CN111930824A - Data comprehensive situation display method based on recommendation model - Google Patents
Data comprehensive situation display method based on recommendation model Download PDFInfo
- Publication number
- CN111930824A CN111930824A CN202010005115.5A CN202010005115A CN111930824A CN 111930824 A CN111930824 A CN 111930824A CN 202010005115 A CN202010005115 A CN 202010005115A CN 111930824 A CN111930824 A CN 111930824A
- Authority
- CN
- China
- Prior art keywords
- data
- classification
- foreground
- display
- plug
- 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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- 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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
Abstract
The invention discloses a data comprehensive situation showing method based on a recommendation model, which is used for constructing a data analysis recommendation model for carrying out data classification and fusion according to special subjects or label dimensions on global data in a background database; customizing a statistical analysis foreground visual chart plug-in, and performing association binding display on a foreground visual chart plug-in display frame and thematic data associated through a background data analysis recommendation model; customizing a built-in method which can be used for showing the change of the showing frame structure and the layout of the foreground visual chart plug-in component along with the time stage according to the time stage passage or the visual showing focus change; the background data associated with the integrated analysis recommendation model is bound with the foreground visual plug-in display frame for displaying and the foreground visual plug-in display frame dynamically changes, and processes of dynamically pushing background data to the foreground and visually displaying in a customized mode in the whole time flow and period are achieved.
Description
Technical Field
The invention belongs to a data front-end visualization display technology, and particularly relates to a data comprehensive situation display method which is customized for specific application in a specific field and based on a tag thematic data recommendation model and changes along with time or focus.
Background
The data visualization technology is scientific and technical research on visual expression of data, and is defined as information extracted in a certain summary form, including various attributes and variables of corresponding information units.
Data visualization mainly aims at clearly and effectively conveying and communicating information by means of a graphical means. However, the current data visualization technology often cannot achieve the balance between design and function well, so that a Chinese and unrealistic data visualization form is generated, on one hand, the main purpose of data visualization cannot be achieved, the data integrity cannot be displayed in a covering manner, information can be effectively transmitted and communicated, on the other hand, the customization requirement of a specific user on a specific application cannot be met, which is the contradiction and the defect of the existing visualization technology.
Disclosure of Invention
The invention aims to provide a data comprehensive situation showing method which is specially customized based on a tag thematic data recommendation model and is specific to specific application in a specific field along with time or focus change.
The technical solution for realizing the invention is as follows: a data comprehensive situation showing method based on a recommendation model comprises the following steps
Step 1: constructing a data analysis recommendation model for carrying out data classification and fusion according to special subjects or label dimensions on global data in a background database;
step 2: customizing a statistical analysis foreground visual chart plug-in, and performing association binding display on a foreground visual chart plug-in display frame and thematic data associated through a background data analysis recommendation model;
and step 3: customizing a built-in method which can be used for showing the change of the showing frame structure and the layout of the foreground visual chart plug-in component along with the time stage according to the time stage passage or the visual showing focus change;
and 4, step 4: the background data associated with the integrated analysis recommendation model is bound with the foreground visual plug-in display frame for displaying and the foreground visual plug-in display frame dynamically changes, and processes of dynamically pushing background data to the foreground and visually displaying in a customized mode in the whole time flow and period are achieved.
In the step 1, an analysis recommendation model for classifying and fusing data according to special subjects or label dimensions is constructed, and the specific method comprises the following steps:
(1.1) traversing all data table names of all data tables and data existing in a background database, and clustering tables with similar associations such as parent-child structure table names, similar or identical classification relations and the like by algorithms such as longest substring matching, character string similarity calculation, text classification and the like;
(1.2) selecting the classification result with the maximum specific gravity as a correct classification clustering conclusion for the classification completed according to the table name; after all correct classifications are finished, the operation of customizing definite labels or special subjects for the classifications is repeated until each complete correct classification has a definite label or a special subject without overlapping intersection;
(1.3) rearranging the data tables in the classified set in the label thematic data set which completes the correct classification, so that one or more data tables are arranged according to the relationship of a definite and ordered parallel or parent-child structure;
(1.4) for any externally input keyword, performing character matching, similarity calculation or other equivalent classification algorithm calculation on the keyword and all the label subject sets of the classification sets, and outputting data by taking the classified data set with the highest calculation value and higher than a certain threshold (here, the value is defined as 0.7, namely, the value is considered to be equivalent matching if the value is higher than 0.7).
Step (1.2) for the classification completed according to the table name, adopting a rule formed by recognized domain professional knowledge to further check and verify, and for the table completed in the automatic algorithm, if the classification accords with the verification rule judgment, considering that the classification has a correct classification result; if the table or tables under the classification are only partially judged to be in accordance with the check rule, reclassifying the tables and clustering the tables under the directly related classification (the classification can select the existing classification or select the new addition); if the classification completely does not accord with the judgment of the check rule, removing the classification, and reclassifying all tables under the original classification into directly related classifications (the classification can select the existing classification or select the new one);
and comprehensively checking the classification result, and selecting the classification result with the maximum specific gravity as a correct classification clustering conclusion.
The method for performing associated binding display on the foreground visual chart plug-in display frame and the background thematic data in the step 2 comprises the following steps:
(2.1) for a data set under the special label topic, dividing data of a data table in the data set in a statistical display form: presenting in an enumeration manner for all entities in a data table; for an entity in a data table, carrying out classified summary statistics on entity data according to the difference of key field values (only having a plurality of fixed state values) in the data table; comparing the entities of the plurality of data tables according to the total value statistics of the data tables; for an entity in a data table, under the condition that a new entity is additionally created or an existing entity is changed on a key field value of the data table (only has a plurality of fixed state values) along with the time, the value of each changed key node is subjected to statistical comparison; other possible scenarios, and so on;
(2.2) dividing according to the display forms listed in the step (2.1), respectively customizing corresponding foreground visual chart plug-ins, listing single-table entities and displaying in a table form; the single-table classification and summary statistics are carried out, the comparison proportion is shown in a pie graph mode, and the display numerical value statistics is shown in a column graph mode; counting the total values of a plurality of tables, displaying the comparison proportion in a pie graph mode, and displaying the numerical value statistics in a bar graph mode; statistics of changes of key field values of the single-form entities are displayed by a bar chart or a line chart; and in other possible situations, analogizing and making a corresponding chart visualization display form;
(2.3) matching a data set of a label special topic with a pre-established foreground chart plug-in visual frame, simultaneously paying attention to whether each data table has the same upper-level common composition structure, and in actual chart customization, displaying the capabilities of dimensional value adjustment, multilayer change of chart plug-ins, customized data drilling and downloading and the like;
and (2.4) in order to meet special requirements, a method for individually customizing the visual chart plug-in presentation framework for specific data is reserved, and the method is used for replacing the fixedly-formulated data to adapt the content of the visual presentation.
The method for the foreground visual chart plug-in display frame to change the structural layout content and the like along with the time stage in the step 3 comprises the following steps:
(3.1) specific to different actual applications, the full set content of the time stage or focus possessed by a specific application is determined, under the specific application condition, different foreground display requirements may exist for different time stages or focus changes, and correspondingly, the statistical mode content which the foreground needs to display under different time stages or under different focus conditions needs to be determined;
(3.2) aiming at the specific application under the conditions of different time stages or focuses, carrying out adjustment customization on each different time stage or focus on the visual chart plug-in display frame displayed by the foreground so as to meet the unique requirements of the application;
and (3.3) displaying the visualization frames on different foreground under different time stages or focus conditions, and dynamically changing the display frames of the foreground visualization chart plug-in by taking the time stages or the focus as a change dimension.
The method for integrating background data, binding the foreground visual plugin display frame for displaying and updating the dynamic change of the focus of the foreground visual plugin display frame along with the time stage in the step 4 comprises the following steps:
(4.1) aiming at a specific application, under the condition that the time stage or the focus complete set of the application is clear, establishing foreground visual customization of the layout content of the visual plug-in showing framework change structure along with the time stage or the focus change related to the application;
(4.2) aiming at specific application, matching and selecting a tag thematic data set according to related keywords input by the application content requirement;
(4.3) performing associated binding adaptation display on the matched and selected label thematic data and a foreground visual chart plug-in display frame aiming at the specific application, and performing associated adaptation display adjustment on the foreground visual chart plug-in display frame of the application at each time stage or under different focus conditions;
and (4.4) integrating the steps to complete the realization of the data comprehensive situation showing method based on the data analysis recommendation model for the specific application.
Compared with the prior art, the invention has the following remarkable advantages:
the present invention is described in further detail below with reference to the attached drawing figures.
Has the advantages that: compared with the prior art, the rail transit data analysis method based on the big data has the following advantages that:
1. the method can be used for constructing a data analysis recommendation model based on the special topic of the label aiming at different requirements of different users on specific application in a specific field, and realizing dynamic visual display of data comprehensive situation under the complex application requirement.
2. A label thematic analysis recommendation model of the data is constructed, so that the visually displayed data set organization has more definite classification and focus, and information can be more clearly and effectively transmitted and communicated;
3. the complexity of the application can be determined according to the specific application in the specific field, the change situation of the application in the dimensions of time stage, focus and the like can be analyzed, and different frame structure contents visually displayed in the change dimension can be formulated;
4. integrating the analysis recommendation of the tag thematic data and the complex flow of the specific application in the specific field, and customizing the dynamic visual display of the data comprehensive situation of the complex specific application;
5. the method for individually customizing the visual chart plug-in presentation framework for specific data presentation requirements is reserved, and can be used for replacing the fixedly-formulated data to adapt to the content of the visual presentation.
Drawings
FIG. 1 is a flow chart of a data comprehensive situation presentation method based on a recommendation model according to the present invention;
FIG. 2 is a flow diagram of foreground page interaction with a background database.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
The following is an embodiment of an actual case of the present invention, and the objects and features of the present invention can also be seen from the description of the case. It is to be understood that the examples described herein are for purposes of illustration and explanation only and are not limiting of the present invention.
A data comprehensive situation showing method based on a recommendation model comprises the following steps
Step 1: constructing a data analysis recommendation model for carrying out data classification and fusion according to special subjects or label dimensions on global data in a background database;
(1.1) traversing all data table names of all data tables and data existing in a background database, and clustering tables with similar associations such as parent-child structure table names, similar or identical classification relations and the like by algorithms such as longest substring matching, character string similarity calculation, text classification and the like;
(1.2) selecting the classification result with the maximum specific gravity as a correct classification clustering conclusion for the classification completed according to the table name; after all correct classifications are finished, the operation of customizing definite labels or special subjects for the classifications is repeated until each complete correct classification has a definite label or a special subject without overlapping intersection;
for classification completed according to the table name, adopting rules formed by accepted domain professional knowledge to further check and verify, and for the table completed into the classification cluster under the automatic algorithm, if the classification accords with the verification rule judgment, considering that the classification has a correct classification result; if the table or tables under the classification are only partially judged to be in accordance with the check rule, reclassifying the tables and clustering the tables under the directly related classification (the classification can select the existing classification or select the new addition); if the classification completely does not accord with the judgment of the check rule, removing the classification, and reclassifying all tables under the original classification into directly related classifications (the classification can select the existing classification or select the new one);
and comprehensively checking the classification result, and selecting the classification result with the maximum specific gravity as a correct classification clustering conclusion.
(1.3) rearranging the data tables in the classified set in the label thematic data set which completes the correct classification, so that one or more data tables are arranged according to the relationship of a definite and ordered parallel or parent-child structure;
(1.4) for any externally input keyword, performing character matching, similarity calculation or other equivalent classification algorithm calculation on the keyword and all the label subject sets of the classification sets, and outputting data by taking the classified data set with the highest calculation value and higher than a certain threshold (here, the value is defined as 0.7, namely, the value is considered to be equivalent matching if the value is higher than 0.7).
Step 2: customizing a statistical analysis foreground visual chart plug-in, and performing association binding display on a foreground visual chart plug-in display frame and thematic data associated through a background data analysis recommendation model;
2.1) for a data set under the special label topic, dividing data of a data table in the data set in a statistical display form: presenting in an enumeration manner for all entities in a data table; for an entity in a data table, carrying out classified summary statistics on entity data according to the difference of key field values (only having a plurality of fixed state values) in the data table; comparing the entities of the plurality of data tables according to the total value statistics of the data tables; for an entity in a data table, under the condition that a new entity is additionally created or an existing entity is changed on a key field value of the data table (only has a plurality of fixed state values) along with the time, the value of each changed key node is subjected to statistical comparison; other possible scenarios, and so on;
(2.2) dividing according to the display forms listed in the step (2.1), respectively customizing corresponding foreground visual chart plug-ins, listing single-table entities and displaying in a table form; the single-table classification and summary statistics are carried out, the comparison proportion is shown in a pie graph mode, and the display numerical value statistics is shown in a column graph mode; counting the total values of a plurality of tables, displaying the comparison proportion in a pie graph mode, and displaying the numerical value statistics in a bar graph mode; statistics of changes of key field values of the single-form entities are displayed by a bar chart or a line chart; and in other possible situations, analogizing and making a corresponding chart visualization display form;
(2.3) matching a data set of a label special topic with a pre-established foreground chart plug-in visual frame, simultaneously paying attention to whether each data table has the same upper-level common composition structure, and in actual chart customization, displaying the capabilities of dimensional value adjustment, multilayer change of chart plug-ins, customized data drilling and downloading and the like;
and (2.4) in order to meet special requirements, a method for individually customizing the visual chart plug-in presentation framework for specific data is reserved, and the method is used for replacing the fixedly-formulated data to adapt the content of the visual presentation.
And step 3: customizing a built-in method which can be used for showing the change of the showing frame structure and the layout of the foreground visual chart plug-in component along with the time stage according to the time stage passage or the visual showing focus change;
(3.1) specific to different actual applications, the full set content of the time stage or focus possessed by a specific application is determined, under the specific application condition, different foreground display requirements may exist for different time stages or focus changes, and correspondingly, the statistical mode content which the foreground needs to display under different time stages or under different focus conditions needs to be determined;
(3.2) aiming at the specific application under the conditions of different time stages or focuses, carrying out adjustment customization on each different time stage or focus on the visual chart plug-in display frame displayed by the foreground so as to meet the unique requirements of the application;
and (3.3) displaying the visualization frames on different foreground under different time stages or focus conditions, and dynamically changing the display frames of the foreground visualization chart plug-in by taking the time stages or the focus as a change dimension.
And 4, step 4: background data associated with the integrated analysis recommendation model is bound with a foreground visual plug-in display frame for displaying and a foreground visual plug-in display frame dynamic change method, so that the processes of background data dynamic pushing and visual customized display to the foreground in the whole time flow and period are realized;
(4.1) aiming at a specific application, under the condition that the time stage or the focus complete set of the application is clear, establishing foreground visual customization of the layout content of the visual plug-in showing framework change structure along with the time stage or the focus change related to the application;
(4.2) aiming at specific application, matching and selecting a tag thematic data set according to related keywords input by the application content requirement;
(4.3) performing associated binding adaptation display on the matched and selected label thematic data and a foreground visual chart plug-in display frame aiming at the specific application, and performing associated adaptation display adjustment on the foreground visual chart plug-in display frame of the application at each time stage or under different focus conditions;
and (4.4) integrating the steps to complete the realization of the data comprehensive situation showing method based on the data analysis recommendation model for the specific application.
The embodiments of the present invention have been described in detail with reference to the drawings and examples, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (6)
1. A data comprehensive situation display method based on a recommendation model is characterized by comprising the following steps: comprises the following steps
Step 1: constructing a data analysis recommendation model for carrying out data classification and fusion according to special subjects or label dimensions on global data in a background database;
step 2: customizing a statistical analysis foreground visual chart plug-in, and performing association binding display on a foreground visual chart plug-in display frame and thematic data associated through a background data analysis recommendation model;
and step 3: customizing a built-in method which can be used for showing the change of the showing frame structure and the layout of the foreground visual chart plug-in component along with the time stage according to the time stage passage or the visual showing focus change;
and 4, step 4: the background data associated with the integrated analysis recommendation model is bound with the foreground visual plug-in display frame for displaying and the foreground visual plug-in display frame dynamically changes, and processes of dynamically pushing background data to the foreground and visually displaying in a customized mode in the whole time flow and period are achieved.
2. The recommendation model-based data synthesis situation presentation method according to claim 1, wherein: in the step 1, an analysis recommendation model for classifying and fusing data according to special subjects or label dimensions is constructed, and the specific method comprises the following steps:
(1.1) traversing all data table names of all data tables and data existing in a background database, and clustering tables with similar associations such as parent-child structure table names, similar or identical classification relations and the like by algorithms such as longest substring matching, character string similarity calculation, text classification and the like;
(1.2) selecting the classification result with the maximum specific gravity as a correct classification clustering conclusion for the classification completed according to the table name; after all correct classifications are finished, the operation of customizing definite labels or special subjects for the classifications is repeated until each complete correct classification has a definite label or a special subject without overlapping intersection;
(1.3) rearranging the data tables in the classified set in the label thematic data set which completes the correct classification, so that one or more data tables are arranged according to the relationship of a definite and ordered parallel or parent-child structure;
(1.4) for any externally input keyword, performing character matching, similarity calculation or other equivalent classification algorithm calculation on the keyword and all the label subject sets of the classification sets, and outputting data by taking the classified data set with the highest calculation value and higher than a certain threshold (here, the value is defined as 0.7, namely, the value is considered to be equivalent matching if the value is higher than 0.7).
3. The data comprehensive situation presentation method based on the recommendation model according to claim 2, characterized in that: step (1.2) for the classification completed according to the table name, adopting a rule formed by recognized domain professional knowledge to further check and verify, and for the table completed in the automatic algorithm, if the classification accords with the verification rule judgment, considering that the classification has a correct classification result; if the table or tables under the classification are only partially judged to be in accordance with the check rule, reclassifying the tables and clustering the tables under the directly related classification (the classification can select the existing classification or select the new addition); if the classification completely does not accord with the judgment of the check rule, removing the classification, and reclassifying all tables under the original classification into directly related classifications (the classification can select the existing classification or select the new one);
and comprehensively checking the classification result, and selecting the classification result with the maximum specific gravity as a correct classification clustering conclusion.
4. The recommendation model-based data synthesis situation presentation method according to claim 1, wherein: the method for performing associated binding display on the foreground visual chart plug-in display frame and the background thematic data in the step 2 comprises the following steps:
(2.1) for a data set under the special label topic, dividing data of a data table in the data set in a statistical display form: presenting in an enumeration manner for all entities in a data table; for an entity in a data table, carrying out classified summary statistics on entity data according to the difference of key field values (only having a plurality of fixed state values) in the data table; comparing the entities of the plurality of data tables according to the total value statistics of the data tables; for an entity in a data table, under the condition that a new entity is additionally created or an existing entity is changed on a key field value of the data table (only has a plurality of fixed state values) along with the time, the value of each changed key node is subjected to statistical comparison; other possible scenarios, and so on;
(2.2) dividing according to the display forms listed in the step (2.1), respectively customizing corresponding foreground visual chart plug-ins, listing single-table entities and displaying in a table form; the single-table classification and summary statistics are carried out, the comparison proportion is shown in a pie graph mode, and the display numerical value statistics is shown in a column graph mode; counting the total values of a plurality of tables, displaying the comparison proportion in a pie graph mode, and displaying the numerical value statistics in a bar graph mode; statistics of changes of key field values of the single-form entities are displayed by a bar chart or a line chart; and in other possible situations, analogizing and making a corresponding chart visualization display form;
(2.3) matching a data set of a label special topic with a pre-established foreground chart plug-in visual frame, simultaneously paying attention to whether each data table has the same upper-level common composition structure, and in actual chart customization, displaying the capabilities of dimensional value adjustment, multilayer change of chart plug-ins, customized data drilling and downloading and the like;
and (2.4) in order to meet special requirements, a method for individually customizing the visual chart plug-in presentation framework for specific data is reserved, and the method is used for replacing the fixedly-formulated data to adapt the content of the visual presentation.
5. The recommendation model-based data synthesis situation presentation method according to claim 1, wherein: the method for the foreground visual chart plug-in display frame to change the structural layout content and the like along with the time stage in the step 3 comprises the following steps:
(3.1) specific to different actual applications, the full set content of the time stage or focus possessed by a specific application is determined, under the specific application condition, different foreground display requirements may exist for different time stages or focus changes, and correspondingly, the statistical mode content which the foreground needs to display under different time stages or under different focus conditions needs to be determined;
(3.2) aiming at the specific application under the conditions of different time stages or focuses, carrying out adjustment customization on each different time stage or focus on the visual chart plug-in display frame displayed by the foreground so as to meet the unique requirements of the application;
and (3.3) displaying the visualization frames on different foreground under different time stages or focus conditions, and dynamically changing the display frames of the foreground visualization chart plug-in by taking the time stages or the focus as a change dimension.
6. The recommendation model-based data synthesis situation presentation method according to claim 1, wherein: the method for integrating background data, binding the foreground visual plugin display frame for displaying and updating the dynamic change of the focus of the foreground visual plugin display frame along with the time stage in the step 4 comprises the following steps:
(4.1) aiming at a specific application, under the condition that the time stage or the focus complete set of the application is clear, establishing foreground visual customization of the layout content of the visual plug-in showing framework change structure along with the time stage or the focus change related to the application;
(4.2) aiming at specific application, matching and selecting a tag thematic data set according to related keywords input by the application content requirement;
(4.3) performing associated binding adaptation display on the matched and selected label thematic data and a foreground visual chart plug-in display frame aiming at the specific application, and performing associated adaptation display adjustment on the foreground visual chart plug-in display frame of the application at each time stage or under different focus conditions;
and (4.4) integrating the steps to complete the realization of the data comprehensive situation showing method based on the data analysis recommendation model for the specific application.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010005115.5A CN111930824A (en) | 2020-01-03 | 2020-01-03 | Data comprehensive situation display method based on recommendation model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010005115.5A CN111930824A (en) | 2020-01-03 | 2020-01-03 | Data comprehensive situation display method based on recommendation model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111930824A true CN111930824A (en) | 2020-11-13 |
Family
ID=73316130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010005115.5A Pending CN111930824A (en) | 2020-01-03 | 2020-01-03 | Data comprehensive situation display method based on recommendation model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111930824A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116451103A (en) * | 2023-06-13 | 2023-07-18 | 中国电子科技集团公司第二十八研究所 | Situation element recommendation method based on label |
-
2020
- 2020-01-03 CN CN202010005115.5A patent/CN111930824A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116451103A (en) * | 2023-06-13 | 2023-07-18 | 中国电子科技集团公司第二十八研究所 | Situation element recommendation method based on label |
| CN116451103B (en) * | 2023-06-13 | 2023-09-22 | 中国电子科技集团公司第二十八研究所 | Situation element recommendation method based on label |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8583419B2 (en) | Latent metonymical analysis and indexing (LMAI) | |
| US7930322B2 (en) | Text based schema discovery and information extraction | |
| US20190243850A1 (en) | Perspective data analysis and management | |
| JP5212604B2 (en) | Risk detection system, risk detection method and program thereof | |
| CN111475612A (en) | Construction method, device and equipment of early warning event map and storage medium | |
| KR960706138A (en) | SEMANTIC OBJECT MODELING SYSTEM FOR CREATING RELATIONAL DATABASE SCHEMAS | |
| JP2013225319A (en) | Visual multidimensional retrieval | |
| CN109299169B (en) | Data visualization method, system, terminal and computer readable storage medium | |
| CN106897309A (en) | The polymerization and device of a kind of similar word | |
| CN104951560A (en) | Knowledge point structure based searcher | |
| CN110222194A (en) | Data drawing list generation method and relevant apparatus based on natural language processing | |
| KR101803150B1 (en) | Important precedents extraction and sorting method using Big Data | |
| CN108664509A (en) | A kind of method, apparatus and server of extemporaneous inquiry | |
| Martinez-Rico et al. | Can deep learning techniques improve classification performance of vandalism detection in Wikipedia? | |
| CN110990587A (en) | Enterprise relation discovery method and system based on topic model | |
| CN111930824A (en) | Data comprehensive situation display method based on recommendation model | |
| US10042913B2 (en) | Perspective data analysis and management | |
| CN113360654A (en) | Text classification method and device, electronic equipment and readable storage medium | |
| JP2009223809A (en) | Sort condition preparation program, sort condition preparation device, and sort condition preparation method | |
| JPH08305724A (en) | Device for managing design supporting information document | |
| JP6868576B2 (en) | Event presentation system and event presentation device | |
| CN113052544A (en) | Method and device for intelligently adapting workflow according to user behavior and storage medium | |
| CN112015912B (en) | Intelligent index visualization method and device based on knowledge graph | |
| CN112529743A (en) | Contract element extraction method, contract element extraction device, electronic equipment and medium | |
| JP2000293537A (en) | Data analysis support method and device |
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 |