charts of semantic analysis provided by Embodiment 2 of the present invention；
Fig. 2 b are the configuration diagram of the semantic machine people and regulation engine involved by the embodiment of the present invention two；
Fig. 3 is a kind of schematic diagram for semantic analysis device that the embodiment of the present invention three provides；
Fig. 4 is a kind of structural schematic diagram for computer equipment that the embodiment of the present invention four provides.
Specific implementation mode
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limitation of the invention.
It also should be noted that only the parts related to the present invention are shown for ease of description, in attached drawing rather than
Full content.It should be mentioned that some exemplary embodiments are described before exemplary embodiment is discussed in greater detail
At the processing or method described as flow chart.Although operations (or step) are described as the processing of sequence by flow chart,
It is that many of which operation can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of operations can be by again
It arranges.The processing can be terminated when its operations are completed, it is also possible to the additional step being not included in attached drawing.
The processing can correspond to method, function, regulation, subroutine, subprogram etc..
Embodiment one
Fig. 1 is a kind of flow chart for semantic analysis that the embodiment of the present invention one provides, and the present embodiment is applicable to pair
The problem of user puts question to carries out the case where difference analysis, and this method can be executed by semantic analysis device, which can be with
It is realized by the mode of software and/or hardware, and can generally be integrated in computer equipment (typical, such as all kinds of servers)
In, it is used cooperatively with the client for completing semantic analysis function, correspondingly, as shown in Figure 1, this method includes following behaviour
Make：
S110, the problem of user puts question to is obtained, described problem is sent to the semantic machine people of the application server.
Wherein, semantic machine people refers to realize natural language the program or entity of semantic understanding.For example, semantic
Robot can be in internet for realizing the artificial intelligence of the e-commerce links such as the pre-sales consulting of offer or after-sale service
Can system, by natural language processing, deep neural network, machine learning, user's portrait and the technologies such as natural language processing,
It can complete round-the-clock and an unbounded quantity of user service.Alternatively, semantic machine people, which can also be, has artificial intelligence conversational system
Entity, such as all kinds of intelligent robots.Intelligent robot usually has the intelligence similar to people, it is equipped with highly sensitive biography
Sensor, thus there is the ability of the vision more than common people, the sense of hearing, smell, tactile, the information of perception can be analyzed, be controlled
Various complicated, the difficult tasks given are completed in factum processed, the variation that processing environment occurs.And have self-teaching,
It concludes, summarize, improve the ability for having grasped knowledge.Optionally, the semantic machine people in the embodiment of the present invention can be with artificial intelligence
The mode of energy system is integrated in the application server.
In embodiments of the present invention, before carrying out analysis answer the problem of puing question to user, it is necessary first to obtain user
The problem of enquirement.Optionally, the mode that word or voice input may be used obtains the problem of user puts question to.It is provided to realize
Differentiation question and answer service will can be sent to semantic machine people the problem of acquisition first, one is carried out to problem by semantic machine people
A preliminary analysis.
S120, the semantic machine people classify to described problem；And classification results and described problem are sent to institute
State the regulation engine of application server.
Correspondingly, after semantic machine people receives the problem of user puts question to, problem is carried out according to default knowledge base preliminary
Classification is to obtain classification results.It should be noted that whether the classification that semantic machine people carries out problem is not related to difference problem
For personalized question, and only problem fields are divided.For example, the problem of user puts question to belongs to field " after sale ".
It after semantic machine people gets classification results, needs classification results and problem being uniformly sent to regulation engine, so that it is carried out
Deep analysis is carried out to problem.
Illustratively, the problem of user puts question to is " how this thing moves back", then semantic machine people receives the problem
Afterwards, the problem is analyzed and is classified according to default knowledge base, the classification results for obtaining the problem are " merchandise return ".
S130, the regulation engine analyze described problem according to the classification results, to determine problem types, and
It is fed back to the semantic machine people according to described problem type.
Wherein, problem types are the types distinguished to problem according to actual demand, for example, problem types can be
Property problem and impersonal theory problem.Problem types include at least two different types.
In embodiments of the present invention, problem is further divided according to the classification results got by regulation engine
Analysis, so that it is determined that the corresponding problem types of problem.For different problems type, different processing may be used in application server
Mode.Therefore, regulation engine needs to handle type feedback the problem of its not responsible processing to semantic machine people.
S140, the semantic machine people or the regulation engine export matched answer according to described problem type.
Correspondingly, semantic machine people and regulation engine can be directed to different problems type, output is respectively matched respectively
Answer is avoided only to realize the analysis and processing that are carried out stratification to same problem using semantic machine people and regulation engine
Unified answer is exported for common question by default knowledge base by semantic machine people, and then improves application server output
The reasonability of answer and accuracy, and promote user experience.
The problem of embodiment of the present invention is by obtaining user's enquirement and the semantic machine people for being sent to application server, so that
Semantic machine people classifies to problem.Then, classification results and problem are uniformly sent to application server by semantic machine people
Regulation engine, regulation engine can be analyzed under different classification results for each problem, so that it is determined that specifically
Problem types, regulation engine are selectively fed back to semantic machine people according to different problems type；Finally by semantic machine
Device people or regulation engine export matched answer according to problem types, and common question can only be directed to by solving existing semantic machine people
The problem of being answered realizes the question and answer service for providing differentiation, to improve reasonability and the accuracy of output answer, in turn
Promote user experience.
Embodiment two
Fig. 2 a are a kind of flow charts of semantic analysis provided by Embodiment 2 of the present invention.The present embodiment is with above-mentioned implementation
It is embodied based on example, is specially first problem type and Second Problem type by problem types in the present embodiment, and
Give the realization method that specific aim processing is carried out according to different problems type.Correspondingly, as shown in Figure 2 a, the present embodiment
Method may include：
S210, the problem of user puts question to is obtained, described problem is sent to the semantic machine people of the application server.
In an alternate embodiment of the present invention where, the problem of user puts question to is being obtained, described problem is sent to semanteme
Before robot, further include：It obtains and presets the problems in knowledge base classification information, classification gauge is obtained according to the classification information
Then, and the classifying rules regulation engine is sent to synchronize.
Wherein, default knowledge base is that the knowledge base system of semantic understanding knowledge is provided for semantic machine people.Default knowledge base
It can obtain the text data of magnanimity from network by using the method for network mass data semantic understanding, cleaned, gone
After the operation of noise, using the semantic understanding technology in natural language, the keyword per data is obtained, the crucial of context is believed
Breath builds the mode of accurately syntax tree structure to construct for every data.In addition, default knowledge base can also be realized periodically more
Newly with maintenance, to guarantee to provide the service to grow with each passing hour to the user.In embodiments of the present invention, knowledge base is preset may be used also
With storage problem classification information.Regulation engine is a kind of component of insertion in the application server, realize by operational decision making from
It is separated in application code, and operational decision making is write using predefined semantic modules.Regulation engine can receive number
According to input, business rule is explained, and operational decision making is made according to business rule.Classifying rules can be according in default knowledge base
Including the problem of classification information carry out the business rule of self-defined setting.Under different application scenarios, classifying rules is also not to the utmost
It is identical.In embodiments of the present invention, whether the problem of classifying rules can be used for puing question to problem is that personalized question is divided
Class.
In embodiments of the present invention, it in order to realize the cooperative cooperating of semantic machine people and regulation engine, is putd question to user
The problem of carry out differentiation answer before, can safeguard different classifying rules from the problems in default knowledge base classification information.
Each Question Classification can correspond at least a set of classifying rules, and classifying rules, which needs to be sent to regulation engine, to be synchronized, with
The problem of alloing regulation engine to be putd question to user according to classifying rules, is analyzed.Optionally, classifying rules can be directed to tool
Body application scenarios (such as electric business) and user related information (such as user identity, order status or physical state) are formulated.
In an alternate embodiment of the present invention where, the semantic machine people and the regulation engine share described preset and know
Know library.
It should be noted that when regulation engine exports problem answers, it is also desirable to the support according to knowledge base.Therefore, in order to
Carrying cost and development cost are reduced, semantic machine people and regulation engine can be made to share default knowledge base.
In an alternate embodiment of the present invention where, the classifying rules is obtained by customized mode；Or
The classifying rules is obtained by default training pattern.
Wherein, default training pattern can be the mass data sample for including using default knowledge base, be instructed by model
Practice the correlation function that method (such as optimal method) determines.
In embodiments of the present invention, classifying rules can be obtained by two ways：First, it can directly use self-defined
Mode formulate corresponding classifying rules according to the data preset in knowledge base；Second, it can also be by default knowledge base
Data sample carries out model training, to obtain default training pattern, and obtains classifying rules by default training pattern.Certainly,
Those skilled in the art can also establish other and obtain classification gauge according to actual demand, under the technical background of the technical program
Mode then, the embodiment of the present invention is to this and is not limited.
Fig. 2 b are the configuration diagram of the semantic machine people and regulation engine involved by the embodiment of the present invention two.Such as Fig. 2 b institutes
Show, in application server 20, semantic machine people 201 and regulation engine 202 can realize interaction, semantic machine people in inside
201 may be implemented the operations such as semantic analysis, Question Classification and default knowledge storehouse matching.Regulation engine 202 can complete regular pipe
The operations such as reason, regular operation, rule parsing and rule match, wherein the corresponding classifying rules of regulation engine can be stored in rule
Then in library 203.Meanwhile semantic machine people and regulation engine can share default knowledge base 204.
S220, the semantic machine people classify to described problem；And classification results and described problem are sent to institute
State the regulation engine of application server.
S230, the regulation engine judge whether described problem type is first problem type, if so, S240 is executed,
Otherwise, S250 is executed.
Wherein, first problem type can be personalized question type, correspondingly, Second Problem type can be with right and wrong individual character
Change problem.
In embodiments of the present invention, regulation engine according in the classification results decision problem received whether there is classification gauge
Then.The problem of storing classifying rules as personalized question, the problem of classifying rules is not present as impersonal theory problem.
If S240, the regulation engine determine that described problem type is first problem type, drawn by the rule
It holds up and analyzing processing is carried out to described problem, and export treated answer.
Correspondingly, when regulation engine determines that problem types are personalized question type, can continue to be directed to by regulation engine
Personalized question is further processed.
Correspondingly, carrying out analyzing processing to described problem by the regulation engine, and treated answer is exported, specifically
May include：
S241, judge whether described problem needs take turns to interact more, if so, executing S242, otherwise, execute S243.
Specifically, when carrying out analyzing processing to problem by regulation engine, can be judged by regulation engine personalized
Whether problem needs take turns to answer more.And it is carried out respectively again for the personalized question for needing more wheels to answer and need not take turns more answer
Processing.It can be seen that the embodiment of the present invention is in addition to may be implemented to answer the differentiation of personalized question, it can also be further real
Answer mostly now is taken turns to the differentiation for needing the personalized question of more wheel interactions.
S242, the more wheel question and answer of output interact answer.
Correspondingly, if regulation engine determines that personalized question needs more wheel question and answer, often taken turns for the output of more wheel problems
Interaction answer.The problem of by realizing the support to more taking turns dialogue, puing question to user, carries out semantic analysis and rule match
Deng, and then provide final reasonable answer to the user, to allow user more to have sense of participation.
S243, output setting answer.
Wherein, setting answer can be the related letter of the application scenarios and active user that are related to for personalized question
The formulated customization answer of breath.For example, setting answer can be " since the current logistics information of the commodity of your purchase shows you
It has been signed for that, therefore, you need selection ' to return goods, reimbursement ' option.”
Correspondingly, if regulation engine determines that personalized question need not take turns question and answer more, it is directed to single-wheel personalized question
Export the setting answer pre-established.
If S250, the regulation engine determine that described problem type is Second Problem type, by described problem type
The semantic machine people is fed back to, and general answer is exported by the semantic machine people.
Correspondingly, when regulation engine determines that problem types are impersonal theory problem types, problem types can be fed back
Semantic machine people is given, general answer is directly exported for the problem by semantic machine people.
In a specific example, it is assumed that by application server be electric business system service, then application server obtain
" thing that I buys has been delivered but there is presently no receive cargo, if can select only to move back for the problem of being putd question to user
Money" after, which is sent to semantic machine people.Semantic machine people receives the problem, and classifies to it, is classified
As a result it is " return of goods ", and " thing that I buys has been delivered but there is presently no receive goods by classification results " return of goods " and problem
Object, if only reimbursement can be selected" uniformly it is sent to regulation engine.Regulation engine is using the classifying rules root pre-defined
Problem is analyzed according to the classification results " return of goods " of reception, determines the case where problem is related to only reimbursement, and according to this
User's correlation logistics information get commodity that user is bought do not signed for by user also (namely commodity are unreceipted can only reimbursement
Classifying rules).The problem of then regulation engine can will receive be determined as personalized question, and by regulation engine to the problem into
One step is analyzed, and judges whether it needs to carry out more wheel question and answer.If it is determined that needing more wheel question and answer, then the more wheels of regulation engine output are asked
Answer interactive answer.After receiving the problem such as regulation engine, judge that it may need more wheel problems, then the output first round hands over first
Mutual answer " can with ".Then, user continues to put question to " if having applied for only reimbursement, subsequently also what if receive commodityNeed me certainly
Oneself retracts at the expense of shipping", then regulation engine can export the second wheel interaction answer and " not need, you only need to refuse to sign for i.e.
Can ".
In another specific example, it is assumed that by application server be electric business system service, then application server
Getting the problem of user puts question to, " how discount coupon is handled after returning goods successfully" after, which is sent to semantic machine people.Language
Adopted robot receives the problem, and classifies to it, and it is " discount coupon handling return " to obtain classification results, and by classification results
" after sale " and problem " discount coupon handling return " is uniformly sent to regulation engine.Regulation engine is using the classification gauge pre-defined
Then problem is analyzed according to the classification results of reception " after sale ", determines that matched classifying rules is not present in the problem, then will
The problem is determined as impersonal theory problem, and gives type feedback the problem of the problem to semantic machine people.It should be noted that language
Adopted robot is matched general in the default knowledge base of random position after being classified to obtain classification results to problem, while also
Answer.Therefore, after semantic machine people receives the feedbacks of problem types, general answer can be directly inputted, such as output " is returned goods successfully
And after seller acknowledges receipt of return of goods commodity, discount coupon can be immediately returned in your account ".
The embodiment of the present invention exports general answer by using semantic machine people for impersonal theory problem, is drawn using rule
It holds up for personalized question output setting answer or more wheel question and answer interaction answers, realizes the question and answer service that differentiation is provided, from
And reasonability and the accuracy of output answer are improved, and then promote user experience.
Embodiment three
Fig. 3 is a kind of schematic diagram for semantic analysis device that the embodiment of the present invention three provides, as shown in figure 3, described device
Including：Problem acquisition module 310, semantic machine people 320 and regulation engine 330, wherein：
Described problem is sent to the application server by problem acquisition module 310 for obtaining the problem of user puts question to
Semantic machine people 320；
Semantic machine people 320, for classifying to described problem；And classification results and described problem are sent to described
The regulation engine 330 of application server；
Regulation engine 330, for being analyzed described problem according to the classification results, to determine problem types, and
It is fed back to semantic machine people 320 according to described problem type；
Semantic machine people 320 or regulation engine 330 are additionally operable to export matched answer according to described problem type.
The problem of embodiment of the present invention is by obtaining user's enquirement and the semantic machine people for being sent to application server, so that
Semantic machine people classifies to problem.Then, classification results and problem are uniformly sent to application server by semantic machine people
Regulation engine, regulation engine can be analyzed under different classification results for each problem, so that it is determined that specifically
Problem types, regulation engine are selectively fed back to semantic machine people according to different problems type；Finally by semantic machine
Device people or regulation engine export matched answer according to problem types, and common question can only be directed to by solving existing semantic machine people
The problem of being answered realizes the question and answer service for providing differentiation, to improve reasonability and the accuracy of output answer, in turn
Promote user experience.
Optionally, described problem type includes first problem type and Second Problem type；Regulation engine 330, is additionally operable to
When described problem type is Second Problem type, the Second Problem type is fed back to the semantic machine people.
Optionally, if regulation engine 330 determines that described problem type is first problem type, pass through regulation engine
330 pairs of described problems carry out analyzing processings, and the answer that exports that treated；If regulation engine 330 determines described problem type
For Second Problem type, then by described problem type feedback to semantic machine people 320, and is exported and led to by semantic machine people 330
Use answer.
Optionally, described device further includes：Synchronizing information module, for obtaining the problems in default knowledge base classification letter
Breath obtains classifying rules according to the classification information, and the classifying rules is sent to regulation engine 330 and is synchronized.
Optionally, if regulation engine 330 determines that described problem needs more wheel interactions, more wheel question and answer interactions is exported and are answered
Case；If regulation engine 330 determines that described problem need not take turns interaction more, setting answer is exported.
Optionally, semantic machine people 320 and regulation engine 330 share the default knowledge base.
Optionally, the classifying rules is obtained by customized mode；Or
The classifying rules is obtained by default training pattern.
Above-mentioned semantic analysis device can perform the semantic analysis that any embodiment of the present invention is provided, and have the side of execution
The corresponding function module of method and advantageous effect.The not technical detail of detailed description in the present embodiment, reference can be made to the present invention is arbitrary
The semantic analysis that embodiment provides.
Example IV
Fig. 4 is a kind of structural schematic diagram for computer equipment that the embodiment of the present invention four provides.Fig. 4 is shown suitable for being used for
Realize the block diagram of the computer equipment 412 of embodiment of the present invention.The computer equipment 412 that Fig. 4 is shown is only an example,
Any restrictions should not be brought to the function and use scope of the embodiment of the present invention.Computer equipment 412 typically undertakes service
The computing device of device function.
As shown in figure 4, computer equipment 412 is showed in the form of universal computing device.The component of computer equipment 412 can
To include but not limited to：One or more processor 416, storage device 428, connection different system component (including storage dress
Set 428 and processor 416) bus 418.
Bus 418 indicates one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using the arbitrary bus structures in a variety of bus structures.It lifts
For example, these architectures include but not limited to industry standard architecture (Industry Standard
Architecture, ISA) bus, microchannel architecture (Micro Channel Architecture, MCA) bus, enhancing
Type isa bus, Video Electronics Standards Association (Video Electronics Standards Association, VESA) local
Bus and peripheral component interconnection (Peripheral Component Interconnect, PCI) bus.
Computer equipment 412 typically comprises a variety of computer system readable media.These media can be it is any can
The usable medium accessed by computer equipment 412, including volatile and non-volatile media, moveable and immovable Jie
Matter.
Storage device 428 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (Random Access Memory, RAM) 430 and/or cache memory 432.Computer equipment 412 can be into
One step includes other removable/nonremovable, volatile/non-volatile computer system storage mediums.Only as an example, it deposits
Storage system 434 can be used for reading and writing immovable, non-volatile magnetic media, and (Fig. 4 do not show, commonly referred to as " hard drive
Device ").Although not shown in fig 4, it can provide for being driven to the disk for moving non-volatile magnetic disk (such as " floppy disk ") read-write
Dynamic device, and to removable anonvolatile optical disk (such as CD-ROM (Compact Disc-Read Only Memory, CD-
ROM), digital video disk (Digital Video Disc-Read Only Memory, DVD-ROM) or other optical mediums) read-write
CD drive.In these cases, each driver can pass through one or more data media interfaces and bus 418
It is connected.Storage device 428 may include at least one program product, which has one group of (for example, at least one) program
Module, these program modules are configured to perform the function of various embodiments of the present invention.
Program 436 with one group of (at least one) program module 426 can be stored in such as storage device 428, this
The program module 426 of sample includes but not limited to operating system, one or more application program, other program modules and program
Data may include the realization of network environment in each or certain combination in these examples.Program module 426 usually executes
Function in embodiment described in the invention and/or method.
Computer equipment 412 can also with one or more external equipments 414 (such as keyboard, sensing equipment, camera,
Display 424 etc.) communication, the equipment interacted with the computer equipment 412 communication can be also enabled a user to one or more,
And/or with enable any equipment that the computer equipment 412 communicated with one or more of the other computing device (such as net
Card, modem etc.) communication.This communication can be carried out by input/output (I/O) interface 422.Also, computer
Equipment 412 can also pass through network adapter 420 and one or more network (such as LAN (Local Area
Network, LAN), wide area network Wide Area Network, WAN) and/or public network, such as internet) communication.As schemed
Show, network adapter 420 is communicated by bus 418 with other modules of computer equipment 412.Although should be understood that in figure not
It shows, other hardware and/or software module can be used in conjunction with computer equipment 412, including but not limited to：Microcode, equipment
Driver, redundant processing unit, external disk drive array, disk array (Redundant Arrays of Independent
Disks, RAID) system, tape drive and data backup storage system etc..
Processor 416 is stored in the program in storage device 428 by operation, to perform various functions application and number
According to processing, such as realize the semantic analysis that the above embodiment of the present invention is provided.
That is, the processing unit is realized when executing described program：The problem of user puts question to is obtained, described problem is sent
To the semantic machine people of the application server；The semantic machine people classifies to described problem；And by classification results and
Described problem is sent to the regulation engine of the application server；The regulation engine is according to the classification results to described problem
It is analyzed, to determine problem types, and is fed back to the semantic machine people according to described problem type；The semanteme machine
Device people or the regulation engine export matched answer according to described problem type.
The problem of user puts question to is obtained by the computer equipment and is sent to the semantic machine people of application server, with
Semantic machine people is set to classify problem.Then, classification results and problem are uniformly sent to application service by semantic machine people
The regulation engine of device, regulation engine can be analyzed under different classification results for each problem, so that it is determined that specifically
The problem of type, regulation engine selectively feeds back to semantic machine people according to different problems type；Finally by semanteme
Robot or regulation engine export matched answer according to problem types, and general ask can only be directed to by solving existing semantic machine people
The problem of topic is answered realizes the question and answer service for providing differentiation, to improve reasonability and the accuracy of output answer, into
And promote user experience.
Embodiment five
The embodiment of the present invention five also provides a kind of computer storage media of storage computer program, the computer program
When being executed by computer processor for executing any semantic analysis of the above embodiment of the present invention：Obtain user
Described problem is sent to the semantic machine people of the application server by the problem of enquirement；The semantic machine people asks described
Topic is classified；And classification results and described problem are sent to the regulation engine of the application server；The regulation engine
Described problem is analyzed according to the classification results, to determine problem types, and according to described problem type to institute's predicate
Adopted robot is fed back；The semantic machine people or the regulation engine export matched answer according to described problem type.
The arbitrary of one or more computer-readable media may be used in the computer storage media of the embodiment of the present invention
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or the arbitrary above combination.The more specific example (non exhaustive list) of computer readable storage medium includes：Tool
There are one or the electrical connection of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory
(Read Only Memory, ROM), erasable programmable read only memory ((Erasable Programmable Read
Only Memory, EPROM) or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic
Memory device or above-mentioned any appropriate combination.In this document, can be any include computer readable storage medium
Or the tangible medium of storage program, which can be commanded execution system, device, and either device uses or in connection makes
With.
Computer-readable signal media may include in a base band or as the data-signal that a carrier wave part is propagated,
Wherein carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By instruction execution system, device either device use or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, radio frequency (Radio Frequency, RF) etc. or above-mentioned any appropriate combination.
It can be write with one or more programming languages or combinations thereof for executing the computer that operates of the present invention
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++, also
Including conventional procedural programming language --- such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partly executes or executed on a remote computer or server completely on the remote computer on the user computer.
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as provided using Internet service
Quotient is connected by internet).
Note that above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The present invention is not limited to specific embodiments described here, can carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out to the present invention by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
May include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of semantic analysis, which is characterized in that it is applied to application server, the method includes：
The problem of user puts question to is obtained, described problem is sent to the semantic machine people of the application server；
The semantic machine people classifies to described problem；And classification results and described problem are sent to the application service
The regulation engine of device；
The regulation engine analyzes described problem according to the classification results, to determine problem types, and according to described
Problem types are fed back to the semantic machine people；
The semantic machine people or the regulation engine export matched answer according to described problem type.
2. according to the method described in claim 1, it is characterized in that, described problem type includes first problem type and second asks
Inscribe type；
It is described to be fed back to the semantic machine people according to described problem type, including：
When described problem type is Second Problem type, the Second Problem type is carried out instead to the semantic machine people
Feedback.
3. according to the method described in claim 2, it is characterized in that, the semantic machine people or the regulation engine are according to
Problem types export matched answer, including：
If the regulation engine determines that described problem type is first problem type, asked described by the regulation engine
Topic carries out analyzing processing, and exports treated answer；
If the regulation engine determines that described problem type is Second Problem type, by described problem type feedback to described
Semantic machine people, and general answer is exported by the semantic machine people.
4. according to the method described in claim 1, it is characterized in that, obtaining the problem of user puts question to, described problem is sent
To before semantic machine people, further include：
It obtains and presets the problems in knowledge base classification information, classifying rules is obtained according to the classification information, and by the classification
Rule is sent to the regulation engine and synchronizes.
5. according to the method described in claim 3, it is characterized in that, described divide described problem by the regulation engine
Analysis is handled, and exports treated answer, including：
If the regulation engine determines that described problem needs more wheel interactions, exports more wheel question and answer and interact answer；
If the regulation engine determines that described problem need not take turns interaction more, setting answer is exported.
6. according to the method described in claim 4, it is characterized in that,
The semantic machine people and the regulation engine share the default knowledge base.
7. according to the method described in claim 4, it is characterized in that,
The classifying rules is obtained by customized mode；Or
The classifying rules is obtained by default training pattern.
8. a kind of semantic analysis device, which is characterized in that be configured at application server, described device includes：
Described problem is sent to the semanteme of the application server by problem acquisition module for obtaining the problem of user puts question to
Robot；
Semantic machine people, for classifying to described problem；And classification results and described problem are sent to the application and are taken
The regulation engine of business device；
Regulation engine, for being analyzed described problem according to the classification results, to determine problem types, and according to described
Problem types are fed back to the semantic machine people；
The semantic machine people or the regulation engine are additionally operable to export matched answer according to described problem type.
9. a kind of computer equipment, which is characterized in that the equipment includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors so that one or more of processors are real
The now semantic analysis as described in any in claim 1-7.
10. a kind of computer storage media, is stored thereon with computer program, which is characterized in that the program is executed by processor
Semantic analysis of the Shi Shixian as described in any in claim 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810677959.7A CN108491394A (en) | 2018-06-27 | 2018-06-27 | A kind of semantic analysis, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810677959.7A CN108491394A (en) | 2018-06-27 | 2018-06-27 | A kind of semantic analysis, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108491394A true CN108491394A (en) | 2018-09-04 |
Family
ID=63343373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810677959.7A Pending CN108491394A (en) | 2018-06-27 | 2018-06-27 | A kind of semantic analysis, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108491394A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109726271A (en) * | 2018-12-14 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Identify method, apparatus, equipment and the storage medium of customer problem content |
| CN110287305A (en) * | 2019-07-03 | 2019-09-27 | 浪潮云信息技术有限公司 | A kind of intelligent answer management system based on natural language processing |
| CN110795548A (en) * | 2019-10-25 | 2020-02-14 | 招商局金融科技有限公司 | Intelligent question answering method, device and computer readable storage medium |
| CN110908663A (en) * | 2018-09-18 | 2020-03-24 | 北京京东尚科信息技术有限公司 | Service problem positioning method and positioning device |
| CN110931009A (en) * | 2019-12-12 | 2020-03-27 | 贵州电力交易中心有限责任公司 | System for rapidly improving conversation capacity of reception robot in electric power transaction hall |
| CN111178489A (en) * | 2019-12-30 | 2020-05-19 | 深圳集智数字科技有限公司 | Conversation robot engine flow distribution method and device |
| CN111858877A (en) * | 2020-06-17 | 2020-10-30 | 平安科技（深圳）有限公司 | Multi-type question intelligent question answering method, system, equipment and readable storage medium |
| CN112035631A (en) * | 2019-12-31 | 2020-12-04 | 北京来也网络科技有限公司 | Dialogue question-answering method, device, equipment and storage medium combining RPA and AI |
| CN112507089A (en) * | 2020-11-25 | 2021-03-16 | 厦门渊亭信息科技有限公司 | Intelligent question-answering engine based on knowledge graph and implementation method thereof |
| WO2021174822A1 (en) * | 2020-03-02 | 2021-09-10 | 平安科技（深圳）有限公司 | Intelligent question-answering method and apparatus based on attention mechanism, and device and storage medium |
| CN113535909A (en) * | 2020-04-20 | 2021-10-22 | 阿里巴巴集团控股有限公司 | Data processing method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573028A (en) * | 2015-01-14 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Intelligent question-answer implementing method and system |
| CN106202270A (en) * | 2016-06-28 | 2016-12-07 | 广州幽联信息技术有限公司 | Interactive method based on natural language and device |
| CN106570181A (en) * | 2016-11-09 | 2017-04-19 | 武汉泰迪智慧科技有限公司 | Context management based intelligent interaction method and system |
| CN106934068A (en) * | 2017-04-10 | 2017-07-07 | 江苏东方金钰智能机器人有限公司 | The method that robot is based on the semantic understanding of environmental context |
| CN107133305A (en) * | 2017-04-28 | 2017-09-05 | 上海斐讯数据通信技术有限公司 | A kind of automatic construction device of chat robots knowledge base and its method |
| CN107169105A (en) * | 2017-05-17 | 2017-09-15 | 北京品智能量科技有限公司 | Question and answer system and method for vehicle |
| CN107301213A (en) * | 2017-06-09 | 2017-10-27 | 腾讯科技（深圳）有限公司 | Intelligent answer method and device |
| CN107368548A (en) * | 2017-06-30 | 2017-11-21 | 华中科技大学鄂州工业技术研究院 | Intelligent government affairs service interaction method and system |
-
2018
- 2018-06-27 CN CN201810677959.7A patent/CN108491394A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573028A (en) * | 2015-01-14 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Intelligent question-answer implementing method and system |
| CN106202270A (en) * | 2016-06-28 | 2016-12-07 | 广州幽联信息技术有限公司 | Interactive method based on natural language and device |
| CN106570181A (en) * | 2016-11-09 | 2017-04-19 | 武汉泰迪智慧科技有限公司 | Context management based intelligent interaction method and system |
| CN106934068A (en) * | 2017-04-10 | 2017-07-07 | 江苏东方金钰智能机器人有限公司 | The method that robot is based on the semantic understanding of environmental context |
| CN107133305A (en) * | 2017-04-28 | 2017-09-05 | 上海斐讯数据通信技术有限公司 | A kind of automatic construction device of chat robots knowledge base and its method |
| CN107169105A (en) * | 2017-05-17 | 2017-09-15 | 北京品智能量科技有限公司 | Question and answer system and method for vehicle |
| CN107301213A (en) * | 2017-06-09 | 2017-10-27 | 腾讯科技（深圳）有限公司 | Intelligent answer method and device |
| CN107368548A (en) * | 2017-06-30 | 2017-11-21 | 华中科技大学鄂州工业技术研究院 | Intelligent government affairs service interaction method and system |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110908663A (en) * | 2018-09-18 | 2020-03-24 | 北京京东尚科信息技术有限公司 | Service problem positioning method and positioning device |
| CN109726271A (en) * | 2018-12-14 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Identify method, apparatus, equipment and the storage medium of customer problem content |
| CN110287305A (en) * | 2019-07-03 | 2019-09-27 | 浪潮云信息技术有限公司 | A kind of intelligent answer management system based on natural language processing |
| CN110795548A (en) * | 2019-10-25 | 2020-02-14 | 招商局金融科技有限公司 | Intelligent question answering method, device and computer readable storage medium |
| CN110931009A (en) * | 2019-12-12 | 2020-03-27 | 贵州电力交易中心有限责任公司 | System for rapidly improving conversation capacity of reception robot in electric power transaction hall |
| CN111178489A (en) * | 2019-12-30 | 2020-05-19 | 深圳集智数字科技有限公司 | Conversation robot engine flow distribution method and device |
| CN111178489B (en) * | 2019-12-30 | 2021-02-19 | 深圳集智数字科技有限公司 | Conversation robot engine flow distribution method and device |
| CN112035631A (en) * | 2019-12-31 | 2020-12-04 | 北京来也网络科技有限公司 | Dialogue question-answering method, device, equipment and storage medium combining RPA and AI |
| WO2021174822A1 (en) * | 2020-03-02 | 2021-09-10 | 平安科技（深圳）有限公司 | Intelligent question-answering method and apparatus based on attention mechanism, and device and storage medium |
| CN113535909B (en) * | 2020-04-20 | 2022-06-10 | 阿里巴巴集团控股有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113535909A (en) * | 2020-04-20 | 2021-10-22 | 阿里巴巴集团控股有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN111858877A (en) * | 2020-06-17 | 2020-10-30 | 平安科技（深圳）有限公司 | Multi-type question intelligent question answering method, system, equipment and readable storage medium |
| WO2021109690A1 (en) * | 2020-06-17 | 2021-06-10 | 平安科技（深圳）有限公司 | Multi-type question smart answering method, system and device, and readable storage medium |
| CN112507089A (en) * | 2020-11-25 | 2021-03-16 | 厦门渊亭信息科技有限公司 | Intelligent question-answering engine based on knowledge graph and implementation method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108491394A (en) | A kind of semantic analysis, device, computer equipment and storage medium | |
| Choi et al. | Virtual reality applications in manufacturing industries: Past research, present findings, and future directions | |
| US20160044380A1 (en) | Personal helper bot system | |
| US10025980B2 (en) | Assisting people with understanding charts | |
| CN107924393A (en) | Distributed server system for language understanding | |
| US20190171970A1 (en) | Trading goods based on image processing for interest, emotion and affinity detection | |
| CN111666416B (en) | Method and device for generating semantic matching model | |
| CN110413769A (en) | Scene classification method, device, storage medium and its electronic equipment | |
| CN111090739A (en) | Information processing method, information processing device, electronic device, and storage medium | |
| CN107329585A (en) | Method and apparatus for inputting word | |
| CN113392180A (en) | Text processing method, device, equipment and storage medium | |
| CN116894711A (en) | Commodity recommendation reason generation method and device and electronic equipment | |
| Oliveira et al. | Progress in Artificial Intelligence: 19th EPIA Conference on Artificial Intelligence, EPIA 2019, Vila Real, Portugal, September 3–6, 2019, Proceedings, Part II | |
| CN109493186A (en) | The method and apparatus for determining pushed information | |
| CN111967599A (en) | Method and device for training model, electronic equipment and readable storage medium | |
| CN111787042A (en) | Method and device for pushing information | |
| CN109951859A (en) | Wireless network connection recommended method, device, electronic equipment and readable medium | |
| CN108776959A (en) | Image processing method, device and terminal device | |
| Duffey | Superhuman innovation: Transforming business with artificial intelligence | |
| CN111414609B (en) | Object verification method and device | |
| CN108876435A (en) | Artificial intelligence platform implementation method, device, computer equipment and storage medium | |
| Kashyap | I am the future: Machine learning in action | |
| CN115545738A (en) | Recommendation method and related device | |
| CN112363716A (en) | Method, system and device for dynamically assembling evaluation model | |
| CN112131484A (en) | Multi-person session establishing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180904 |