CN108959290A - The processing method and equipment of knowledge data - Google Patents
The processing method and equipment of knowledge data Download PDFInfo
- Publication number
- CN108959290A CN108959290A CN201710354503.2A CN201710354503A CN108959290A CN 108959290 A CN108959290 A CN 108959290A CN 201710354503 A CN201710354503 A CN 201710354503A CN 108959290 A CN108959290 A CN 108959290A
- Authority
- CN
- China
- Prior art keywords
- knowledge data
- knowledge
- reasoning
- data
- conflict
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present invention proposes the processing method and equipment of a kind of knowledge data.The described method includes: obtaining knowledge data to be detected；Knowledge data to be detected is analyzed, the structural knowledge of knowledge data to be detected is obtained；Detect knowledge data to be detected with have with reference to knowledge data with the presence or absence of conflicting.Wherein, the detection includes being compared the structural knowledge of knowledge data to be detected with having according to two or more with reference to the structural knowledge that the structural knowledge knowledge-based inference of knowledge data obtains, and is conflicted with determination knowledge data to be detected with having to whether there is with reference to knowledge data.The accuracy rate of collision detection can be improved in knowledge data processing method according to an embodiment of the present invention.
Description
Technical field
This invention relates generally to technical field of data processing, the particularly a kind of processing method of knowledge data and place
Manage equipment.
Background technique
With the development of internet, people obtain knowledge channel it is more and more abundant, in addition to the expert knowledge library in each field,
All kinds of internet knowledge bases are also come into being, such as wikipedia, Baidupedia.Expert knowledge library is mainly from domain expert's
Experience is faced with the update of knowledge with the development of technology.Internet knowledge base is participated in establishing by Internet user, and having can
There can be the knowledge of mistake.For the knowledge from different data sources, between the knowledge data of same knowledget opic there may be
Difference, or even can exist and collide with one another or mistake.
Therefore, it when constructing knowledge base using the knowledge data in multiple knowledge data sources, needs to knowledge number therein
According to being handled, the conflict between knowledge data, the knowledge of debug are detected.
For existing technology when detecting Knowledge Conflicts, it is right one by one by new knowledge and the existing knowledge in knowledge base usually to consider
Than detection, but does not account for existing between new knowledge and the combination of knowledge a plurality of in knowledge base and conflict.Therefore, existing patent can not
Detect that new knowledge conflicts with all of knowledge in knowledge base, so that the knowledge data accuracy rate in knowledge base is lower
Therefore, it is necessary to a kind of mechanism of the higher processing knowledge data of accuracy.
Summary of the invention
In order to overcome at least some defects of the above-mentioned prior art, the embodiment of the present invention proposes a kind of place of knowledge data
Method and apparatus is managed, when detecting Knowledge Conflicts, each item not only allowed in new knowledge and knowledge base has between knowledge
With the presence or absence of conflict, and considers to whether there is between new knowledge and the combination of a plurality of knowledge in knowledge base and conflict.Therefore,
Improve collision detection accuracy rate.Correspondingly, the accuracy rate of the knowledge data in the knowledge base built up can be improved.
According to the first aspect of the invention, a kind of processing method of knowledge data is provided.The described method includes: obtain to
The knowledge data of detection；Knowledge data to be detected is analyzed, the structural knowledge of knowledge data to be detected is obtained；It detects to be checked
The knowledge data of survey with have with reference to knowledge data with the presence or absence of conflicting.Wherein, the detection includes by knowledge number to be detected
According to structural knowledge with the structural knowledge knowledge-based inference with reference to knowledge data had according to two or more obtain
To structural knowledge be compared, with determination knowledge data to be detected with have with reference to knowledge data with the presence or absence of conflicting.
In some embodiments, the method also includes: detecting knowledge data to be detected and having with reference to knowledge number
Before with the presence or absence of conflict, according to preset attribute constraint detected rule, determine that the structuring of knowledge data to be detected is known
Know and whether meets preset attribute constraint condition.
In some embodiments, the knowledge data includes causal knowledge data, and the knowledge reasoning includes causal knowledge
Reasoning and the conflict include causality conflict.
In some embodiments, causal knowledge data comprise at least one of the following:
A → B indicates that A is the immediate cause of B；
Indicate that A is not the immediate cause of B；
A-B indicates there is direct causality between A and B；
A ⊥ B indicates that A and B will not influence each other；
Indicate that A will affect B；
Indicate that A will not influence B；
A~B indicates that A and B is related；
A≤B, indicate the order of the A in the chain of causation prior to B,
Wherein A indicates the main body in causal knowledge data, and B indicates the object in causal knowledge data, the symbol between A and B
Number indicate causal knowledge data in predicate.
In some embodiments, causal knowledge reasoning includes at least one of the following:
According to having with reference to knowledge data A → B and B → C, reasoning obtains A → B, B → C and
According to having with reference to knowledge data A → B and A-B, reasoning obtains A → B；
According to having with reference to knowledge data A → B and B-A, reasoning obtains A → B；
According to having with reference to knowledge data A → B andReasoning obtains A → B,With
According to having with reference to knowledge data A → B andReasoning obtains A → B,With
According to having with reference to knowledge data A → B and A~B, reasoning obtains A → B；
According to having with reference to knowledge data A → B and B~A, reasoning obtains A → B；
According to having with reference to knowledge data A → B and A≤B, reasoning obtains A → B；
According to having with reference to knowledge data A → B and C≤A, reasoning obtains A → B, C≤A and C≤B；
Knowledge data is referred to according to havingAnd A-B, reasoning obtain B → A；
Knowledge data is referred to according to havingAnd B-A, reasoning obtain B → A；
Knowledge data is referred to according to havingWith A ⊥ B, reasoning obtains A ⊥ B；
Knowledge data is referred to according to havingWith B ⊥ A, reasoning obtains B ⊥ A；
According to having with reference to knowledge data A-B andReasoning obtainsWith A → B；
According to having with reference to knowledge data A-B andReasoning obtainsWith B → A；
According to having with reference to knowledge data A-B andReasoning obtains B → A；
According to having with reference to knowledge data A-B andReasoning obtains A → B；
According to having with reference to knowledge data A-B and A≤B, reasoning obtains A → B；
According to having with reference to knowledge data A-B and B≤A, reasoning obtains B → A；
Knowledge data is referred to according to havingWithReasoning obtainsWith
Knowledge data is referred to according to havingWith A~B, reasoning is obtained
Knowledge data is referred to according to havingWith B~A, reasoning is obtained
Knowledge data is referred to according to havingWith A≤B, reasoning is obtained
Knowledge data is referred to according to havingWith C≤A, reasoning is obtainedC≤A and C≤B；And
According to having with reference to knowledge data A≤B and B≤C, reasoning obtains A≤B, B≤C and A≤C.
In some embodiments, causality conflict includes at least one of the following:
A → B and B → A,A ⊥ B, B ⊥ A, With any of B≤A conflict；
Conflict with A → B；
Any of A-B and A ⊥ B and B ⊥ A conflict；
A ⊥ B and A → B, B → A, A-B, B-A,A~B,With any of B~A conflict；
With B → A, Any of B≤A, A ⊥ B and B ⊥ A conflict；
With A → B andAny of conflict；
Any of A~B and A ⊥ B and B ⊥ A conflict；
A≤B and B → A andAny of conflict.
According to the second aspect of the invention, a kind of processing equipment of knowledge data is provided.The processing equipment includes: one
A or multiple processors；And storage device, for storing one or more programs.Wherein, when one or more of programs
When being executed by one or more of processors, so that one or more of processors are configured as executing the above method.
According to the third aspect of the invention we, a kind of computer readable storage medium is provided, computer is stored thereon with and refers to
Enable, described instruction when being executed by processor, realize method described above the step of.
Detailed description of the invention
Illustrate preferred embodiment of the present disclosure with reference to the accompanying drawing, will make above-mentioned and other purposes of the invention, feature and
Advantage is clearer, in which:
Fig. 1 shows the schematic flow diagram of the method for processing knowledge data according to an embodiment of the present invention；
Fig. 2 shows the schematic flow diagrams of the method for processing knowledge data according to another embodiment of the present invention；
Fig. 3 shows the schematic block diagram of the equipment of processing knowledge data according to an embodiment of the present invention.
In all attached drawings of the disclosure, the same or similar appended drawing reference mark indicates the same or similar element.
Specific embodiment
The principle and spirit of the disclosure are described below in conjunction with attached drawing with reference to several exemplary embodiments.It should be appreciated that
These embodiments are provided merely to making those skilled in the art can better understand that realizing the disclosure in turn, and be not to appoint
Where formula limits the scope of the present disclosure.In addition, for simplicity being omitted to the known skill not being directly linked with the present invention
The detailed description of art, to prevent the understanding of the present invention from causing to obscure.
Terms used herein are only used for description exemplary embodiment, are not intended to limit exemplary embodiment.As herein
It uses, unless explicitly pointing out in context, otherwise singular is not excluded for also may include plural form.It should also be understood that working as
When using in the present specification, "and/or" includes the related one or more any and all combinations for listing item.Term " packet
Include " and/or " having " regulation there are cited features, number, step, operation, component, element or combinations thereof, and be not excluded for
In the presence of or add other one or more features, number, step, operation, component, element or combinations thereof.
Unless otherwise defined explicitly, otherwise all terms used herein have in exemplary embodiment fields
The identical meaning that those of ordinary skill is generally understood.It is also understood that unless separately explicitly defining herein, term should
The consistent meaning of meaning being interpreted as having in the specification understood with those of ordinary skill in the art when the invention time.
The embodiment of the present invention proposes the processing method and equipment of a kind of knowledge data, when detecting Knowledge Conflicts, no
It only accounts for new knowledge and each item in knowledge base has between knowledge with the presence or absence of conflicting, and consider new knowledge and knowledge
With the presence or absence of conflict between the combination of a plurality of knowledge in library.This improves the accuracys of detection data conflict.Correspondingly,
The accuracy rate of the knowledge data in knowledge base constructed using the knowledge data processing method of the embodiment of the present invention is improved.
In order to make it easy to understand, being briefly described below to several terms used in the present invention.In the disclosure, knowledge
Library refers to the needs solved for a certain (or certain) field question, is being counted using certain (or several) knowledge representation mode
The knowledge collection interknited for storing, organize, managing and using in calculation machine memory.Collision detection refers to that detection difference is known
It whether there is contradiction between knowledge.
Fig. 1 shows the schematic flow diagram of the method 100 of processing knowledge data according to an embodiment of the present invention.
As previously mentioned, needing when constructing knowledge base using the knowledge data in multiple knowledge data sources to therein
Knowledge data is handled, and detects the conflict between knowledge data, the knowledge of debug.In this case, it can be used
According to the method for the embodiment of the present invention 100.
As shown, in step s 110, obtaining knowledge data to be detected.Can from various knowledge data sources obtain to
The knowledge data of detection.Knowledge data source for example can be various knowledge bases, such as expert knowledge library, internet knowledge base.
Knowledge data can be one or more sentences in knowledge base.The example of knowledge data is as " Nanjing is located in China
Eastern region, THE LOWER YANGTZE VALLEY are provincial capitals of Jiangsu Province ", for another example " sales volume that temperature directly affects beer ".
In the step s 120, knowledge data to be detected is analyzed, the structural knowledge of knowledge data to be detected is obtained.
In some instances, main body, the data of predicate and object can be extracted from knowledge data to be detected, obtained to be checked
The structural knowledge of the knowledge data of survey.For example, main body can be the subject in knowledge data, predicate be can be in knowledge data
Predicate, object can be the object in knowledge data.The structural knowledge of knowledge data can be by main body, predicate and object
The knowledge data of composition.For example, " Nanjing is located in East China, THE LOWER YANGTZE VALLEY, is provincial capital of Jiangsu Province " such knowledge,
It can be structured as (Nanjing is provincial capital of Jiangsu Province).
In some instances, the causality between noun and noun can be extracted from knowledge data to be detected, obtained
To the structural knowledge of knowledge data to be detected (this knowledge is also referred to as causal knowledge data).For example, " temperature directly affects
The such knowledge of the sales volume of beer ", can be structured as (temperature directly affects, the sales volume of beer).
In step s 130, detect knowledge data to be detected with have with reference to knowledge data with the presence or absence of conflicting.
Having, which can be with reference to knowledge data, has been acknowledged as accurate knowledge data.Having can be with reference to knowledge data
Selected from knowledge data existing in building knowledge base.Optionally, having can be with reference to knowledge data selected from as reference source
There is no the knowledge datas of the existing knowledge base (such as expert knowledge library) of conflict.
Particularly, detection in step s 130 may include by the structural knowledge and basis of knowledge data to be detected
Two or more has is compared with reference to the structural knowledge that the structural knowledge knowledge-based inference of knowledge data obtains
Compared with, with determination knowledge data to be detected with have with reference to knowledge data with the presence or absence of conflicting.In other words, in the embodiment of the present invention
In, it not only include that each item has with reference to knowledge with the references object that knowledge data to be detected compares when detecting conflict
Data itself, and have the knowledge number obtained with reference to knowledge data knowledge-based inference algorithm reasoning including two or more
According to.It should be understood that herein, referring to that the comparison between knowledge data refers between the respective structural knowledge of knowledge data
Comparison, rather than the comparison between knowledge data original text, this merely to description simplicity, hereafter repeat no more.
Knowledge data includes multiple types.For particular kind of knowledge data, there may be corresponding collision detection to advise
Then.
In the example of conflict between the structural knowledge that detection is made of main body, predicate and object, when two knowledge
Main body, predicate it is identical with any two content informations in object, and when remaining one content information difference, can recognize
There is conflict for this two knowledge.
Optionally, in the example of the conflict between detection causality data, the causality contained by two knowledge
Between when there is conflict, it is believed that there is conflict in this two knowledge.
Mainly the collision detection in step S130 is illustrated with causal knowledge data instance below.For the ease of reason
Solution, in such embodiments, knowledge data to be detected and to have be causal knowledge data with reference to knowledge data.It removes below
Separately have and express, knowledge or knowledge data generally refer to causal knowledge data.Have with reference to knowledge data can based on such as because
The knowledge reasoning algorithm reasoning of fruit knowledge reasoning etc is obtained with reference to knowledge data set.It is deposited when between two causal knowledge data
It can be assumed that the two has conflict in causality conflict.
For causal knowledge data, 8 kinds can be summarized as, is described in table 1 below according to causality predicate.
Table 1
It is a plurality of with reference to knowledge for what is selected, causal knowledge reasoning can be carried out according to the inference rule of following table 2, obtained
To reference knowledge data set.
Table 2
Table 2 shows two existing causal knowledge data (as shown in that column of existing causality) by causal knowledge reasoning
Obtained causal knowledge data acquisition system (as shown in that column of the reasoning results).
It is readily appreciated that, can be obtained based on the rule of table 2 by the principle of combination of two with reasoning even more by three
Item has the causal knowledge data acquisition system that causal knowledge data reasoning obtains.For example, according to three existing causal knowledge data: A
→ B, B → C, C → D can obtain A → B, B → C, C → D with reasoning,
Every one kind causal knowledge has corresponding conflict to gather.Table 3 below shows every a kind of causal knowledge and its punchings
Prominent collection.
Table 3
In step s 130, detect knowledge data to be detected with have with reference to knowledge data with the presence or absence of conflicting and can lead to
It crosses and detects whether knowledge data to be detected is having with reference to determining in the conflict set of knowledge data and its reasoning results.If
Knowledge to be detected has any with reference in the conflict set of knowledge data or its reasoning results, then can determine to be detected
Knowledge data with have with reference to knowledge data exist conflict.
It should be understood that 100 being not limited to step and sequence illustrated above according to the method for the embodiment of the present invention.
Optionally, before step S130, pre-detection step can be first carried out.It, can basis in the pre-detection step
Preset attribute constraint detected rule, determines whether the structural knowledge of knowledge data to be detected meets preset attribute constraint
Condition.For example, needing to meet constraint condition, (age is greater than 0, and the age is small when the attribute information of main body or object is the age
In 200).
Optionally, in step s 130, when have with reference to knowledge data selected from knowledge data existing in building knowledge base
When, knowledge base can be traversed, with detect knowledge data to be detected whether with existing knowledge data exist conflict.
The 100 each items not only allowed in new knowledge and knowledge base have between knowledge according to the method for the embodiment of the present invention
With the presence or absence of conflict, and considers to whether there is between new knowledge and the combination of a plurality of knowledge in knowledge base and conflict.Therefore,
It can be found that more conflict knowledge data, improve collision detection accuracy rate.
In the following, with reference to Fig. 2 shows a preferred embodiment of the present invention.Fig. 2 shows another embodiments according to the present invention
Processing knowledge data method 200 schematic flow diagram.Method 200 can be used for constructing the knowledge base of high-accuracy.
As shown, in step S210, available knowledge data (hereinafter also referred to as new knowledge) to be detected.
Specifically, knowledge data to be detected can be obtained from some source, such as expert knowledge library, internet knowledge base
Deng.
In step S220, knowledge data to be detected can be handled as structural knowledge.
Specifically, main body, the data of predicate and object are extracted from knowledge data to be detected, obtain corresponding structuring
Knowledge data.For example, " sales volume that temperature directly affects beer " such knowledge, can be structured as (temperature, direct shadow
Ring, the sales volume of beer), and it is labeled as m → n, wherein m indicates that temperature, n indicate the sales volume of beer, → indicate the former direct shadow
Ring the latter.
In optional step S230, it can be determined that whether meet attribute constraint condition.
It specifically, can be according to preset attribute constraint detected rule to the subject and object in knowledge data to be detected
Attribute information analyzed, determine whether knowledge data to be detected meets preset attribute constraint condition.For example, working as attribute
When information is the age, needing to meet constraint condition, (age is greater than 0, and the age is less than 200).
If judgement is unsatisfactory for attribute constraint condition, then method proceeds to step S240 in step S230.In step
In S240, output attribute miscue information.
If judgement meets attribute constraint condition, then method proceeds to step S250 in step S230.In step S250
In, from selected in building knowledge base several existing causal knowledge data as with reference to knowledge.Due to knowledge data to be detected
May between acquainted combination a plurality of in knowledge base exist conflict, it is therefore desirable to once from database selection two or
More a plurality of existing knowledge, to judge whether knowledge data to be detected exists with the combinations of these knowledge in the following step
Conflict.
In step S260, for a plurality of existing knowledge selected, according to causal knowledge reasoning, its corresponding knowledge is obtained
Set.For example, when once select two knowledge when, can by directly according to table 2 in a manner of carry out causal knowledge reasoning.When primary choosing
Three or when more a plurality of knowledge out, as previously described can be according to the principle of table 2, such as by way of combination of two, pass through
Reasoning obtains corresponding knowledge collection.
As an example, if having knowledge in knowledge baseWith p≤m, then by inference rule 24, can infer p≤
N, to obtain knowledge collectionP≤m and p≤n.
In step S270, according to collision detection algorithm, whether knowledge data to be detected and existing knowledge data are detected
There are conflicts.
As shown in table 3, every a kind of causal knowledge data have corresponding conflict to gather.When carrying out collision detection, need
Several knowledge and its reasoning results (being obtained in step S260) that whether detection new knowledge is selected in step s 250 one by one
Conflict set in.
For example, if new knowledge isThe two existing knowledge selected from knowledge base in step s 250 areWith p≤m, goes out p≤n by this two knowledge reasonings in step S260, obtain knowledge collectionP≤m and p≤
n.Then, it when carrying out collision detection in step S270, needs successively to detectWhetherP≤m, p≤n this
In the conflict set of three knowledge.In this example, due toIn the conflict set of p≤n, therefore there is conflict.
If detecting conflict in step S270, then method proceeds to step S280.In step S280, output conflict
Prompt information.
If not detecting conflict in step S280, then method proceeds to step S290.In step S290, judgement
Whether entire knowledge base is traversed.If it is not, then method returns in step S250, from selected in building knowledge base in addition several it is existing
Causal knowledge data, which are used as, refers to knowledge.Then proceed to abovementioned steps S260~290, detect knowledge data to be detected whether with
There is conflict in this several existing causal knowledge data being selected from.
If judgement has had stepped through entire knowledge base in step S290, method proceeds to step S295, will test
At knowledge data be added database.
200 when detecting Knowledge Conflicts according to the method for the embodiment of the present invention, and knowledge-based inference algorithm, consideration will be added
The new knowledge to be detected of knowledge base and in knowledge base between the acquainted various combinations of institute with the presence or absence of conflicting, and to knowledge base
Various combinations traversed.Method of knowledge processing based on the disclosure can detecte out new knowledge and knowledge in knowledge base
All conflicts smoothly realize the building of knowledge base, improve the accuracy rate of knowledge base.
Fig. 3 diagrammatically illustrates the schematic block diagram of the processing equipment 300 of knowledge data according to an embodiment of the present invention.
As shown in figure 3, the processing equipment includes processing unit or processor 136.The processor 136 can be individual unit
Or the combination of multiple units, for executing various operations, the method including processing knowledge data according to an embodiment of the present invention,
Such as method 100 or 200.Processing equipment 300 may also include that input unit 132, for receiving signal from other equipment or component；
And output unit 134, for providing signal to other equipment or component.Input unit and output unit can be arranged to one
A entirety.
In addition, being deposited in storage device 138 as shown, processing equipment 300 further includes one or more storage devices 138
Contain computer program 139.
Computer program 139 may include code/computer executable instructions, make when being executed by processor 136
Processor 136 executes for example above in conjunction with the operating process of method described in FIG. 1 to FIG. 2 and its any deformation.
Computer program 139 can be configured to have the computer program code for example including computer program module.Example
Such as, in the exemplary embodiment, the code in computer program 139 may include one or more program modules, for example including
139A, module 139B ....It should be noted that the division mode and number of module are not fixation, those skilled in the art can
To be combined according to the actual situation using suitable program module or program module, when these program modules are combined by processor 136
When execution, processor 136 is executed for example above in conjunction with method flow described in Fig. 1 and Fig. 2 and its any deformation.
Having been combined preferred embodiment above, invention has been described.At knowledge data according to an embodiment of the present invention
Reason method can detecte out new knowledge and conflict with all of knowledge in knowledge base, smoothly realize the building of knowledge base, improve knowledge
The accuracy rate in library.
It is appreciated that device and method illustrated above are merely exemplary.Equipment of the invention may include than showing
The more or fewer components of component.Method of the invention is not limited to step and sequence illustrated above.Art technology
Personnel can carry out many change and modification according to the introduction of illustrated embodiment.
It can be by there is the electricity of computing capability according to the above method of each embodiment of the application, device, unit and/or module
Sub- equipment executes the software comprising computer instruction to realize.The system may include storage equipment, described above to realize
Various storages.The electronic equipment for having computing capability may include general processor, digital signal processor, dedicated processes
Device, re-configurable processor etc. are able to carry out the device of computer instruction, but not limited to this.Such instruction is executed so that electricity
Sub- equipment is configured as executing the above-mentioned operations according to the application.Above-mentioned each equipment and/or module can be in an electronics
It realizes, can also be realized in distinct electronic apparatuses in equipment.These softwares may be stored in a computer readable storage medium.
Computer-readable recording medium storage one or more program (software module), one or more of programs include instruction, when
When one or more processors in electronic equipment execute described instruction, described instruction makes electronic equipment execute the side of the application
Method.
These softwares can store the form for volatile memory or non-volatile memory device (such as similar to ROM etc.
Store equipment), it is whether erasable or rewritable, or it is stored as form (such as the RAM, storage core of memory
Piece, equipment or integrated circuit), or be stored on light readable medium or magnetic readable medium (for example, CD, DVD, disk or magnetic
Band etc.).It should be appreciated that storage equipment and storage medium are adapted for storing the machine readable storage dress of one or more programs
The embodiment set, one program or multiple programs include instruction, when executed, realize the implementation of the application
Example.Embodiment provides program and stores the machine-readable storage device of this program, and described program includes for realizing the application
Any one claim described in device or method code.Furthermore, it is possible to via any medium (for example, via wired
Connection is wirelessly connected the signal of communication carried) it sends a telegram here and transmits these programs, multiple embodiments uitably include these programs.
Such as field programmable gate can also be used according to the method, apparatus of each embodiment of the application, unit and/or module
Array (FPGA), programmable logic array (PLA), system on chip, the system on substrate, the system in encapsulation, dedicated integrated electricity
Road (ASIC) can be for carrying out the hardware such as any other rational method that is integrated or encapsulating or firmware in fact to circuit
It is existing, or realized with software, the appropriately combined of three kinds of implementations of hardware and firmware.The system may include storage equipment,
To realize storage as described above.When realizing in such ways, used software, hardware and/or firmware be programmed or
It is designed as executing the corresponding above method, step and/or the function according to the application.Those skilled in the art can be according to practical need
Come suitably by one or more of these systems and module, or in which a part or multiple portions use it is different upper
Implementation is stated to realize.These implementations each fall within the protection scope of the application.
Although the application, art technology has shown and described referring to the certain exemplary embodiments of the application
Personnel it should be understood that in the case where the spirit and scope limited without departing substantially from the following claims and their equivalents,
A variety of changes in form and details can be carried out to the application.Therefore, scope of the present application should not necessarily be limited by above-described embodiment,
But should be not only determined by appended claims, also it is defined by the equivalent of appended claims.
Claims (13)
1. a kind of processing method of knowledge data, comprising:
Knowledge data to be detected is obtained,
Knowledge data to be detected is analyzed, the structural knowledge of knowledge data to be detected is obtained,
Detect knowledge data to be detected with have with reference to knowledge data with the presence or absence of conflicting,
Wherein, the detection includes having ginseng by the structural knowledge of knowledge data to be detected and according to two or more
It examines the structural knowledge that the structural knowledge knowledge-based inference of knowledge data obtains to be compared, with determination knowledge to be detected
Data with have with reference to knowledge data with the presence or absence of conflicting.
2. according to the method described in claim 1, further include:
According to preset attribute constraint detected rule, it is preset to determine whether the structural knowledge of knowledge data to be detected meets
Attribute constraint condition.
3. according to the method described in claim 1, wherein the knowledge data includes causal knowledge data, the knowledge reasoning packet
Including causal knowledge reasoning and the conflict includes causality conflict.
4. according to the method described in claim 3, wherein causal knowledge data comprise at least one of the following:
A → B indicates that A is the immediate cause of B；
Indicate that A is not the immediate cause of B；
A-B indicates there is direct causality between A and B；
A ⊥ B indicates that A and B will not influence each other；
Indicate that A will affect B；
Indicate that A will not influence B；
A~B indicates that A and B is related；
A≤B, indicate the order of the A in the chain of causation prior to B,
Wherein A indicates the main body in causal knowledge data, and B indicates the object in causal knowledge data, the symbol table between A and B
Show the predicate in causal knowledge data.
5. according to the method described in claim 4, wherein, the causal knowledge reasoning includes at least one of the following:
According to having with reference to knowledge data A → B and B → C, reasoning obtains A → B, B → C and
According to having with reference to knowledge data A → B and A-B, reasoning obtains A → B；
According to having with reference to knowledge data A → B and B-A, reasoning obtains A → B；
According to having with reference to knowledge data A → B andReasoning obtains A → B,With
According to having with reference to knowledge data A → B andReasoning obtains A → B,With
According to having with reference to knowledge data A → B and A~B, reasoning obtains A → B；
According to having with reference to knowledge data A → B and B~A, reasoning obtains A → B；
According to having with reference to knowledge data A → B and A≤B, reasoning obtains A → B；
According to having with reference to knowledge data A → B and C≤A, reasoning obtains A → B, C≤A and C≤B；
Knowledge data is referred to according to havingAnd A-B, reasoning obtain B → A；
Knowledge data is referred to according to havingAnd B-A, reasoning obtain B → A；
Knowledge data is referred to according to havingWith A ⊥ B, reasoning obtains A ⊥ B；
Knowledge data is referred to according to havingWith B ⊥ A, reasoning obtains B ⊥ A；
According to having with reference to knowledge data A-B andReasoning obtainsWith A → B；
According to having with reference to knowledge data A-B andReasoning obtainsWith B → A；
According to having with reference to knowledge data A-B andReasoning obtains B → A；
According to having with reference to knowledge data A-B andReasoning obtains A → B；
According to having with reference to knowledge data A-B and A≤B, reasoning obtains A → B；
According to having with reference to knowledge data A-B and B≤A, reasoning obtains B → A；
Knowledge data is referred to according to havingWithReasoning obtainsWith
Knowledge data is referred to according to havingWith A~B, reasoning is obtained
Knowledge data is referred to according to havingWith B~A, reasoning is obtained
Knowledge data is referred to according to havingWith A≤B, reasoning is obtained
Knowledge data is referred to according to havingWith C≤A, reasoning is obtainedC≤A and C≤B；And
According to having with reference to knowledge data A≤B and B≤C, reasoning obtains A≤B, B≤C and A≤C.
6. according to the method described in claim 4, wherein, the causality conflict includes at least one of the following:
A → B and B → A,A ⊥ B, B ⊥ A,With any of B≤A conflict；
Conflict with A → B；
Any of A-B and A ⊥ B and B ⊥ A conflict；
A ⊥ B and A → B, B → A, A-B, B-A,A~B,With any of B~A conflict；
With B → A,Any of B≤A, A ⊥ B and B ⊥ A conflict；
With A → B andAny of conflict；
Any of A~B and A ⊥ B and B ⊥ A conflict；
A≤B and B → A andAny of conflict.
7. a kind of processing equipment of knowledge data, comprising:
One or more processors；And
Storage device, for storing one or more programs,
Wherein, when one or more of programs are executed by one or more of processors, so that one or more of
Processor is configured as:
Knowledge data to be detected is obtained,
Knowledge data to be detected is analyzed, the structural knowledge of knowledge data to be detected is obtained,
Detect knowledge data to be detected with have with reference to knowledge data with the presence or absence of conflicting,
Wherein, the detection includes having ginseng by the structural knowledge of knowledge data to be detected and according to two or more
It examines the structural knowledge that the structural knowledge knowledge-based inference of knowledge data obtains to be compared, with determination knowledge to be detected
Data with have with reference to knowledge data with the presence or absence of conflicting.
8. processing equipment according to claim 7, one or more of processors are also configured to
According to preset attribute constraint detected rule, it is preset to determine whether the structural knowledge of knowledge data to be detected meets
Attribute constraint condition.
9. processing equipment according to claim 7, wherein the knowledge data includes causal knowledge data, the knowledge is pushed away
Reason includes causal knowledge reasoning and the conflict includes causality conflict.
10. processing equipment according to claim 9, wherein causal knowledge data comprise at least one of the following:
A → B indicates that A is the immediate cause of B；
Indicate that A is not the immediate cause of B；
A-B indicates there is direct causality between A and B；
A ⊥ B indicates that A and B will not influence each other；
Indicate that A will affect B；
Indicate that A will not influence B；
A~B indicates that A and B is related；
A≤B, indicate the order of the A in the chain of causation prior to B,
Wherein A indicates the main body in causal knowledge data, and B indicates the object in causal knowledge data, the symbol table between A and B
Show the predicate in causal knowledge data.
11. processing equipment according to claim 10, wherein the causal knowledge reasoning includes at least one in following
:
According to having with reference to knowledge data A → B and B → C, reasoning obtains A → B, B → C and
According to having with reference to knowledge data A → B and A-B, reasoning obtains A → B；
According to having with reference to knowledge data A → B and B-A, reasoning obtains A → B；
According to having with reference to knowledge data A → B andReasoning obtains A → B,With
According to having with reference to knowledge data A → B andReasoning obtains A → B,With
According to having with reference to knowledge data A → B and A~B, reasoning obtains A → B；
According to having with reference to knowledge data A → B and B~A, reasoning obtains A → B；
According to having with reference to knowledge data A → B and A≤B, reasoning obtains A → B；
According to having with reference to knowledge data A → B and C≤A, reasoning obtains A → B, C≤A and C≤B；
Knowledge data is referred to according to havingAnd A-B, reasoning obtain B → A；
Knowledge data is referred to according to havingAnd B-A, reasoning obtain B → A；
Knowledge data is referred to according to havingWith A ⊥ B, reasoning obtains A ⊥ B；
Knowledge data is referred to according to havingWith B ⊥ A, reasoning obtains B ⊥ A；
According to having with reference to knowledge data A-B andReasoning obtainsWith A → B；
According to having with reference to knowledge data A-B andReasoning obtainsWith B → A；
According to having with reference to knowledge data A-B andReasoning obtains B → A；
According to having with reference to knowledge data A-B andReasoning obtains A → B；
According to having with reference to knowledge data A-B and A≤B, reasoning obtains A → B；
According to having with reference to knowledge data A-B and B≤A, reasoning obtains B → A；
Knowledge data is referred to according to havingWithReasoning obtainsWith
Knowledge data is referred to according to havingWith A~B, reasoning is obtained
Knowledge data is referred to according to havingWith B~A, reasoning is obtained
Knowledge data is referred to according to havingWith A≤B, reasoning is obtained
Knowledge data is referred to according to havingWith C≤A, reasoning is obtainedC≤A and C≤B；And
According to having with reference to knowledge data A≤B and B≤C, reasoning obtains A≤B, B≤C and A≤C.
12. processing equipment according to claim 10, wherein the causality conflict includes at least one of the following:
A → B and B → A,A ⊥ B, B ⊥ A,WithAny of conflict；
Conflict with A → B；
Any of A-B and A ⊥ B and B ⊥ A conflict；
A ⊥ B and A → B, B → A, A-B, B-A,A~B,With any of B~A conflict；
With B → A,Any of B≤A, A ⊥ B and B ⊥ A conflict；
With A → B andAny of conflict；
Any of A~B and A ⊥ B and B ⊥ A conflict；
A≤B and B → A andAny of conflict.
13. a kind of computer readable storage medium is stored thereon with computer instruction, described instruction when being executed by processor,
The step of realizing method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710354503.2A CN108959290A (en) | 2017-05-18 | 2017-05-18 | The processing method and equipment of knowledge data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710354503.2A CN108959290A (en) | 2017-05-18 | 2017-05-18 | The processing method and equipment of knowledge data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108959290A true CN108959290A (en) | 2018-12-07 |
Family
ID=64462555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710354503.2A Pending CN108959290A (en) | 2017-05-18 | 2017-05-18 | The processing method and equipment of knowledge data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108959290A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111198876A (en) * | 2020-01-02 | 2020-05-26 | 泰康保险集团股份有限公司 | Data cleaning method and device based on knowledge base |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5197116A (en) * | 1989-07-10 | 1993-03-23 | Hitachi, Ltd. | Method of resolution for rule conflict in a knowledge based system |
| CN105279277A (en) * | 2015-11-12 | 2016-01-27 | 百度在线网络技术（北京）有限公司 | Knowledge data processing method and device |
| CN105354224A (en) * | 2015-09-30 | 2016-02-24 | 百度在线网络技术（北京）有限公司 | Knowledge data processing method and apparatus |
| CN106156083A (en) * | 2015-03-31 | 2016-11-23 | 联想(北京)有限公司 | A kind of domain knowledge processing method and processing device |
| CN106649394A (en) * | 2015-11-03 | 2017-05-10 | 中兴通讯股份有限公司 | Fusion knowledge base processing method and device and knowledge base management system |
-
2017
- 2017-05-18 CN CN201710354503.2A patent/CN108959290A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5197116A (en) * | 1989-07-10 | 1993-03-23 | Hitachi, Ltd. | Method of resolution for rule conflict in a knowledge based system |
| CN106156083A (en) * | 2015-03-31 | 2016-11-23 | 联想(北京)有限公司 | A kind of domain knowledge processing method and processing device |
| CN105354224A (en) * | 2015-09-30 | 2016-02-24 | 百度在线网络技术（北京）有限公司 | Knowledge data processing method and apparatus |
| CN106649394A (en) * | 2015-11-03 | 2017-05-10 | 中兴通讯股份有限公司 | Fusion knowledge base processing method and device and knowledge base management system |
| CN105279277A (en) * | 2015-11-12 | 2016-01-27 | 百度在线网络技术（北京）有限公司 | Knowledge data processing method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111198876A (en) * | 2020-01-02 | 2020-05-26 | 泰康保险集团股份有限公司 | Data cleaning method and device based on knowledge base |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11734583B2 (en) | Automated creation of semantically-enriched diagnosis models | |
| CA2940752C (en) | Intelligent visualization munging | |
| EP3032409B1 (en) | Transitive source code violation matching and attribution | |
| US10366371B2 (en) | Method and apparatus for processing service requests | |
| US10572822B2 (en) | Modular memoization, tracking and train-data management of feature extraction | |
| US10042932B2 (en) | Analytics based on pipes programming model | |
| US9208209B1 (en) | Techniques for monitoring transformation techniques using control charts | |
| CN101751333A (en) | Method, computer program and computer system for assisting in analyzing program | |
| US9489433B2 (en) | User interface for predictive model generation | |
| CN109583470A (en) | A kind of explanation feature of abnormality detection determines method and apparatus | |
| US9910487B1 (en) | Methods, systems and computer program products for guiding users through task flow paths | |
| KR20130058336A (en) | Analysis apparatus and method for usability of mobile application using user bebavior log | |
| US20190086908A1 (en) | Devices, methods, and systems for a distributed rule based automated fault detection | |
| CN113849166B (en) | Intelligent water environment building block type zero-code development platform | |
| US20180267522A1 (en) | Manufacturing process analysis device, manufacturing process analysis method, and recording medium whereupon manufacturing process analysis program is stored | |
| US20170242661A1 (en) | Module Division Assistance Device, Module Division Assistance Method, and Module Division Assistance Program | |
| CN108959290A (en) | The processing method and equipment of knowledge data | |
| US9563540B2 (en) | Automated defect positioning based on historical data | |
| Aslanyan et al. | Model checking exact cost for attack scenarios | |
| US20220206773A1 (en) | Systems and methods for building and deploying machine learning applications | |
| US8261227B2 (en) | Circuit design approximation | |
| CN112015912B (en) | Intelligent index visualization method and device based on knowledge graph | |
| US20160178590A1 (en) | System and method for predicting harmful materials | |
| US8010477B2 (en) | Integrated problem solving system | |
| US9286353B2 (en) | Method for generating processing specifications for a stream of data items |
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 |