CN115048925A - Data processing system for determining abnormal text - Google Patents
Data processing system for determining abnormal text Download PDFInfo
- Publication number
- CN115048925A CN115048925A CN202210976335.1A CN202210976335A CN115048925A CN 115048925 A CN115048925 A CN 115048925A CN 202210976335 A CN202210976335 A CN 202210976335A CN 115048925 A CN115048925 A CN 115048925A
- Authority
- CN
- China
- Prior art keywords
- text
- initial
- entity relationship
- target
- determining
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- 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
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
-
- 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
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a data processing system for determining abnormal texts, which comprises: a database, a processor and a memory storing a computer program which, when executed by the processor, performs the steps of: acquiring an initial statement list and initial characters according to the initial text; acquiring an entity relationship probability list and a target entity relationship probability list; acquiring the maximum probability value of the target entity relationship; acquiring the priority corresponding to the initial text; when the priority is greater than or equal to a preset priority threshold, determining the initial text as a target text; otherwise, determining the initial text as an abnormal text. On one hand, in the process of processing the text, the entity is extracted by using only one preset model, so that the used text data is less, the workload of a labeling person is reduced, and on the other hand, in the process of extracting the entity relationship, the entity relationship is extracted by using multiple methods, so that the accuracy of the model for predicting the entity relationship is improved.
Description
Technical Field
The invention relates to the technical field of text processing, in particular to a data processing system for determining abnormal texts.
Background
Most of existing abnormal text determination methods determine whether an entity in a text meets a preset condition, input the text to be recognized into an entity recognition model, extract various entities from the text, process the extracted entities, and determine that the text is an abnormal text when the entity does not meet the preset condition.
The existing entity relationship extraction method comprises the following steps: determining a sentence distributed vector of each sentence in the target sentence sub-packet and a relation distributed vector of the query relation; each sentence in the target sentence sub-packet comprises a first entity and a second entity; determining a strategy function according to the sentence distributed vectors and the relation distributed vectors, and dividing all sentences in the target sentence sub-packet into positive examples and unmarked examples by utilizing the strategy function; and training a relation extraction model by using the normal example and the unmarked example to obtain the entity relation between the first entity and the second entity.
However, the above method also has the following technical problems:
firstly, in the process of processing the text, a plurality of preset models are required to be used for extracting the entity, a large amount of text data and storage space are required to be used, and the workload of a marking person is overlarge.
Secondly, in the extraction process of the entity relationship, the processing process is single, the entity relationship can be extracted only in one mode, and the prediction accuracy of the model on the entity relationship is low.
Disclosure of Invention
Aiming at the technical problems, the technical scheme adopted by the invention is as follows:
a data processing system for determining anomalous text, said system comprising: a database, a processor, and a memory storing a computer program, wherein the database comprises: initial text list H = { H = { (H) 1 ,……,H i ,……,H m },H i Is the ith initial textWhere i =1 … … m, m being the number of initial texts, the computer program, when executed by a processor, performs the steps of:
s100 according to H i Obtaining H i Corresponding initial sentence list D i ={D i1 ,……,D ij ,……,D ini },D ij =(D 1 ij ,……,D r ij ,……,D sj ij ),D r ij Is H i The r initial character of the j initial sentence, j =1 … … ni, ni is H i R =1 … … sj, sj being the number of initial characters in the jth initial sentence.
S200, according to D r ij Obtaining D r ij Corresponding initial entity relationship list G r ij ={G r1 ij ,……,G rx ij ,……,G rq ij },G rx ij Is D r ij And the probability value of the corresponding x-th type initial entity relation, x =1 … … q, and q is the type number of the initial entity relation.
S300, traverse G r ij And when G is rx ij When the type of the corresponding initial entity relationship is the type of the non-target relationship, the secondary G r ij Deletion in G rx ij Construction of D r ij Corresponding target entity relation list U r ij ={U r1 ij ,……,U ry ij ,……,U rp ij },U ry ij Is D r ij And the probability value of the corresponding y-th category target entity relation, y =1 … … p, and p is the type number of the target entity relation.
S400, traversing U r ij And when U is turned ry ij ≥U 0 Then, from U r ij In order to obtain the maximum probability value, U, of the target entity relationship 0 Is a preset confidence threshold.
S500, determining H according to the maximum probability value of the target entity relationship i Is an abnormal text.
The invention has at least the following beneficial effects:
the invention provides a data processing system for determining abnormal texts, which comprises: a database, a processor, and a memory storing a computer program, wherein the database comprises: an initial text set, which when executed by a processor, performs the steps of: acquiring an initial sentence list and initial characters corresponding to the initial text according to the initial text; acquiring a corresponding entity relationship probability list according to the initial character, and performing traversal processing on the entity relationship probability list to acquire a target entity relationship probability list corresponding to the initial character; traversing the target entity relationship probability list to obtain the maximum probability value of the target entity relationship; acquiring the priority corresponding to the initial text according to the maximum probability value of the target entity relationship; when the priority is greater than or equal to a preset priority threshold, determining the initial text as a target text; when the priority is smaller than a preset priority threshold, determining the initial text as an abnormal text; therefore, on one hand, in the process of processing the text, the entity can be extracted by using only one preset model, so that the used text data is less, and the workload of marking personnel is reduced; on the other hand, in the extraction process of the entity relationship, the entity relationship can be extracted by using various methods, so that the prediction accuracy of the model on the entity relationship is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart of a computer program executed by a data processing system for determining an abnormal text according to an 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 derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope 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.
The embodiment provides a data processing system for determining an abnormal text, which includes: a database, a processor, and a memory storing a computer program, wherein the database comprises: initial text list H = { H = { (H) 1 ,……,H i ,……,H m },H i For the i-th initial text, i =1 … … m, m being the number of initial texts, which when executed by a processor performs the following steps, as shown in fig. 1:
s100 according to H i Obtaining H i Corresponding initial sentence list D i ={D i1 ,……,D ij ,……,D ini },D ij =(D 1 ij ,……,D r ij ,……,D sj ij ),D r ij Is H i The r initial character of the j initial sentence, j =1 … … ni, ni is H i R =1 … … sj, sj being the number of initial characters in the jth initial sentence.
Specifically, the initial sentence is a sentence obtained by performing sentence splitting processing on an initial text, where a person skilled in the art knows that any sentence splitting processing method in the prior art belongs to the protection scope of this embodiment, and is not described herein again.
Further, the initial character refers to any character in the initial sentence.
S200, according to D r ij Obtaining D r ij Corresponding initial entity relationship list G r ij ={G r1 ij ,……,G rx ij ,……,G rq ij },G rx ij Is D r ij And the probability value of the corresponding x-th type initial entity relation, x =1 … … q, and q is the type number of the initial entity relation.
Specifically, the initial entity relationship is an association relationship between entities in a triple corresponding to the initial sentence, wherein a probability value of the entity relationship and the triple are obtained through a preset model.
Further, the preset model is an active learning model, and those skilled in the art know that any active learning model in the prior art belongs to the protection scope of the present embodiment, and is not described herein again.
In particular, sigma q x=1 (G rx ij )=1。
S300, go through G r ij And when G is rx ij When the type of the corresponding initial entity relationship is the type of the non-target relationship, the secondary G r ij Deletion in G rx ij Construction of D r ij Corresponding target entity relation list U r ij ={U r1 ij ,……,U ry ij ,……,U rp ij },U ry ij Is D r ij Probability value of corresponding y-th class target entity relationY =1 … … p, p being the number of types of target entity relationships.
Specifically, the non-target relationship is a relationship without an association state between entities, for example, the non-target relationship.
S400, traversing U r ij And when U is turned ry ij ≥U 0 Then, from U r ij In order to obtain the maximum probability value, U, of the target entity relationship 0 Is a preset probability value threshold.
In particular, U 0 The value range of (A) is 0.5-0.6.
Preferably, U 0 The value is 0.5, and the situation that the threshold value is set too high, so that some relation probabilities are deleted, data are omitted, and further, the abnormal text is judged inaccurately can be avoided.
S500, determining H according to the maximum probability value of the target entity relationship i Is an abnormal text.
Specifically, step S500 includes the steps of:
s501, based on U r ij The maximum probability value of the medium target entity relationship is constructed into H i Corresponding first intermediate data list V i ={V i1 ,……,V ij ,……,V ini },V ij =(V 1 ij ,……,V t ij ,……,V kj ij ),V t ij Is H i The probability value of the t target character in the corresponding j initial sentence, t =1 … … kj, kj is the number of the target characters in the j initial sentence.
S503 according to V t ij Obtaining F 0 i ,F 0 i The following conditions are met:
s505, when F 0 i ≥F 0 Then, H is determined i Is a target text, wherein F 0 Is a preset priority threshold.
S507, when F 0 i <F 0 Then, H is determined i Is an abnormal text.
In the process of processing the text, the entity and the data in the text are extracted by using only one preset model instead of using multiple preset models, so that the used text data are less, and the workload of a marking person is reduced.
In a specific embodiment, step S500 further includes the following steps:
s501, obtaining H according to the maximum probability value of the target entity relationship i Corresponding priority list F i ={F i1 ,……,F iy ,……,F ip },F iy Is H i The corresponding priority of the y-th category target entity relationship.
Wherein F is further acquired in the step S501 through the following steps iy :
S5011, based on U r ij The maximum probability value of the medium target entity relationship is constructed into H i Corresponding second intermediate data list C i ={C i1 ,……,C iy ,……,C ip },C iy ={C 1 iy ,……,C g iy ,……,C zy iy },C g iy =(C g1 iy ,……,C ge iy ,……,C gwg iy ),C ge iy Is at H i In the corresponding y-th category target entity relationship, the probability value of the e-th target character in the g-th initial sentence is g =1 … … zy, zy is the number of the g-th initial sentences in the y-th category target entity relationship, e =1 … … wg, wg is the number of the target characters in the g-th initial sentence.
S5013 according to C ge iy ,F iy The following conditions are met:
s503, when F ip ≥F 0 Then, H is determined i Is a target text, wherein F 0 Is a preset priority threshold.
S505, when F ip <F 0 Then, H is determined i Is an abnormal text.
Compared with the embodiment, the classification method is adopted when the abnormal text is determined, the initial text can be determined to be the abnormal text only when any kind of relation does not exist between the entities, and the prediction accuracy of the model on the entity relation is improved.
In another embodiment, step S500 further includes the steps of:
s501, based on U r ij The maximum probability value of the medium target entity relationship is constructed into H i Corresponding first intermediate data list V i ={V i1 ,……,V ij ,……,V ini },V ij =(V 1 ij ,……,V t ij ,……,V kj ij ),V t ij Is H i The probability value of the t target character in the corresponding j initial sentence, t =1 … … kj, kj is the number of the target characters in the j initial sentence.
S503 according to V t ij Obtaining F 0 i ,F 0 i The following conditions are met:
s505, when F 0 i ≥F 0 Then, H is determined i Is a target text, wherein F 0 Is a preset priority threshold.
S507, when F 0 i <F 0 Then, H is determined i Is a text to be processed and performs the step S509.
S509, according to H i Obtaining the maximum probability value of the target entity relationship H i Corresponding priority list F i ={F i1 ,……,F iy ,……,F ip },F iy Is H i The corresponding priority of the y-th category target entity relationship.
Further, F is also acquired in step S509 by the following steps iy :
S5091 based on U r ij The maximum probability value of the medium target entity relationship is constructed into H i Corresponding second intermediate data list C i ={C i1 ,……,C iy ,……,C ip },C iy ={C 1 iy ,……,C g iy ,……,C zy iy },C g iy =(C g1 iy ,……,C ge iy ,……,C gwg iy ),C ge iy Is at H i In the corresponding y-th category target entity relationship, the probability value of the e-th target character in the g-th initial sentence is g =1 … … zy, zy is the number of the g-th initial sentences in the y-th category target entity relationship, e =1 … … wg, wg is the number of the target characters in the g-th initial sentence.
S5093 according to C ge iy ,F iy The following conditions are met:
s511, when F ip ≥F 0 Then, H is determined i Is a target text, wherein F 0 Is a preset priority threshold.
S513, when F ip <F 0 Then, H is determined i Is an abnormal text.
Compared with the first embodiment, the method and the device for predicting the entity relationship have the advantages that the probability of judging the target text into the abnormal text can be reduced, the accuracy of the model for predicting the entity relationship is further improved, compared with the second embodiment, the efficiency is improved, and the workload of annotating personnel is reduced.
Specifically, the target character is when U ry ij ≥U 0 While, U ry ij The corresponding initial character.
Specifically, F 0 The value range of (a) is 0.8-1.
Preferably, F 0 The value is 0.8, so that the situation that the judgment on the abnormal text is not accurate enough due to too low threshold value setting can be avoided.
More preferably, F 0 The value is 0.9, so that the abnormal text can be judged more accurately.
Most preferably, F 0 The value is 1, and the initial text can be completely determined to be the abnormal text.
Specifically, the target text is text in which the priority of the entity relationship in the annotation text is not less than the priority threshold.
Specifically, the abnormal text is a text in which the priority of the entity relationship in the annotation text is smaller than a priority threshold, where the abnormal text may be understood as an initial text of an entity relationship type corresponding to the initial text in a preset entity relationship type, or the abnormal text may also be understood as an initial text in which an error is annotated to the entity relationship.
The embodiment provides a data processing system for determining an abnormal text, which comprises: a database, a processor, and a memory storing a computer program, wherein the database comprises: an initial text set, which when executed by a processor, performs the steps of: acquiring an initial sentence list and initial characters corresponding to the initial text according to the initial text; acquiring a corresponding entity relationship probability list according to the initial character, and performing traversal processing on the entity relationship probability list to acquire a target entity relationship probability list corresponding to the initial character; traversing the target entity relationship probability list to obtain the maximum probability value of the target entity relationship; acquiring the priority corresponding to the initial text according to the maximum probability value of the target entity relationship; when the priority is greater than or equal to a preset priority threshold, determining the initial text as a target text; when the priority is smaller than a preset priority threshold, determining the initial text as an abnormal text; therefore, on one hand, in the process of processing the text, the entity can be extracted by using only one preset model, so that the used text data is less, and the workload of marking personnel is reduced; on the other hand, in the extraction process of the entity relationship, the entity relationship can be extracted by using various methods, so that the prediction accuracy of the model on the entity relationship 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 (10)
1. A data processing system for determining anomalous text, said system comprising: a database, a processor, and a memory storing a computer program, wherein the database comprises: initial text list H = { H = { (H) 1 ,……,H i ,……,H m },H i For the ith initial text, i =1 … … m, m being the number of initial texts, which when executed by a processor performs the steps of:
s100 according to H i Obtaining H i Corresponding initial sentence list D i ={D i1 ,……,D ij ,……,D ini },D ij =(D 1 ij ,……,D r ij ,……,D sj ij ),D r ij Is H i The r initial character of the j initial sentence, j =1 … … ni, ni is H i R =1 … … sj, sj being the number of initial characters in the jth initial sentence;
s200, according to D r ij Obtaining D r ij Corresponding initial entity relationship list G r ij ={G r1 ij ,……,G rx ij ,……,G rq ij },G rx ij Is D r ij The probability value of the corresponding x-th type initial entity relationship, x =1 … … q, q is the type number of the initial entity relationship;
s300, traverse G r ij And when G is rx ij When the type of the corresponding initial entity relationship is the type of the non-target relationship, the secondary G r ij Deletion in G rx ij Construction of D r ij Corresponding target entity relation list U r ij ={U r1 ij ,……,U ry ij ,……,U rp ij },U ry ij Is D r ij The probability value of the corresponding y-th category target entity relationship, y =1 … … p, p is the type number of the target entity relationship;
s400, traversing U r ij And when U is turned ry ij ≥U 0 Then, from U r ij In order to obtain the maximum probability value, U, of the target entity relationship 0 Is a preset probability value threshold;
s500, determining H according to the maximum probability value of the target entity relationship i Is an abnormal text.
2. The data processing system for determining abnormal texts according to claim 1, wherein in the step S200, the initial entity relationship is an association relationship between entities in a triplet corresponding to an initial sentence.
3. The data processing system for determining an abnormal text according to claim 1, wherein in step S200, Σ q x=1 (G rx ij )=1。
4. The data processing system for determining abnormal text according to claim 1, wherein in the step S300, the non-target relationship is an unassociated relationship between entities.
5. Determining abnormal text according to claim 1Is characterized in that, in the step S400, U 0 The value range of (A) is 0.5-0.6.
6. The data processing system for determining an abnormal text according to claim 1, further comprising the following steps in the step S500:
s501, based on U r ij The maximum probability value of the medium target entity relationship is constructed into H i Corresponding first intermediate data list V i ={V i1 ,……,V ij ,……,V ini },V ij =(V 1 ij ,……,V t ij ,……,V kj ij ),V t ij Is H i The probability value of the t target character in the corresponding j initial sentence, t =1 … … kj, kj is the number of the target characters in the j initial sentence;
s503 according to V t ij Obtaining F 0 i ,F 0 i The following conditions are met:
s505, when F 0 i ≥F 0 Then, H is determined i Is a target text, wherein F 0 Is a preset priority threshold;
s507, when F 0 i <F 0 Then, H is determined i Is an abnormal text.
7. The data processing system for determining an abnormal text according to claim 1, wherein the step S500 is performed by:
s501, obtaining H according to the maximum probability value of the target entity relationship i Corresponding priority list F i ={F i1 ,……,F iy ,……,F ip },F iy Is H i The priority corresponding to the y-th category target entity relationship;
wherein F is further acquired in the step S501 through the following steps iy :
S5011, based on U r ij The maximum probability value of the medium target entity relationship is constructed into H i Corresponding second intermediate data list C i ={C i1 ,……,C iy ,……,C ip },C iy ={C 1 iy ,……,C g iy ,……,C zy iy },C g iy =(C g1 iy ,……,C ge iy ,……,C gwg iy ),C ge iy Is at H i In the corresponding y category target entity relationship, the probability value of the e target character in the g initial sentence is g =1 … … zy, zy is the number of the g initial sentence in the y category target entity relationship, e =1 … … wg is the number of the target character in the g initial sentence;
s5013 according to C ge iy ,F iy The following conditions are met:
s503, when F ip ≥F 0 Then, H is determined i Is a target text, wherein F 0 Is a preset priority threshold;
s505, when F ip <F 0 Then, H is determined i Is an abnormal text.
8. The data processing system for determining abnormal text according to claim 6 or 7, wherein F is 0 The value range of (A) is 0.8-1.
9. The data processing system for determining abnormal text according to claim 6 or 7, wherein the target text is a text in which the priority of the entity relationship in the annotation text is not less than a preset priority threshold.
10. The data processing system for determining abnormal text according to claim 6 or 7, wherein the abnormal text is a text in which the priority of the entity relationship in the annotation text is less than a preset priority threshold.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210976335.1A CN115048925B (en) | 2022-08-15 | 2022-08-15 | Data processing system for determining abnormal text |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210976335.1A CN115048925B (en) | 2022-08-15 | 2022-08-15 | Data processing system for determining abnormal text |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115048925A true CN115048925A (en) | 2022-09-13 |
CN115048925B CN115048925B (en) | 2022-11-04 |
Family
ID=83167812
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210976335.1A Active CN115048925B (en) | 2022-08-15 | 2022-08-15 | Data processing system for determining abnormal text |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115048925B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115408160A (en) * | 2022-09-16 | 2022-11-29 | 湖南胜云光电科技有限公司 | Data processing system for process monitoring |
CN115410104A (en) * | 2022-09-16 | 2022-11-29 | 湖南胜云光电科技有限公司 | Data processing system for acquiring image acquisition points of aircraft |
CN115858208A (en) * | 2022-09-29 | 2023-03-28 | 杭州中电安科现代科技有限公司 | Method for acquiring target data and extracting text list |
CN116167339A (en) * | 2022-12-02 | 2023-05-26 | 中科雨辰科技有限公司 | Data processing system for acquiring link entity based on entity relationship |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109344396A (en) * | 2018-08-31 | 2019-02-15 | 阿里巴巴集团控股有限公司 | Text recognition method, device and computer equipment |
CN109582833A (en) * | 2018-11-06 | 2019-04-05 | 阿里巴巴集团控股有限公司 | Abnormal Method for text detection and device |
US20200327194A1 (en) * | 2019-04-10 | 2020-10-15 | International Business Machines Corporation | Displaying text classification anomalies predicted by a text classification model |
CN111832287A (en) * | 2020-07-22 | 2020-10-27 | 广东工业大学 | Entity relationship joint extraction method and device |
CN112632996A (en) * | 2020-12-08 | 2021-04-09 | 浙江大学 | Entity relation triple extraction method based on comparative learning |
CN113011189A (en) * | 2021-03-26 | 2021-06-22 | 深圳壹账通智能科技有限公司 | Method, device and equipment for extracting open entity relationship and storage medium |
-
2022
- 2022-08-15 CN CN202210976335.1A patent/CN115048925B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109344396A (en) * | 2018-08-31 | 2019-02-15 | 阿里巴巴集团控股有限公司 | Text recognition method, device and computer equipment |
CN109582833A (en) * | 2018-11-06 | 2019-04-05 | 阿里巴巴集团控股有限公司 | Abnormal Method for text detection and device |
US20200327194A1 (en) * | 2019-04-10 | 2020-10-15 | International Business Machines Corporation | Displaying text classification anomalies predicted by a text classification model |
CN111832287A (en) * | 2020-07-22 | 2020-10-27 | 广东工业大学 | Entity relationship joint extraction method and device |
CN112632996A (en) * | 2020-12-08 | 2021-04-09 | 浙江大学 | Entity relation triple extraction method based on comparative learning |
CN113011189A (en) * | 2021-03-26 | 2021-06-22 | 深圳壹账通智能科技有限公司 | Method, device and equipment for extracting open entity relationship and storage medium |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115408160A (en) * | 2022-09-16 | 2022-11-29 | 湖南胜云光电科技有限公司 | Data processing system for process monitoring |
CN115410104A (en) * | 2022-09-16 | 2022-11-29 | 湖南胜云光电科技有限公司 | Data processing system for acquiring image acquisition points of aircraft |
CN115408160B (en) * | 2022-09-16 | 2023-05-05 | 湖南胜云光电科技有限公司 | Data processing system for process monitoring |
CN115410104B (en) * | 2022-09-16 | 2023-06-16 | 湖南胜云光电科技有限公司 | Data processing system for acquiring image acquisition points of aircraft |
CN115858208A (en) * | 2022-09-29 | 2023-03-28 | 杭州中电安科现代科技有限公司 | Method for acquiring target data and extracting text list |
CN115858208B (en) * | 2022-09-29 | 2024-05-14 | 杭州中电安科现代科技有限公司 | Method for acquiring target data and extracting text list |
CN116167339A (en) * | 2022-12-02 | 2023-05-26 | 中科雨辰科技有限公司 | Data processing system for acquiring link entity based on entity relationship |
CN116167339B (en) * | 2022-12-02 | 2023-08-15 | 中科雨辰科技有限公司 | Data processing system for acquiring link entity based on entity relationship |
Also Published As
Publication number | Publication date |
---|---|
CN115048925B (en) | 2022-11-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115048925B (en) | Data processing system for determining abnormal text | |
US20210382937A1 (en) | Image processing method and apparatus, and storage medium | |
CN110991178B (en) | Intelligent customer service and manual customer service switching method and device and computer equipment | |
WO2020259280A1 (en) | Log management method and apparatus, network device and readable storage medium | |
CN110362814B (en) | Named entity identification method and device based on improved loss function | |
CN109739975B (en) | Hot event extraction method and device, readable storage medium and electronic equipment | |
CN110321426B (en) | Digest extraction method and device and computer equipment | |
WO2022001517A1 (en) | Information sending method and apparatus based on rumor prediction model, and computer device | |
CN112699923A (en) | Document classification prediction method and device, computer equipment and storage medium | |
CN109271957B (en) | Face gender identification method and device | |
AU2020441876A1 (en) | Method for determining human phenotype ontology, and related devices | |
CN114021573B (en) | Natural language processing method, device, equipment and readable storage medium | |
WO2021217619A1 (en) | Label smoothing-based speech recognition method, terminal, and medium | |
CN115017269B (en) | Data processing system for determining similar texts | |
CN113806565B (en) | Data processing system for text labeling | |
CN114021572B (en) | Natural language processing method, device, equipment and readable storage medium | |
CN116186658A (en) | User identity verification data processing system | |
CN115062137A (en) | Data processing system for determining abnormal text based on active learning | |
CN113157788B (en) | Big data mining method and system | |
CN113095073B (en) | Corpus tag generation method and device, computer equipment and storage medium | |
CN110543634B (en) | Corpus data set processing method and device, electronic equipment and storage medium | |
US20240249078A1 (en) | Method and system for automated q&a via enriched text similarity | |
CN115733903B (en) | Network asset identification method and system based on natural processing feature engineering | |
CN114417838B (en) | Method for extracting synonym block pairs based on transformer model | |
CN118093325B (en) | Log template acquisition method, electronic 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 |