CN112597763A - Method and device for extracting and displaying judicial literature information in association manner and storage medium - Google Patents
Method and device for extracting and displaying judicial literature information in association manner and storage medium Download PDFInfo
- Publication number
- CN112597763A CN112597763A CN202011483150.4A CN202011483150A CN112597763A CN 112597763 A CN112597763 A CN 112597763A CN 202011483150 A CN202011483150 A CN 202011483150A CN 112597763 A CN112597763 A CN 112597763A
- Authority
- CN
- China
- Prior art keywords
- crime
- entity
- fact
- expression
- ith
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000014509 gene expression Effects 0.000 claims description 100
- 238000012545 processing Methods 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000003058 natural language processing Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 210000000056 organ Anatomy 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Technology Law (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of entity recognition in natural language processing, in particular to a method, a device and a storage medium for extracting and displaying judicial literature information in an associated manner. The method comprises the steps of respectively identifying and extracting corresponding entity sets from each criminal fact of the judicial documents by using entity identification rules, displaying the entity sets by using an axis generation rule through a time axis, and realizing the association display between the time axis and the judicial documents by using association rules. The entity identification technology adopted by the invention can accurately acquire the attribute information of the criminal fact, and the entity set is displayed more visually by adopting the time axis. The invention not only ensures the accuracy of information acquisition, simplifies the information acquisition steps, but also assists the case handling personnel to improve the case handling efficiency.
Description
Technical Field
The invention relates to an entity identification technology in the technical field of natural language processing, in particular to a judicial literature information extraction and association display method. In addition, the application also relates to a judicial literature information extraction and association display device and a computer readable storage medium.
Background
The judicial works refer to works with specific structure and certain effectiveness used by public security organs and political institutions such as courts and inspection centers, for example, investigation works made by public security organs (inquiry/inquiry records) and inspection works made by inspection centers (inquiry records).
In order to assist the case handling personnel to visually learn the important elements in the judicial documents and improve the case handling efficiency, firstly, natural language processing technology can be used for extracting information from the documents, and then the information is presented to the case handling personnel through visual presentation patterns to help the case handling personnel to quickly know the case information.
However, in the process of implementing the present invention, the inventors found that the following problems exist in the prior art: the data information in the prosecution opinion book is only the paragraph fragments obtained by extraction, the word level is not specified, the data needs to be further read if the data is directly obtained, and meanwhile, the displayed information obtained by the prior art is not visual enough, and the efficiency of helping the case handling personnel to obtain the information is not high enough. In addition, if the case handling personnel want to quickly locate and match the position in the original document according to the information extracted from the complaint suggestion book, the prior art can not provide help, and the problems cause time and labor waste of the case handling personnel in the case handling process and increase the case handling cost.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide a method, a device and a storage medium for extracting and displaying judicial literature information in an associated manner. The judicial literature information extraction and association display method not only ensures the accuracy of information acquisition, but also simplifies the information acquisition steps. The problem of low accuracy of information acquisition of the conventional case handling personnel is solved, and the case handling cost is reduced.
In order to achieve the above purpose and solve the problems existing in the prior art, the invention adopts the technical scheme that: a judicial literature information extraction and association display method comprises the following steps:
identifying and extracting a corresponding entity set from each crime fact of a judicial document by utilizing an entity identification rule, wherein the entity identification rule is a rule for identifying three entity attributes of time, place and people, the crime fact is a statement paragraph of the crime fact in the judicial document, and the entity set comprises at least one entity attribute;
displaying the entity set by using an axis generation rule, wherein the axis generation rule is a rule used for determining a time axis style, and the time axis style comprises the distribution layout of event frames in the time axis;
the method comprises the steps that association display between a time axis and a judicial essay is achieved through association rules, the association rules are rules used for information linkage between criminal facts and event boxes, and the information linkage is unique and corresponding;
and correspondingly storing the entity set extracted from the crime facts and the incidence relation between the crime facts and the time axis according to the entity attributes and the time axis style of the crime facts in the judicial documents.
The entity identification rule comprises a time expression, a place expression and a figure expression, wherein the time expression is used for identifying and extracting a time entity in the crime fact, the place expression is used for identifying and extracting a place entity in the crime fact, and the figure expression is used for identifying and extracting a figure entity in the crime fact;
the step of identifying and extracting the corresponding entity set from each crime fact of the judicial works by utilizing the entity identification rule comprises the following steps:
matching the time expression, the place expression and the character expression with the ith crime fact respectively, and identifying the time, the place and the character entity attributes of the ith crime fact; wherein i is 1,2, … …, m-1, m; m represents the total number of crime facts in the judicial paperwork;
the time, place, and person entity attributes identifying the ith crime fact are considered as the entity set for the ith crime fact.
The axis generation rule comprises a style expression corresponding to a time axis style;
the method for displaying the time axis of the entity set by using the axis generation rule comprises the following steps:
matching the style expression with each entity set of the crime facts, and generating a time axis with m event boxes according to the total number m of the crime facts in the judicial literature, wherein the content displayed by the event boxes is the entity set corresponding to the crime facts, namely the content displayed by the ith event box is the entity set of the ith crime fact, and i is 1,2, … …, m-1, m;
the association rule comprises a first class of association expression and a second class of association expression, wherein the first class of association expression is used for realizing association display from a criminal fact to an event box, and the second class of association expression is used for realizing association display from the event box to the criminal fact;
the method for realizing the association display between the time axis and the judicial works by utilizing the association rules comprises the following steps:
matching the selected ith crime fact clicked with the first type of associated expression, highlighting the ith crime fact in the judicial literature, and associating the ith event box of the highlighted time axis;
matching the clicked ith event box with the second type of associated expression, highlighting the ith event box in the time axis, and associating the ith criminal fact in the highlighted judicial literature.
A judicial literature information extraction and association display device comprises:
the first processing unit is used for identifying and extracting a corresponding entity set from each crime fact of the judicial documents by utilizing an entity identification rule; displaying the time axis of the entity set by using an axis generation rule; the entity identification rule is a rule used for identifying three entity attributes of time, place and people, the crime fact is a statement paragraph of the crime fact in a judicial literature, the entity set comprises at least one entity attribute, the axis generation rule is a rule used for determining a time axis pattern, and the time axis pattern comprises a distribution layout of event boxes in a time axis;
the second processing unit is used for realizing the association display between the time axis and the judicial documents by utilizing the association rule; the association rule is a rule for information linkage between the criminal fact and the event box, and the information linkage is unique and corresponding;
and the storage unit is used for correspondingly storing the entity set extracted from the crime facts and the incidence relation between the crime facts and the time axis according to the entity attributes and the time axis style of the crime facts in the judicial documents.
The entity identification rule comprises a time expression, a place expression and a person expression; the time expression is used for identifying and extracting time entities in the crime fact, the place expression is used for identifying and extracting place entities in the crime fact, and the figure expression is used for identifying and extracting figure entities in the crime fact;
the first processing unit includes:
the entity identification module is used for respectively matching the time expression, the place expression and the person expression with the ith crime fact and identifying the time, the place and the person entity attributes of the ith crime fact; wherein i is 1,2, … …, m-1, m; m represents the total number of crime facts in the judicial paperwork; the time, place, and person entity attributes identifying the ith crime fact are considered as the entity set for the ith crime fact.
The axis generation rule comprises a style expression corresponding to a time axis style;
the first processing unit further comprises:
the axis generation module is used for matching the style expression with each entity set of the crime facts, and generating a time axis with m event boxes according to the number m of the crime facts, wherein the content displayed by the event boxes is the entity set corresponding to the crime facts, namely the content displayed by the ith event box is the entity set of the ith crime fact; wherein i is 1,2, … …, m-1, m; m represents the total number of crime facts in the judicial paperwork.
The association rule comprises a first class of association expression and a second class of association expression, wherein the first class of association expression is used for realizing association display from a criminal fact to an event box, and the second class of association expression is used for realizing association display from the event box to the criminal fact;
the second processing unit includes:
the 1 st association module is used for matching the selected ith crime fact clicked with a first type of association expression, highlighting the ith crime fact in the judicial literature and associating the ith event box with the highlighted time axis;
and the 2 nd correlation module is used for matching the clicked and selected ith event box with the second type of correlation expression, highlighting the ith event box in the time axis and correlating the ith criminal fact in the highlighted judicial literature.
A computer-readable storage medium having instructions stored therein, which when executed on a computer, cause the computer to perform any of the methods described herein.
The invention has the beneficial effects that: provided are a method, a device and a storage medium for extracting and displaying judicial literature information in an associated manner. The method comprises the following steps: and identifying and extracting corresponding entity sets from each criminal fact of the judicial documents by using the entity identification rules, displaying the entity sets by using the axis generation rules on a time axis, and realizing the association display between the time axis and the judicial documents by using the association rules. The device comprises a first processing unit, a second processing unit and a storage unit. The readable storage medium has stored therein instructions which, when run on a computer, cause the computer to perform any of the methods described herein. Compared with the prior art, the method adopts the entity recognition technology in the field of natural language processing, can more accurately acquire attribute information of crime facts, adopts a time axis to display an entity set for more intuitively and conveniently acquiring information, and more importantly, designs and invents the association display method for enhancing association interaction, can realize positioning association of information.
Drawings
Fig. 1 is a flowchart of a first embodiment of a method for extracting and displaying judicial literature information according to the present application.
Fig. 2 is a diagram showing the contents of crime facts in the judicial literature in the first embodiment of the present application.
Fig. 3 is a schematic diagram illustrating that entity sets are respectively identified and extracted from each crime fact of a judicial literature by using entity identification rules in the first embodiment of the present application.
Fig. 4 is a schematic diagram illustrating a time axis of an entity set by using an axis generation rule in the first embodiment of the present application.
Fig. 5 is a schematic diagram illustrating matching of crime facts with first-class associated expressions in the first embodiment of the present application.
Fig. 6 is a schematic diagram of matching an event box with a second-class associated expression in the first embodiment of the present application.
Fig. 7 is a block diagram of a device for extracting and displaying forensic document information corresponding to the first embodiment in a second embodiment of the present application.
Detailed Description
The judicial works are written according to certain rules. For example, the corresponding document name, organization name and number need to be written at the head of the original document, the text content needs to include the certificate of the house of the criminal suspect and the most important statement of the criminal fact, but when a large amount of criminal facts appear in the document, the conventional extraction method is to perform paragraph-level segmentation, which is difficult to capture the element information in the extraction fact, meanwhile, the conventional display method of directly extracting paragraph segments to generate texts is not intuitive enough, which needs further reading by the clerk, and in addition, if the clerk wants to perform text positioning according to the extracted information, the conventional method appears to be complicated, but these problems are often needed to be solved by the clerk urgently, so the research on the extraction of legal document information and the related display method is very necessary.
Therefore, the application provides a new information extraction and association display method applied to the judicial documents, which is convenient for the case handling personnel to rapidly analyze the electronic files and obtain the case information in the documents, and more importantly, provides the information association positioning query for the case handling personnel and improves the case handling efficiency.
Specifically, as shown in fig. 1, a method for extracting and displaying judicial literature information includes the following steps.
The first step is as follows: and respectively identifying and extracting a corresponding entity set from each crime fact of the judicial documents by utilizing an entity identification rule.
In the present application, an entity identification rule is a rule for identifying three entity attributes of time, place and person, the crime fact is a statement paragraph of crime fact in a judicial literature, and the entity set includes at least one entity attribute.
More specifically, the entity identification rules include a time expression, a place expression, and a people expression.
In this case, the local part of the prosecution comment in the judicial literature is shown in fig. 2. The prosecution opinion is a prosecution document which is proposed by a detection department of a monitoring department, a public security department, a national security department and a detection department of the detection department and requires the prosecution department of the detection department to check and recommend the case at the end of detection according to law, a crime fact part in the prosecution document is shown in fig. 2, a fact statement part can be quickly positioned according to 'finding out through examination', then segmentation is carried out according to paragraphs until 'confirming the fact', and the paragraphs obtained by segmentation constitute the crime fact of the document.
As shown in fig. 3, for the ith crime fact, the time, place and person entity attributes are extracted, which includes the following steps:
matching the time expression, the place expression and the character expression with the ith crime fact respectively, and identifying the time, the place and the character entity attributes of the ith crime fact; wherein i is 1,2, … …, m-1, m; m represents the total number of crime facts in the judicial paperwork;
the time, place and person entity attributes identifying the ith crime fact are taken as the entity set of the ith crime fact, and the entity identification rules are partially exemplified as shown in table 1.
TABLE 1
In table 1, the crime fact is matched with the entity identification rule, first the crime fact is matched with the time expression, and a sign "#" is inserted before and after the time to separate the crime fact and the crime fact, so that the content of the interval is the time of the crime fact; then the crime fact is matched with the place expression, the front position and the rear position of the place are separated by using a symbol "+", and the content of the interval is the place of the crime fact; finally, the criminal fact is matched with the human expression, and since the human attributes in the criminal fact are not unique and may exist in a plurality of numbers, in the extraction process, extraction matching is performed for a plurality of times to generate a plurality of contents separated by the symbol "&", and the separated contents jointly form the character information of the criminal fact.
On one hand, in the technology, label classification can be accurately carried out on each word, and the possibility of what type each word is can be obtained, so that the judgment on the attribute information in the crime fact can be formed, and the extraction error condition can be greatly reduced.
On the other hand, the discriminant model used in the technology is obtained by training on the basis of a large number of prosecution opinion books, has universality, is applicable to the prosecution opinion books of most of crime types, ensures the effective practicability of the method, has high factual basis and ensures the accuracy of identification and extraction.
The second step is that: and displaying the time axis of the entity set by using an axis generation rule.
In the present application, the axis generation rule is a rule for determining a timeline style, and the timeline style includes a distribution layout of event boxes in a timeline.
More specifically, the axis generation rule includes a style expression corresponding to a timeline style.
As shown in fig. 4, the step of performing a time axis display on the entity set by using an axis generation rule includes:
matching the style expression with each entity set of the crime facts, and generating a time axis with m event boxes according to the total number m of the crime facts, wherein the content displayed by the event boxes is the entity set corresponding to the crime facts, namely the content displayed by the ith event box is the entity set of the ith crime facts; wherein i is 1,2, … …, m-1, m; m represents the total number of crime facts in the judicial paperwork.
In the process of matching the pattern expression with the crime facts, firstly, the number of time boxes in the time axis is determined according to the number of the crime facts, then the time boxes are corresponding according to the description sequence of the crime facts, and the corresponding entity set of the crime facts is displayed in each time box.
The third step: and realizing the association display between the time axis and the judicial documents by utilizing association rules.
In the invention, the association rule is a rule for information linkage between the criminal fact and the event box, and the information linkage is unique and corresponding.
More specifically, the association rule includes a first type of association expression and a second type of association expression, the first type of association expression is used for realizing association display from a criminal fact to an event box, and the second type of association expression is used for realizing association display from the event box to the criminal fact.
The method for realizing the association display between the time axis and the judicial works by utilizing the association rules comprises the following steps:
matching the selected ith crime fact clicked with the first type of associated expression, highlighting the ith crime fact in the judicial literature, and associating the ith event box of the highlighted time axis;
matching the clicked ith event box with the second type of associated expression, highlighting the ith event box in the time axis, and associating the ith criminal fact in the highlighted judicial literature.
Firstly, matching the selected ith crime fact by clicking with a first-class associated expression, as shown in fig. 5, selecting a certain crime fact, and associating the highlighted corresponding event box because the entity information in the crime fact is uniquely matched and corresponding to the display content of the event box in the time axis.
Secondly, matching the selected ith event box by clicking with the second type of associated expression, as shown in fig. 6, selecting a certain crime fact, and associating the highlighted corresponding crime fact because the display content of the event box in the time axis is uniquely matched and corresponding to the entity information in the crime fact.
As shown in fig. 7, in a second embodiment of the present application, a device for extracting and associating forensic document information corresponding to the first embodiment is provided, which includes:
the first processing unit is used for identifying and extracting a corresponding entity set from each crime fact of the judicial documents by utilizing an entity identification rule; displaying the time axis of the entity set by using an axis generation rule; the entity identification rule is a rule used for identifying three entity attributes of time, place and people, the crime fact is a statement paragraph of the crime fact in a judicial literature, the entity set comprises at least one entity attribute, the axis generation rule is a rule used for determining a time axis pattern, and the time axis pattern comprises a distribution layout of event boxes in a time axis;
the second processing unit is used for realizing the association display between the time axis and the judicial documents by utilizing the association rule; the association rule is a rule for information linkage between the criminal fact and the event box, and the information linkage is unique and corresponding;
and the storage unit is used for correspondingly storing the entity set extracted from the crime facts and the incidence relation between the crime facts and the time axis according to the entity attributes and the time axis style of the crime facts in the judicial documents.
Optionally, the entity identification rule includes a time expression, a place expression and a person expression; the time expression is used for identifying a time entity in the extracted crime fact, the place expression is used for identifying a place entity in the extracted crime fact, and the person expression is used for identifying a person entity in the extracted crime fact.
The first processing unit includes:
an entity identification module: matching the time expression, the place expression and the character expression with the ith crime fact respectively, and identifying the time, the place and the character entity attributes of the ith crime fact; wherein i is 1,2, … …, m-1, m; m represents the total number of crime facts in the judicial paperwork; the time, place, and person entity attributes identifying the ith crime fact are considered as the entity set for the ith crime fact.
Optionally, the axis generation rule includes a style expression corresponding to a timeline style.
The first processing unit further comprises:
an axis generation module: matching the style expression with each entity set of the crime facts, and generating a time axis with m event boxes according to the number m of the crime facts, wherein the content displayed by the event boxes is the entity set corresponding to the crime facts, namely the content displayed by the ith event box is the entity set of the ith crime facts; wherein i is 1,2, … …, m-1, m; m represents the total number of crime facts in the judicial paperwork.
Optionally, the association rule includes a first type of association expression and a second type of association expression, the first type of association expression is used for implementing association display from a criminal fact to an event box, and the second type of association expression is used for implementing association display from the event box to the criminal fact.
The second processing unit includes:
the 1 st association module: matching the selected ith crime fact clicked with the first type of associated expression, highlighting the ith crime fact in the judicial literature, and associating the ith event box of the highlighted time axis;
the 2 nd association module: matching the clicked ith event box with the second type of associated expression, highlighting the ith event box in the time axis, and associating the ith criminal fact in the highlighted judicial literature.
Furthermore, the present application also provides a computer-readable storage medium having stored therein instructions which, when run on a computer, cause the computer to perform the method steps of any of the preceding first embodiments. The computer-readable storage medium can be any available medium that can be accessed by a computer or a storage device, such as a server, data center, etc., that incorporates one or more available media.
Claims (9)
1. A judicial literature information extraction and association display method is characterized by comprising the following steps:
identifying and extracting a corresponding entity set from each crime fact of a judicial document by utilizing an entity identification rule, wherein the entity identification rule is a rule for identifying three entity attributes of time, place and people, the crime fact is a statement paragraph of the crime fact in the judicial document, and the entity set comprises at least one entity attribute;
displaying the entity set by using an axis generation rule, wherein the axis generation rule is a rule used for determining a time axis style, and the time axis style comprises the distribution layout of event frames in the time axis;
the method comprises the steps that association display between a time axis and a judicial essay is achieved through association rules, the association rules are rules used for information linkage between criminal facts and event boxes, and the information linkage is unique and corresponding;
and correspondingly storing the entity set extracted from the crime facts and the incidence relation between the crime facts and the time axis according to the entity attributes and the time axis style of the crime facts in the judicial documents.
2. The method of claim 1, wherein the entity identification rules include a time expression for identifying a time entity extracted from the crime fact, a location expression for identifying a location entity extracted from the crime fact, and a people expression for identifying a people entity extracted from the crime fact;
the step of identifying and extracting the corresponding entity set from each crime fact of the judicial works by utilizing the entity identification rule comprises the following steps:
matching the time expression, the place expression and the character expression with the ith crime fact respectively, and identifying the time, the place and the character entity attributes of the ith crime fact; wherein i is 1,2, … …, m-1, m; m represents the total number of crime facts in the judicial paperwork;
the time, place, and person entity attributes identifying the ith crime fact are considered as the entity set for the ith crime fact.
3. The method of claim 1, wherein the axis generation rule comprises a style expression corresponding to a timeline style;
the method for displaying the time axis of the entity set by using the axis generation rule comprises the following steps:
matching the style expression with each entity set of the crime facts, and generating a time axis with m event boxes according to the total number m of the crime facts in the judicial literature, wherein the content displayed by the event boxes is the entity set corresponding to the crime facts, namely the content displayed by the ith event box is the entity set of the ith crime facts, and i is 1,2, … …, m-1 and m.
4. The method of claim 1, wherein the association rule comprises a first class of association expressions for implementing an associated presentation from a criminal fact to an event box and a second class of association expressions for implementing an associated presentation from an event box to a criminal fact;
the method for realizing the association display between the time axis and the judicial works by utilizing the association rules comprises the following steps:
matching the selected ith crime fact clicked with the first type of associated expression, highlighting the ith crime fact in the judicial literature, and associating the ith event box of the highlighted time axis;
matching the clicked ith event box with the second type of associated expression, highlighting the ith event box in the time axis, and associating the ith criminal fact in the highlighted judicial literature.
5. A judicial literature information extraction and association display device is characterized by comprising:
the first processing unit is used for identifying and extracting a corresponding entity set from each crime fact of the judicial documents by utilizing an entity identification rule; displaying the time axis of the entity set by using an axis generation rule; the entity identification rule is a rule used for identifying three entity attributes of time, place and people, the crime fact is a statement paragraph of the crime fact in a judicial literature, the entity set comprises at least one entity attribute, the axis generation rule is a rule used for determining a time axis pattern, and the time axis pattern comprises a distribution layout of event boxes in a time axis;
the second processing unit is used for realizing the association display between the time axis and the judicial documents by utilizing the association rule; the association rule is a rule for information linkage between the criminal fact and the event box, and the information linkage is unique and corresponding;
and the storage unit is used for correspondingly storing the entity set extracted from the crime facts and the incidence relation between the crime facts and the time axis according to the entity attributes and the time axis style of the crime facts in the judicial documents.
6. The apparatus of claim 5, wherein the entity identification rules comprise a time expression, a location expression, and a people expression; the time expression is used for identifying and extracting time entities in the crime fact, the place expression is used for identifying and extracting place entities in the crime fact, and the figure expression is used for identifying and extracting figure entities in the crime fact;
the first processing unit includes:
the entity identification module is used for respectively matching the time expression, the place expression and the person expression with the ith crime fact and identifying the time, the place and the person entity attributes of the ith crime fact; wherein i is 1,2, … …, m-1, m; m represents the total number of crime facts in the judicial paperwork; the time, place, and person entity attributes identifying the ith crime fact are considered as the entity set for the ith crime fact.
7. The apparatus of claim 5, wherein the axis generation rule comprises a style expression corresponding to a timeline style;
the first processing unit further comprises:
the axis generation module is used for matching the style expression with each entity set of the crime facts, and generating a time axis with m event boxes according to the number m of the crime facts, wherein the content displayed by the event boxes is the entity set corresponding to the crime facts, namely the content displayed by the ith event box is the entity set of the ith crime fact; wherein i is 1,2, … …, m-1, m; m represents the total number of crime facts in the judicial paperwork.
8. The apparatus of claim 5, wherein the association rule comprises a first class of association expressions for implementing association presentation from a criminal fact to an event box and a second class of association expressions for implementing association presentation from the event box to a criminal fact;
the second processing unit includes:
the 1 st association module is used for matching the selected ith crime fact clicked with a first type of association expression, highlighting the ith crime fact in the judicial literature and associating the ith event box with the highlighted time axis;
and the 2 nd correlation module is used for matching the clicked and selected ith event box with the second type of correlation expression, highlighting the ith event box in the time axis and correlating the ith criminal fact in the highlighted judicial literature.
9. A computer-readable storage medium having stored therein instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011483150.4A CN112597763A (en) | 2020-12-16 | 2020-12-16 | Method and device for extracting and displaying judicial literature information in association manner and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011483150.4A CN112597763A (en) | 2020-12-16 | 2020-12-16 | Method and device for extracting and displaying judicial literature information in association manner and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112597763A true CN112597763A (en) | 2021-04-02 |
Family
ID=75196462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011483150.4A Pending CN112597763A (en) | 2020-12-16 | 2020-12-16 | Method and device for extracting and displaying judicial literature information in association manner and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112597763A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116304035A (en) * | 2023-02-28 | 2023-06-23 | 中国司法大数据研究院有限公司 | Multi-notice multi-crime name relation extraction method and device in complex case |
-
2020
- 2020-12-16 CN CN202011483150.4A patent/CN112597763A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116304035A (en) * | 2023-02-28 | 2023-06-23 | 中国司法大数据研究院有限公司 | Multi-notice multi-crime name relation extraction method and device in complex case |
| CN116304035B (en) * | 2023-02-28 | 2023-11-03 | 中国司法大数据研究院有限公司 | Multi-notice multi-crime name relation extraction method and device in complex case |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Isenberg et al. | vispubdata. org: A metadata collection about IEEE visualization (VIS) publications | |
| US9256798B2 (en) | Document alteration based on native text analysis and OCR | |
| CN110442744A (en) | Extract method, apparatus, electronic equipment and the readable medium of target information in image | |
| CN109933796B (en) | Method and device for extracting key information of bulletin text | |
| CN112800848A (en) | Structured extraction method, device and equipment of information after bill identification | |
| US20220343077A1 (en) | Method for displaying entity-associated information based on electronic book and electronic device | |
| CN111259160B (en) | Knowledge graph construction method, device, equipment and storage medium | |
| CN110909123B (en) | Data extraction method and device, terminal equipment and storage medium | |
| CN110675289A (en) | Method for compiling electronic file catalogue with case criminal review | |
| Fu et al. | Automatic record linkage of individuals and households in historical census data | |
| JP5205028B2 (en) | Handwritten annotation management device and interface | |
| CN110765889A (en) | Legal document feature extraction method, related device and storage medium | |
| Schmøkel et al. | FBAdLibrarian and Pykognition: open science tools for the collection and emotion detection of images in Facebook political ads with computer vision | |
| US11941565B2 (en) | Citation and policy based document classification | |
| CN112597763A (en) | Method and device for extracting and displaying judicial literature information in association manner and storage medium | |
| Khan et al. | Offline pashto characters dataset for Ocr systems | |
| CN112330501A (en) | Document processing method and device, electronic equipment and storage medium | |
| Yurtsever et al. | Figure search by text in large scale digital document collections | |
| US20200019547A1 (en) | Apparatus and method for displaying search results using cognitive pattern recognition in locating documents and information within | |
| Randby et al. | Digital curation and machine learning experimentation in archives | |
| JP5766438B2 (en) | Method and system for click-through function in electronic media | |
| CN112990110B (en) | Method for extracting key information from research report and related equipment | |
| CN113722472B (en) | Technical literature information extraction method, system and storage medium | |
| Akinwumi | Indexing and abstracting services in libraries: A legal perspective | |
| Zhitomirsky-Geffet, Gila Prebor and Isaac Miller | Ontology-based analysis of the large collection of historical Hebrew manuscripts |
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 |