CN116562260A - Text information processing method and processing system - Google Patents
Text information processing method and processing system Download PDFInfo
- Publication number
- CN116562260A CN116562260A CN202310827523.2A CN202310827523A CN116562260A CN 116562260 A CN116562260 A CN 116562260A CN 202310827523 A CN202310827523 A CN 202310827523A CN 116562260 A CN116562260 A CN 116562260A
- Authority
- CN
- China
- Prior art keywords
- normalized
- key information
- text
- information
- association
- 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
- 230000010365 information processing Effects 0.000 title claims abstract description 29
- 238000003672 processing method Methods 0.000 title claims abstract description 22
- 238000012545 processing Methods 0.000 title claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000006243 chemical reaction Methods 0.000 claims abstract description 4
- 238000005516 engineering process Methods 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000005065 mining Methods 0.000 abstract description 7
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/041—Abduction
Abstract
The invention relates to the technical field of information processing, and discloses a text information processing method and a text information processing system, wherein the text information processing method comprises the following steps: constructing a key information extraction model, and extracting key information in a target text based on the key information extraction model; constructing a normalized expression rule, and performing normalized conversion on the key information based on the normalized expression rule to obtain normalized key information; establishing an inference rule, and inferring normalized key information based on the inference rule to obtain an association rule between the normalized key information; reasoning association relation between normalized key information based on association rules, and obtaining constraint information between the normalized key information based on the association relation; correlating the normalized key information based on the constraint information; the invention solves the problems of low text mining and association accuracy under the conditions of fewer texts and missing training data in the existing text processing mode.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a text information processing method and a processing system.
Background
Current machine learning relies on training data sets, however, in some scenarios the training data sets are small in size or even scarce, for which case it is necessary to design text mining techniques under training-missing conditions. The methods commonly used at present are as follows: classification, regression analysis, clustering, association rules, neural network methods, web data mining, etc., which mine data from different angles, but these methods have problems of less text, text mining in the absence of training data, and lower association accuracy. It can be seen that the existing text processing method has the problem of low text mining and association accuracy under the conditions of fewer texts and missing training data.
Disclosure of Invention
The invention provides a text information processing method and a text information processing system, which are used for solving the problems of low text mining and association accuracy under the conditions of fewer texts and missing training data in the existing text processing mode.
In order to achieve the above object, the present invention is realized by the following technical scheme:
in a first aspect, the present invention provides a text information processing method, including:
constructing a key information extraction model, and extracting key information in a few-sample target text based on the key information extraction model;
constructing a normalized expression rule, and performing normalized conversion on the key information based on the normalized expression rule to obtain normalized key information;
establishing an inference rule based on text information of front and rear positions of the normalized key information in a few sample target text, and inferring the normalized key information based on the inference rule to obtain an association rule between the normalized key information;
reasoning association relations among the normalized key information based on the association rules, and screening the association relations based on processing requirements to obtain constraint information among the normalized key information;
and associating the normalized key information based on the constraint information.
Optionally, the constructing the key information extraction model includes:
and constructing a text extraction model, training the text extraction model by taking text information to be extracted as a training set, and taking the trained text extraction model as a key information extraction model.
Optionally, the constructing a normalized expression rule includes:
and determining a normalized expression text based on the key information, and constructing a normalized expression rule based on the normalized expression text.
Optionally, the performing normalized transformation on the key information based on the normalized expression rule to obtain normalized key information includes:
constructing a normalized corpus, and establishing a pairing rule text for text information in the normalized corpus based on the normalized expression rule;
comparing the key information with text information in the normalized corpus, outputting the text information in the normalized corpus when the key information is matched with the pairing rule text corresponding to the text information in the normalized corpus, and taking the text information as normalized key information.
Optionally, the constructing an inference rule based on the text information of the front and rear positions of the normalized key information in the few sample target text includes:
and acquiring the associated text of the front and rear positions of the normalized key information in the few sample target text, obtaining the relation between the normalized key information and other text information based on the associated text, and taking the relation as an inference rule.
Optionally, the reasoning the normalized key information based on the reasoning rule to obtain an association rule between the normalized key information includes:
reasoning the normalized key information by utilizing the reasoning rule based on the attribute of the normalized key information, wherein the attribute of the normalized key information comprises a space-time attribute and a space attribute;
aiming at the time-space attribute, distinguishing two basic tenses of a time point and a time period, and finding out the equality between the time points through a time sequence target similarity calculation technology, wherein the time association relations of the time periods are prior, overlapped, contained and accepted;
aiming at the spatial attribute, three basic spatial forms of points, lines and areas are distinguished, and the equal space relationship between the spatial points and the intersection between the lines are found out through a spatial line group target similarity calculation technology, wherein the adjacent space relationship between the areas comprises equal space association relations;
and taking the time association relationship and the space association relationship as association rules.
Optionally, the reasoning the association relation between the normalized key information based on the association rule includes:
and reasoning the association relation of the time text in the normalized key information based on the time association relation, and reasoning the association relation of the space text in the normalized key information based on the space association relation.
Optionally, the filtering the association relation based on the processing requirement to obtain constraint information between the normalized key information includes:
a space-time ontology representation model oriented to the combat environment and application requirements is established, space-time information is used as a limiting condition of the ontology, the existing space-time reasoning and space reasoning technology is comprehensively applied, and various relations of the information in space-time dimension are calculated and integrated, so that constraint information of target movement in time and space dimension is obtained.
Optionally, the associating the normalized key information based on the constraint information includes:
and after constraint information is acquired, carrying out association processing on the tracks intersecting, the areas adjacent and the inclusion on the normalized key information in the time equality, the time period prior to, coincident with, including and bearing the normalized key information and the space point.
In a second aspect, an embodiment of the present application provides a text information processing system, including a processor and a memory;
a memory for storing a computer program;
a processor for implementing the method steps of any one of the first aspects when executing a program stored on a memory.
The beneficial effects are that:
according to the text information processing method provided by the invention, key information in a target text is extracted by constructing a key information extraction model, a normalized expression rule is constructed, the key information is normalized and converted to obtain normalized key information, an inference rule is constructed, and an association rule between the normalized key information is obtained, so that the association relation between the normalized key information is inferred, constraint information between the normalized key information is obtained based on the association relation, and finally the normalized key information is associated based on the constraint information; the method solves the problem of low text mining and association accuracy under the conditions of less text and lack of training data by extracting and associating the text.
Drawings
Fig. 1 is a flowchart of a text information processing method according to a preferred embodiment of the present invention.
Detailed Description
The following description of the present invention will be made clearly and fully, and it is apparent that the embodiments described are only some, but not all, of the embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. Likewise, the terms "a" or "an" and the like do not denote a limitation of quantity, but rather denote the presence of at least one. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate a relative positional relationship, which changes accordingly when the absolute position of the object to be described changes.
Referring to fig. 1, an embodiment of the present application provides a text information processing method, including:
constructing a key information extraction model, and extracting key information in a few-sample target text based on the key information extraction model;
constructing a normalized expression rule, and performing normalized conversion on the key information based on the normalized expression rule to obtain normalized key information;
establishing an inference rule based on text information of front and rear positions of the normalized key information in a few sample target text, and inferring the normalized key information based on the inference rule to obtain an association rule between the normalized key information;
reasoning association relations among the normalized key information based on the association rules, and screening the association relations based on processing requirements to obtain constraint information among the normalized key information;
and associating the normalized key information based on the constraint information.
In the embodiment, key information in a target text is extracted through constructing a key information extraction model, a normalized expression rule is constructed, the key information is normalized and converted to obtain normalized key information, an inference rule is constructed, and an association rule between the normalized key information is obtained, so that an association relation between the normalized key information is inferred, constraint information between the normalized key information is obtained based on the association relation, and finally the normalized key information is associated based on the constraint information; the method solves the problem of low text mining and association accuracy under the conditions of less text and lack of training data by extracting and associating the text.
The small sample target text refers to a target text with a small or even almost no training data set in the target text in some scenes, and the target text cannot be trained by means of the existing machine learning mode.
Optionally, the constructing the key information extraction model includes:
and constructing a text extraction model, training the text extraction model by taking text information to be extracted as a training set, and taking the trained text extraction model as a key information extraction model.
Optionally, the constructing a normalized expression rule includes:
and determining a normalized expression text based on the key information, and constructing a normalized expression rule based on the normalized expression text.
Optionally, the performing normalized transformation on the key information based on the normalized expression rule to obtain normalized key information includes:
constructing a normalized corpus, and establishing a pairing rule text for text information in the normalized corpus based on the normalized expression rule;
comparing the key information with text information in the normalized corpus, outputting the text information in the normalized corpus when the key information is matched with the pairing rule text corresponding to the text information in the normalized corpus, and taking the text information as normalized key information.
Optionally, the constructing an inference rule based on the text information of the front and rear positions of the normalized key information in the few sample target text includes:
and acquiring the associated text of the front and rear positions of the normalized key information in the few sample target text, obtaining the relation between the normalized key information and other text information based on the associated text, and taking the relation as an inference rule.
In the above embodiment, when there is an associated word in the front-rear position in the target text of the few samples for the normalized key information, the associated word is extracted as an associated text, for example: adjacent related words exist before and after normalized key information in a certain few sample target text, the related words can be used as related text, and the relation between the normalized key information and other text information is obtained based on the related text.
Examples: the text information in the small sample target text is 'Canadian adjacent American adjacent Mexico', the American is normalized key information, and the related text is adjacent, so that the relationship between Canadian and the United states and the relationship between Mexico and the United states can be obtained.
The above examples are for illustrative purposes only and are not intended to be limiting.
Optionally, the reasoning the normalized key information based on the reasoning rule to obtain an association rule between the normalized key information includes:
reasoning the normalized key information by utilizing the reasoning rule based on the attribute of the normalized key information, wherein the attribute of the normalized key information comprises a space-time attribute and a space attribute;
aiming at the time-space attribute, distinguishing two basic tenses of a time point and a time period, and finding out the equality between the time points through a time sequence target similarity calculation technology, wherein the time association relations of the time periods are prior, overlapped, contained and accepted;
aiming at the spatial attribute, three basic spatial forms of points, lines and areas are distinguished, and the equal space relationship between the spatial points and the intersection between the lines are found out through a spatial line group target similarity calculation technology, wherein the adjacent space relationship between the areas comprises equal space association relations;
and taking the time association relationship and the space association relationship as association rules.
In the above embodiment, the normalized key information has the text with the space attribute and the text with the space attribute, and the associated text between the text with the space attribute cannot be mutually applied, so that the normalized key information needs to be distinguished, the text information containing the associated text screened by the inference rule is screened, and the associated text corresponding to the normalized key information is determined according to the attribute of the normalized key information, thereby determining the association rule.
Optionally, the reasoning the association relation between the normalized key information based on the association rule includes:
and reasoning the association relation of the time text in the normalized key information based on the time association relation, and reasoning the association relation of the space text in the normalized key information based on the space association relation.
Optionally, filtering the association relation based on processing requirements to obtain constraint information between the normalized key information includes:
a space-time ontology representation model oriented to the combat environment and application requirements is established, space-time information is used as a limiting condition of the ontology, the existing space-time reasoning and space reasoning technology is comprehensively applied, and various relations of the information in space-time dimension are calculated and integrated, so that constraint information of target movement in time and space dimension is obtained.
In the above embodiment, the association relationship can be screened according to the actual use requirement or the application environment, so as to obtain the association requirement between the normalized key information more accurately, for example: some usage requirement is that the inclusion relationship between spaces needs to be associated and mined, such as: long sand is contained in Hunan and Hunan is contained in China, so that unnecessary association relations can be removed through screening of association relations, and association relations between adjacent and other relations which are not considered with demands are removed, so that association and excavation between normalized key information are more accurate.
Optionally, the associating the normalized key information based on the constraint information includes:
and after constraint information is acquired, carrying out association processing on the tracks intersecting, the areas adjacent and the inclusion on the normalized key information in the time equality, the time period prior to, coincident with, including and bearing the normalized key information and the space point.
The embodiment of the application also provides a text information processing system, which comprises a processor and a memory;
a memory for storing a computer program;
and the processor is used for realizing any one of the method steps in the text information processing method when executing the program stored in the memory.
The text information processing system can realize each embodiment of the text information processing method and achieve the same beneficial effects, and the detailed description is omitted here.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention by one of ordinary skill in the art without undue burden. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (10)
1. A text information processing method, characterized by comprising:
constructing a key information extraction model, and extracting key information in a few-sample target text based on the key information extraction model;
constructing a normalized expression rule, and performing normalized conversion on the key information based on the normalized expression rule to obtain normalized key information;
establishing an inference rule based on text information of front and rear positions of the normalized key information in a few sample target text, and inferring the normalized key information based on the inference rule to obtain an association rule between the normalized key information;
reasoning association relations among the normalized key information based on the association rules, and screening the association relations based on processing requirements to obtain constraint information among the normalized key information;
and associating the normalized key information based on the constraint information.
2. The text information processing method according to claim 1, wherein the constructing a key information extraction model includes:
and constructing a text extraction model, training the text extraction model by taking text information to be extracted as a training set, and taking the trained text extraction model as a key information extraction model.
3. The text information processing method according to claim 1, wherein the constructing a normalized expression rule includes:
and determining a normalized expression text based on the key information, and constructing a normalized expression rule based on the normalized expression text.
4. The text information processing method according to claim 1, wherein the normalizing the key information based on the normalized expression rule to obtain normalized key information includes:
constructing a normalized corpus, and establishing a pairing rule text for text information in the normalized corpus based on the normalized expression rule;
comparing the key information with text information in the normalized corpus, outputting the text information in the normalized corpus when the key information is matched with the pairing rule text corresponding to the text information in the normalized corpus, and taking the text information as normalized key information.
5. The text information processing method according to claim 1, wherein the constructing an inference rule based on text information of front and rear positions of the normalized key information in a few-sample target text includes:
and acquiring the associated text of the front and rear positions of the normalized key information in the few sample target text, obtaining the relation between the normalized key information and other text information based on the associated text, and taking the relation as an inference rule.
6. The text information processing method according to claim 1, wherein the reasoning the normalized key information based on the reasoning rule to obtain an association rule between the normalized key information includes:
reasoning the normalized key information by utilizing the reasoning rule based on the attribute of the normalized key information, wherein the attribute of the normalized key information comprises a space-time attribute and a space attribute;
aiming at the time-space attribute, distinguishing two basic tenses of a time point and a time period, and finding out the equality between the time points through a time sequence target similarity calculation technology, wherein the time association relations of the time periods are prior, overlapped, contained and accepted;
aiming at the spatial attribute, three basic spatial forms of points, lines and areas are distinguished, and the spatial incidence relation between the points and the intersection between the lines and the adjacent and contained space between the areas is found through a spatial line group target similarity calculation technology;
and taking the time association relationship and the space association relationship as association rules.
7. The text information processing method according to claim 1, wherein said reasoning about association between the normalized key information based on the association rule includes:
and reasoning the association relation of the time text in the normalized key information based on the time association relation, and reasoning the association relation of the space text in the normalized key information based on the space association relation.
8. The text information processing method according to claim 1, wherein the filtering the association relation based on the processing requirement to obtain constraint information between the normalized key information includes:
a space-time ontology representation model oriented to the combat environment and application requirements is established, space-time information is used as a limiting condition of the ontology, the existing space-time reasoning and space reasoning technology is comprehensively applied, and various relations of the information in space-time dimension are calculated and integrated, so that constraint information of target movement in time and space dimension is obtained.
9. The text information processing method according to claim 1, wherein the associating the normalized key information based on the constraint information includes:
and after constraint information is acquired, carrying out association processing on the tracks intersecting, the areas adjacent and the inclusion on the normalized key information in the time equality, the time period prior to, coincident with, including and bearing the normalized key information and the space point.
10. A text information processing system, comprising a processor and a memory;
a memory for storing a computer program;
a processor for implementing the method steps of any one of claims 1-9 when executing a program stored on a memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310827523.2A CN116562260B (en) | 2023-07-07 | 2023-07-07 | Text information processing method and processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310827523.2A CN116562260B (en) | 2023-07-07 | 2023-07-07 | Text information processing method and processing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116562260A true CN116562260A (en) | 2023-08-08 |
| CN116562260B CN116562260B (en) | 2023-10-03 |
Family
ID=87488307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310827523.2A Active CN116562260B (en) | 2023-07-07 | 2023-07-07 | Text information processing method and processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116562260B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992294A (en) * | 2023-09-26 | 2023-11-03 | 成都国恒空间技术工程股份有限公司 | Satellite measurement and control training evaluation method, device, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492065A (en) * | 2018-10-26 | 2019-03-19 | 桂林电子科技大学 | A kind of abstracting method of indoor semantic map time-space relationship |
| CN112733828A (en) * | 2020-12-30 | 2021-04-30 | 航天信息股份有限公司 | Method and system for character recognition |
| CN112764762A (en) * | 2021-02-09 | 2021-05-07 | 清华大学 | Method and system for automatically converting standard text into computable logic rule |
| US20210248420A1 (en) * | 2020-02-07 | 2021-08-12 | International Business Machines Corporation | Automated generation of structured training data from unstructured documents |
| CN114282534A (en) * | 2021-12-30 | 2022-04-05 | 南京大峡谷信息科技有限公司 | Meteorological disaster event aggregation method based on element information extraction |
| CN114912435A (en) * | 2022-05-17 | 2022-08-16 | 国网浙江省电力有限公司电力科学研究院 | Power text knowledge discovery method and device based on frequent itemset algorithm |
| US20220374607A1 (en) * | 2019-10-02 | 2022-11-24 | Nec Corporation | Inferential knowledge construction support apparatus, inferential knowledge construction support method, and computer-readable recording medium |
-
2023
- 2023-07-07 CN CN202310827523.2A patent/CN116562260B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492065A (en) * | 2018-10-26 | 2019-03-19 | 桂林电子科技大学 | A kind of abstracting method of indoor semantic map time-space relationship |
| US20220374607A1 (en) * | 2019-10-02 | 2022-11-24 | Nec Corporation | Inferential knowledge construction support apparatus, inferential knowledge construction support method, and computer-readable recording medium |
| US20210248420A1 (en) * | 2020-02-07 | 2021-08-12 | International Business Machines Corporation | Automated generation of structured training data from unstructured documents |
| CN112733828A (en) * | 2020-12-30 | 2021-04-30 | 航天信息股份有限公司 | Method and system for character recognition |
| CN112764762A (en) * | 2021-02-09 | 2021-05-07 | 清华大学 | Method and system for automatically converting standard text into computable logic rule |
| CN114282534A (en) * | 2021-12-30 | 2022-04-05 | 南京大峡谷信息科技有限公司 | Meteorological disaster event aggregation method based on element information extraction |
| CN114912435A (en) * | 2022-05-17 | 2022-08-16 | 国网浙江省电力有限公司电力科学研究院 | Power text knowledge discovery method and device based on frequent itemset algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 刘然 等: "多源异构战场信息关联挖掘技术研究", 国防科技, vol. 38, no. 4, pages 37 - 38 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992294A (en) * | 2023-09-26 | 2023-11-03 | 成都国恒空间技术工程股份有限公司 | Satellite measurement and control training evaluation method, device, equipment and storage medium |
| CN116992294B (en) * | 2023-09-26 | 2023-12-19 | 成都国恒空间技术工程股份有限公司 | Satellite measurement and control training evaluation method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116562260B (en) | 2023-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xia et al. | Emotion-cause pair extraction: A new task to emotion analysis in texts | |
| Yang et al. | Cross-modal relationship inference for grounding referring expressions | |
| CN107992597B (en) | Text structuring method for power grid fault case | |
| US10347019B2 (en) | Intelligent data munging | |
| CN109933656B (en) | Public opinion polarity prediction method, public opinion polarity prediction device, computer equipment and storage medium | |
| CN116562260B (en) | Text information processing method and processing system | |
| Li et al. | Forecasting business failure using two‐stage ensemble of multivariate discriminant analysis and logistic regression | |
| CN113722490B (en) | Visual rich document information extraction method based on key value matching relation | |
| CN111742322A (en) | System and method for domain and language independent definition extraction using deep neural networks | |
| CN109033427A (en) | The screening technique and device of stock, computer equipment and readable storage medium storing program for executing | |
| CN106156340A (en) | A kind of name entity link method | |
| CN113947087B (en) | Label-based relation construction method and device, electronic equipment and storage medium | |
| CN106663421B (en) | Sound recognition system and sound identification method | |
| CN113244627A (en) | Method and device for identifying plug-in, electronic equipment and storage medium | |
| CN113705164A (en) | Text processing method and device, computer equipment and readable storage medium | |
| CN109492289B (en) | Part machinability rule modeling method | |
| CN110889284A (en) | Multi-task learning Chinese language disease diagnosis method based on bidirectional long-time and short-time memory network | |
| Hassanat et al. | Rule-and dictionary-based solution for variations in written Arabic names in social networks, big data, accounting systems and large databases | |
| Meselhi et al. | Hybrid named entity recognition-application to Arabic language | |
| CN110097258A (en) | A kind of customer relationship network creating method, device and computer readable storage medium | |
| CN115310606A (en) | Deep learning model depolarization method and device based on data set sensitive attribute reconstruction | |
| CN109446318A (en) | A kind of method and relevant device of determining auto repair document subject matter | |
| CN113158672A (en) | Relation analysis method and device based on news events | |
| CN104424332A (en) | Unambiguous Japanese name list building method and name identification method and device | |
| CN109145293B (en) | Case-oriented keyword extraction method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |