CN111639494A - Case affair relation determining method and system - Google Patents
Case affair relation determining method and system Download PDFInfo
- Publication number
- CN111639494A CN111639494A CN202010312498.0A CN202010312498A CN111639494A CN 111639494 A CN111639494 A CN 111639494A CN 202010312498 A CN202010312498 A CN 202010312498A CN 111639494 A CN111639494 A CN 111639494A
- Authority
- CN
- China
- Prior art keywords
- event
- case
- word segmentation
- determining
- neural network
- 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 56
- 230000011218 segmentation Effects 0.000 claims abstract description 73
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000003062 neural network model Methods 0.000 claims description 37
- 230000015654 memory Effects 0.000 claims description 26
- 238000000605 extraction Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008450 motivation Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Technology Law (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a case affair relation determining method and a case affair relation determining system, wherein the method comprises the steps of collecting a description text of a case, and determining all event types corresponding to the attributes of the case; performing word segmentation processing on the description text to obtain word segmentation results, and extracting entity information in the case from the word segmentation results; extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information; and determining the event relation among all the events in the case based on the event information corresponding to each event. According to the method for the case structure disassembly by taking the event as the core and determining the case affair relation, the case information is fully used, the method can be used for constructing downstream tasks such as event logic chains, meta-event prediction and motivation analysis, and the effects of completing intelligent legal tasks such as related law and law searching and automatic judgment can be further achieved.
Description
Technical Field
The invention relates to the technical field of legal information processing, in particular to a case affair relationship determining method and system.
Background
In the case investigation process, the analysis of the case information is very important. In the prior art, case information is generally analyzed in a structural table form, keyword such as time, case party, location, behavior and the like is used for extracting the case information, a table is constructed, and follow-up tasks such as follow-up case analysis, related method search, automatic judgment and the like are performed in a table searching mode.
However, the method provided in the prior art does not consider the case relationship among a series of events in a case, and splits the events and events under the same case, so that deep analysis such as human motivation analysis and emotion analysis cannot be performed, and a large amount of information is lost when tasks such as related law and law search and automatic judgment are performed.
Therefore, it is urgently needed to provide a case affair relationship determining method and system.
Disclosure of Invention
To overcome the above problems or at least partially solve the above problems, embodiments of the present invention provide a case affairs relationship determining method and system.
In a first aspect, an embodiment of the present invention provides a method for determining a case affair relationship, including:
collecting a description text of a case, and determining all event types corresponding to the attributes of the case;
performing word segmentation processing on the description text to obtain word segmentation results, and extracting entity information in the case from the word segmentation results;
extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information;
and determining the event relation among all the events in the case based on the event information corresponding to each event.
Preferably, the extracting entity information in the case from the word segmentation result specifically includes:
inputting the word segmentation result into a long-short term memory neural network model, and outputting entity information in the case by the long-short term memory neural network model;
the long-short term memory neural network model adopts a feature extractor based on self attention to extract features, and is obtained by training sample words and entity information corresponding to the sample words.
Preferably, the output layer of the long-short term memory neural network model is constructed based on a Softmax function or a conditional random field.
Preferably, the extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information specifically includes:
inputting the word segmentation result into a target neural network model, and outputting event information corresponding to each event in the case by the target neural network model;
the target neural network model is obtained by training events to which sample words belong and event information corresponding to the events to which the sample words belong, and the events to which the sample words belong correspond to all event types and the entity information.
Preferably, the event information includes event trigger, event type and event argument; accordingly, the number of the first and second electrodes,
the inputting the word segmentation result into a target neural network model, and outputting event information corresponding to each event in the case by the target neural network model specifically includes:
the target neural network model is based on a pipeline model, firstly, an event trigger corresponding to each event in the word segmentation result is recognized, then, an event type corresponding to the event trigger is determined, and finally, an event argument corresponding to the event trigger is determined.
Preferably, the target neural network model is a convolutional neural network model and/or a recurrent neural network model.
Preferably, the event information includes event trigger, event type and event argument;
correspondingly, the determining the event relationship among all the events in the case based on the event information corresponding to each event specifically includes:
determining the superior-inferior relation between all events in the case based on the superior-inferior relation of the event types according to the event type corresponding to each event in the case;
and determining the sequential relation among all the events in the case according to the event trigger, the event type and the event argument corresponding to each event in the case.
In a second aspect, an embodiment of the present invention provides a case affairs relationship determining system, including: the system comprises an event type determining module, an entity information extracting module, an event information extracting module and a matter relation determining module. Wherein the content of the first and second substances,
the event type determining module is used for acquiring description texts of cases and determining all event types contained in the cases;
the entity information extraction module is used for carrying out word segmentation processing on the description text to obtain word segmentation results and extracting entity information in the case from the word segmentation results;
the event information extraction module is used for extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information;
and the case relation determining module is used for determining the case relation among all the events in the case based on the event information corresponding to each event.
In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the case affairs relationship determination method according to the first aspect when executing the program.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the case affair relationship determination method according to the first aspect.
The embodiment of the invention provides a case affair relation determining method and a case affair relation determining system, wherein the method comprises the steps of collecting a description text of a case, and determining all event types corresponding to the attributes of the case; performing word segmentation processing on the description text to obtain word segmentation results, and extracting entity information in the case from the word segmentation results; extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information; and determining the event relation among all the events in the case based on the event information corresponding to each event. According to the method for the case structure disassembly by taking the event as the core and determining the case affair relation, the case information is fully used, the method can be used for constructing downstream tasks such as event logic chains, meta-event prediction and motivation analysis, and the effects of completing intelligent legal tasks such as related law and law searching and automatic judgment can be further achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a case affair relationship determining method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a directed acyclic graph formed in the case affairs relationship determination method according to the embodiment of the present invention;
fig. 3 is a schematic structural diagram of a case affairs relationship determining system according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a case affairs relationship determining method, including:
s1, collecting the description text of the case, and determining all event types contained in the case;
s2, performing word segmentation processing on the description text to obtain word segmentation results, and extracting entity information in the case from the word segmentation results;
s3, extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information;
s4, determining the event relation among all the events in the case based on the event information corresponding to each event.
Specifically, in the case affair relationship determining method provided in the embodiment of the present invention, the execution subject is a server, specifically, the execution subject may be a local server, or may be a cloud server, and the local server may be a computer.
Step S1 is first executed, a description text of a case is collected, the case refers to a combination including a plurality of events, an attribute of the case refers to a type of the case, and the case may be an administrative penalty case, a criminal case, or another case requiring determination of a physical relationship between events included inside the case, which is not specifically limited in the embodiment of the present invention. Each event contained in the case is composed of event arguments such as event principal, event occurrence time and event occurrence place and event trigger, wherein the event trigger refers to action related to the event. In the embodiment of the invention, the description text of the case refers to the content obtained by recording event arguments, event triggers and the like of the case in a text mode. After the description text of the case is collected, all event types corresponding to the attribute of the case can be determined through the form of expert discussion, for example, if the attribute of the case is an administrative penalty case, all corresponding event types may include an attack event, a theft event, a fraud event, a penalty event, a fine event, a non-repudiation event, and the like. In the embodiment of the invention, after all event types corresponding to the attributes of the case are determined, all event types can form a set, and the set is an event type set. The upper and lower bit relations of all event types in the event type set can be determined to form a tree diagram. The upper and lower relationships of the event types refer to the inclusion or contained relationship between the event types, for example, the penalty event is a higher concept of a fine event, a non-repudiation event, etc., and the penalty event, the non-repudiation event, etc. is a lower concept of the penalty event, that is, the penalty event includes the fine event, the non-repudiation event, etc.
Then, step 2 is executed, sentence separation processing and word separation processing are carried out on the description text, each sentence content in the description text can contain one or more event types, and event discovery and event argument extraction are carried out by using a Chinese legal event extraction technology; the method comprises the steps of segmenting each sentence of content in a description text by using a Chinese segmentation technology of an added legal dictionary, splitting each sentence of content in the description text into a list of a plurality of words, and enabling all single words to form a segmentation result. And classifying each word to determine entity information in the case. The entity information refers to information such as time, place, people, actions and the like related in the whole case, and the process of determining the entity information in the case is the process of determining the category to which each word belongs.
Then, step S3 is executed to extract event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information in the case. According to all event types, extracting a plurality of events in the word segmentation result by taking the events as units, wherein the event information corresponding to each event comprises event trigger, event types, event arguments and the like. In the embodiment of the present invention, the extracted events may also be numbered, that is, the event information corresponding to each event further includes an event number. In the embodiment of the invention, the event information corresponding to each event can be stored, and the storage mode can be that the event number, the event type, the event trigger and the event argument corresponding to the event are jointly stored. It should be noted that event triggers, events and event numbers are in one-to-one correspondence, that is, one event has only one number, and also has only one event trigger, and different event triggers correspond to different events. The same event type may correspond to different event triggers, i.e. to different events. That is, different events may have the same event type.
And finally, executing step S4, and determining the event relation among all the events in the case according to the event information corresponding to each event in the case determined in step S3. The event relationship may include an upper-lower relationship and a sequential relationship, where the upper-lower relationship refers to an inclusion or contained relationship of an event, and the sequential relationship refers to a conditional relationship and a causal relationship of the event.
In the embodiment of the invention, a Directed Acyclic Graph (DAG) between all events can be constructed according to the affair relationship between all events in the case, so that the affair relationship is more intuitive. For example, if it is determined that the case includes an overload event, an impound event, a payment event, a fine event, and a return event by the method provided in the embodiment of the present invention, a directed acyclic graph is constructed as shown in fig. 2.
The case affair relationship determining method provided by the embodiment of the invention comprises the steps of collecting description texts of cases, and determining all event types corresponding to the attributes of the cases; performing word segmentation processing on the description text to obtain word segmentation results, and extracting entity information in the case from the word segmentation results; extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information; and determining the event relation among all the events in the case based on the event information corresponding to each event. According to the method for the case structure disassembly by taking the event as the core and determining the case affair relation, the case information is fully used, the method can be used for constructing downstream tasks such as event logic chains, meta-event prediction and motivation analysis, and the effects of completing intelligent legal tasks such as related law and law searching and automatic judgment can be further achieved.
On the basis of the above embodiment, the case affair relationship determining method provided in the embodiment of the present invention extracts entity information in the case from the word segmentation result, and specifically includes:
inputting the word segmentation result into a long-short term memory neural network model, and outputting entity information in the case by the long-short term memory neural network model;
the long-short term memory neural network model adopts a feature extractor based on self attention to extract features, and is obtained by training sample words and entity information corresponding to the sample words.
Specifically, in the embodiment of the present invention, when the entity information in the case is extracted from the word segmentation result in step S2, the extraction may be specifically implemented by a Long Short-term memory neural network (LSTM) model, the word segmentation result is input to the LSTM model, the LSTM model performs entity extraction, and the entity information is output. The LSTM model may be combined with a self-attention-based feature extractor (Transformer) to perform feature extraction by the Transformer. The output layer of the LSTM model may be implemented by using a Softmax function, or may also be implemented by using a Conditional Random Field (CRF), which is not specifically limited in the embodiment of the present invention.
The case affair relationship determining method provided by the embodiment of the invention adopts the long-short term memory neural network model and combines the feature extractor based on self-attention and the conditional random field, so that the extraction efficiency of the entity information is higher, and the extracted entity information is more accurate.
On the basis of the foregoing embodiment, the case affair relationship determining method provided in the embodiment of the present invention is a case affair relationship determining method that extracts, from the word segmentation result, event information corresponding to each event in the case based on all event types and the entity information, and specifically includes:
inputting the word segmentation result into a target neural network model, and outputting event information corresponding to each event in the case by the target neural network model;
the target neural network model is obtained by training events to which sample words belong and event information corresponding to the events to which the sample words belong, and the events to which the sample words belong correspond to all event types and the entity information.
Specifically, in the embodiment of the present invention, when step S3 is executed, the target neural network model processes the word segmentation result, and determines event information corresponding to each event. The target Neural network model may be a Convolutional Neural Network (CNN) model or a Recurrent Neural Network (RNN) model, or may be a combination of a CNN model and an RNN model. The embodiment of the invention can also adopt a CNN model or an RNN model based on an attention mechanism, or a combination of the CNN model and the RNN model.
On the basis of the above embodiment, in the case affair relationship determining method provided in the embodiment of the present invention, the event information includes event trigger, event type, and event argument; correspondingly, the inputting the word segmentation result into a target neural network model, and outputting event information corresponding to each event in the case by the target neural network model specifically includes:
the target neural network model is based on a pipeline model, firstly, an event trigger corresponding to each event in the word segmentation result is recognized, then, an event type corresponding to the event trigger is determined, and finally, an event argument corresponding to the event trigger is determined.
Specifically, in the embodiment of the present invention, a Pipeline model (Pipeline) may be introduced into the target neural network model, the event trigger corresponding to each event is identified first, then the event type corresponding to the event trigger is determined, and finally the event argument corresponding to the event trigger is extracted according to the characteristics of the event type to form the structured expression of the event in the case.
On the basis of the above embodiment, in the case affair relationship determining method provided in the embodiment of the present invention, the event information includes event trigger, event type, and event argument;
correspondingly, the determining the event relationship among all the events in the case based on the event information corresponding to each event specifically includes:
determining the superior-inferior relation between all events in the case based on the superior-inferior relation of the event types according to the event type corresponding to each event in the case;
and determining the sequential relation among all the events in the case according to the event trigger, the event type and the event argument corresponding to each event in the case.
Specifically, in the embodiment of the present invention, when step S4 is executed, the upper and lower relationships of each event may be determined by comparing the event type with the event type corresponding to each event in the case and combining the upper and lower relationships of the event type, where the upper and lower relationships of the event type are consistent with the upper and lower relationships of the event. And then comparing event types, event triggers, event arguments such as event time, people, places and the like, and determining the cis-bearing relation among all the events in the case. And obtaining the superior-subordinate relation and the sequential relation among all the events in the case, namely determining the affair relation among all the events in the case.
As shown in fig. 3, on the basis of the above embodiment, an embodiment of the present invention provides a case affairs relationship determining system, including: an event type determination module 31, an entity information extraction module 32, an event information extraction module 33, and a case relationship determination module 34.
The event type determining module 31 is configured to collect description texts of cases, and determine all event types included in the cases;
the entity information extraction module 32 is configured to perform word segmentation processing on the description text to obtain word segmentation results, and extract entity information in the case from the word segmentation results;
the event information extraction module 33 is configured to extract event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information;
the case relation determining module 34 is configured to determine a case relation between all events in the case based on the event information corresponding to each event.
Specifically, the functions of the modules in the case affair relationship determination system provided in the embodiment of the present invention correspond to the operation flows of the steps in the method embodiments one to one, and the implementation effects are also consistent.
As shown in fig. 4, on the basis of the above embodiment, an embodiment of the present invention provides an electronic device, including: a processor (processor)401, a memory (memory)402, a communication Interface (Communications Interface)403, and a communication bus 404; wherein the content of the first and second substances,
the processor 401, the memory 402 and the communication interface 403 complete communication with each other through the communication bus 404. The memory 402 stores program instructions executable by the processor 401, and the processor 401 is configured to call the program instructions in the memory 402 to perform the method provided by the above-mentioned embodiments of the method, for example, including: collecting a description text of a case, and determining all event types corresponding to the attributes of the case; performing word segmentation processing on the description text to obtain word segmentation results, and extracting entity information in the case from the word segmentation results; extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information; and determining the event relation among all the events in the case based on the event information corresponding to each event.
It should be noted that, when being implemented specifically, the electronic device in this embodiment may be a server, a PC, or another device, as long as the structure includes the processor 401, the communication interface 403, the memory 402, and the communication bus 404 shown in fig. 4, where the processor 401, the communication interface 403, and the memory 402 complete mutual communication through the communication bus 404, and the processor 401 may call a logic instruction in the memory 402 to execute the above method. The embodiment does not limit the specific implementation form of the electronic device.
The logic instructions in memory 402 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone article of manufacture. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Further, embodiments of the present invention disclose a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, which when executed by a computer, the computer is capable of performing the methods provided by the above-mentioned method embodiments, for example, comprising: collecting a description text of a case, and determining all event types corresponding to the attributes of the case; performing word segmentation processing on the description text to obtain word segmentation results, and extracting entity information in the case from the word segmentation results; extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information; and determining the event relation among all the events in the case based on the event information corresponding to each event.
On the basis of the foregoing embodiments, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented to perform the transmission method provided by the foregoing embodiments when executed by a processor, and the method includes: collecting a description text of a case, and determining all event types corresponding to the attributes of the case; performing word segmentation processing on the description text to obtain word segmentation results, and extracting entity information in the case from the word segmentation results; extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information; and determining the event relation among all the events in the case based on the event information corresponding to each event.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A case affairs relation determining method is characterized by comprising the following steps:
collecting a description text of a case, and determining all event types corresponding to the attributes of the case;
performing word segmentation processing on the description text to obtain word segmentation results, and extracting entity information in the case from the word segmentation results;
extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information;
and determining the event relation among all the events in the case based on the event information corresponding to each event.
2. A case affairs relationship determination method according to claim 1, wherein the extracting entity information in the case from the word segmentation result specifically includes:
inputting the word segmentation result into a long-short term memory neural network model, and outputting entity information in the case by the long-short term memory neural network model;
the long-short term memory neural network model adopts a feature extractor based on self attention to extract features, and is obtained by training sample words and entity information corresponding to the sample words.
3. A case affairs relationship determination method according to claim 2, wherein an output layer of the long-short term memory neural network model is constructed based on a Softmax function or a conditional random field.
4. The case affairs relationship determining method according to claim 1, wherein the extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information specifically includes:
inputting the word segmentation result into a target neural network model, and outputting event information corresponding to each event in the case by the target neural network model;
the target neural network model is obtained by training events to which sample words belong and event information corresponding to the events to which the sample words belong, and the events to which the sample words belong correspond to all event types and the entity information.
5. A case affairs relationship determination method according to claim 4, wherein the event information includes event trigger, event type and event argument; accordingly, the number of the first and second electrodes,
the inputting the word segmentation result into a target neural network model, and outputting event information corresponding to each event in the case by the target neural network model specifically includes:
the target neural network model is based on a pipeline model, firstly, an event trigger corresponding to each event in the word segmentation result is recognized, then, an event type corresponding to the event trigger is determined, and finally, an event argument corresponding to the event trigger is determined.
6. A case affairs relationship determination method according to claim 4, wherein the target neural network model is specifically a convolutional neural network model and/or a recurrent neural network model.
7. A case affairs relationship determination method according to any one of claims 1-6, wherein the event information includes event trigger, event type and event argument;
correspondingly, the determining the event relationship among all the events in the case based on the event information corresponding to each event specifically includes:
determining the superior-inferior relation between all events in the case based on the superior-inferior relation of the event types according to the event type corresponding to each event in the case;
and determining the sequential relation among all the events in the case according to the event trigger, the event type and the event argument corresponding to each event in the case.
8. A case affairs relationship determination system, comprising:
the event type determining module is used for acquiring description texts of cases and determining all event types contained in the cases;
the entity information extraction module is used for carrying out word segmentation processing on the description text to obtain word segmentation results and extracting entity information in the case from the word segmentation results;
the event information extraction module is used for extracting event information corresponding to each event in the case from the word segmentation result based on all event types and the entity information;
and the case relation determining module is used for determining the case relation among all the events in the case based on the event information corresponding to each event.
9. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the case affairs relationship determination method according to any of claims 1-7 when executing the program.
10. A non-transitory computer readable storage medium, having stored thereon a computer program, characterized in that the computer program, when being executed by a processor, is adapted to carry out the steps of the case affairs relationship determination method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010312498.0A CN111639494A (en) | 2020-04-20 | 2020-04-20 | Case affair relation determining method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010312498.0A CN111639494A (en) | 2020-04-20 | 2020-04-20 | Case affair relation determining method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111639494A true CN111639494A (en) | 2020-09-08 |
Family
ID=72330782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010312498.0A Pending CN111639494A (en) | 2020-04-20 | 2020-04-20 | Case affair relation determining method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111639494A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113626618A (en) * | 2021-10-12 | 2021-11-09 | 深圳前海环融联易信息科技服务有限公司 | Case series connection method and device based on cross-chapter event extraction and related components |
| CN114707004A (en) * | 2022-05-24 | 2022-07-05 | 国网浙江省电力有限公司信息通信分公司 | Method and system for extracting and processing case-affair relation based on image model and language model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130226844A1 (en) * | 2005-12-12 | 2013-08-29 | Qin Zhang | Content Summarizing and Search Method and System Using Thinking System |
| CN110457443A (en) * | 2019-08-12 | 2019-11-15 | 贵州大学 | A kind of criminal offence chain building method based on criminal case |
| CN110738039A (en) * | 2019-09-03 | 2020-01-31 | 平安科技（深圳）有限公司 | Prompting method, device, storage medium and server for case auxiliary information |
| CN110858269A (en) * | 2018-08-09 | 2020-03-03 | 清华大学 | Criminal name prediction method and device |
| CN110969549A (en) * | 2018-09-30 | 2020-04-07 | 北京国双科技有限公司 | Judicial data processing method and system |
-
2020
- 2020-04-20 CN CN202010312498.0A patent/CN111639494A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130226844A1 (en) * | 2005-12-12 | 2013-08-29 | Qin Zhang | Content Summarizing and Search Method and System Using Thinking System |
| CN110858269A (en) * | 2018-08-09 | 2020-03-03 | 清华大学 | Criminal name prediction method and device |
| CN110969549A (en) * | 2018-09-30 | 2020-04-07 | 北京国双科技有限公司 | Judicial data processing method and system |
| CN110457443A (en) * | 2019-08-12 | 2019-11-15 | 贵州大学 | A kind of criminal offence chain building method based on criminal case |
| CN110738039A (en) * | 2019-09-03 | 2020-01-31 | 平安科技（深圳）有限公司 | Prompting method, device, storage medium and server for case auxiliary information |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113626618A (en) * | 2021-10-12 | 2021-11-09 | 深圳前海环融联易信息科技服务有限公司 | Case series connection method and device based on cross-chapter event extraction and related components |
| CN113626618B (en) * | 2021-10-12 | 2022-02-15 | 深圳前海环融联易信息科技服务有限公司 | Case series connection method and device based on cross-chapter event extraction and related components |
| WO2023060634A1 (en) * | 2021-10-12 | 2023-04-20 | 深圳前海环融联易信息科技服务有限公司 | Case concatenation method and apparatus based on cross-chapter event extraction, and related component |
| CN114707004A (en) * | 2022-05-24 | 2022-07-05 | 国网浙江省电力有限公司信息通信分公司 | Method and system for extracting and processing case-affair relation based on image model and language model |
| CN114707004B (en) * | 2022-05-24 | 2022-08-16 | 国网浙江省电力有限公司信息通信分公司 | Method and system for extracting and processing case-affair relation based on image model and language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Enayet et al. | NileTMRG at SemEval-2017 task 8: Determining rumour and veracity support for rumours on Twitter. | |
| CN108073568A (en) | keyword extracting method and device | |
| CN108536681A (en) | Intelligent answer method, apparatus, equipment and storage medium based on sentiment analysis | |
| KR20200007969A (en) | Information processing methods, terminals, and computer storage media | |
| Udanor et al. | Combating the challenges of social media hate speech in a polarized society: A Twitter ego lexalytics approach | |
| JP2021101361A (en) | Method, device, apparatus and storage medium for generating event topics | |
| CN110929520A (en) | Non-named entity object extraction method and device, electronic equipment and storage medium | |
| CN111178701B (en) | Risk control method and device based on feature derivation technology and electronic equipment | |
| CN111581956A (en) | Sensitive information identification method and system based on BERT model and K nearest neighbor | |
| CN111639494A (en) | Case affair relation determining method and system | |
| EP3477575A1 (en) | Computer implemented method and system for detecting a set of relevant communities | |
| CN116340606A (en) | Analysis method, device, storage medium and equipment for major emergency | |
| Suhas Bharadwaj et al. | A novel multimodal hybrid classifier based cyberbullying detection for social media platform | |
| AlAjlan et al. | Machine learning approach for threat detection on social media posts containing Arabic text | |
| CN110069686A (en) | User behavior analysis method, apparatus, computer installation and storage medium | |
| CN115033668B (en) | Story venation construction method and device, electronic equipment and storage medium | |
| Gupta et al. | Real-time sentiment analysis of tweets: A case study of Punjab elections | |
| CN112507214B (en) | User name-based data processing method, device, equipment and medium | |
| CN109597879B (en) | Service behavior relation extraction method and device based on 'citation relation' data | |
| KR20220105792A (en) | AI-based Decision Making Support System utilizing Dynamic Text Sources | |
| CN114117057A (en) | Keyword extraction method of product feedback information and terminal equipment | |
| Laaksonen et al. | From hate speech recognition to happiness indexing: critical issues in datafication of emotion in text mining | |
| Barrows et al. | Sentiment and objectivity in Iranian state-sponsored propaganda on twitter | |
| Sandaka et al. | Sentiment Analysis and Time-series Analysis for the COVID-19 vaccine Tweets | |
| CN112487165A (en) | Question and answer method, device and medium based on keywords |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200908 |