CN113064971A - Interactive graph structure-based policy text relation mining and expressing method - Google Patents
Interactive graph structure-based policy text relation mining and expressing method Download PDFInfo
- Publication number
- CN113064971A CN113064971A CN202110387708.7A CN202110387708A CN113064971A CN 113064971 A CN113064971 A CN 113064971A CN 202110387708 A CN202110387708 A CN 202110387708A CN 113064971 A CN113064971 A CN 113064971A
- Authority
- CN
- China
- Prior art keywords
- policy
- text
- graph structure
- target
- entities
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- 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
- G06F16/338—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a method for mining and expressing a policy text relation based on an interactive graph structure, which adopts a natural language processing and deep learning method to perform word segmentation and subject word extraction on policy text data, and draws the correlation among policies based on a display mode of a knowledge graph; the interactive graph structure-based policy text relation mining and expressing method provided by the invention analyzes the potential relevance of the policy text data and shows the internal relation of the policy text data.
Description
Technical Field
The invention belongs to the fields of natural language processing technology and knowledge maps, and particularly relates to a policy text relation mining and expressing method based on interactive graph structures and based on policy subject word mining and subject word association of deep learning.
Background
Currently, various levels of governments and various line departments set up various policies, and internalization correlation may exist among the policy texts, such as: a series of policies issued by different levels of government departments for a specific event and a specific policy object may have a strong correlation therebetween. This dependency hidden between policies is not known by reading and understanding. Therefore, there is a need to expose the inherent relationships of policy text using an interactive expression based on policy text relationship mining.
In order to extract the key information in the policy text and embody the correlation between the policy texts, a policy key information extraction method based on natural language processing needs to be provided, and the correlation between the policies is drawn based on a display mode of a knowledge graph.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide a method for mining and expressing a policy-text relationship based on an interactive graph structure.
The invention discloses a method for mining and expressing a policy text relation based on an interactive graph structure, which comprises the following steps of:
s1, acquiring text data issued by the government by using a web crawler technology, and extracting a policy text from the text data;
s2, carrying out fuzzy search of each policy topic on the policy text extracted in the step S1, and marking the searched target political text with the corresponding policy topic;
s3, processing and extracting target subject words and/or target subject phrases in target policy texts corresponding to the policy topics by utilizing natural language, labeling the corresponding target policy texts on the target subject words and/or the target subject phrases, and taking the target subject words and/or the target subject phrases as nodes to represent entities in the interactive graph structure;
s4, if two or more entities appear in the same target policy text, representing that the two or more entities are related, and representing the relationship between the entities by entity relationship;
s5, displaying the relevance of the target policy text through an interactive graph structure, wherein the interactive graph structure comprises three modules which are linked with each other: the interactive graph structure is used for jointly displaying the target policy text, the entities and the entity relations.
In the specific embodiment provided by the present invention, the text issued by the government in the step S1 includes text data issued by the state, province, city and prefecture governments in the government information disclosure column.
In the embodiment provided by the present invention, a policy text list under each policy topic may be output through the step S2.
In an embodiment of the present invention, the node in step S3 is a target subject word and/or target subject phrase extracted from each target policy text and having strong association with the corresponding policy topic and high frequency.
In the specific embodiment provided by the present invention, after the target subject words and/or target subject phrases in the target policy text corresponding to each policy topic are processed and extracted by using natural language in step S3, a threshold is set for deleting and filtering out longer target subject words and/or target subject phrases.
In the embodiment provided by the present invention, the interactive graph structure in step S5 may jointly show the entities and the relationships between the entities related to the target policy text, the dynamic graph of the entity relationship may show all the entities and the entity relationships under all the target policy texts under each policy topic, and the relationships between the entities may jointly show the target policy list related to the entities.
In the embodiment provided by the present invention, the policy text interactive map structure in step S5 dynamically shows the map structure elements of the entities and entity relationships under each policy topic in the middle of the interactive map structure.
In the embodiment of the present invention, one side of the interactive policy text diagram structure in step S5 shows each policy topic, and the policy topics are shown in a time-flow manner in an inverted manner, and when one side of the interactive policy text diagram structure is selected, entities unrelated to the policy topics in the interactive policy text diagram structure will be virtualized.
In the specific embodiment provided by the present invention, after the user clicks and pays attention to a certain entity, another entity matched with the entity appears on the other side of the interactive graph structure of the policy text in the step S5, and clicks a corresponding entity relationship, a target policy text in which the keyword pair appears is displayed for the user, so that the user can quickly find the corresponding target policy text according to the keyword pair desired to be searched.
By the scheme, the invention at least has the following advantages:
the invention provides a policy key information extraction method based on natural language processing, and the relevance among policies is drawn based on a display mode of a knowledge graph.
Firstly, policy information is required to be classified according to topics, secondly, extraction and labeling of policy special words and subject phrases are required to be carried out on the policy information under each policy special topic, and meanwhile, a threshold value is set to delete and filter out longer subject words and subject phrases, so that the relation between the subject words and subject phrases output after natural language processing and policies can be displayed in a knowledge graph mode.
The interactive graph structure displays the elements such as entities, relations and the like which are related to the graph structure at the middle position; one side of the interactive graph structure shows that under different policy topics, policy data are shown in a time flow mode; selecting a policy text at one side, wherein an entity irrelevant to the policy in a graph structure is virtualized, so that a user can conveniently observe the main content of the policy; the other side of the interactive graph structure shows the relevance of the entities, after a user clicks and pays attention to a certain entity, other entities matched with the entity can appear on the other side of the interactive graph structure, corresponding entity relations are clicked, the policy of the keyword pair appearance can be shown for the user, the user can quickly find the corresponding policy according to the keyword pair to be found, and accurate display is achieved.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical solutions of the present invention more clearly understood and to implement them in accordance with the contents of the description, the following detailed description is given with reference to the preferred embodiments of the present invention and the accompanying drawings.
Drawings
FIG. 1 is an interactive graph structure in which graph-related elements such as entities and relationships are shown in middle positions in the interactive graph structure-based policy text relationship mining and expression method of the present invention;
fig. 2 is an interactive graph structure in which entities on a graph that are not related to a policy are blurred when a policy topic or a target policy text is selected in the interactive graph structure-based policy text relation mining and expression method of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Natural Language Processing (NLP) is a technology that enables computers to understand human Language, and word segmentation is a fundamental task of NLP. The NLP algorithm generally performs semantic analysis on deep grammar with words as basic units. When building NLP models, modelers are typically required to master some linguistic knowledge to facilitate extraction of appropriate features. The excellent generalization ability of deep learning can extract features based on data without supervision, and learn context information features from training data, thereby providing high-quality training data, reducing linguistic requirements on modeling personnel, and enabling an experimenter to only need to design a structure of a neural network.
The interactive graph structure uses nodes to represent the entities in the graph structure, and uses edges to represent various relationships among the entities. The complex knowledge domain obtained by data mining is visually demonstrated using a visualized map.
The policy text relation is mined by adopting a natural language processing and deep learning method, word segmentation and subject word extraction are carried out on policy text data, and the relevance among policies is drawn based on a display mode of a knowledge graph. The method analyzes the potential relevance of the policy text data through algorithm improvement, and shows the internal relation of the policy text data.
The invention provides a method for mining and expressing a policy text relation based on an interactive graph structure, which is used for mining and expressing the policy text relation based on the interactive graph structure and comprises the following steps:
s1, acquiring text data issued by the government by using a web crawler technology, and extracting policy texts from the text data, wherein the texts issued by the government comprise the text data issued by the state, province, city and ground level governments in government information public columns;
s2, according to the display requirements of policies, defining policy topics, carrying out fuzzy search on the policy texts extracted in the step S1, marking the searched target political texts with corresponding policy topics, and outputting the policy topics and a policy text list under each policy topic;
s3, processing and extracting target subject words and/or target subject phrases in target policy texts corresponding to various policy topics by utilizing natural language, setting a threshold value of the target subject words and/or target subject phrases, deleting and filtering out longer target subject words and/or target subject phrases, labeling corresponding target policy texts on the target subject words and/or target subject phrases, extracting target subject words and/or target subject phrases with strong relevance and high frequency with policies, and taking the target subject words and/or target subject phrases as nodes to represent entities in the interactive graph structure;
s4, if two or more entities appear in the same target policy text, representing that the two or more entities are related, and representing the relationship between the entities by entity relationship;
s5, displaying the relevance of the target policy text through an interactive graph structure, wherein the interactive graph structure comprises three modules which are linked with each other: the interactive graph structure is used for jointly displaying the target policy text, the entities and the entity relations.
The dynamic diagram of the entity relationship can show all entities and entity relationships under all policy texts under the policy topic; the relationship between the entities can display the policy list related to the entities in a linkage manner, the entity and relationship under the policy theme and other graph structure elements are dynamically displayed in the middle position of the interactive graph structure, one side of the interactive graph structure displays the policies under different policy themes, the policy titles are displayed in a time flow manner in an inverted manner, the policy title on one side is selected, the entity irrelevant to the policy on the graph is virtualized, so that the main content of the policy can be conveniently observed by a user, the relationship of the entities is displayed on the other side of the interactive graph structure, after the user clicks and pays attention to a certain entity, other entities matched with the entity appear on the other side of the interactive graph structure, the corresponding entity relationship is clicked, the policy appearing in the keyword pair can be displayed for the user, and the user can quickly find the corresponding policy according to the keyword pair to be searched, so as to realize accurate display, the function is nested in a policy precision pushing platform, and humanized service is provided for users.
The principle of the interactive graph structure-based policy text relation mining and expressing method provided by the invention is as follows:
1. and (5) classifying the policy text by special subjects: according to the requirement for showing the policy, the policy subject is determined, such as the policy subject of medium and small enterprises and the policy subject of different industries, and the policy title, the policy content and each policy subject in the policy text are subjected to fuzzy search; if the policy title and the policy content of a specific policy text can be matched with the policy subject of the medium and small enterprises through fuzzy search, the policy is classified into the policy text data under the policy subject of the medium and small enterprises, the policy text which can be determined through the fuzzy search is marked with the subject, and the policy subject and the policy text list under each subject are output.
2. Extracting and labeling policy special words and topic phrases: and extracting and labeling the policy special words and the theme phrases by using a keyword and key phrase extraction method processed by natural language, and setting threshold values of the policy special words and the theme phrases to delete and filter out longer theme words and theme phrases.
3. Extracting entities and relations in the interactive graph structure: and performing data association on each subject word and subject phrase output after natural language processing and a policy, further extracting subject words which are strongly associated with the policy and have high frequency, setting the subject words as nodes to represent entities in a graph structure, setting correlation among entities appearing in the same policy text, and representing the correlation among the entities by using the relationship.
In the specific embodiment provided by the invention, in 50 policy text records under the special policy subjects of medium and small enterprises, natural language processing is adopted for each policy text, so that corresponding policy subject words and subject phrases are extracted for each policy text. And after counting the frequency of all the subject words and the subject phrases under the special subjects of the small and medium enterprises, setting the threshold value to be 8, and screening the subject words and the subject phrases with the frequency higher than the threshold value. Determining entities under the thematic map according to the relevance of the thematic words, the thematic phrases and the thematic of the small and medium-sized enterprises, such as: subject words and/or subject phrases such as "small micro" and/or "business" and/or "high and new technology". Meanwhile, counting the frequency of the main bodies in the same policy text, and if the main bodies in the same policy text appear at the same time, judging that a relationship exists between the two main bodies.
4. And displaying the relevance of the data through an interactive graph structure: the graph structure is provided with three modules which are mutually linked, and the policy text is linked with the entity and the relation between the entities; the policy text can jointly display the entities related to the text and the relationship among the entities; the dynamic diagram of the entity relationship can show all entities and entity relationships under all policy texts under the policy topic; the relationship between the entities can display the policy list related to the entities in a linkage mode.
First, elements related to the graph, such as entities and relationships, are shown in the middle of the interactive graph structure, see fig. 1.
In the interactive graph structure, different types of icons are used to represent the bodies of different attributes, and lines are used to represent the relationships between the entities. The icon of the entity is designed according to the word attribute of the entity, such as: entities with different attributes, such as place names, person names, etc., will adopt different icons. If two entities are related by a line, the two entities are represented in the same policy text, and a relationship exists between the two entities.
Then, one side of the interactive graph structure is displayed under different policy topics, and the policy data are displayed in a time flow mode; selecting a policy topic or target policy text, entities on the map that are not related to the policy will be blurred, so that the user can observe the main entities of the policy and the relationship between the entities, as shown in fig. 2.
Finally, the other side of the interactive graph structure shows the relevance of the entities, after a user clicks and pays attention to a certain entity, other entities matched with the entity appear on the other side of the interactive graph structure, the corresponding entity relation is clicked, the policy of the appearance of the entity pair can be shown for the user, the user can quickly find the corresponding policy according to the keyword pair to be searched, and accurate display is achieved.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, it should be noted that, for those skilled in the art, many modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (9)
1. A method for mining and expressing policy text relations based on an interactive graph structure is characterized by comprising the following steps:
s1, acquiring text data issued by the government by using a web crawler technology, and extracting a policy text from the text data;
s2, carrying out fuzzy search of each policy topic on the policy text extracted in the step S1, and marking the searched target political text with the corresponding policy topic;
s3, processing and extracting target subject words and/or target subject phrases in target policy texts corresponding to the policy topics by utilizing natural language, labeling the corresponding target policy texts on the target subject words and/or the target subject phrases, and taking the target subject words and/or the target subject phrases as nodes to represent entities in the interactive graph structure;
s4, if two or more entities appear in the same target policy text, representing that the two or more entities are related, and representing the relationship between the entities by entity relationship;
s5, displaying the relevance of the target policy text through an interactive graph structure, wherein the interactive graph structure comprises three modules which are linked with each other: the interactive graph structure is used for jointly displaying the target policy text, the entities and the entity relations.
2. The interactive graph structure-based mining and expression method of policy-text relations according to claim 1, wherein: the government issued text in said step S1 includes text data issued by the national, provincial, municipal and prefectural governments in the government information disclosure column.
3. The interactive graph structure-based mining and expression method of policy-text relations according to claim 1, wherein: a list of policy texts under respective policy topics may be output through the step S2.
4. The interactive graph structure-based mining and expression method of policy-text relations according to claim 1, wherein: the nodes in step S3 are target subject words and/or target subject phrases extracted from each target policy text, reverse the occurrence frequency of the target subject words and/or target subject phrases, set a threshold, and select real words whose word frequency is higher than the threshold.
5. The interactive graph structure-based mining and expression method of policy-text relations according to claim 1, wherein: in the step S3, after the target subject words and/or target subject phrases in the target policy text corresponding to each policy topic are processed and extracted by using natural language, a threshold is set for deleting and filtering out longer target subject words and/or target subject phrases.
6. The interactive graph structure-based mining and expression method of policy-text relations according to claim 1, wherein: the interactive graph structure in step S5 may jointly show the entities and the relationships between the entities related to the target policy text, the dynamic graph of the entity relationship may show all the entities and the entity relationships under all the target policy texts under each policy topic, and the relationships between the entities may jointly show the target policy list related to the entities.
7. The interactive graph structure-based mining and expression method of policy-text relations according to claim 1, wherein: the policy text interactive graph structure in the step S5 dynamically shows graph structure elements of entities and entity relationships under each policy topic in the middle of the interactive graph structure.
8. The interactive graph structure-based mining and expression method of policy-text relations according to claim 7, wherein: in the step S5, one side of the structure of the interactive map of policy text shows each policy topic, and the policy topics are shown in a time-flow manner in an inverted manner.
9. The interactive graph structure-based mining and expression method of policy-text relations according to claim 8, wherein: in the step S5, the other side of the interactive map structure of the policy text shows the relevance of the entity, and after the user clicks and pays attention to a certain entity, the other entity matching the entity appears on the other side of the interactive map structure, and the corresponding entity relationship is clicked, so that the target policy text where the keyword pair appears is shown for the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110387708.7A CN113064971A (en) | 2021-04-12 | 2021-04-12 | Interactive graph structure-based policy text relation mining and expressing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110387708.7A CN113064971A (en) | 2021-04-12 | 2021-04-12 | Interactive graph structure-based policy text relation mining and expressing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113064971A true CN113064971A (en) | 2021-07-02 |
Family
ID=76566341
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110387708.7A Pending CN113064971A (en) | 2021-04-12 | 2021-04-12 | Interactive graph structure-based policy text relation mining and expressing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113064971A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1508704A (en) * | 2002-12-18 | 2004-06-30 | User interface assembly expression having simplified view | |
| CN109635082A (en) * | 2018-11-26 | 2019-04-16 | 平安科技（深圳）有限公司 | Policy implication analysis method, device, computer equipment and storage medium |
| CN111401068A (en) * | 2020-03-23 | 2020-07-10 | 西南科技大学 | Knowledge graph-based explosive formula aided design visualization method and system |
| CN112035667A (en) * | 2020-09-02 | 2020-12-04 | 河南中原消费金融股份有限公司 | Knowledge graph display method and device and terminal equipment |
| CN112182248A (en) * | 2020-10-19 | 2021-01-05 | 深圳供电局有限公司 | Statistical method for key policy of electricity price |
| CN112380318A (en) * | 2020-11-12 | 2021-02-19 | 中国科学技术大学智慧城市研究院(芜湖) | Enterprise policy matching method based on label similarity |
| CN112559734A (en) * | 2019-09-26 | 2021-03-26 | 中国科学技术信息研究所 | Presentation generation method and device, electronic equipment and computer readable storage medium |
| CN112580331A (en) * | 2020-12-15 | 2021-03-30 | 国家工业信息安全发展研究中心 | Method and system for establishing knowledge graph of policy text |
-
2021
- 2021-04-12 CN CN202110387708.7A patent/CN113064971A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1508704A (en) * | 2002-12-18 | 2004-06-30 | User interface assembly expression having simplified view | |
| CN109635082A (en) * | 2018-11-26 | 2019-04-16 | 平安科技（深圳）有限公司 | Policy implication analysis method, device, computer equipment and storage medium |
| CN112559734A (en) * | 2019-09-26 | 2021-03-26 | 中国科学技术信息研究所 | Presentation generation method and device, electronic equipment and computer readable storage medium |
| CN111401068A (en) * | 2020-03-23 | 2020-07-10 | 西南科技大学 | Knowledge graph-based explosive formula aided design visualization method and system |
| CN112035667A (en) * | 2020-09-02 | 2020-12-04 | 河南中原消费金融股份有限公司 | Knowledge graph display method and device and terminal equipment |
| CN112182248A (en) * | 2020-10-19 | 2021-01-05 | 深圳供电局有限公司 | Statistical method for key policy of electricity price |
| CN112380318A (en) * | 2020-11-12 | 2021-02-19 | 中国科学技术大学智慧城市研究院(芜湖) | Enterprise policy matching method based on label similarity |
| CN112580331A (en) * | 2020-12-15 | 2021-03-30 | 国家工业信息安全发展研究中心 | Method and system for establishing knowledge graph of policy text |
Non-Patent Citations (1)
| Title |
|---|
| 叶江峰等: "中国国家级产业园区30年发展政策的主题与演变", 科学学研究, vol. 33, no. 11, pages 1634 - 1640 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11416535B2 (en) | User interface for visualizing search data | |
| Faber et al. | Representing environmental knowledge in EcoLexicon | |
| CN113065003B (en) | Knowledge graph generation method based on multiple indexes | |
| Wellen et al. | Toward an inclusive semantic interoperability: the case of Cree hydrographic features | |
| CN111813874B (en) | Terahertz knowledge graph construction method and system | |
| Wang et al. | Visual analytics and information extraction of geological content for text-based mineral exploration reports | |
| Jeffrey et al. | The Archaeotools project: faceted classification and natural language processing in an archaeological context | |
| Sherchan et al. | Harnessing Twitter and Instagram for disaster management | |
| Ma et al. | Text visualization for geological hazard documents via text mining and natural language processing | |
| Ahmed et al. | Framing South Asian politics: An analysis of Indian and Pakistani English print media discourses regarding Kartarpur corridor | |
| Semian et al. | Name as a regional brand: The case of Local Action Groups in Czechia | |
| Panagiotidou et al. | Communicating uncertainty in digital humanities visualization research | |
| CN116701648A (en) | Mapping knowledge graph and schema design method based on standard specification | |
| Yan et al. | Two Diverging roads: a semantic network analysis of chinese social connection (“guanxi”) on Twitter | |
| CN113064971A (en) | Interactive graph structure-based policy text relation mining and expressing method | |
| Romele et al. | From philosopher to network. Using digital traces for understanding Paul Ricoeur’s legacy | |
| Ballatore | Semantic challenges for volunteered geographic information | |
| Murasugi | Linguistic cybercartography: Expanding the boundaries of language maps | |
| Peng | digital humanities approach to comparative literature: opportunities and challenges | |
| Wang et al. | iPoster: Interactive poster generation based on topic structure and slide presentation | |
| Lima et al. | Using geocoding and topic extraction to make sense of comments on social network pages of local government agencies | |
| Dashdorj et al. | High‐level event identification in social media | |
| Stock et al. | He Tatai Whenua: Automated Extraction of Landscape Terms and their Meanings in New Zealand Maori. GeoComputation 2019 | |
| Wang et al. | Creating spatiotemporal semantic maps from web text documents | |
| Clarinval et al. | Evoq: a visualization tool to support structural analysis of text documents |
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 |