CN114579675A - Data processing system for determining common finger event - Google Patents
Data processing system for determining common finger event Download PDFInfo
- Publication number
- CN114579675A CN114579675A CN202210480177.0A CN202210480177A CN114579675A CN 114579675 A CN114579675 A CN 114579675A CN 202210480177 A CN202210480177 A CN 202210480177A CN 114579675 A CN114579675 A CN 114579675A
- Authority
- CN
- China
- Prior art keywords
- event
- entity
- list
- determining
- cluster
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The invention relates to a data processing system for determining co-referred events. The system comprises: a database, a processor and a memory storing a computer program which, when executed by the processor, performs the steps of: acquiring a first entity list corresponding to a first event and a second entity list corresponding to a second event, clustering the first entity list to obtain a first entity cluster list, clustering the second entity list to obtain a second entity cluster list, acquiring the same number of entity clusters and event similarity between the first event and the second event according to the first entity cluster list and the second entity cluster list, and determining whether the first event and the second event are the same event according to the event similarity; the method and the device can accurately determine that the two events represent the same event, avoid repeated query of the user and improve the experience of the user, and avoid the repeated text describing the same event and reduce the text amount of the event.
Description
Technical Field
The invention relates to the technical field of event processing, in particular to a data processing system for determining a common finger event.
Background
Currently, each event is independent, but in practice, there is often an association relationship between two events, or two events are to be referred to as representing the same event, and only because the manner of describing the event is different, when the event is classified, the event is divided into two events.
Therefore, some problems may arise: for example, on one hand, two events are used for representing the same event, which causes the user to repeatedly query the same event, which affects the experience of the user, and on the other hand, because the two events represent the same event, the text corresponding to each event has repeated text, which causes a large amount of text.
Disclosure of Invention
In view of the above technical problems, the technical solution adopted by the present invention is a data processing system for determining a common denominator event, the system comprising: a database, a processor, and a memory storing a computer program, wherein the database comprises: text set of events H = { H = { (H)1,……,Hr,……,Hs},HrRefers to a text list corresponding to the r-th event, r =1 … … s, s is the number of events, and when the computer program is executed by a processor, the following steps are implemented:
s100, traversing H and according to HrAcquiring a first entity list A = { A) corresponding to the first event1,……,Ai,……,AM},AiThe method refers to the ith first entity corresponding to the first event, i =1 … … M, and M is the number of the first entities;
s200, according to HrObtaining a second entity list B = { B ] corresponding to the second event1,……,Bj,……,BN},BjJ =1 … … N, where N is the number of second entities;
s300, for all AiClustering to obtain a first entity cluster list C = { C = { (C) }1,……,Cx,……,Cp},CxThe method is characterized in that the method refers to an x-th first entity cluster, wherein x =1 … … p, and p is a first entity cluster;
s400, for all BjClustering to obtain a second entity cluster list D = { D =1,……,Dy,……,Dq},DyThe method is characterized in that the method refers to the y-th second entity cluster, wherein y =1 … … q, and q is the second entity cluster;
s500, when CxAnd DyWhen they are consistent, determining CxThe corresponding first entity cluster is a target entity cluster;
s600, acquiring the number k of the target entity clusters and acquiring event similarity F between a first event and a second event based on k;
s700, when F is more than or equal to F0Determining that the first event and the second event refer to the same event, wherein F0The method comprises the steps of indicating a preset event similarity threshold value;
s800, when F is less than F0Determining that the first event and the second event do not refer to the same event.
Compared with the prior art, the invention has obvious advantages and beneficial effects. By means of the technical scheme, the data processing system for determining the common finger event can achieve considerable technical progress and practicability, has wide industrial utilization value and at least has the following advantages:
a data processing system for determining a co-referent event according to the present invention comprises: a database, a processor, and a memory storing a computer program, wherein the database comprises: a text set of events, which when executed by a processor, performs the steps of: acquiring a first entity list corresponding to a first event and a second entity list corresponding to a second event according to a text list of any event in a text set of the event, clustering all first entities in the first entity list to obtain a first entity cluster list, clustering all second entities in the second entity list to obtain a second entity cluster list, acquiring the same number of entity clusters in the first entity cluster list and the second entity cluster list according to the first entity cluster list and the second entity cluster list so as to acquire event similarity between the first event and the second event according to the same number of entity clusters, and determining whether the first event and the second event are the same event according to the event similarity; on one hand, the method can accurately determine that two events represent the same event, avoid repeated inquiry of a user and improve the experience of the user, and on the other hand, avoid the texts of repeated texts to describe the same event and reduce the text amount of the events.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.
Drawings
FIG. 1 is a flow chart of a computer program executed by a data processing system for determining co-designated events according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given with reference to the accompanying drawings and preferred embodiments of a data processing system for acquiring a target position and its effects.
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.
Examples
The present embodiment provides a data processing system for determining a co-referred event, the system comprising: database, processor and computer programA memory, wherein the database comprises: text set of events H = { H = { (H)1,……,Hr,……,Hs},HrRefers to the text list corresponding to the r-th event, r =1 … … s, s is the number of events, and when the computer program is executed by a processor, the following steps are implemented, as shown in fig. 1:
s100, traversing H and according to HrAcquiring a first entity list A = { A) corresponding to the first event1,……,Ai,……,AM},AiThe method refers to the ith first entity corresponding to the first event, i =1 … … M, and M is the number of the first entities.
Specifically, a is also acquired in the S100 step by:
s101, determining any H from HrTaking the corresponding event as a first event;
s103, obtaining,HraRefers to the a text of the r event, where a =1 … … er,erThe number of texts referring to the r-th event;
s105, for HraPerforming entity extraction to obtain HraA corresponding first initial entity list and a first intermediate entity list are obtained based on all the first initial entity lists, wherein a person skilled in the art can adopt any entity extraction method in the prior art, and details are not repeated herein;
s107, performing deduplication processing on the first intermediate entity list to obtain a, and a person skilled in the art may adopt any entity deduplication method, which is not described herein again.
S200, according to HrAcquiring a second entity list B = { B ] corresponding to the second event1,……,Bj,……,BN},BjThe j =1 … … N is the number of the second entities corresponding to the second event.
Specifically, B is also acquired in the S200 step by:
s201, deleting H from HrAcquiring a corresponding text list to obtain a middle text set H ' = { H ' of the event '1,……,H't,……,H's-1},H'tThe method is characterized by comprising the steps of referring to a text list corresponding to the t-th event in the middle text set of the event, wherein t =1 … … s-1;
s203, determining any H 'from H'tTaking the corresponding event as a second event;
s205, obtaining,H'tbRefers to the b-th text of the t-th event, where b =1 … … ft,ftThe number of texts of the t-th event is referred to;
s207, to H'tbCarrying out entity extraction to obtain H'tbA corresponding second initial entity list and a second intermediate entity list are obtained based on all the second initial entity lists, wherein a person skilled in the art can adopt any entity extraction method in the prior art, and details are not repeated herein;
s209, performing deduplication processing on the second intermediate entity list to obtain B, and a person skilled in the art may adopt any entity deduplication method, which is not described herein again.
S300, for all AiClustering to obtain a first entity cluster list C = { C = { (C) }1,……,Cx……,Cp},CxRefers to the x-th first entity cluster, x =1 … … p, p is the first entity cluster.
Specifically, the step S300 further includes the steps of:
s301, obtaining a first ontology list A '= { A'1,……,A'α,……,A'm},A'αRefers to the α -th first body corresponding to a, α =1 … … m, and m is the number of first bodies corresponding to a.
Specifically, a' is also acquired in the following steps before the step S301:
s3011, obtaining AiCorresponding body and based on all AiCorresponding ontology, constructing the first initial ontology list corresponding to A, and the skilled in the artThe body can be obtained by any method in the prior art, and the details are not repeated herein; the first initial ontology list includes a plurality of ontology types, e.g., places, people, etc.
S3013, perform deduplication processing on the first initial ontology list corresponding to the first entity to obtain a', where a person skilled in the art may obtain the first ontology list by using any deduplication method in the prior art, and details are not described here.
S303, obtaining A'αCorresponding entity list,UαgRefers to the g-th first entity in the entity list corresponding to the alpha-th first ontology, g =1 … …,Is of A'αThe number of the first entities in the corresponding entity list.
S305 according to UαgObtaining UαgCorresponding first Key entity List U'αg={U1 αg,……,Uβ αg,……,Uz αg},Uβ αgIs beta to the UαgThe corresponding first key entity, β =1 … … z, z obeys the following condition:。
specifically, UαgThe corresponding first key entity is denoted at A'αDivide U in the corresponding entity listαgAny first entity other than.
S307, according to UαgAnd U'αgObtaining UαgCorresponding first entity similarity list Tαg={T1 αg,……,Tβ αg,……,TZ αg},Tβ αgIs referred to as UαgAnd Uβ αgThe entity similarity between them.
In particular, Tβ αgThe following conditions are met:
is referred to as UαgThe corresponding gamma bit value, NK, in the vectorβ γIs referred to as Uβ αgThe corresponding gamma bit value in the vector, gamma =1 … …, Is referred to as UαgVector dimension in corresponding vector and Uβ αgCorresponding vector and UαgThe vector dimensions of the corresponding vectors are consistent.
Preferably, UαgCorresponding vector sum Uβ αgThe corresponding vectors are obtained through a pre-training language model, such as a Bert model, a sensor-transformer model, and the like.
Further, UαgCorresponding vector sum Uβ αgThe corresponding vector is a 768-dimensional vector, i.e.=768。
S309 according to TαgAnd acquiring a first entity cluster.
Specifically, the step S309 further includes the steps of:
s3091, traverse TαgAnd when each T isβ αg<F'0Determining UαgIs a first solid cluster block, wherein'0Refers to a predetermined entity similarity.
Preference is given toAnd F'0Is 0.6.
S3092, when any Tβ αg≥F'0From TαgThe first key entity corresponding to the maximum similarity is obtained as the first target entity and is based on the first target entity and the UαgBuilding UαgCorresponding first intermediate entity clusters.
S3093, according to the vector corresponding to the first target entity And UαgCorresponding vector Obtaining UαgVectors of corresponding intermediate entity clusters Wherein, in the step (A),refers to the gamma bit value in the vector corresponding to the first target entity,means thatThe corresponding average value, wherein,the following conditions are met:
s3094 according to UαgCorresponding intermediate solid clusters and UαgObtaining U corresponding to the first appointed entity listαgCorresponding first intermediate similarity list, wherein UαgAny one of the corresponding first intermediate similarity listsCorresponding intermediate degree of similarity meansAnd any one UαgSimilarity between vectors of corresponding first designated entities.
Specifically, UαgThe corresponding first designated entity is U'αgAny first key entity other than the first target entity.
In particular, the amount of the solvent to be used,corresponding intermediate similarity obtaining method and Tβ αgThe obtaining methods are consistent and are not described herein again.
S3095, mixing UαgInserting the first designated entity corresponding to the maximum similarity obtained from the corresponding first intermediate similarity list into UαgGenerating new U in corresponding intermediate entity clusterαgCorresponding intermediate entity clusters.
S3096, repeating the steps S3093-S305 until UαgEach similarity in the corresponding similarity list is less than F'0While determining UαgTaking an intermediate entity cluster corresponding to the corresponding final similarity list as a first entity cluster; it can be understood that: different entities are clustered into an entity cluster, so that whether different events refer to the same event or not is determined according to the same number of the entity clusters among different events, and the experience of users is improved.
S400, for all BjClustering to obtain a second entity cluster list D = { D =1,……,Dy,……,Dq},DyRefers to the y second entity cluster, wherein y =1 … … q, and q is the second entity cluster.
Specifically, the method for acquiring the second entity cluster is the same as the method for acquiring the first entity cluster, and is not described herein again.
S500, when CxAnd DyWhen they are consistent, determining CxThe corresponding first entity cluster is a target entity cluster;
specifically, the step S500 further comprises the following steps of target entity clusters:
s501, obtaining Cx={Cx1,……,Cxη,……,Cxn},CxηThe method is characterized in that the method refers to an eta first entity in an x first entity cluster, eta =1 … … n, and n is the number of the first entities in the x first entity cluster;
s503, obtaining Dy={Dy1,……,Dyδ,……,DywThe Dy delta refers to a delta second entity in the y second entity cluster, delta =1 … … w, and w is the number of the second entities in the y second entity cluster;
s505, when Cxη=DyδWhen, C is determinedxAnd the corresponding first entity cluster is a target entity cluster.
S600, acquiring the number k of the target entity clusters and acquiring event similarity F between a first event and a second event based on k.
Specifically, F satisfies the following condition:
F=2k/(p+q)。
in a specific embodiment, F further satisfies the following condition:
F=k(p+q)/2pq。
s700, when F is more than or equal to F0When the first event and the second event refer to the same event, namely the first event and the second event are determined as the common events, wherein F0Refers to a preset event similarity threshold.
Specifically, the method further includes the following steps before the step S700:
when F =2 k/(p + q), F is determined0=F01Wherein F is01To prepareSetting a first similarity threshold;
when F = k (p + q)/2 pq, F is determined0=F02Wherein F is02Is a preset second similarity threshold.
In the above, different similarity thresholds are determined according to different acquisition modes of the similarity, so that the method can be accurate.
Further, F01≠F02Preferably, F01Has a value of 0.8, F02Is 0.85.
S800, when F is less than F0Determining that the first event and the second event do not refer to the same event.
The embodiment provides a data processing system for determining a common finger event, which comprises: a database, a processor, and a memory storing a computer program, wherein the database comprises: a text set of events, which when executed by a processor, performs the steps of: acquiring a first entity list corresponding to a first event and a second entity list corresponding to a second event according to a text list of any event in a text set of the event, clustering all first entities in the first entity list to obtain a first entity cluster list, clustering all second entities in the second entity list to obtain a second entity cluster list, acquiring the same number of entity clusters in the first entity cluster list and the second entity cluster list according to the first entity cluster list and the second entity cluster list so as to acquire event similarity between the first event and the second event according to the same number of entity clusters, and determining whether the first event and the second event refer to the same event or not according to the event similarity; the method has the advantages that the same event represented by the two events can be accurately determined, repeated query of a user is avoided, experience of the user is improved, the same event is prevented from being described by texts of repeated texts, and the text quantity of the events is reduced.
Although the present invention has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A data processing system for determining coreference events, the system comprising: a database, a processor, and a memory storing a computer program, wherein the database comprises: text set of events H = { H = { (H)1,……,Hr,……,Hs},HrRefers to a text list corresponding to the r-th event, r =1 … … s, s is the number of events, and when the computer program is executed by a processor, the following steps are implemented:
s100, traversing H and according to HrAcquiring a first entity list A = { A) corresponding to the first event1,……,Ai,……,AM},AiThe method refers to the ith first entity corresponding to the first event, i =1 … … M, and M is the number of the first entities;
s200, according to HrAcquiring a second entity list B = { B ] corresponding to the second event1,……,Bj,……,BN},BjJ =1 … … N, where N is the number of second entities;
s300, for all AiClustering to obtain a first entity cluster list C = { C = { (C) }1,……,Cx,……,Cp},CxThe method is characterized in that the method refers to an x-th first entity cluster, wherein x =1 … … p, and p is a first entity cluster;
s400, for all BjClustering to obtain a second entity cluster list D = { D =1,……,Dy,……,Dq},DyThe method is characterized in that the method refers to the y-th second entity cluster, wherein y =1 … … q, and q is the second entity cluster;
s500, when CxAnd DyWhen they are consistent, determine CxThe corresponding first entity cluster is a target entity cluster;
s600, acquiring the number k of the target entity clusters and acquiring event similarity F between a first event and a second event based on k;
s700, when F is more than or equal to F0Determining that the first event and the second event refer to the same event, wherein F0The method comprises the steps of indicating a preset event similarity threshold value;
s800, when F is less than F0Determining that the first event and the second event do not refer to the same event.
2. The data processing system for determining co-designated events according to claim 1, characterized in that a is also obtained in step S100 by:
s101, determining any H from HrTaking the corresponding event as a first event;
s103, obtaining,HraRefers to the a text of the r event, where a =1 … … er,erThe number of texts referring to the r-th event;
s105, for HraPerforming entity extraction to obtain HraAcquiring a first intermediate entity list based on all the first initial entity lists corresponding to the first initial entity lists;
and S107, carrying out duplicate removal processing on the first intermediate entity list to obtain A.
3. The data processing system for determining a co-designated event according to claim 2, wherein B is further acquired in step S200 by:
s201, deleting H from HrAcquiring a corresponding text list to obtain a middle text set H ' = { H ' of the event '1,……,H't,……,H's-1},H'tThe method is characterized by comprising the steps of referring to a text list corresponding to the t-th event in the middle text set of the event, wherein t =1 … … s-1;
s203, determining any H 'from H'tTaking the corresponding event as a second event;
s205, obtaining,H'tbRefers to the b-th text of the t-th event, where b =1 … … ft,ftThe number of texts of the t-th event is referred to;
s207, to H'tbCarrying out entity extraction to obtain H'tbA corresponding second initial entity list and a second intermediate entity list are obtained based on all the second initial entity lists;
s209, carrying out duplicate removal processing on the second intermediate entity list to obtain B.
4. The data processing system for determining a co-designated event according to claim 1, further comprising the step of, in the step S300:
s301, a first ontology list A ' = { A ' corresponding to A is obtained '1,……,A'α,……,A'm},A'αThe number of the alpha first ontologies corresponding to A is defined, alpha =1 … … m, and m is the number of the first ontologies corresponding to A;
s303, obtaining A'αCorresponding entity list,UαgThe method refers to the g-th first entity in the entity list corresponding to the alpha-th first ontology, and g =1 … …,Is of A'αThe number of first entities in the corresponding entity list;
s305 according to UαgObtaining UαgCorresponding first Key entity List U'αg={U1 αg,……,Uβ αg,……,Uz αg},Uβ αgIs beta to the UαgThe corresponding first key entity, β =1 … … z, meets the following condition:;
s307, according to UαgAnd U'αgObtaining UαgCorresponding first entity similarity list Tαg={T1 αg,……,Tβ αg,……,TZ αg},Tβ αgIs referred to as UαgAnd Uβ αgEntity similarity between, wherein Tβ αgThe following conditions are met:
is referred to as UαgThe corresponding gamma bit value, NK, in the vectorβ γIs referred to as Uβ αgThe corresponding gamma bit value in the vector, gamma =1 … …,Is referred to as UαgVector dimension and U in corresponding vectorβ αgCorresponding vector and UαgThe vector dimensions of the corresponding vectors are consistent;
s309 according to TαgAnd acquiring a first entity cluster.
5. The data processing system for determining co-referenceevents as claimed in claim 1, wherein in the step S400, the acquisition method of the second entity cluster is identical to that of the first entity cluster.
6. The data processing system for determining co-referenceable events according to claim 1, wherein F satisfies the following condition:
F=2k/(p+q)。
7. the data processing system for determining co-referenceable events according to claim 1, wherein F satisfies the following condition:
F=k(p+q)/2pq。
8. the data processing system for determining co-referent events according to claim 6 or 7, further comprising the following steps before the step of S700:
when F =2 k/(p + q), F0=F01Wherein F is01Is a preset first similarity threshold;
when F = k (p + q)/2 pq, F0=F02Wherein F is02Is a preset second similarity threshold.
9. The data processing system for determining coreference events of claim 8, wherein the first similarity threshold value takes a value of 0.8.
10. The data processing system for determining co-designated events of claim 8, wherein the second similarity threshold value is 0.85.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210480177.0A CN114579675B (en) | 2022-05-05 | 2022-05-05 | Data processing system for determining common finger event |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210480177.0A CN114579675B (en) | 2022-05-05 | 2022-05-05 | Data processing system for determining common finger event |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114579675A true CN114579675A (en) | 2022-06-03 |
CN114579675B CN114579675B (en) | 2022-07-15 |
Family
ID=81784098
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210480177.0A Active CN114579675B (en) | 2022-05-05 | 2022-05-05 | Data processing system for determining common finger event |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114579675B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114792085A (en) * | 2022-06-22 | 2022-07-26 | 中科雨辰科技有限公司 | Data processing system for error correction of label text |
CN114925692A (en) * | 2022-07-21 | 2022-08-19 | 中科雨辰科技有限公司 | Data processing system for acquiring target event |
CN115017269A (en) * | 2022-08-05 | 2022-09-06 | 中科雨辰科技有限公司 | Data processing system for determining similar texts |
CN115169319A (en) * | 2022-07-21 | 2022-10-11 | 中科雨辰科技有限公司 | Data processing system for identification symbol |
CN117435697A (en) * | 2023-12-21 | 2024-01-23 | 中科雨辰科技有限公司 | Data processing system for acquiring core event |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130311467A1 (en) * | 2012-05-18 | 2013-11-21 | Xerox Corporation | System and method for resolving entity coreference |
CN110633330A (en) * | 2018-06-01 | 2019-12-31 | 北京百度网讯科技有限公司 | Event discovery method, device, equipment and storage medium |
CN111143576A (en) * | 2019-12-18 | 2020-05-12 | 中科院计算技术研究所大数据研究院 | Event-oriented dynamic knowledge graph construction method and device |
CN112559745A (en) * | 2020-12-11 | 2021-03-26 | 科大讯飞股份有限公司 | Method and related device for determining hot event |
CN113282703A (en) * | 2021-04-01 | 2021-08-20 | 中科雨辰科技有限公司 | Method and device for constructing event associated map of news data |
CN113468345A (en) * | 2021-09-02 | 2021-10-01 | 中科雨辰科技有限公司 | Entity co-reference detection data processing system based on knowledge graph |
CN114064918A (en) * | 2021-11-06 | 2022-02-18 | 中国电子科技集团公司第五十四研究所 | Multi-modal event knowledge graph construction method |
-
2022
- 2022-05-05 CN CN202210480177.0A patent/CN114579675B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130311467A1 (en) * | 2012-05-18 | 2013-11-21 | Xerox Corporation | System and method for resolving entity coreference |
CN110633330A (en) * | 2018-06-01 | 2019-12-31 | 北京百度网讯科技有限公司 | Event discovery method, device, equipment and storage medium |
CN111143576A (en) * | 2019-12-18 | 2020-05-12 | 中科院计算技术研究所大数据研究院 | Event-oriented dynamic knowledge graph construction method and device |
CN112559745A (en) * | 2020-12-11 | 2021-03-26 | 科大讯飞股份有限公司 | Method and related device for determining hot event |
CN113282703A (en) * | 2021-04-01 | 2021-08-20 | 中科雨辰科技有限公司 | Method and device for constructing event associated map of news data |
CN113468345A (en) * | 2021-09-02 | 2021-10-01 | 中科雨辰科技有限公司 | Entity co-reference detection data processing system based on knowledge graph |
CN114064918A (en) * | 2021-11-06 | 2022-02-18 | 中国电子科技集团公司第五十四研究所 | Multi-modal event knowledge graph construction method |
Non-Patent Citations (2)
Title |
---|
王君泽 等: "面向共指事件识别的同义表述模式抽取研究", 《情报学报》 * |
魏萍等: "基于触发词语义选择的Twitter事件共指消解研究", 《计算机科学》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114792085A (en) * | 2022-06-22 | 2022-07-26 | 中科雨辰科技有限公司 | Data processing system for error correction of label text |
CN114792085B (en) * | 2022-06-22 | 2022-09-16 | 中科雨辰科技有限公司 | Data processing system for error correction of label text |
CN114925692A (en) * | 2022-07-21 | 2022-08-19 | 中科雨辰科技有限公司 | Data processing system for acquiring target event |
CN115169319A (en) * | 2022-07-21 | 2022-10-11 | 中科雨辰科技有限公司 | Data processing system for identification symbol |
CN114925692B (en) * | 2022-07-21 | 2022-10-11 | 中科雨辰科技有限公司 | Data processing system for acquiring target event |
CN115017269A (en) * | 2022-08-05 | 2022-09-06 | 中科雨辰科技有限公司 | Data processing system for determining similar texts |
CN115017269B (en) * | 2022-08-05 | 2022-10-25 | 中科雨辰科技有限公司 | Data processing system for determining similar texts |
CN117435697A (en) * | 2023-12-21 | 2024-01-23 | 中科雨辰科技有限公司 | Data processing system for acquiring core event |
CN117435697B (en) * | 2023-12-21 | 2024-03-22 | 中科雨辰科技有限公司 | Data processing system for acquiring core event |
Also Published As
Publication number | Publication date |
---|---|
CN114579675B (en) | 2022-07-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114579675B (en) | Data processing system for determining common finger event | |
CN114925692B (en) | Data processing system for acquiring target event | |
Wang et al. | Fast Bayesian inference in Dirichlet process mixture models | |
CN108519971B (en) | Cross-language news topic similarity comparison method based on parallel corpus | |
Tu et al. | Unsupervised structure learning of stochastic and-or grammars | |
Chen et al. | Dependent normalized random measures | |
WO2021051508A1 (en) | Robot dialogue generating method and apparatus, readable storage medium, and robot | |
Song et al. | Bayesian analysis of two‐level nonlinear structural equation models with continuous and polytomous data | |
WO2021008037A1 (en) | A-bilstm neural network-based text classification method, storage medium, and computer device | |
Huang et al. | Solution Path for Pin-SVM Classifiers With Positive and Negative $\tau $ Values | |
Hu et al. | Clustering matrix sequences based on the iterative dynamic time deformation procedure | |
CN114996414B (en) | Data processing system for determining similar events | |
CN112348079A (en) | Data dimension reduction processing method and device, computer equipment and storage medium | |
Teimouri | EM algorithm for mixture of skew-normal distributions fitted to grouped data | |
Shatkay et al. | Information retrieval meets gene analysis | |
Psutka et al. | Sample size for maximum-likelihood estimates of gaussian model depending on dimensionality of pattern space | |
Kundaje et al. | Combining sequence and time series expression data to learn transcriptional modules | |
CN110377721B (en) | Automatic question answering method, device, storage medium and electronic equipment | |
CN110413750B (en) | Method and device for recalling standard questions according to user questions | |
Yin et al. | Accelerating distributed Expectation–Maximization algorithms with frequent updates | |
CN115017269A (en) | Data processing system for determining similar texts | |
Navlakha et al. | Finding biologically accurate clusterings in hierarchical tree decompositions using the variation of information | |
De Iorio et al. | Bayesian nonparametric mixture modeling for temporal dynamics of gender stereotypes | |
Corder et al. | Estimating average treatment effects utilizing fractional imputation when confounders are subject to Missingness | |
Yuan et al. | Unsupervised clustering of gene expression time series with conditional random fields |
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 |