CN115618140B - Data processing system for acquiring link entity - Google Patents
Data processing system for acquiring link entity Download PDFInfo
- Publication number
- CN115618140B CN115618140B CN202211538039.XA CN202211538039A CN115618140B CN 115618140 B CN115618140 B CN 115618140B CN 202211538039 A CN202211538039 A CN 202211538039A CN 115618140 B CN115618140 B CN 115618140B
- Authority
- CN
- China
- Prior art keywords
- entity
- priority
- preset
- obtaining
- key
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9558—Details of hyperlinks; Management of linked annotations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/382—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using citations
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a data processing system for obtaining a link entity, which comprises: an initial entity list, a preset entity tag priority set, a processor, and a memory storing a computer program that, when executed by the processor, performs the steps of: comparing the number of the initial entities with a preset entity number threshold, and when the number of the initial entities is smaller than the preset entity number threshold, acquiring a key entity set corresponding to an initial entity list so as to acquire a target priority set corresponding to the key entity set, wherein the label priority is the association degree between any entity label and other entity labels or any entity, and acquiring a link entity corresponding to the initial entities according to the target priority set; according to the method and the device, when the link entity is obtained, the entity label corresponding to the entity and the association degree between the entity label and the entity label are considered, and the accuracy of the obtained link entity is improved.
Description
Technical Field
The invention relates to the technical field of entity linking, in particular to a data processing system for acquiring a linked entity.
Background
With the popularization and development of the internet, a large amount of information data is stored in an internet platform, for example, a large amount of text information is stored in databases such as encyclopedia, wikipedia and the like, and how to process the text information in the databases to obtain valuable information becomes a popular research direction at present.
At present, the method for acquiring the link entity in the prior art is as follows: and acquiring entities in the text, traversing all candidate entities associated with the entities in the text in the knowledge base to perform entity link, and selecting the candidate entity with the highest priority corresponding to the candidate entity as a link entity.
In summary, the method for acquiring the link entity has the following problems: when the link entity is obtained, the link entity is limited to the entity, the entity tag corresponding to the entity and the association degree between the entity tag and the entity tag are not considered, and the accuracy of the obtained link entity is reduced.
Disclosure of Invention
Aiming at the technical problem, the technical scheme adopted by the invention is as follows: a data processing system for obtaining linked entities, comprising: initial entity list a = { a = 1 ，A 2 ，……，A i ，……，A m A, a set of preset entity tag priorities, a processor and a memory storing a computer program, wherein a i For the ith initial entity, i =1,2 \ 8230 \8230: \ 8230m, m is the number of initial entities, which when executed by a processor, performs the following steps:
s100, comparing m with a preset entity quantity threshold value m 0 And (6) carrying out comparison.
S110, when m is less than m 0 And acquiring a key entity set A '= { A' 1 ，A' 2 ，……，A' i ，……，A' m Key entity priority set FA '= { FA' 1 ，FA' 2 ，……，FA' i ，……，FA' m In which, A' i ={A' i1 ，A' i2 ，……，A' ij ，……，A' in }，A' ij Is A i Jth critical entity, FA 'in the corresponding list of critical entities' i ={FA' i1 ，FA' i2 ，……，FA' ij ，……，FA' in }，FA' ij Is A' ij The corresponding key entity priority, j =1,2 \8230, n is the number of key entities in the key entity list.
S120, according to a preset entity tag priority set, obtaining a target priority set RA ' = { RA ' corresponding to A ' 1 ，RA' 2 ，……，RA' i ，……，RA' m }，RA' i ={RA' i1 ，RA' i2 ，……，RA' ij ，……，RA' in }，RA' ij Is A' ij Corresponding target priority, wherein RA 'is obtained in S120 by' ij ：
S1201, obtaining A' ij Corresponding key entity tag A ij Wherein A is ij Is A 'obtained from a preset entity label list' ij And the corresponding preset entity tag.
S1203, according to U 0 Obtaining A ij Corresponding first intermediate label priority list PA ij ={PA 1 ij ，PA 2 ij ，……，PA r ij ，……，PA s ij }，PA r ij Is A ij A corresponding first mth middle tag priority; it can be understood that: when A is ij And U 0 fr When the corresponding preset entity labels are consistent, then U 0 fr =PA r ij 。
S1205, obtain A i Corresponding second intermediate tag label priority list KA' i ={KA' i1 ，KA' i2 ，……，KA' ir ，……，KA' is }，KA' ir Is A i Corresponding second mid-tag priority.
S1207, according to PA ij And KA' i Obtaining RA' ij 。
S130, according to RA' i Obtaining the linked entity list A corresponding to A 0 ={A 0 1j ，A 0 2j ，……，A 0 ij ，……，A 0 mj In which A 0 ij Is A i The linking entity of (2).
Compared with the prior art, the data processing system for acquiring the link entity has obvious beneficial effects, can achieve considerable technical progress and practicability by the technical scheme, has industrial wide utilization value, and at least has the following beneficial effects:
the invention provides a data processing system for obtaining a link entity, which comprises: an initial entity list, a set of preset entity tag priorities, a processor and a memory storing a computer program that, when executed by the processor, performs the steps of: comparing the number of initial entities with a preset entity number threshold, when the number of the initial entities is smaller than the preset entity number threshold, acquiring a key entity set corresponding to an initial entity list, acquiring a target priority set corresponding to the key entity set according to a preset entity tag priority set, wherein the preset entity tag priority is a tag priority between a preset entity tag and a non-preset entity tag, the tag priority is an association degree between any entity tag and other entity tags or any entity, and acquiring a link entity corresponding to the initial entities according to the target priority set; in the above, when the link entity is obtained, the link entity is not limited to the entity itself, the entity tag corresponding to the entity and the association degree between the entity tag and the entity tag are considered, and the accuracy of the obtained link entity is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart illustrating a computer program executed by a data processing system for obtaining a linked entity according to an embodiment of the present invention;
fig. 2 is a flowchart of the step S120 according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a computer program executed by a data processing system for obtaining a linking entity according to a second embodiment of the present invention;
fig. 4 is a flowchart of a computer program executed by a data processing system for acquiring a linked entity according to a first embodiment of the present invention;
fig. 5 is a flowchart of a computer program executed by a data processing system for acquiring a linked entity according to a first embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
This embodiment provides a data processing system for acquiring a linked entity, where the system includes: initial entity list a = { a = 1 ，A 2 ，……，A i ，……，A m A, a set of preset entity tag priorities, a processor and a memory storing a computer program, wherein a i I =1,2 \8230, 8230, m, m is the number of initial entities; when the computer program is executed by a processor, it is implementedNow the following steps are shown in fig. 1:
s100, comparing m with a preset entity quantity threshold value m 0 And (6) carrying out comparison.
In particular, m 0 Is 3.
S110, when m is less than m 0 And then, obtaining a key entity set A '= { A' 1 ，A' 2 ，……，A' i ，……，A' m Key entity priority set FA '= { FA' 1 ，FA' 2 ，……，FA' i ，……，FA' m In which, A' i ={A' i1 ，A' i2 ，……，A' ij ，……，A' in }，A' ij Is A i J-th key entity, FA 'in corresponding key entity list' i ={FA' i1 ，FA' i2 ，……，FA' ij ，……，FA' in }，FA' ij Is A' ij And the corresponding priority of the key entities, j =1,2 \8230, wherein \8230n, n is the number of the key entities in the key entity list.
Specifically, the system further includes an initial text set, where the initial text set includes a plurality of initial texts, where the initial texts are texts obtained by a user through a crawler method from any web page, and as known to those skilled in the art, any crawler method in the prior art belongs to the protection scope of the present invention and is not described herein again.
Further, the initial entity is an entity obtained by inputting an initial text into the entity recognition model; those skilled in the art also know that any method for obtaining an entity through an entity identification model in the prior art belongs to the protection scope of the present invention, and is not described herein again; for example, the entity recognition model is a NER model.
Specifically, the system further includes a preset entity list, a preset entity tag list corresponding to the preset entity list, and a preset triplet set, where the preset entity list includes a plurality of preset entities, the preset entity tag list includes a preset entity tag corresponding to each preset entity, and the preset triplet set includes a preset triplet list corresponding to each preset entity, where the preset triplet list includes a plurality of preset triplets corresponding to each preset entity.
Furthermore, the preset entity is any entity obtained from a preset knowledge base, and those skilled in the art know that any knowledge base in the prior art belongs to the protection scope of the present invention, and is not described herein again; for example, the knowledge base is wikipedia, etc.
Furthermore, the preset entity tag is a unique tag representing an entity type corresponding to the preset entity, and those skilled in the art know that any method for obtaining the entity tag corresponding to the entity in the prior art belongs to the protection scope of the present invention, and is not described herein again.
Specifically, the key entity is an entity except the initial entity in each preset triplet in a preset triplet list corresponding to a preset entity consistent with the initial entity; for example, when the initial entity is beijing, the obtained key entities are beiping, yanjing, and the like.
Further, the key entity priority is a matching probability between the initial entity and the key entity corresponding to the initial entity, which is obtained by inputting the initial entity and the key entity corresponding to the initial entity into the entity matching model, where it is known to those skilled in the art that any entity matching model in the prior art belongs to the protection scope of the present invention, and is not described herein again.
Specifically, the preset entity tag priority set U 0 ={U 0 1 ，U 0 2 ，……，U 0 f ，……，U 0 z }，U 0 f ={U 0 f1 ，U 0 f2 ，……，U 0 fr ，……，U 0 fs }，U 0 fr F =1,2 8230for the tag priority between the f-th preset entity tag and the r-th non-preset entity tag, 8230z, r =1,2 8230for the number of preset entity tags, and r =1,2 8230z, 8230s, s, are non-preset entity tagsPresetting the number of entity labels; one skilled in the art will appreciate that the tag priority is the degree of association between any entity tag and other entity tags or any entity.
Further, the non-preset entity label is an entity label obtained by performing deduplication processing on a sample entity label, where the sample entity label is an entity label obtained by inputting a sample text into an entity recognition model, and a person skilled in the art knows that the sample text is a text used for training the entity recognition model and is not described herein again.
S120, according to a preset entity tag priority set, obtaining a target priority set RA ' = { RA ' corresponding to A ' 1 ，RA' 2 ，……，RA' i ，……，RA' m }，RA' i ={RA' i1 ，RA' i2 ，……，RA' ij ，……，RA' in }，RA' ij Is A' ij The corresponding target priority.
Specifically, RA 'is obtained in S120 by the following steps' ij As shown in fig. 2:
s1201, obtaining A' ij Corresponding Key entity tag A ij Wherein A is ij Is A 'obtained from a preset entity label list' ij And the corresponding preset entity label.
S1203, according to U 0 Obtaining A ij Corresponding first intermediate label priority list PA ij ={PA 1 ij ，PA 2 ij ，……，PA r ij ，……，PA s ij }，PA r ij Is A ij A corresponding first mth middle tag priority; it can be understood that: when A is ij And U 0 fr When the corresponding preset entity labels are consistent, then U 0 fr =PA r ij 。
S1205, obtain A i Corresponding second intermediate tag label priority list KA' i ={KA' i1 ，KA' i2 ，……，KA' ir ，……，KA' is }，KA' ir Is A i To correspond to the firstTwo intermediate label priorities.
Specifically, the second middle tag priority is a tag priority corresponding to a non-preset entity tag obtained by inputting the initial entity into the entity identification model.
S1207, according to PA ij And KA' i Obtaining RA' ij 。
Specifically, S1207 further includes the following steps:
s12071, when the preset entity label priority set does not have the preset entity label priority with the negative value, obtaining RA' ij Wherein, RA' ij The following conditions are met:
s12073, when the preset entity tag priority set has the preset entity tag priority with the negative value, RA 'is obtained' ij Wherein, RA' ij The following conditions are met:
by judging the value representation mode of the preset entity priority in the preset entity label priority set, different methods for obtaining the target priority are provided, the obtained target priority is more accurate, and the accuracy of obtaining the link entity is improved.
S130, according to RA' i Obtaining the linked entity list A corresponding to A 0 ={A 0 1j ，A 0 2j ，……，A 0 ij ，……，A 0 mj In which A 0 ij Is A i The linking entity of (2); it can be understood that: when RA' ij Is RA' i At the time of the maximum target priority, A' ij As A 0 ij 。
Specifically, the link entity is an entity obtained by performing entity link on any entity.
By the method, the entity priority corresponding to the key entity of any initial entity is processed, and then the more accurate entity priority is obtained, so that the link entity of the initial entity is obtained according to the more accurate entity priority, and the accuracy of obtaining the link entity is improved.
A data processing system for acquiring a link entity provided in this embodiment includes: an initial entity list, a set of preset entity tag priorities, a processor and a memory storing a computer program that, when executed by the processor, performs the steps of: comparing the number of initial entities with a preset entity number threshold, when the number of the initial entities is smaller than the preset entity number threshold, acquiring a key entity set corresponding to an initial entity list, acquiring a target priority set corresponding to the key entity set according to a preset entity tag priority set, wherein the preset entity tag priority is a tag priority between a preset entity tag and a non-preset entity tag, the tag priority is an association degree between any entity tag and other entity tags or any entity, and acquiring a link entity corresponding to the initial entities according to the target priority set; in the above, when the link entity is obtained, the link entity is not limited to the entity itself, the entity tag corresponding to the entity and the association degree between the entity tag and the entity tag are considered, and the accuracy of the obtained link entity is improved.
Example two
The second embodiment provides a data processing system for acquiring a link entity, the system includes: initial entity list a = { a = 1 ，A 2 ，……，A i ，……，A m A, a set of preset entity relationship priorities, a processor and a memory storing a computer program, wherein a i I =1,2 \8230, 8230, m, m is the number of initial entities; when executed by a processor, the computer program realizes the following steps, as shown in fig. 3:
s200, comparing m with a preset entity quantity threshold value m 0 And (6) carrying out comparison.
In particular, m 0 Is 3.
S210, when m is more than or equal to m 0 And acquiring a key entity set A '= { A' 1 ，A' 2 ，……，A' i ，……，A' m Key entity priority set FA '= { FA' 1 ，FA' 2 ，……，FA' i ，……，FA' m In which, A' i ={A' i1 ，A' i2 ，……，A' ij ，……，A' in }，A' ij Is A i J-th key entity, FA 'in corresponding key entity list' i ={FA' i1 ，FA' i2 ，……，FA' ij ，……，FA' in }，FA' ij Is A' ij The corresponding key entity priority, j =1,2 \8230, n is the number of key entities in the key entity list.
Specifically, the system further includes an initial text set, where the initial text set includes a plurality of initial texts, where the initial texts are texts obtained by a user through a crawler method from any web page, and as known to those skilled in the art, any crawler method in the prior art belongs to the protection scope of the present invention and is not described herein again.
Further, the initial entity is an entity obtained by inputting an initial text into the entity recognition model; those skilled in the art also know that any method for obtaining an entity through an entity identification model in the prior art belongs to the protection scope of the present invention, and is not described herein again; for example, the entity recognition model is a NER model.
Specifically, the system further includes a preset entity list and a preset triplet set, where the preset entity list includes a plurality of preset entities, and the preset triplet set includes a preset triplet list corresponding to each preset entity, where the preset triplet list includes a plurality of preset triplets corresponding to each preset entity, and those skilled in the art know that any method for acquiring triplets in the prior art belongs to the protection scope of the present invention, and details thereof are not described herein.
Furthermore, the preset entity is any entity obtained from a preset knowledge base, and as known to those skilled in the art, any knowledge base in the prior art belongs to the protection scope of the present invention, and is not described herein again; for example, the knowledge base is wikipedia, and the like.
Further, the priority of the key entity is obtained by inputting the initial entity and the key entity corresponding to the initial entity into the entity matching model, and the matching probability between the initial entity and the key entity corresponding to the initial entity is obtained, where a person skilled in the art knows that any entity matching model in the prior art belongs to the protection scope of the present invention, and details thereof are not repeated herein.
Specifically, the preset entity relationship priority set Y 0 ={Y 0 1 ，Y 0 2 ，……，Y 0 a ，……，Y 0 u }，Y 0 a ={Y 0 a1 ，Y 0 a2 ，……，Y 0 ay ，……，Y 0 aq }，Y 0 ay For the entity relationship priority between the a-th preset triplet and the y-th non-preset triplet, a =1,2 (8230); \8230u, u is the number of the preset triples, and y =1,2 (8230); 8230q, q is the number of the non-preset triples; as known to those skilled in the art, the entity relationship priority is the degree of association between any entity relationship and other entity relationships or entities, wherein the entity relationship is a triple including any two entities and the relationship between two entities.
Further, the non-preset triplet is a triplet obtained by performing deduplication processing on a sample triplet, where the sample triplet is a triplet obtained by inputting a sample text into the entity relationship extraction model, and a person skilled in the art knows that the sample text is a text used for training the entity relationship extraction model and is not described herein again.
Further, those skilled in the art know that any method for obtaining the triplet through the entity relationship extraction model in the prior art belongs to the protection scope of the present invention, and details are not described herein.
S220, acquiring an intermediate entity set FA = { FA' according to FA = 1 ，FA 2 ，……，FA g ，……，FA m-1 Intermediate priority set TFA = { TFA } for FA and 1 ，TFA 2 ，……，TFA g ，……，TFA m-1 }，FA g is the g-th intermediate entity list, TFA g Is FA g Corresponding intermediate priority list, g =2 \ 8230; \8230; m-1.
Specifically, in S220, the FA is acquired by the following steps g ：
S2201, traversing TFA g-1 Obtaining TFA g-1 The medium-maximum intermediate priority.
S2203, from FA g-1 Deletion of TFA g-1 After the intermediate entity corresponding to the middle-maximum intermediate priority is obtained, the FA is obtained g 。
Further, TFA is obtained in S2201 by the following steps g-1 ：
S22011, obtaining FA g-2 Corresponding first critical entity set, DFA g-2 ={DFA g-2 1 ，DFA g-2 2 ，……，DFA g -2 x ，……，DFA g-2 m-g+2 }，DFA g-2 x ={DFA g-2 x1 ，DFA g-2 x2 ，……，DFA g-2 xj ，……，DFA g-2 xn }，DFA g-2 xj Is FA g-2 The method comprises the following steps of obtaining a first key entity corresponding to the xth intermediate entity from A ', wherein the first key entity is the key entity corresponding to the intermediate entity obtained from A', and x =1,2 \8230; and m-g +2.
S22013, obtaining TFA g-2 ={TFA g-2 1 ，TFA g-2 2 ，……，TFA g-2 x ，……，TFA g-2 m-g }，TFA g-2 x ={TFA g -2 x1 ，TFA g-2 x2 ，……，TFA g-2 xj ，……，TFA g-2 xn }，TFA g-2 xj Is DFA g-2 xj Corresponding intermediate priority.
S22015, as TFA g-2 xj Is TFA g-2 When the intermediate priority is the maximum, the FA is obtained g-2 The xth intermediate entity and DFA g-2 xj 。
S22017, obtaining a candidate priority set GFA g-2 ={GFA g-2 1 ，GFA g-2 2 ，……，GFA g-2 p ，……，GFA g -2 m-g-1 }，GFA g-2 p ={GFA g-2 p1 ，GFA g-2 p2 ，……，GFA g-2 pj ，……，GFA g-2 pn }，GFA g-2 pj P =1,2 \ 8230; \8230; m-g-1 for the jth candidate priority in the pth candidate priority list, wherein the candidate priority list is TFA g-2 Deletion of TFA g -2 x And other intermediate priority lists are sequentially arranged to obtain the intermediate priority list.
S22019, according to the preset entity relation priority list, obtaining TFA g-1 ={TFA g-1 1 ，TFA g-1 2 ，……，TFA g -1 p ，……，TFA g-1 m-g-1 }，TFA g-1 p ={TFA g-1 p1 ，TFA g-1 p2 ，……，TFA g-1 pj ，……，TFA g-1 pn In which TFA g-1 pj To the GFA g-2 pj And processing the obtained data.
Specifically, TFA is obtained in S22019 by the following steps g-1 pj ：
S1, according to TFA g-1 pj Corresponding first key entity and DFA g-2 xj Obtaining TFA g-1 pj Corresponding first key triplet, wherein TFA g-1 pj The corresponding first key triplet is TFA g-1 pj Corresponding first Key entity, DFA g-2 xj And TFA g-1 pj Corresponding first key entity and DFA g-2 xj Of a relationship betweenA triplet.
S2, acquiring TFA according to a preset entity relationship priority set g-1 pj First priority E of corresponding first critical triplet 0 ={E 0 1 ，E 0 2 ，……，E 0 y ，……，E 0 q }，E 0 y Is TFA g-1 pj The y-th first priority of the corresponding first key triplet; it can be understood that: when TFA g-1 pj Corresponding first key triplet and Y 0 a When they are consistent, then E 0 y =Y 0 ay 。
S3, according to FA g-2 The xth intermediate and TFA g-1 pj Corresponding initial entity, obtaining TFA g-1 pj Corresponding second key triplet, wherein said TFA g-1 pj The corresponding second key triple is including FA g-2 Middle x intermediate entity, TFA g-1 pj Corresponding initial entity and FA g-2 The xth intermediate and TFA g-1 pj A triplet of relationships between corresponding initial entities.
S4, obtaining TFA g-1 pj A second priority list T corresponding to the corresponding second key triple 0 ={T 0 1 ，T 0 2 ，……，T 0 y ，……，T 0 q }，T 0 y Is TFA g-1 pj The corresponding second critical triplet corresponds to the y-th second priority.
Specifically, the second priority is to include the FA g-2 The xth intermediate and TFA g-1 pj And inputting the corresponding sample text of the initial entity into the priority corresponding to the non-preset triple acquired in the entity relation extraction model.
S5, according to E 0 And T 0 Obtaining TFA g-1 pj 。
Further, the method in S5 further includes the following steps:
s51, when the preset entity relationship priority of the negative value does not exist in the preset entity relationship priority table, obtaining TFA g xj Wherein, TFA g xj The following conditions are met:
s53, when the preset entity relationship priority with a negative value exists in the preset entity relationship priority table, TFA is obtained g xj Wherein, TFA g xj The following conditions are met:
in the above, by judging the value representation mode of the preset entity relationship priority in the preset entity relationship priority set, different methods for obtaining the intermediate priority are provided, so that the obtained intermediate priority is more accurate, and the accuracy of obtaining the link entity is further improved.
In a particular embodiment of the present invention,
when g =2, TFA was obtained by the following procedure 1 ：
S11, obtaining FA 0 Corresponding first critical entity set, DFA 0 ={DFA 0 1 ，DFA 0 2 ，……，DFA 0 i ，……，DFA 0 m }，DFA 0 i ={DFA 0 i1 ，DFA 0 i2 ，……，DFA 0 ij ，……，DFA 0 in In which DFA 0 i And A' i Consensus, DFA 0 ij And A' ij And (5) the consistency is achieved.
S21, obtaining TFA 0 ={FA' 1 ，FA' 2 ，……，FA' i ，……，FA' m }，FA' i ={FA' i1 ，FA' i2 ，……，FA' ij ，……，FA' in }。
S31, acquiring TFA according to the preset entity relation priority list 1 Wherein, TFA 1 Refer to steps S22015 to 22019 in this embodiment.
In a particular embodiment of the present invention,
when g =2, FA is acquired by the following steps 1 ：
S10, traversing the FA 'to acquire the maximum key entity priority in the FA'.
S20, deleting the key entity corresponding to the maximum key entity priority in the FA 'from the A', and acquiring the FA 1 。
S230, according to TFA, obtaining a link entity list FA corresponding to FA 0 ={FA 0 1 ，FA 0 2 ，……，FA 0 g ，……，FA 0 m-1 Wherein, FA 0 g The obtained g-th link entity; it can be understood that: when TFA g And when one intermediate priority is the maximum priority, acquiring the link entity of which the corresponding intermediate entity is the initial entity corresponding to the intermediate entity.
Specifically, the link entity is an entity obtained by performing entity link on any entity.
According to the method, the entity priority corresponding to the key entity of any initial entity is processed based on the relationship between the entities, and then the more accurate entity priority is obtained, so that the link entity of the initial entity is obtained according to the more accurate entity priority, and the accuracy of obtaining the link entity is improved.
In a second embodiment, a data processing system for obtaining linked entities includes an initial entity list, a preset entity relationship priority set, a processor, and a memory storing a computer program, where when the computer program is executed by the processor, the following steps are implemented: comparing the number of the initial entities with a preset entity number threshold, when the number of the initial entities is greater than or equal to the preset entity number threshold, acquiring a key entity set corresponding to a key entity set and a key entity priority set corresponding to the key entity set of the initial entity list, acquiring an intermediate priority set corresponding to an intermediate entity set and the intermediate entity set according to the key entity priority set, wherein the entity relationship priority is the association degree between any entity relationship and other entity relationships or entities, and acquiring a linked entity list corresponding to the intermediate entity according to the intermediate priority set; in the process of acquiring the link entity, the entity priority is processed based on the entity relationship and the association degree between the entity relationship and the entity relationship without being limited to the similarity between the entities, so that a more accurate entity priority is acquired, and the accuracy of acquiring the link entity is improved.
EXAMPLE III
The embodiment provides a data processing system for acquiring a link entity, the system comprising: initial entity list a = { a = 1 ，A 2 ，……，A i ，……，A m A set of preset entity relationship priorities, a processor and a memory storing a computer program, wherein A i I =1,2 \8230, 8230, m, m is the number of initial entities; when executed by a processor, the computer program performs the following steps, as shown in fig. 4:
s300, comparing m with a preset entity quantity threshold value m 0 And (6) carrying out comparison.
In particular, m 0 Is 3.
S310, when m is more than or equal to m 0 And then, obtaining a key entity set A '= { A' 1 ，A' 2 ，……，A' i ，……，A' m Key entity priority set FA '= { FA' 1 ，FA' 2 ，……，FA' i ，……，FA' m In which, A' i ={A' i1 ，A' i2 ，……，A' ij ，……，A' in }，A' ij Is A i J-th key entity, FA 'in corresponding key entity list' i ={FA' i1 ，FA' i2 ，……，FA' ij ，……，FA' in }，FA' ij Is A' ij Corresponding key entity priority, j =1,2 \ 8230; \8230n, n is the number of key entities in the key entity list, wherein FA' i1 ＞FA' i2 ＞……＞FA' ij ＞……＞FA' in 。
Specifically, the system further includes a preset entity list and a preset triple set, where the preset entity list includes a plurality of preset entities, and the preset triple set includes a preset triple list corresponding to each preset entity, where the preset triple list includes a plurality of preset triples corresponding to each preset entity.
Furthermore, the preset entity is any entity obtained from a preset knowledge base, and as known to those skilled in the art, any knowledge base in the prior art belongs to the protection scope of the present invention, and is not described herein again; for example, the knowledge base is wikipedia, and the like.
Further, the key entity priority is a matching probability between the initial entity and the key entity corresponding to the initial entity, which is obtained by inputting the initial entity and the key entity corresponding to the initial entity into the entity matching model, where it is known to those skilled in the art that any entity matching model in the prior art belongs to the protection scope of the present invention, and is not described herein again.
Specifically, the preset entity relationship priority set Y 0 ={Y 0 1 ，Y 0 2 ，……，Y 0 a ，……，Y 0 u }，Y 0 a ={Y 0 a1 ，Y 0 a2 ，……，Y 0 ay ，……，Y 0 aq }，Y 0 ay The entity relationship priority between the a-th preset triple and the y-th non-preset triple is a =1,2 \ 8230 \8230: \ 8230, u is the number of preset triples, y =1,2 \ 8230 \8230: \ 8230, q, q is the number of non-preset triples; as known to those skilled in the art, the entity relationship priority is the degree of association between any entity relationship and other entity relationships or entities, wherein the entity relationship is a triple including any two entities and the relationship between two entities.
Further, the non-preset triplet is a triplet obtained by performing deduplication processing on a sample triplet, where the sample triplet is a triplet obtained by inputting a sample text into the entity relationship extraction model, and as known by those skilled in the art, the sample text is a text used for training the entity relationship extraction model and is not described herein again.
Further, those skilled in the art know that any method for obtaining triples through an entity relationship extraction model in the prior art belongs to the protection scope of the present invention, and details are not repeated herein.
S320, when FA' i1 A 'is obtained when the maximum key priority is in FA' i1 Is A i The link entity in (2), wherein the link entity is an entity obtained by performing entity link on any entity.
S330, deleting A from A i Acquiring a first initial entity list B = { B = 1 ，B 2 ，……，B d ，……，B m-1 B corresponding first set of intermediate entities B '= { B' 1 ，B' 2 ，……，B' d ，……，B' m-1 First set of intermediate priorities FB ' = { FB ' = and B ' corresponding to B ' } and B ' 1 ，FB' 2 ，……，FB' d ，……，FB' m-1 In which B d Is the d first initial entity, B' d ={B' d1 ，B' d2 ，……，B' dj ，……，B' dn }，B' dj Is B d Jth first intermediate entity, FB 'in a corresponding first intermediate entity list' d ={FB' d1 ，FB' d2 ，……，FB' dj ，……，FB' dn }，FB' dj Is B' dj Corresponding first intermediate priority, d =1,2 \ 8230; \8230l, m-1, where FB' d1 ＞FB' d2 ＞……＞FB' dj ＞……＞FB' dn 。
Specifically, the first initial entity is to delete a from a i The first intermediate entity is a key entity corresponding to the first initial entity obtained from A', and the first intermediate entity has priorityThe level is the key priority corresponding to the first initial entity obtained from the FA'.
S340, according to the preset entity relationship priority set, obtaining a first key priority set VFB ' = { VFB ' corresponding to B ' 1 ，VFB' 2 ，……，VFB' d ，……，VFB' m-1 }，VFB' d ={VFB' d1 ，VFB' d2 ，……，VFB' dj ，……，VFB' dn Of which VFB' dj Is the corresponding first critical priority.
Specifically, in S340, VFB 'is obtained through the following steps' dj ：
S3401, according to A i And B d Obtaining B d Corresponding first candidate triplet AB id Wherein, said B d The corresponding first candidate triple includes A i 、B d And A i And B d A triplet of relationships between.
S3403, acquiring the AB according to the preset entity relationship priority set id Corresponding first to-be-determined priority = { EAB 1 id ，EAB 2 id ，……，EAB y id ，……，EAB q id }，EAB y id Is AB id A corresponding y-th first priority to be determined; it can be understood that: when AB is used id And Y 0 a When they are consistent, then EAB y id =Y 0 ay 。
S3405, according to A' i1 And B' d Obtaining B' d Corresponding first candidate triplet AB' id Wherein, the B 'is' d Corresponding first candidate triple comprises A' i1 、B' d And A' i1 And B' d A triplet of relationships between.
S3407, obtaining AB' id Corresponding second pending priority list WAB' id ={WAB' 1 id ，WAB' 2 id ，……，WAB' y id ，……，WAB' q id }，WAB' y id Is AB' id Corresponding yth second waiting definitionA priority level.
Specifically, the second pending priority is to include A' i1 And B' d And inputting the sample text into the entity relation extraction model to obtain the corresponding priority of the non-preset triple.
S3409, according to EAB id And WAB' id Obtaining VFB' dj 。
Further, in S3409, the method further includes the following steps:
s34091, when no negative value preset entity relationship priority exists in the preset entity relationship priority table, obtaining VFB' dj Wherein, VFB' dj The following conditions are met:
s34093, when the preset entity relationship priority with the negative value exists in the preset entity relationship priority table, obtaining the VFB' dj Wherein, VFB' dj The following conditions are met:
by judging the value representation mode of the preset entity relationship priority in the preset entity relationship priority set, different methods for acquiring the intermediate priority are provided, the acquired intermediate priority is more accurate, and the accuracy of acquiring the link entity is improved.
S350, according to VFB', obtaining a first target link entity list C = { C 1 ，C 2 ，……，C ζ ，……，C η }，C ζ ζ =1,2 \ 8230 \ 8230η, η is the number of first target link entities, wherein the first target link entities are when VFB' d1 Is VFB' d B 'is obtained when the first key priority is the maximum' d1 Is B d A corresponding linking entity; it can be understood that: FB' d Location of medium maximum with VFB' d Bit of maximum value inWhen the position is not changed, obtaining VFB' d The first intermediate entity corresponding to the maximum value in (b) is the linking entity of the first initial entity corresponding to the first intermediate entity.
S360, according to C, obtaining a second initial entity list D = { D = { (D) } 1 ，D 2 ，……，D e ，……，D t }，D e Is the e-th second initial entity, wherein the second initial entity is the deletion of C from B ζ Any initial entity after the corresponding first initial entity.
Specifically, η + t = m-1.
The entity priority corresponding to the key entity of any initial entity is processed based on the relationship between the entities, and when the position of the maximum entity priority in the entity priorities acquired after the entity priorities corresponding to the key entities of the initial entities are processed remains unchanged, the key entities meeting the conditions are directly acquired as the link entities of the initial entities, so that the data volume needing to be processed is reduced, the efficiency of acquiring the link entities is improved, and the accuracy of the acquired link entities is higher.
S370, according to D, obtaining a second target link entity list C 0 ={C 0 1 ，C 0 2 ，……，C 0 i ，……，C 0 m }，C 0 i Is A i Corresponding linking entity, wherein C 0 And repeating the steps S320-S360 until the obtained second initial entity list is an empty set.
According to the method, the entity priority corresponding to the key entity of any initial entity is processed based on the relationship between the entities, and then the more accurate entity priority is obtained, so that the link entity of the initial entity is obtained according to the more accurate entity priority, and the accuracy of obtaining the link entity is improved.
In this embodiment, a data processing system for obtaining a link entity based on an entity relationship includes: an initial entity list, a set of preset entity relationship priorities, a processor and a memory storing a computer program that, when executed by the processor, performs the steps of: comparing the number of initial entities with a preset entity number threshold, when the number of the initial entities is greater than or equal to the preset entity number threshold, acquiring a key entity set corresponding to a key entity set and a key entity priority set corresponding to the key entity set, acquiring a maximum key priority, taking the key entity corresponding to the maximum key priority as a link entity of the initial entity corresponding to the key entity, deleting the initial entity corresponding to the maximum key priority from the initial entity list, acquiring a first initial entity list and a first intermediate priority set corresponding to a first intermediate entity set and a first intermediate entity set corresponding to the first initial entity list, acquiring a first key priority set corresponding to the first intermediate entity set according to a preset entity relationship priority set, acquiring a first target link entity list according to the first key priority set, acquiring a second initial entity list according to the first target link entity list, and acquiring a second target link entity list according to the second initial entity list; in the process of acquiring the link entity, the entity relationship and the association degree between the entity relationship and the entity relationship are considered, the priority of each entity is not processed for many times, the efficiency of acquiring the link entity is increased, and the accuracy of acquiring the link entity is improved.
Example four
A data processing system for obtaining linked entities, the system comprising: initial entity list a = { a = 1 ，A 2 ，……，A i ，……，A m A set of preset entity tag priorities, a set of preset entity relationship priorities, a processor and a memory storing a computer program, wherein A i The method is the ith initial entity, i =1,2 \8230, wherein \8230, m and m are the number of the initial entities; when executed by a processor, the computer program performs the following steps, as shown in fig. 5:
s400, obtaining a key entity set A ' = { A ' corresponding to A ' 1 ，A' 2 ，……，A' i ，……，A' m Key entity priority set FA '= { FA' 1 ，FA' 2 ，……，FA' i ，……，FA' m In which, A' i ={A' i1 ，A' i2 ，……，A' ij ，……，A' in }，A' ij Is A i J-th key entity, FA 'in corresponding key entity list' i ={FA' i1 ，FA' i2 ，……，FA' ij ，……，FA' in }，FA' ij Is A' ij And the corresponding priority of the key entities, j =1,2 \8230, wherein \8230n, n is the number of the key entities in the key entity list.
Specifically, the obtaining manner of the key entity may refer to the obtaining manner of the key entity in the first embodiment, and details are not described herein.
Specifically, the obtaining manner of the priority of the key entity may refer to the obtaining manner of the priority of the key entity in the first embodiment, and details are not described herein again.
S410, according to the preset entity tag priority set, obtaining a first candidate priority set SA ' = { SA ' corresponding to A ' 1 ，SA' 2 ，……，SA' i ，……，SA' m }，SA' i ={SA' i1 ，SA' i2 ，……，SA' ij ，……，SA' in }，SA' ij Is A' ij Corresponding first candidate priority.
Concretely, SA' ij Can be obtained by referring to RA 'in the first embodiment' ij The obtaining method is not described herein again.
S420, according to the preset entity relationship priority set, acquiring a second candidate priority set VA ' = { VA ' corresponding to A ' 1 ，VA' 2 ，……，VA' i ，……，VA' m }，VA' i ={VA' i1 ，VA' i2 ，……，VA' ij ，……，VA' in }，VA' ij Is A' ij Corresponding second candidate priority.
Specifically, VA' ij Can be obtained by referring to TFA in example II g-1 pj VFB 'of Example III' dj The obtaining mode of (2).
S430, obtaining A 'pairs according to SA' and VACorresponding final priority set EA '= { EA' 1 ，EA' 2 ，……，EA' i ，……，EA' m }，EA' i ={EA' i1 ，EA' i2 ，……，EA' ij ，……，EA' in - }, wherein, EA' ij The following conditions are met:
EA' ij =（SA' ij +VA' ij ）/2。
s440, according to EA' i Obtaining a final linked entity list PA = { PA of a 1j ，PA 2j ，……，PA ij ，……，PA mj In which PA is ij Is A i The final linking entity of (2); it can be understood that: is EA' ij Is EA' i At the maximum final priority of medium, A' i As PA ij 。
In the above way, the entity priority corresponding to the key entity of any initial entity is processed in two ways to obtain a more accurate entity priority, so that the link entity of the initial entity is obtained according to the more accurate entity priority, and the accuracy of obtaining the link entity is further improved.
In a fourth embodiment, a data processing system for obtaining a link entity based on an entity relationship includes an initial entity list, a preset entity tag priority set, a preset entity relationship priority set, a processor, and a memory storing a computer program, where when the computer program is executed by the processor, the following steps are implemented: acquiring a key entity set corresponding to the initial entity list and a key entity priority set corresponding to the key entity set, acquiring a first candidate priority set corresponding to the key entity set according to a preset entity label priority set, acquiring a second candidate priority set corresponding to the key entity according to a preset entity relationship priority set, acquiring a final priority set corresponding to the key entity according to the first candidate priority set and the second candidate priority set, and acquiring a final linked entity list corresponding to the initial entity list according to the final priority set; by the method, the more accurate entity priority is obtained by considering the association degree of the entity tag and the association degree between the entity relationship and the entity relationship, so that the link entity of the initial entity is obtained according to the more accurate entity priority, and the accuracy of obtaining the link entity is improved.
Although some specific embodiments of the present invention have been described in detail by way of illustration, it should be understood by those skilled in the art that the above illustration is only for the purpose of illustration and is not intended to limit the scope of the invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.
Claims (9)
1. A data processing system for obtaining linked entities, the system comprising: initial text set, initial entity list a = { a = { a } 1 ，A 2 ，……，A i ，……，A m The method comprises the steps of (1) obtaining an initial text set, a preset entity tag priority set, a processor and a memory storing a computer program, wherein the initial text set comprises a plurality of initial texts, the initial texts are texts obtained by a user from any webpage through a crawler method, and A i I =1,2 \ 8230 \\ 8230:/\ 8230, m, m is the number of initial entities, which are entities obtained by inputting initial text into an entity recognition model, which when executed by a processor, performs the following steps:
s100, comparing m with a preset entity quantity threshold value m 0 Carrying out comparison;
s110, when m is less than m 0 And then, obtaining a key entity set A '= { A' 1 ，A' 2 ，……，A' i ，……，A' m Key entity priority set FA '= { FA' 1 ，FA' 2 ，……，FA' i ，……，FA' m In which, A' i ={A' i1 ，A' i2 ，……，A' ij ，……，A' in }，A' ij Is A i Jth critical entity, FA 'in the corresponding list of critical entities' i ={FA' i1 ，FA' i2 ，……，FA' ij ，……，FA' in }，FA' ij Is A' ij The corresponding key entity priority, j =1,2 \8230, \8230, n is the number of key entities in the key entity list;
s120, according to the preset entity tag priority set, obtaining a target priority set RA '= { RA' 1 ，RA' 2 ，……，RA' i ，……，RA' m }，RA' i ={RA' i1 ，RA' i2 ，……，RA' ij ，……，RA' in }，RA' ij Is A' ij Corresponding target priority, wherein RA 'is obtained in S120 by' ij ：
S1201, obtaining A' ij Corresponding key entity tag A ij Wherein A is ij Is A 'obtained from a preset entity label list' ij A corresponding preset entity label;
s1203, according to U 0 Obtaining A ij Corresponding first intermediate label priority list PA ij ={PA 1 ij ，PA 2 ij ，……，PA r ij ，……，PA s ij }，PA r ij Is A ij Corresponding first middle label priority, wherein, when A ij And U 0 fr When the corresponding preset entity labels are consistent, then U 0 fr =PA r ij The pre-set entity tag priority set U 0 ={U 0 1 ，U 0 2 ，……，U 0 f ，……，U 0 z }，U 0 f ={U 0 f1 ，U 0 f2 ，……，U 0 fr ，……，U 0 fs }，U 0 fr F =1,2, 8230, r =1,2, 8230, z, z is the number of the preset entity tags, r =1,2, 8230, s, s is the number of the non-preset entity tags, for the tag priority between the f-th preset entity tag and the r-th non-preset entity tag;
s1205, obtain A i Corresponding second intermediate tag label priority list KA' i ={KA' i1 ，KA' i2 ，……，KA' ir ，……，KA' is }，KA' ir Is A i A corresponding second intermediate label priority;
s1207, according to PA ij And KA' i Obtaining RA' ij ；
S130, according to RA' i Obtaining the linked entity list A corresponding to A 0 ={A 0 1j ，A 0 2j ，……，A 0 ij ，……，A 0 mj In which A 0 ij Is A i The linking entity of (2).
2. The data processing system of claim 1, wherein m is a link entity 0 Is 3.
3. The data processing system for obtaining the linking entity of claim 1, further comprising a preset entity list, a preset entity tag list corresponding to the preset entity list, and a preset triplet set.
4. The data processing system for obtaining the link entity of claim 3, wherein the predetermined entity tag is a unique tag characterizing an entity type corresponding to the predetermined entity.
5. The data processing system for acquiring a linking entity of claim 1, further comprising the following step in S1207:
s12071, when the preset entity label priority set does not have the preset entity label priority with the negative value, obtaining RA' ij Wherein, RA' ij The following conditions are met:
s12073, when the preset entity label priority set has negative value, the preset entity label is superiorIn the first stage, RA 'is obtained' ij Wherein, RA' ij The following conditions are met:
6. the data processing system of obtaining chained entities of claim 1, wherein in S130 when RA' ij Is RA' i At the time of the maximum target priority, A' ij As A 0 ij 。
7. The data processing system for obtaining the linked entity of claim 1, wherein the linked entity is an entity for entity linking of any entity.
8. The data processing system for obtaining linking entities according to claim 1, wherein said system, when said computer program is executed by a processor, further performs the steps of:
s400, obtaining a key entity set A '= { A' 1 ，A' 2 ，……，A' i ，……，A' m Respective Key entity priority set FA '= { FA' 1 ，FA' 2 ，……，FA' i ，……，FA' m In which, A' i ={A' i1 ，A' i2 ，……，A' ij ，……，A' in }，A' ij Is A i Jth critical entity, FA 'in the corresponding list of critical entities' i ={FA' i1 ，FA' i2 ，……，FA' ij ，……，FA' in }，FA' ij Is A' ij The corresponding key entity priority, j =1,2 \8230, \8230, n is the number of key entities in the key entity list;
s410, according to the preset entity tag priority set, obtaining a first candidate priority set SA ' = { SA ' corresponding to A ' 1 ，SA' 2 ，……，SA' i ，……，SA' m }，SA' i ={SA' i1 ，SA' i2 ，……，SA' ij ，……，SA' in }，SA' ij Is A' ij A corresponding first candidate priority;
s420, according to the preset entity relationship priority set, obtaining a second candidate priority set VA ' = { VA ' corresponding to A ' 1 ，VA' 2 ，……，VA' i ，……，VA' m }，VA' i ={VA' i1 ，VA' i2 ，……，VA' ij ，……，VA' in }，VA' ij Is A' ij A corresponding second candidate priority;
s430, obtaining a final priority set EA ' = { EA ' corresponding to A ' according to SA ' and VA ' 1 ，EA' 2 ，……，EA' i ，……，EA' m }，EA' i ={EA' i1 ，EA' i2 ，……，EA' ij ，……，EA' in - }, wherein, EA' ij The following conditions are met:
EA' ij =（SA' ij +VA' ij ）/2；
s440, according to EA' i Obtaining a final linked entity list PA = { PA of a 1j ，PA 2j ，……，PA ij ，……，PA mj In which PA is ij Is A i The final linking entity of (2); it can be understood that: is EA' ij Is EA' i At the highest final priority level, A' i As PA ij 。
9. The data processing system of obtaining chained entities of claim 8, wherein SA' ij The sample of (4) may be obtained by referring to RA 'in S120' ij The manner of acquisition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211538039.XA CN115618140B (en) | 2022-12-02 | 2022-12-02 | Data processing system for acquiring link entity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211538039.XA CN115618140B (en) | 2022-12-02 | 2022-12-02 | Data processing system for acquiring link entity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115618140A CN115618140A (en) | 2023-01-17 |
| CN115618140B true CN115618140B (en) | 2023-03-07 |
Family
ID=84879810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211538039.XA Active CN115618140B (en) | 2022-12-02 | 2022-12-02 | Data processing system for acquiring link entity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115618140B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116049447B (en) * | 2023-03-24 | 2023-06-13 | 中科雨辰科技有限公司 | Entity linking system based on knowledge base |
| CN116684205B (en) * | 2023-08-03 | 2023-09-29 | 北京立思辰安科技术有限公司 | Method, medium and equipment for obtaining network system abnormality degree |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105138636A (en) * | 2015-08-21 | 2015-12-09 | 浪潮软件集团有限公司 | Graph construction method and device for entity relationship |
| CN113868382A (en) * | 2021-08-17 | 2021-12-31 | 北京智谱华章科技有限公司 | Method and device for extracting structured knowledge from Chinese natural language |
| CN114254336A (en) * | 2020-09-25 | 2022-03-29 | 英特尔公司 | Method, apparatus and system for enforcing data boundaries by using boundary tags |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2948788B1 (en) * | 2009-07-30 | 2011-09-16 | Xaga Network | APPLICATION MANAGEMENT SYSTEM |
| CA2854886A1 (en) * | 2011-11-08 | 2013-05-16 | Google Inc. | Systems and methods for generating and displaying hierarchical search results |
| US11227183B1 (en) * | 2020-08-31 | 2022-01-18 | Accenture Global Solutions Limited | Section segmentation based information retrieval with entity expansion |
-
2022
- 2022-12-02 CN CN202211538039.XA patent/CN115618140B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105138636A (en) * | 2015-08-21 | 2015-12-09 | 浪潮软件集团有限公司 | Graph construction method and device for entity relationship |
| CN114254336A (en) * | 2020-09-25 | 2022-03-29 | 英特尔公司 | Method, apparatus and system for enforcing data boundaries by using boundary tags |
| CN113868382A (en) * | 2021-08-17 | 2021-12-31 | 北京智谱华章科技有限公司 | Method and device for extracting structured knowledge from Chinese natural language |
Non-Patent Citations (2)
| Title |
|---|
| Mamatjan Abdurxit等.an efficient method for biomedical entity linking based on inter-and intra-entity attention.2022,全文. * |
| 张祥 ; 王紫悦 ; 杨清清 ; 丁金如 ; .基于知识图谱的实体标签可视化.2020,(03),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115618140A (en) | 2023-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115618140B (en) | Data processing system for acquiring link entity | |
| CN107004159B (en) | Active machine learning | |
| US11232141B2 (en) | Method and device for processing an electronic document | |
| US9390176B2 (en) | System and method for recursively traversing the internet and other sources to identify, gather, curate, adjudicate, and qualify business identity and related data | |
| US9633002B1 (en) | Systems and methods for coreference resolution using selective feature activation | |
| CN105210064A (en) | Classifying resources using a deep network | |
| JP2005182730A (en) | Automatic document separation | |
| CN110866491A (en) | Target retrieval method, device, computer readable storage medium and computer equipment | |
| CN111984792A (en) | Website classification method and device, computer equipment and storage medium | |
| CN113011529B (en) | Training method, training device, training equipment and training equipment for text classification model and readable storage medium | |
| CN112699923A (en) | Document classification prediction method and device, computer equipment and storage medium | |
| CN112800248B (en) | Similar case retrieval method, similar case retrieval device, computer equipment and storage medium | |
| CN115795051B (en) | Data processing system for acquiring link entity based on entity relationship | |
| US20230177267A1 (en) | Automated classification and interpretation of life science documents | |
| CN116956026A (en) | Training method and system for network asset identification model | |
| CN111324687A (en) | Data processing method and device in knowledge base, computer equipment and storage medium | |
| CN116167339B (en) | Data processing system for acquiring link entity based on entity relationship | |
| CN112364169B (en) | Nlp-based wifi identification method, electronic device and medium | |
| CN110888977A (en) | Text classification method and device, computer equipment and storage medium | |
| CN115203372A (en) | Text intention classification method and device, computer equipment and storage medium | |
| CN111460268B (en) | Method and device for determining database query request and computer equipment | |
| WO2018100700A1 (en) | Data conversion device and data conversion method | |
| Mayet et al. | Skipw: Resource adaptable RNN with strict upper computational limit | |
| CN117827685B (en) | Fuzzy test input generation method, device, terminal and medium | |
| CN116681054A (en) | Text similarity recognition method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |