CN109408788A - A kind of text marking method towards judgement document - Google Patents
A kind of text marking method towards judgement document Download PDFInfo
- Publication number
- CN109408788A CN109408788A CN201811170433.6A CN201811170433A CN109408788A CN 109408788 A CN109408788 A CN 109408788A CN 201811170433 A CN201811170433 A CN 201811170433A CN 109408788 A CN109408788 A CN 109408788A
- Authority
- CN
- China
- Prior art keywords
- text
- marked
- data
- page
- administrator
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/169—Annotation, e.g. comment data or footnotes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/131—Fragmentation of text files, e.g. creating reusable text-blocks; Linking to fragments, e.g. using XInclude; Namespaces
Abstract
The text marking method towards judgement document that the invention discloses a kind of, comprising the following steps: segmentation extraction and text segmentation from judgement document's text form the data file to be marked of Excel format；Administrator logs in be imported with data to be marked；Administrator creates ordinary user；Administrator creates project to be marked and distributes data to be marked with for ordinary user；Ordinary user logs in and submits mark；Administrator exports the data after mark.Present invention enhances the management to project participant to be integrated with the distribution of mark task, labeled data acquisition and derived function, be improved the working efficiency of the text marking towards judgement document using the design of input serial number distribution text.
Description
Technical field
The present invention relates to a kind of document mask method towards judgement document, belongs to big data digging technology field.
Background technique
Cost of judicial is reduced, the theme that judicial efficiency is always Chinese justice process of reform is improved.When with big data
How the arrival in generation is acquired the mass data generated in the judicial adjudication using big data technology, analyze, arrange, sorting out,
Made full use of case data information, mining data value, allow information technology be the judicial adjudication and socio-economic development service at
It is worth the important topic of research for one.
In the judicial adjudication, the carrier that judgement document records as law trial procedure, completely reflect party advocate,
The objective composition put to the proof, and legal basis, factual evidence and reasoning process that judgement document's result is formed are elaborated comprehensively.Cut-off
It has had more than 48,000,000 parts of judgement documents and has been included and is published in Chinese judgement document's net in July, 2018.Nowadays big data strategy
The important development strategy in China is had become, China, which starts to implement in full, promotes big data developing activity.At the same time, people's court
Also the construction of wisdom law court is being carried forward vigorously, to make full use of case data information, big data is being allowed to be the judicial adjudication and economic society
Development service.True and law article relationship is the project that law court's artificial intelligence field is well worth doing in research judgement document.One side
The law article that face can recommend case that may be applicable in for judge, improves the working efficiency of judge.The recommendation of another aspect law article can be helped
It helps party to understand the lawsuit result and related law article of similar case, forms optimal lawsuit strategy, save legal advice and tell
The cost disputed.And due to the particularity of the research field, in academia there is no relevant public data collection, need to prepare a large amount of
Artificial labeled data collection.Traditional document mask method there are problems that being difficult to managing and count, the present invention be exactly be solution
This problem and generate.The present invention is not only that the related works such as law article recommendation provide data collection, but also are convenient for pipe
Reason and statistical data collection.
Document mask method towards judgement document exists for the value dimension of the correlative studys work such as law article recommendation, a side
Document mask method of the face towards judgement document can be recommended to provide data set for law article, be conducive to law article and recommend correlative study work
The expansion of work.On the one hand compared with traditional document mark, the document mask method towards judgement document of this paper can more section
Geo-statistic and management data are learned, a large amount of time and efforts is saved.
Summary of the invention
The present invention is a kind of text marking method towards judgement document, provides a kind of side of judgement document's Text Pretreatment
Method, including to extraction and text segmentation in judgement document's text, data to be marked are imported, and allocation of items to be marked, user logs in
It is marked with submitting, the data after export mark.
This method such as can recommend to provide a large amount of text marking data set at the research work for law article, and to obtain data set into
The relevant statistics of row and management, save plenty of time and energy.
1. a kind of text marking method towards judgement document, it is characterised in that comprise the steps of:
Step (1) is segmented extraction and text segmentation from judgement document's text, forms the data to be marked text of Excel format
Part；
Step (2) is logged in be imported with data to be marked；
Step (3) creates ordinary user；
Step (4) creates project to be marked and distributes data to be marked with for ordinary user；
Step (5) logs in and submits mark；
Step (6) is logged in be exported with the data after mark；
2. a kind of text marking method towards judgement document according to claim 1, it is characterised in that step (1)
In from judgement document's text segmentation extract and text segmentation, formed Excel format data file to be marked.Specific sub-step
Include:
Step (1.1) document structuring；
Step (1.2) extracts the fact that document section and drawn law article list；
Step (1.3) establishes document fact collection；
Step (1.4) establishes the reference positive collected works of law article；
Step (1.5) creates document and marks table.
3. a kind of text marking method towards judgement document according to claim 1, it is characterised in that step (2)
Middle login is imported with data to be marked.Specifically sub-step includes:
Step (2.1) opens login page, is logged in using administrator's account, into text marking system；
Step (2.2), which enters, imports the Excel page；
The data file to be marked for the Excel format that the needs that step (2.3) selection locally saves import, is imported.
4. a kind of text marking method towards judgement document according to claim 1, it is characterised in that step (3)
Middle creation ordinary user.Specifically sub-step includes:
Step (3.1) is when administrator's account logs in, into checking User Page；
Step (3.2) creates ordinary user, and the username and password of the user is arranged.
5. a kind of text marking method towards judgement document according to claim 1, it is characterised in that step (4)
Middle creation project to be marked distributes data to be marked with for ordinary user.Specifically sub-step includes:
Step (4.1) is when administrator's account logs in, into checking item page；
Step (4.2) creates new projects, and project name is arranged；
The task that step (43) enters the project distributes interface；
Step (4.4) selects to participate in the user of this subtask, distributes data to be marked for these users.
6. a kind of text marking method towards judgement document according to claim 1, it is characterised in that step (5)
Middle login is marked with submission.Specifically sub-step includes:
Step (5.1) opens login page, is logged in using ordinary user's account, into text marking system；
Step (5.2) is according to the project name of distribution, into the text list page of the project；
Whether step (5.3) selects each fact related to law article according to text title into the mark page, submits
Mark operates, until all text markings finish into the mark page of next chapter text before repeating.
7. a kind of text marking method towards judgement document according to claim 1, it is characterised in that step (6)
Middle login is exported with the data after mark.Specifically sub-step includes:
Step (6.1) opens login page, is logged in using administrator's account, into text marking system；
Step (6.2) is according to project name, and into the project judging result page, the law article studied as needed enters
Export results page；
Step (6.3) preview export as a result, by result export as Excel formatted file and download be saved in local.
Compared with traditional artificial mark Excel technology, remarkable advantage is the present invention: using Excel leading-in technique, will count
According to being saved in database, the safety of data is improved；Using administrator creation user, the design that can be just marked after login,
It avoids and Excel data file is issued to personal situation, reduce the risk of judgement document's diffusion, while strengthening to project
The management of participant；Using the design of input serial number distribution text, the efficiency that text need to be marked to user's distribution is improved；It keeps away
The case where conventional method need to open each Excel file and insert 0,1 inefficiency is exempted from, it is only necessary to which clicking mouse can be completed
The time that traditional artificial mask method needs to expend is greatly saved in mark；It is led using according to law article set is associated true
It designs out, facilitates subsequent research.
Detailed description of the invention
A kind of text marking method flow diagram towards judgement document of Fig. 1
The mark table example diagram of Fig. 2 Excel format
Four literary name section hum patterns such as document table in Fig. 3 database
Four literary name section hum patterns such as user's table in Fig. 4 database
Specific embodiment
It is right below in conjunction with the accompanying drawings and the specific embodiments to be more clear the object, technical solutions and advantages of the present invention
The present invention is described in detail.
It is an object of the invention to solve the problems, such as the text marking of judgement document, a kind of text towards judgement document is proposed
Mask method.It using Excel leading-in technique, stores data into database, improves the safety of data；Using administrator
User is created, the design that can just mark after login avoids and Excel data file is issued to personal situation, reduces judge
The risk of document diffusion, while strengthening the management to project participant；Using the design of input serial number distribution text, promoted
The efficiency of text need to be marked to user's distribution；Each Excel file need to be opened and insert 0,1 low efficiency by avoiding conventional method
Under situation, it is only necessary to clicking mouse can be completed mark, and the time that traditional artificial mask method needs to expend is greatly saved；
It is designed using true export is associated according to law article set, facilitates subsequent research.The present invention mainly includes in short
Following steps:
Step (1) is segmented extraction and text segmentation from judgement document's text, forms the data to be marked text of Excel format
Part；
Step (2) is logged in be imported with data to be marked；
Step (3) creates ordinary user；
Step (4) creates project to be marked and distributes data to be marked with for ordinary user；
Step (5) logs in and submits mark；
Step (6) is logged in be exported with the data after mark；
The detailed operation process of a kind of above-mentioned text marking method towards judgement document is as shown in Figure 1.It here will be to upper
Step is stated to be described in detail.
1. segmentation extraction and text segmentation, form the data file to be marked of Excel format first from judgement document.Tool
Body step is
Step (1.1) document structuring.Most of original judgement document's file is all the formats such as doc, docx, rtf
Text-only file, we directly can not therefrom obtain information, therefore we define one according to the writing rules of judgement document
Template finally stores mould using xml from being extracted in corresponding text filling template in document using information extraction according to template
Plate.According to case property, judicial procedure by judgement document be divided into the civil first sentence, civil second trial, the criminal first sentence, criminal second trial,
The administrative first sentence, administrative second trial, and formulated corresponding XML format template for each type, all XML format templates be all by
Document cutting is " text is first ", " party ", " court document ", " case basic condition ", " umpire analysis process ", " judgement is tied
Fruit ", " literary tail " seven logical segments, the difference of the XML template of different case types are that the subsegment in each logic paragraph is fallen not
Same, item of information difference.
Step (1.2) extracts the fact that document section and drawn law article list.We " find out thing from the document of xml format
Real section " node obtains the fact that document text, obtains the paperwork from " law grouping redundancy " node and quotes law article name list.?
When practical document writing, there may be various clerical errors for law article title, and therefore, we also need to carry out the law article title of acquisition
Standardization obtains the list of standard law article.
Step (13) establishes document fact collection.The fact that obtain from xml document node section usually contains a big Duan Wenben,
Therefore, we use "；." true text is cut, filter out space and ineffective law, rule, etc. sheet.Obtain true collection corresponding to the paperwork.
Step (1.4) establishes the reference positive collected works of law article.We remove law article number according to the law article title in standard law article list
According to law article text is inquired in library, the reference positive collected works of law article are established.
Step (1.5) creates document and marks table.After obtaining document fact collection and the reference positive collected works of law article, we are with the fact
For row, law article text is column, creates the mark table of Excel format, concrete form is as shown in Figure 2:
2. the data file for the Excel format for needing first to form step 1 in step 2 imports for subsequent mark
Into database.It comprises the concrete steps that:
Step (2.1) opens login page, input administrator's account title in user name text box, in cryptogram frame
Password is inputted, " login " button is clicked, into text marking system；
Step (2.2) the click upper right corner " I ", there is combobox, click " importing Excel ", into Excel pages of importing
Face；
Step (2.3) clicks " select file ", opens Windows file selection window, selects local preservation Excel format
Data file to be marked, can with multiselect, click determine, close, back page, click " starting to import " button, these
File can be uploaded on server, be parsed one by one, the data in extraction unit lattice, and be saved in the database on server
In.These data can be saved in four tables in database, these tables include: document table, law article table, document-law article table,
True table, field is as shown in Figure 3 in specific tables of data.After all files all import, server can return to prompt information
Onto the page, it is seen that successful information is shown, then shows to import successfully.
3. needing for each one account of personnel assignment for participating in mark project.Specific steps include:
Step (3.1) the click upper right corner " I ", there is combobox, clicks " checking user ", click to enter and check user
The page；
Step (3.2) clicks " creating new user " button, will pop up window, defeated in the user name text box of pop-up window
Enter the user name of user to be created, output will create the password of user in cryptogram frame, click the Create button, then input
Data can be saved in user's table of database, and field is as shown in Figure 4 in specific tables of data.Meeting auto-returned is checked after success
User Page, while user list can refresh, and show the user created.If certain ordinary user forgets Password, can also modify
The password of the user inputs the password to be modified in user's row right Text Entry, clicks " Modify password " button, mentions
It is successfully modified to show that successful information then shows.
4. in view of different emphasis may be carried out by different people or be needed to study to follow-up study, so mark task answers root
It according to item dividing, and is each allocation of items personnel, the document that need to be marked for each personnel assignment.Specific steps include:
Step (4.1) the click upper right corner " I ", there is combobox, clicks " checking project ", click to enter the project of checking
The page；
Step (4.2) clicks " creation new projects " button, will pop up window, in the project name text box of pop-up window
The project name to be created is inputted, the Create button is clicked, then the data inputted can be saved in the project table of database, specifically
Tables of data in field it is as shown in Figure 4；
Item page is checked in step (4.3) return, and list can refresh, and shows the project created, is clicked and " is carried out task point
With " button, into task assignment page；
Step (4.4) selects to participate in the user of this subtask, chooses " whether participating in project " radio box, plan of distribution column
In will appear two Text Entries, in " begin " text box filling import Excel data file start serial number, at " end "
Filling imports Excel end of data file serial number in text box, clicks confirmation distribution, then the data inputted can be saved in database
Task list in, while initializing judgement table, will indicate that the field value of connection is set as -1 in judgement table, expression does not start also to sentence
Disconnected, field is as shown in Figure 4 in specific tables of data.After being assigned, the bulleted list page can be returned to.If after being assigned,
Additional personnel are also needed, in the bulleted list page, clicks and needs on the right side of additional project " distribution of modification task " button, into appointing
The business distribution modification page, distributes similar operations with task, and personnel are selected in lists of persons to be allocated, and input document starts and ties
Beam serial number clicks confirmation distribution.
5. after administrator distributes task to ordinary user, ordinary user can start to be labeled.Specific step
Suddenly include:
Step (5.1) opens login page, and ordinary user's account title, cryptogram frame are inputted in user name text box
Middle input password clicks " login " button, and into the bulleted list page, which can show all items column being assigned
Table；
Step (5.2) clicks the project name to be marked, and into the text list page, which can show assigned institute
There is text list；
Step (5.3) clicks text title, and into the mark page, for the page with each fact for main sequence, law article is order
To be arranged.Each top of form is the content of each fact, and inside table is the essential information for quoting law article.Whether phase
Guan Liezhong is defaulted as uncorrelated.After judgement, if thinking, the fact is related to the law article, clicks " correlation ", all facts
After judgement, bottom " submission " button is clicked, then judgement table can be inquired in the database and update expression connection
Field value, uncorrelated to be set as 0, correlation is set as 1, and returns success in pop-up window, clicks " next chapter " button, can be into
Enter the mark page of next chapter text, is operated before repeating, until all text markings finish.
6. administrator can export the data after mark after ordinary user marks.Specific steps include:
Step (6.1) opens login page, input administrator's account title in user name text box, in cryptogram frame
Password is inputted, " login " button is clicked, into checking item page；
Step (6.2) clicks " checking that task is distributed " button, into the judging result page, it can be seen that participate in this purpose
Whether ordinary user's list and the user judge the information terminated, if being shown as "Yes", click " exporting result according to law article "
Button, into export results page；
Step (63) exports in results page, and main part can list all users in the project and think existed facts and its
Associated law article, and arranged according to how much sequences of incidence number.Selection needs the law article studied, " pre- after clicking the entry
Look at " button, result preview page can be entered, which can show all true lists associated with the law article, click " export
Excel " button, will pop up Windows file download window, click " downloading ", can be literary by Excel format that true list is formed
Part is saved in local.
A kind of text marking method towards judgement document implemented according to the present invention is carried out by reference to attached drawing above
Detailed description.The present invention has the advantage that storing data into database using Excel leading-in technique, number is improved
According to safety；User is created using administrator, the design that can just mark after login avoids and issues Excel data file
Personal situation, reduces the risk of judgement document's diffusion, while strengthening the management to project participant；Using input sequence
The design of number distribution text, the efficiency of text need to be marked to user's distribution by improving；Avoid conventional method need to open it is each
The case where Excel file and 0,1 inefficiency of filling, it is only necessary to which clicking mouse can be completed mark, and traditional people is greatly saved
Work mask method needs the time expended；It is designed using true export is associated according to law article set, facilitates subsequent grind
Study carefully.
It needs to define, the invention is not limited to specific configuration described above and shown in figure and processing.Also,
For brevity, the detailed description to known method technology is omitted here.Current embodiment is all counted as in all respects
It is exemplary rather than limited, the scope of the present invention is by appended claims rather than foregoing description defines, also, falls into power
Whole changes in the range of meaning and equivalent that benefit requires are to all be included among the scope of the present invention.
Claims (7)
1. a kind of text marking method towards judgement document, it is characterised in that comprise the steps of:
Step (1) is segmented extraction and text segmentation from judgement document's text, forms the data file to be marked of Excel format；
Step (2) administrator logs in be imported with data to be marked；
Step (3) administrator creates ordinary user；
Step (4) administrator creates project to be marked and distributes data to be marked with for ordinary user；
Step (5) ordinary user logs in and submits mark；
Step (6) administrator exports the data after mark.
2. a kind of text marking method towards judgement document according to claim 1, it is characterised in that in step (1) from
Segmentation extraction and text segmentation, form the data file to be marked of Excel format in judgement document's text.Specific sub-step packet
It includes:
Step (1.1) document structuring；
Step (1.2) extracts the fact that document section and drawn law article list；
Step (1.3) establishes document fact collection；
Step (1.4) establishes the reference positive collected works of law article；
Step (1.5) creates document and marks table.
3. a kind of text marking method towards judgement document according to claim 1, it is characterised in that pipe in step (2)
Reason person logs in be imported with data to be marked.Specifically sub-step includes:
Step (2.1) opens login page, is logged in using administrator's account, into text marking system；
Step (2.2), which enters, imports the Excel page；
The data file to be marked for the Excel format that the needs that step (2.3) selection locally saves import, is imported.
4. a kind of text marking method towards judgement document according to claim 1, it is characterised in that pipe in step (3)
Reason person creates ordinary user.Specifically sub-step includes:
Step (3.1) is when administrator's account logs in, into checking User Page；
Step (3.2) creates ordinary user, and the username and password of the user is arranged.
5. a kind of text marking method towards judgement document according to claim 1, it is characterised in that pipe in step (4)
Reason person creates project to be marked and distributes data to be marked with for ordinary user.Specifically sub-step includes:
Step (4.1) is when administrator's account logs in, into checking item page:
Step (4.2) creates new projects, and project name is arranged；
The task that step (4.3) enters the project distributes interface；
Step (4.4) selects to participate in the user of this subtask, distributes data to be marked for these users.
6. a kind of text marking method towards judgement document according to claim 1, it is characterised in that general in step (5)
General family logs in and submits mark.Specifically sub-step includes:
Step (5.1) opens login page, is logged in using ordinary user's account, into text marking system；
Step (5.2) is according to the project name of distribution, into the text list page of the project；
Whether step (5.3) selects each fact related to law article according to text title into the mark page, submits mark,
Into the mark page of next chapter text, operated before repeating, until all text markings finish.
7. a kind of text marking method towards judgement document according to claim 1, it is characterised in that pipe in step (6)
Reason person exports the data after mark.Specifically sub-step includes:
Step (6.1) opens login page, is logged in using administrator's account, into text marking system；
Step (6.2) is according to project name, into the project judging result page, the law article studied as needed, into export
Results page；
Step (6.3) preview export as a result, by result export as Excel formatted file and download be saved in local.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811170433.6A CN109408788A (en) | 2018-09-26 | 2018-09-26 | A kind of text marking method towards judgement document |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811170433.6A CN109408788A (en) | 2018-09-26 | 2018-09-26 | A kind of text marking method towards judgement document |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109408788A true CN109408788A (en) | 2019-03-01 |
Family
ID=65466865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811170433.6A Pending CN109408788A (en) | 2018-09-26 | 2018-09-26 | A kind of text marking method towards judgement document |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109408788A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110096480A (en) * | 2019-03-28 | 2019-08-06 | 厦门快商通信息咨询有限公司 | A kind of text marking system, method and storage medium |
| CN110853717A (en) * | 2019-10-16 | 2020-02-28 | 云知声智能科技股份有限公司 | Method and device for controlling associated defect items by document fields |
| CN111178021A (en) * | 2019-11-29 | 2020-05-19 | 厦门快商通科技股份有限公司 | Project alignment marking tool creating method and system |
| CN113506075A (en) * | 2021-06-01 | 2021-10-15 | 大箴(杭州)科技有限公司 | Data labeling method and device, storage medium and computer equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040261016A1 (en) * | 2003-06-20 | 2004-12-23 | Miavia, Inc. | System and method for associating structured and manually selected annotations with electronic document contents |
| CN106156025A (en) * | 2015-03-25 | 2016-11-23 | 阿里巴巴集团控股有限公司 | The management method of a kind of data mark and device |
| CN107273492A (en) * | 2017-06-15 | 2017-10-20 | 复旦大学 | A kind of exchange method based on mass-rent platform processes image labeling task |
| CN107632968A (en) * | 2017-05-22 | 2018-01-26 | 南京大学 | A kind of construction method of chain of evidence relational model towards judgement document |
-
2018
- 2018-09-26 CN CN201811170433.6A patent/CN109408788A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040261016A1 (en) * | 2003-06-20 | 2004-12-23 | Miavia, Inc. | System and method for associating structured and manually selected annotations with electronic document contents |
| CN106156025A (en) * | 2015-03-25 | 2016-11-23 | 阿里巴巴集团控股有限公司 | The management method of a kind of data mark and device |
| CN107632968A (en) * | 2017-05-22 | 2018-01-26 | 南京大学 | A kind of construction method of chain of evidence relational model towards judgement document |
| CN107273492A (en) * | 2017-06-15 | 2017-10-20 | 复旦大学 | A kind of exchange method based on mass-rent platform processes image labeling task |
Non-Patent Citations (1)
| Title |
|---|
| 聂震云: "基于众包的数据标注系统", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110096480A (en) * | 2019-03-28 | 2019-08-06 | 厦门快商通信息咨询有限公司 | A kind of text marking system, method and storage medium |
| CN110853717A (en) * | 2019-10-16 | 2020-02-28 | 云知声智能科技股份有限公司 | Method and device for controlling associated defect items by document fields |
| CN110853717B (en) * | 2019-10-16 | 2022-06-17 | 云知声智能科技股份有限公司 | Method and device for controlling associated defect items by document fields |
| CN111178021A (en) * | 2019-11-29 | 2020-05-19 | 厦门快商通科技股份有限公司 | Project alignment marking tool creating method and system |
| CN113506075A (en) * | 2021-06-01 | 2021-10-15 | 大箴(杭州)科技有限公司 | Data labeling method and device, storage medium and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109408788A (en) | A kind of text marking method towards judgement document | |
| WO2018218708A1 (en) | Deep-learning-based public opinion hotspot category classification method | |
| CN111475513B (en) | Form generation method and device, electronic equipment and medium | |
| CN111767247A (en) | File specification and synchronous forming control platform for real-time supervision of engineering data | |
| US6374270B1 (en) | Corporate disclosure and repository system utilizing inference synthesis as applied to a database | |
| CN104572615A (en) | Method and system for on-line case investigation processing | |
| CN102496083B (en) | Credit rating report manuscript manufacturing method | |
| CN112651218A (en) | Automatic generation method and management method of bidding document, medium and computer | |
| CN107679977A (en) | A kind of tax administration platform and implementation method based on semantic analysis | |
| CN113064992A (en) | Complaint work order structured processing method, device, equipment and storage medium | |
| Wang et al. | Measuring technology complementarity between enterprises with an hLDA topic model | |
| CN107301593A (en) | A kind of financial information system | |
| CN110544035A (en) | internal control detection method, system and computer readable storage medium | |
| Jiang et al. | Research on BIM-based Construction Domain Text Information Management. | |
| CN107798137A (en) | A kind of multi-source heterogeneous data fusion architecture system based on additive models | |
| Wellman | How to use SAS to study egocentric networks | |
| CN112258061A (en) | Intelligent risk analysis early warning system and early warning method for whole process of project | |
| CN115438995B (en) | Business processing method and equipment for clothing customization enterprise based on knowledge graph | |
| CN108897763A (en) | A kind of block chain data conversion system | |
| CN115759562A (en) | Logic relation and construction period calculation algorithm of preventive maintenance work order for overhaul of nuclear power plant | |
| CN113064924A (en) | Nuclear power big data experience retrieval and pushing method | |
| Garigliotti et al. | Do bridges dream of water pollutants? Towards DreamsKG, a knowledge graph to make digital access for sustainable environmental assessment come true | |
| CN112418600A (en) | Enterprise policy scoring method and system based on index set | |
| CN110928990A (en) | Method special for recommending standing book data of power equipment based on user portrait | |
| Elias | Using a deductive approach in validating a measurement model |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190301 |
|
| WD01 | Invention patent application deemed withdrawn after publication |