CN109902087A - For the data processing method and device of question and answer, server - Google Patents
For the data processing method and device of question and answer, server Download PDFInfo
- Publication number
- CN109902087A CN109902087A CN201910107972.3A CN201910107972A CN109902087A CN 109902087 A CN109902087 A CN 109902087A CN 201910107972 A CN201910107972 A CN 201910107972A CN 109902087 A CN109902087 A CN 109902087A
- Authority
- CN
- China
- Prior art keywords
- answer
- question
- main body
- attribute
- data processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
This application discloses a kind of data processing method for question and answer and devices, server.This method includes establishing question and answer knowledge frame table；According to the question and answer knowledge frame table, preset attribute Value Data is obtained；And the INQUIRE statement of question and answer is used for by safeguarding, it is exported the preset attribute value as the answer of question and answer.Present application addresses the technical problems poor for the data processing method effect for question and answer.Management of the two-dimensional table to the chart database for question and answer is realized by the application, so that table knowledge data is easy to maintain, timeliness is strong.In addition, this application provides support quick response and can be towards the solution of the B end subscriber question answering system of enterprise customer businessman.
Description
Technical field
This application involves data processing field, in particular to a kind of data processing method for question and answer and device,
Server.
Background technique
Table (table) is a kind of widely used data storage method, is widely used in storage and display structure number
According to.Chart database is a seed type of NoSQL database, the relation information between its Graphics Application theory storage entity.
Inventors have found that if carrying out the acquisition of retrieval and the answer of problem using chart database in question answering system field,
Efficiency is lower, quantity amount to be treated is larger.Further, it can not provide and support quick response and can be towards enterprise customer quotient
The B end subscriber question answering system solution of family.
For problem poor for the data processing method effect for question and answer in the related technology, not yet propose have at present
The solution of effect.
Summary of the invention
The main purpose of the application is to provide a kind of data processing method for question and answer and device, server, with solution
Problem certainly poor for the data processing method effect for question and answer.
To achieve the goals above, according to the one aspect of the application, a kind of data processing side for question and answer is provided
Method.
The data processing method for question and answer according to the application includes: to establish question and answer knowledge frame table；It is asked according to described
Knowledge frame table is answered, preset attribute Value Data is obtained；And the INQUIRE statement of question and answer is used for by safeguarding, by the preset attribute
It is worth and is exported as the answer of question and answer.
Further, establishing question and answer knowledge frame table includes: to determine the main body of two dimension knowledge table according to question and answer type；
Obtain attribute relevant to the main body；Determine the two-dimensional table relationship of the main body and multiple attributes.
Further, the INQUIRE statement of question and answer is used for by safeguarding, the preset attribute value is defeated as the answer of question and answer
After out further include: the step of realizing the searching attribute value structuralized query of main body and attribute in the knowledge frame table, packet
It includes: retrieval and relevant question and answer knowledge frame table the problem of question and answer input in table set；The nature that the question and answer are inputted
Language issues are converted to query statement；The query statement is executed, the answer of question and answer is obtained.
Further, by safeguarding that the INQUIRE statement for question and answer includes: by safeguarding that the main body for question and answer inquires language
Sentence；It include: to obtain and the main body INQUIRE statement language for being used for question and answer using the preset attribute value as the answer of question and answer output
Main body question and answer problem similar in justice；According to the main body question and answer problem, the correspondence attribute value in the main body is searched as question and answer
Answer output.
Further, by safeguarding that the INQUIRE statement for question and answer includes: the attribute enquiry language for being used for question and answer by safeguarding
Sentence；It include: to obtain and the attribute enquiry sentence language for being used for question and answer using the preset attribute value as the answer of question and answer output
Attribute question and answer problem similar in justice；According to the attribute question and answer problem, the correspondence attribute value in the main body is searched as question and answer
Answer output.
To achieve the goals above, according to the another aspect of the application, a kind of data processing dress for question and answer is provided
It sets.
It include: to establish module according to the data processing equipment for question and answer of the application, for establishing question and answer knowledge frame
Table；Module is obtained, for obtaining preset attribute Value Data according to the question and answer knowledge frame table；And maintenance module, for leading to
The INQUIRE statement that maintenance is used for question and answer is crossed, is exported the preset attribute value as the answer of question and answer.
Further, the module of establishing includes: the first determination unit, for determining two dimension knowledge according to question and answer type
The main body of table；Attribute acquiring unit, for obtaining attribute relevant to the main body；Second determination unit, for determining
State the two-dimensional table relationship of main body and multiple attributes.
Further, the maintenance module includes: main body maintenance unit, is inquired for the main body by maintenance for question and answer
Sentence；First acquisition unit, for obtaining and the main body question and answer problem of the main body INQUIRE statement semantic similarity for question and answer；
First searching unit, according to the main body question and answer problem, the correspondence attribute value searched in the main body is defeated as the answer of question and answer
Out.
Further, the maintenance module includes attribute maintenance unit, and the attribute enquiry sentence of question and answer is used for by safeguarding；
Second acquisition unit obtains and attribute question and answer problem similar in the attribute enquiry statement semantics for question and answer；Second searches
Unit, according to the attribute question and answer problem, the correspondence attribute value searched in the main body is exported as the answer of question and answer.
To achieve the goals above, according to the another aspect of the application, a kind of data processing clothes for question and answer are provided
Business device, including the data processing equipment.
In the embodiment of the present application, by the way of establishing question and answer knowledge frame table, by according to the question and answer knowledge frame
Frame table, obtain preset attribute Value Data, reached by safeguard be used for question and answer INQUIRE statement, using the preset attribute value as
The purpose of the answer output of question and answer, to realize technical effect clear in structure, easy to maintain, that timeliness is strong, and then solves
The technical problem poor for the data processing method effect for question and answer.
Detailed description of the invention
The attached drawing constituted part of this application is used to provide further understanding of the present application, so that the application's is other
Feature, objects and advantages become more apparent upon.The illustrative examples attached drawing and its explanation of the application is for explaining the application, not
Constitute the improper restriction to the application.In the accompanying drawings:
Fig. 1 is the data processing method flow diagram for question and answer according to the application first embodiment；
Fig. 2 is the data processing method flow diagram for question and answer according to the application second embodiment；
Fig. 3 is the data processing method flow diagram for question and answer according to the application 3rd embodiment；
Fig. 4 is the data processing method flow diagram for question and answer according to the application fourth embodiment；
Fig. 5 is the data processing method flow diagram for question and answer according to the 5th embodiment of the application；
Fig. 6 is the data processing equipment structural diagram for question and answer according to the application first embodiment；
Fig. 7 is the data processing equipment structural diagram for question and answer according to the application second embodiment；
Fig. 8 is the data processing equipment structural diagram for question and answer according to the application 3rd embodiment；
Fig. 9 is the data processing equipment structural diagram for question and answer according to the application fourth embodiment.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection
It encloses.
It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to embodiments herein described herein.In addition, term " includes " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing a series of steps or units
Process, method, system, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include without clear
Other step or units listing to Chu or intrinsic for these process, methods, product or equipment.
In this application, term " on ", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outside",
" in ", "vertical", "horizontal", " transverse direction ", the orientation or positional relationship of the instructions such as " longitudinal direction " be orientation based on the figure or
Positional relationship.These terms are not intended to limit indicated dress primarily to better describe the application and embodiment
Set, element or component must have particular orientation, or constructed and operated with particular orientation.
Also, above-mentioned part term is other than it can be used to indicate that orientation or positional relationship, it is also possible to for indicating it
His meaning, such as term " on " also are likely used for indicating certain relations of dependence or connection relationship in some cases.For ability
For the those of ordinary skill of domain, the concrete meaning of these terms in this application can be understood as the case may be.
In addition, term " installation ", " setting ", " being equipped with ", " connection ", " connected ", " socket " shall be understood in a broad sense.For example,
It may be a fixed connection, be detachably connected or monolithic construction；It can be mechanical connection, or electrical connection；It can be direct phase
It even, or indirectly connected through an intermediary, or is two connections internal between device, element or component.
For those of ordinary skills, the concrete meaning of above-mentioned term in this application can be understood as the case may be.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
As shown in Figure 1, this method includes the following steps, namely S102 to step S106:
Step S102 establishes question and answer knowledge frame table；
Question and answer knowledge frame table is obtained in background server, the question and answer knowledge frame table has fixed format, and root
Different business datums can be filled into according to different business scenarios.It can be recorded in a manner of database in background server
The question and answer indicate frame table, and include at least to have in the question and answer knowledge frame table and can carry out mapping relations, can be one
To more or one-to-one.
Specifically, knowledge frame table is by the way of two-dimensional table, by the business number for obtaining user's input in WEB terminal
According to determining question and answer knowledge frame bivariate table.
It should be noted that the embodiment of specific question and answer knowledge frame table is not limited in this application, as long as energy
Enough meet mapping relations, those skilled in the art can select according to the actual situation.
Step S104 obtains preset attribute Value Data according to the question and answer knowledge frame table；
Background server can further obtain default category in the question and answer knowledge frame table according to above-mentioned acquisition
Property Value Data.According to question and answer knowledge frame table record attribute Value Data in background server, and according to preset corresponding relationship into
Row storage.
Specifically, by provide backstage login system, can consistency operation personnel input preset attribute Value Data after with
Background server is synchronous, and the attribute value data recorded in background server is according to reflecting in default question and answer knowledge frame table
It penetrates or other corresponding relationships store and can be called.
Step S106 is used for the INQUIRE statement of question and answer by safeguarding, the preset attribute value is defeated as the answer of question and answer
Out.
It can be used to safeguard the content in question and answer problem and answer answer by obtaining multiple INQUIRE statements.And it is safeguarding
The preset attribute value in question and answer knowledge frame table result can be issued as the answer of question and answer while INQUIRE statement to use backward
Family output.
Specifically, backstage personnel are received in background server by being inputted after login background system according in actual scene
User's INQUIRE statement, and when the INQUIRE statement saved in user's INQUIRE statement and background server is approximate, background server
In will do it find out corresponding attribute value and as the answer of inquiry to user export.For example, different by constantly updating
The INQUIRE statement of attribute can receive user proposition about the problem of same alike result when match most like problem and will
Attribute value is as the answer inquired in question and answer.
It can be seen from the above description that the application realizes following technical effect:
In the embodiment of the present application, by the way of establishing question and answer knowledge frame table, by according to the question and answer knowledge frame
Frame table, obtain preset attribute Value Data, reached by safeguard be used for question and answer INQUIRE statement, using the preset attribute value as
The purpose of the answer output of question and answer, to realize technical effect clear in structure, easy to maintain, that timeliness is strong, and then solves
The technical problem poor for the data processing method effect for question and answer.
In addition, being used for the inquiry of question and answer by safeguarding as the preferred of the data processing method for question and answer in the application
It asks sentence, after the preset attribute value is exported as the answer of question and answer, has also specifically included in given question and answer knowledge frame
The understanding and generation of natural language are carried out on the basis of table.It may include being converted into natural language problem to be understood by machine
Semantic expressiveness, and the step of expression can be obtained the semantic parsing of answer is executed in the table.It also may include: as language
Justice parsing inverse process, reduces the step of semantic parser generates the problem of a large amount of dependences for marking training datas.It can also wrap
It includes: for taking turns the semantic parsing task of session operational scenarios more, need to effectively solving the omission in context and referring to the dialogue step of phenomenon
Suddenly.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in Fig. 2, establishing question and answer knowledge frame table packet
It includes:
Step S202 determines the main body of two dimension knowledge table according to question and answer type；
According to the type of question and answer in background server, the main body in two-dimentional knowledge table can be determined.
For example, it be film, main body is sport etc. that main body, which is fund, main body,.
Specifically, the class of question and answer is obtained when background server can be by configuring from backstage personnel by background system
Type.It and is the body matter for the two-dimentional knowledge table established according to the determination of the type of question and answer.
Step S204 obtains attribute relevant to the main body；
Under the premise of determining the main body of two-dimentional knowledge table, background server is available to relevant to the theme
All properties information.Those usual attribute informations, which are based on business, has relevant contact to the main body.For example, what main body determined
Film, then attribute information may include: a word introduction of film, the description of film, film downloading/viewing network address, electricity
The country of shadow, film the relevant attribute information of protagonist etc..
Step S206 determines the two-dimensional table relationship of the main body and multiple attributes.
According to the mapping relations of main body and multiple attributes, and establish two-dimensional table relationship.For example, as indicated to know in the following table 1
Know the frame of structure: table 1
| Main body title | Attribute title 1 | Attribute title 4 | Attribute title 3 |
For another example, as in the following table 2 have knowledge content two-dimensional table relation table 2
| Main body title | Attribute title 1 | Attribute title 4 | Attribute title 3 |
| Main body value 1 | Attribute value 1 | Attribute value 2 | Attribute value 3 |
Specifically, by realizing the upload of list data in WEB terminal, server end obtains following content in real time:
The question and answer table that user edits in background server: according to confirmation main body and attribute, from the category of question and answer table acquisition
Property value, safeguards the INQUIRE statement of user.
Attribute value is imported in background server: the main body and attribute saved according to WEB terminal generates two-dimensional table template.It leads
Two-dimensional table template and after background user fills in main body value and attribute value out, then background system is imported, in background server
It can service body value and attribute value.
User must exactly match the entity value of main body reference entity when backstage inputs main body value.If attribute column is associated with
Entity, attribute value need to meet the rule of preset regular expression in entity value or background server, otherwise can not on
It reaches in background server and is saved.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in figure 3, being used for the inquiry of question and answer by maintenance
Sentence is asked, after the preset attribute value is exported as the answer of question and answer further include: realize main body in the knowledge frame table
The step of with the searching attribute value structuralized query of attribute comprising:
Step S302, retrieval and relevant question and answer knowledge frame table the problem of question and answer input in table set；
Since database always saves a variety of tables, so background server needs retrieve in table set and question and answer
The problem of input relevant question and answer knowledge frame table.The relevant question and answer knowledge frame table of many problems is usually had, so needing
Selection is maximally related.
The natural language problem that the question and answer input is converted to query statement by step S304；
Background server obtains the natural language problem that the question and answer input from WEB terminal, and executes in background server
The natural language problem that the question and answer input is converted into the semantic expressiveness that machine is understood that, such as SQL by natural language processing
Query statement.
Step S306 executes the query statement, obtains the answer of question and answer.
Corresponding query statement is executed in frame table can be obtained the answer of corresponding question and answer.
Further, it is also possible to by executing the semantic parsing task for more taking turns session operational scenarios in the server, by effective
It solves the omission in context and is converted to query statement after referring to phenomenon.
Specifically, realization body includes the following steps: with the inquiry of attribute retrieval attribute-value structureization
Firstly, extracting several possible main bodys from training sentence, first score score_1 is calculated；
Then, for the possible attribute of each main body, computation attribute and training are gone with non-supervisory method based on term vector
The similarity of sentence calculates second score score_2；
Then, many training sentence pattern are extracted from training data, if current problem meets one specifically
Pattern then calculates third score score_3；
Finally, above 3 scores are carried out linear weighted function, (main body and/or the attribute) after finally obtaining sequence is to composition
Querying condition.
In addition, further including the steps that data preparation: needing backstage personnel to the INQUIRE statement of attribute.Background server can return
Repetitive generation: the directly corresponding attribute value of reply main body.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in figure 4, being used for the inquiry of question and answer by maintenance
Ask that sentence includes:
Step S402 is used for the main body INQUIRE statement of question and answer by safeguarding；
Maintenance is used for the main body INQUIRE statement of question and answer in background server, refers to and main body phase for main body INQUIRE statement
All INQUIRE statements closed.For example, " film A is good-looking? ", " where go go to the cinema A? ", " film A is who is drilled ".Deng all belonging to
In main body INQUIRE statement.
Include: using the preset attribute value as the answer of question and answer output
Step S404 obtains the main body question and answer problem with the main body INQUIRE statement semantic similarity for question and answer；
The main body question and answer problem with the main body INQUIRE statement semantic similarity for question and answer is obtained in background server, after
The main body question and answer problem of semantic similarity can be obtained in platform server from WEB terminal.For example, " film A is good-looking? " Similar Problems are also
May is that " how is film A? ", " scoring of film A is how many? " Deng.
Step S406 searches correspondence attribute value the answering as question and answer in the main body according to the main body question and answer problem
Case output.
Background server can search correspondence attribute value the answering as question and answer in the main body according to main body question and answer problem
Case issues.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in figure 5, being used for the inquiry of question and answer by maintenance
Ask that sentence includes:
Step S502 is used for the attribute enquiry sentence of question and answer by safeguarding；
Maintenance is used for the attribute enquiry sentence of question and answer in background server, refers to and attribute phase for attribute enquiry sentence
All user's INQUIRE statements closed.For example, " what is your name by the fund manager of fund A? ", " who be fund B fund warp
Reason? ", " who is responsible for managed fund A? " etc. belonging to attribute enquiry sentence.
Include: using the preset attribute value as the answer of question and answer output
Step S504 is obtained and attribute question and answer problem similar in the attribute enquiry statement semantics for question and answer；
Acquisition and attribute question and answer problem similar in the attribute enquiry statement semantics for question and answer in background server, after
The attribute question and answer problem of semantic similarity can be obtained in platform server from WEB terminal.For example, " who is responsible for managed fund A? " it is similar to ask
Topic may also is that " what is your name by the fund manager of fund A? ", " fund A is responsible for by whom? ".
Step S506 searches correspondence attribute value the answering as question and answer in the main body according to the attribute question and answer problem
Case output.
Background server can search correspondence attribute value the answering as question and answer in the main body according to attribute question and answer problem
Case issues.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with not
The sequence being same as herein executes shown or described step.
According to the embodiment of the present application, additionally provide a kind of for implementing the dress of the above-mentioned data processing method for question and answer
It sets, as shown in fig. 6, the device includes: to establish module 10, for establishing question and answer knowledge frame table；Obtain module 20, for according to
The question and answer knowledge frame table obtains preset attribute Value Data；And maintenance module 30, for being used for the inquiry of question and answer by maintenance
It asks sentence, is exported the preset attribute value as the answer of question and answer.
Establishing in module 10 for the embodiment of the present application obtains question and answer knowledge frame table, the question and answer knowledge in background server
Frame table has fixed format, and different business datums can be filled into according to different business scenarios.It is taken on backstage
The question and answer instruction frame table can be recorded in business device in a manner of database, and is included at least in the question and answer knowledge frame table
Mapping relations can be carried out by having, and can be one-to-many or one-to-one.
Specifically, knowledge frame table is by the way of two-dimensional table, by the business number for obtaining user's input in WEB terminal
According to determining question and answer knowledge frame bivariate table.
It should be noted that the embodiment of specific question and answer knowledge frame table is not limited in this application, as long as energy
Enough meet mapping relations, those skilled in the art can select according to the actual situation.
Background server is in the question and answer knowledge frame according to above-mentioned acquisition in the acquisition module 20 of the embodiment of the present application
Table can further obtain default attribute value data.According to question and answer knowledge frame table record attribute value in background server
Data, and stored according to preset corresponding relationship.
Specifically, by provide backstage login system, can consistency operation personnel input preset attribute Value Data after with
Background server is synchronous, and the attribute value data recorded in background server is according to reflecting in default question and answer knowledge frame table
It penetrates or other corresponding relationships store and can be called.
In the maintenance module 30 of the embodiment of the present application by obtain multiple INQUIRE statements can be used to safeguard question and answer problem and
Answer the content in answer.And the preset attribute value in question and answer knowledge frame table can be made while safeguarding INQUIRE statement
The output of result rear line is issued for the answer of question and answer.
Specifically, backstage personnel are received in background server by being inputted after login background system according in actual scene
User's INQUIRE statement, and when the INQUIRE statement saved in user's INQUIRE statement and background server is approximate, background server
In will do it find out corresponding attribute value and as the answer of inquiry to user export.For example, different by constantly updating
The INQUIRE statement of attribute can receive user proposition about the problem of same alike result when match most like problem and will
Attribute value is as the answer inquired in question and answer.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in fig. 7, the module 20 of establishing includes:
One determination unit 201, for determining the main body of two dimension knowledge table according to question and answer type；Attribute acquiring unit 202, for obtaining
Take attribute relevant to the main body；Second determination unit 203, for determining the bivariate table of the main body and multiple attributes
Case relation.
Type in first determination unit 201 of the embodiment of the present application in background server according to question and answer, can determine
Main body in two-dimentional knowledge table.
For example, it be film, main body is sport etc. that main body, which is fund, main body,.
Specifically, the class of question and answer is obtained when background server can be by configuring from backstage personnel by background system
Type.It and is the body matter for the two-dimentional knowledge table established according to the determination of the type of question and answer.
In the attribute acquiring unit 202 of the embodiment of the present application under the premise of determining the main body of two-dimentional knowledge table, backstage
Server is available to arrive all properties information relevant to the theme.Those usual attribute informations are based on business and the master
Body has relevant connection.For example, main body is it is confirmed that film, then attribute information may include: a word introduction of film, electricity
The description of shadow, downloading/viewing network address of film, the country of film, film the relevant attribute information of protagonist etc..
According to the mapping relations of main body and multiple attributes in second determination unit 203 of the embodiment of the present application, and establish two
Dimension table case relation.For example, the frame as indicated the structure of knowledge in the following table 1: table 1
| Main body title | Attribute title 1 | Attribute title 4 | Attribute title 3 |
For another example, as in the following table 2 have knowledge content two-dimensional table relation table 2
| Main body title | Attribute title 1 | Attribute title 4 | Attribute title 3 |
| Main body value 1 | Attribute value 1 | Attribute value 2 | Attribute value 3 |
Specifically, by realizing the upload of list data in WEB terminal, server end obtains following content in real time:
The question and answer table that user edits in background server: according to confirmation main body and attribute, from the category of question and answer table acquisition
Property value, safeguards the INQUIRE statement of user.
Attribute value is imported in background server: the main body and attribute saved according to WEB terminal generates two-dimensional table template.It leads
Two-dimensional table template and after background user fills in main body value and attribute value out, then background system is imported, in background server
It can service body value and attribute value.
User must exactly match the entity value of main body reference entity when backstage inputs main body value.If attribute column is associated with
Entity, attribute value need to meet the rule of preset regular expression in entity value or background server, otherwise can not on
It reaches in background server and is saved.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in figure 8, the maintenance module 30 includes: master
Body maintenance unit 301, for being used for the main body INQUIRE statement of question and answer by maintenance；First acquisition unit 302, for acquisition and institute
State the main body question and answer problem of the main body INQUIRE statement semantic similarity for question and answer；First searching unit 303, is asked according to the main body
Question and answer topic, the correspondence attribute value searched in the main body are exported as the answer of question and answer.
Since database always saves a variety of tables in the main body maintenance unit 301 of the embodiment of the present application, so backstage takes
Business device needs retrieve the problem of inputting to question and answer relevant question and answer knowledge frame table in table set.It usually has and much asks
Relevant question and answer knowledge frame table is inscribed, so need selection is maximally related.
In the first acquisition unit 302 of the embodiment of the present application background server obtain that the question and answer input from WEB terminal from
Right language issues, and natural language processing is executed in background server, the natural language problem that the question and answer are inputted is converted
At machine it is understood that semantic expressiveness, such as SQL query statement.
Corresponding query statement is executed in frame table in first searching unit 303 of the embodiment of the present application can be obtained phase
The answer for the question and answer answered.
Further, it is also possible to by executing the semantic parsing task for more taking turns session operational scenarios in the server, by effective
It solves the omission in context and is converted to query statement after referring to phenomenon.
Specifically, realization body and the inquiry of attribute retrieval attribute-value structureization include following module:
Score computing module extracts several possible main bodys from training sentence, calculates first score
score_1；
Similarity calculation module goes to calculate based on term vector for the possible attribute of each main body with non-supervisory method
The similarity of attribute and training sentence, calculates second score score_2；
Judgment module extracts many training sentence pattern, if current problem meets a spy from training data
Fixed pattern then calculates third score score_3；
Above 3 scores are carried out linear weighted function by weighting block, and (main body and/or the attribute) after finally obtaining sequence is right
Constitute querying condition.
In addition, further including that data preparation automatically replies module: needing the backstage personnel to the INQUIRE statement of attribute.Backstage takes
Business device can reply generation: directly reply the corresponding attribute value of main body.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in figure 9, the maintenance module 30 includes: to belong to
Property maintenance unit 304, by safeguard be used for question and answer attribute enquiry sentence；Second acquisition unit 305 is obtained with described for asking
Attribute question and answer problem similar in the attribute enquiry statement semantics answered；Second searching unit 306, according to the attribute question and answer problem,
The correspondence attribute value searched in the main body is exported as the answer of question and answer.
Maintenance is used for the attribute enquiry language of question and answer in background server in the attribute maintenance unit 304 of the embodiment of the present application
Sentence, refers to all user's INQUIRE statements relevant to attribute for attribute enquiry sentence.For example, " fund manager of fund A cries assorted
Name? ", " who is the fund manager of fund B? ", " who is responsible for managed fund A? " etc. belonging to attribute enquiry sentence.
It obtains in background server in the second acquisition unit 305 of the embodiment of the present application and is ask with the attribute for question and answer
It asks attribute question and answer problem similar in statement semantics, can be asked from the attribute question and answer that WEB terminal obtains semantic similarity in background server
Topic.For example, " who is responsible for managed fund A? " Similar Problems may also is that " what is your name by the fund manager of fund A? ", " fund
A is responsible for by whom? ".
Background server can search institute according to attribute question and answer problem in second searching unit 306 of the embodiment of the present application
The correspondence attribute value stated in main body is issued as the answer of question and answer.
In another embodiment of the application, the data processing server for question and answer is additionally provided, including the number
According to processing unit.The realization principle and beneficial effect of the data processing equipment are as described above, are no longer repeated herein.
Obviously, those skilled in the art should be understood that each module of above-mentioned the application or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
Be performed by computing device in the storage device, perhaps they are fabricated to each integrated circuit modules or by they
In multiple modules or step be fabricated to single integrated circuit module to realize.In this way, the application be not limited to it is any specific
Hardware and software combines.
The foregoing is merely preferred embodiment of the present application, are not intended to limit this application, for the skill of this field
For art personnel, various changes and changes are possible in this application.Within the spirit and principles of this application, made any to repair
Change, equivalent replacement, improvement etc., should be included within the scope of protection of this application.
Claims (10)
1. a kind of data processing method for question and answer characterized by comprising
Establish question and answer knowledge frame table；
According to the question and answer knowledge frame table, preset attribute Value Data is obtained；And
It is used for the INQUIRE statement of question and answer by safeguarding, is exported the preset attribute value as the answer of question and answer.
2. data processing method according to claim 1, which is characterized in that establishing question and answer knowledge frame table includes:
According to question and answer type, the main body of two dimension knowledge table is determined；
Obtain attribute relevant to the main body；
Determine the two-dimensional table relationship of the main body and multiple attributes.
3. data processing method according to claim 1, which is characterized in that the INQUIRE statement of question and answer is used for by safeguarding,
After using the preset attribute value as the answer of question and answer output further include: realize main body and attribute in the knowledge frame table
The step of searching attribute value structuralized query comprising:
Retrieval and relevant question and answer knowledge frame table the problem of question and answer input in table set；
The natural language problem that the question and answer input is converted into query statement；
The query statement is executed, the answer of question and answer is obtained.
4. data processing method according to claim 1, which is characterized in that
Include: by the INQUIRE statement that maintenance is used for question and answer
The main body INQUIRE statement of question and answer is used for by safeguarding；
Include: using the preset attribute value as the answer of question and answer output
Obtain the main body question and answer problem with the main body INQUIRE statement semantic similarity for question and answer；
According to the main body question and answer problem, the correspondence attribute value searched in the main body is exported as the answer of question and answer.
5. data processing method according to claim 1, which is characterized in that
Include: by the INQUIRE statement that maintenance is used for question and answer
The attribute enquiry sentence of question and answer is used for by safeguarding；
Include: using the preset attribute value as the answer of question and answer output
It obtains and attribute question and answer problem similar in the attribute enquiry statement semantics for question and answer；
According to the attribute question and answer problem, the correspondence attribute value searched in the main body is exported as the answer of question and answer.
6. a kind of data processing equipment for question and answer characterized by comprising
Module is established, for establishing question and answer knowledge frame table；
Module is obtained, for obtaining preset attribute Value Data according to the question and answer knowledge frame table；And
Maintenance module, it is for being used for the INQUIRE statement of question and answer by maintenance, the preset attribute value is defeated as the answer of question and answer
Out.
7. data processing equipment according to claim 6, which is characterized in that the module of establishing includes:
First determination unit, for determining the main body of two dimension knowledge table according to question and answer type；
Attribute acquiring unit, for obtaining attribute relevant to the main body；
Second determination unit, for determining the two-dimensional table relationship of the main body and multiple attributes.
8. data processing equipment according to claim 6, which is characterized in that the maintenance module includes:
Main body maintenance unit, for being used for the main body INQUIRE statement of question and answer by maintenance；
First acquisition unit, for obtaining and the main body question and answer problem of the main body INQUIRE statement semantic similarity for question and answer；
First searching unit searches correspondence attribute value the answering as question and answer in the main body according to the main body question and answer problem
Case output.
9. data processing equipment according to claim 6, which is characterized in that the maintenance module includes:
Attribute maintenance unit is used for the attribute enquiry sentence of question and answer by safeguarding；
Second acquisition unit obtains and attribute question and answer problem similar in the attribute enquiry statement semantics for question and answer；
Second searching unit searches correspondence attribute value the answering as question and answer in the main body according to the attribute question and answer problem
Case output.
10. a kind of data processing server for question and answer, which is characterized in that described in any item including such as claim 6 to 9
Data processing equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910107972.3A CN109902087B (en) | 2019-02-02 | 2019-02-02 | Data processing method and device for questions and answers and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910107972.3A CN109902087B (en) | 2019-02-02 | 2019-02-02 | Data processing method and device for questions and answers and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109902087A true CN109902087A (en) | 2019-06-18 |
| CN109902087B CN109902087B (en) | 2023-05-30 |
Family
ID=66944696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910107972.3A Active CN109902087B (en) | 2019-02-02 | 2019-02-02 | Data processing method and device for questions and answers and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109902087B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287304A (en) * | 2019-06-30 | 2019-09-27 | 联想(北京)有限公司 | Question and answer information processing method, device and computer equipment |
| CN110851618A (en) * | 2019-10-18 | 2020-02-28 | 南京云问网络技术有限公司 | Management method and device of table data |
| CN111324693A (en) * | 2020-01-21 | 2020-06-23 | 招商银行股份有限公司 | Intelligent response method and device and computer readable storage medium |
| CN113535916A (en) * | 2021-06-30 | 2021-10-22 | 北京百度网讯科技有限公司 | Question and answer method and device based on table and computer equipment |
| CN113553414A (en) * | 2021-06-30 | 2021-10-26 | 北京百度网讯科技有限公司 | Intelligent dialogue method and device, electronic equipment and storage medium |
| CN114090760A (en) * | 2022-01-20 | 2022-02-25 | 阿里巴巴达摩院(杭州)科技有限公司 | Data processing method of table question and answer, electronic equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090136910A1 (en) * | 2007-11-26 | 2009-05-28 | Liran Mayost | Memorization aid |
| CN105701253A (en) * | 2016-03-04 | 2016-06-22 | 南京大学 | Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method |
| CN107885842A (en) * | 2017-11-10 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Method, apparatus, server and the storage medium of intelligent answer |
| CN107918634A (en) * | 2017-06-27 | 2018-04-17 | 上海壹账通金融科技有限公司 | Intelligent answer method, apparatus and computer-readable recording medium |
| CN107977415A (en) * | 2017-11-22 | 2018-05-01 | 北京寻领科技有限公司 | Automatic question-answering method and device |
| CN107993724A (en) * | 2017-11-09 | 2018-05-04 | 易保互联医疗信息科技（北京）有限公司 | A kind of method and device of medicine intelligent answer data processing |
-
2019
- 2019-02-02 CN CN201910107972.3A patent/CN109902087B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090136910A1 (en) * | 2007-11-26 | 2009-05-28 | Liran Mayost | Memorization aid |
| CN105701253A (en) * | 2016-03-04 | 2016-06-22 | 南京大学 | Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method |
| CN107918634A (en) * | 2017-06-27 | 2018-04-17 | 上海壹账通金融科技有限公司 | Intelligent answer method, apparatus and computer-readable recording medium |
| CN107993724A (en) * | 2017-11-09 | 2018-05-04 | 易保互联医疗信息科技（北京）有限公司 | A kind of method and device of medicine intelligent answer data processing |
| CN107885842A (en) * | 2017-11-10 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Method, apparatus, server and the storage medium of intelligent answer |
| CN107977415A (en) * | 2017-11-22 | 2018-05-01 | 北京寻领科技有限公司 | Automatic question-answering method and device |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110287304A (en) * | 2019-06-30 | 2019-09-27 | 联想(北京)有限公司 | Question and answer information processing method, device and computer equipment |
| CN110851618A (en) * | 2019-10-18 | 2020-02-28 | 南京云问网络技术有限公司 | Management method and device of table data |
| CN110851618B (en) * | 2019-10-18 | 2023-09-26 | 南京云问网络技术有限公司 | Management method and device for form data |
| CN111324693A (en) * | 2020-01-21 | 2020-06-23 | 招商银行股份有限公司 | Intelligent response method and device and computer readable storage medium |
| CN113535916A (en) * | 2021-06-30 | 2021-10-22 | 北京百度网讯科技有限公司 | Question and answer method and device based on table and computer equipment |
| CN113553414A (en) * | 2021-06-30 | 2021-10-26 | 北京百度网讯科技有限公司 | Intelligent dialogue method and device, electronic equipment and storage medium |
| CN113535916B (en) * | 2021-06-30 | 2023-07-25 | 北京百度网讯科技有限公司 | Question and answer method and device based on table and computer equipment |
| CN113553414B (en) * | 2021-06-30 | 2023-08-25 | 北京百度网讯科技有限公司 | Intelligent dialogue method, intelligent dialogue device, electronic equipment and storage medium |
| CN114090760A (en) * | 2022-01-20 | 2022-02-25 | 阿里巴巴达摩院(杭州)科技有限公司 | Data processing method of table question and answer, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109902087B (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109902087A (en) | For the data processing method and device of question and answer, server | |
| CN108345690B (en) | Intelligent question and answer method and system | |
| CN102955781B (en) | A kind of personage's searching method and device | |
| CN106155522B (en) | Session data processing, knowledge base foundation, optimization, exchange method and device | |
| CN105630938A (en) | Intelligent question-answering system | |
| CN104317839B (en) | The method and apparatus for generating report form template | |
| CN102866990A (en) | Thematic conversation method and device | |
| CN110472068A (en) | Big data processing method, equipment and medium based on heterogeneous distributed knowledge mapping | |
| CN106096037A (en) | Search Results polymerization based on artificial intelligence, device and search engine | |
| CN107168991A (en) | A kind of search result methods of exhibiting and device | |
| CN114691831A (en) | Task-type intelligent automobile fault question-answering system based on knowledge graph | |
| CN107220274A (en) | One kind visualization data-interface fairground implementation method | |
| CN107577749A (en) | A kind of management method of supplier | |
| CN112632239A (en) | Brain-like question-answering system based on artificial intelligence technology | |
| CN105631014B (en) | Toy problem information replying method and device | |
| CN106919703A (en) | Film information searching method and device | |
| CN114090760B (en) | Data processing method of table question and answer, electronic equipment and readable storage medium | |
| CN106156262A (en) | A kind of search information processing method and system | |
| CN114707000A (en) | Knowledge graph-based question-answer library generation method and device, electronic equipment and storage medium | |
| CN104660581A (en) | Method, device and system for determining target users for business strategy | |
| CN112527924A (en) | Dynamically updated knowledge graph expansion method and device | |
| CN107832342A (en) | Robot chat method and system | |
| CN109299241B (en) | Knowledge base organization method and device for chat robot | |
| CN115757720A (en) | Project information searching method, device, equipment and medium based on knowledge graph | |
| CN107644103A (en) | It is a kind of can tracing information source information storage method and system |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 138, building 3, 33 Leshan Road, Xuhui District, Shanghai 200030 Applicant after: Shanghai laiyibert Network Technology Co.,Ltd. Address before: Room 138, building 3, 33 Leshan Road, Xuhui District, Shanghai 200030 Applicant before: SHANGHAI BENYING NETWORK TECHNOLOGY CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |